From 92a78f611e77e2b5108bbaf980535f64e553616f Mon Sep 17 00:00:00 2001 From: "James R. Barlow" Date: Thu, 17 Apr 2025 02:10:40 -0700 Subject: [PATCH 1/5] rst -> md migration in progress --- docs/batch.md | 248 +++++++++++++++++++++++++ docs/batch.rst | 228 ----------------------- docs/conf.py | 5 +- docs/contributing.md | 72 ++++++++ docs/contributing.rst | 77 -------- docs/cookbook.md | 404 +++++++++++++++++++++++++++++++++++++++++ docs/cookbook.rst | 410 ------------------------------------------ docs/docker.md | 245 +++++++++++++++++++++++++ docs/docker.rst | 254 -------------------------- pyproject.toml | 7 +- uv.lock | 95 ++++++++-- 11 files changed, 1059 insertions(+), 986 deletions(-) create mode 100644 docs/batch.md delete mode 100644 docs/batch.rst create mode 100644 docs/contributing.md delete mode 100644 docs/contributing.rst create mode 100644 docs/cookbook.md delete mode 100644 docs/cookbook.rst create mode 100644 docs/docker.md delete mode 100644 docs/docker.rst diff --git a/docs/batch.md b/docs/batch.md new file mode 100644 index 00000000..798e61d8 --- /dev/null +++ b/docs/batch.md @@ -0,0 +1,248 @@ +% SPDX-FileCopyrightText: 2022 James R. Barlow +% SPDX-License-Identifier: CC-BY-SA-4.0 + +Batch processing +================ + +This article provides information about running OCRmyPDF on multiple +files or configuring it as a service triggered by file system events. + +Batch jobs +---------- + +Consider using the excellent [GNU +Parallel](https://www.gnu.org/software/parallel/) to apply OCRmyPDF to +multiple files at once. + +Both `parallel` and `ocrmypdf` will try to use all available processors. +To maximize parallelism without overloading your system with processes, +consider using `parallel -j 2` to limit parallel to running two jobs at +once. + +This command will run `ocrmypdf` on all files named `*.pdf` in the +current directory and write them to the previously created `output/` +folder. It will not search subdirectories. + +The `--tag` argument tells parallel to print the filename as a prefix +whenever a message is printed, so that one can trace any errors to the +file that produced them. + +:::{code} bash +parallel --tag -j 2 ocrmypdf '{}' 'output/{}' ::: *.pdf +::: + +OCRmyPDF automatically repairs PDFs before parsing and gathering +information from them. + +Directory trees +--------------- + +This will walk through a directory tree and run OCR on all files in +place, and printing each filename in between runs: + +:::{code} bash +find . -name '*.pdf' -printf '%p\n' -exec ocrmypdf '{}' '{}' \; +::: + +This only runs one `ocrmypdf` process at a time. This variation uses +`find` to create a directory list and `parallel` to parallelize runs of +`ocrmypdf`, again updating files in place. + +:::{code} bash +find . -name '*.pdf' | parallel --tag -j 2 ocrmypdf '{}' '{}' +::: + +In a Windows batch file, use + +:::{code} bat +for /r %%f in (*.pdf) do ocrmypdf %%f %%f +::: + +With a Docker container, you will need to stream through standard input +and output: + +:::{code} bash +find . -name '*.pdf' -print0 | xargs -0 | while read pdf; do + pdfout=$(mktemp) + docker run --rm -i jbarlow83/ocrmypdf - - <$pdf >$pdfout && cp $pdfout $pdf +done +::: + +### Sample script + +This user contributed script also provides an example of batch +processing. + +:::{literalinclude} ../misc/batch.py +--- +caption: misc/batch.py +--- +::: + +### Synology DiskStations + +Synology DiskStations (Network Attached Storage devices) can run the +Docker image of OCRmyPDF if the Synology [Docker +package](https://www.synology.com/en-global/dsm/packages/Docker) is +installed. Attached is a script to address particular quirks of using +OCRmyPDF on one of these devices. + +At the time this script was written, it only worked for x86-based +Synology products. It is not known if it will work on ARM-based Synology +products. Further adjustments might be needed to deal with the +Synology\'s relatively limited CPU and RAM. + +:::{literalinclude} ../misc/synology.py +--- +caption: misc/synology.py - Sample script for Synology DiskStations +--- +::: + +### Huge batch jobs + +If you have thousands of files to work with, contact the author. +Consulting work related to OCRmyPDF helps fund this open source project +and all inquiries are appreciated. + +Hot (watched) folders +--------------------- + +### Watched folders with watcher.py + +OCRmyPDF has a folder watcher called watcher.py, which is currently +included in source distributions but not part of the main program. It +may be used natively or may run in a Docker container. Native instances +tend to give better performance. watcher.py works on all platforms. + +Users may need to customize the script to meet their requirements. + +:::{code} bash +pip3 install ocrmypdf[watcher] + +env OCR_INPUT_DIRECTORY=/mnt/input-pdfs \ + OCR_OUTPUT_DIRECTORY=/mnt/output-pdfs \ + OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1 \ + python3 watcher.py +::: + +:::{list-table} watcher.py environment variables +--- +header-rows: 1 +--- + +* - Environment variable + - Description +* - OCR\_INPUT\_DIRECTORY + - Set input directory to monitor (recursive) +* - OCR\_OUTPUT\_DIRECTORY + - Set output directory (should not be under input) +* - OCR\_ARCHIVE\_DIRECTORY + - Set archive directory for processed originals (should not be under input, requires `OCR_ON_SUCCESS_ARCHIVE` to be set) +* - OCR\_ON\_SUCCESS\_DELETE + - This will move the processed original file to `OCR_ARCHIVE_DIRECTORY` if the exit code is 0 (OK). Note that `OCR_ON_SUCCESS_DELETE` takes precedence over this option, i.e. if both options are set, the input file will be deleted. +* - OCR\_OUTPUT\_DIRECTORY\_YEAR\_MONTH + - This will place files in the output in `{output}/{year}/{month}/{filename}` +* - OCR\_DESKEW + - Apply deskew to crooked input PDFs +* - OCR\_JSON\_SETTINGS + - A JSON string specifying any other arguments for `ocrmypdf.ocr`, e.g. `'OCR_JSON_SETTINGS={"rotate_pages": true, "optimize": "3"}'`. +* - OCR\_POLL\_NEW\_FILE\_SECONDS + - Polling interval +* - OCR\_LOGLEVEL + - Level of log messages t +::: + +One could configure a networked scanner or scanning computer to drop +files in the watched folder. + +### Watched folders with Docker + +The watcher service is included in the OCRmyPDF Docker image. To run it: + +:::{code} bash +docker run \ + --volume :/input \ + --volume :/output \ + --volume :/processed \ + --env OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1 \ + --env OCR_ON_SUCCESS_ARCHIVE=1 \ + --env OCR_DESKEW=1 \ + --env PYTHONUNBUFFERED=1 \ + --interactive --tty --entrypoint python3 \ + jbarlow83/ocrmypdf \ + watcher.py +::: + +This service will watch for a file that matches `/input/\*.pdf`, convert +it to a OCRed PDF in `/output/`, and move the processed original to +`/processed`. The parameters to this image are: + +:::{list-table} Watcher Docker Parameters +:header-rows: 1 + +* - Parameter + - Description +* - `--volume :/input` + - Files placed in this location will be OCRed +* - `--volume :/output` + - This is where OCRed files will be stored +* - `--volume :/processed` + - Archive processed originals here +* - `--env OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1` + - Define environment variable `OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1` to place files in the output in `{output}/{year}/{month}/{filename}` +* - `--env OCR_ON_SUCCESS_ARCHIVE=1` + - Define environment variable `OCR_ON_SUCCESS_ARCHIVE` to move processed originals +* - `--env OCR_DESKEW=1` + - Define environment variable `OCR_DESKEW` to apply deskew to crooked input PDFs +* - `--env PYTHONBUFFERED=1` + - This will force `STDOUT` to be unbuffered and allow you to see messages in docker logs +::: + +This service relies on polling to check for changes to the filesystem. +It may not be suitable for some environments, such as filesystems shared +on a slow network. + +A configuration manager such as Docker Compose could be used to ensure +that the service is always available. + +:::{literalinclude} ../misc/docker-compose.example.yml +--- +caption: misc/docker-compose.example.yml +--- +::: + +### Caveats + +- `watchmedo` may not work properly on a networked file system, + depending on the capabilities of the file system client and server. +- This simple recipe does not filter for the type of file system + event, so file copies, deletes and moves, and directory operations, + will all be sent to ocrmypdf, producing errors in several cases. + Disable your watched folder if you are doing anything other than + copying files to it. +- If the source and destination directory are the same, watchmedo may + create an infinite loop. +- On BSD, FreeBSD and older versions of macOS, you may need to + increase the number of file descriptors to monitor more files, using + `ulimit -n 1024` to watch a folder of up to 1024 files. + +### Alternatives + +- On Linux, [systemd user + services](https://wiki.archlinux.org/index.php/Systemd/User) can be + configured to automatically perform OCR on a collection of files. +- [Watchman](https://facebook.github.io/watchman/) is a more powerful + alternative to `watchmedo`. + +macOS Automator +--------------- + +You can use the Automator app with macOS, to create a Workflow or Quick +Action. Use a *Run Shell Script* action in your workflow. In the context +of Automator, the `PATH` may be set differently your Terminal\'s `PATH`; +you may need to explicitly set the PATH to include `ocrmypdf`. The +following example may serve as a starting point: + +![](images/macos-workflow.png) + +You may customize the command sent to ocrmypdf. diff --git a/docs/batch.rst b/docs/batch.rst deleted file mode 100644 index 8daffa09..00000000 --- a/docs/batch.rst +++ /dev/null @@ -1,228 +0,0 @@ -.. SPDX-FileCopyrightText: 2022 James R. Barlow -.. -.. SPDX-License-Identifier: CC-BY-SA-4.0 - -================ -Batch processing -================ - -This article provides information about running OCRmyPDF on multiple -files or configuring it as a service triggered by file system events. - -Batch jobs -========== - -Consider using the excellent `GNU -Parallel `__ to apply OCRmyPDF -to multiple files at once. - -Both ``parallel`` and ``ocrmypdf`` will try to use all available -processors. To maximize parallelism without overloading your system with -processes, consider using ``parallel -j 2`` to limit parallel to running -two jobs at once. - -This command will run ``ocrmypdf`` on all files named ``*.pdf`` in the -current directory and write them to the previously created ``output/`` -folder. It will not search subdirectories. - -The ``--tag`` argument tells parallel to print the filename as a prefix -whenever a message is printed, so that one can trace any errors to the -file that produced them. - -.. code-block:: bash - - parallel --tag -j 2 ocrmypdf '{}' 'output/{}' ::: *.pdf - -OCRmyPDF automatically repairs PDFs before parsing and gathering -information from them. - -Directory trees -=============== - -This will walk through a directory tree and run OCR on all files in -place, and printing each filename in between runs: - -.. code-block:: bash - - find . -name '*.pdf' -printf '%p\n' -exec ocrmypdf '{}' '{}' \; - -This only runs one ``ocrmypdf`` process at a time. This variation uses -``find`` to create a directory list and ``parallel`` to parallelize runs -of ``ocrmypdf``, again updating files in place. - -.. code-block:: bash - - find . -name '*.pdf' | parallel --tag -j 2 ocrmypdf '{}' '{}' - -In a Windows batch file, use - -.. code-block:: bat - - for /r %%f in (*.pdf) do ocrmypdf %%f %%f - -With a Docker container, you will need to stream through standard input and output: - -.. code-block:: bash - - find . -name '*.pdf' -print0 | xargs -0 | while read pdf; do - pdfout=$(mktemp) - docker run --rm -i jbarlow83/ocrmypdf - - <$pdf >$pdfout && cp $pdfout $pdf - done - -Sample script -------------- - -This user contributed script also provides an example of batch -processing. - -.. literalinclude:: ../misc/batch.py - :caption: misc/batch.py - -Synology DiskStations ---------------------- - -Synology DiskStations (Network Attached Storage devices) can run the -Docker image of OCRmyPDF if the Synology `Docker -package `__ is -installed. Attached is a script to address particular quirks of using -OCRmyPDF on one of these devices. - -At the time this script was written, it only worked for x86-based Synology -products. It is not known if it will work on ARM-based Synology products. -Further adjustments might be needed to deal with the Synology's relatively -limited CPU and RAM. - -.. literalinclude:: ../misc/synology.py - :caption: misc/synology.py - Sample script for Synology DiskStations - -Huge batch jobs ---------------- - -If you have thousands of files to work with, contact the author. -Consulting work related to OCRmyPDF helps fund this open source project -and all inquiries are appreciated. - -Hot (watched) folders -===================== - -Watched folders with watcher.py -------------------------------- - -OCRmyPDF has a folder watcher called watcher.py, which is currently included in source -distributions but not part of the main program. It may be used natively or may run -in a Docker container. Native instances tend to give better performance. watcher.py -works on all platforms. - -Users may need to customize the script to meet their requirements. - -.. code-block:: bash - - pip3 install ocrmypdf[watcher] - - env OCR_INPUT_DIRECTORY=/mnt/input-pdfs \ - OCR_OUTPUT_DIRECTORY=/mnt/output-pdfs \ - OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1 \ - python3 watcher.py - -.. csv-table:: watcher.py environment variables - :header: "Environment variable", "Description" - :widths: 50, 50 - - "OCR_INPUT_DIRECTORY", "Set input directory to monitor (recursive)" - "OCR_OUTPUT_DIRECTORY", "Set output directory (should not be under input)" - "OCR_ARCHIVE_DIRECTORY", "Set archive directory for processed originals (should not be under input, requires ``OCR_ON_SUCCESS_ARCHIVE`` to be set)" - "OCR_ON_SUCCESS_DELETE", "This will delete the input file if the exit code is 0 (OK)" - "OCR_ON_SUCCESS_ARCHIVE", "This will move the processed original file to ``OCR_ARCHIVE_DIRECTORY`` if the exit code is 0 (OK). Note that ``OCR_ON_SUCCESS_DELETE`` takes precedence over this option, i.e. if both options are set, the input file will be deleted." - "OCR_OUTPUT_DIRECTORY_YEAR_MONTH", "This will place files in the output in ``{output}/{year}/{month}/{filename}``" - "OCR_DESKEW", "Apply deskew to crooked input PDFs" - "OCR_JSON_SETTINGS", "A JSON string specifying any other arguments for ``ocrmypdf.ocr``, e.g. ``'OCR_JSON_SETTINGS={""rotate_pages"": true, ""optimize"": ""3""}'``." - "OCR_POLL_NEW_FILE_SECONDS", "Polling interval" - "OCR_LOGLEVEL", "Level of log messages to report" - -One could configure a networked scanner or scanning computer to drop files in the -watched folder. - -Watched folders with Docker ---------------------------- - -The watcher service is included in the OCRmyPDF Docker image. To run it: - -.. code-block:: bash - - docker run \ - --volume :/input \ - --volume :/output \ - --volume :/processed \ - --env OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1 \ - --env OCR_ON_SUCCESS_ARCHIVE=1 \ - --env OCR_DESKEW=1 \ - --env PYTHONUNBUFFERED=1 \ - --interactive --tty --entrypoint python3 \ - jbarlow83/ocrmypdf \ - watcher.py - -This service will watch for a file that matches ``/input/\*.pdf``, -convert it to a OCRed PDF in ``/output/``, and move the processed -original to ``/processed``. The parameters to this image are: - -.. csv-table:: watcher.py parameters for Docker - :header: "Parameter", "Description" - :widths: 50, 50 - - "``--volume :/input``", "Files placed in this location will be OCRed" - "``--volume :/output``", "This is where OCRed files will be stored" - "``--volume :/processed``", "Archive processed originals here" - "``--env OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1``", "Define environment variable ``OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1`` to place files in the output in ``{output}/{year}/{month}/{filename}``" - "``--env OCR_ON_SUCCESS_ARCHIVE=1``", "Define environment variable ``OCR_ON_SUCCESS_ARCHIVE`` to move processed originals" - "``--env OCR_DESKEW=1``", "Define environment variable ``OCR_DESKEW`` to apply deskew to crooked input PDFs" - "``--env PYTHONBUFFERED=1``", "This will force ``STDOUT`` to be unbuffered and allow you to see messages in docker logs" - -This service relies on polling to check for changes to the filesystem. It -may not be suitable for some environments, such as filesystems shared on a -slow network. - -A configuration manager such as Docker Compose could be used to ensure that the -service is always available. - -.. literalinclude:: ../misc/docker-compose.example.yml - :language: yaml - :caption: misc/docker-compose.example.yml - -Caveats -------- - -- ``watchmedo`` may not work properly on a networked file system, - depending on the capabilities of the file system client and server. -- This simple recipe does not filter for the type of file system event, - so file copies, deletes and moves, and directory operations, will all - be sent to ocrmypdf, producing errors in several cases. Disable your - watched folder if you are doing anything other than copying files to - it. -- If the source and destination directory are the same, watchmedo may - create an infinite loop. -- On BSD, FreeBSD and older versions of macOS, you may need to increase - the number of file descriptors to monitor more files, using - ``ulimit -n 1024`` to watch a folder of up to 1024 files. - -Alternatives ------------- - -- On Linux, `systemd user services `__ - can be configured to automatically perform OCR on a collection of files. - -- `Watchman `__ is a more - powerful alternative to ``watchmedo``. - -macOS Automator -=============== - -You can use the Automator app with macOS, to create a Workflow or Quick -Action. Use a *Run Shell Script* action in your workflow. In the context -of Automator, the ``PATH`` may be set differently your Terminal's -``PATH``; you may need to explicitly set the PATH to include -``ocrmypdf``. The following example may serve as a starting point: - -.. figure:: images/macos-workflow.png - :alt: Example macOS Automator workflow - -You may customize the command sent to ocrmypdf. diff --git a/docs/conf.py b/docs/conf.py index 57b8532d..fc89bace 100755 --- a/docs/conf.py +++ b/docs/conf.py @@ -36,6 +36,7 @@ import datetime # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom # ones. extensions = [ + 'myst_parser', 'sphinx.ext.autodoc', 'sphinx.ext.intersphinx', 'sphinx.ext.autosummary', @@ -44,6 +45,8 @@ extensions = [ 'sphinx_issues', ] +myst_enable_extensions = ['colon_fence', 'attrs_block', 'attrs_inline'] + # Extension settings intersphinx_mapping = {'python': ('https://docs.python.org/3', None)} napoleon_use_rtype = False @@ -53,7 +56,7 @@ issues_github_path = "ocrmypdf/OCRmyPDF" templates_path = ['_templates'] # The suffix(es) of source filenames. -source_suffix = {'.rst': 'restructuredtext', '.md': 'markdown'} +source_suffix = {'.rst': 'restructuredtext', '.md': 'markdown', '.txt': 'markdown'} # The encoding of source files. # diff --git a/docs/contributing.md b/docs/contributing.md new file mode 100644 index 00000000..90264c61 --- /dev/null +++ b/docs/contributing.md @@ -0,0 +1,72 @@ +% SPDX-FileCopyrightText: 2025 James R. Barlow +% SPDX-License-Identifier: CC-BY-SA-4.0 + +# Contributing guidelines + +Contributions are welcome! + +## Big changes + +Please open a new issue to discuss or propose a major change. Not only +is it fun to discuss big ideas, but we might save each other\'s time +too. Perhaps some of the work you\'re contemplating is already half-done +in a development branch. + +## Code style + +We use `ruff` for code formatting. +The settings for these programs are in `pyproject.toml`. Pull requests +should follow the style guide. One difference we use from \"black\" +style is that strings shown to the user are always in double quotes +(`"`) and strings for internal uses are in single quotes (`'`). + +## Tests + +New features should come with tests that confirm their correctness. + +## New dependencies + +If you are proposing a change that will require a new dependency, we +prefer dependencies that are already packaged by Debian or Red Hat. This +makes life much easier for our downstream package maintainers. A package +that is only available on PyPI or GitHub, and not more widely packaged, +may not be accepted. + +We are unlikely to accept a dependency on CUDA or other GPU-based +libraries, because these are still difficult to package and install on +many systems. We recommend implementing these changes as plugins. + +Python dependencies must also be license-compatible. GPLv3 or AGPLv3 are +likely incompatible with the project\'s license, but LGPLv3 is +compatible. + +## New non-Python dependencies + +OCRmyPDF uses several external programs (Tesseract, Ghostscript and +others) for its functionality. In general we prefer to avoid adding new +external programs, and if we are to add external programs, we prefer +those that are already packaged by Debian or Red Hat. + +## Plugins + +Some new features may be a good fit for a plugin. Plugins are a way to +add features to OCRmyPDF without adding them to the core program. +Plugins are installed separately from OCRmyPDF. They are written in +Python and can be installed from PyPI. See the [plugin +documentation](https://ocrmypdf.readthedocs.io/en/latest/plugins.html). + +We are happy to link users to your plugin from the documentation. + +## Style guide: Is it OCRmyPDF or ocrmypdf? + +The program/project is OCRmyPDF and the name of the executable or +library is ocrmypdf. + +## Copyright and license + +For contributions over 10 lines of code, please add your name to list of +copyright holders for that file. The core program is licensed under +MPL-2.0, test files and documentation under CC-BY-SA 4.0, and +miscellaneous files under MIT, with a few minor exceptions. Please +contribute only content that you own or have the right to contribute +under these licenses. diff --git a/docs/contributing.rst b/docs/contributing.rst deleted file mode 100644 index e1c8e138..00000000 --- a/docs/contributing.rst +++ /dev/null @@ -1,77 +0,0 @@ -.. SPDX-FileCopyrightText: 2022 James R. Barlow -.. -.. SPDX-License-Identifier: CC-BY-SA-4.0 - -======================= -Contributing guidelines -======================= - -Contributions are welcome! - -Big changes -=========== - -Please open a new issue to discuss or propose a major change. Not only is it fun -to discuss big ideas, but we might save each other's time too. Perhaps some of the -work you're contemplating is already half-done in a development branch. - -Code style -========== - -We use PEP8, ``black`` for code formatting and ``ruff`` for everything else. The -settings for these programs are in ``pyproject.toml``. Pull -requests should follow the style guide. One difference we use from "black" style -is that strings shown to the user are always in double quotes (``"``) and strings -for internal uses are in single quotes (``'``). - -Tests -===== - -New features should come with tests that confirm their correctness. - -New dependencies -================ - -If you are proposing a change that will require a new dependency, we -prefer dependencies that are already packaged by Debian or Red Hat. This makes -life much easier for our downstream package maintainers. A package that is only -available on PyPI or GitHub, and not more widely packaged, may not be accepted. - -We are unlikely to accept a dependency on CUDA or other GPU-based libraries, -because these are still difficult to package and install on many systems. -We recommend implementing these changes as plugins. - -Python dependencies must also be license-compatible. GPLv3 or AGPLv3 are likely -incompatible with the project's license, but LGPLv3 is compatible. - -New non-Python dependencies -=========================== - -OCRmyPDF uses several external programs (Tesseract, Ghostscript and others) for -its functionality. In general we prefer to avoid adding new external programs, -and if we are to add external programs, we prefer those that are already -packaged by Debian or Red Hat. - -Plugins -======= - -Some new features may be a good fit for a plugin. Plugins are a way to add -features to OCRmyPDF without adding them to the core program. Plugins are -installed separately from OCRmyPDF. They are written in Python and can be -installed from PyPI. See the `plugin documentation `_. - -We are happy to link users to your plugin from the documentation. - -Style guide: Is it OCRmyPDF or ocrmypdf? -======================================== - -The program/project is OCRmyPDF and the name of the executable or library is ocrmypdf. - -Copyright and license -===================== - -For contributions over 10 lines of code, please add your name to list of -copyright holders for that file. The core program is licensed under MPL-2.0, -test files and documentation under CC-BY-SA 4.0, and miscellaneous files under -MIT, with a few minor exceptions. Please contribute only content that you own -or have the right to contribute under these licenses. diff --git a/docs/cookbook.md b/docs/cookbook.md new file mode 100644 index 00000000..0bdcc941 --- /dev/null +++ b/docs/cookbook.md @@ -0,0 +1,404 @@ +% SPDX-FileCopyrightText: 2025 James R. Barlow +% SPDX-License-Identifier: CC-BY-SA-4.0 + +Cookbook +======== + +Basic examples +-------------- + +### Help! + +ocrmypdf has built-in help. + +:::{code} bash +ocrmypdf --help +::: + +### Add an OCR layer and convert to PDF/A + +:::{code} bash +ocrmypdf input.pdf output.pdf +::: + +### Add an OCR layer and output a standard PDF + +:::{code} bash +ocrmypdf --output-type pdf input.pdf output.pdf +::: + +### Create a PDF/A with all color and grayscale images converted to JPEG + +:::{code} bash +ocrmypdf --output-type pdfa --pdfa-image-compression jpeg input.pdf output.pdf +::: + +### Modify a file in place + +The file will only be overwritten if OCRmyPDF is successful. + +:::{code} bash +ocrmypdf myfile.pdf myfile.pdf +::: + +### Correct page rotation + +OCR will attempt to automatic correct the rotation of each page. This +can help fix a scanning job that contains a mix of landscape and +portrait pages. + +:::{code} bash +ocrmypdf --rotate-pages myfile.pdf myfile.pdf +::: + +You can increase (decrease) the parameter `--rotate-pages-threshold` to +make page rotation more (less) aggressive. The threshold number is the +ratio of how confidence the OCR engine is that the document image should +be changed, compared to kept the same. The default value is quite +conservative; on some files it may not attempt rotations at all unless +it is very confident that the current rotation is wrong. A lower value +of `2.0` will produce more rotations, and more false positives. Run with +`-v1` to see the confidence level for each page to see if there may be a +better value for your files. + +If the page is \"just a little off horizontal\", like a crooked picture, +then you want `--deskew`. `--rotate-pages` is for when the cardinal +angle is wrong. + +### OCR languages other than English + +OCRmyPDF assumes the document is in English unless told otherwise. OCR +quality may be poor if the wrong language is used. + +:::{code} bash +ocrmypdf -l fra LeParisien.pdf LeParisien.pdf +ocrmypdf -l eng+fra Bilingual-English-French.pdf Bilingual-English-French.pdf +::: + +Language packs must be installed for all languages specified. See +`Installing additional language packs `{.interpreted-text +role="ref"}. + +Unfortunately, the Tesseract OCR engine has no ability to detect the +language when it is unknown. + +### Produce PDF and text file containing OCR text + +This produces a file named \"output.pdf\" and a companion text file +named \"output.txt\". + +:::{code} bash +ocrmypdf --sidecar output.txt input.pdf output.pdf +::: + +:::{note} +The sidecar file contains the **OCR text** found by OCRmyPDF. If the +document contains pages that already have text, that text will not +appear in the sidecar. If the option `--pages` is used, only those pages +on which OCR was performed will be included in the sidecar. If certain +pages were skipped because of options like `--skip-big` or +`--tesseract-timeout`, those pages will not be in the sidecar. + +If you don\'t want to generate the output PDF, use `--output-type=none` +to avoid generating one. Set the output filename to `-` (i.e. redirect +to stdout). + +To extract all text from a PDF, whether generated from OCR or otherwise, +use a program like Poppler\'s `pdftotext` or `pdfgrep`. +::: + +### OCR images, not PDFs + +#### Option: use Tesseract + +If you are starting with images, you can just use Tesseract directly to +convert images to PDFs: + +:::{code} bash +tesseract my-image.jpg output-prefix pdf +::: + +:::{code} bash +# When there are multiple images +tesseract text-file-containing-list-of-image-filenames.txt output-prefix pdf +::: + +Tesseract\'s PDF output is quite good -- OCRmyPDF uses it internally, in +some cases. However, OCRmyPDF has many features not available in +Tesseract like image processing, metadata control, and PDF/A generation. + +#### Option: use img2pdf + +You can also use a program like +[img2pdf](https://gitlab.mister-muffin.de/josch/img2pdf) to convert your +images to PDFs, and then pipe the results to run ocrmypdf. The `-` tells +ocrmypdf to read standard input. + +:::{code} bash +img2pdf my-images*.jpg | ocrmypdf - myfile.pdf +::: + +`img2pdf` is recommended because it does an excellent job at generating +PDFs without transcoding images. + +#### Option: use OCRmyPDF (single images only) + +For convenience, OCRmyPDF can also convert single images to PDFs on its +own. If the resolution (dots per inch, DPI) of an image is not set or is +incorrect, it can be overridden with `--image-dpi`. (As 1 inch is 2.54 +cm, 1 dpi = 0.39 dpcm). + +:::{code} bash +ocrmypdf --image-dpi 300 image.png myfile.pdf +::: + +If you have multiple images, you must use `img2pdf` to convert the +images to PDF. + +#### Not recommended + +We caution against using ImageMagick or Ghostscript to convert images to +PDF, since they may transcode images or produce downsampled images, +sometimes without warning. + +Image processing +---------------- + +OCRmyPDF perform some image processing on each page of a PDF, if +desired. The same processing is applied to each page. It is suggested +that the user review files after image processing as these commands +might remove desirable content, especially from poor quality scans. + +- `--rotate-pages` attempts to determine the correct orientation for + each page and rotates the page if necessary. +- `--remove-background` attempts to detect and remove a noisy + background from grayscale or color images. Monochrome images are + ignored. This should not be used on documents that contain color + photos as it may remove them. +- `--deskew` will correct pages that were scanned at a skewed angle by + rotating them back into place. +- `--clean` uses [unpaper](https://www.flameeyes.eu/projects/unpaper) + to clean up pages before OCR, but does not alter the final output. + This makes it less likely that OCR will try to find text in + background noise. +- `--clean-final` uses unpaper to clean up pages before OCR and + inserts the page into the final output. You will want to review each + page to ensure that unpaper did not remove something important. + +:::{note} +In many cases image processing will rasterize PDF pages as images, +potentially losing quality. +::: + +:::{warning} +`--clean-final` and `--remove-background` may leave undesirable visual +artifacts in some images where their algorithms have shortcomings. Files +should be visually reviewed after using these options. +::: + +### Example: OCR and correct document skew (crooked scan) + +Deskew: + +:::{code} bash +ocrmypdf --deskew input.pdf output.pdf +::: + +Image processing commands can be combined. The order in which options +are given does not matter. OCRmyPDF always applies the steps of the +image processing pipeline in the same order (rotate, remove background, +deskew, clean). + +:::{code} bash +ocrmypdf --deskew --clean --rotate-pages input.pdf output.pdf +::: + +Don\'t actually OCR my PDF +-------------------------- + +If you set `--tesseract-timeout 0` OCRmyPDF will apply its image +processing without performing OCR (by causing OCR to time out). This +works if all you want to is to apply image processing or PDF/A +conversion. + +:::{code} bash +ocrmypdf --tesseract-timeout=0 --remove-background input.pdf output.pdf +::: + +::: {.versionchanged} +v14.1.0 + +Prior to this version, `--tesseract-timeout 0` would prevent other uses +of Tesseract, such as deskewing, from working. This is no longer the +case. Use `--tesseract-non-ocr-timeout` to control the timeout for +non-OCR operations, if needed. +::: + +### Remove all text or OCR from my PDF + +This is getting ridiculous, but OCRmyPDF can complete strip all textual +information from a PDF and reconstruct it as a \"bag of images\" PDF. + +:::{code} bash +ocrmypdf --tesseract-timeout 0 --force-ocr input.pdf output.pdf +::: + +Why would you want to do this? Perhaps you have a PDF where OCR fails to +produce useful results, and just want to get rid of all OCR information. +This command also removes OCR generated by third party tools. + +### Optimize images without performing OCR + +You can also optimize all images without performing any OCR: + +:::{code} bash +ocrmypdf --tesseract-timeout=0 --optimize 3 --skip-text input.pdf output.pdf +::: + +### Process only certain pages + +You can ask OCRmyPDF to only apply [image processing](#image-processing) +and OCR to certain pages. + +:::{code} bash +ocrmypdf --pages 2,3,13-17 input.pdf output.pdf +::: + +Hyphens denote a range of pages and commas separate page numbers. If you +prefer to use spaces, quote all of the page numbers: +`--pages '2, 3, 5, 7'`. + +OCRmyPDF will warn if your list of page numbers contains duplicates or +overlapping pages. OCRmyPDF does not currently account for document page +numbers, such as an introduction section of a book that uses Roman +numerals. It simply counts the number of virtual pieces of paper since +the start. If your list of pages is out of numerical order, OCRmyPDF +will sort it for you. + +Regardless of the argument to `--pages`, OCRmyPDF will optimize all +pages/images in the file and convert it to PDF/A, unless you disable +those options. Both of these steps are \"whole file\" operations. In +this example, we want to OCR only the title and otherwise change the PDF +as little as possible: + +:::{code} bash +ocrmypdf --pages 1 --output-type pdf --optimize 0 input.pdf output.pdf +::: + +Redo existing OCR +----------------- + +To redo OCR on a file OCRed with other OCR software or a previous +version of OCRmyPDF and/or Tesseract, you may use the `--redo-ocr` +argument. (Normally, OCRmyPDF will exit with an error if asked to modify +a file with OCR.) + +This may be helpful for users who want to take advantage of accuracy +improvements in Tesseract for files they previously OCRed with an +earlier version of Tesseract and OCRmyPDF. + +:::{code} bash +ocrmypdf --redo-ocr input.pdf output.pdf +::: + +This method will replace OCR without rasterizing, reducing quality or +removing vector content. If a file contains a mix of pure digital text +and OCR, digital text will be ignored and OCR will be replaced. As such +this mode is incompatible with image processing options, since they +alter the appearance of the file. + +In some cases, existing OCR cannot be detected or replaced. Files +produced by OCRmyPDF v2.2 or earlier, for example, are internally +represented as having visible text with an opaque image drawn on top. +This situation cannot be detected. + +If `--redo-ocr` does not work, you can use `--force-ocr`, which will +force rasterization of all pages, potentially reducing quality or losing +vector content. + +Improving OCR quality +--------------------- + +The [Image processing](#image-processing) features can improve OCR +quality. + +Rotating pages and deskewing helps to ensure that the page orientation +is correct before OCR begins. Removing the background and/or cleaning +the page can also improve results. The `--oversample DPI` argument can +be specified to resample images to higher resolution before attempting +OCR; this can improve results as well. + +OCR quality will suffer if the resolution of input images is not correct +(since the range of pixel sizes that will be checked for possible fonts +will also be incorrect). + +PDF optimization +---------------- + +By default OCRmyPDF will attempt to perform lossless optimizations on +the images inside PDFs after OCR is complete. Optimization is performed +even if no OCR text is found. + +The `--optimize N` (short form `-O`) argument controls optimization, +where `N` ranges from 0 to 3 inclusive, analogous to the optimization +levels in the GCC compiler. + +:::{list-table} +--- +widths: auto +header-rows: 1 +--- + +* - Level + - Comments +* - ``--optimize=0`` + - Disables optimization. +* - ``--optimize 1`` + - Enables lossless optimizations, such as transcoding images to more + efficient formats. Also compress other uncompressed objects in the + PDF and enables the more efficient "object streams" within the PDF. + (If ``--jbig2-lossy`` is issued, then lossy JBIG2 optimization is used. + The decision to use lossy JBIG2 is separate from standard optimization + settings.) +* - ``--optimize 2`` + - All of the above, and enables lossy optimizations and color quantization. +* - ``--optimize 3`` + - All of the above, and enables more aggressive optimizations and targets lower image quality. +::: + +Optimization is improved when a JBIG2 encoder is available and when +`pngquant` is installed. If either of these components are missing, then +some types of images cannot be optimized. + +The types of optimization available may expand over time. By default, +OCRmyPDF compresses data streams inside PDFs, and will change +inefficient compression modes to more modern versions. A program like +`qpdf` can be used to change encodings, e.g. to inspect the internals +for a PDF. + +:::{code} bash +ocrmypdf --optimize 3 in.pdf out.pdf # Make it small +::: + +Some users may consider enabling lossy JBIG2. See: +`jbig2-lossy`{.interpreted-text role="ref"}. + +:::{note} +Image processing and PDF/A conversion can also introduce lossy +transformations to your PDF images, even when `--optimize 1` is in use. +::: + +Digitally signed PDFs +--------------------- + +OCRmyPDF cannot preserve digital signatures in PDFs and also add OCR to +them. By default, it will refuse to modify a signed PDF regardless of +other settings. You can override this behavior with +`--invalidate-digital-signatures`; as the name suggests, any digital +signatures will be invalidated. + +OCRmyPDF cannot open documents that are encrypted with a digital +certificate. + +Versions of OCRmyPDF prior to 14.4.0 would invalidate existing digital +signatures without warning. diff --git a/docs/cookbook.rst b/docs/cookbook.rst deleted file mode 100644 index 2a5429ba..00000000 --- a/docs/cookbook.rst +++ /dev/null @@ -1,410 +0,0 @@ -.. SPDX-FileCopyrightText: 2022 James R. Barlow -.. -.. SPDX-License-Identifier: CC-BY-SA-4.0 - -======== -Cookbook -======== - -Basic examples -============== - -Help! ------ - -ocrmypdf has built-in help. - -.. code-block:: bash - - ocrmypdf --help - -Add an OCR layer and convert to PDF/A -------------------------------------- - -.. code-block:: bash - - ocrmypdf input.pdf output.pdf - -Add an OCR layer and output a standard PDF ------------------------------------------- - -.. code-block:: bash - - ocrmypdf --output-type pdf input.pdf output.pdf - -Create a PDF/A with all color and grayscale images converted to JPEG --------------------------------------------------------------------- - -.. code-block:: bash - - ocrmypdf --output-type pdfa --pdfa-image-compression jpeg input.pdf output.pdf - -Modify a file in place ----------------------- - -The file will only be overwritten if OCRmyPDF is successful. - -.. code-block:: bash - - ocrmypdf myfile.pdf myfile.pdf - -Correct page rotation ---------------------- - -OCR will attempt to automatic correct the rotation of each page. This -can help fix a scanning job that contains a mix of landscape and -portrait pages. - -.. code-block:: bash - - ocrmypdf --rotate-pages myfile.pdf myfile.pdf - -You can increase (decrease) the parameter ``--rotate-pages-threshold`` -to make page rotation more (less) aggressive. The threshold number is the ratio -of how confidence the OCR engine is that the document image should be changed, -compared to kept the same. The default value is quite conservative; on some files -it may not attempt rotations at all unless it is very confident that the current -rotation is wrong. A lower value of ``2.0`` will produce more rotations, and -more false positives. Run with ``-v1`` to see the confidence level for each -page to see if there may be a better value for your files. - -If the page is "just a little off horizontal", like a crooked picture, -then you want ``--deskew``. ``--rotate-pages`` is for when the cardinal -angle is wrong. - -OCR languages other than English --------------------------------- - -OCRmyPDF assumes the document is in English unless told otherwise. OCR -quality may be poor if the wrong language is used. - -.. code-block:: bash - - ocrmypdf -l fra LeParisien.pdf LeParisien.pdf - ocrmypdf -l eng+fra Bilingual-English-French.pdf Bilingual-English-French.pdf - -Language packs must be installed for all languages specified. See -:ref:`Installing additional language packs `. - -Unfortunately, the Tesseract OCR engine has no ability to detect the -language when it is unknown. - -Produce PDF and text file containing OCR text ---------------------------------------------- - -This produces a file named "output.pdf" and a companion text file named -"output.txt". - -.. code-block:: bash - - ocrmypdf --sidecar output.txt input.pdf output.pdf - -.. note:: - - The sidecar file contains the **OCR text** found by OCRmyPDF. If the document - contains pages that already have text, that text will not appear in the - sidecar. If the option ``--pages`` is used, only those pages on which OCR - was performed will be included in the sidecar. If certain pages were skipped - because of options like ``--skip-big`` or ``--tesseract-timeout``, those pages - will not be in the sidecar. - - If you don't want to generate the output PDF, use ``--output-type=none`` to - avoid generating one. Set the output filename to ``-`` (i.e. redirect to stdout). - - To extract all text from a PDF, whether generated from OCR or otherwise, - use a program like Poppler's ``pdftotext`` or ``pdfgrep``. - -OCR images, not PDFs --------------------- - -Option: use Tesseract -~~~~~~~~~~~~~~~~~~~~~ - -If you are starting with images, you can just use Tesseract directly to -convert images to PDFs: - -.. code-block:: bash - - tesseract my-image.jpg output-prefix pdf - -.. code-block:: bash - - # When there are multiple images - tesseract text-file-containing-list-of-image-filenames.txt output-prefix pdf - -Tesseract's PDF output is quite good – OCRmyPDF uses it internally, in -some cases. However, OCRmyPDF has many features not available in -Tesseract like image processing, metadata control, and PDF/A generation. - -Option: use img2pdf -~~~~~~~~~~~~~~~~~~~ - -You can also use a program like -`img2pdf `__ to convert -your images to PDFs, and then pipe the results to run ocrmypdf. The -``-`` tells ocrmypdf to read standard input. - -.. code-block:: bash - - img2pdf my-images*.jpg | ocrmypdf - myfile.pdf - -``img2pdf`` is recommended because it does an excellent job at -generating PDFs without transcoding images. - -Option: use OCRmyPDF (single images only) -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - -For convenience, OCRmyPDF can also convert single images to PDFs on its -own. If the resolution (dots per inch, DPI) of an image is not set or is -incorrect, it can be overridden with ``--image-dpi``. (As 1 inch is 2.54 -cm, 1 dpi = 0.39 dpcm). - -.. code-block:: bash - - ocrmypdf --image-dpi 300 image.png myfile.pdf - -If you have multiple images, you must use ``img2pdf`` to convert the -images to PDF. - -Not recommended -~~~~~~~~~~~~~~~ - -We caution against using ImageMagick or Ghostscript to convert images to -PDF, since they may transcode images or produce downsampled images, -sometimes without warning. - -Image processing -================ - -OCRmyPDF perform some image processing on each page of a PDF, if -desired. The same processing is applied to each page. It is suggested -that the user review files after image processing as these commands -might remove desirable content, especially from poor quality scans. - -- ``--rotate-pages`` attempts to determine the correct orientation for - each page and rotates the page if necessary. -- ``--remove-background`` attempts to detect and remove a noisy - background from grayscale or color images. Monochrome images are - ignored. This should not be used on documents that contain color - photos as it may remove them. -- ``--deskew`` will correct pages that were scanned at a skewed angle by - rotating them back into place. -- ``--clean`` uses - `unpaper `__ to clean up - pages before OCR, but does not alter the final output. This makes it - less likely that OCR will try to find text in background noise. -- ``--clean-final`` uses unpaper to clean up pages before OCR and - inserts the page into the final output. You will want to review each - page to ensure that unpaper did not remove something important. - -.. note:: - - In many cases image processing will rasterize PDF pages as images, - potentially losing quality. - -.. warning:: - - ``--clean-final`` and ``--remove-background`` may leave undesirable - visual artifacts in some images where their algorithms have - shortcomings. Files should be visually reviewed after using these - options. - -Example: OCR and correct document skew (crooked scan) ------------------------------------------------------ - -Deskew: - -.. code-block:: bash - - ocrmypdf --deskew input.pdf output.pdf - -Image processing commands can be combined. The order in which options -are given does not matter. OCRmyPDF always applies the steps of the -image processing pipeline in the same order (rotate, remove background, -deskew, clean). - -.. code-block:: bash - - ocrmypdf --deskew --clean --rotate-pages input.pdf output.pdf - -Don't actually OCR my PDF -========================= - -If you set ``--tesseract-timeout 0`` OCRmyPDF will apply its image -processing without performing OCR (by causing OCR to time out). This works -if all you want to is to apply image processing or PDF/A conversion. - -.. code-block:: bash - - ocrmypdf --tesseract-timeout=0 --remove-background input.pdf output.pdf - -.. versionchanged:: v14.1.0 - - Prior to this version, ``--tesseract-timeout 0`` would prevent other - uses of Tesseract, such as deskewing, from working. This is no longer - the case. Use ``--tesseract-non-ocr-timeout`` to control the timeout - for non-OCR operations, if needed. - -Remove all text or OCR from my PDF ----------------------------------- - -This is getting ridiculous, but OCRmyPDF can complete strip all textual -information from a PDF and reconstruct it as a "bag of images" PDF. - -.. code-block:: - - ocrmypdf --tesseract-timeout 0 --force-ocr input.pdf output.pdf - -Why would you want to do this? Perhaps you have a PDF where OCR -fails to produce useful results, and just want to get rid of all OCR information. -This command also removes OCR generated by third party tools. - -Optimize images without performing OCR --------------------------------------- - -You can also optimize all images without performing any OCR: - -.. code-block:: bash - - ocrmypdf --tesseract-timeout=0 --optimize 3 --skip-text input.pdf output.pdf - -Process only certain pages --------------------------- - -You can ask OCRmyPDF to only apply `image processing <#image-processing>`__ -and OCR to certain pages. - -.. code-block:: bash - - ocrmypdf --pages 2,3,13-17 input.pdf output.pdf - -Hyphens denote a range of pages and commas separate page numbers. If you prefer -to use spaces, quote all of the page numbers: ``--pages '2, 3, 5, 7'``. - -OCRmyPDF will warn if your list of page numbers contains duplicates or -overlapping pages. OCRmyPDF does not currently account for document page numbers, -such as an introduction section of a book that uses Roman numerals. It simply -counts the number of virtual pieces of paper since the start. If your list of -pages is out of numerical order, OCRmyPDF will sort it for you. - -Regardless of the argument to ``--pages``, OCRmyPDF will optimize all pages/images -in the file and convert it to PDF/A, unless you disable those options. Both of these -steps are "whole file" operations. In this example, we want to OCR only the title -and otherwise change the PDF as little as possible: - -.. code-block:: bash - - ocrmypdf --pages 1 --output-type pdf --optimize 0 input.pdf output.pdf - -Redo existing OCR -================= - -To redo OCR on a file OCRed with other OCR software or a previous -version of OCRmyPDF and/or Tesseract, you may use the ``--redo-ocr`` -argument. (Normally, OCRmyPDF will exit with an error if asked to modify -a file with OCR.) - -This may be helpful for users who want to take advantage of accuracy -improvements in Tesseract for files they previously OCRed with an -earlier version of Tesseract and OCRmyPDF. - -.. code-block:: bash - - ocrmypdf --redo-ocr input.pdf output.pdf - -This method will replace OCR without rasterizing, reducing quality or -removing vector content. If a file contains a mix of pure digital text -and OCR, digital text will be ignored and OCR will be replaced. As such -this mode is incompatible with image processing options, since they -alter the appearance of the file. - -In some cases, existing OCR cannot be detected or replaced. Files -produced by OCRmyPDF v2.2 or earlier, for example, are internally -represented as having visible text with an opaque image drawn on top. -This situation cannot be detected. - -If ``--redo-ocr`` does not work, you can use ``--force-ocr``, which will -force rasterization of all pages, potentially reducing quality or losing -vector content. - -Improving OCR quality -===================== - -The `Image processing <#image-processing>`__ features can improve OCR -quality. - -Rotating pages and deskewing helps to ensure that the page orientation -is correct before OCR begins. Removing the background and/or cleaning -the page can also improve results. The ``--oversample DPI`` argument can -be specified to resample images to higher resolution before attempting -OCR; this can improve results as well. - -OCR quality will suffer if the resolution of input images is not correct -(since the range of pixel sizes that will be checked for possible fonts -will also be incorrect). - -PDF optimization -================ - -By default OCRmyPDF will attempt to perform lossless optimizations on -the images inside PDFs after OCR is complete. Optimization is performed -even if no OCR text is found. - -The ``--optimize N`` (short form ``-O``) argument controls optimization, -where ``N`` ranges from 0 to 3 inclusive, analogous to the optimization -levels in the GCC compiler. - -.. list-table:: - :widths: auto - :header-rows: 1 - - * - Level - - Comments - * - ``--optimize 0`` - - Disables optimization. - * - ``--optimize 1`` - - Enables lossless optimizations, such as transcoding images to more - efficient formats. Also compress other uncompressed objects in the - PDF and enables the more efficient "object streams" within the PDF. - (If ``--jbig2-lossy`` is issued, then lossy JBIG2 optimization is used. - The decision to use lossy JBIG2 is separate from standard optimization - settings.) - * - ``--optimize 2`` - - All of the above, and enables lossy optimizations and color quantization. - * - ``--optimize 3`` - - All of the above, and enables more aggressive optimizations and targets lower image quality. - -Optimization is improved when a JBIG2 encoder is available and when -``pngquant`` is installed. If either of these components are missing, -then some types of images cannot be optimized. - -The types of optimization available may expand over time. By default, -OCRmyPDF compresses data streams inside PDFs, and will change -inefficient compression modes to more modern versions. A program like -``qpdf`` can be used to change encodings, e.g. to inspect the internals -for a PDF. - -.. code-block:: bash - - ocrmypdf --optimize 3 in.pdf out.pdf # Make it small - -Some users may consider enabling lossy JBIG2. See: :ref:`jbig2-lossy`. - -.. note:: - - Image processing and PDF/A conversion can also introduce lossy transformations - to your PDF images, even when ``--optimize 1`` is in use. - - -Digitally signed PDFs -===================== - -OCRmyPDF cannot preserve digital signatures in PDFs and also add OCR to them. -By default, it will refuse to modify a signed PDF regardless of other settings. You can -override this behavior with ``--invalidate-digital-signatures``; as the name suggests, -any digital signatures will be invalidated. - -OCRmyPDF cannot open documents that are encrypted with a digital certificate. - -Versions of OCRmyPDF prior to 14.4.0 would invalidate existing digital signatures -without warning. diff --git a/docs/docker.md b/docs/docker.md new file mode 100644 index 00000000..d1d15e70 --- /dev/null +++ b/docs/docker.md @@ -0,0 +1,245 @@ +# OCRmyPDF Docker image {#docker} + +OCRmyPDF is also available in Docker images that packages recent +versions of all dependencies. + +For users who already have Docker installed this may be an easy and +convenient option. + +On platforms other than Linux, Docker runs in a virtual machine, and so +may be less performant. You may also want to adjust the Docker virtual +machine\'s memory and CPU allocation. On Linux, the Docker image runs +natively and performance is comparable to a system installation. + +{#docker-install} +## Installing the Docker image + +If you have [Docker](https://docs.docker.com/) installed on your system, +you can install a Docker image of the latest release. + +If you can run this command successfully, your system is ready to +download and execute the image: + +:::{code} bash +docker run hello-world +::: + +:::{list-table} Docker Images +:header-rows: 1 + +* - Image + - Architecture + - Description +* - `jbarlow83/ocrmypdf-alpine` + - x86_64 and arm64 + - Recommended image, based on Alpine Linux. +* - `jbarlow83/ocrmypdf-ubuntu` + - x86_64 and arm64 + - Alternate image, based on Ubuntu. When the Alpine image is considered stable and available for arm64, this image will be deprecated. +* - `jbarlow83/ocrmypdf` + - x86_64 and arm64 + - Currently an alias for ocrmypdf-ubuntu. When the Alpine image is considered stable and available for arm64, this name will point to the Alpine image. If you don\'t know about the difference between Alpine and Ubuntu, use this image. +::: + +To install: + +:::{code} bash +docker pull jbarlow83/ocrmypdf-alpine +::: + +The `ocrmypdf` image is also available, but is deprecated and will be +removed in the future. + +OCRmyPDF will use all available CPU cores. See the Docker documentation +for [adjusting memory and CPU on other +platforms](https://docs.docker.com/config/containers/resource_constraints/) +if you are using Docker on macOS or Windows, where you may need to +manually assign more resources. On Linux, all resources will be +available automatically. + +The underlying operating system and other details in Docker images are +considered implementation details and **subject to change at minor +releases**. If you are modifying the image, you should pin the version +you intend to use. + +## Using the Docker image on the command line + +**Unlike typical Docker containers**, in this section the OCRmyPDF +Docker container is ephemeral -- it runs for one OCR job and terminates, +just like a command line program. We are using Docker to deliver an +application (as opposed to the more conventional case, where a Docker +container runs as a server). For that reason we usually use the `--rm` +argument to delete the container when it exits. + +To start a Docker container (instance of the image): + +:::{code} bash +docker run --rm -i jbarlow83/ocrmypdf-alpine (... all other arguments here...) - - +::: + +For convenience, create a shell alias to hide the Docker command. It is +easier to send the input file as stdin and read the output from stdout +-- **this avoids the messy permission issues with Docker entirely**. + +:::{code} bash +alias docker_ocrmypdf='docker run --rm -i jbarlow83/ocrmypdf-alpine' +docker_ocrmypdf --version # runs docker version +docker_ocrmypdf - - output.pdf +::: + +Or in the wonderful [fish shell](https://fishshell.com/): + +:::{code} fish +alias docker_ocrmypdf 'docker run --rm jbarlow83/ocrmypdf-alpine' +funcsave docker_ocrmypdf +::: + +Alternately, you could mount the local current working directory as a +Docker volume: + +:::{code} bash +alias docker_ocrmypdf='docker run --rm -i --user "$(id -u):$(id -g)" --workdir /data -v "$PWD:/data" jbarlow83/ocrmypdf-alpine' +docker_ocrmypdf /data/input.pdf /data/output.pdf +::: + +## Podman + +Especially if you use [Podman](https://podman.io/) (or have SELinux +enabled on your system), you may need to add `--userns keep-id` there, +otherwise you may get access errors, because the user is otherwise not +mapped to the same UID as on the host: + +:::{code} bash +alias podman_ocrmypdf='podman run --rm -i --user "$(id -u):$(id -g)" --userns keep-id --workdir /data -v "$PWD:/data" ocrmypdf' +podman_ocrmypdf /data/input.pdf /data/output.pdf +::: + +If you use SELinux you may additionally need to add the `:Z` [suffix to +the +volume](https://docs.podman.io/en/stable/markdown/podman-run.1.html#volume-v-source-volume-host-dir-container-dir-options) +or disable SELinux for the container using +`--security-opt label=disable`, which is suggested for system files as +they should not be re-labelled. Please refer to the „Note" section at +the end of the linked podman documentation for details. + +{#docker-lang-packs} +## Adding languages to the Docker image + +By default the Docker image includes English, German, Simplified +Chinese, French, Portuguese and Spanish, the most popular languages for +OCRmyPDF users based on feedback. You may add other languages by +creating a new Dockerfile based on the public one. + +:::{code} dockerfile +FROM jbarlow83/ocrmypdf + +# Example: add Italian +RUN apt install tesseract-ocr-ita +::: + +To install language packs (training data) such as the +[tessdata\_best](https://github.com/tesseract-ocr/tessdata_best) suite +or custom data, you first need to determine the version of Tesseract +data files, which may differ from the Tesseract program version. Use +this command to determine the data file version: + +:::{code} bash +docker run -i --rm --entrypoint /bin/ls jbarlow83/ocrmypdf /usr/share/tesseract-ocr +::: + +As of 2021, the data file version is probably `4.00`. + +You can then add new data with either a Dockerfile: + +:::{code} dockerfile +FROM jbarlow83/ocrmypdf:{TAG} + +# Example: add a tessdata_best file +COPY chi_tra_vert.traineddata /usr/share/tesseract-ocr//tessdata/ +::: + +When creating your own image, you should always pin a specific version +of the OCRmyPDF Docker image. This ensures that your image will not +break when a new version of OCRmyPDF is released. + +Alternately, you can copy training data into a Docker container as +follows: + +:::{code} bash +docker cp mycustomtraining.traineddata name_of_container:/usr/share/tesseract-ocr//tessdata/ +::: + +Extending the Docker image +-------------------------- + +You can extend the Docker image with your own customizations, similar to +the way it is extended to add language packs. + +Note that the Docker image is subject to change at any time. For +example, the base image may be updated to a newer version of Ubuntu or +Debian. Such changes will be noted in the release notes but might occur +at minor versions releases, unless the way a \"casual\" user of the +Docker image is affected. + +If you extend the Docker image, you should pin a specific version of the +OCRmyPDF Docker image. + +Executing the test suite +------------------------ + +The OCRmyPDF test suite is installed with image. To run it: + +:::{code} bash +docker run --rm --entrypoint python jbarlow83/ocrmypdf -m pytest +::: + +Accessing the shell +------------------- + +To use the shell in the Docker image: + +:::{code} bash +docker run -it --entrypoint sh jbarlow83/ocrmypdf +::: + +Using the OCRmyPDF web service wrapper +-------------------------------------- + +The OCRmyPDF Docker image includes an example, barebones HTTP web +service. The webservice may be launched as follows: + +:::{code} bash +docker run --entrypoint python -p 5000:5000 jbarlow83/ocrmypdf webservice.py +::: + +We omit the `--rm` parameter so that the container will not be +automatically deleted when it exits. + +This will configure the machine to listen on port 5000. On Linux +machines this is port 5000 of localhost. On macOS or Windows machines +running Docker, this is port 5000 of the virtual machine that runs your +Docker images. You can find its IP address using the command +`docker-machine ip`. + +Unlike command line usage this program will open a socket and wait for +connections. + +:::{warning} +The OCRmyPDF web service wrapper is intended for demonstration or +development. It provides no security, no authentication, no protection +against denial of service attacks, and no load balancing. The default +Flask WSGI server is used, which is intended for development only. The +server is single-threaded and so can respond to only one client at a +time. While running OCR, it cannot respond to any other clients. +::: + +Clients must keep their open connection while waiting for OCR to +complete. This may entail setting a long timeout; this interface is more +useful for internal HTTP API calls. + +Unlike the rest of OCRmyPDF, this web service is licensed under the +Affero GPLv3 (AGPLv3) since Ghostscript is also licensed in this way. + +In addition to the above, please read our +`general remarks on using OCRmyPDF as a service `{.interpreted-text +role="ref"}. diff --git a/docs/docker.rst b/docs/docker.rst deleted file mode 100644 index bcd715ad..00000000 --- a/docs/docker.rst +++ /dev/null @@ -1,254 +0,0 @@ -.. SPDX-FileCopyrightText: 2022 James R. Barlow -.. -.. SPDX-License-Identifier: CC-BY-SA-4.0 - -.. _docker: - -===================== -OCRmyPDF Docker image -===================== - -OCRmyPDF is also available in Docker images that packages recent -versions of all dependencies. - -For users who already have Docker installed this may be an easy and -convenient option. - -On platforms other than Linux, Docker runs in a virtual machine, and so may -be less performant. You may also want to adjust the Docker virtual machine's -memory and CPU allocation. On Linux, the Docker image runs natively and -performance is comparable to a system installation. - -.. _docker-install: - -Installing the Docker image -=========================== - -If you have `Docker `__ installed on your -system, you can install a Docker image of the latest release. - -If you can run this command successfully, your system is ready to download and -execute the image: - -.. code-block:: bash - - docker run hello-world - -.. list-table:: Docker images - :widths: 30 20 50 - :header-rows: 1 - - * - Image - - Architecture - - Description - * - ``jbarlow83/ocrmypdf-alpine`` - - x86_64 and arm64 - - Recommended image, based on Alpine Linux. - * - ``jbarlow83/ocrmypdf-ubuntu`` - - x86_64 and arm64 - - Alternate image, based on Ubuntu. When the Alpine image is considered - stable and available for arm64, this image will be deprecated. - * - ``jbarlow83/ocrmypdf`` - - x86_64 and arm64 - - Currently an alias for ocrmypdf-ubuntu. When the Alpine image is - considered stable and available for arm64, this name point to the - Alpine image. If you don't about the difference between Alpine and - Ubuntu, use this image. - -To install: - -.. code-block:: bash - - docker pull jbarlow83/ocrmypdf-alpine - -The ``ocrmypdf`` image is also available, but is deprecated and will be removed -in the future. - -OCRmyPDF will use all available CPU cores. See the Docker documentation for -`adjusting memory and CPU on other platforms `__ -if you are using Docker on macOS or Windows, where you may need to manually assign -more resources. On Linux, all resources will be available automatically. - -The underlying operating system and other details in Docker images are considered -implementation details and **subject to change at minor releases**. If you are -modifying the image, you should pin the version you intend to use. - -Using the Docker image on the command line -========================================== - -**Unlike typical Docker containers**, in this section the OCRmyPDF Docker -container is ephemeral – it runs for one OCR job and terminates, just like a -command line program. We are using Docker to deliver an application (as opposed -to the more conventional case, where a Docker container runs as a server). -For that reason we usually use the ``--rm`` argument to delete the container -when it exits. - -To start a Docker container (instance of the image): - -.. code-block:: bash - - docker run --rm -i jbarlow83/ocrmypdf-alpine (... all other arguments here...) - - - -For convenience, create a shell alias to hide the Docker command. It is -easier to send the input file as stdin and read the output from -stdout – **this avoids the messy permission issues with Docker entirely**. - -.. code-block:: bash - - alias docker_ocrmypdf='docker run --rm -i jbarlow83/ocrmypdf-alpine' - docker_ocrmypdf --version # runs docker version - docker_ocrmypdf - - output.pdf - -Or in the wonderful `fish shell `__: - -.. code-block:: fish - - alias docker_ocrmypdf 'docker run --rm jbarlow83/ocrmypdf-alpine' - funcsave docker_ocrmypdf - -Alternately, you could mount the local current working directory as a -Docker volume: - -.. code-block:: bash - - alias docker_ocrmypdf='docker run --rm -i --user "$(id -u):$(id -g)" --workdir /data -v "$PWD:/data" jbarlow83/ocrmypdf-alpine' - docker_ocrmypdf /data/input.pdf /data/output.pdf - -Podman -====== - -Especially if you use `Podman `__ (or have SELinux enabled on your -system), you may need to add ``--userns keep-id`` there, otherwise you may get access -errors, because the user is otherwise not mapped to the same UID as on the host: - -.. code-block:: bash - - alias podman_ocrmypdf='podman run --rm -i --user "$(id -u):$(id -g)" --userns keep-id --workdir /data -v "$PWD:/data" ocrmypdf' - podman_ocrmypdf /data/input.pdf /data/output.pdf - -If you use SELinux you may additionally need to add the ``:Z`` `suffix to the volume -`__ -or disable SELinux for the container using ``--security-opt label=disable``, which is -suggested for system files as they should not be re-labelled. Please refer to the „Note” -section at the end of the linked podman documentation for details. - -.. _docker-lang-packs: - -Adding languages to the Docker image -==================================== - -By default the Docker image includes English, German, Simplified Chinese, -French, Portuguese and Spanish, the most popular languages for OCRmyPDF -users based on feedback. You may add other languages by creating a new -Dockerfile based on the public one. - -.. code-block:: dockerfile - - FROM jbarlow83/ocrmypdf - - # Example: add Italian - RUN apt install tesseract-ocr-ita - -To install language packs (training data) such as the -`tessdata_best `_ suite or -custom data, you first need to determine the version of Tesseract data files, which -may differ from the Tesseract program version. Use this command to determine the data -file version: - -.. code-block:: bash - - docker run -i --rm --entrypoint /bin/ls jbarlow83/ocrmypdf /usr/share/tesseract-ocr - -As of 2021, the data file version is probably ``4.00``. - -You can then add new data with either a Dockerfile: - -.. code-block:: dockerfile - - FROM jbarlow83/ocrmypdf:{TAG} - - # Example: add a tessdata_best file - COPY chi_tra_vert.traineddata /usr/share/tesseract-ocr//tessdata/ - -When creating your own image, you should always pin a specific version of the -OCRmyPDF Docker image. This ensures that your image will not break when a new -version of OCRmyPDF is released. - -Alternately, you can copy training data into a Docker container as follows: - -.. code-block:: bash - - docker cp mycustomtraining.traineddata name_of_container:/usr/share/tesseract-ocr//tessdata/ - -Extending the Docker image -========================== - -You can extend the Docker image with your own customizations, similar to the way -it is extended to add language packs. - -Note that the Docker image is subject to change at any time. For example, the base -image may be updated to a newer version of Ubuntu or Debian. Such changes will be -noted in the release notes but might occur at minor versions releases, unless the -way a "casual" user of the Docker image is affected. - -If you extend the Docker image, you should pin a specific version of the OCRmyPDF -Docker image. - -Executing the test suite -======================== - -The OCRmyPDF test suite is installed with image. To run it: - -.. code-block:: bash - - docker run --rm --entrypoint python jbarlow83/ocrmypdf -m pytest - -Accessing the shell -=================== - -To use the shell in the Docker image: - -.. code-block:: bash - - docker run -it --entrypoint sh jbarlow83/ocrmypdf - -Using the OCRmyPDF web service wrapper -====================================== - -The OCRmyPDF Docker image includes an example, barebones HTTP web -service. The webservice may be launched as follows: - -.. code-block:: bash - - docker run --entrypoint python -p 5000:5000 jbarlow83/ocrmypdf webservice.py - -We omit the ``--rm`` parameter so that the container will not be -automatically deleted when it exits. - -This will configure the machine to listen on port 5000. On Linux machines -this is port 5000 of localhost. On macOS or Windows machines running -Docker, this is port 5000 of the virtual machine that runs your Docker -images. You can find its IP address using the command ``docker-machine ip``. - -Unlike command line usage this program will open a socket and wait for -connections. - -.. warning:: - - The OCRmyPDF web service wrapper is intended for demonstration or - development. It provides no security, no authentication, no - protection against denial of service attacks, and no load balancing. - The default Flask WSGI server is used, which is intended for - development only. The server is single-threaded and so can respond to - only one client at a time. While running OCR, it cannot respond to - any other clients. - -Clients must keep their open connection while waiting for OCR to -complete. This may entail setting a long timeout; this interface is more -useful for internal HTTP API calls. - -Unlike the rest of OCRmyPDF, this web service is licensed under the -Affero GPLv3 (AGPLv3) since Ghostscript is also licensed in this way. - -In addition to the above, please read our -:ref:`general remarks on using OCRmyPDF as a service `. diff --git a/pyproject.toml b/pyproject.toml index 000db690..cef89d25 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -48,7 +48,12 @@ Tracker = "https://github.com/ocrmypdf/OCRmyPDF/issues" Changelog = "https://github.com/ocrmypdf/OCRmyPDF/docs/release_notes.rst" [project.optional-dependencies] -docs = ["sphinx", "sphinx-issues", "sphinx-rtd-theme"] +docs = [ + "myst-parser>=4.0.1", + "sphinx", + "sphinx-issues", + "sphinx-rtd-theme", +] extended_test = ["PyMuPDF>=1.19.1"] test = [ "coverage[toml]>=6.2", diff --git a/uv.lock b/uv.lock index f59051c2..dd4cf990 100644 --- a/uv.lock +++ b/uv.lock @@ -1,4 +1,5 @@ version = 1 +revision = 1 requires-python = ">=3.10" resolution-markers = [ "python_full_version < '3.11'", @@ -234,7 +235,7 @@ name = "click" version = "8.1.7" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "colorama", marker = "platform_system == 'Windows'" }, + { name = "colorama", marker = "sys_platform == 'win32'" }, ] sdist = { url = "https://files.pythonhosted.org/packages/96/d3/f04c7bfcf5c1862a2a5b845c6b2b360488cf47af55dfa79c98f6a6bf98b5/click-8.1.7.tar.gz", hash = "sha256:ca9853ad459e787e2192211578cc907e7594e294c7ccc834310722b41b9ca6de", size = 336121 } wheels = [ @@ -537,7 +538,7 @@ name = "ipykernel" version = "6.29.5" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "appnope", marker = "platform_system == 'Darwin'" }, + { name = "appnope", marker = "sys_platform == 'darwin'" }, { name = "comm" }, { name = "debugpy" }, { name = "ipython" }, @@ -823,6 +824,18 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/8f/8e/9ad090d3553c280a8060fbf6e24dc1c0c29704ee7d1c372f0c174aa59285/matplotlib_inline-0.1.7-py3-none-any.whl", hash = "sha256:df192d39a4ff8f21b1895d72e6a13f5fcc5099f00fa84384e0ea28c2cc0653ca", size = 9899 }, ] +[[package]] +name = "mdit-py-plugins" +version = "0.4.2" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "markdown-it-py" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/19/03/a2ecab526543b152300717cf232bb4bb8605b6edb946c845016fa9c9c9fd/mdit_py_plugins-0.4.2.tar.gz", hash = "sha256:5f2cd1fdb606ddf152d37ec30e46101a60512bc0e5fa1a7002c36647b09e26b5", size = 43542 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/a7/f7/7782a043553ee469c1ff49cfa1cdace2d6bf99a1f333cf38676b3ddf30da/mdit_py_plugins-0.4.2-py3-none-any.whl", hash = "sha256:0c673c3f889399a33b95e88d2f0d111b4447bdfea7f237dab2d488f459835636", size = 55316 }, +] + [[package]] name = "mdurl" version = "0.1.2" @@ -875,6 +888,23 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/2a/e2/5d3f6ada4297caebe1a2add3b126fe800c96f56dbe5d1988a2cbe0b267aa/mypy_extensions-1.0.0-py3-none-any.whl", hash = "sha256:4392f6c0eb8a5668a69e23d168ffa70f0be9ccfd32b5cc2d26a34ae5b844552d", size = 4695 }, ] +[[package]] +name = "myst-parser" +version = "4.0.1" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "docutils" }, + { name = "jinja2" }, + { name = "markdown-it-py" }, + { name = "mdit-py-plugins" }, + { name = "pyyaml" }, + { name = "sphinx" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/66/a5/9626ba4f73555b3735ad86247a8077d4603aa8628537687c839ab08bfe44/myst_parser-4.0.1.tar.gz", hash = "sha256:5cfea715e4f3574138aecbf7d54132296bfd72bb614d31168f48c477a830a7c4", size = 93985 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/5f/df/76d0321c3797b54b60fef9ec3bd6f4cfd124b9e422182156a1dd418722cf/myst_parser-4.0.1-py3-none-any.whl", hash = "sha256:9134e88959ec3b5780aedf8a99680ea242869d012e8821db3126d427edc9c95d", size = 84579 }, +] + [[package]] name = "narwhals" version = "1.15.2" @@ -957,7 +987,6 @@ wheels = [ [[package]] name = "ocrmypdf" -version = "16.7.1.dev17+gbfbe571f.d20250104" source = { editable = "." } dependencies = [ { name = "deprecation" }, @@ -973,6 +1002,7 @@ dependencies = [ [package.optional-dependencies] docs = [ + { name = "myst-parser" }, { name = "sphinx" }, { name = "sphinx-issues" }, { name = "sphinx-rtd-theme" }, @@ -997,7 +1027,6 @@ watcher = [ { name = "watchdog" }, ] webservice = [ - { name = "port-for" }, { name = "streamlit" }, ] @@ -1016,13 +1045,13 @@ requires-dist = [ { name = "deprecation", specifier = ">=2.1.0" }, { name = "hypothesis", marker = "extra == 'test'", specifier = ">=6.36.0" }, { name = "img2pdf", specifier = ">=0.5" }, + { name = "myst-parser", marker = "extra == 'docs'", specifier = ">=4.0.1" }, { name = "packaging", specifier = ">=20" }, { name = "pdfminer-six", specifier = ">=20220319" }, { name = "pi-heif" }, { name = "pikepdf", specifier = ">=8.10.1" }, { name = "pillow", specifier = ">=10.0.1" }, { name = "pluggy", specifier = ">=1" }, - { name = "port-for", marker = "extra == 'webservice'", specifier = ">=0.7.4" }, { name = "pymupdf", marker = "extra == 'extended-test'", specifier = ">=1.19.1" }, { name = "pytest", marker = "extra == 'test'", specifier = ">=6.2.5" }, { name = "pytest-cov", marker = "extra == 'test'", specifier = ">=3.0.0" }, @@ -1040,6 +1069,7 @@ requires-dist = [ { name = "types-pillow", marker = "extra == 'test'" }, { name = "watchdog", marker = "extra == 'watcher'", specifier = ">=1.0.2" }, ] +provides-extras = ["docs", "extended-test", "test", "watcher", "webservice"] [package.metadata.requires-dev] dev = [ @@ -1316,15 +1346,6 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/88/5f/e351af9a41f866ac3f1fac4ca0613908d9a41741cfcf2228f4ad853b697d/pluggy-1.5.0-py3-none-any.whl", hash = "sha256:44e1ad92c8ca002de6377e165f3e0f1be63266ab4d554740532335b9d75ea669", size = 20556 }, ] -[[package]] -name = "port-for" -version = "0.7.4" -source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/f6/84/ad5114c85217426d7a5170a74a6f9d6b724df117c2f3b75e41fc9d6c6811/port_for-0.7.4.tar.gz", hash = "sha256:fc7713e7b22f89442f335ce12536653656e8f35146739eccaeff43d28436028d", size = 25077 } -wheels = [ - { url = "https://files.pythonhosted.org/packages/9c/a2/579dcefbb0285b31f8d65b537f8a9932ed51319e0a3694e01b5bbc271f92/port_for-0.7.4-py3-none-any.whl", hash = "sha256:08404aa072651a53dcefe8d7a598ee8a1dca320d9ac44ac464da16ccf2a02c4a", size = 21369 }, -] - [[package]] name = "prompt-toolkit" version = "3.0.48" @@ -1576,6 +1597,50 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/26/df/2b63e3e4f2df0224f8aaf6d131f54fe4e8c96400eb9df563e2aae2e1a1f9/pywin32-308-cp313-cp313-win_arm64.whl", hash = "sha256:ef313c46d4c18dfb82a2431e3051ac8f112ccee1a34f29c263c583c568db63cd", size = 7974986 }, ] +[[package]] +name = "pyyaml" +version = "6.0.2" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/54/ed/79a089b6be93607fa5cdaedf301d7dfb23af5f25c398d5ead2525b063e17/pyyaml-6.0.2.tar.gz", hash = "sha256:d584d9ec91ad65861cc08d42e834324ef890a082e591037abe114850ff7bbc3e", size = 130631 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/9b/95/a3fac87cb7158e231b5a6012e438c647e1a87f09f8e0d123acec8ab8bf71/PyYAML-6.0.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:0a9a2848a5b7feac301353437eb7d5957887edbf81d56e903999a75a3d743086", size = 184199 }, + { url = "https://files.pythonhosted.org/packages/c7/7a/68bd47624dab8fd4afbfd3c48e3b79efe09098ae941de5b58abcbadff5cb/PyYAML-6.0.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:29717114e51c84ddfba879543fb232a6ed60086602313ca38cce623c1d62cfbf", size = 171758 }, + { url = "https://files.pythonhosted.org/packages/49/ee/14c54df452143b9ee9f0f29074d7ca5516a36edb0b4cc40c3f280131656f/PyYAML-6.0.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8824b5a04a04a047e72eea5cec3bc266db09e35de6bdfe34c9436ac5ee27d237", size = 718463 }, + { url = "https://files.pythonhosted.org/packages/4d/61/de363a97476e766574650d742205be468921a7b532aa2499fcd886b62530/PyYAML-6.0.2-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:7c36280e6fb8385e520936c3cb3b8042851904eba0e58d277dca80a5cfed590b", size = 719280 }, + { url = "https://files.pythonhosted.org/packages/6b/4e/1523cb902fd98355e2e9ea5e5eb237cbc5f3ad5f3075fa65087aa0ecb669/PyYAML-6.0.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ec031d5d2feb36d1d1a24380e4db6d43695f3748343d99434e6f5f9156aaa2ed", size = 751239 }, + { url = "https://files.pythonhosted.org/packages/b7/33/5504b3a9a4464893c32f118a9cc045190a91637b119a9c881da1cf6b7a72/PyYAML-6.0.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:936d68689298c36b53b29f23c6dbb74de12b4ac12ca6cfe0e047bedceea56180", size = 695802 }, + { url = "https://files.pythonhosted.org/packages/5c/20/8347dcabd41ef3a3cdc4f7b7a2aff3d06598c8779faa189cdbf878b626a4/PyYAML-6.0.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:23502f431948090f597378482b4812b0caae32c22213aecf3b55325e049a6c68", size = 720527 }, + { url = "https://files.pythonhosted.org/packages/be/aa/5afe99233fb360d0ff37377145a949ae258aaab831bde4792b32650a4378/PyYAML-6.0.2-cp310-cp310-win32.whl", hash = "sha256:2e99c6826ffa974fe6e27cdb5ed0021786b03fc98e5ee3c5bfe1fd5015f42b99", size = 144052 }, + { url = "https://files.pythonhosted.org/packages/b5/84/0fa4b06f6d6c958d207620fc60005e241ecedceee58931bb20138e1e5776/PyYAML-6.0.2-cp310-cp310-win_amd64.whl", hash = "sha256:a4d3091415f010369ae4ed1fc6b79def9416358877534caf6a0fdd2146c87a3e", size = 161774 }, + { url = "https://files.pythonhosted.org/packages/f8/aa/7af4e81f7acba21a4c6be026da38fd2b872ca46226673c89a758ebdc4fd2/PyYAML-6.0.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:cc1c1159b3d456576af7a3e4d1ba7e6924cb39de8f67111c735f6fc832082774", size = 184612 }, + { url = "https://files.pythonhosted.org/packages/8b/62/b9faa998fd185f65c1371643678e4d58254add437edb764a08c5a98fb986/PyYAML-6.0.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:1e2120ef853f59c7419231f3bf4e7021f1b936f6ebd222406c3b60212205d2ee", size = 172040 }, + { url = "https://files.pythonhosted.org/packages/ad/0c/c804f5f922a9a6563bab712d8dcc70251e8af811fce4524d57c2c0fd49a4/PyYAML-6.0.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5d225db5a45f21e78dd9358e58a98702a0302f2659a3c6cd320564b75b86f47c", size = 736829 }, + { url = "https://files.pythonhosted.org/packages/51/16/6af8d6a6b210c8e54f1406a6b9481febf9c64a3109c541567e35a49aa2e7/PyYAML-6.0.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5ac9328ec4831237bec75defaf839f7d4564be1e6b25ac710bd1a96321cc8317", size = 764167 }, + { url = "https://files.pythonhosted.org/packages/75/e4/2c27590dfc9992f73aabbeb9241ae20220bd9452df27483b6e56d3975cc5/PyYAML-6.0.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3ad2a3decf9aaba3d29c8f537ac4b243e36bef957511b4766cb0057d32b0be85", size = 762952 }, + { url = "https://files.pythonhosted.org/packages/9b/97/ecc1abf4a823f5ac61941a9c00fe501b02ac3ab0e373c3857f7d4b83e2b6/PyYAML-6.0.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:ff3824dc5261f50c9b0dfb3be22b4567a6f938ccce4587b38952d85fd9e9afe4", size = 735301 }, + { url = "https://files.pythonhosted.org/packages/45/73/0f49dacd6e82c9430e46f4a027baa4ca205e8b0a9dce1397f44edc23559d/PyYAML-6.0.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:797b4f722ffa07cc8d62053e4cff1486fa6dc094105d13fea7b1de7d8bf71c9e", size = 756638 }, + { url = "https://files.pythonhosted.org/packages/22/5f/956f0f9fc65223a58fbc14459bf34b4cc48dec52e00535c79b8db361aabd/PyYAML-6.0.2-cp311-cp311-win32.whl", hash = "sha256:11d8f3dd2b9c1207dcaf2ee0bbbfd5991f571186ec9cc78427ba5bd32afae4b5", size = 143850 }, + { url = "https://files.pythonhosted.org/packages/ed/23/8da0bbe2ab9dcdd11f4f4557ccaf95c10b9811b13ecced089d43ce59c3c8/PyYAML-6.0.2-cp311-cp311-win_amd64.whl", hash = "sha256:e10ce637b18caea04431ce14fabcf5c64a1c61ec9c56b071a4b7ca131ca52d44", size = 161980 }, + { url = "https://files.pythonhosted.org/packages/86/0c/c581167fc46d6d6d7ddcfb8c843a4de25bdd27e4466938109ca68492292c/PyYAML-6.0.2-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:c70c95198c015b85feafc136515252a261a84561b7b1d51e3384e0655ddf25ab", size = 183873 }, + { url = "https://files.pythonhosted.org/packages/a8/0c/38374f5bb272c051e2a69281d71cba6fdb983413e6758b84482905e29a5d/PyYAML-6.0.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:ce826d6ef20b1bc864f0a68340c8b3287705cae2f8b4b1d932177dcc76721725", size = 173302 }, + { url = "https://files.pythonhosted.org/packages/c3/93/9916574aa8c00aa06bbac729972eb1071d002b8e158bd0e83a3b9a20a1f7/PyYAML-6.0.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1f71ea527786de97d1a0cc0eacd1defc0985dcf6b3f17bb77dcfc8c34bec4dc5", size = 739154 }, + { url = "https://files.pythonhosted.org/packages/95/0f/b8938f1cbd09739c6da569d172531567dbcc9789e0029aa070856f123984/PyYAML-6.0.2-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9b22676e8097e9e22e36d6b7bda33190d0d400f345f23d4065d48f4ca7ae0425", size = 766223 }, + { url = "https://files.pythonhosted.org/packages/b9/2b/614b4752f2e127db5cc206abc23a8c19678e92b23c3db30fc86ab731d3bd/PyYAML-6.0.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:80bab7bfc629882493af4aa31a4cfa43a4c57c83813253626916b8c7ada83476", size = 767542 }, + { url = "https://files.pythonhosted.org/packages/d4/00/dd137d5bcc7efea1836d6264f049359861cf548469d18da90cd8216cf05f/PyYAML-6.0.2-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:0833f8694549e586547b576dcfaba4a6b55b9e96098b36cdc7ebefe667dfed48", size = 731164 }, + { url = "https://files.pythonhosted.org/packages/c9/1f/4f998c900485e5c0ef43838363ba4a9723ac0ad73a9dc42068b12aaba4e4/PyYAML-6.0.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8b9c7197f7cb2738065c481a0461e50ad02f18c78cd75775628afb4d7137fb3b", size = 756611 }, + { url = "https://files.pythonhosted.org/packages/df/d1/f5a275fdb252768b7a11ec63585bc38d0e87c9e05668a139fea92b80634c/PyYAML-6.0.2-cp312-cp312-win32.whl", hash = "sha256:ef6107725bd54b262d6dedcc2af448a266975032bc85ef0172c5f059da6325b4", size = 140591 }, + { url = "https://files.pythonhosted.org/packages/0c/e8/4f648c598b17c3d06e8753d7d13d57542b30d56e6c2dedf9c331ae56312e/PyYAML-6.0.2-cp312-cp312-win_amd64.whl", hash = "sha256:7e7401d0de89a9a855c839bc697c079a4af81cf878373abd7dc625847d25cbd8", size = 156338 }, + { url = "https://files.pythonhosted.org/packages/ef/e3/3af305b830494fa85d95f6d95ef7fa73f2ee1cc8ef5b495c7c3269fb835f/PyYAML-6.0.2-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:efdca5630322a10774e8e98e1af481aad470dd62c3170801852d752aa7a783ba", size = 181309 }, + { url = "https://files.pythonhosted.org/packages/45/9f/3b1c20a0b7a3200524eb0076cc027a970d320bd3a6592873c85c92a08731/PyYAML-6.0.2-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:50187695423ffe49e2deacb8cd10510bc361faac997de9efef88badc3bb9e2d1", size = 171679 }, + { url = "https://files.pythonhosted.org/packages/7c/9a/337322f27005c33bcb656c655fa78325b730324c78620e8328ae28b64d0c/PyYAML-6.0.2-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0ffe8360bab4910ef1b9e87fb812d8bc0a308b0d0eef8c8f44e0254ab3b07133", size = 733428 }, + { url = "https://files.pythonhosted.org/packages/a3/69/864fbe19e6c18ea3cc196cbe5d392175b4cf3d5d0ac1403ec3f2d237ebb5/PyYAML-6.0.2-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:17e311b6c678207928d649faa7cb0d7b4c26a0ba73d41e99c4fff6b6c3276484", size = 763361 }, + { url = "https://files.pythonhosted.org/packages/04/24/b7721e4845c2f162d26f50521b825fb061bc0a5afcf9a386840f23ea19fa/PyYAML-6.0.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:70b189594dbe54f75ab3a1acec5f1e3faa7e8cf2f1e08d9b561cb41b845f69d5", size = 759523 }, + { url = "https://files.pythonhosted.org/packages/2b/b2/e3234f59ba06559c6ff63c4e10baea10e5e7df868092bf9ab40e5b9c56b6/PyYAML-6.0.2-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:41e4e3953a79407c794916fa277a82531dd93aad34e29c2a514c2c0c5fe971cc", size = 726660 }, + { url = "https://files.pythonhosted.org/packages/fe/0f/25911a9f080464c59fab9027482f822b86bf0608957a5fcc6eaac85aa515/PyYAML-6.0.2-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:68ccc6023a3400877818152ad9a1033e3db8625d899c72eacb5a668902e4d652", size = 751597 }, + { url = "https://files.pythonhosted.org/packages/14/0d/e2c3b43bbce3cf6bd97c840b46088a3031085179e596d4929729d8d68270/PyYAML-6.0.2-cp313-cp313-win32.whl", hash = "sha256:bc2fa7c6b47d6bc618dd7fb02ef6fdedb1090ec036abab80d4681424b84c1183", size = 140527 }, + { url = "https://files.pythonhosted.org/packages/fa/de/02b54f42487e3d3c6efb3f89428677074ca7bf43aae402517bc7cca949f3/PyYAML-6.0.2-cp313-cp313-win_amd64.whl", hash = "sha256:8388ee1976c416731879ac16da0aff3f63b286ffdd57cdeb95f3f2e085687563", size = 156446 }, +] + [[package]] name = "pyzmq" version = "26.2.0" @@ -1991,7 +2056,7 @@ dependencies = [ { name = "toml" }, { name = "tornado" }, { name = "typing-extensions" }, - { name = "watchdog", marker = "platform_system != 'Darwin'" }, + { name = "watchdog", marker = "sys_platform != 'darwin'" }, ] sdist = { url = "https://files.pythonhosted.org/packages/78/33/14b5ac0369ecf0af675911e5e84b934e6fcc2cec850857d2390eb373b0a6/streamlit-1.41.1.tar.gz", hash = "sha256:6626d32b098ba1458b71eebdd634c62af2dd876380e59c4b6a1e828a39d62d69", size = 8712473 } wheels = [ From 3b9367fc69f563050550aa78a39caae47a4d5d3e Mon Sep 17 00:00:00 2001 From: "James R. Barlow" Date: Thu, 17 Apr 2025 02:27:59 -0700 Subject: [PATCH 2/5] Continuing rst -> md --- docs/cloud.md | 84 ++++++++++++++++++ docs/cloud.rst | 92 -------------------- docs/design_notes.md | 30 +++++++ docs/design_notes.rst | 32 ------- docs/errors.md | 51 +++++++++++ docs/errors.rst | 57 ------------ docs/jbig2.md | 74 ++++++++++++++++ docs/jbig2.rst | 81 ----------------- docs/maintainers.md | 71 +++++++++++++++ docs/maintainers.rst | 77 ---------------- docs/optimizer.md | 100 +++++++++++++++++++++ docs/optimizer.rst | 100 --------------------- docs/{pdfsecurity.rst => pdfsecurity.md} | 106 ++++++++++------------- 13 files changed, 457 insertions(+), 498 deletions(-) create mode 100644 docs/cloud.md delete mode 100644 docs/cloud.rst create mode 100644 docs/design_notes.md delete mode 100644 docs/design_notes.rst create mode 100644 docs/errors.md delete mode 100644 docs/errors.rst create mode 100644 docs/jbig2.md delete mode 100644 docs/jbig2.rst create mode 100644 docs/maintainers.md delete mode 100644 docs/maintainers.rst create mode 100644 docs/optimizer.md delete mode 100644 docs/optimizer.rst rename docs/{pdfsecurity.rst => pdfsecurity.md} (53%) diff --git a/docs/cloud.md b/docs/cloud.md new file mode 100644 index 00000000..520df176 --- /dev/null +++ b/docs/cloud.md @@ -0,0 +1,84 @@ +% SPDX-FileCopyrightText: 2025 James R. Barlow +% SPDX-License-Identifier: CC-BY-SA-4.0 + +{#ocr-service} + +# Online deployments + +OCRmyPDF is designed to be used as a command line tool, but it can be +used in a web service. This document describes some considerations for +doing so. + +A basic web service implementation is provided in the source code +repository, as `misc/webservice.py`. It is only demonstration quality +and is not intended for production use. + +OCRmyPDF is not designed for use as a public web service where a +malicious user could upload a chosen PDF. In particular, it is not +necessarily secure against PDF malware or PDFs that cause denial of +service. For further discussino of security, see +[security](security). + +OCRmyPDF relies on Ghostscript, and therefore, if deployed online one +should be prepared to comply with Ghostscript\'s Affero GPL license, and +any other licenses. + +Setting aside these concerns, a side effect of OCRmyPDF is that it may +incidentally sanitize PDFs containing certain types of malware. It +repairs the PDF with pikepdf/libqpdf, which could correct malformed PDF +structures that are part of an attack. When PDF/A output is selected +(the default), the input PDF is partially reconstructed by Ghostscript. +When `--force-ocr` is used, all pages are rasterized and reconverted to +PDF, which could remove malware in embedded images. + +## Limiting CPU usage + +OCRmyPDF will attempt to use all available CPUs and storage, so +executing `nice ocrmypdf` or limiting the number of jobs with the +`--jobs` argument may ensure the server remains responsive. Another +option would be to run OCRmyPDF jobs inside a Docker container, a +virtual machine, or a cloud instance, which can impose its own limits on +CPU usage and be terminated \"from orbit\" if it fails to complete. + +## Temporary storage requirements + +OCRmyPDF will use a large amount of temporary storage for its work, +proportional to the total number of pixels needed to rasterize the PDF. +The raster image of a 8.5×11\" color page at 300 DPI takes 25 MB +uncompressed; OCRmyPDF saves its intermediates as PNG, but that still +means it requires about 9 MB per intermediate based on average +compression ratios. Multiple intermediates per page are also required, +depending on the command line given. A rule of thumb would be to allow +100 MB of temporary storage per page in a file -- meaning that a small +cloud servers or small VM partitions should be provisioned with plenty +of extra space, if say, a 500 page file might be sent. + +To change the temporary directory, see [tmpdir](advanced#tmpdir). + +On Amazon Web Services or other cloud vendors, consider setting your +temporary directory to [empheral +storage](https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/InstanceStorage.html). + +## Timeouts + +To prevent excessively long OCR jobs consider setting +`--tesseract-timeout` and/or `--skip-big` arguments. `--skip-big` is +particularly helpful if your PDFs include documents such as reports on +standard page sizes with large images attached - often large images are +not worth OCR\'ing anyway. + +## Document management systems + +If you are looking for a full document management system, consider +[paperless-ngx](https://github.com/paperless-ngx/paperless-ngx), which +is a web application that uses OCRmyPDF to automatically OCR and archive +documents. + +## Commercial OCR alternatives + +The author also provides professional services that include OCR and +building databases around PDFs, and is happy to provide consultation. + +Abbyy Cloud OCR is viable commercial alternative with a web services +API. Amazon Textract, Google Cloud Vision, and Microsoft Azure Computer +Vision provide advanced OCR but have less PDF rendering capability. diff --git a/docs/cloud.rst b/docs/cloud.rst deleted file mode 100644 index 2798c672..00000000 --- a/docs/cloud.rst +++ /dev/null @@ -1,92 +0,0 @@ -.. SPDX-FileCopyrightText: 2023 James R. Barlow -.. -.. SPDX-License-Identifier: CC-BY-SA-4.0 - - -.. _ocr-service: - -================== -Online deployments -================== - -OCRmyPDF is designed to be used as a command line tool, but it can be -used in a web service. This document describes some considerations for -doing so. - -A basic web service implementation is provided in the source code -repository, as ``misc/webservice.py``. It is only demonstration quality -and is not intended for production use. - -OCRmyPDF is not designed for use as a public web service where a -malicious user could upload a chosen PDF. In particular, it is not -necessarily secure against PDF malware or PDFs that cause denial of -service. For further discussino of security, see :ref:`security`. - -OCRmyPDF relies on Ghostscript, and therefore, if deployed -online one should be prepared to comply with Ghostscript's Affero GPL -license, and any other licenses. - -Setting aside these concerns, a side effect of OCRmyPDF is that it may -incidentally sanitize PDFs containing certain types of malware. It -repairs the PDF with pikepdf/libqpdf, which could correct malformed PDF -structures that are part of an attack. When PDF/A output is selected -(the default), the input PDF is partially reconstructed by Ghostscript. -When ``--force-ocr`` is used, all pages are rasterized and reconverted -to PDF, which could remove malware in embedded images. - -Limiting CPU usage ------------------- - -OCRmyPDF will attempt to use all available CPUs and storage, so -executing ``nice ocrmypdf`` or limiting the number of jobs with the -``--jobs`` argument may ensure the server remains responsive. Another option -would be to run OCRmyPDF jobs inside a Docker container, a virtual machine, -or a cloud instance, which can impose its own limits on CPU usage and be -terminated "from orbit" if it fails to complete. - -Temporary storage requirements ------------------------------- - -OCRmyPDF will use a large amount of temporary storage for its work, -proportional to the total number of pixels needed to rasterize the PDF. -The raster image of a 8.5×11" color page at 300 DPI takes 25 MB -uncompressed; OCRmyPDF saves its intermediates as PNG, but that still -means it requires about 9 MB per intermediate based on average -compression ratios. Multiple intermediates per page are also required, -depending on the command line given. A rule of thumb would be to allow -100 MB of temporary storage per page in a file – meaning that a small -cloud servers or small VM partitions should be provisioned with plenty -of extra space, if say, a 500 page file might be sent. - -To change the temporary directory, see :ref:`tmpdir`. - -On Amazon Web Services or other cloud vendors, consider setting your -temporary directory to `empheral -storage `__. - -Timeouts --------- - -To prevent excessively long OCR jobs consider setting -``--tesseract-timeout`` and/or ``--skip-big`` arguments. ``--skip-big`` -is particularly helpful if your PDFs include documents such as reports -on standard page sizes with large images attached - often large images -are not worth OCR'ing anyway. - -Document management systems ---------------------------- - -If you are looking for a full document management system, consider -`paperless-ngx `__, -which is a web application that uses OCRmyPDF to automatically OCR and -archive documents. - -Commercial OCR alternatives ---------------------------- - -The author also provides professional services that include OCR and -building databases around PDFs, and is happy to provide consultation. - -Abbyy Cloud OCR is viable commercial alternative with a web services -API. Amazon Textract, Google Cloud Vision, and Microsoft Azure -Computer Vision provide advanced OCR but have less PDF rendering capability. \ No newline at end of file diff --git a/docs/design_notes.md b/docs/design_notes.md new file mode 100644 index 00000000..4d8b761a --- /dev/null +++ b/docs/design_notes.md @@ -0,0 +1,30 @@ +% SPDX-FileCopyrightText: 2023 James R. Barlow +% SPDX-License-Identifier: CC-BY-SA-4.0 + +# Design notes + +## Why doesn\'t OCRmyPDF use PyTesseract? + +PyTesseract is a Python wrapper around the Tesseract OCR engine. When +OCRmyPDF was first written, PyTesseract used ABI bindings to call the +Tesseract library. This was not a good fit for OCRmyPDF because ABI +bindings can be fragile. + +PyTesseract has since evolved calling the Tesseract executable, +abandoning the ABI approach and using the CLI instead, just like +OCRmyPDF does. If it were written from scratch today, OCRmyPDF might use +PyTesseract. + +PyTesseract has more features don\'t particularly need PDF output, but +less features than OCRmyPDF\'s API for creating PDFs. + +## What is `executor()`? + +OCRmyPDF uses a custom concurrent executor which can support either +threads or processes with the same interface. This is useful because +OCRmyPDF can use either threads or processes to parallelize work, +whichever is more appropriate for the task at hand. + +The interface is currently private and subject to change. In particular, +if experiments with asyncio and anyio are successful, the interface will +change. diff --git a/docs/design_notes.rst b/docs/design_notes.rst deleted file mode 100644 index d4dbd307..00000000 --- a/docs/design_notes.rst +++ /dev/null @@ -1,32 +0,0 @@ -.. SPDX-FileCopyrightText: 2023 James R. Barlow -.. SPDX-License-Identifier: CC-BY-SA-4.0 - -============ -Design notes -============ - -Why doesn't OCRmyPDF use PyTesseract? -===================================== - -PyTesseract is a Python wrapper around the Tesseract OCR engine. When OCRmyPDF was -first written, PyTesseract used ABI bindings to call the Tesseract library. This -was not a good fit for OCRmyPDF because ABI bindings can be fragile. - -PyTesseract has since evolved calling the Tesseract executable, abandoning the ABI -approach and using the CLI instead, just like OCRmyPDF does. If it were written from -scratch today, OCRmyPDF might use PyTesseract. - -PyTesseract has more features don't particularly need PDF output, but less features -than OCRmyPDF's API for creating PDFs. - -What is ``executor()``? -======================= - -OCRmyPDF uses a custom concurrent executor which can support either threads or -processes with the same interface. This is useful because OCRmyPDF can use -either threads or processes to parallelize work, whichever is more appropriate -for the task at hand. - -The interface is currently private and subject to change. In particular, if -experiments with asyncio and anyio are successful, the interface will change. - diff --git a/docs/errors.md b/docs/errors.md new file mode 100644 index 00000000..01b51b6c --- /dev/null +++ b/docs/errors.md @@ -0,0 +1,51 @@ +% SPDX-FileCopyrightText: 2022 James R. Barlow +% SPDX-License-Identifier: CC-BY-SA-4.0 + +# Common error messages + +## Page already has text + +:::{code} +ERROR - 1: page already has text! – aborting (use --force-ocr to force OCR) +::: + +You ran ocrmypdf on a file that already contains printable text or a +hidden OCR text layer (it can\'t quite tell the difference). You +probably don\'t want to do this, because the file is already searchable. + +As the error message suggests, your options are: + +- `ocrmypdf --force-ocr` to + `rasterize `{.interpreted-text role="ref"} all vector + content and run OCR on the images. This is useful if a previous OCR + program failed, or if the document contains a text watermark. +- `ocrmypdf --skip-text` to skip OCR and other processing on any pages + that contain text. Text pages will be copied into the output PDF + without modification. +- `ocrmypdf --redo-ocr` to scan the file for any existing OCR + (non-printing text), remove it, and do OCR again. This is one way to + take advantage of improvements in OCR accuracy. Printable vector + text is excluded from OCR, so this can be used on files that contain + a mix of digital and scanned files. + +## Input file \'filename\' is not a valid PDF + +OCRmyPDF checks files with pikepdf, a library that in turn uses libqpdf +to fixes errors in PDFs, before it tries to work on them. In most cases +this happens because the PDF is corrupt and truncated (incomplete file +copying) and not much can be done. + +You can try rewriting the file with Ghostscript: + +:::{code} bash +gs -o output.pdf -dSAFER -sDEVICE=pdfwrite input.pdf +::: + +`pdftk` can also rewrite PDFs: + +:::{code} bash +pdftk input.pdf cat output output.pdf +::: + +Sometimes Acrobat can repair PDFs with its [Preflight +tool](https://helpx.adobe.com/acrobat/using/correcting-problem-areas-preflight-tool.html). diff --git a/docs/errors.rst b/docs/errors.rst deleted file mode 100644 index d6017f10..00000000 --- a/docs/errors.rst +++ /dev/null @@ -1,57 +0,0 @@ -.. SPDX-FileCopyrightText: 2022 James R. Barlow -.. -.. SPDX-License-Identifier: CC-BY-SA-4.0 - -===================== -Common error messages -===================== - -Page already has text -===================== - -.. code-block:: - - ERROR - 1: page already has text! – aborting (use --force-ocr to force OCR) - -You ran ocrmypdf on a file that already contains printable text or a -hidden OCR text layer (it can't quite tell the difference). You probably -don't want to do this, because the file is already searchable. - -As the error message suggests, your options are: - -- ``ocrmypdf --force-ocr`` to :ref:`rasterize ` all - vector content and run OCR on the images. This is useful if a - previous OCR program failed, or if the document contains a text - watermark. -- ``ocrmypdf --skip-text`` to skip OCR and other processing on any - pages that contain text. Text pages will be copied into the output - PDF without modification. -- ``ocrmypdf --redo-ocr`` to scan the file for any existing OCR - (non-printing text), remove it, and do OCR again. This is one way - to take advantage of improvements in OCR accuracy. Printable vector - text is excluded from OCR, so this can be used on files that contain - a mix of digital and scanned files. - - -Input file 'filename' is not a valid PDF -======================================== - -OCRmyPDF checks files with pikepdf, a library that in turn uses libqpdf to fixes -errors in PDFs, before it tries to work on them. In most cases this happens -because the PDF is corrupt and truncated (incomplete file copying) and not much -can be done. - -You can try rewriting the file with Ghostscript: - -.. code-block:: bash - - gs -o output.pdf -dSAFER -sDEVICE=pdfwrite input.pdf - -``pdftk`` can also rewrite PDFs: - -.. code-block:: bash - - pdftk input.pdf cat output output.pdf - -Sometimes Acrobat can repair PDFs with its `Preflight -tool `__. diff --git a/docs/jbig2.md b/docs/jbig2.md new file mode 100644 index 00000000..4af41e7b --- /dev/null +++ b/docs/jbig2.md @@ -0,0 +1,74 @@ +% SPDX-FileCopyrightText: 2022 James R. Barlow +% SPDX-License-Identifier: CC-BY-SA-4.0 + +{#jbig2} + +# Installing the JBIG2 encoder + +Most Linux distributions do not include a JBIG2 encoder since JBIG2 +encoding was patented for a long time. All known JBIG2 US patents have +expired as of 2017, but it is possible that unknown patents exist. + +JBIG2 encoding is recommended for OCRmyPDF and is used to losslessly +create smaller PDFs. If JBIG2 encoding is not available, lower quality +CCITT encoding will be used for monochrome images. + +JBIG2 decoding is not patented and is performed automatically by most +PDF viewers. It is widely supported and has been part of the PDF +specification since 2001. + +JBIG encoding is automatically provided by these OCRmyPDF packages: - +Docker image (both Ubuntu and Alpine) - Snap package - ArchLinux AUR +package - Alpine Linux package - Homebrew on macOS + +For all other platforms, you would need to build the JBIG2 encoder from +source: + +:::{code} bash +git clone https://github.com/agl/jbig2enc +cd jbig2enc +./autogen.sh +./configure && make +[sudo] make install +::: + +Dependencies include libtoolize and libleptonica, which on Ubuntu +systems are packaged as libtool and libleptonica-dev. On Fedora (35) +they are packaged as libtool and leptonica-devel. For this to work, +please make sure to install `autotools`, `automake`, `libtool` and +`leptonica` first if not already installed. + +:::{code} bash +[sudo] apt install autotools-dev automake libtool libleptonica-dev +::: + +{#jbig2-lossy} + +## Lossy mode JBIG2 + +OCRmyPDF provides lossy mode JBIG2 as an advanced and potentially +dangerous feature. Users should [review the technical concerns with +JBIG2 in lossy mode](https://en.wikipedia.org/wiki/JBIG2#Disadvantages) +and decide if this feature is acceptable for their use case. In general, +this mode should not be used for archival purposes, should not be used +when the original document is not available or will be destroyed, and +should not be used when numbers present in the document are important, +because there is a risk of 6/8 and 8/6 substitution errors. + +JBIG2 lossy mode does achieve higher compression ratios than any other +monochrome (bitonal) compression technology; for large text documents +the savings are considerable. JBIG2 lossless still gives great +compression ratios and is a major improvement over the older CCITT G4 +standard. + +To turn on JBIG2 lossy mode, add the argument `--jbig2-lossy`. +`--optimize {1,2,3}` are necessary for the argument to take effect also +required. Also, a JBIG2 encoder must be installed as described in the +previous section. + +You can adjust the threshold for JBIG2 compression with the +`--jbig2-threshold`. The default is 0.85, meaning that if two symbols +are 85% similar, they will be compressed together. + +*Due to an oversight, ocrmypdf v7.0 and v7.1 used lossy mode by +default.* diff --git a/docs/jbig2.rst b/docs/jbig2.rst deleted file mode 100644 index 41bdee87..00000000 --- a/docs/jbig2.rst +++ /dev/null @@ -1,81 +0,0 @@ -.. SPDX-FileCopyrightText: 2022 James R. Barlow -.. -.. SPDX-License-Identifier: CC-BY-SA-4.0 - -.. _jbig2: - -============================ -Installing the JBIG2 encoder -============================ - -Most Linux distributions do not include a JBIG2 encoder since JBIG2 -encoding was patented for a long time. All known JBIG2 US patents have -expired as of 2017, but it is possible that unknown patents exist. - -JBIG2 encoding is recommended for OCRmyPDF and is used to losslessly -create smaller PDFs. If JBIG2 encoding is not available, lower quality -CCITT encoding will be used for monochrome images. - -JBIG2 decoding is not patented and is performed automatically by most -PDF viewers. It is widely supported and has been part of the PDF -specification since 2001. - -JBIG encoding is automatically provided by these OCRmyPDF packages: -- Docker image (both Ubuntu and Alpine) -- Snap package -- ArchLinux AUR package -- Alpine Linux package -- Homebrew on macOS - -For all other platforms, you would need to build the JBIG2 encoder from source: - -.. code-block:: bash - - git clone https://github.com/agl/jbig2enc - cd jbig2enc - ./autogen.sh - ./configure && make - [sudo] make install - -Dependencies include libtoolize and libleptonica, which on Ubuntu systems -are packaged as libtool and libleptonica-dev. On Fedora (35) they are packaged -as libtool and leptonica-devel. For this to work, please make sure to install -``autotools``, ``automake``, ``libtool`` and ``leptonica`` first if not already -installed. - -.. code-block:: bash - - [sudo] apt install autotools-dev automake libtool libleptonica-dev - -.. _jbig2-lossy: - -Lossy mode JBIG2 -================ - -OCRmyPDF provides lossy mode JBIG2 as an advanced and potentially dangerous -feature. Users should -`review the technical concerns with JBIG2 in lossy -mode `__ -and decide if this feature is acceptable for their use case. In general, -this mode should not be used for archival purposes, should not be used when -the original document is not available or will be destroyed, and should -not be used when numbers present in the document are important, because -there is a risk of 6/8 and 8/6 substitution errors. - -JBIG2 lossy mode does achieve higher compression ratios than any other -monochrome (bitonal) compression technology; for large text documents -the savings are considerable. JBIG2 lossless still gives great -compression ratios and is a major improvement over the older CCITT G4 -standard. - -To turn on JBIG2 lossy mode, add the argument ``--jbig2-lossy``. -``--optimize {1,2,3}`` are necessary for the argument to take effect -also required. Also, a JBIG2 encoder must be installed as described in -the previous section. - -You can adjust the threshold for JBIG2 compression with the -``--jbig2-threshold``. The default is 0.85, meaning that if two symbols -are 85% similar, they will be compressed together. - -*Due to an oversight, ocrmypdf v7.0 and v7.1 used lossy mode by -default.* diff --git a/docs/maintainers.md b/docs/maintainers.md new file mode 100644 index 00000000..0a2b3fd4 --- /dev/null +++ b/docs/maintainers.md @@ -0,0 +1,71 @@ +% SPDX-FileCopyrightText: 2022 James R. Barlow +% SPDX-License-Identifier: CC-BY-SA-4.0 + +# Maintainer notes + +This is for those who package OCRmyPDF for downstream use. (Thank you +for your hard work.) + +## Known ports/packagers + +OCRmyPDF has been ported to many platforms already. If you are +interesting in porting to a new platform, check with +[Repology](https://repology.org/projects/?search=ocrmypdf) to see the +status of that platform. + +### Make sure you can package pikepdf + +pikepdf, created by the same author, is a mixed Python and C++14 package +with much stiffer build requirements. If you want to use OCRmyPDF on +some novel platform or distribution, first make sure you can package +pikepdf. + +### Non-Python dependencies + +Note that we have non-Python dependencies. In particular, OCRmyPDF +requires Ghostscript and Tesseract OCR to be installed and needs to be +able to locate their binaries on the system PATH. On Windows, OCRmyPDF +will also check the registry for their locations. + +Tesseract OCR relies on SIMD for performance and only has proper support +for this on ARM and x86\_64. Performance may be poor on other processor +architectures. + +### Versioning scheme + +OCRmyPDF uses hatch-vcs for versioning, which derives the version from +Git as a single source of truth. This may be unsuitable for some +distributions, e.g. to indicate that your distribution modifies OCRmyPDF +in some way. + +You can patch the `__version__` variable in `src/ocrmypdf/_version.py` +if necessary, or set the environment variable +`SETUPTOOLS_SCM_PRETEND_VERSION` to the required version, if you need to +override versioning for some reason. + +### jbig2enc + +OCRmyPDF will use jbig2enc, a JBIG2 encoder, if one can be found. Some +distributions have shied away from packaging JBIG2 because it contains +patented algorithms, but all patents have expired since 2017. If +possible, consider packaging it too to improve OCRmyPDF\'s compression. + +### Command line completions + +Please ensure that command line completions are installed, as described +in the installation documentation. + +### 32-bit Linux support + +If you maintain a Linux distribution that supports 32-bit x86 or ARM, +OCRmyPDF should continue to work as long as all of its dependencies +continue to be available in 32-bit form. Please note we do not test on +32-bit platforms. + +### HEIF/HEIC + +OCRmyPDF defaults to installing the pi-heif PyPI package, which supports +converting HEIF (High Efficiency Image File Format) images to PDF from +the command line. If your distribution does not have this library +available, you can exclude it and OCRmyPDF will gracefully degrade +automatically, losing only support for this feature. diff --git a/docs/maintainers.rst b/docs/maintainers.rst deleted file mode 100644 index 33c77cb8..00000000 --- a/docs/maintainers.rst +++ /dev/null @@ -1,77 +0,0 @@ -.. SPDX-FileCopyrightText: 2022 James R. Barlow -.. -.. SPDX-License-Identifier: CC-BY-SA-4.0 - -================ -Maintainer notes -================ - -This is for those who package OCRmyPDF for downstream use. (Thank you -for your hard work.) - -Known ports/packagers -===================== - -OCRmyPDF has been ported to many platforms already. If you are interesting in -porting to a new platform, check with -`Repology `__ to see the status -of that platform. - -Make sure you can package pikepdf ---------------------------------- - -pikepdf, created by the same author, is a mixed Python and C++14 package with -much stiffer build requirements. If you want to use OCRmyPDF on some novel platform -or distribution, first make sure you can package pikepdf. - -Non-Python dependencies ------------------------ - -Note that we have non-Python dependencies. In particular, OCRmyPDF requires -Ghostscript and Tesseract OCR to be installed and needs to be able to locate their -binaries on the system PATH. On Windows, OCRmyPDF will also check the registry -for their locations. - -Tesseract OCR relies on SIMD for performance and only has proper support for this -on ARM and x86_64. Performance may be poor on other processor architectures. - -Versioning scheme ------------------ - -OCRmyPDF uses hatch-vcs for versioning, which derives the version from -Git as a single source of truth. This may be unsuitable for some distributions, e.g. -to indicate that your distribution modifies OCRmyPDF in some way. - -You can patch the ``__version__`` variable in ``src/ocrmypdf/_version.py`` if -necessary, or set the environment variable ``SETUPTOOLS_SCM_PRETEND_VERSION`` -to the required version, if you need to override versioning for some reason. - -jbig2enc --------- - -OCRmyPDF will use jbig2enc, a JBIG2 encoder, if one can be found. Some distributions -have shied away from packaging JBIG2 because it contains patented algorithms, but -all patents have expired since 2017. If possible, consider packaging it too to -improve OCRmyPDF's compression. - -Command line completions ------------------------- - -Please ensure that command line completions are installed, as described in the -installation documentation. - -32-bit Linux support --------------------- - -If you maintain a Linux distribution that supports 32-bit x86 or ARM, OCRmyPDF -should continue to work as long as all of its dependencies continue to be -available in 32-bit form. Please note we do not test on 32-bit platforms. - -HEIF/HEIC ---------- - -OCRmyPDF defaults to installing the pi-heif PyPI package, which supports converting -HEIF (High Efficiency Image File Format) images to PDF from the command line. -If your distribution does not have this library available, you can exclude it and -OCRmyPDF will gracefully degrade automatically, losing only support for this -feature. \ No newline at end of file diff --git a/docs/optimizer.md b/docs/optimizer.md new file mode 100644 index 00000000..aeda78a8 --- /dev/null +++ b/docs/optimizer.md @@ -0,0 +1,100 @@ +% SPDX-FileCopyrightText: 2022 James R. Barlow +% SPDX-License-Identifier: CC-BY-SA-4.0 + +# PDF optimization + +OCRmyPDF includes an image-oriented PDF optimizer. By default, the +optimizer runs with safe settings with the goal of improving compression +at no loss of quality. At higher optimization levels, lossy +optimizations may be applied and tuned. Optimization occurs after OCR, +and only if OCR succeeded. It does not perform other possible +optimizations such as deduplicating resources, consolidating fonts, +simplifying vector drawings, or anything of that nature. + +:::{list-table} OCRmyPDF optimization settings +--- +widths: 33 6 60 +header-rows: 1 +--- + +* - Optimization level + - Shorthand + - Description +* - ``--optimize 0`` + - ``-O0`` + - Disable most optimizations. +* - ``--optimize 1`` (default) + - ``-O1`` + - Safe and lossless optimizations. +* - ``--optimize 2`` + - ``-O2`` + - Safe and lossy optimizations. +* - ``--optimize 3`` + - ``-O3`` + - Aggressive lossy optimizations. +::: + +The exact type of optimizations performed will vary over time, and +depend on the availability of third-party tools. + +Despite optimizations, OCRmyPDF might still increase the overall file +size, since it must embed information about the recognized text, and +depending on the settings chosen, may not be able to represent the +output file as compactly as the input file. + +## Optimizations that always occurs + +OCRmyPDF will automatically replace obsolete or inferior compression +schemes such as RLE or LZW with superior schemes such as Deflate, and +convert monochrome images to CCITT G4. Since this is lossless, it always +occurs and there is no way to disable it. Other non-image compressed +objects are compressed as well. + +## Fast web view + +OCRmyPDF automatically optimizes PDFs for \"fast web view\" in Adobe +Acrobat\'s parlance, or equivalently, linearizes PDFs so that the +resources they reference are presented in the order a viewer needs them +for sequential display. This reduces the latency of viewing a PDF both +online and from local storage, in exchange for a slight increase in file +size. + +To disable this optimization and all others, use +`ocrmypdf --optimize 0 ...` or the shorthand `-O0`. + +Adobe Acrobat might not report the file as being \"fast web view\". + +## Lossless optimizations + +At optimization level `-O1` (the default), OCRmyPDF will also attempt +lossless image optimization. + +If a JBIG2 encoder is available, then monochrome images will be +converted to JBIG2, with the potential for huge savings on large black +and white images, since JBIG2 is far more efficient than any other +monochrome (bi-level) compression. (All known US patents related to +JBIG2 have probably expired, but it remains the responsibility of the +user to supply a JBIG2 encoder such as +[jbig2enc](https://github.com/agl/jbig2enc). OCRmyPDF does not implement +JBIG2 encoding on its own.) + +OCRmyPDF currently does not attempt to recompress losslessly compressed +objects more aggressively. + +## Lossy optimizations + +At optimization level `-O2` and `-O3`, OCRmyPDF will some attempt lossy +image optimization. + +If `pngquant` is installed, OCRmyPDF will use it to perform quantize +paletted images to reduce their size. + +The quality of JPEGs may be lowered, on the assumption that a lower +quality image may be suitable for storage after OCR. + +It is not possible to optimize all image types. Uncommon image types may +be skipped by the optimizer. + +OCRmyPDF provides `lossy mode JBIG2 `{.interpreted-text +role="ref"} as an advanced feature that additional requires the argument +`--jbig2-lossy`. diff --git a/docs/optimizer.rst b/docs/optimizer.rst deleted file mode 100644 index 8d298c85..00000000 --- a/docs/optimizer.rst +++ /dev/null @@ -1,100 +0,0 @@ -.. SPDX-FileCopyrightText: 2022 James R. Barlow -.. -.. SPDX-License-Identifier: CC-BY-SA-4.0 - -================ -PDF optimization -================ - -OCRmyPDF includes an image-oriented PDF optimizer. By default, the optimizer -runs with safe settings with the goal of improving compression at no loss of -quality. At higher optimization levels, lossy optimizations may be applied and -tuned. Optimization occurs after OCR, and only if OCR succeeded. It does not -perform other possible optimizations such as deduplicating resources, -consolidating fonts, simplifying vector drawings, or anything of that nature. - -.. list-table:: Title - :widths: 33 6 60 - :header-rows: 1 - - * - Optimization level - - Shorthand - - Description - * - ``--optimize 0`` - - ``-O0`` - - Disable most optimizations. - * - ``--optimize 1`` (default) - - ``-O1`` - - Safe and lossless optimizations. - * - ``--optimize 2`` - - ``-O2`` - - Safe and lossy optimizations. - * - ``--optimize 3`` - - ``-O3`` - - Aggressive lossy optimizations. - -The exact type of optimizations performed will vary over time, and depend on -the availability of third-party tools. - -Despite optimizations, OCRmyPDF might still increase the overall file size, -since it must embed information about the recognized text, and depending on the -settings chosen, may not be able to represent the output file as compactly as -the input file. - -Optimizations that always occurs -================================ - -OCRmyPDF will automatically replace obsolete or inferior compression schemes -such as RLE or LZW with superior schemes such as Deflate, and convert -monochrome images to CCITT G4. Since this is lossless, it always occurs and there -is no way to disable it. Other non-image compressed objects are compressed as -well. - -Fast web view -============= - -OCRmyPDF automatically optimizes PDFs for "fast web view" in Adobe Acrobat's -parlance, or equivalently, linearizes PDFs so that the resources they reference -are presented in the order a viewer needs them for sequential display. This -reduces the latency of viewing a PDF both online and from local storage, in -exchange for a slight increase in file size. - -To disable this optimization and all others, use ``ocrmypdf --optimize 0 ...`` -or the shorthand ``-O0``. - -Adobe Acrobat might not report the file as being "fast web view". - -Lossless optimizations -====================== - -At optimization level ``-O1`` (the default), OCRmyPDF will also attempt lossless -image optimization. - -If a JBIG2 encoder is available, then monochrome images will be converted to -JBIG2, with the potential for huge savings on large black and white images, -since JBIG2 is far more efficient than any other monochrome (bi-level) -compression. (All known US patents related to JBIG2 have probably expired, but -it remains the responsibility of the user to supply a JBIG2 encoder such as -`jbig2enc `__. OCRmyPDF does not implement -JBIG2 encoding on its own.) - -OCRmyPDF currently does not attempt to recompress losslessly compressed objects -more aggressively. - -Lossy optimizations -=================== - -At optimization level ``-O2`` and ``-O3``, OCRmyPDF will some attempt lossy -image optimization. - -If ``pngquant`` is installed, OCRmyPDF will use it to perform quantize paletted -images to reduce their size. - -The quality of JPEGs may be lowered, on the assumption that a lower quality -image may be suitable for storage after OCR. - -It is not possible to optimize all image types. Uncommon image types may be -skipped by the optimizer. - -OCRmyPDF provides :ref:`lossy mode JBIG2 ` as an advanced feature -that additional requires the argument ``--jbig2-lossy``. diff --git a/docs/pdfsecurity.rst b/docs/pdfsecurity.md similarity index 53% rename from docs/pdfsecurity.rst rename to docs/pdfsecurity.md index ef4056e9..73eb628e 100644 --- a/docs/pdfsecurity.rst +++ b/docs/pdfsecurity.md @@ -1,15 +1,9 @@ -.. SPDX-FileCopyrightText: 2022 James R. Barlow -.. -.. SPDX-License-Identifier: CC-BY-SA-4.0 +{#security} -.. _security: +# PDF security issues -=================== -PDF security issues -=================== - - OCRmyPDF should only be used on PDFs you trust. It is not designed to - protect you against malware. +> OCRmyPDF should only be used on PDFs you trust. It is not designed to +> protect you against malware. Recognizing that many users have an interest in handling PDFs and applying OCR to PDFs they did not generate themselves, this article @@ -18,89 +12,84 @@ themselves. The disclaimer applies: this software has no warranties of any kind. -PDFs may contain malware -======================== +## PDFs may contain malware PDF is a rich, complex file format. The official PDF 1.7 specification, ISO 32000:2008, is hundreds of pages long and references several annexes each of which are similar in length. PDFs can contain video, audio, XML, JavaScript and other programming, and forms. In some cases, they can -open internet connections to pre-selected URLs. All of these are possible -attack vectors. +open internet connections to pre-selected URLs. All of these are +possible attack vectors. -In short, PDFs `may contain -viruses `__. +In short, PDFs [may contain +viruses](https://security.stackexchange.com/questions/64052/can-a-pdf-file-contain-a-virus). If you do not trust a PDF or its source, do not open it or use OCRmyPDF on it. Consider using a Docker container or virtual machine to isolate an untrusted PDF from your system. -How OCRmyPDF processes PDFs -=========================== +## How OCRmyPDF processes PDFs OCRmyPDF must open and interpret your PDF in order to insert an OCR layer. First, it runs all PDFs through -`pikepdf `__, a library based on -`QPDF `__, a program that repairs PDFs -with syntax errors. This is done because, in the author's experience, a +[pikepdf](https://github.com/pikepdf/pikepdf), a library based on +[QPDF](https://github.com/qpdf/qpdf), a program that repairs PDFs with +syntax errors. This is done because, in the author\'s experience, a significant number of PDFs in the wild, especially those created by scanners, are not well-formed files. QPDF makes it more likely that OCRmyPDF will succeed, but offers no security guarantees. QPDF is also used to split the PDF into single page PDFs. Finally, OCRmyPDF rasterizes each page of the PDF using -`Ghostscript `__ in ``-dSAFER`` mode. +[Ghostscript](http://ghostscript.com/) in `-dSAFER` mode. Depending on the options specified, OCRmyPDF may graft the OCR layer -into the existing PDF or it may essentially reconstruct ("re-fry") a +into the existing PDF or it may essentially reconstruct (\"re-fry\") a visually identical PDF that may be quite different at the binary level. That said, OCRmyPDF is not a tool designed for sanitizing PDFs. -Password protected PDFs -======================= +## Password protected PDFs Password protected PDFs usually have two passwords, and owner and user password. When the user password is set to empty, PDF readers will open -the file automatically and mark it as "(SECURED)". Password security can -also request certain restrictions on the PDF, but anyone can remove these -restrictions if they have either the owner *or* user password. Passwords -mainly present a barrier for casual users. +the file automatically and mark it as \"(SECURED)\". Password security +can also request certain restrictions on the PDF, but anyone can remove +these restrictions if they have either the owner *or* user password. +Passwords mainly present a barrier for casual users. OCRmyPDF cannot remove passwords from PDFs. If you want to remove a -password from a PDF, you must use other software, such as ``qpdf``. +password from a PDF, you must use other software, such as `qpdf`. -If the owner and user password are set, a -password is required for ``qpdf``. If only the owner password is set, then the -password can be stripped, even if one does not have the owner password. To -remove the password from a using QPDF, use: +If the owner and user password are set, a password is required for +`qpdf`. If only the owner password is set, then the password can be +stripped, even if one does not have the owner password. To remove the +password from a using QPDF, use: -.. code-block:: bash - - qpdf --decrypt --password='abc123' input.pdf no_password.pdf +:::{code} bash +qpdf --decrypt --password='abc123' input.pdf no_password.pdf +::: Then you can run OCRmyPDF on the file. -In its default mode, OCRmyPDF generates PDF/A. Passwords may not be set on PDF/A -documents. If you want to set a password on the output PDF, you must -specify ``--output-type pdf``. +In its default mode, OCRmyPDF generates PDF/A. Passwords may not be set +on PDF/A documents. If you want to set a password on the output PDF, you +must specify `--output-type pdf`. -Signature images -================ +## Signature images -Many programs exist which are capable of inserting an image of someone's -signature. On its own, this offers no security guarantees. It is trivial -to remove the signature image and apply it to other files. This practice -offers no real security. +Many programs exist which are capable of inserting an image of +someone\'s signature. On its own, this offers no security guarantees. It +is trivial to remove the signature image and apply it to other files. +This practice offers no real security. -Digital signatures -================== +## Digital signatures Important documents can be digitally signed and certified to attest to their authorship, approval or execution of a legal agreement. OCRmyPDF will detect signed PDFs and will not modify them, unless the -``--invalidate-digital-signatures`` option is used, which will -invalidate any signatures. (The signature may still be present in the PDF -if opened, but PDF readers will not validate it.) +`--invalidate-digital-signatures` option is used, which will invalidate +any signatures. (The signature may still be present in the PDF if +opened, but PDF readers will not validate it.) A digital signature adds a cryptographic hash of the document to the document, so tamper protection is provided. That also precludes OCRmyPDF @@ -108,20 +97,19 @@ from modifying the document and preserving the signature. Digital signatures are not the same as a signature image. A digital signature is a cryptographic hash of the document that is encrypted with -the author's private key. The signature is decrypted with the author's +the author\'s private key. The signature is decrypted with the author\'s public key. The public key is usually distributed by a certificate authority. The signature is then verified by the PDF reader. If the document is modified, the signature will be invalidated. -Certificate-encrypted PDFs -========================== +## Certificate-encrypted PDFs PDFs can be encrypted with a certificate. This is a more secure form of encryption than a password. The certificate is usually issued by a -certificate authority. A certificate is used to encrypt the document using -the public key for the benefit of a specific recipient who possesses -the private key. +certificate authority. A certificate is used to encrypt the document +using the public key for the benefit of a specific recipient who +possesses the private key. OCRmyPDF cannot open certificate-encrypted PDFs. If you have the -certificate, you can use other PDF software, such as Acrobat, to -decrypt the PDF. \ No newline at end of file +certificate, you can use other PDF software, such as Acrobat, to decrypt +the PDF. From d1a45e4abc0189852e532d096bd732d9e53065eb Mon Sep 17 00:00:00 2001 From: "James R. Barlow" Date: Thu, 17 Apr 2025 15:03:21 -0700 Subject: [PATCH 3/5] Convert remaining rst -> md --- docs/advanced.md | 461 +++ docs/advanced.rst | 486 ---- docs/{api.rst => api.md} | 103 +- docs/{apiref.rst => apiref.md} | 44 +- docs/conf.py | 2 +- docs/cookbook.md | 106 +- docs/index.md | 57 + docs/index.rst | 56 - docs/installation.md | 730 +++++ docs/installation.rst | 740 ----- docs/{introduction.rst => introduction.md} | 143 +- docs/languages.md | 129 + docs/languages.rst | 141 - docs/performance.md | 24 + docs/performance.rst | 26 - docs/{plugins.rst => plugins.md} | 190 +- docs/release_notes.md | 2840 ++++++++++++++++++ docs/release_notes.rst | 3043 -------------------- 18 files changed, 4538 insertions(+), 4783 deletions(-) create mode 100644 docs/advanced.md delete mode 100644 docs/advanced.rst rename docs/{api.rst => api.md} (51%) rename docs/{apiref.rst => apiref.md} (59%) create mode 100644 docs/index.md delete mode 100644 docs/index.rst create mode 100644 docs/installation.md delete mode 100644 docs/installation.rst rename docs/{introduction.rst => introduction.md} (68%) create mode 100644 docs/languages.md delete mode 100644 docs/languages.rst create mode 100644 docs/performance.md delete mode 100644 docs/performance.rst rename docs/{plugins.rst => plugins.md} (60%) create mode 100644 docs/release_notes.md delete mode 100644 docs/release_notes.rst diff --git a/docs/advanced.md b/docs/advanced.md new file mode 100644 index 00000000..505067b5 --- /dev/null +++ b/docs/advanced.md @@ -0,0 +1,461 @@ +% SPDX-FileCopyrightText: 2022 James R. Barlow +% SPDX-License-Identifier: CC-BY-SA-4.0 + +# Advanced features + +## Control of unpaper + +OCRmyPDF uses `unpaper` to provide the implementation of the +`--clean` and `--clean-final` arguments. +[unpaper](https://github.com/Flameeyes/unpaper/blob/main/doc/basic-concepts.md) +provides a variety of image processing filters to improve images. + +By default, OCRmyPDF uses only `unpaper` arguments that were found to +be safe to use on almost all files without having to inspect every page +of the file afterwards. This is particularly true when only `--clean` +is used, since that instructs OCRmyPDF to only clean the image before +OCR and not the final image. + +However, if you wish to use the more aggressive options in `unpaper`, +you may use `--unpaper-args '...'` to override the OCRmyPDF's defaults +and forward other arguments to unpaper. This option will forward +arguments to `unpaper` without any knowledge of what that program +considers to be valid arguments. The string of arguments must be quoted +as shown in the examples below. No filename arguments may be included. +OCRmyPDF will assume it can append input and output filename of +intermediate images to the `--unpaper-args` string. + +In this example, we tell `unpaper` to expect two pages of text on a +sheet (image), such as occurs when two facing pages of a book are +scanned. `unpaper` uses this information to deskew each independently +and clean up the margins of both. + +```bash +ocrmypdf --clean --clean-final --unpaper-args '--layout double' input.pdf output.pdf +ocrmypdf --clean --clean-final --unpaper-args '--layout double --no-noisefilter' input.pdf output.pdf +``` + +:::{warning} +Some `unpaper` features will reposition text within the image. +`--clean-final` is recommended to avoid this issue. +::: + +:::{warning} +Some `unpaper` features cause multiple input or output files to be +consumed or produced. OCRmyPDF requires `unpaper` to consume one +file and produce one file; errors will result if this assumption is not +met. +::: + +:::{note} +`unpaper` uses uncompressed PBM/PGM/PPM files for its intermediate +files. For large images or documents, it can take a lot of temporary +disk space. +::: + +## Control of OCR options + +OCRmyPDF provides many features to control the behavior of the OCR +engine, Tesseract. + +### When OCR is skipped + +If a page in a PDF seems to have text, by default OCRmyPDF will exit +without modifying the PDF. This is to ensure that PDFs that were +previously OCRed or were "born digital" rather than scanned are not +processed. + +If `--skip-text` is issued, then no image processing or OCR will be +performed on pages that already have text. The page will be copied to +the output. This may be useful for documents that contain both "born +digital" and scanned content, or to use OCRmyPDF to normalize and +convert to PDF/A regardless of their contents. + +If `--redo-ocr` is issued, then a detailed text analysis is performed. +Text is categorized as either visible or invisible. Invisible text (OCR) +is stripped out. Then an image of each page is created with visible text +masked out. The page image is sent for OCR, and any additional text is +inserted as OCR. If a file contains a mix of text and bitmap images that +contain text, OCRmyPDF will locate the additional text in images without +disrupting the existing text. Some PDF OCR solutions render text as +technically printable or visible in some way, perhaps by drawing it and +then painting over it. OCRmyPDF cannot distinguish this type of OCR +text from real text, so it will not be "redone". + +If `--force-ocr` is issued, then all pages will be rasterized to +images, discarding any hidden OCR text, rasterizing any printable +text, and flattening form fields or interactive objects into their visual +representation. This is useful for redoing OCR, for fixing OCR text +with a damaged character map (text is selectable but not searchable), +and destroying redacted information. + +### Time and image size limits + +By default, OCRmyPDF permits tesseract to run for three minutes (180 +seconds) per page. This is usually more than enough time to find all +text on a reasonably sized page with modern hardware. + +If a page is skipped, it will be inserted without OCR. If preprocessing +was requested, the preprocessed image layer will be inserted. + +If you want to adjust the amount of time spent on OCR, change +`--tesseract-timeout`. You can also automatically skip images that +exceed a certain number of megapixels with `--skip-big`. (A 300 DPI, +8.5×11" page image is 8.4 megapixels.) + +```bash +# Allow 300 seconds for OCR; skip any page larger than 50 megapixels +ocrmypdf --tesseract-timeout 300 --skip-big 50 bigfile.pdf output.pdf +``` + +### OCR for huge images + +Tesseract has internal limits on the size +of images it will process. By default, +`--tesseract-downsample-large-images` is enabled, and OCRmyPDF will +downsample images to fit Tesseract limits. (The limits are usually encountered +only for scanned images of oversized media, such as large maps or blueprints exceeding +110 cm or 43 inches in either dimension, and at high DPI.) This feature can disabled +using `--no-tesseract-downsample-large-images`. + +`--tesseract-downsample-above Npixels` adjusts the threshold at which images +will be downsampled. By default, only images that exceed any of Tesseract's +internal limits are downsampled (32767 pixels on either dimension). + +You will also need to set `--tesseract-timeout` high enough to allow +for processing. + +Only the image sent for OCR is downsampled. The original image is +preserved. + +```bash +# Allow 600 seconds for OCR on huge images +ocrmypdf --tesseract-timeout 600 \ + --tesseract-downsample-large-images \ + bigfile.pdf output.pdf + +# Downsample images above 5000 pixels on the longest dimension to +# 5000 pixels +ocrmypdf --tesseract-timeout 120 \ + --tesseract-downsample-large-images \ + --tesseract-downsample-above 5000 \ + bigfile.pdf output_downsampled_ocr.pdf +``` + +### Overriding default tesseract + +OCRmyPDF checks the system `PATH` for the `tesseract` binary. + +Some relevant environment variables that influence Tesseract's behavior +include: + +```{eval-rst} +.. envvar:: TESSDATA_PREFIX + + Overrides the path to Tesseract's data files. This can allow + simultaneous installation of the "best" and "fast" training data + sets. OCRmyPDF does not manage this environment variable. +``` + +```{eval-rst} +.. envvar:: OMP_THREAD_LIMIT + + Controls the number of threads Tesseract will use. OCRmyPDF will + manage this environment variable if it is not already set. +``` + +For example, if you have a development build of Tesseract don't wish to +use the system installation, you can launch OCRmyPDF as follows: + +```bash +env \ + PATH=/home/user/src/tesseract/api:$PATH \ + TESSDATA_PREFIX=/home/user/src/tesseract \ + ocrmypdf input.pdf output.pdf +``` + +In this example `TESSDATA_PREFIX` is required to redirect Tesseract to +an alternate folder for its "tessdata" files. + +### Overriding other support programs + +In addition to tesseract, OCRmyPDF uses the following external binaries: + +- `gs` (Ghostscript) +- `unpaper` +- `pngquant` +- `jbig2` + +In each case OCRmyPDF will search the `PATH` environment variable to +locate the binaries. By modifying the `PATH` environment variable, you +can override the binaries that OCRmyPDF uses. + +### Changing Tesseract configuration variables + +You can override Tesseract's default [control +parameters](https://tesseract-ocr.github.io/tessdoc/tess3/ControlParams.html) +with a configuration file. + +As an example, this configuration will disable Tesseract's dictionary +for current language. Normally the dictionary is helpful for +interpolating words that are unclear, but it may interfere with OCR if +the document does not contain many words (for example, a list of part +numbers). + +Create a file named "no-dict.cfg" with these contents: + +``` +load_system_dawg 0 +language_model_penalty_non_dict_word 0 +language_model_penalty_non_freq_dict_word 0 +``` + +then run ocrmypdf as follows (along with any other desired arguments): + +```bash +ocrmypdf --tesseract-config no-dict.cfg input.pdf output.pdf +``` + +:::{warning} +Some combinations of control parameters will break Tesseract or break +assumptions that OCRmyPDF makes about Tesseract's output. +::: + +### Changing page segmentation mode + +The directive `--tesseract-pagesegmode Nmode` forwards the desired page segmentation +mode to Tesseract OCR. The default is 3. + +Page segmentation can improve OCR results when you know that a PDF ought to be +analyzed a particular way, such as PDFs whose pages contain only a single line of +text. For the vast majority of users, changing the page segmentation mode will only +make things worse. + +As of June 2024, the Tesseract page segmentation modes are: + +| ID | Description | +| --- | --------------------------------------------------------------------------------------------- | +| 0 | Orientation and script detection (OSD) only. | +| 1 | Automatic page segmentation with OSD. | +| 2 | Automatic page segmentation, but no OSD, or OCR. (not implemented) | +| 3 | Fully automatic page segmentation, but no OSD. (Default) | +| 4 | Assume a single column of text of variable sizes. | +| 5 | Assume a single uniform block of vertically aligned text. | +| 6 | Assume a single uniform block of text. | +| 7 | Treat the image as a single text line. | +| 8 | Treat the image as a single word. | +| 9 | Treat the image as a single word in a circle. | +| 10 | Treat the image as a single character. | +| 11 | Sparse text. Find as much text as possible in no particular order. | +| 12 | Sparse text with OSD. | +| 13 | Raw line. Treat the image as a single text line, bypassing hacks that are Tesseract-specific. | + +Modes 0, 1, 2, and 12 (all of those that enable orientation and script detection) +are not compatible with OCRmyPDF, which performs OSD in a separate step from OCR. +Their use may interfere with `--rotate-pages` and other features. + +It is currently not possible to use advanced Tesseract OCR features, such as creating +OCR information, when using Tesseract through OCRmyPDF. + +## Changing the PDF renderer + +rasterizing + +: Converting a PDF to an image for display. + +rendering + +: Creating a new PDF from other data (such as an existing PDF). + +OCRmyPDF has these PDF renderers: `sandwich` and `hocr`. The +renderer may be selected using `--pdf-renderer`. The default is +`auto` which lets OCRmyPDF select the renderer to use. Currently, +`auto` always selects `hocr`. + +### The `hocr` renderer + +:::{versionchanged} 16.0.0 +::: + +In both renderers, a text-only layer is rendered and sandwiched (overlaid) +on to either the original PDF page, or newly rasterized version of the +original PDF page (when `--force-ocr` is used). In this way, loss +of PDF information is generally avoided. (You may need to disable PDF/A +conversion and optimization to eliminate all lossy transformations.) + +The current approach used by the new hOCR renderer is a re-implementation +of Tesseract's PDF renderer, using the same Glyphless font and general +ideas, but fixing many technical issues that impeded it. The new hocr +provides better text placement accuracy, avoids issues with word +segmentation, and provides better positioning of skewed text. + +Using the experimental API, it is also possible to edit the OCR output +from Tesseract, using any tool that is capable of editing hOCR files. + +Older versions of this renderer did not support non-Latin languages, but +it is now universal. + +### The `sandwich` renderer + +The `sandwich` renderer uses Tesseract's text-only PDF feature, +which produces a PDF page that lays out the OCR in invisible text. + +Currently some problematic PDF viewers like Mozilla PDF.js and macOS +Preview have problems with segmenting its text output, and +mightrunseveralwordstogether. It also does not implement right to left +fonts (Arabic, Hebrew, Persian). The output of this renderer cannot +be edited. The sandwich renderer is retained for testing. + +When image preprocessing features like `--deskew` are used, the +original PDF will be rendered as a full page and the OCR layer will be +placed on top. + +## Rendering and rasterizing options + +:::{versionadded} 14.3.0 +::: + +The `--continue-on-soft-render-error` option allows OCRmyPDF to +proceed if a page cannot be rasterized/rendered. This is useful if you are +trying to get the best possible OCR from a PDF that is not well-formed, +and you are willing to accept some pages that may not visually match the +input, and that may not OCR well. + +## Color conversion strategy + +:::{versionadded} 15.0.0 +::: + +OCRmyPDF uses Ghostscript to convert PDF to PDF/A. In some cases, this +conversion requires color conversion. The default strategy is to convert +using the `LeaveColorUnchanged` strategy, which preserves the original +color space wherever possible (some rare color spaces might still be +converted). + +Usually document scanners produce PDFs in the sRGB color space, and do +not need to be converted, so the default strategy is appropriate. + +Suppose that you have a document that was prepared for professional +printing in a Separation or CMYK color space, and text was converted to +curves. In this case, you may want to use a different color conversion +strategy. The `--color-conversion-strategy` option allows you to select a +different strategy, such as `RGB`. + +## Return code policy + +OCRmyPDF writes all messages to `stderr`. `stdout` is reserved for +piping output files. `stdin` is reserved for piping input files. + +The return codes generated by the OCRmyPDF are considered part of the +stable user interface. They may be imported from +`ocrmypdf.exceptions`. + +```{eval-rst} +.. list-table:: Return codes + :widths: 5 35 60 + :header-rows: 1 + + * - Code + - Name + - Interpretation + * - 0 + - ``ExitCode.ok`` + - Everything worked as expected. + * - 1 + - ``ExitCode.bad_args`` + - Invalid arguments, exited with an error. + * - 2 + - ``ExitCode.input_file`` + - The input file does not seem to be a valid PDF. + * - 3 + - ``ExitCode.missing_dependency`` + - An external program required by OCRmyPDF is missing. + * - 4 + - ``ExitCode.invalid_output_pdf`` + - An output file was created, but it does not seem to be a valid PDF. The file will be available. + * - 5 + - ``ExitCode.file_access_error`` + - The user running OCRmyPDF does not have sufficient permissions to read the input file and write the output file. + * - 6 + - ``ExitCode.already_done_ocr`` + - The file already appears to contain text so it may not need OCR. See output message. + * - 7 + - ``ExitCode.child_process_error`` + - An error occurred in an external program (child process) and OCRmyPDF cannot continue. + * - 8 + - ``ExitCode.encrypted_pdf`` + - The input PDF is encrypted. OCRmyPDF does not read encrypted PDFs. Use another program such as ``qpdf`` to remove encryption. + * - 9 + - ``ExitCode.invalid_config`` + - A custom configuration file was forwarded to Tesseract using ``--tesseract-config``, and Tesseract rejected this file. + * - 10 + - ``ExitCode.pdfa_conversion_failed`` + - A valid PDF was created, PDF/A conversion failed. The file will be available. + * - 15 + - ``ExitCode.other_error`` + - Some other error occurred. + * - 130 + - ``ExitCode.ctrl_c`` + - The program was interrupted by pressing Ctrl+C. + +``` + +(tmpdir)= + +## Changing temporary storage location + +OCRmyPDF generates many temporary files during processing. + +To change where temporary files are stored, change the `TMPDIR` +environment variable for ocrmypdf's environment. (Python's +`tempfile.gettempdir()` returns the root directory in which temporary +files will be stored.) For example, one could redirect `TMPDIR` to a +large RAM disk to avoid wear on HDD/SSD and potentially improve +performance. + +On Windows, the `TEMP` environment variable is used instead. + +## Debugging the intermediate files + +OCRmyPDF normally saves its intermediate results to a temporary folder +and deletes this folder when it exits, whether it succeeded or failed. + +If the `--keep-temporary-files` (`-k`) argument is issued on the +command line, OCRmyPDF will keep the temporary folder and print the location, +whether it succeeded or failed. An example message is: + +```none +Temporary working files retained at: +/tmp/ocrmypdf.io.u20wpz07 +``` + +When OCRmyPDF is launched as a snap, this corresponds to the snap filesystem, for instance: + +> /tmp/snap-private-tmp/snap.ocrmypdf/tmp/ocrmypdf.io.u20wpz07 + +The organization of this folder is an implementation detail and subject +to change between releases. However the general organization is that +working files on a per page basis have the page number as a prefix +(starting with page 1), an infix indicates the processing stage, and a +suffix indicates the file type. Some important files include: + +- `_rasterize.png` - what the input page looks like +- `_ocr.png` - the file that is sent to Tesseract for OCR; depending + on arguments this may differ from the presentation image +- `_pp_deskew.png` - the image, after deskewing +- `_pp_clean.png` - the image, after cleaning with unpaper +- `_ocr_hocr.pdf` - the OCR file; appears as a blank page with invisible + text embedded +- `_ocr_hocr.txt` - the OCR text (not necessarily all text on the page, + if the page is mixed format) +- `fix_docinfo.pdf` - a temporary file created to fix the PDF DocumentInfo + data structure +- `graft_layers.pdf` - the rendered PDF with OCR layers grafted on +- `pdfa.pdf` - `graft_layers.pdf` after conversion to PDF/A +- `pdfa.ps` - a PostScript file used by Ghostscript for PDF/A conversion +- `optimize.pdf` - the PDF generated before optimization +- `optimize.out.pdf` - the PDF generated by optimization +- `origin` - the input file +- `origin.pdf` - the input file or the input image converted to PDF +- `images/*` - images extracted during the optimization process; here + the prefix indicates a PDF object ID not a page number diff --git a/docs/advanced.rst b/docs/advanced.rst deleted file mode 100644 index fd1fb997..00000000 --- a/docs/advanced.rst +++ /dev/null @@ -1,486 +0,0 @@ -.. SPDX-FileCopyrightText: 2022 James R. Barlow -.. SPDX-License-Identifier: CC-BY-SA-4.0 - -================= -Advanced features -================= - -Control of unpaper -================== - -OCRmyPDF uses ``unpaper`` to provide the implementation of the -``--clean`` and ``--clean-final`` arguments. -`unpaper `__ -provides a variety of image processing filters to improve images. - -By default, OCRmyPDF uses only ``unpaper`` arguments that were found to -be safe to use on almost all files without having to inspect every page -of the file afterwards. This is particularly true when only ``--clean`` -is used, since that instructs OCRmyPDF to only clean the image before -OCR and not the final image. - -However, if you wish to use the more aggressive options in ``unpaper``, -you may use ``--unpaper-args '...'`` to override the OCRmyPDF's defaults -and forward other arguments to unpaper. This option will forward -arguments to ``unpaper`` without any knowledge of what that program -considers to be valid arguments. The string of arguments must be quoted -as shown in the examples below. No filename arguments may be included. -OCRmyPDF will assume it can append input and output filename of -intermediate images to the ``--unpaper-args`` string. - -In this example, we tell ``unpaper`` to expect two pages of text on a -sheet (image), such as occurs when two facing pages of a book are -scanned. ``unpaper`` uses this information to deskew each independently -and clean up the margins of both. - -.. code-block:: bash - - ocrmypdf --clean --clean-final --unpaper-args '--layout double' input.pdf output.pdf - ocrmypdf --clean --clean-final --unpaper-args '--layout double --no-noisefilter' input.pdf output.pdf - -.. warning:: - - Some ``unpaper`` features will reposition text within the image. - ``--clean-final`` is recommended to avoid this issue. - -.. warning:: - - Some ``unpaper`` features cause multiple input or output files to be - consumed or produced. OCRmyPDF requires ``unpaper`` to consume one - file and produce one file; errors will result if this assumption is not - met. - -.. note:: - - ``unpaper`` uses uncompressed PBM/PGM/PPM files for its intermediate - files. For large images or documents, it can take a lot of temporary - disk space. - -Control of OCR options -====================== - -OCRmyPDF provides many features to control the behavior of the OCR -engine, Tesseract. - -When OCR is skipped -------------------- - -If a page in a PDF seems to have text, by default OCRmyPDF will exit -without modifying the PDF. This is to ensure that PDFs that were -previously OCRed or were "born digital" rather than scanned are not -processed. - -If ``--skip-text`` is issued, then no image processing or OCR will be -performed on pages that already have text. The page will be copied to -the output. This may be useful for documents that contain both "born -digital" and scanned content, or to use OCRmyPDF to normalize and -convert to PDF/A regardless of their contents. - -If ``--redo-ocr`` is issued, then a detailed text analysis is performed. -Text is categorized as either visible or invisible. Invisible text (OCR) -is stripped out. Then an image of each page is created with visible text -masked out. The page image is sent for OCR, and any additional text is -inserted as OCR. If a file contains a mix of text and bitmap images that -contain text, OCRmyPDF will locate the additional text in images without -disrupting the existing text. Some PDF OCR solutions render text as -technically printable or visible in some way, perhaps by drawing it and -then painting over it. OCRmyPDF cannot distinguish this type of OCR -text from real text, so it will not be "redone". - -If ``--force-ocr`` is issued, then all pages will be rasterized to -images, discarding any hidden OCR text, rasterizing any printable -text, and flattening form fields or interactive objects into their visual -representation. This is useful for redoing OCR, for fixing OCR text -with a damaged character map (text is selectable but not searchable), -and destroying redacted information. - -Time and image size limits --------------------------- - -By default, OCRmyPDF permits tesseract to run for three minutes (180 -seconds) per page. This is usually more than enough time to find all -text on a reasonably sized page with modern hardware. - -If a page is skipped, it will be inserted without OCR. If preprocessing -was requested, the preprocessed image layer will be inserted. - -If you want to adjust the amount of time spent on OCR, change -``--tesseract-timeout``. You can also automatically skip images that -exceed a certain number of megapixels with ``--skip-big``. (A 300 DPI, -8.5×11" page image is 8.4 megapixels.) - -.. code-block:: bash - - # Allow 300 seconds for OCR; skip any page larger than 50 megapixels - ocrmypdf --tesseract-timeout 300 --skip-big 50 bigfile.pdf output.pdf - -OCR for huge images -------------------- - -Tesseract has internal limits on the size -of images it will process. By default, -``--tesseract-downsample-large-images`` is enabled, and OCRmyPDF will -downsample images to fit Tesseract limits. (The limits are usually encountered -only for scanned images of oversized media, such as large maps or blueprints exceeding -110 cm or 43 inches in either dimension, and at high DPI.) This feature can disabled -using ``--no-tesseract-downsample-large-images``. - -``--tesseract-downsample-above Npixels`` adjusts the threshold at which images -will be downsampled. By default, only images that exceed any of Tesseract's -internal limits are downsampled (32767 pixels on either dimension). - -You will also need to set ``--tesseract-timeout`` high enough to allow -for processing. - -Only the image sent for OCR is downsampled. The original image is -preserved. - -.. code-block:: bash - - # Allow 600 seconds for OCR on huge images - ocrmypdf --tesseract-timeout 600 \ - --tesseract-downsample-large-images \ - bigfile.pdf output.pdf - - # Downsample images above 5000 pixels on the longest dimension to - # 5000 pixels - ocrmypdf --tesseract-timeout 120 \ - --tesseract-downsample-large-images \ - --tesseract-downsample-above 5000 \ - bigfile.pdf output_downsampled_ocr.pdf - - -Overriding default tesseract ----------------------------- - -OCRmyPDF checks the system ``PATH`` for the ``tesseract`` binary. - -Some relevant environment variables that influence Tesseract's behavior -include: - -.. envvar:: TESSDATA_PREFIX - - Overrides the path to Tesseract's data files. This can allow - simultaneous installation of the "best" and "fast" training data - sets. OCRmyPDF does not manage this environment variable. - -.. envvar:: OMP_THREAD_LIMIT - - Controls the number of threads Tesseract will use. OCRmyPDF will - manage this environment variable if it is not already set. - -For example, if you have a development build of Tesseract don't wish to -use the system installation, you can launch OCRmyPDF as follows: - -.. code-block:: bash - - env \ - PATH=/home/user/src/tesseract/api:$PATH \ - TESSDATA_PREFIX=/home/user/src/tesseract \ - ocrmypdf input.pdf output.pdf - -In this example ``TESSDATA_PREFIX`` is required to redirect Tesseract to -an alternate folder for its "tessdata" files. - -Overriding other support programs ---------------------------------- - -In addition to tesseract, OCRmyPDF uses the following external binaries: - -- ``gs`` (Ghostscript) -- ``unpaper`` -- ``pngquant`` -- ``jbig2`` - -In each case OCRmyPDF will search the ``PATH`` environment variable to -locate the binaries. By modifying the ``PATH`` environment variable, you -can override the binaries that OCRmyPDF uses. - -Changing Tesseract configuration variables ------------------------------------------- - -You can override Tesseract's default `control -parameters `__ -with a configuration file. - -As an example, this configuration will disable Tesseract's dictionary -for current language. Normally the dictionary is helpful for -interpolating words that are unclear, but it may interfere with OCR if -the document does not contain many words (for example, a list of part -numbers). - -Create a file named "no-dict.cfg" with these contents: - -:: - - load_system_dawg 0 - language_model_penalty_non_dict_word 0 - language_model_penalty_non_freq_dict_word 0 - -then run ocrmypdf as follows (along with any other desired arguments): - -.. code-block:: bash - - ocrmypdf --tesseract-config no-dict.cfg input.pdf output.pdf - -.. warning:: - - Some combinations of control parameters will break Tesseract or break - assumptions that OCRmyPDF makes about Tesseract's output. - -Changing page segmentation mode -------------------------------- - -The directive ``--tesseract-pagesegmode Nmode`` forwards the desired page segmentation -mode to Tesseract OCR. The default is 3. - -Page segmentation can improve OCR results when you know that a PDF ought to be -analyzed a particular way, such as PDFs whose pages contain only a single line of -text. For the vast majority of users, changing the page segmentation mode will only -make things worse. - -As of June 2024, the Tesseract page segmentation modes are: - -+-----+----------------------------------------------------------------------------------+ -| ID | Description | -+=====+==================================================================================+ -| 0 | Orientation and script detection (OSD) only. | -+-----+----------------------------------------------------------------------------------+ -| 1 | Automatic page segmentation with OSD. | -+-----+----------------------------------------------------------------------------------+ -| 2 | Automatic page segmentation, but no OSD, or OCR. (not implemented) | -+-----+----------------------------------------------------------------------------------+ -| 3 | Fully automatic page segmentation, but no OSD. (Default) | -+-----+----------------------------------------------------------------------------------+ -| 4 | Assume a single column of text of variable sizes. | -+-----+----------------------------------------------------------------------------------+ -| 5 | Assume a single uniform block of vertically aligned text. | -+-----+----------------------------------------------------------------------------------+ -| 6 | Assume a single uniform block of text. | -+-----+----------------------------------------------------------------------------------+ -| 7 | Treat the image as a single text line. | -+-----+----------------------------------------------------------------------------------+ -| 8 | Treat the image as a single word. | -+-----+----------------------------------------------------------------------------------+ -| 9 | Treat the image as a single word in a circle. | -+-----+----------------------------------------------------------------------------------+ -| 10 | Treat the image as a single character. | -+-----+----------------------------------------------------------------------------------+ -| 11 | Sparse text. Find as much text as possible in no particular order. | -+-----+----------------------------------------------------------------------------------+ -| 12 | Sparse text with OSD. | -+-----+----------------------------------------------------------------------------------+ -| 13 | Raw line. Treat the image as a single text line, bypassing hacks that are | -| | Tesseract-specific. | -+-----+----------------------------------------------------------------------------------+ - -Modes 0, 1, 2, and 12 (all of those that enable orientation and script detection) -are not compatible with OCRmyPDF, which performs OSD in a separate step from OCR. -Their use may interfere with ``--rotate-pages`` and other features. - -It is currently not possible to use advanced Tesseract OCR features, such as creating -OCR information, when using Tesseract through OCRmyPDF. - -Changing the PDF renderer -========================= - -rasterizing - Converting a PDF to an image for display. - -rendering - Creating a new PDF from other data (such as an existing PDF). - -OCRmyPDF has these PDF renderers: ``sandwich`` and ``hocr``. The -renderer may be selected using ``--pdf-renderer``. The default is -``auto`` which lets OCRmyPDF select the renderer to use. Currently, -``auto`` always selects ``hocr``. - -The ``hocr`` renderer ---------------------- - -.. versionchanged:: 16.0.0 - -In both renderers, a text-only layer is rendered and sandwiched (overlaid) -on to either the original PDF page, or newly rasterized version of the -original PDF page (when ``--force-ocr`` is used). In this way, loss -of PDF information is generally avoided. (You may need to disable PDF/A -conversion and optimization to eliminate all lossy transformations.) - -The current approach used by the new hOCR renderer is a re-implementation -of Tesseract's PDF renderer, using the same Glyphless font and general -ideas, but fixing many technical issues that impeded it. The new hocr -provides better text placement accuracy, avoids issues with word -segmentation, and provides better positioning of skewed text. - -Using the experimental API, it is also possible to edit the OCR output -from Tesseract, using any tool that is capable of editing hOCR files. - -Older versions of this renderer did not support non-Latin languages, but -it is now universal. - -The ``sandwich`` renderer -------------------------- - -The ``sandwich`` renderer uses Tesseract's text-only PDF feature, -which produces a PDF page that lays out the OCR in invisible text. - -Currently some problematic PDF viewers like Mozilla PDF.js and macOS -Preview have problems with segmenting its text output, and -mightrunseveralwordstogether. It also does not implement right to left -fonts (Arabic, Hebrew, Persian). The output of this renderer cannot -be edited. The sandwich renderer is retained for testing. - -When image preprocessing features like ``--deskew`` are used, the -original PDF will be rendered as a full page and the OCR layer will be -placed on top. - -Rendering and rasterizing options -================================= - -.. versionadded:: 14.3.0 - -The ``--continue-on-soft-render-error`` option allows OCRmyPDF to -proceed if a page cannot be rasterized/rendered. This is useful if you are -trying to get the best possible OCR from a PDF that is not well-formed, -and you are willing to accept some pages that may not visually match the -input, and that may not OCR well. - -Color conversion strategy -========================= - -.. versionadded:: 15.0.0 - -OCRmyPDF uses Ghostscript to convert PDF to PDF/A. In some cases, this -conversion requires color conversion. The default strategy is to convert -using the ``LeaveColorUnchanged`` strategy, which preserves the original -color space wherever possible (some rare color spaces might still be -converted). - -Usually document scanners produce PDFs in the sRGB color space, and do -not need to be converted, so the default strategy is appropriate. - -Suppose that you have a document that was prepared for professional -printing in a Separation or CMYK color space, and text was converted to -curves. In this case, you may want to use a different color conversion -strategy. The ``--color-conversion-strategy`` option allows you to select a -different strategy, such as ``RGB``. - -Return code policy -================== - -OCRmyPDF writes all messages to ``stderr``. ``stdout`` is reserved for -piping output files. ``stdin`` is reserved for piping input files. - -The return codes generated by the OCRmyPDF are considered part of the -stable user interface. They may be imported from -``ocrmypdf.exceptions``. - -.. list-table:: Return codes - :widths: 5 35 60 - :header-rows: 1 - - * - Code - - Name - - Interpretation - * - 0 - - ``ExitCode.ok`` - - Everything worked as expected. - * - 1 - - ``ExitCode.bad_args`` - - Invalid arguments, exited with an error. - * - 2 - - ``ExitCode.input_file`` - - The input file does not seem to be a valid PDF. - * - 3 - - ``ExitCode.missing_dependency`` - - An external program required by OCRmyPDF is missing. - * - 4 - - ``ExitCode.invalid_output_pdf`` - - An output file was created, but it does not seem to be a valid PDF. The file will be available. - * - 5 - - ``ExitCode.file_access_error`` - - The user running OCRmyPDF does not have sufficient permissions to read the input file and write the output file. - * - 6 - - ``ExitCode.already_done_ocr`` - - The file already appears to contain text so it may not need OCR. See output message. - * - 7 - - ``ExitCode.child_process_error`` - - An error occurred in an external program (child process) and OCRmyPDF cannot continue. - * - 8 - - ``ExitCode.encrypted_pdf`` - - The input PDF is encrypted. OCRmyPDF does not read encrypted PDFs. Use another program such as ``qpdf`` to remove encryption. - * - 9 - - ``ExitCode.invalid_config`` - - A custom configuration file was forwarded to Tesseract using ``--tesseract-config``, and Tesseract rejected this file. - * - 10 - - ``ExitCode.pdfa_conversion_failed`` - - A valid PDF was created, PDF/A conversion failed. The file will be available. - * - 15 - - ``ExitCode.other_error`` - - Some other error occurred. - * - 130 - - ``ExitCode.ctrl_c`` - - The program was interrupted by pressing Ctrl+C. - - -.. _tmpdir: - -Changing temporary storage location -=================================== - -OCRmyPDF generates many temporary files during processing. - -To change where temporary files are stored, change the ``TMPDIR`` -environment variable for ocrmypdf's environment. (Python's -``tempfile.gettempdir()`` returns the root directory in which temporary -files will be stored.) For example, one could redirect ``TMPDIR`` to a -large RAM disk to avoid wear on HDD/SSD and potentially improve -performance. - -On Windows, the ``TEMP`` environment variable is used instead. - -Debugging the intermediate files -================================ - -OCRmyPDF normally saves its intermediate results to a temporary folder -and deletes this folder when it exits, whether it succeeded or failed. - -If the ``--keep-temporary-files`` (``-k``) argument is issued on the -command line, OCRmyPDF will keep the temporary folder and print the location, -whether it succeeded or failed. An example message is: - -.. code-block:: none - - Temporary working files retained at: - /tmp/ocrmypdf.io.u20wpz07 - -When OCRmyPDF is launched as a snap, this corresponds to the snap filesystem, for instance: - - /tmp/snap-private-tmp/snap.ocrmypdf/tmp/ocrmypdf.io.u20wpz07 - -The organization of this folder is an implementation detail and subject -to change between releases. However the general organization is that -working files on a per page basis have the page number as a prefix -(starting with page 1), an infix indicates the processing stage, and a -suffix indicates the file type. Some important files include: - -- ``_rasterize.png`` - what the input page looks like -- ``_ocr.png`` - the file that is sent to Tesseract for OCR; depending - on arguments this may differ from the presentation image -- ``_pp_deskew.png`` - the image, after deskewing -- ``_pp_clean.png`` - the image, after cleaning with unpaper -- ``_ocr_hocr.pdf`` - the OCR file; appears as a blank page with invisible - text embedded -- ``_ocr_hocr.txt`` - the OCR text (not necessarily all text on the page, - if the page is mixed format) -- ``fix_docinfo.pdf`` - a temporary file created to fix the PDF DocumentInfo - data structure -- ``graft_layers.pdf`` - the rendered PDF with OCR layers grafted on -- ``pdfa.pdf`` - ``graft_layers.pdf`` after conversion to PDF/A -- ``pdfa.ps`` - a PostScript file used by Ghostscript for PDF/A conversion -- ``optimize.pdf`` - the PDF generated before optimization -- ``optimize.out.pdf`` - the PDF generated by optimization -- ``origin`` - the input file -- ``origin.pdf`` - the input file or the input image converted to PDF -- ``images/*`` - images extracted during the optimization process; here - the prefix indicates a PDF object ID not a page number diff --git a/docs/api.rst b/docs/api.md similarity index 51% rename from docs/api.rst rename to docs/api.md index abdbfda7..b38567c8 100644 --- a/docs/api.rst +++ b/docs/api.md @@ -1,10 +1,7 @@ -.. SPDX-FileCopyrightText: 2022 James R. Barlow -.. -.. SPDX-License-Identifier: CC-BY-SA-4.0 +% SPDX-FileCopyrightText: 2022 James R. Barlow +% SPDX-License-Identifier: CC-BY-SA-4.0 -====================== -Using the OCRmyPDF API -====================== +# Using the OCRmyPDF API OCRmyPDF originated as a command line program and continues to have this legacy, but parts of it can be imported and used in other Python @@ -13,100 +10,95 @@ applications. Some applications may want to consider running ocrmypdf from a subprocess call anyway, as this provides isolation of its activities. -Example -======= +## Example OCRmyPDF provides one high-level function to run its main engine from an application. The parameters are symmetric to the command line arguments and largely have the same functions. -.. code-block:: python +```python +import ocrmypdf - import ocrmypdf - - if __name__ == '__main__': # To ensure correct behavior on Windows and macOS - ocrmypdf.ocr('input.pdf', 'output.pdf', deskew=True) +if __name__ == '__main__': # To ensure correct behavior on Windows and macOS + ocrmypdf.ocr('input.pdf', 'output.pdf', deskew=True) +``` With some exceptions, all of the command line arguments are available and may be passed as equivalent keywords. -A few differences are that ``verbose`` and ``quiet`` are not available. +A few differences are that `verbose` and `quiet` are not available. Instead, output should be managed by configuring logging. -Parent process requirements ---------------------------- +### Parent process requirements -The :func:`ocrmypdf.ocr` function runs OCRmyPDF similar to command line +The {func}`ocrmypdf.ocr` function runs OCRmyPDF similar to command line execution. To do this, it will: - create worker processes or threads - manage the signal flags of its worker processes - execute other subprocesses (forking and executing other programs) -The Python process that calls :func:`ocrmypdf.ocr()` must be sufficiently +The Python process that calls {func}`ocrmypdf.ocr()` must be sufficiently privileged to perform these actions. There currently is no option to manage how jobs are scheduled other -than the argument ``jobs=`` which will limit the number of worker +than the argument `jobs=` which will limit the number of worker processes. -Creating a child process to call :func:`ocrmypdf.ocr()` is suggested. That +Creating a child process to call {func}`ocrmypdf.ocr()` is suggested. That way your application will survive and remain interactive even if OCRmyPDF fails for any reason. For example: -.. code-block:: python +```python +from multiprocessing import Process - from multiprocessing import Process +def ocrmypdf_process(): + ocrmypdf.ocr('input.pdf', 'output.pdf') - def ocrmypdf_process(): - ocrmypdf.ocr('input.pdf', 'output.pdf') +def call_ocrmypdf_from_my_app(): + p = Process(target=ocrmypdf_process) + p.start() + p.join() +``` - def call_ocrmypdf_from_my_app(): - p = Process(target=ocrmypdf_process) - p.start() - p.join() - -Programs that call :func:`ocrmypdf.ocr()` should also install a SIGBUS signal +Programs that call {func}`ocrmypdf.ocr()` should also install a SIGBUS signal handler (except on Windows), to raise an exception if access to a memory mapped file fails. OCRmyPDF may use memory mapping. -:func:`ocrmypdf.ocr()` will take a threading lock to prevent multiple runs of itself +{func}`ocrmypdf.ocr()` will take a threading lock to prevent multiple runs of itself in the same Python interpreter process. This is not thread-safe, because of how OCRmyPDF's plugins and Python's library import system work. If you need to parallelize OCRmyPDF, use processes. -.. warning:: +:::{warning} +On Windows and macOS, the script that calls {func}`ocrmypdf.ocr()` must be +protected by an "ifmain" guard (`if __name__ == '__main__'`). If you do +not take at least one of these steps, process semantics will prevent +OCRmyPDF from working correctly. +::: - On Windows and macOS, the script that calls :func:`ocrmypdf.ocr()` must be - protected by an "ifmain" guard (``if __name__ == '__main__'``). If you do - not take at least one of these steps, process semantics will prevent - OCRmyPDF from working correctly. +### Logging -Logging -------- - -OCRmyPDF will log under loggers named ``ocrmypdf``. In addition, it -imports ``pdfminer`` and ``PIL``, both of which post log messages under +OCRmyPDF will log under loggers named `ocrmypdf`. In addition, it +imports `pdfminer` and `PIL`, both of which post log messages under those logging namespaces. You can configure the logging as desired for your application or call -:func:`ocrmypdf.configure_logging` to configure logging the same way -OCRmyPDF itself does. The command line parameters such as ``--quiet`` -and ``--verbose`` have no equivalents in the API; you must use the +{func}`ocrmypdf.configure_logging` to configure logging the same way +OCRmyPDF itself does. The command line parameters such as `--quiet` +and `--verbose` have no equivalents in the API; you must use the provided configuration function or do configuration in a way that suits your use case. -Progress monitoring -------------------- +### Progress monitoring -OCRmyPDF uses the ``rich`` package to implement its progress bars. -:func:`ocrmypdf.configure_logging` will set up logging output to -``sys.stderr`` in a way that is compatible with the display of the -progress bar. Use ``ocrmypdf.ocr(...progress_bar=False)`` to disable +OCRmyPDF uses the `rich` package to implement its progress bars. +{func}`ocrmypdf.configure_logging` will set up logging output to +`sys.stderr` in a way that is compatible with the display of the +progress bar. Use `ocrmypdf.ocr(...progress_bar=False)` to disable the progress bar. -Standard output ---------------- +### Standard output OCRmyPDF is strict about not writing to standard output so that users can safely use it in a pipeline and produce a valid output @@ -116,12 +108,11 @@ behavior and support piping to a file. Another benefit of running OCRmyPDF in a child process, as recommended above, is that it will not interfere with the parent process's standard output. -Exceptions ----------- +### Exceptions -OCRmyPDF may throw standard Python exceptions, ``ocrmypdf.exceptions.*`` +OCRmyPDF may throw standard Python exceptions, `ocrmypdf.exceptions.*` exceptions, some exceptions related to multiprocessing, and -:exc:`KeyboardInterrupt`. The parent process should provide an exception +{exc}`KeyboardInterrupt`. The parent process should provide an exception handler. OCRmyPDF will clean up its temporary files and worker processes automatically when an exception occurs. diff --git a/docs/apiref.rst b/docs/apiref.md similarity index 59% rename from docs/apiref.rst rename to docs/apiref.md index 33fbc285..ae4d0299 100644 --- a/docs/apiref.rst +++ b/docs/apiref.md @@ -1,56 +1,60 @@ -.. SPDX-FileCopyrightText: 2022 James R. Barlow -.. -.. SPDX-License-Identifier: CC-BY-SA-4.0 +% SPDX-FileCopyrightText: 2022 James R. Barlow +% SPDX-License-Identifier: CC-BY-SA-4.0 -============= -API reference -============= +# API reference This page summarizes the rest of the public API. Generally speaking this should be mainly of interest to plugin developers. -ocrmypdf.api -============ +## ocrmypdf.api +```{eval-rst} .. automodule:: ocrmypdf.api :members: +``` -ocrmypdf.exceptions -=================== +## ocrmypdf.exceptions +```{eval-rst} .. automodule:: ocrmypdf.exceptions :members: :undoc-members: +``` -ocrmypdf.helpers -================ +## ocrmypdf.helpers +```{eval-rst} .. automodule:: ocrmypdf.helpers :members: :noindex: deprecated .. autodecorator:: deprecated +``` -ocrmypdf.hocrtransform -====================== +## ocrmypdf.hocrtransform +```{eval-rst} .. automodule:: ocrmypdf.hocrtransform :members: +``` -ocrmypdf.pdfa -============= +## ocrmypdf.pdfa +```{eval-rst} .. automodule:: ocrmypdf.pdfa :members: +``` -ocrmypdf.quality -================ +## ocrmypdf.quality +```{eval-rst} .. automodule:: ocrmypdf.quality :members: +``` -ocrmypdf.subprocess -=================== +## ocrmypdf.subprocess +```{eval-rst} .. automodule:: ocrmypdf.subprocess :members: +``` diff --git a/docs/conf.py b/docs/conf.py index fc89bace..301154ee 100755 --- a/docs/conf.py +++ b/docs/conf.py @@ -45,7 +45,7 @@ extensions = [ 'sphinx_issues', ] -myst_enable_extensions = ['colon_fence', 'attrs_block', 'attrs_inline'] +myst_enable_extensions = ['colon_fence', 'attrs_block', 'attrs_inline', 'substitution'] # Extension settings intersphinx_mapping = {'python': ('https://docs.python.org/3', None)} diff --git a/docs/cookbook.md b/docs/cookbook.md index 0bdcc941..29201b9b 100644 --- a/docs/cookbook.md +++ b/docs/cookbook.md @@ -1,45 +1,43 @@ % SPDX-FileCopyrightText: 2025 James R. Barlow % SPDX-License-Identifier: CC-BY-SA-4.0 -Cookbook -======== +# Cookbook -Basic examples --------------- +## Basic examples ### Help! ocrmypdf has built-in help. -:::{code} bash +```bash ocrmypdf --help -::: +``` ### Add an OCR layer and convert to PDF/A -:::{code} bash +```bash ocrmypdf input.pdf output.pdf -::: +``` ### Add an OCR layer and output a standard PDF -:::{code} bash +```bash ocrmypdf --output-type pdf input.pdf output.pdf -::: +``` ### Create a PDF/A with all color and grayscale images converted to JPEG -:::{code} bash +```bash ocrmypdf --output-type pdfa --pdfa-image-compression jpeg input.pdf output.pdf -::: +``` ### Modify a file in place The file will only be overwritten if OCRmyPDF is successful. -:::{code} bash +```bash ocrmypdf myfile.pdf myfile.pdf -::: +``` ### Correct page rotation @@ -47,9 +45,9 @@ OCR will attempt to automatic correct the rotation of each page. This can help fix a scanning job that contains a mix of landscape and portrait pages. -:::{code} bash +```bash ocrmypdf --rotate-pages myfile.pdf myfile.pdf -::: +``` You can increase (decrease) the parameter `--rotate-pages-threshold` to make page rotation more (less) aggressive. The threshold number is the @@ -70,10 +68,10 @@ angle is wrong. OCRmyPDF assumes the document is in English unless told otherwise. OCR quality may be poor if the wrong language is used. -:::{code} bash +```bash ocrmypdf -l fra LeParisien.pdf LeParisien.pdf ocrmypdf -l eng+fra Bilingual-English-French.pdf Bilingual-English-French.pdf -::: +``` Language packs must be installed for all languages specified. See `Installing additional language packs `{.interpreted-text @@ -87,9 +85,9 @@ language when it is unknown. This produces a file named \"output.pdf\" and a companion text file named \"output.txt\". -:::{code} bash +```bash ocrmypdf --sidecar output.txt input.pdf output.pdf -::: +``` :::{note} The sidecar file contains the **OCR text** found by OCRmyPDF. If the @@ -114,14 +112,14 @@ use a program like Poppler\'s `pdftotext` or `pdfgrep`. If you are starting with images, you can just use Tesseract directly to convert images to PDFs: -:::{code} bash +```bash tesseract my-image.jpg output-prefix pdf -::: +``` -:::{code} bash +```bash # When there are multiple images tesseract text-file-containing-list-of-image-filenames.txt output-prefix pdf -::: +``` Tesseract\'s PDF output is quite good -- OCRmyPDF uses it internally, in some cases. However, OCRmyPDF has many features not available in @@ -134,9 +132,9 @@ You can also use a program like images to PDFs, and then pipe the results to run ocrmypdf. The `-` tells ocrmypdf to read standard input. -:::{code} bash +```bash img2pdf my-images*.jpg | ocrmypdf - myfile.pdf -::: +``` `img2pdf` is recommended because it does an excellent job at generating PDFs without transcoding images. @@ -148,9 +146,9 @@ own. If the resolution (dots per inch, DPI) of an image is not set or is incorrect, it can be overridden with `--image-dpi`. (As 1 inch is 2.54 cm, 1 dpi = 0.39 dpcm). -:::{code} bash +```bash ocrmypdf --image-dpi 300 image.png myfile.pdf -::: +``` If you have multiple images, you must use `img2pdf` to convert the images to PDF. @@ -161,8 +159,9 @@ We caution against using ImageMagick or Ghostscript to convert images to PDF, since they may transcode images or produce downsampled images, sometimes without warning. -Image processing ----------------- +(image-processing)= + +## Image processing OCRmyPDF perform some image processing on each page of a PDF, if desired. The same processing is applied to each page. It is suggested @@ -200,18 +199,18 @@ should be visually reviewed after using these options. Deskew: -:::{code} bash +```bash ocrmypdf --deskew input.pdf output.pdf -::: +``` Image processing commands can be combined. The order in which options are given does not matter. OCRmyPDF always applies the steps of the image processing pipeline in the same order (rotate, remove background, deskew, clean). -:::{code} bash +```bash ocrmypdf --deskew --clean --rotate-pages input.pdf output.pdf -::: +``` Don\'t actually OCR my PDF -------------------------- @@ -221,12 +220,11 @@ processing without performing OCR (by causing OCR to time out). This works if all you want to is to apply image processing or PDF/A conversion. -:::{code} bash +```bash ocrmypdf --tesseract-timeout=0 --remove-background input.pdf output.pdf -::: +``` -::: {.versionchanged} -v14.1.0 +:::{versionchanged} v14.1.0 Prior to this version, `--tesseract-timeout 0` would prevent other uses of Tesseract, such as deskewing, from working. This is no longer the @@ -239,9 +237,9 @@ non-OCR operations, if needed. This is getting ridiculous, but OCRmyPDF can complete strip all textual information from a PDF and reconstruct it as a \"bag of images\" PDF. -:::{code} bash +```bash ocrmypdf --tesseract-timeout 0 --force-ocr input.pdf output.pdf -::: +``` Why would you want to do this? Perhaps you have a PDF where OCR fails to produce useful results, and just want to get rid of all OCR information. @@ -251,18 +249,18 @@ This command also removes OCR generated by third party tools. You can also optimize all images without performing any OCR: -:::{code} bash +```bash ocrmypdf --tesseract-timeout=0 --optimize 3 --skip-text input.pdf output.pdf -::: +``` ### Process only certain pages You can ask OCRmyPDF to only apply [image processing](#image-processing) and OCR to certain pages. -:::{code} bash +```bash ocrmypdf --pages 2,3,13-17 input.pdf output.pdf -::: +``` Hyphens denote a range of pages and commas separate page numbers. If you prefer to use spaces, quote all of the page numbers: @@ -281,9 +279,9 @@ those options. Both of these steps are \"whole file\" operations. In this example, we want to OCR only the title and otherwise change the PDF as little as possible: -:::{code} bash +```bash ocrmypdf --pages 1 --output-type pdf --optimize 0 input.pdf output.pdf -::: +``` Redo existing OCR ----------------- @@ -297,9 +295,9 @@ This may be helpful for users who want to take advantage of accuracy improvements in Tesseract for files they previously OCRed with an earlier version of Tesseract and OCRmyPDF. -:::{code} bash +```bash ocrmypdf --redo-ocr input.pdf output.pdf -::: +``` This method will replace OCR without rasterizing, reducing quality or removing vector content. If a file contains a mix of pure digital text @@ -351,18 +349,18 @@ header-rows: 1 * - Level - Comments -* - ``--optimize=0`` +* - ``--optimize=0`` - Disables optimization. -* - ``--optimize 1`` +* - ``--optimize 1`` - Enables lossless optimizations, such as transcoding images to more efficient formats. Also compress other uncompressed objects in the PDF and enables the more efficient "object streams" within the PDF. (If ``--jbig2-lossy`` is issued, then lossy JBIG2 optimization is used. The decision to use lossy JBIG2 is separate from standard optimization settings.) -* - ``--optimize 2`` +* - ``--optimize 2`` - All of the above, and enables lossy optimizations and color quantization. -* - ``--optimize 3`` +* - ``--optimize 3`` - All of the above, and enables more aggressive optimizations and targets lower image quality. ::: @@ -376,9 +374,9 @@ inefficient compression modes to more modern versions. A program like `qpdf` can be used to change encodings, e.g. to inspect the internals for a PDF. -:::{code} bash +```bash ocrmypdf --optimize 3 in.pdf out.pdf # Make it small -::: +``` Some users may consider enabling lossy JBIG2. See: `jbig2-lossy`{.interpreted-text role="ref"}. diff --git a/docs/index.md b/docs/index.md new file mode 100644 index 00000000..aa3086d6 --- /dev/null +++ b/docs/index.md @@ -0,0 +1,57 @@ +% SPDX-FileCopyrightText: 2022 James R. Barlow +% SPDX-License-Identifier: CC-BY-SA-4.0 + +# OCRmyPDF documentation + +:::{figure} images/logo.svg +::: + +OCRmyPDF adds an optical character recognition (OCR) text layer to scanned PDF +files, allowing them to be searched. + +PDF is the best format for storing and exchanging scanned documents. +Unfortunately, PDFs can be difficult to modify. OCRmyPDF makes it easy to apply +image processing and OCR (recognized, searchable text) to existing PDFs. + +```{toctree} +:maxdepth: 1 + +introduction +release_notes +installation +languages +jbig2 +``` + +```{toctree} +:caption: Usage +:maxdepth: 2 + +cookbook +optimizer +docker +advanced +batch +cloud +performance +pdfsecurity +errors +``` + +```{toctree} +:caption: Developers +:maxdepth: 2 + +api +plugins +apiref +design_notes +contributing +maintainers +``` + +# Indices and tables + +- {ref}`genindex` +- {ref}`modindex` +- {ref}`search` diff --git a/docs/index.rst b/docs/index.rst deleted file mode 100644 index a8803595..00000000 --- a/docs/index.rst +++ /dev/null @@ -1,56 +0,0 @@ -.. SPDX-FileCopyrightText: 2022 James R. Barlow -.. -.. SPDX-License-Identifier: CC-BY-SA-4.0 - -OCRmyPDF documentation -====================== - -.. figure:: images/logo.svg - -OCRmyPDF adds an optical character recognition (OCR) text layer to scanned PDF -files, allowing them to be searched. - -PDF is the best format for storing and exchanging scanned documents. -Unfortunately, PDFs can be difficult to modify. OCRmyPDF makes it easy to apply -image processing and OCR (recognized, searchable text) to existing PDFs. - -.. toctree:: - :maxdepth: 1 - - introduction - release_notes - installation - languages - jbig2 - -.. toctree:: - :caption: Usage - :maxdepth: 2 - - cookbook - optimizer - docker - advanced - batch - cloud - performance - pdfsecurity - errors - -.. toctree:: - :caption: Developers - :maxdepth: 2 - - api - plugins - apiref - design_notes - contributing - maintainers - -Indices and tables -================== - -* :ref:`genindex` -* :ref:`modindex` -* :ref:`search` diff --git a/docs/installation.md b/docs/installation.md new file mode 100644 index 00000000..16ed5167 --- /dev/null +++ b/docs/installation.md @@ -0,0 +1,730 @@ +--- +myst: + substitutions: + deb_11: |- + :::{image} https://repology.org/badge/version-for-repo/debian_11/ocrmypdf.svg + :alt: Debian 11 + ::: + deb_12: |- + :::{image} https://repology.org/badge/version-for-repo/debian_12/ocrmypdf.svg + :alt: Debian 12 + ::: + deb_unstable: |- + :::{image} https://repology.org/badge/version-for-repo/debian_unstable/ocrmypdf.svg + :alt: Debian unstable + ::: + fedora_38: |- + :::{image} https://repology.org/badge/version-for-repo/fedora_38/ocrmypdf.svg + :alt: Fedora 38 + ::: + fedora_39: |- + :::{image} https://repology.org/badge/version-for-repo/fedora_39/ocrmypdf.svg + :alt: Fedora 39 + ::: + fedora_rawhide: |- + :::{image} https://repology.org/badge/version-for-repo/fedora_rawhide/ocrmypdf.svg + :alt: Fedore Rawhide + ::: + latest: |- + :::{image} https://img.shields.io/pypi/v/ocrmypdf.svg + :alt: OCRmyPDF latest released version on PyPI + ::: + ubu_2004: |- + :::{image} https://repology.org/badge/version-for-repo/ubuntu_20_04/ocrmypdf.svg + :alt: Ubuntu 20.04 LTS + ::: + ubu_2204: |- + :::{image} https://repology.org/badge/version-for-repo/ubuntu_22_04/ocrmypdf.svg + :alt: Ubuntu 22.04 LTS + ::: +--- + +% SPDX-FileCopyrightText: 2022 James R. Barlow +% SPDX-License-Identifier: CC-BY-SA-4.0 + +# Installing OCRmyPDF + +(latest)= + +The easiest way to install OCRmyPDF is to follow the steps for your operating +system/platform. This version may be out of date, however. + +These platforms have one-liner installs: + +:::{list-table} +:header-rows: 0 + +* - Debian, Ubuntu + - ``apt install ocrmypdf`` +* - Windows Subsystem for Linux + - ``apt install ocrmypdf`` +* - Fedora + - ``dnf install ocrmypdf tesseract-osd`` +* - macOS (Homebrew) + - ``brew install ocrmypdf`` +* - macOS (MacPorts) + - ``port install ocrmypdf`` +* - LinuxBrew + - ``brew install ocrmypdf`` +* - FreeBSD + - ``pkg install textproc/py-ocrmypdf`` +* - Snap (snapcraft packaging) + - ``snap install ocrmypdf`` +::: + +More detailed procedures are outlined below. If you want to do a manual +install, or install a more recent version than your platform provides, read on. + +:::{contents} Platform-specific steps +:depth: 2 +:local: true +::: + +## Installing on Linux + +### Debian and Ubuntu 20.04 or newer + +:::{list-table} +:header-rows: 1 + +* - OCRmyPDF versions in Debian & Ubuntu +* - {{ latest }} +* - {{ deb_11 }} {{ deb_12 }} {{ deb_unstable }} +* - {{ ubu_2004 }} {{ ubu_2204 }} +::: + +Users of Debian or Ubuntu may simply + +```bash +apt install ocrmypdf +``` + +As indicated in the table above, Debian and Ubuntu releases may lag +behind the latest version. If the version available for your platform is +out of date, you could opt to install the latest version from source. +See [Installing HEAD revision from +sources](#installing-head-revision-from-sources). + +For full details on version availability for your platform, check the +[Debian Package Tracker](https://tracker.debian.org/pkg/ocrmypdf) or +[Ubuntu launchpad.net](https://launchpad.net/ocrmypdf). + +:::{note} +OCRmyPDF for Debian and Ubuntu currently omit the JBIG2 encoder. +OCRmyPDF works fine without it but will produce larger output files. +If you build jbig2enc from source, ocrmypdf will +automatically detect it (specifically the `jbig2` binary) on the +`PATH`. To add JBIG2 encoding, see {ref}`jbig2`. +::: + +### Fedora + +:::{list-table} +:header-rows: 1 + +* - OCRmyPDF version +* - {{latest}} +* - {{fedora_38}} {{fedora_39}} {{fedora_rawhide}} +::: + +Users of Fedora may simply + +```bash +dnf install ocrmypdf tesseract-osd +``` + +For full details on version availability, check the [Fedora Package +Tracker](https://packages.fedoraproject.org/pkgs/ocrmypdf/ocrmypdf/). + +If the version available for your platform is out of date, you could opt +to install the latest version from source. See [Installing HEAD revision +from sources](#installing-head-revision-from-sources). + +:::{note} +OCRmyPDF for Fedora currently omits the JBIG2 encoder due to patent +issues. OCRmyPDF works fine without it but will produce larger output +files. If you build jbig2enc from source, ocrmypdf 7.0.0 and later +will automatically detect it on the `PATH`. To add JBIG2 encoding, +see {ref}`Installing the JBIG2 encoder `. +::: + +(ubuntu-lts-latest)= + +### RHEL 9 + +Prepare the environment by getting Python 3.11: + +```bash +dnf install python3.11 python3.11-pip +``` + +Then, follow [Requirements for pip and HEAD install](#requirements-for-pip-and-head-install) to install dependencies: + +```bash +dnf install ghostscript tesseract +``` + +and build ocrmypdf in virtual environment: + +```bash +python3.11 -m venv .venv +``` + +To add JBIG2 encoding, see {ref}`Installing the JBIG2 encoder `. + +Note Fedora packages for language data haven't been branched for RHEL/EPEL, but you can get traineddata files directly from [tesseract](https://github.com/tesseract-ocr/tessdata/) and place them in `/usr/share/tesseract/tessdata`. + +### Installing the latest version on Ubuntu 22.04 LTS + +Ubuntu 22.04 includes ocrmypdf 13.4.0 - you can install that with +`apt install ocrmypdf`. To install a more recent version for the current +user, follow these steps: + +```bash +sudo apt-get update +sudo apt-get -y install ocrmypdf python3-pip + +pip install --user --upgrade ocrmypdf +``` + +If you get the message `WARNING: The script ocrmypdf is installed in +'/home/$USER/.local/bin' which is not on PATH.`, you may need to re-login +or open a new shell, or manually adjust your PATH. + +To add JBIG2 encoding, see {ref}`jbig2`. + +### Ubuntu 20.04 LTS + +Ubuntu 20.04 includes ocrmypdf 9.6.0 - you can install that with `apt`. The +most convenient way to install recent OCRmyPDF on older Ubuntu is to use +Homebrew on Linux (Linuxbrew). + +```bash +brew install ocrmypdf +``` + +### Arch Linux (AUR) + +:::{image} https://repology.org/badge/version-for-repo/aur/ocrmypdf.svg +:alt: ArchLinux +:target: https://repology.org/metapackage/ocrmypdf +::: + +There is an [Arch User Repository (AUR) package for OCRmyPDF](https://aur.archlinux.org/packages/ocrmypdf/). + +Installing AUR packages as root is not allowed, so you must first [setup a +non-root user](https://wiki.archlinux.org/index.php/Users_and_groups#User_management) and +[configure sudo](https://wiki.archlinux.org/index.php/Sudo#Configuration). +The standard Docker image, `archlinux/base:latest`, does **not** have a +non-root user configured, so users of that image must follow these guides. If +you are using a VM image, such as [the official Vagrant image](https://app.vagrantup.com/archlinux/boxes/archlinux), this work may already +be completed for you. + +Next you should install the [base-devel package group](https://archlinux.org/packages/core/any/base-devel/). This includes the +standard tooling needed to build packages, such as a compiler and binary tools. + +```bash +sudo pacman -S --needed base-devel +``` + +Now you are ready to install the OCRmyPDF package. + +```bash +curl -O https://aur.archlinux.org/cgit/aur.git/snapshot/ocrmypdf.tar.gz +tar xvzf ocrmypdf.tar.gz +cd ocrmypdf +makepkg -sri +``` + +At this point you will have a working install of OCRmyPDF, but the Tesseract +install won’t include any OCR language data. You can install [the +tesseract-data package group](https://www.archlinux.org/groups/any/tesseract-data/) to add all supported +languages, or use that package listing to identify the appropriate package for +your desired language. + +```bash +sudo pacman -S tesseract-data-eng +``` + +As an alternative to this manual procedure, consider using an [AUR helper](https://wiki.archlinux.org/index.php/AUR_helpers). Such a tool will +automatically fetch, build and install the AUR package, resolve dependencies +(including dependencies on AUR packages), and ease the upgrade procedure. + +If you have any difficulties with installation, check the repository package +page. + +:::{note} +The OCRmyPDF AUR package currently omits the JBIG2 encoder. OCRmyPDF works +fine without it but will produce larger output files. The encoder is +available from [the jbig2enc-git AUR package](https://aur.archlinux.org/packages/jbig2enc-git/) and may be installed +using the same series of steps as for the installation OCRmyPDF AUR +package. Alternatively, it may be built manually from source following the +instructions in {ref}`Installing the JBIG2 encoder `. If JBIG2 is +installed, OCRmyPDF 7.0.0 and later will automatically detect it. +::: + +### Alpine Linux + +:::{image} https://repology.org/badge/version-for-repo/alpine_edge/ocrmypdf.svg +:alt: Alpine Linux +:target: https://repology.org/metapackage/ocrmypdf +::: + +To install OCRmyPDF for Alpine Linux: + +```bash +apk add ocrmypdf +``` + +### Gentoo Linux + +:::{image} https://repology.org/badge/version-for-repo/gentoo_ovl_guru/ocrmypdf.svg +:alt: Gentoo Linux +:target: https://repology.org/metapackage/ocrmypdf +::: + +To install OCRmyPDF on Gentoo Linux, use the following commands: + +```bash +eselect repository enable guru +emaint sync --repo guru +emerge --ask app-text/OCRmyPDF +``` + +### Other Linux packages + +See the +[Repology](https://repology.org/metapackage/ocrmypdf/versions) page. + +In general, first install the OCRmyPDF package for your system, then +optionally use the procedure [Installing with Python +pip](#installing-with-python-pip) to install a more recent version. + +## Installing on macOS + +### Homebrew + +:::{image} https://img.shields.io/homebrew/v/ocrmypdf.svg +:alt: homebrew +:target: https://formulae.brew.sh/formula/ocrmypdf +::: + +OCRmyPDF is now a standard [Homebrew](https://brew.sh) formula. To +install on macOS: + +```bash +brew install ocrmypdf +``` + +This will include only the English language pack. If you need other +languages you can optionally install them all: + +```bash +brew install tesseract-lang # Optional: Install all language packs +``` + +### MacPorts + +:::{image} https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fports.macports.org%2Fapi%2Fv1%2Fports%2Focrmypdf%2F%3Fformat%3Djson&query=version&label=MacPorts +:alt: Macports Version Information +:target: https://ports.macports.org/port/ocrmypdf +::: + +OCRmyPDF is includes in MacPorts: + +```bash +sudo port install ocrmypdf +``` + +Note that while this will install tesseract you will need to install +the appropriate tesseract [language ports](https://ports.macports.org/search/?selected_facets=categories_exact%3Atextproc&installed_file=&q=tesseract&name=on). + +### Manual installation on macOS + +These instructions probably work on all macOS supported by Homebrew, and are +for installing a more current version of OCRmyPDF than is available from +Homebrew. Note that the Homebrew versions usually track the release versions +fairly closely. + +If it's not already present, [install Homebrew](http://brew.sh/). + +Update Homebrew: + +```bash +brew update +``` + +Install or upgrade the required Homebrew packages, if any are missing. +To do this, use `brew edit ocrmypdf` to obtain a recent list of Homebrew +dependencies. You could also check the `.workflows/build.yml`. + +This will include the English, French, German and Spanish language +packs. If you need other languages you can optionally install them all: + +(macos-all-languages)= + +> ```bash +> brew install tesseract-lang # Option 2: for all language packs +> ``` + +Update the homebrew pip: + +```bash +pip install --upgrade pip +``` + +You can then install OCRmyPDF from PyPI for the current user: + +```bash +pip install --user ocrmypdf +``` + +The command line program should now be available: + +```bash +ocrmypdf --help +``` + +## Installing on Windows + +### Native Windows + +% If you have a Windows that is not the Home edition, you can use Windows Sandbox to test on a blank Windows instance. +% https://learn.microsoft.com/en-us/windows/security/application-security/application-isolation/windows-sandbox/ + +:::{note} +Administrator privileges will be required for some of these steps. +::: + +You must install the following for Windows: + +- Python 64-bit +- Tesseract 64-bit +- Ghostscript 64-bit + +Using the [winget](https://docs.microsoft.com/en-us/windows/package-manager/winget/) +package manager: + +- `winget install -e --id Python.Python.3.11` +- `winget install -e --id UB-Mannheim.TesseractOCR` + +You will need to install Ghostscript manually, [since it does not support automated +installs anymore](https://artifex.com/news/ghostscript-10.01.0-disabling-silent-install-option). + +- [Ghostscript download page](https://ghostscript.com/releases/gsdnld.html).\` + +(Or alternately, using the [Chocolatey](https://chocolatey.org/) package manager, install +the following when running in an Administrator command prompt): + +- `choco install python3` +- `choco install --pre tesseract` +- `choco install pngquant` (optional) + +Either set of commands will install the required software. At the moment there is no +single command to install Windows. + +You may then use `pip` to install ocrmypdf. (This can performed by a user or +Administrator.): + +- `python3 -m pip install ocrmypdf` + +% The Windows Python versions do not place any python or python3 executable in the path. +% They add the py launcher to the path: +% https://docs.python.org/3/using/windows.html#python-launcher-for-windows + +If you installed Python using WinGet, then use the following command instead: + +- `py -m pip install ocrmypdf` + +and use: + +- `py -m ocrmypdf` + +To start OCRmyPDF. + +If you intend to use more Python software on your Windows machine, consider the use of +[pipx](https://pipx.pypa.io/stable/) or a similar tool to create isolated Python +environments for each Python software that you want to use. + +OCRmyPDF will check the Windows Registry and standard locations in your Program Files +for third party software it needs (specifically, Tesseract and Ghostscript). To +override the versions OCRmyPDF selects, you can modify the `PATH` environment +variable. [Follow these directions](https://www.computerhope.com/issues/ch000549.htm#dospath) +to change the PATH. + +:::{warning} +As of early 2021, users have reported problems with the Microsoft Store version of +Python and OCRmyPDF. These issues affect many other third party Python packages. +Please download Python from Python.org or a package manager instead of the +Microsoft Store version. +::: + +:::{warning} +32-bit Windows is not supported. +::: + +### Windows Subsystem for Linux + +1. Install Ubuntu 22.04 for Windows Subsystem for Linux, if not already installed. +2. Follow the procedure to install {ref}`OCRmyPDF on Ubuntu 22.04 `. +3. Open the Windows command prompt and create a symlink: + +```powershell +wsl sudo ln -s /home/$USER/.local/bin/ocrmypdf /usr/local/bin/ocrmypdf +``` + +Then confirm that the expected version from PyPI ({{ latest }}) is installed: + +```powershell +wsl ocrmypdf --version +``` + +You can then run OCRmyPDF in the Windows command prompt or Powershell, prefixing +`wsl`, and call it from Windows programs or batch files. + +### Cygwin64 + +First install the the following prerequisite Cygwin packages using `setup-x86_64.exe`: + +``` +python310 (or later) +python3?-devel +python3?-pip +python3?-lxml +python3?-imaging + + (where 3? means match the version of python3 you installed) + +gcc-g++ +ghostscript +libexempi3 +libexempi-devel +libffi6 +libffi-devel +pngquant +qpdf +libqpdf-devel +tesseract-ocr +tesseract-ocr-devel +``` + +Then open a Cygwin terminal (i.e. `mintty`), run the following commands. Note +that if you are using the version of `pip` that was installed with the Cygwin +Python package, the command name will be `pip3`. If you have since updated +`pip` (with, for instance `pip3 install --upgrade pip`) the the command is +likely just `pip` instead of `pip3`: + +```bash +pip3 install wheel +pip3 install ocrmypdf +``` + +The optional dependency "unpaper" that is currently not available under Cygwin. +Without it, certain options such as `--clean` will produce an error message. +However, the OCR-to-text-layer functionality is available. + +### Docker + +You can also [Install the Docker image](docker) on Windows. Ensure that +your command prompt can run the docker "hello world" container. + +## Installing on FreeBSD + +:::{image} https://repology.org/badge/version-for-repo/freebsd/ocrmypdf.svg +:alt: FreeBSD +:target: https://repology.org/project/ocrmypdf/versions +::: + +```bash +pkg install textproc/py-ocrmypdf +``` + +To install a more recent version, you could attempt to first install the system +version with `pkg`, then use `pip install --user ocrmypdf`. + +## Installing the Docker image + +For some users, installing the Docker image will be easier than +installing all of OCRmyPDF's dependencies. + +See [Installing the Docker image](docker) for more information. + +(installing-with-python-pip)= + +## Installing with Python pip + +OCRmyPDF is delivered by PyPI because it is a convenient way to install +the latest version. However, PyPI and `pip` cannot address the fact +that `ocrmypdf` depends on certain non-Python system libraries and +programs being installed. + +For best results, first install [your platform's +version](https://repology.org/metapackage/ocrmypdf/versions) of +`ocrmypdf`, using the instructions elsewhere in this document. Then +you can use `pip` to get the latest version if your platform version +is out of date. Chances are that this will satisfy most dependencies. + +Use `ocrmypdf --version` to confirm what version was installed. + +Then you can install the latest OCRmyPDF from the Python wheels. First +try: + +```bash +pip install --user ocrmypdf +``` + +(If the message appears `Requirement already satisfied: ocrmypdf in...`, +you will need to use `pip install --user --upgrade ocrmypdf`.) + +You should then be able to run `ocrmypdf --version` and see that the +latest version was located. + +## Installing with pipx + +Some users may prefer pipx. As with the method above, you will need to +satisfy all non-Python dependencies. Then if pipx is installed, you +can use + +```bash +pipx run ocrmypdf +``` + +(If not installed, pipx will install first.) + +(requirements-for-pip-and-head-install)= + +### Requirements for pip and HEAD install + +OCRmyPDF currently requires these external programs and libraries to be +installed, and must be satisfied using the operating system package +manager. `pip` cannot provide them. + +The following versions are required: + +- Python 3.10 or newer +- Ghostscript 9.54 or newer +- Tesseract 4.1.1 or newer +- jbig2enc 0.29 or newer +- pngquant 2.5 or newer +- unpaper 6.1 + +We recommend 64-bit versions of all software. (32-bit versions are not +supported, although on Linux, they may still work.) + +jbig2enc, pngquant, and unpaper are optional. If missing certain +features are disabled. OCRmyPDF will discover them as soon as they are +available. + +**jbig2enc**, if present, will be used to optimize the encoding of +monochrome images. This can significantly reduce the file size of the +output file. It is not required. +[jbig2enc](https://github.com/agl/jbig2enc) is not generally +available for Ubuntu or Debian due to lingering concerns about patent +issues, but can easily be built from source. To add JBIG2 encoding, see +{ref}`jbig2`. + +**pngquant**, if present, is optionally used to optimize the encoding of +PNG-style images in PDFs (actually, any that are that losslessly +encoded) by lossily quantizing to a smaller color palette. It is only +activated then the `--optimize` argument is `2` or `3`. + +**unpaper**, if present, enables the `--clean` and `--clean-final` +command line options. + +These are in addition to the Python packaging dependencies, meaning that +unfortunately, the `pip install` command cannot satisfy all of them. + +(installing-head-revision-from-sources)= + +## Installing HEAD revision from sources + +If you have `git` and Python 3.10 or newer installed, you can install +from source. When the `pip` installer runs, it will alert you if +dependencies are missing. + +If you prefer to build every from source, you will need to [build +pikepdf from +source](https://pikepdf.readthedocs.io/en/latest/installation.html#building-from-source). +First ensure you can build and install pikepdf. + +To install the HEAD revision from sources in the current Python 3 +environment: + +```bash +pip install git+https://github.com/ocrmypdf/OCRmyPDF.git +``` + +Or, to install in editable mode +allowing customization of OCRmyPDF, use the `-e` flag: + +```bash +pip install -e git+https://github.com/ocrmypdf/OCRmyPDF.git +``` + +You may find it easiest to install in a virtual environment, rather than +system-wide: + +```bash +git clone -b main https://github.com/ocrmypdf/OCRmyPDF.git +python3 -m venv .venv +source .venv/bin/activate +cd OCRmyPDF +pip install . +``` + +However, `ocrmypdf` will only be accessible on the system PATH when +you activate the virtual environment. + +To run the program: + +```bash +ocrmypdf --help +``` + +If not yet installed, the script will notify you about dependencies that +need to be installed. The script requires specific versions of the +dependencies. Older version than the ones mentioned in the release notes +are likely not to be compatible to OCRmyPDF. + +### For development + +To install all of the development and test requirements: + +```bash +git clone -b main https://github.com/ocrmypdf/OCRmyPDF.git +python -m venv .venv +source .venv/bin/activate +cd OCRmyPDF +pip install -e .[test] +``` + +To add JBIG2 encoding, see {ref}`jbig2`. + +## Shell completions + +Completions for `bash` and `fish` are available in the project's +`misc/completion` folder. The `bash` completions are likely `zsh` +compatible but this has not been confirmed. Package maintainers, please +install these at the appropriate locations for your system. + +To manually install the `bash` completion, copy +`misc/completion/ocrmypdf.bash` to `/etc/bash_completion.d/ocrmypdf` +(rename the file). + +To manually install the `fish` completion, copy +`misc/completion/ocrmypdf.fish` to +`~/.config/fish/completions/ocrmypdf.fish`. + +## Note on 32-bit support + +Many Python libraries no longer provide 32-bit binary wheels for Linux. This +includes many of the libraries that OCRmyPDF depends on, such as +Pillow. The easiest way to express this to end users is to say we don't +support 32-bit Linux. + +However, if your Linux distribution still supports 32-bit binaries, you +can still install and use OCRmyPDF. A warning message will appear. +In practice, OCRmyPDF may need more than 32-bit memory space to run when +large documents are processed, so there are practical limitations to what +users can accomplish with it. Still, for the common use case of an 32-bit +ARM NAS or Raspberry Pi processing small documents, it should work. diff --git a/docs/installation.rst b/docs/installation.rst deleted file mode 100644 index 26e5b2bc..00000000 --- a/docs/installation.rst +++ /dev/null @@ -1,740 +0,0 @@ -.. SPDX-FileCopyrightText: 2022 James R. Barlow -.. -.. SPDX-License-Identifier: CC-BY-SA-4.0 - -=================== -Installing OCRmyPDF -=================== - -.. |latest| image:: https://img.shields.io/pypi/v/ocrmypdf.svg - :alt: OCRmyPDF latest released version on PyPI - -|latest| - -The easiest way to install OCRmyPDF is to follow the steps for your operating -system/platform. This version may be out of date, however. - -These platforms have one-liner installs: - -+-------------------------------+-----------------------------------------+ -| Debian, Ubuntu | ``apt install ocrmypdf`` | -+-------------------------------+-----------------------------------------+ -| Windows Subsystem for Linux | ``apt install ocrmypdf`` | -+-------------------------------+-----------------------------------------+ -| Fedora | ``dnf install ocrmypdf tesseract-osd`` | -+-------------------------------+-----------------------------------------+ -| macOS (Homebrew) | ``brew install ocrmypdf`` | -+-------------------------------+-----------------------------------------+ -| macOS (MacPorts) | ``port install ocrmypdf`` | -+-------------------------------+-----------------------------------------+ -| LinuxBrew | ``brew install ocrmypdf`` | -+-------------------------------+-----------------------------------------+ -| FreeBSD | ``pkg install textproc/py-ocrmypdf`` | -+-------------------------------+-----------------------------------------+ -| Snap (snapcraft packaging) | ``snap install ocrmypdf`` | -+-------------------------------+-----------------------------------------+ - -More detailed procedures are outlined below. If you want to do a manual -install, or install a more recent version than your platform provides, read on. - -.. contents:: Platform-specific steps - :depth: 2 - :local: - -Installing on Linux -=================== - -Debian and Ubuntu 20.04 or newer --------------------------------- - -.. |deb-11| image:: https://repology.org/badge/version-for-repo/debian_11/ocrmypdf.svg - :alt: Debian 11 - -.. |deb-12| image:: https://repology.org/badge/version-for-repo/debian_12/ocrmypdf.svg - :alt: Debian 12 - -.. |deb-unstable| image:: https://repology.org/badge/version-for-repo/debian_unstable/ocrmypdf.svg - :alt: Debian unstable - -.. |ubu-2004| image:: https://repology.org/badge/version-for-repo/ubuntu_20_04/ocrmypdf.svg - :alt: Ubuntu 20.04 LTS - -.. |ubu-2204| image:: https://repology.org/badge/version-for-repo/ubuntu_22_04/ocrmypdf.svg - :alt: Ubuntu 22.04 LTS - -+-----------------------------------------------+ -| **OCRmyPDF versions in Debian & Ubuntu** | -+-----------------------------------------------+ -| |latest| | -+-----------------------------------------------+ -| |deb-11| |deb-12| |deb-unstable| | -+-----------------------------------------------+ -| |ubu-2004| |ubu-2204| | -+-----------------------------------------------+ - -Users of Debian or Ubuntu may simply - -.. code-block:: bash - - apt install ocrmypdf - -As indicated in the table above, Debian and Ubuntu releases may lag -behind the latest version. If the version available for your platform is -out of date, you could opt to install the latest version from source. -See `Installing HEAD revision from -sources <#installing-head-revision-from-sources>`__. - -For full details on version availability for your platform, check the -`Debian Package Tracker `__ or -`Ubuntu launchpad.net `__. - -.. note:: - - OCRmyPDF for Debian and Ubuntu currently omit the JBIG2 encoder. - OCRmyPDF works fine without it but will produce larger output files. - If you build jbig2enc from source, ocrmypdf will - automatically detect it (specifically the ``jbig2`` binary) on the - ``PATH``. To add JBIG2 encoding, see :ref:`jbig2`. - -Fedora ------- - -.. |fedora-38| image:: https://repology.org/badge/version-for-repo/fedora_38/ocrmypdf.svg - :alt: Fedora 38 - -.. |fedora-39| image:: https://repology.org/badge/version-for-repo/fedora_39/ocrmypdf.svg - :alt: Fedora 39 - -.. |fedora-rawhide| image:: https://repology.org/badge/version-for-repo/fedora_rawhide/ocrmypdf.svg - :alt: Fedore Rawhide - -+-----------------------------------------------+ -| **OCRmyPDF version** | -+-----------------------------------------------+ -| |latest| | -+-----------------------------------------------+ -| |fedora-38| |fedora-39| |fedora-rawhide| | -+-----------------------------------------------+ - -Users of Fedora may simply - -.. code-block:: bash - - dnf install ocrmypdf tesseract-osd - -For full details on version availability, check the `Fedora Package -Tracker `__. - -If the version available for your platform is out of date, you could opt -to install the latest version from source. See `Installing HEAD revision -from sources <#installing-head-revision-from-sources>`__. - -.. note:: - - OCRmyPDF for Fedora currently omits the JBIG2 encoder due to patent - issues. OCRmyPDF works fine without it but will produce larger output - files. If you build jbig2enc from source, ocrmypdf 7.0.0 and later - will automatically detect it on the ``PATH``. To add JBIG2 encoding, - see :ref:`Installing the JBIG2 encoder `. - -.. _ubuntu-lts-latest: - -RHEL 9 ------- - -Prepare the environment by getting Python 3.11: - -.. code-block:: bash - - dnf install python3.11 python3.11-pip - -Then, follow `Requirements for pip and HEAD install <#requirements-for-pip-and-head-install>`__ to install dependencies: - -.. code-block:: bash - - dnf install ghostscript tesseract - -and build ocrmypdf in virtual environment: - -.. code-block:: bash - - python3.11 -m venv .venv - -To add JBIG2 encoding, see :ref:`Installing the JBIG2 encoder `. - -Note Fedora packages for language data haven't been branched for RHEL/EPEL, but you can get traineddata files directly from `tesseract -`__ and place them in ``/usr/share/tesseract/tessdata``. - -Installing the latest version on Ubuntu 22.04 LTS -------------------------------------------------- - -Ubuntu 22.04 includes ocrmypdf 13.4.0 - you can install that with -``apt install ocrmypdf``. To install a more recent version for the current -user, follow these steps: - -.. code-block:: bash - - sudo apt-get update - sudo apt-get -y install ocrmypdf python3-pip - - pip install --user --upgrade ocrmypdf - -If you get the message ``WARNING: The script ocrmypdf is installed in -'/home/$USER/.local/bin' which is not on PATH.``, you may need to re-login -or open a new shell, or manually adjust your PATH. - -To add JBIG2 encoding, see :ref:`jbig2`. - -Ubuntu 20.04 LTS ----------------- - -Ubuntu 20.04 includes ocrmypdf 9.6.0 - you can install that with ``apt``. The -most convenient way to install recent OCRmyPDF on older Ubuntu is to use -Homebrew on Linux (Linuxbrew). - -.. code-block:: bash - - brew install ocrmypdf - -Arch Linux (AUR) ----------------- - -.. image:: https://repology.org/badge/version-for-repo/aur/ocrmypdf.svg - :alt: ArchLinux - :target: https://repology.org/metapackage/ocrmypdf - -There is an `Arch User Repository (AUR) package for OCRmyPDF -`__. - -Installing AUR packages as root is not allowed, so you must first `setup a -non-root user -`__ and -`configure sudo `__. -The standard Docker image, ``archlinux/base:latest``, does **not** have a -non-root user configured, so users of that image must follow these guides. If -you are using a VM image, such as `the official Vagrant image -`__, this work may already -be completed for you. - -Next you should install the `base-devel package group -`__. This includes the -standard tooling needed to build packages, such as a compiler and binary tools. - -.. code-block:: bash - - sudo pacman -S --needed base-devel - -Now you are ready to install the OCRmyPDF package. - -.. code-block:: bash - - curl -O https://aur.archlinux.org/cgit/aur.git/snapshot/ocrmypdf.tar.gz - tar xvzf ocrmypdf.tar.gz - cd ocrmypdf - makepkg -sri - -At this point you will have a working install of OCRmyPDF, but the Tesseract -install won’t include any OCR language data. You can install `the -tesseract-data package group -`__ to add all supported -languages, or use that package listing to identify the appropriate package for -your desired language. - -.. code-block:: bash - - sudo pacman -S tesseract-data-eng - -As an alternative to this manual procedure, consider using an `AUR helper -`__. Such a tool will -automatically fetch, build and install the AUR package, resolve dependencies -(including dependencies on AUR packages), and ease the upgrade procedure. - -If you have any difficulties with installation, check the repository package -page. - -.. note:: - - The OCRmyPDF AUR package currently omits the JBIG2 encoder. OCRmyPDF works - fine without it but will produce larger output files. The encoder is - available from `the jbig2enc-git AUR package - `__ and may be installed - using the same series of steps as for the installation OCRmyPDF AUR - package. Alternatively, it may be built manually from source following the - instructions in :ref:`Installing the JBIG2 encoder `. If JBIG2 is - installed, OCRmyPDF 7.0.0 and later will automatically detect it. - -Alpine Linux ------------- - -.. image:: https://repology.org/badge/version-for-repo/alpine_edge/ocrmypdf.svg - :alt: Alpine Linux - :target: https://repology.org/metapackage/ocrmypdf - -To install OCRmyPDF for Alpine Linux: - -.. code-block:: bash - - apk add ocrmypdf - -Gentoo Linux ------------- - -.. image:: https://repology.org/badge/version-for-repo/gentoo_ovl_guru/ocrmypdf.svg - :alt: Gentoo Linux - :target: https://repology.org/metapackage/ocrmypdf - -To install OCRmyPDF on Gentoo Linux, use the following commands: - -.. code-block:: bash - - eselect repository enable guru - emaint sync --repo guru - emerge --ask app-text/OCRmyPDF - -Other Linux packages --------------------- - -See the -`Repology `__ page. - -In general, first install the OCRmyPDF package for your system, then -optionally use the procedure `Installing with Python -pip <#installing-with-python-pip>`__ to install a more recent version. - -Installing on macOS -=================== - -Homebrew --------- - -.. image:: https://img.shields.io/homebrew/v/ocrmypdf.svg - :alt: homebrew - :target: https://formulae.brew.sh/formula/ocrmypdf - -OCRmyPDF is now a standard `Homebrew `__ formula. To -install on macOS: - -.. code-block:: bash - - brew install ocrmypdf - -This will include only the English language pack. If you need other -languages you can optionally install them all: - -.. code-block:: bash - - brew install tesseract-lang # Optional: Install all language packs - -MacPorts --------- - -.. image:: https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fports.macports.org%2Fapi%2Fv1%2Fports%2Focrmypdf%2F%3Fformat%3Djson&query=version&label=MacPorts - :alt: Macports Version Information - :target: https://ports.macports.org/port/ocrmypdf - -OCRmyPDF is includes in MacPorts: - -.. code-block:: bash - - sudo port install ocrmypdf - -Note that while this will install tesseract you will need to install -the appropriate tesseract `language ports `__. - -Manual installation on macOS ----------------------------- - -These instructions probably work on all macOS supported by Homebrew, and are -for installing a more current version of OCRmyPDF than is available from -Homebrew. Note that the Homebrew versions usually track the release versions -fairly closely. - -If it's not already present, `install Homebrew `__. - -Update Homebrew: - -.. code-block:: bash - - brew update - -Install or upgrade the required Homebrew packages, if any are missing. -To do this, use ``brew edit ocrmypdf`` to obtain a recent list of Homebrew -dependencies. You could also check the ``.workflows/build.yml``. - -This will include the English, French, German and Spanish language -packs. If you need other languages you can optionally install them all: - -.. _macos-all-languages: - - .. code-block:: bash - - brew install tesseract-lang # Option 2: for all language packs - -Update the homebrew pip: - -.. code-block:: bash - - pip install --upgrade pip - -You can then install OCRmyPDF from PyPI for the current user: - -.. code-block:: bash - - pip install --user ocrmypdf - -The command line program should now be available: - -.. code-block:: bash - - ocrmypdf --help - -Installing on Windows -===================== - -Native Windows --------------- - -.. - If you have a Windows that is not the Home edition, you can use Windows Sandbox to test on a blank Windows instance. - https://learn.microsoft.com/en-us/windows/security/application-security/application-isolation/windows-sandbox/ - -.. note:: - - Administrator privileges will be required for some of these steps. - -You must install the following for Windows: - -* Python 64-bit -* Tesseract 64-bit -* Ghostscript 64-bit - -Using the `winget `_ -package manager: - -* ``winget install -e --id Python.Python.3.11`` -* ``winget install -e --id UB-Mannheim.TesseractOCR`` - -You will need to install Ghostscript manually, `since it does not support automated -installs anymore `_. - -* `Ghostscript download page `_.` - -(Or alternately, using the `Chocolatey `_ package manager, install -the following when running in an Administrator command prompt): - -* ``choco install python3`` -* ``choco install --pre tesseract`` -* ``choco install pngquant`` (optional) - -Either set of commands will install the required software. At the moment there is no -single command to install Windows. - -You may then use ``pip`` to install ocrmypdf. (This can performed by a user or -Administrator.): - -* ``python3 -m pip install ocrmypdf`` - -.. - The Windows Python versions do not place any python or python3 executable in the path. - They add the py launcher to the path: - https://docs.python.org/3/using/windows.html#python-launcher-for-windows - -If you installed Python using WinGet, then use the following command instead: - -* ``py -m pip install ocrmypdf`` - -and use: - -* ``py -m ocrmypdf`` - -To start OCRmyPDF. - -If you intend to use more Python software on your Windows machine, consider the use of -`pipx `_ or a similar tool to create isolated Python -environments for each Python software that you want to use. - -OCRmyPDF will check the Windows Registry and standard locations in your Program Files -for third party software it needs (specifically, Tesseract and Ghostscript). To -override the versions OCRmyPDF selects, you can modify the ``PATH`` environment -variable. `Follow these directions `_ -to change the PATH. - -.. warning:: - - As of early 2021, users have reported problems with the Microsoft Store version of - Python and OCRmyPDF. These issues affect many other third party Python packages. - Please download Python from Python.org or a package manager instead of the - Microsoft Store version. - -.. warning:: - - 32-bit Windows is not supported. - -Windows Subsystem for Linux ---------------------------- - -#. Install Ubuntu 22.04 for Windows Subsystem for Linux, if not already installed. -#. Follow the procedure to install :ref:`OCRmyPDF on Ubuntu 22.04 `. -#. Open the Windows command prompt and create a symlink: - -.. code-block:: powershell - - wsl sudo ln -s /home/$USER/.local/bin/ocrmypdf /usr/local/bin/ocrmypdf - -Then confirm that the expected version from PyPI (|latest|) is installed: - -.. code-block:: powershell - - wsl ocrmypdf --version - -You can then run OCRmyPDF in the Windows command prompt or Powershell, prefixing -``wsl``, and call it from Windows programs or batch files. - -Cygwin64 --------- - -First install the the following prerequisite Cygwin packages using ``setup-x86_64.exe``:: - - python310 (or later) - python3?-devel - python3?-pip - python3?-lxml - python3?-imaging - - (where 3? means match the version of python3 you installed) - - gcc-g++ - ghostscript - libexempi3 - libexempi-devel - libffi6 - libffi-devel - pngquant - qpdf - libqpdf-devel - tesseract-ocr - tesseract-ocr-devel - -Then open a Cygwin terminal (i.e. ``mintty``), run the following commands. Note -that if you are using the version of ``pip`` that was installed with the Cygwin -Python package, the command name will be ``pip3``. If you have since updated -``pip`` (with, for instance ``pip3 install --upgrade pip``) the the command is -likely just ``pip`` instead of ``pip3``: - -.. code-block:: bash - - pip3 install wheel - pip3 install ocrmypdf - -The optional dependency "unpaper" that is currently not available under Cygwin. -Without it, certain options such as ``--clean`` will produce an error message. -However, the OCR-to-text-layer functionality is available. - -Docker ------- - -You can also :ref:`Install the Docker ` container on Windows. Ensure that -your command prompt can run the docker "hello world" container. - -Installing on FreeBSD -===================== - -.. image:: https://repology.org/badge/version-for-repo/freebsd/ocrmypdf.svg - :alt: FreeBSD - :target: https://repology.org/project/ocrmypdf/versions - -.. code-block:: bash - - pkg install textproc/py-ocrmypdf - -To install a more recent version, you could attempt to first install the system -version with ``pkg``, then use ``pip install --user ocrmypdf``. - -Installing the Docker image -=========================== - -For some users, installing the Docker image will be easier than -installing all of OCRmyPDF's dependencies. - -See :ref:`docker` for more information. - -Installing with Python pip -========================== - -OCRmyPDF is delivered by PyPI because it is a convenient way to install -the latest version. However, PyPI and ``pip`` cannot address the fact -that ``ocrmypdf`` depends on certain non-Python system libraries and -programs being installed. - -For best results, first install `your platform's -version `__ of -``ocrmypdf``, using the instructions elsewhere in this document. Then -you can use ``pip`` to get the latest version if your platform version -is out of date. Chances are that this will satisfy most dependencies. - -Use ``ocrmypdf --version`` to confirm what version was installed. - -Then you can install the latest OCRmyPDF from the Python wheels. First -try: - -.. code-block:: bash - - pip install --user ocrmypdf - -(If the message appears ``Requirement already satisfied: ocrmypdf in...``, -you will need to use ``pip install --user --upgrade ocrmypdf``.) - -You should then be able to run ``ocrmypdf --version`` and see that the -latest version was located. - -Installing with pipx -==================== - -Some users may prefer pipx. As with the method above, you will need to -satisfy all non-Python dependencies. Then if pipx is installed, you -can use - -.. code-block:: bash - - pipx run ocrmypdf - -(If not installed, pipx will install first.) - -Requirements for pip and HEAD install -------------------------------------- - -OCRmyPDF currently requires these external programs and libraries to be -installed, and must be satisfied using the operating system package -manager. ``pip`` cannot provide them. - -The following versions are required: - -- Python 3.10 or newer -- Ghostscript 9.54 or newer -- Tesseract 4.1.1 or newer -- jbig2enc 0.29 or newer -- pngquant 2.5 or newer -- unpaper 6.1 - -We recommend 64-bit versions of all software. (32-bit versions are not -supported, although on Linux, they may still work.) - -jbig2enc, pngquant, and unpaper are optional. If missing certain -features are disabled. OCRmyPDF will discover them as soon as they are -available. - -**jbig2enc**, if present, will be used to optimize the encoding of -monochrome images. This can significantly reduce the file size of the -output file. It is not required. -`jbig2enc `__ is not generally -available for Ubuntu or Debian due to lingering concerns about patent -issues, but can easily be built from source. To add JBIG2 encoding, see -:ref:`jbig2`. - -**pngquant**, if present, is optionally used to optimize the encoding of -PNG-style images in PDFs (actually, any that are that losslessly -encoded) by lossily quantizing to a smaller color palette. It is only -activated then the ``--optimize`` argument is ``2`` or ``3``. - -**unpaper**, if present, enables the ``--clean`` and ``--clean-final`` -command line options. - -These are in addition to the Python packaging dependencies, meaning that -unfortunately, the ``pip install`` command cannot satisfy all of them. - -Installing HEAD revision from sources -===================================== - -If you have ``git`` and Python 3.10 or newer installed, you can install -from source. When the ``pip`` installer runs, it will alert you if -dependencies are missing. - -If you prefer to build every from source, you will need to `build -pikepdf from -source `__. -First ensure you can build and install pikepdf. - -To install the HEAD revision from sources in the current Python 3 -environment: - -.. code-block:: bash - - pip install git+https://github.com/ocrmypdf/OCRmyPDF.git - -Or, to install in editable mode -allowing customization of OCRmyPDF, use the ``-e`` flag: - -.. code-block:: bash - - pip install -e git+https://github.com/ocrmypdf/OCRmyPDF.git - -You may find it easiest to install in a virtual environment, rather than -system-wide: - -.. code-block:: bash - - git clone -b main https://github.com/ocrmypdf/OCRmyPDF.git - python3 -m venv .venv - source .venv/bin/activate - cd OCRmyPDF - pip install . - -However, ``ocrmypdf`` will only be accessible on the system PATH when -you activate the virtual environment. - -To run the program: - -.. code-block:: bash - - ocrmypdf --help - -If not yet installed, the script will notify you about dependencies that -need to be installed. The script requires specific versions of the -dependencies. Older version than the ones mentioned in the release notes -are likely not to be compatible to OCRmyPDF. - -For development ---------------- - -To install all of the development and test requirements: - -.. code-block:: bash - - git clone -b main https://github.com/ocrmypdf/OCRmyPDF.git - python -m venv .venv - source .venv/bin/activate - cd OCRmyPDF - pip install -e .[test] - -To add JBIG2 encoding, see :ref:`jbig2`. - -Shell completions -================= - -Completions for ``bash`` and ``fish`` are available in the project's -``misc/completion`` folder. The ``bash`` completions are likely ``zsh`` -compatible but this has not been confirmed. Package maintainers, please -install these at the appropriate locations for your system. - -To manually install the ``bash`` completion, copy -``misc/completion/ocrmypdf.bash`` to ``/etc/bash_completion.d/ocrmypdf`` -(rename the file). - -To manually install the ``fish`` completion, copy -``misc/completion/ocrmypdf.fish`` to -``~/.config/fish/completions/ocrmypdf.fish``. - -Note on 32-bit support -====================== - -Many Python libraries no longer provide 32-bit binary wheels for Linux. This -includes many of the libraries that OCRmyPDF depends on, such as -Pillow. The easiest way to express this to end users is to say we don't -support 32-bit Linux. - -However, if your Linux distribution still supports 32-bit binaries, you -can still install and use OCRmyPDF. A warning message will appear. -In practice, OCRmyPDF may need more than 32-bit memory space to run when -large documents are processed, so there are practical limitations to what -users can accomplish with it. Still, for the common use case of an 32-bit -ARM NAS or Raspberry Pi processing small documents, it should work. diff --git a/docs/introduction.rst b/docs/introduction.md similarity index 68% rename from docs/introduction.rst rename to docs/introduction.md index 53f06968..45c38fc7 100644 --- a/docs/introduction.rst +++ b/docs/introduction.md @@ -1,10 +1,14 @@ -.. SPDX-FileCopyrightText: 2022 James R. Barlow -.. -.. SPDX-License-Identifier: CC-BY-SA-4.0 +--- +substitutions: + image: |- + ```{image} images/bitmap_vs_svg.svg + ``` +--- -============ -Introduction -============ +% SPDX-FileCopyrightText: 2022 James R. Barlow +% SPDX-License-Identifier: CC-BY-SA-4.0 + +# Introduction OCRmyPDF is a Python application and library that adds text "layers" to images in PDFs, making scanned image PDFs searchable. It uses OCR to guess the text @@ -13,31 +17,30 @@ that enable customization of its processing steps, and it is highly tolerant of PDFs containing scanned images and "born digital" content that doesn't require text recognition. -About OCR -========= +## About OCR -`Optical character -recognition `__ +[Optical character +recognition](https://en.wikipedia.org/wiki/Optical_character_recognition) is a technology that converts images of typed or handwritten text, such as in a scanned document, into computer text that can be selected, searched and copied. OCRmyPDF uses -`Tesseract `__, a widely +[Tesseract](https://github.com/tesseract-ocr/tesseract), a widely available open source OCR engine, to perform OCR. -.. _raster-vector: +(raster-vector)= -About PDFs -========== +## About PDFs PDFs are page description files that attempt to preserve a layout -exactly. They contain `vector -graphics `__ +exactly. They contain [vector +graphics](http://vector-conversions.com/vectorizing/raster_vs_vector.html) that can contain raster objects, such as scanned images. Because PDFs can contain multiple pages (unlike many image formats) and can contain fonts and text, they are a suitable format for exchanging scanned documents. -|image| +:::{image} images/bitmap_vs_svg.svg +::: A PDF page may contain multiple images, even if it appears to have only one image. Some scanners or scanning software may segment pages into @@ -48,10 +51,9 @@ Rasterizing a PDF is the process of generating corresponding raster images. OCR engines like Tesseract work with images, not scalable vector graphics or mixed raster-vector-text graphics such as PDF. -About PDF/A -=========== +## About PDF/A -`PDF/A `__ is an ISO-standardized +[PDF/A](https://en.wikipedia.org/wiki/PDF/A) is an ISO-standardized subset of the full PDF specification that is designed for archiving (the 'A' stands for Archive). PDF/A differs from PDF primarily by omitting features that could complicate future file readability, @@ -63,8 +65,8 @@ of embedded content, it is likely more secure. There are various conformance levels and versions, such as "PDF/A-2b". In general, the preferred format for scanned documents is PDF/A. Some -governments and jurisdictions, US Courts in particular, `mandate the use -of PDF/A `__ for scanned +governments and jurisdictions, US Courts in particular, [mandate the use +of PDF/A](https://pdfblog.com/2012/02/13/what-is-pdfa/) for scanned documents. Since most individuals scanning documents aim for long-term readability, @@ -78,13 +80,12 @@ files can be digitally signed but may not be encrypted to ensure future readability. Fortunately, converting from PDF/A to a regular PDF is straightforward, and any PDF viewer can handle PDF/A files. -What OCRmyPDF does -================== +## What OCRmyPDF does OCRmyPDF analyzes each page of a PDF to determine the required colorspace and resolution (DPI) for capturing all the information on that page without losing content. It uses -`Ghostscript `__ to rasterize each page and subsequently +[Ghostscript](http://ghostscript.com/) to rasterize each page and subsequently performs OCR on the rasterized image to generate an OCR "layer." This layer is then integrated back into the original PDF. @@ -101,10 +102,9 @@ options are utilized, the OCR layer is integrated into the processed image. By default, OCRmyPDF generates archival PDFs in the PDF/A format, which is a more rigid subset of PDF features designed for long-term archives. If you prefer regular PDFs, you can disable this feature using the -``--output-type pdf`` option. +`--output-type pdf` option. -Why you shouldn't do this manually -================================== +## Why you shouldn't do this manually A PDF is similar to an HTML file, in that it contains document structure along with images. While some PDFs may solely display a full-page image, @@ -142,55 +142,53 @@ like pikepdf and QPDF, it can auto-repair damaged PDFs. You don't need to understand the intricacies of these issues; you should be able to use OCRmyPDF with any PDF file, and expect reasonable results. -Limitations -=========== +## Limitations OCRmyPDF is subject to limitations imposed by the Tesseract OCR engine. These limitations are inherent to any software relying on Tesseract: -- The OCR accuracy may not match that of commercial OCR solutions. -- It is incapable of recognizing handwriting. -- It may detect gibberish and report it as OCR output. -- Results may be subpar when a document contains languages not specified - in the ``-l LANG`` argument. -- Tesseract may struggle to analyze the natural reading order of documents. - For instance, it might fail to recognize two columns in a document and - attempt to join text across columns. -- Poor quality scans can result in subpar OCR quality. In other words, the - quality of the OCR output depends on the quality of the input. -- Tesseract does not provide information about the font family to which text - belongs. -- Tesseract does not divide text into paragraphs or headings. It only provides - the text and its bounding box. As such, the generated PDF does not - contain any information about the document's structure. +- The OCR accuracy may not match that of commercial OCR solutions. +- It is incapable of recognizing handwriting. +- It may detect gibberish and report it as OCR output. +- Results may be subpar when a document contains languages not specified + in the `-l LANG` argument. +- Tesseract may struggle to analyze the natural reading order of documents. + For instance, it might fail to recognize two columns in a document and + attempt to join text across columns. +- Poor quality scans can result in subpar OCR quality. In other words, the + quality of the OCR output depends on the quality of the input. +- Tesseract does not provide information about the font family to which text + belongs. +- Tesseract does not divide text into paragraphs or headings. It only provides + the text and its bounding box. As such, the generated PDF does not + contain any information about the document's structure. Ghostscript also imposes some limitations: -- PDFs containing JPEG 2000-encoded content may be converted to JPEG - encoding, which may introduce compression artifacts, if Ghostscript - PDF/A is enabled. -- Ghostscript may transcode grayscale and color images, potentially - lossily, based on an internal algorithm. This - behavior can be suppressed by setting ``--pdfa-image-compression`` to - ``jpeg`` or ``lossless`` to set all images to one type or the other. - Ghostscript lacks an option to maintain the input image's format. - (Modern Ghostscript can copy JPEG images without transcoding them.) -- Ghostscript's PDF/A conversion removes any XMP metadata that is not - one of the standard XMP metadata namespaces for PDFs. In particular, - PRISM Metadata is removed. -- Ghostscript's PDF/A conversion may remove or deactivate - hyperlinks and other active content. +- PDFs containing JPEG 2000-encoded content may be converted to JPEG + encoding, which may introduce compression artifacts, if Ghostscript + PDF/A is enabled. +- Ghostscript may transcode grayscale and color images, potentially + lossily, based on an internal algorithm. This + behavior can be suppressed by setting `--pdfa-image-compression` to + `jpeg` or `lossless` to set all images to one type or the other. + Ghostscript lacks an option to maintain the input image's format. + (Modern Ghostscript can copy JPEG images without transcoding them.) +- Ghostscript's PDF/A conversion removes any XMP metadata that is not + one of the standard XMP metadata namespaces for PDFs. In particular, + PRISM Metadata is removed. +- Ghostscript's PDF/A conversion may remove or deactivate + hyperlinks and other active content. -You can use ``--output-type pdf`` to disable PDF/A conversion and produce +You can use `--output-type pdf` to disable PDF/A conversion and produce a standard, non-archival PDF. Regarding OCRmyPDF itself: -- PDFs using transparency are not currently represented in the test - suite +- PDFs using transparency are not currently represented in the test + suite -Similar programs -================ +## Similar programs To the author's knowledge, OCRmyPDF is the most feature-rich and thoroughly tested command line OCR PDF conversion tool. If it does not @@ -199,8 +197,7 @@ meet your needs, contributions and suggestions are welcome. Ghostscript recently added three "pdfocr" output devices. They work by rasterizing all content and converting all pages to a single colour space. -Web front-ends -============== +## Web front-ends The Docker image of OCRmyPDF provides a web service front-end that allows files to submitted over HTTP, and the results can be downloaded. @@ -210,16 +207,14 @@ public internet and does not provide any security measures. In addition, the following third-party integrations are available: -- `Paperless-ngx `__ is a free software - document management system that uses OCRmyPDF to perform OCR on - uploaded documents. -- `Nextcloud OCR `__ is a free software - plugin for the Nextcloud private cloud software. +- [Paperless-ngx](https://docs.paperless-ngx.com/) is a free software + document management system that uses OCRmyPDF to perform OCR on + uploaded documents. +- [Nextcloud OCR](https://github.com/janis91/ocr) is a free software + plugin for the Nextcloud private cloud software. OCRmyPDF is not designed to be secure against malware-bearing PDFs (see -`Using OCRmyPDF online `__). Users should ensure they +[Using OCRmyPDF online](ocr-service)). Users should ensure they comply with OCRmyPDF's licenses and the licenses of all dependencies. In particular, OCRmyPDF requires Ghostscript, which is licensed under AGPLv3. - -.. |image| image:: images/bitmap_vs_svg.svg diff --git a/docs/languages.md b/docs/languages.md new file mode 100644 index 00000000..c3d129f0 --- /dev/null +++ b/docs/languages.md @@ -0,0 +1,129 @@ +% SPDX-FileCopyrightText: 2022 James R. Barlow +% SPDX-License-Identifier: CC-BY-SA-4.0 + +(lang-packs)= + +# Installing additional language packs + +OCRmyPDF uses Tesseract for OCR, and relies on its language packs for all languages. +On most platforms, English is installed with Tesseract by default, but not always. + +Tesseract supports [most +languages](https://github.com/tesseract-ocr/tesseract/blob/main/doc/tesseract.1.asc#languages). +Languages are identified by standardized three-letter codes (called ISO 639-2 Alpha-3). +Tesseract's documentation also lists the three-letter code for your language. +Some are anglicized, e.g. Spanish is `spa` rather than `esp`, while others +are not, e.g. German is `deu` and French is `fra`. + +Language packs (strictly speaking, Tesseract "traineddata" files) generally correspond +to the language in question, but different language packs are used in certain +situations. For German, the "Fraktur" language pack can assist with reading older +materials in the Fraktur typeface family (`deu_frak`). Some communities have changed +their script from Cyrillic to Latin; the Cyrillic version of Uzbek is available +as `uzb_cyrl` and the Latin version is `uzb`. + +After you have installed a language pack, you can use it with `ocrmypdf -l `, +for example `ocrmypdf -l spa`. For multilingual documents, you can specify +all languages to be expected, e.g. `ocrmypdf -l eng+fra` for English and French. +English is assumed by default unless other language(s) are specified. + +For Linux users, you can often find packages that provide language +packs. + +## Platform install steps + +### Debian and Ubuntu (apt) + +```bash +# Display a list of all Tesseract language packs +apt-cache search tesseract-ocr + +# Install Chinese Simplified language pack +apt-get install tesseract-ocr-chi-sim +``` + +You can then pass the `-l LANG` argument to OCRmyPDF to give a hint as +to what languages it should search for. Multiple languages can be +requested using either `-l eng+fra` (English and French) or +`-l eng -l fra`. + +### Fedora + +```bash +# Display a list of all Tesseract language packs +dnf search tesseract + +# Install Chinese Simplified language pack +dnf install tesseract-langpack-chi_sim +``` + +You can then pass the `-l LANG` argument to OCRmyPDF to give a hint as +to what languages it should search for. Multiple languages can be +requested using either `-l eng+fra` (English and French) or +`-l eng -l fra`. + +### Arch Linux + +```bash +# Display a list of all Tesseract language packs +pacman -Ss tesseract-data + +# Install German language pack +pacman -S tesseract-data-deu +``` + +You can then pass the `-l LANG` argument to OCRmyPDF to give a hint as +to what languages it should search for. Multiple languages can be +requested using either `-l eng+fra` (English and French) or +`-l eng -l fra`. + +### Gentoo + +On Gentoo the package `app-text/tessdata_fast`, which `app-text/tesseract` depends on, handles Tesseract languages. +It accepts USE flags to select what languages should be installed, these can be set in `/etc/portage/package.use`. +Alternatively one can globally set the [L10N use extension](https://wiki.gentoo.org/wiki/Localization/Guide#L10N) in `/etc/portage/make.conf`. +This enables these languages for all packages (e.g. including aspell). + +```bash +# Display a list of all Tesseract language packs +equery uses app-text/tessdata_fast + +# Add English and German language support for Tesseract only +echo 'app-text/tessdata_fast l10n_de l10n_en' >> /etc/portage/package.use + +# Add global English and German language support (the `l10n_` from equery has to be omitted) +echo L10N="de en" >> /etc/portage/make.conf + +# update system to reflect changed USE flags +emerge --update --deep --newuse @world +``` + +You can then pass the `-l LANG` argument to OCRmyPDF to give a hint as +to what languages it should search for. Multiple languages can be +requested using either `-l eng+fra` (English and French) or +`-l eng -l fra`. + +### macOS + +You can install additional language packs by +{ref}`installing Tesseract using Homebrew with all language packs `. + +### Docker + +Users of the OCRmyPDF Docker image should install language packs into a +derived Docker image as +{ref}`described in that section `. + +### Windows + +The Tesseract installer provided by Chocolatey currently includes only English language. +To install other languages, download the respective language pack (`.traineddata` file) +from and place it in +`C:\\Program Files\\Tesseract-OCR\\tessdata` (or wherever Tesseract OCR is installed). + +## Custom language packs + +If you have fine-tuned or trained Tesseract and generated custom trained data, you can +copy your `customlang.traineddata` file into your Tesseract "tessdata" folder, and +then use the `-l customlang` argument to tell OCRmyPDF to pass that language on to +Tesseract. diff --git a/docs/languages.rst b/docs/languages.rst deleted file mode 100644 index b66f0e9b..00000000 --- a/docs/languages.rst +++ /dev/null @@ -1,141 +0,0 @@ -.. SPDX-FileCopyrightText: 2022 James R. Barlow -.. -.. SPDX-License-Identifier: CC-BY-SA-4.0 - -.. _lang-packs: - -==================================== -Installing additional language packs -==================================== - -OCRmyPDF uses Tesseract for OCR, and relies on its language packs for all languages. -On most platforms, English is installed with Tesseract by default, but not always. - -Tesseract supports `most -languages `__. -Languages are identified by standardized three-letter codes (called ISO 639-2 Alpha-3). -Tesseract's documentation also lists the three-letter code for your language. -Some are anglicized, e.g. Spanish is ``spa`` rather than ``esp``, while others -are not, e.g. German is ``deu`` and French is ``fra``. - -Language packs (strictly speaking, Tesseract "traineddata" files) generally correspond -to the language in question, but different language packs are used in certain -situations. For German, the "Fraktur" language pack can assist with reading older -materials in the Fraktur typeface family (``deu_frak``). Some communities have changed -their script from Cyrillic to Latin; the Cyrillic version of Uzbek is available -as ``uzb_cyrl`` and the Latin version is ``uzb``. - -After you have installed a language pack, you can use it with ``ocrmypdf -l ``, -for example ``ocrmypdf -l spa``. For multilingual documents, you can specify -all languages to be expected, e.g. ``ocrmypdf -l eng+fra`` for English and French. -English is assumed by default unless other language(s) are specified. - -For Linux users, you can often find packages that provide language -packs. - -Platform install steps -====================== - -Debian and Ubuntu (apt) ------------------------ - -.. code-block:: bash - - # Display a list of all Tesseract language packs - apt-cache search tesseract-ocr - - # Install Chinese Simplified language pack - apt-get install tesseract-ocr-chi-sim - -You can then pass the ``-l LANG`` argument to OCRmyPDF to give a hint as -to what languages it should search for. Multiple languages can be -requested using either ``-l eng+fra`` (English and French) or -``-l eng -l fra``. - -Fedora ------- - -.. code-block:: bash - - # Display a list of all Tesseract language packs - dnf search tesseract - - # Install Chinese Simplified language pack - dnf install tesseract-langpack-chi_sim - -You can then pass the ``-l LANG`` argument to OCRmyPDF to give a hint as -to what languages it should search for. Multiple languages can be -requested using either ``-l eng+fra`` (English and French) or -``-l eng -l fra``. - -Arch Linux ----------- - -.. code-block:: bash - - # Display a list of all Tesseract language packs - pacman -Ss tesseract-data - - # Install German language pack - pacman -S tesseract-data-deu - -You can then pass the ``-l LANG`` argument to OCRmyPDF to give a hint as -to what languages it should search for. Multiple languages can be -requested using either ``-l eng+fra`` (English and French) or -``-l eng -l fra``. - -Gentoo ------- - -On Gentoo the package ``app-text/tessdata_fast``, which ``app-text/tesseract`` depends on, handles Tesseract languages. -It accepts USE flags to select what languages should be installed, these can be set in ``/etc/portage/package.use``. -Alternatively one can globally set the `L10N use extension `__ in ``/etc/portage/make.conf``. -This enables these languages for all packages (e.g. including aspell). - -.. code-block:: bash - - # Display a list of all Tesseract language packs - equery uses app-text/tessdata_fast - - # Add English and German language support for Tesseract only - echo 'app-text/tessdata_fast l10n_de l10n_en' >> /etc/portage/package.use - - # Add global English and German language support (the `l10n_` from equery has to be omitted) - echo L10N="de en" >> /etc/portage/make.conf - - # update system to reflect changed USE flags - emerge --update --deep --newuse @world - -You can then pass the ``-l LANG`` argument to OCRmyPDF to give a hint as -to what languages it should search for. Multiple languages can be -requested using either ``-l eng+fra`` (English and French) or -``-l eng -l fra``. - -macOS ------ - -You can install additional language packs by -:ref:`installing Tesseract using Homebrew with all language packs `. - -Docker ------- - -Users of the OCRmyPDF Docker image should install language packs into a -derived Docker image as -:ref:`described in that section `. - -Windows -------- - -The Tesseract installer provided by Chocolatey currently includes only English language. -To install other languages, download the respective language pack (``.traineddata`` file) -from https://github.com/tesseract-ocr/tessdata/ and place it in -``C:\\Program Files\\Tesseract-OCR\\tessdata`` (or wherever Tesseract OCR is installed). - -Custom language packs -===================== - -If you have fine-tuned or trained Tesseract and generated custom trained data, you can -copy your ``customlang.traineddata`` file into your Tesseract "tessdata" folder, and -then use the ``-l customlang`` argument to tell OCRmyPDF to pass that language on to -Tesseract. diff --git a/docs/performance.md b/docs/performance.md new file mode 100644 index 00000000..bd096f1f --- /dev/null +++ b/docs/performance.md @@ -0,0 +1,24 @@ +% SPDX-FileCopyrightText: 2022 James R. Barlow +% SPDX-License-Identifier: CC-BY-SA-4.0 + +# Performance + +Some users have noticed that current versions of OCRmyPDF do not run as +quickly as some older versions (specifically 6.x and older). This is +because OCRmyPDF added image optimization as a postprocessing step, and +it is enabled by default. + +## Speed + +If running OCRmyPDF quickly is your main goal, you can use settings such +as: + +- `--optimize 0` to disable file size optimization +- `--output-type pdf` to disable PDF/A generation +- `--fast-web-view 999999` to disable fast web view optimization +- `--skip-big` to skip large images, if some pages have large images + +You can also avoid: + +- `--force-ocr` +- Image preprocessing diff --git a/docs/performance.rst b/docs/performance.rst deleted file mode 100644 index ca05f694..00000000 --- a/docs/performance.rst +++ /dev/null @@ -1,26 +0,0 @@ -.. SPDX-FileCopyrightText: 2022 James R. Barlow -.. -.. SPDX-License-Identifier: CC-BY-SA-4.0 - -=========== -Performance -=========== - -Some users have noticed that current versions of OCRmyPDF do not run as quickly -as some older versions (specifically 6.x and older). This is because OCRmyPDF -added image optimization as a postprocessing step, and it is enabled by default. - -Speed -===== - -If running OCRmyPDF quickly is your main goal, you can use settings such as: - -* ``--optimize 0`` to disable file size optimization -* ``--output-type pdf`` to disable PDF/A generation -* ``--fast-web-view 999999`` to disable fast web view optimization -* ``--skip-big`` to skip large images, if some pages have large images - -You can also avoid: - -* ``--force-ocr`` -* Image preprocessing diff --git a/docs/plugins.rst b/docs/plugins.md similarity index 60% rename from docs/plugins.rst rename to docs/plugins.md index 3f8564cd..d83b1f83 100644 --- a/docs/plugins.rst +++ b/docs/plugins.md @@ -1,15 +1,12 @@ -.. SPDX-FileCopyrightText: 2022 James R. Barlow -.. -.. SPDX-License-Identifier: CC-BY-SA-4.0 +% SPDX-FileCopyrightText: 2022 James R. Barlow +% SPDX-License-Identifier: CC-BY-SA-4.0 -======= -Plugins -======= +# Plugins - The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL - NOT", "SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and - "OPTIONAL" in this document are to be interpreted as described in - RFC 2119. +> The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL +> NOT", "SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and +> "OPTIONAL" in this document are to be interpreted as described in +> RFC 2119. You can use plugins to customize the behavior of OCRmyPDF at certain points of interest. @@ -24,75 +21,71 @@ Currently, it is possible to: - replace Ghostscript with another PDF to image converter (rasterizer) or PDF/A generator -OCRmyPDF plugins are based on the Python ``pluggy`` package and conform to its +OCRmyPDF plugins are based on the Python `pluggy` package and conform to its conventions. Note that: plugins installed with as setuptools entrypoints are not checked currently, because OCRmyPDF assumes you may not want to enable plugins for all files. -See [OCRmyPDF-EasyOCR](https://github.com/ocrmypdf/OCRmyPDF-EasyOCR) for an +See \[OCRmyPDF-EasyOCR\]() for an example of a straightforward, fully working plugin. -Script plugins -============== +## Script plugins Script plugins may be called from the command line, by specifying the name of a file. Script plugins may be convenient for informal or "one-off" plugins, when a certain batch of files needs a special processing step for example. -.. code-block:: bash +```bash +ocrmypdf --plugin ocrmypdf_example_plugin.py input.pdf output.pdf +``` - ocrmypdf --plugin ocrmypdf_example_plugin.py input.pdf output.pdf +Multiple plugins may be installed by issuing the `--plugin` argument multiple times. -Multiple plugins may be installed by issuing the ``--plugin`` argument multiple times. - -Packaged plugins -================ +## Packaged plugins Installed plugins may be installed into the same virtual environment as OCRmyPDF is installed into. They may be invoked using Python standard module naming. If you are intending to distribute a plugin, please package it. -.. code-block:: bash - - ocrmypdf --plugin ocrmypdf_fancypants.pockets.contents input.pdf output.pdf +```bash +ocrmypdf --plugin ocrmypdf_fancypants.pockets.contents input.pdf output.pdf +``` OCRmyPDF does not automatically import plugins, because the assumption is that plugins affect different files differently and you may not want them activated -all the time. The command line or ``ocrmypdf.ocr(plugin='...')`` must call +all the time. The command line or `ocrmypdf.ocr(plugin='...')` must call for them. Third parties that wish to distribute packages for ocrmypdf should package them -as packaged plugins, and these modules should begin with the name ``ocrmypdf_`` -similar to ``pytest`` packages such as ``pytest-cov`` (the package) and -``pytest_cov`` (the module). +as packaged plugins, and these modules should begin with the name `ocrmypdf_` +similar to `pytest` packages such as `pytest-cov` (the package) and +`pytest_cov` (the module). -.. note:: +:::{note} +We recommend plugin authors name their plugins with the prefix +`ocrmypdf-` (for the package name on PyPI) and `ocrmypdf_` (for the +module), just like pytest plugins. At the same time, please make it clear +that your package is not official. +::: - We recommend plugin authors name their plugins with the prefix - ``ocrmypdf-`` (for the package name on PyPI) and ``ocrmypdf_`` (for the - module), just like pytest plugins. At the same time, please make it clear - that your package is not official. - -Plugins -======= +## Plugins You can also create a plugin that OCRmyPDF will always automatically load if both are installed in the same virtual environment, using a project entrypoint. OCRmyPDF uses the entrypoint namespace "ocrmypdf". -For example, ``pyproject.toml`` would need to contain the following, for a plugin named -``ocrmypdf-exampleplugin``: +For example, `pyproject.toml` would need to contain the following, for a plugin named +`ocrmypdf-exampleplugin`: -.. code-block:: toml +```toml +[project] +name = "ocrmypdf-exampleplugin" - [project] - name = "ocrmypdf-exampleplugin" +[project.entry-points."ocrmypdf"] +exampleplugin = "exampleplugin.pluginmodule" +``` - [project.entry-points."ocrmypdf"] - exampleplugin = "exampleplugin.pluginmodule" - -Plugin requirements -=================== +## Plugin requirements OCRmyPDF generally uses multiple worker processes. When a new worker is started, Python will import all plugins again, including all plugins that were imported earlier. @@ -103,14 +96,14 @@ to obtain a reference to shared state prepared by another hook implementation. Plugins must expect that other instances of the plugin will be running simultaneously. -The ``context`` object that is passed to many hooks can be used to share information +The `context` object that is passed to many hooks can be used to share information about a file being worked on. Plugins must write private, plugin-specific data to -a subfolder named ``{options.work_folder}/ocrmypdf-plugin-name``. Plugins MAY -read and write files in ``options.work_folder``, but should be aware that their +a subfolder named `{options.work_folder}/ocrmypdf-plugin-name`. Plugins MAY +read and write files in `options.work_folder`, but should be aware that their semantics are subject to change. -OCRmyPDF will delete ``options.work_folder`` when it has finished OCRing -a file, unless invoked with ``--keep-temporary-files``. +OCRmyPDF will delete `options.work_folder` when it has finished OCRing +a file, unless invoked with `--keep-temporary-files`. The documentation for some plugin hooks contain a detailed description of the execution context in which they will be called. @@ -119,114 +112,139 @@ Plugins should be prepared to work whether executed in worker threads or worker processes. Generally, OCRmyPDF uses processes, but has a semi-hidden threaded argument that simplifies debugging. - -Plugin hooks -============ +## Plugin hooks A plugin may provide the following hooks. Hooks must be decorated with -``ocrmypdf.hookimpl``, for example: +`ocrmypdf.hookimpl`, for example: -.. code-block:: python +```python +from ocrmpydf import hookimpl - from ocrmpydf import hookimpl - - @hookimpl - def add_options(parser): - pass +@hookimpl +def add_options(parser): + pass +``` The following is a complete list of hooks that are available, and when they are called. -.. _firstresult: +(firstresult)= **Note on firstresult hooks** If multiple plugins install implementations for this hook, they will be called in the reverse of the order in which they are installed (i.e., last plugin wins). When each hook implementation is called in order, the first implementation that -returns a value other than ``None`` will "win" and prevent execution of all other +returns a value other than `None` will "win" and prevent execution of all other hooks. As such, you cannot "chain" a series of plugin filters together in this way. Instead, a single hook implementation should be responsible for any such chaining operations. -Examples -======== +## Examples -* OCRmyPDF's test suite contains several plugins that are used to simulate certain +- OCRmyPDF's test suite contains several plugins that are used to simulate certain test conditions. -* `ocrmypdf-papermerge `_ is +- [ocrmypdf-papermerge](https://github.com/papermerge/OCRmyPDF_papermerge) is a production plugin that integrates OCRmyPDF and the Papermerge document management system. +### Suppressing or overriding other plugins -Suppressing or overriding other plugins ---------------------------------------- - +```{eval-rst} .. autofunction:: ocrmypdf.pluginspec.initialize +``` -Custom command line arguments ------------------------------ +### Custom command line arguments +```{eval-rst} .. autofunction:: ocrmypdf.pluginspec.add_options +``` +```{eval-rst} .. autofunction:: ocrmypdf.pluginspec.check_options +``` -Execution and progress reporting --------------------------------- +### Execution and progress reporting +```{eval-rst} .. autoclass:: ocrmypdf.pluginspec.ProgressBar :members: :special-members: __init__, __enter__, __exit__ +``` +```{eval-rst} .. autoclass:: ocrmypdf.pluginspec.Executor :members: :special-members: __call__ +``` +```{eval-rst} .. autofunction:: ocrmypdf.pluginspec.get_logging_console +``` +```{eval-rst} .. autofunction:: ocrmypdf.pluginspec.get_executor +``` +```{eval-rst} .. autofunction:: ocrmypdf.pluginspec.get_progressbar_class +``` -Applying special behavior before processing -------------------------------------------- +### Applying special behavior before processing +```{eval-rst} .. autofunction:: ocrmypdf.pluginspec.validate +``` -PDF page to image ------------------ +### PDF page to image +```{eval-rst} .. autofunction:: ocrmypdf.pluginspec.rasterize_pdf_page +``` -Modifying intermediate images ------------------------------ +### Modifying intermediate images +```{eval-rst} .. autofunction:: ocrmypdf.pluginspec.filter_ocr_image +``` +```{eval-rst} .. autofunction:: ocrmypdf.pluginspec.filter_page_image +``` +```{eval-rst} .. autofunction:: ocrmypdf.pluginspec.filter_pdf_page +``` -OCR engine ----------- +### OCR engine +```{eval-rst} .. autofunction:: ocrmypdf.pluginspec.get_ocr_engine +``` +```{eval-rst} .. autoclass:: ocrmypdf.pluginspec.OcrEngine :members: .. automethod:: __str__ +``` +```{eval-rst} .. autoclass:: ocrmypdf.pluginspec.OrientationConfidence +``` -PDF/A production ----------------- +### PDF/A production +```{eval-rst} .. autofunction:: ocrmypdf.pluginspec.generate_pdfa +``` -PDF optimization ----------------- +### PDF optimization +```{eval-rst} .. autofunction:: ocrmypdf.pluginspec.optimize_pdf +``` -.. autofunction:: ocrmypdf.pluginspec.is_optimization_enabled \ No newline at end of file +```{eval-rst} +.. autofunction:: ocrmypdf.pluginspec.is_optimization_enabled +``` diff --git a/docs/release_notes.md b/docs/release_notes.md new file mode 100644 index 00000000..b081155f --- /dev/null +++ b/docs/release_notes.md @@ -0,0 +1,2840 @@ +% SPDX-FileCopyrightText: 2022 James R. Barlow +% SPDX-License-Identifier: CC-BY-SA-4.0 + +# Release notes + +OCRmyPDF uses [semantic versioning](http://semver.org/) for its +command line interface and its public API. + +OCRmyPDF's output messages are not considered part of the stable interface - +that is, output messages may be improved at any release level, so parsing them +may be unreliable. Use the API to depend on precise behavior. + +The public API may be useful in scripts that launch OCRmyPDF processes or that +wish to use some of its features for working with PDFs. + +The most recent release of OCRmyPDF is ![version](https://img.shields.io/pypi/v/ocrmypdf.svg). Any newer versions +referred to in these notes may exist the main branch but have not been +tagged yet. + +OCRmyPDF typically supports the three most recent Python versions. + +:::{note} +Attention maintainers: these release notes may be updated with information +about a forthcoming release that has not been tagged yet. A release is only +official when it's tagged and posted to PyPI. +::: + +## v16.10.0 + +- Added hocr textangle processing, improving handling of text at angles. + Thanks @0dinD {issue}`1467` +- Docker documentation updates related to podman. Thanks @rugk. {issue}`1489,1488` +- Dropped webservice.py's fragile use of ttyd. Instead, messages from ocrmypdf are + printed to the console. +- Fixed broken test test_hocrtransform_matches_sandwich, which had become + an invalid test. Thanks @QuLogic for reporting. +- Improved install instructions for Windows. Thanks @alex. + +## v16.9.0 + +- Added hocr caption processing. Thanks @0dinD {issue}`1466` +- ocrmypdf-alpine Docker image is now built with Alpine 3.21. +- Fixed error handling of PDFs that contain invalid images with both ImageMask + and ColorSpace defined. {issue}`1453` +- Fixed test suite regression when only older Ghostscripts are installed. +- Improved documetnation of \_progressbar.py. Thanks @QuentinFuxa. {issue}`1456` +- Disabling building of documentation as PDF on ReadTheDocs, as this caused + complex build issues deemed not worth solving. + +## v16.8.0 + +- Upgraded webservice.py demonstration using streamlit. It's now possible to + exercise most of OCRmyPDF's functionality in a simple web UI. +- Added cache to Dockerfiles to improve build speed. +- Fixed numerous formatting errors in the documentation that prevented some + parts of documentation from generating correctly. +- Improved OCR text rendering by suppressing negative-width spaces. Thanks + @pajowu. {issue}`1446` +- Improved detecting of invisible text when using `--redo-ocr`. Thanks + @pajowu. {issue}`1448`` + +## v16.7.0 + +- Fixed further issues with Docker build and updated some versions. +- Main Docker image returned to Ubuntu 24.04 since the fix in v16.6.2 resolved + that concern. +- Code that previously sent Ghostscript output to stdout has been changed to + output to temporary files, since Ghostscript was doing that anyway internally. + This is a modest efficiency improvement. +- Fixed an issue with debug log output being parsed as rich markup. {issue}`1444` + +## v16.6.2 + +- Remove invalid hyperlink annotations to satisfy Ghostscript 10.x during PDF/A + conversion. {issue}`1425` + +## v16.6.1 + +- Fixed some issues with Docker build, such as removing unnecessary content and using + a stable Tesseract version. +- Reverted Docker image to Ubuntu 22.04 to access older/more stable Ghostscript + for now. +- Clarified batch commands in documentation. +- Fixed an issue with JSON serialization and pickling of HOCRResult. {issue}`1427` + +## v16.6.0 + +- Fixed an issue where damaged PDFs would fail with `--redo-ocr`. {issue}`1403` +- Fixed an error that prevented JBIG2 optimization on Windows if the image + was optimized in an earlier step. {issue}`1396` +- Fixed an error detecting the version of unpaper 7.0.0. {issue}`1409` +- Fixed a performance regression when scanning pages. {issue}`1378`. Thanks @aliemjay. +- Fixed Alpine Docker image by enforcing Alpine 3.19. Alpine 3.20 includes a + defective version of Tesseract OCR and so is not usable. +- Upgraded Ubuntu Docker image to use Ubuntu 24.04. +- Build and test scripts/actions switched to uv. +- When running in a container, we now remind the user that temporary folders + are inside the container and may not be accessible. +- Fixed Linux test coverage matrix, which was missing some key versions. + +## v16.5.0 + +- Fixed issue with interpreting PDFs that have images with array masks. + {issue}`1377` +- Enabled testing on Python 3.13. +- Fixed a test that did not work correctly but still passed. {issue}`1382` +- Improved "PDF/A conversion failed" warning message to better describe implications. +- Updated documentation to better explain OCR_JSON_SETTINGS in batch processing. +- Build backend changed from setuptools to hatchling. + +## v16.4.3 + +- Work around pdfminer.six issue where a token on the buffer boundary is incorrectly + parsed as two tokens. {issue}`1361` +- New rules are applied to stencil masks and explicit masks when calculating the + optimal page DPI for rendering. {issue}`1362` +- Fixed attempts to use an incompatible jbig2.EXE provided by TeX Live. {issue}`1363` + +## v16.4.2 + +- Fixed order of filenames passed to Ghostscript for PDF/A generation. {issue}`1359` +- Suppressed missing jbig2dec warning message. {issue}`1358` +- Fixed calculation of image size when soft mask dimensions don't match image + dimension. {issue}`1351` +- Several fixes to documentation. Thanks to users Iris and JoKalliauer + who contributed these changes. +- Fixed error on processing PDFs that are missing certain image metadata. {issue}`1315` + +## v16.4.1 + +- Fixed calculation of image printed area (used in finding weighted DPI for OCR). + {issue}`1334` +- Fixed "NotImplementedError: not sure how to get colorspace" error + messages in logs which simply records a failure to optimize images with + print production colorspaces. {issue}`1315` + +## v16.4.0 + +- Selecting the `osd` and `equ` pseudo-languages with `-l/--language` now + exits with an error when using Tesseract OCR, because these are not + regular Tesseract languages but implementation details implemented. + Using them can cause Tesseract to crash. +- The hOCR renderer is more tolerant of extra whitespace in input files. +- watcher.py now changes the output file extension to .pdf when the input is not + .pdf. +- Improved handling of PDFs that contain circularly referenced Form XObjects. + {issue}`1321` +- Fixed Alpine Docker image for ARM64, which was not building correctly. +- Docker images now use pikepdf 9.0.0. +- Prevent use of Tesseract OCR 5.4.0, a version with known regressions. +- Disabled progressbar for "Linearizing" when `--no-progress-bar` set. +- Fixed some tests that warn about missing JBIG2 decoding via pikepdf, by + installing the necessary libraries during tests. + +## v16.3.1 + +- Fixed a test suite failure with Ghostscript 10.03.0+. {issue}`1316` +- Fixed an issue with the presentation of the "OCR" progress bar. {issue}`1313` + +## v16.3.0 + +- Fixed progress bar not displaying for Ghostscript PDF/A conversion. {issue}`1313` +- Added progress bar for linearization. {issue}`1313` +- If `--rotate-pages-threshold` issued without `--rotate-pages` we now exit with + an error since the user likely intended to use `--rotate-pages`. {issue}`1309` +- If Tesseract hOCR gives an invalid line box, print an error message instead of + exiting with an error. {issue}`1312` + +## v16.2.0 + +- Fixed issue 'NoneType' object has no attribute 'get' when optimizing certain PDFs. + {issue}`1293,1271` +- Switched formatting from black to ruff. +- Added support for sending sidecar output to io.BytesIO. +- Added support for converting HEIF/HEIC images (the native image of iPhones and + some other devices) to PDFs, when the appropriate pi-hief library is installed. + This library is marked as a dependency, but maintainers may opt out if needed. +- We now default to downsampling large images that would exceed Tesseract's internal + limits, but only if it cause processing to fail. Previously, this behavior only + occurred if specifically requested on command line. It can still be configured + and disabled. See the --tesseract command line options. +- Added Macports install instructions. Thanks @akierig. +- Improved logging output when an unexpected error occurs while trying to obtain + the version of a third party program. + +## v16.1.2 + +- Fixed test suite failure when using Ghostscript 10.3. +- Other minor corrections. + +## v16.1.1 + +- Fixed PyPy 3.10 support. + +## v16.1.0 + +- Improved hOCR renderer is now default for left to right languages. +- Improved handling of rotated pages. Previously, OCR text might be missing for + pages that were rotated with a /Rotate tag on the page entry. +- Improved handling of cropped pages. Previously, in some cases a page with a + crop box would not have its OCR applied correctly and misalignment between + OCR text and visible text coudl occur. +- Documentation improvements, especially installation instructions for less + common platforms. + +## v16.0.4 + +- Fixed some issues for left-to-right text with the new hOCR renderer. It is still + not default yet but will be made so soon. Right-to-left text is still in progress. +- Added an error to prevent use of several versions of Ghostscript that seem + corrupt existing text in input PDFs. Newly generated OCR is not affected. + For best results, use Ghostscript 10.02.1 or newer, which contains the fix + for the issue. + +## v16.0.3 + +- Changed minimum required Ghostscript to 9.54, to support users of RHEL 9 and its + derivatives, since that is the latest version available there. +- Removed warning message about CVE-2023-43115, on the assumption that most + distributions have backported the patch by now. + +## v16.0.2 + +- Temporarily changed PDF text renderer back to sandwich by default to address + regressions in macOS Preview. + +## v16.0.1 + +- Fixed text rendering issue with new hOCR text renderer - extraneous byte order + marks. +- Tightened dependencies. + +## v16.0.0 + +- Added OCR text renderer, combined the best ideas of Tesseract's PDF + generator and the older hOCR transformer renderer. The result is a hopefully + permanent fix for wordssmushedtogetherwithoutspaces issues in extracted text, + better registration/position of text on skewed baselines {issue}`1009`, + fixes to character output when the German Fraktur script is used {issue}`1191`, + proper rendering of right to left languages (Arabic, Hebrew, Persian) {issue}`1157`. + Asian languages may still have excessive word breaks compared to expectations. + The new renderer is the default; the old sandwich renderer is still available + using `--pdf-renderer sandwich`; the old hOCR renderer is no more. +- The `ocrmypdf.hocrtransform` API has changed substantially. +- Support for Python 3.9 has been dropped. Python 3.10+ is now required. +- pikepdf >= 8.8.0 is now required. + +## v15.4.4 + +- Fixed documentation for installing Ghostscript on Windows. {issue}`1198` +- Added warning message about security issue in older versions of Ghostscript. + +## v15.4.3 + +- Fixed deprecation warning in pikepdf older than 8.7.1; pikepdf >= 8.7.1 is + now required. + +## v15.4.2 + +- We now raise an exception on a certain class of PDFs that likely need an + explicit color conversion strategy selected to display correctly + for PDF/A conversion. +- Fixed an error that occurred while trying to write a log message after the + debug log handler was removed. + +## v15.4.1 + +- Fixed misc/watcher.py regressions: accept `--ocr-json-settings` as either + filename or JSON string, as previously; and argument count mismatch. + {issue}`1183,1185` +- We no longer attempt to set /ProcSet in the PDF output, since this is an + obsolete PDF feature. +- Documentation improvements. + +## v15.4.0 + +- Added new experimental APIs to support offline editing of the final text. + Specifically, one can now generate hOCR files with OCRmyPDF, edit them with + some other tool, and then finalize the PDF. They are experimental and + subject to change, including details of how the working folder is used. + There is no command line interface. +- Code reorganization: executors, progress bars, initialization and setup. +- Fixed test coverage in cases where the coverage tool did not properly trace + into threads or subprocesses. This code was still being tested but appeared + as not covered. +- In the test suite, reduced use of subprocesses and other techniques that + interfere with coverage measurement. +- Improved error check for when we appear to be running inside a snap container + and files are not available. +- Plugin specification now properly defines progress bars as a protocol rather + than defining them as "tqdm-like". +- We now default to using "forkserver" process creation on POSIX platforms + rather than fork, since this is method is more robust and avoids some + issues when threads are present. +- Fixed an instance where the user's request to `--no-use-threads` was ignored. +- If a PDF does not have language metadata on its top level object, we add + the OCR language. +- Replace some cryptic test error messages with more helpful ones. +- Debug messages for how OCRmyPDF picks the colorspace for a page are now + more descriptive. + +## v15.3.1 + +- Fixed an issue with logging settings for misc/watcher.py introduced in the + previous release. {issue}`1180` +- We now attempt to preserve the input's extended attributes when creating + the output file. +- For some reason, the macOS build now needs OpenSSL explicitly installed. +- Updated documentation on Docker performance concerns. + +## v15.3.0 + +- Update misc/watcher.py to improve command line interface using Typer, and + support `.env` specification of environment variables. Improved error + messages. Thanks to @mflagg2814 for the PR that prompted this improvement. +- Improved error message when a file cannot be read because we are running in + a snap container. + +## v15.2.0 + +- Added a Docker image based on Alpine Linux. This image is smaller than the + Ubuntu-based image and may be useful in some situations. Currently hosted at + jbarlow83/ocrmypdf-alpine. Currently not available in ARM flavor. +- The Ubuntu Docker is now aliased to jbarlow83/ocrmypdf-ubuntu. +- Updated Docker documentation. + +## v15.1.0 + +- We now require Pillow 10.0.1, due a serious security vulnerability in all earlier + versions of that dependency. The vulnerability concerns WebP images and could + be triggered in OCRmyPDF when creating a PDF from a malicious WebP image. +- Added some keyword arguments to `ocrmypdf.ocr` that were previously accepted + but undocumented. +- Documentation updates and typing improvements. + +## v15.0.2 + +- Added Python 3.12 to test matrix. +- Updated documentation for notes on Python 3.12, 32-bit support and some new + features in v15. + +## v15.0.1 + +- Wheels Python tag changed to py39. +- Marked as a expected fail a test that fails on recent Ghostscript versions. +- Clarified documentation and release notes around the extent of 32-bit support. +- Updated installation documentation to changes in v15. + +## v15.0.0 + +- Dropped support for Python 3.8. +- Dropped support some older dependencies, specifically `coloredlogs` and + `tqdm` in favor of rich - see `pyproject.toml` for details. + Generally speaking, Ubuntu 22.04 is our new baseline system. +- Tightened version requirements for some dependencies. +- Dropped support for 32-bit Linux wheels. We strongly recommend a 64-bit operating + system, and 64-bit versions of Python, Tesseract and Ghostscript to use OCRmyPDF. + Many of our dependencies are dropping 32-bit builds (e.g. Pillow), and we are + following suit. (Maintainers may still build 32-bit versions from source.) +- Changed to trusted release for PyPI publishing. +- pikepdf memory mapping is enabled again for improved performance, now that an + issue with feature in pikepdf is fixed. +- `ocrmypdf.helpers.calculate_downsample` previously had two variants, one + that took a `PIL.Image` and one that took a `tuple[int, int]`. The latter + was removed. +- The snap version of ocrmypdf is now based on Ubuntu core22. +- We now account for situations where a small portion of an image on a page is drawn + at high DPI (resolution). Previously, the entire page would be rasterized at the + highest resolution of any feature, which caused performance problems. Now, + the page is rasterized + at a resolution based on the average DPI of the page, weighted by the area that + each feature occupies. Typically, small areas of high resolution in PDFs are + errors or quirks from the repeated use of assets and high resolution is not + beneficial. {issue}`1010,1104,1004,1079,1010` +- Ghostscript color conversion strategy is now configurable using + `--color-conversion-strategy`. {issue}`1143` +- JBIG2 threshold for optimization is now configurable using + `--jbig2-threshold`. {issue}`1133` + +## v14.4.0 + +- Digitally signed PDFs are now detected. If the PDF is signed, OCRmyPDF will + refuse to modify it. Previously, only encrypted PDFs were detected, not + those that were signed but not encrypted. {issue}`1040` +- In addition, `--invalidate-digital-signatures` can be used to override the + above behavior and modify the PDF anyway. {issue}`1040` +- tqdm progress bars replaced with "rich" progress bars. The rich library is + a new dependency. Certain APIs that used tqdm are now deprecated and will + be removed in the next major release. +- Improved integration with GitHub Releases. Thanks to @stumpylog. + +## v14.3.0 + +- Renamed master branch to main. +- Improve PDF rasterization accuracy by using the `-dPDFSTOPONERROR` option + to Ghostscript. Use `--continue-on-soft-render-error` if you want to render + the PDF anyway. The plugin specification was adjusted to support this feature; + plugin authors may want to adapt PDF rasterizing and rendering + plugins. {issue}`1083` +- The calculated deskew angle is now recorded in the logged output. {issue}`1101` +- Metadata can now be unset by setting a metadata type such as `--title` to an + empty string. {issue}`1117,1059` +- Fixed random order of languages due to use of a set. This may have caused output + to vary when multiple languages were set for OCR. {issue}`1113` +- Clarified the optimization ratio reported in the log output. +- Documentation improvements. + +## v14.2.1 + +- Fixed {issue}`977`, where images inside Form XObjects were always excluded + from image optimization. + +## v14.2.0 + +- Added `--tesseract-downsample-above` to downsample larger images even when + they do not exceed Tesseract's internal limits. This can be used to speed + up OCR, possibly sacrificing accuracy. +- Fixed resampling AttributeError on older Pillow. {issue}`1096` +- Removed an error about using Ghostscript on PDFs with that have the /UserUnit + feature in use. Previously, Ghostscript would fail to process these PDFs, + but in all supported versions it is now supported, so the error is no longer + needed. +- Improved documentation around installing other language packs for Tesseract. + +## v14.1.0 + +- Added `--tesseract-non-ocr-timeout`. This allows using Tesseract's deskew + and other non-OCR features while disabling OCR using `--tesseract-timeout 0`. +- Added `--tesseract-downsample-large-images`. This downsamples larges images + that exceed the maximum image size Tesseract can handle. Large images may still + take a long time to process, but this allows them to be processed if that + is desired. +- Fixed {issue}`1082`, an issue with snap packaged building. +- Change linter to ruff, fix lint errors, update documentation. + +## v14.0.4 + +- Fixed {issue}`1066, 1075`, an exception when processing certain malformed PDFs. + +## v14.0.3 + +- Fixed {issue}`1068`, avoid deleting /dev/null when running as root. +- Other documentation fixes. + +## v14.0.2 + +- Fixed {issue}`1052`, an exception on attempting to process certain nonconforming PDFs. +- Explicitly documented that Windows 32-bit is no longer supported. +- Fixed source installation instructions. +- Other documentation fixes. + +## v14.0.1 + +- Fixed some version checks done with smart version comparison. +- Added missing jbig2dec to Docker image. + +## v14.0.0 + +- Dropped support for Python 3.7. +- Dropped support generally speaking, all dependencies older than what Ubuntu 20.04 + provides. +- Ghostscript 9.50 or newer is now required. Shims to support old versions were + removed. +- Tesseract 4.1.1 or newer is now required. Shims to support old versions were + removed. +- Docker image now uses Tesseract 5. +- Dropped setup.cfg configuration for pyproject.toml. +- Removed deprecation exception PdfMergeFailedError. +- A few more public domain test files were removed or replaced. We are aiming for + 100% compliance with SPDX and generally towards simplifying copyright. + +## v13.7.0 + +- Fixed an exception when attempting to run and Tesseract is not installed. +- Changed to SPDX license tracking and information files. + +## v13.6.2 + +- Added a shim to prevent an "error during error handling" for Python 3.7 and 3.8. +- Modernized some type annotations. +- Improved annotations on our \_windows module to help IDEs and mypy figure out what + we're doing. + +## v13.6.1 + +- Require setuptools-scm 7.0.5 to avoid possible issues with source distributions in + earlier versions of setuptools-scm. +- Suppress a spurious warning, improve tests, improve typing and other miscellany. + +## v13.6.0 + +- Added a new `initialize` plugin hook, making it possible to suppress built-in + plugins more easily, among other possibilities. +- Fixed an issue where unpaper would exit with a "wrong stream" error, probably + related to images with an odd integer width. {issue}`887, 665` + +## v13.5.0 + +- Added a new `optimize_pdf` plugin hook, making it possible to create plugins that + replace or enhance OCRmyPDF's PDF optimizer. +- Removed all max version restrictions. Our new policy is to blacklist known-bad releases + and only block known-bad versions of dependencies. +- The naming schema for object that holds all OCR text that OCRmyPDF inserts has + changed. This has always been an implementation detail (and remains so), but possibly, + someone was relying on it and would appreciate the heads-up. +- Cleanup. + +## v13.4.7 + +- Fixed PermissionError when cleaning up temporary files in rare cases. {issue}`974` +- Fixed PermissionError when calling `os.nice` on platforms that lack it. {issue}`973` +- Suppressed some warnings from libxmp during tests. + +## v13.4.6 + +- Convert error on corrupt ICC profiles into a warning. Thanks to @oscherler. + +## v13.4.5 + +- Remove upper bound on pdfminer.six version. +- Documentation. + +## v13.4.4 + +- Updated pdfminer.six version. +- Docker image changed to Ubuntu 22.04 now that it is released and provides the + dependencies we need. This seems more consistent than our recent change to + Debian. + +## v13.4.3 + +- Fix error on pytest.skip() with older versions of pytest. +- Documentation updates. + +## v13.4.2 + +- Worked around a + [major regression in Ghostscript 9.56.0](https://bugs.ghostscript.com/show_bug.cgi?id=705187) + where **all OCR text is stripped out of the PDF**. It simply removes all text, + even generated by software other than OCRmyPDF. Fortunately, we can ask + Ghostscript 9.56.0 to use its old behavior that worked correctly for our purposes. + Users must avoid the combination (Ghostscript 9.56.0, ocrmypdf \<13.4.2) since + older versions of OCRmyPDF have no way of detecting that this particular + version of Ghostscript removes all OCR text. +- Marked pdfminer 20220319 as supported. +- Fixed some deprecation warnings from recent versions of Pillow and pytest. +- Test suite now covers Python 3.10 (Python 3.10 worked fine before, but was not + being tested). +- Docker image now uses debian:bookworm-slim as the base image to fix the Docker + image build. + +## v13.4.1 + +- Temporarily make threads rather than processes the default executor worker, due + to a persistent deadlock issue when processes are used. Add a new command line + argument `--no-use-threads` to disable this. + +## v13.4.0 + +- Fixed test failures when using pikepdf 5.0.0. +- Various improvements to the optimizer. In particular, we now recognize PDF images + that are encoded with both deflate (PNG) and DCT (JPEG), and also produce PDF + with images compressed with deflate and DCT, since this often yields file size + improvements compared to plain DCT. + +## v13.3.0 + +- Made a harmless but "scary" exception after failing to optimize an image less scary. +- Added a warning if a page image is too large for unpaper to clean. The image is + passed through without cleaning. This is due to a hard-coded limitation in a + C library used by unpaper so it cannot be rectified easily. +- We now use better default settings when calling img2pdf. +- We no longer try to optimize images that we failed to save in certain situations. +- We now account for some differences in text output from Tesseract 5 compared to + Tesseract 4. +- Better handling of Ghostscript producing empty images when attempting to rasterize + page images. + +## v13.2.0 + +- Removed all runtime uses of distutils since it is deprecated in standard library. We + previous used `distutils.version` to examine version numbers of dependencies + at run time, and now use `packaging.version` for this. This is a new + dependency. +- Fixed an error message advising the user that Ghostscript was not installed being + suppressed when this condition actually happens. +- Fixed an issue with incorrect page number and totals being displayed in the progress + bar. This was purely a display/presentation issue. {issue}`876`. + +## v13.1.1 + +- Fixed issue with attempting to deskew a blank page on Tesseract 5. {issue}`868`. + +## v13.1.0 + +- Changed to using Python concurrent.futures-based parallel execution instead of + pools, since futures have now exceed pools in features. +- If a child worker is terminated (perhaps by the operating system or the user + killing it in a task manager), the parallel task will fail an error message. + Previously, the main ocrmypdf process would "hang" indefinitely, waiting for the + child to report. +- Added new argument `--tesseract-thresholding` to provide control over Tesseract 5's + threshold parameter. +- Documentation updates and changes. Better documentation for `--output-type none`, + added a few releases ago. Removed some obsolete documentation. +- Improved bash completions - thanks to @FPille. + +## v13.0.0 + +**Breaking changes** + +- The deprecated module `ocrmypdf.leptonica` has been removed. +- We no longer depend on Leptonica (`liblept`) or CFFI (`libffi`, + `python3-cffi`). (Note that Tesseract still requires Leptonica; OCRmyPDF no longer + directly uses this library.) +- The argument `--remove-background` is temporarily disabled while we search for an + alternative to the Leptonica implementation of this feature. +- The `--threshold` argument has been removed, since this also depended on Leptonica. + Tesseract 5.x has implemented improvements to thresholding, so this feature will be + redundant anyway. +- `--deskew` was previous calculated by a Leptonica algorithm. We now use a feature + of Tesseract to find the appropriate the angle to deskew a page. The deskew angle + according to Tesseract may differ from Leptonica's algorithm. At least in theory, + Tesseract's deskew angle is informed by a more complex analysis than Leptonica, + so this should improve results in general. We also use Pillow to perform the + deskewing, which may affect the appearance of the image compared to Leptonica. +- Support for Python 3.6 was dropped, since this release is approaching end of life. +- We now require pikepdf 4.0 or newer. This, in turn, means that OCRmyPDF requires + a system compatible with the manylinux2014 specification. This change was "forced" + by Pillow not releasing manylinux2010 wheels anymore. +- We no longer provide requirements.txt-style files. Use `pip install ocrmypdf[...]` + instead. +- Bumped required versions of several libraries. + +**Fixes** + +- Fixed an issue where OCRmyPDF failed to find Ghostscript on Windows even when + installed, and would exit with an error. +- By removing Leptonica, we fixed all issues related to Leptonica on Apple + Silicon or Leptonica failing to import on Windows. + +## v12.7.2 + +- Fixed "invalid version number" error for Tesseract packaging with nonstandard + version "5.0.0-rc1.20211030". +- Fixed use of deprecated `importlib.resources.read_binary`. +- Replace some uses of string paths with `pathlib.Path`. +- Fixed a leaked file handle when using `--output-type none`. +- Removed shims to support versions of pikepdf that are no longer supported. + +## v12.7.1 + +- Declare support for pdfminer.six v20211012. + +## v12.7.0 + +- Fixed test suite failure when using pikepdf 3.2.0 that was compiled with pybind11 + 2.8.0. {issue}`843` +- Improve advice to user about using `--max-image-mpixels` if OCR fails for this + reason. +- Minor documentation fixes. (Thanks to @mara004.) +- Don't require importlib-metadata and importlib-resources backports on versions of + Python where the standard library implementation is sufficient. + (Thanks to Marco Genasci.) + +## v12.6.0 + +- Implemented `--output-type=none` to skip producing PDFs for applications that + only want sidecar files ({issue}`787`). +- Fixed ambiguities in descriptions of behavior of `--jbig2-lossy`. +- Various improvements to documentation. + +## v12.5.0 + +- Fixed build failure for the combination of PyPy 3.6 and pikepdf 3.0. This + combination can work in a source build but does not work with wheels. +- Accepted bot that wanted to upgrade our deprecated requirements.txt. +- Documentation updates. +- Replace pkg_resources and install dependency on setuptools with + importlib-metadata and importlib-resources. +- Fixed regression in hocrtransform causing text to be omitted when this + renderer was used. +- Fixed some typing errors. + +## v12.4.0 + +- When grafting text layers, use pikepdf's `unparse_content_stream` if available. +- Confirmed support for pluggy 1.0. (Thanks @QuLogic.) +- Fixed some typing issues, improved pre-commit settings, and fixed issues + flagged by linters. +- PyPy 7.3.3 (=Python 3.6) is now supported. Note that PyPy does not necessarily + run faster, because the vast majority of OCRmyPDF's execution time is spent + running OCR or generally executing native code. However, PyPy may bring speed + improvements in some areas. + +## v12.3.3 + +- watcher.py: fixed interpretation of boolean env vars ({issue}`821`). +- Adjust CI scripts to test Tesseract 5 betas. +- Document our support for the Tesseract 5 betas. + +## v12.3.2 + +- Indicate support for flask 2.x, watcher 2.x ({issue}`815, 816`). + +## v12.3.1 + +- Fixed issue with selection of text when using the hOCR renderer ({issue}`813`). +- Fixed build errors with the Docker image by upgrading to a newer Ubuntu. + Also set the timezone of this image to UTC. + +## v12.3.0 + +- Fixed a regression introduced in Pillow 8.3.0. Pillow no longer rounds DPI + for image resolutions. We now account for this ({issue}`802`). +- We no longer use some API calls that are deprecated in the latest versions of + pikepdf. +- Improved error message when a language is requested that doesn't look like a + typical ISO 639-2 code. +- Fixed some tests that attempted to symlink on Windows, breaking tests on a + Windows desktop but not usually on CI. +- Documentation fixes (thanks to @mara004) + +## v12.2.0 + +- Fixed invalid Tesseract version number on Windows ({issue}`795`). +- Documentation tweaks. Documentation build now depends on sphinx-issues package. + +## v12.1.0 + +- For security reasons we now require Pillow >= 8.2.x. (Older versions will continue + to work if upgrading is not an option.) +- The build system was reorganized to rely on `setup.cfg` instead of `setup.py`. + All changes should work with previously supported versions of setuptools. +- The files in `requirements/*` are now considered deprecated but will be retained for v12. + Instead use `pip install ocrmypdf[test]` instead of `requirements/test.txt`, etc. + These files will be removed in v13. + +## v12.0.3 + +- Expand the list of languages supported by the hocr PDF renderer. + Several languages were previously considered not supported, particularly those + non-European languages that use the Latin alphabet. +- Fixed a case where the exception stack trace was suppressed in verbose mode. +- Improved documentation around commercial OCR. + +## v12.0.2 + +- Fixed exception thrown when using `--remove-background` on files containing small + images ({issue}`769`). +- Improve documentation for description of adding language packs to the Docker image + and corrected name of French language pack. + +## v12.0.1 + +- Fixed "invalid version number" for untagged tesseract versions ({issue}`770`). + +## v12.0.0 + +**Breaking changes** + +- Due to recent security issues in pikepdf, Pillow and reportlab, we now require + newer versions of these libraries and some of their dependencies. (If necessary, + package maintainers may override these versions at their discretion; lower + versions will often work.) +- We now use the "LeaveColorUnchanged" color conversion strategy when directing + Ghostscript to create a PDF/A. Generally this is faster than performing a + color conversion, which is not always necessary. +- OCR text is now packaged in a Form XObject. This makes it easier to isolate + OCR from other document content. However, some poorly implemented PDF text + extraction algorithms may fail to detect the text. +- Many API functions have stricter parameter checking or expect keyword arguments + were they previously did not. +- Some deprecated functions in `ocrmypdf.optimize` were removed. +- The `ocrmypdf.leptonica` module is now deprecated, due to difficulties with + the current strategy of ABI binding on newer platforms like Apple Silicon. + It will be removed and replaced, either by repackaging Leptonica as an + independent library using or using a different image processing library. +- Continuous integration moved to GitHub Actions. +- We no longer depend on `pytest_helpers_namespace` for testing. + +**New features** + +- New plugin hook: `get_progressbar_class`, for progress reporting, + allowing developers to replace the standard console progress bar with some + other mechanism, such as updating a GUI progress bar. +- New plugin hook: `get_executor`, for replacing the concurrency model. + This is primarily to support execution on AWS Lambda, which does not support + standard Python `multiprocessing` due to its lack of shared memory. +- New plugin hook: `get_logging_console`, for replacing the standard + way OCRmyPDF outputs its messages. +- New plugin hook: `filter_pdf_page`, for modifying individual PDF + pages produced by OCRmyPDF. +- OCRmyPDF now runs on nonstandard execution environments that do not have + interprocess semaphores, such as AWS Lambda and Android Termux. If the environment + does not have semaphores, OCRmyPDF will automatically select an alternate + process executor that does not use semaphores. +- Continuous integration moved to GitHub Actions. +- We now generate an ARM64-compatible Docker image alongside the x64 image. + Thanks to @andkrause for doing most of the work in a pull request several months + ago, which we were finally able to integrate now. Also thanks to @0x326 for + review comments. + +**Fixes** + +- Fixed a possible deadlock on attempting to flush `sys.stderr` when older + versions of Leptonica are in use. +- Some worker processes inherited resources from their parents such as log + handlers that may have also lead to deadlocks. These resources are now released. +- Improvements to test coverage. +- Removed vestiges of support for Tesseract versions older than 4.0.0-beta1 ( + which ships with Ubuntu 18.04). +- OCRmyPDF can now parse all of Tesseract version numbers, since several + schemes have been in use. +- Fixed an issue with parsing PDFs that contain images drawn at a scale of 0. ({issue}`761`) +- Removed a frequently repeated message about disabling mmap. + +## v11.7.3 + +- Exclude CCITT Group 3 images from being optimized. Some libraries + OCRmyPDF uses do not seem to handle this obscure compression format properly. + You may get errors or possible corrupted output images without this fix. + +## v11.7.2 + +- Updated pinned versions in main.txt, primarily to upgrade Pillow to 8.1.2, due + to recently disclosed security vulnerabilities in that software. +- The `--sidecar` parameter now causes an exception if set to the same file as + the input or output PDF. + +## v11.7.1 + +- Some exceptions while attempting image optimization were only logged at the debug + level, causing them to be suppressed. These errors are now logged appropriately. +- Improved the error message related to `--unpaper-args`. +- Updated documentation to mention the new conda distribution. + +## v11.7.0 + +- We now support using `--sidecar` in conjunction with `--pages`; these arguments + used to be mutually exclusive. ({issue}`735`) +- Fixed a possible issue with PDF/A-1b generation. Acrobat complained that our PDFs use + object streams. More robust PDF/A validators like veraPDF don't consider this a + problem, but we'll honor Acrobat's objection from here on. This may increase file + size of PDF/A-1b files. PDF/A-2b files will not be affected. + +## v11.6.2 + +- Fixed a regression where the wrong page orientation would be produced when using + arguments such as `--deskew --rotate-pages` ({issue}`730`). + +## v11.6.1 + +- Fixed an issue with attempting optimize unusually narrow-width images by excluding + these images from optimization ({issue}`732`). +- Remove an obsolete compatibility shim for a version of pikepdf that is no longer + supported. + +## v11.6.0 + +- OCRmyPDF will now automatically register plugins from the same virtual environment + with an appropriate setuptools entrypoint. +- Refactor the plugin manager to remove unnecessary complications and make plugin + registration more automatic. +- `PageContext` and `PdfContext` are now formally part of the API, as they + should have been, since they were part of `ocrmypdf.pluginspec`. + +## v11.5.0 + +- Fixed an issue where the output page size might differ by a fractional amount + due to rounding, when `--force-ocr` was used and the page contained objects + with multiple resolutions. +- When determining the resolution at which to rasterize a page, we now consider + printed text on the page as requiring a higher resolution. This fixes issues + with certain pages being rendered with unacceptably low resolution text, but + may increase output file sizes in some workflows where low resolution text + is acceptable. +- Added a workaround to fix an exception that occurs when trying to + `import ocrmypdf.leptonica` on Apple ARM silicon (or potentially, other + platforms that do not permit write+executable memory). + +## v11.4.5 + +- Fixed an issue where files may not be closed when the API is used. +- Improved `setup.cfg` with better settings for test coverage. + +## v11.4.4 + +- Fixed `AttributeError: 'NoneType' object has no attribute 'userunit'` ({issue}`700`), + related to OCRmyPDF not properly forwarded an error message from pdfminer.six. +- Adjusted typing of some arguments. +- `ocrmypdf.ocr` now takes a `threading.Lock` for reasons outlined in the + documentation. + +## v11.4.3 + +- Removed a redundant debug message. +- Test suite now asserts that most patched functions are called when they should be. +- Test suite now skips a test that fails on two particular versions of piekpdf. + +## v11.4.2 + +- Fixed support for Cygwin, hopefully. +- watcher.py: Fixed an issue with the OCR_LOGLEVEL not being interpreted. + +## v11.4.1 + +- Fixed an issue where invalid pages ranges passed using the `pages` argument, + such as "1-0" would cause unhandled exceptions. +- Accepted a user-contributed to the Synology demo script in misc/synology.py. +- Clarified documentation about change of temporary file location `ocrmypdf.io`. +- Fixed Python wheel tag which was incorrectly set to py35 even though we long + since dropped support for Python 3.5. + +## v11.4.0 + +- When looking for Tesseract and Ghostscript, we now check the Windows Registry to + see if their installers registered the location of their executables. This should + help Windows users who have installed these programs to non-standard + locations. +- We now report on the progress of PDF/A conversion, since this operation is + sometimes slow. +- Improved command line completions. +- The prefix of the temporary folder OCRmyPDF creates has been changed from + `com.github.ocrmypdf` to `ocrmypdf.io`. Scripts that chose to depend on this + prefix may need to be adjusted. (This has always been an implementation detail so is + not considered part of the semantic versioning "contract".) +- Fixed {issue}`692`, where a particular file with malformed fonts would flood an + internal message cue by generating so many debug messages. +- Fixed an exception on processing hOCR files with no page record. Tesseract + is not known to generate such files. + +## v11.3.4 + +- Fixed an error message 'called readLinearizationData for file that is not + linearized' that may occur when pikepdf 2.1.0 is used. (Upgrading to pikepdf + 2.1.1 also fixes the issue.) +- File watcher now automatically includes `.PDF` in addition to `.pdf` to + better support case sensitive file systems. +- Some documentation and comment improvements. + +## v11.3.3 + +- If unpaper outputs non-UTF-8 data, quietly fix this rather than choke on the + conversion. (Possibly addresses {issue}`671`.) + +## v11.3.2 + +- Explicitly require pikepdf 2.0.0 or newer when running on Python 3.9. (There are + concerns about the stability of pybind11 2.5.x with Python 3.9, which is used in + pikepdf 1.x.) +- Fixed another issue related to page rotation. +- Fixed an issue where image marked as image masks were not properly considered + as optimization candidates. +- On some systems, unpaper seems to be unable to process the PNGs we offer it + as input. We now convert the input to PNM format, which unpaper always accepts. + Fixes {issue}`665` and {issue}`667`. +- DPI sent to unpaper is now rounded to a more reasonable number of decimal digits. +- Debug and error messages from unpaper were being suppressed. +- Some documentation tweaks. + +## v11.3.1 + +- Declare support for new versions: pdfminer.six 20201018 and pikepdf 2.x +- Fixed warning related to `--pdfa-image-compression` that appears at the wrong + time. + +## v11.3.0 + +- The "OCR" step is describing as "Image processing" in the output messages when + OCR is disabled, to better explain the application's behavior. +- Debug logs are now only created when run as a command line, and not when OCR + is performed for an API call. It is the calling application's responsibility + to set up logging. +- For PDFs with a low number of pages, we gathered information about the input PDF + in a thread rather than process (when there are more pages). When run as a + thread, we did not close the file handle to the working PDF, leaking one file + handle per call of `ocrmypdf.ocr`. +- Fixed an issue where debug messages send by child worker processes did not match + the log settings of parent process, causing messages to be dropped. This affected + macOS and Windows only where the parent process is not forked. +- Fixed the hookspec of rasterize_pdf_page to remove default parameters that + were not handled in an expected way by pluggy. +- Fixed another issue with automatic page rotation ({issue}`658`) due to the issue above. + +## v11.2.1 + +- Fixed an issue where optimization of a 1-bit image with a color palette or + associated ICC that was optimized to JBIG2 could have its colors inverted. + +## v11.2.0 + +- Fixed an issue with optimizing PNG-type images that had soft masks or image masks. + This is a regression introduced in (or about) v11.1.0. +- Improved type checking of the `plugins` parameter for the `ocrmypdf.ocr` + API call. + +## v11.1.2 + +- Fixed hOCR renderer writing the text in roughly reverse order. This should not + affect reasonably smart PDF readers that properly locate the position of all + text, but may confuse those that rely on the order of objects in the content + stream. ({issue}`642`) + +## v11.1.1 + +- We now avoid using named temporary files when using pngquant allowing containerized + pngquant installs to be used. +- Clarified an error message. +- Highest number of 1's in a release ever! + +## v11.1.0 + +- Fixed page rotation issues: {issue}`634,589`. +- Fixed some cases where optimization created an invalid image such as a + 1-bit "RGB" image: {issue}`629,620`. +- Page numbers are now displayed in debug logs when pages are being grafted. +- ocrmypdf.optimize.rewrite_png and ocrmypdf.optimize.rewrite_png_as_g4 were + marked deprecated. Strictly speaking these should have been internal APIs, + but they were never hidden. +- As a precaution, pikepdf mmap-based file access has been disabled due to a + rare race condition that causes a crash when certain objects are deallocated. + The problem is likely in pikepdf's dependency pybind11. +- Extended the example plugin to demonstrate conversion to mono. + +## v11.0.2 + +- Fixed {issue}`612`, TypeError exception. Fixed by eliminating unnecessary repair of + input PDF metadata in memory. + +## v11.0.1 + +- Blacklist pdfminer.six 20200720, which has a regression fixed in 20200726. +- Approve img2pdf 0.4 as it passes tests. +- Clarify that the GPL-3 portion of pdfa.py was removed with the changes in v11.0.0; + the debian/copyright file did not properly annotate this change. + +## v11.0.0 + +- Project license changed to Mozilla Public License 2.0. Some miscellaneous + code is now under MIT license and non-code content/media remains under + CC-BY-SA 4.0. License changed with approval of all people who were found + to have contributed to GPLv3 licensed sections of the project. ({issue}`600`) +- Because the license changed, this is being treated as a major version number + change; however, there are no known breaking changes in functional behavior + or API compared to v10.x. + +## v10.3.3 + +- Fixed a "KeyError: 'dpi'" error message when using `--threshold` on an image. + ({issue}`607`) + +## v10.3.2 + +- Fixed a case where we reported "no reason" for a file size increase, when we + could determine the reason. +- Enabled support for pdfminer.six 20200726. + +## v10.3.1 + +- Fixed a number of test suite failures with pdfminer.six older than version 20200402. +- Enabled support for pdfminer.six 20200720. + +## v10.3.0 + +- Fixed an issue where we would consider images that were already JBIG2-encoded + for optimization, potentially producing a less optimized image than the original. + We do not believe this issue would ever cause an image to loss fidelity. +- Where available, pikepdf memory mapping is now used. This improves performance. +- When Leptonica 1.79+ is installed, use its new error handling API to avoid + a "messy" redirection of stderr which was necessary to capture its error + messages. +- For older versions of Leptonica, added a new thread level lock. This fixes a + possible race condition in handling error conditions in Leptonica (although + there is no evidence it ever caused issues in practice). +- Documentation improvements and more type hinting. + +## v10.2.1 + +- Disabled calculation of text box order with pdfminer. We never needed this result + and it is expensive to calculate on files with complex pre-existing text. +- Fixed plugin manager to accept `Path(plugin)` as a path to a plugin. +- Fixed some typing errors. +- Documentation improvements. + +## v10.2.0 + +- Update Docker image to use Ubuntu 20.04. +- Fixed issue PDF/A acquires title "Untitled" after conversion. ({issue}`582`) +- Fixed a problem where, when using `--pdf-renderer hocr`, some text would + be missing from the output when using a more recent version of Tesseract. + Tesseract began adding more detailed markup about the semantics of text + that our HOCR transform did not recognize, so it ignored them. This option is + not the default. If necessary `--redo-ocr` also redoing OCR to fix such issues. +- Fixed an error in Python 3.9 beta, due to removal of deprecated + `Element.getchildren()`. ({issue}`584`) +- Implemented support using the API with `BytesIO` and other file stream objects. + ({issue}`545`) + +## v10.1.1 + +- Fixed `OMP_THREAD_LIMIT` set to invalid value error messages on some input + files. (The error was harmless, apart from less than optimal performance in + some cases.) + +## v10.1.0 + +- Previously, we `--clean-final` would cause an unpaper-cleaned page image to + be produced twice, which was necessary in some cases but not in general. We + now take this optimization opportunity and reuse the image if possible. +- We now provide PNG files as input to unpaper, since it accepts them, instead + of generating PPM files which can be very large. This can improve performance + and temporary disk usage. +- Documentation updated for plugins. + +## v10.0.1 + +- Fixed regression when `-l lang1+lang2` is used from command line. + +## v10.0.0 + +**Breaking changes** + +- Support for pdfminer.six version 20181108 has been dropped, along with a + monkeypatch that made this version work. +- Output messages are now displayed in color (when supported by the terminal) + and prefixes describing the severity of the message are removed. As such + programs that parse OCRmyPDF's log message will need to be revised. (Please + consider using OCRmyPDF as a library instead.) +- The minimum version for certain dependencies has increased. +- Many API changes; see developer changes. +- The Python libraries pluggy and coloredlogs are now required. + +**New features and improvements** + +- PDF page scanning is now parallelized across CPUs, speeding up this phase + dramatically for files with a high page counts. +- PDF page scanning is optimized, addressing some performance regressions. +- PDF page scanning is no longer run on pages that are not selected when the + `--pages` argument is used. +- PDF page scanning is now independent of Ghostscript, ending our past reliance + on this occasionally unstable feature in Ghostscript. +- A plugin architecture has been added, currently allowing one to more easily + use a different OCR engine or PDF renderer from Tesseract and Ghostscript, + respectively. A plugin can also override some decisions, such changing + the OCR settings after initial scanning. +- Colored log messages. + +**Developer changes** + +- The test spoofing mechanism, used to test correct handling of failures in + Tesseract and Ghostscript, has been removed in favor of using plugins for + testing. The spoofing mechanism was fairly complex and required many special + hacks for Windows. +- Code describing the resolution in DPI of images was refactored into a + `ocrmypdf.helpers.Resolution` class. +- The module `ocrmypdf._exec` is now private to OCRmyPDF. +- The `ocrmypdf.hocrtransform` module has been updated to follow PEP8 naming + conventions. +- Ghostscript is no longer used for finding the location of text in PDFs, and + APIs related to this feature have been removed. +- Lots of internal reorganization to support plugins. + +## v9.8.2 + +- Fixed an issue where OCRmyPDF would ignore text inside Form XObject when + making certain decisions about whether a document already had text. +- Fixed file size increase warning to take overhead of small files into account. +- Added instructions for installing on Cygwin. + +## v9.8.1 + +- Fixed an issue where unexpected files in the `%PROGRAMFILES%\gs` directory + (Windows) caused an exception. +- Mark pdfminer.six 20200517 as supported. +- If jbig2enc is missing and optimization is requested, a warning is issued + instead of an error, which was the intended behavior. +- Documentation updates. + +## v9.8.0 + +- Fixed issue where only the first PNG (FlateDecode) image in a file would be + considered for optimization. File sizes should be improved from here on. +- Fixed a startup crash when the chosen language was Japanese ({issue}`543`). +- Added options to configure polling and log level to watcher.py. + +## v9.7.2 + +- Fixed an issue with `ocrmypdf.ocr(...language=)` not accepting a list of + languages as documented. +- Updated setup.py to confirm that pdfminer.six version 20200402 is supported. + +## v9.7.1 + +- Fixed version check failing when used with qpdf 10.0.0. +- Added some missing type annotations. +- Updated documentation to warn about need for "ifmain" guard and Windows. + +## v9.7.0 + +- Fixed an error in watcher.py if `OCR_JSON_SETTINGS` was not defined. +- Ghostscript 9.51 is now blacklisted, due to numerous problems with this version. +- Added a workaround for a problem with "txtwrite" in Ghostscript 9.52. +- Fixed an issue where the incorrect number of threads used was shown when + `OMP_THREAD_LIMIT` was manipulated. +- Removed a possible performance bottlenecks for files that use hundreds to + thousands of images on the same page. +- Documentation improvements. +- Optimization will now be applied to some monochrome images that have a color + profile defined instead of only black and white. +- ICC profiles are consulted when determining the simplified colorspace of an + image. + +## v9.6.1 + +- Documentation improvements - thanks to many users for their contributions! + + > - Fixed installation instructions for ArchLinux (@pigmonkey) + > - Updated installation instructions for FreeBSD and other OSes (@knobix) + > - Added instructions for using Docker Compose with watchdog (@ianalexander, + > @deisi) + > - Other miscellany (@mb720, @toy, @caiofacchinato) + > - Some scripts provided in the documentation have been migrated out so that + > they can be copied out as whole files, and to ensure syntax checking + > is maintained. + +- Fixed an error that caused bash completions to fail on macOS. ({issue}`502,504`; + @AlexanderWillner) + +- Fixed a rare case where OCRmyPDF threw an exception while processing a PDF + with the wrong object type in its `/Trailer /Info`. The error is now logged + and incorrect object is ignored. ({issue}`497`) + +- Removed potentially non-free file `enron1.pdf` and simplified the test that + used it. + +- Removed potentially non-free file `misc/media/logo.afdesign`. + +## v9.6.0 + +- Fixed a regression with transferring metadata from the input PDF to the output + PDF in certain situations. +- pdfminer.six is now supported up to version 2020-01-24. +- Messages are explaining page rotation decisions are now shown at the standard + verbosity level again when `--rotate-pages`. In some previous version they + were set to debug level messages that only appeared with the parameter `-v1`. +- Improvements to `misc/watcher.py`. Thanks to @ianalexander and @svenihoney. +- Documentation improvements. + +## v9.5.0 + +- Added API functions to measure OCR quality. +- Modest improvements to handling PDFs with difficult/non compliant metadata. + +## v9.4.0 + +- Updated recommended dependency versions. +- Improvements to test coverage and changes to facilitate better measurement of + test coverage, such as when tests run in subprocesses. +- Improvements to error messages when Leptonica is not installed correctly. +- Fixed use of pytest "session scope" that may have caused some intermittent + CI failures. +- When the argument `--keep-temporary-files` or verbosity is set to `-v1`, + a debug log file is generated in the working temporary folder. + +## v9.3.0 + +- Improved native Windows support: we now check in the obvious places in + the "Program Files" folders installations of Tesseract and Ghostscript, + rather than relying on the user to edit `PATH` to specify their location. + The `PATH` environment variable can still be used to differentiate when + multiple installations are present or the programs are installed to non- + standard locations. +- Fixed an exception on parsing Ghostscript error messages. +- Added an improved example demonstrating how to set up a watched folder + for automated OCR processing (thanks to @ianalexander for the contribution). + +## v9.2.0 + +- Native Windows is now supported. +- Continuous integration moved to Azure Pipelines. +- Improved test coverage and speed of tests. +- Fixed an issue where a page that was originally a JPEG would be saved as a + PNG, increasing file size. This occurred only when a preprocessing option + was selected along with `--output-type=pdf` and all images on the original + page were JPEGs. Regression since v7.0.0. +- OCRmyPDF no longer depends on the QPDF executable `qpdf` or `libqpdf`. + It uses pikepdf (which in turn depends on `libqpdf`). Package maintainers + should adjust dependencies so that OCRmyPDF no longer calls for libqpdf on + its own. For users of Python binary wheels, this change means a separate + installation of QPDF is no longer necessary. This change is mainly to + simplify installation on Windows. +- Fixed a rare case where log messages from Tesseract would be discarded. +- Fixed incorrect function signature for pixFindPageForeground, causing + exceptions on certain platforms/Leptonica versions. + +## v9.1.1 + +- Expand the range of pdfminer.six versions that are supported. +- Fixed Docker build when using pikepdf 1.7.0. +- Fixed documentation to recommend using pip from get-pip.py. + +## v9.1.0 + +- Improved diagnostics when file size increases at output. Now warns if JBIG2 + or pngquant were not available. +- pikepdf 1.7.0 is now required, to pick up changes that remove the need for + a source install on Linux systems running Python 3.8. + +## v9.0.5 + +- The Alpine Docker image (jbarlow83/ocrmypdf-alpine) has been dropped due to + the difficulties of supporting Alpine Linux. +- The primary Docker image (jbarlow83/ocrmypdf) has been improved to take on + the extra features that used to be exclusive to the Alpine image. +- No changes to application code. +- pdfminer.six version 20191020 is now supported. + +## v9.0.4 + +- Fixed compatibility with Python 3.8 (but requires source install for the moment). +- Fixed Tesseract settings for `--user-words` and `--user-patterns`. +- Changed to pikepdf 1.6.5 (for Python 3.8). +- Changed to Pillow 6.2.0 (to mitigate a security vulnerability in earlier Pillow). +- A debug message now mentions when English is automatically selected if the locale + is not English. + +## v9.0.3 + +- Embed an encoded version of the sRGB ICC profile in the intermediate + Postscript file (used for PDF/A conversion). Previously we included the + filename, which required Postscript to run with file access enabled. For + security, Ghostscript 9.28 enables `-dSAFER` and as such, no longer + permits access to any file by default. This fix is necessary for + compatibility with Ghostscript 9.28. +- Exclude a test that sometimes times out and fails in continuous integration + from the standard test suite. + +## v9.0.2 + +- The image optimizer now skips optimizing flate (PNG) encoded images in some + situations where the optimization effort was likely wasted. +- The image optimizer now ignores images that specify arbitrary decode arrays, + since these are rare. +- Fixed an issue that caused inversion of black and white in monochrome images. + We are not certain but the problem seems to be linked to Leptonica 1.76.0 and + older. +- Fixed some cases where the test suite failed if + English or German Tesseract language packs were not installed. +- Fixed a runtime error if the Tesseract English language is not installed. +- Improved explicit closing of Pillow images after use. +- Actually fixed of Alpine Docker image build. +- Changed to pikepdf 1.6.3. + +## v9.0.1 + +- Fixed test suite failing when either of optional dependencies unpaper and + pngquant were missing. +- Attempted fix of Alpine Docker image build. +- Documented that FreeBSD ports are now available. +- Changed to pikepdf 1.6.1. + +## v9.0.0 + +**Breaking changes** + +- The `--mask-barcodes` experimental feature has been dropped due to poor + reliability and occasional crashes, both due to the underlying library that + implements this feature (Leptonica). +- The `-v` (verbosity level) parameter now accepts only `0`, `1`, and + `2`. +- Dropped support for Tesseract 4.00.00-alpha releases. Tesseract 4.0 beta and + later remain supported. +- Dropped the `ocrmypdf-polyglot` and `ocrmypdf-webservice` images. + +**New features** + +- Added a high level API for applications that want to integrate OCRmyPDF. + Special thanks to Martin Wind (@mawi1988) whose made significant contributions + to this effort. +- Added progress bars for long-running steps. ■■■■■■■□□ +- We now create linearized ("fast web view") PDFs by default. The new parameter + `--fast-web-view` provides control over when this feature is applied. +- Added a new `--pages` feature to limit OCR to only a specific page range. + The list may contain commas or single pages, such as `1, 3, 5-11`. +- When the number of pages is small compared to the number of allowed jobs, we + run Tesseract in multithreaded (OpenMP) mode when available. This should + improve performance on files with low page counts. +- Removed dependency on `ruffus`, and with that, the non-reentrancy + restrictions that previous made an API impossible. +- Output and logging messages overhauled so that ocrmypdf may be integrated + into applications that use the logging module. +- pikepdf 1.6.0 is required. +- Added a logo. 😊 + +**Bug fixes** + +- Pages with vector artwork are treated as full color. Previously, vectors + were ignored when considering the colorspace needed to cover a page, which + could cause loss of color under certain settings. +- Test suite now spawns processes less frequently, allowing more accurate + measurement of code coverage. +- Improved test coverage. +- Fixed a rare division by zero (if optimization produced an invalid file). +- Updated Docker images to use newer versions. +- Fixed images encoded as JBIG2 with a colorspace other than `/DeviceGray` + were not interpreted correctly. +- Fixed a OCR text-image registration (i.e. alignment) problem when the page + when MediaBox had a nonzero corner. + +## v8.3.2 + +- Dropped workaround for macOS that allowed it work without pdfminer.six, + now a proper sdist release of pdfminer.six is available. +- pikepdf 1.5.0 is now required. + +## v8.3.1 + +- Fixed an issue where PDFs with malformed metadata would be rendered as + blank pages. {issue}`398`. + +## v8.3.0 + +- Improved the strategy for updating pages when a new image of the page + was produced. We now attempt to preserve more content from the + original file, for annotations in particular. +- For PDFs with more than 100 pages and a sequence where one PDF page + was replaced and one or more subsequent ones were skipped, an + intermediate file would be corrupted while grafting OCR text, causing + processing to fail. This is a regression, likely introduced in + v8.2.4. +- Previously, we resized the images produced by Ghostscript by a small + number of pixels to ensure the output image size was an exactly what + we wanted. Having discovered a way to get Ghostscript to produce the + exact image sizes we require, we eliminated the resizing step. +- Command line completions for `bash` are now available, in addition + to `fish`, both in `misc/completion`. Package maintainers, please + install these so users can take advantage. +- Updated requirements. +- pikepdf 1.3.0 is now required. + +## v8.2.4 + +- Fixed a false positive while checking for a certain type of PDF that + only Acrobat can read. We now more accurately detect Acrobat-only + PDFs. +- OCRmyPDF holds fewer open file handles and is more prompt about + releasing those it no longer needs. +- Minor optimization: we no longer traverse the table of contents to + ensure all references in it are resolved, as changes to libqpdf have + made this unnecessary. +- pikepdf 1.2.0 is now required. + +## v8.2.3 + +- Fixed that `--mask-barcodes` would occasionally leave a unwanted + temporary file named `junkpixt` in the current working folder. +- Fixed (hopefully) handling of Leptonica errors in an environment + where a non-standard `sys.stderr` is present. +- Improved help text for `--verbose`. + +## v8.2.2 + +- Fixed a regression from v8.2.0, an exception that occurred while + attempting to report that `unpaper` or another optional dependency + was unavailable. +- In some cases, `ocrmypdf [-c|--clean]` failed to exit with an error + when `unpaper` is not installed. + +## v8.2.1 + +- This release was canceled. + +## v8.2.0 + +- A major improvement to our Docker image is now available thanks to + hard work contributed by @mawi12345. The new Docker image, + ocrmypdf-alpine, is based on Alpine Linux, and includes most of the + functionality of three existed images in a smaller package. This + image will replace the main Docker image eventually but for now all + are being built. [See documentation for + details](https://ocrmypdf.readthedocs.io/en/latest/docker.html). +- Documentation reorganized especially around the use of Docker images. +- Fixed a problem with PDF image optimization, where the optimizer + would unnecessarily decompress and recompress PNG images, in some + cases losing the benefits of the quantization it just had just + performed. The optimizer is now capable of embedding PNG images into + PDFs without transcoding them. +- Fixed a minor regression with lossy JBIG2 image optimization. All + JBIG2 candidates images were incorrectly placed into a single + optimization group for the whole file, instead of grouping pages + together. This usually makes a larger JBIG2Globals dictionary and + results in inferior compression, so it worked less well than + designed. However, quality would not be impacted. Lossless JBIG2 was + entirely unaffected. +- Updated dependencies, including pikepdf to 1.1.0. This fixes + {issue}`358`. +- The install-time version checks for certain external programs have + been removed from setup.py. These tests are now performed at + run-time. +- The non-standard option to override install-time checks + (`setup.py install --force`) is now deprecated and prints a + warning. It will be removed in a future release. + +## v8.1.0 + +- Added a feature, `--unpaper-args`, which allows passing arbitrary + arguments to `unpaper` when using `--clean` or `--clean-final`. + The default, very conservative unpaper settings are suppressed. +- The argument `--clean-final` now implies `--clean`. It was + possible to issue `--clean-final` on its before this, but it would + have no useful effect. +- Fixed an exception on traversing corrupt table of contents entries + (specifically, those with invalid destination objects) +- Fixed an issue when using `--tesseract-timeout` and image + processing features on a file with more than 100 pages. + {issue}`347` +- OCRmyPDF now always calls `os.nice(5)` to signal to operating + systems that it is a background process. + +## v8.0.1 + +- Fixed an exception when parsing PDFs that are missing a required + field. {issue}`325` +- pikepdf 1.0.5 is now required, to address some other PDF parsing + issues. + +## v8.0.0 + +No major features. The intent of this release is to sever support for +older versions of certain dependencies. + +**Breaking changes** + +- Dropped support for Tesseract 3.x. Tesseract 4.0 or newer is now + required. +- Dropped support for Python 3.5. +- Some `ocrmypdf.pdfa` APIs that were deprecated in v7.x were + removed. This functionality has been moved to pikepdf. + +**Other changes** + +- Fixed an unhandled exception when attempting to mask barcodes. + {issue}`322` +- It is now possible to use ocrmypdf without pdfminer.six, to support + distributions that do not have it or cannot currently use it (e.g. + Homebrew). Downstream maintainers should include pdfminer.six if + possible. +- A warning is now issue when PDF/A conversion removes some XMP + metadata from the input PDF. (Only a "whitelist" of certain XMP + metadata types are allowed in PDF/A.) +- Fixed several issues that caused PDF/As to be produced with + nonconforming XMP metadata (would fail validation with veraPDF). +- Fixed some instances where invalid DocumentInfo from a PDF cause XMP + metadata creation to fail. +- Fixed a few documentation problems. +- pikepdf 1.0.2 is now required. + +## v7.4.0 + +- `--force-ocr` may now be used with the new `--threshold` and + `--mask-barcodes` features +- pikepdf >= 0.9.1 is now required. +- Changed metadata handling to pikepdf 0.9.1. As a result, metadata + handling of non-ASCII characters in Ghostscript 9.25 or later is + fixed. +- chardet >= 3.0.4 is temporarily listed as required. pdfminer.six + depends on it, but the most recent release does not specify this + requirement. + ({issue}`326`) +- python-xmp-toolkit and libexempi are no longer required. +- A new Docker image is now being provided for users who wish to access + OCRmyPDF over a simple HTTP interface, instead of the command line. +- Increase tolerance of PDFs that overflow or underflow the PDF + graphics stack. + ({issue}`325`) + +## v7.3.1 + +- Fixed performance regression from v7.3.0; fast page analysis was not + selected when it should be. +- Fixed a few exceptions related to the new `--mask-barcodes` feature + and improved argument checking +- Added missing detection of TrueType fonts that lack a Unicode mapping + +## v7.3.0 + +- Added a new feature `--redo-ocr` to detect existing OCR in a file, + remove it, and redo the OCR. This may be particularly helpful for + anyone who wants to take advantage of OCR quality improvements in + Tesseract 4.0. Note that OCR added by OCRmyPDF before version 3.0 + cannot be detected since it was not properly marked as invisible text + in the earliest versions. OCR that constructs a font from visible + text, such as Adobe Acrobat's ClearScan. + +- OCRmyPDF's content detection is generally more sophisticated. It + learns more about the contents of each PDF and makes better + recommendations: + + - OCRmyPDF can now detect when a PDF contains text that cannot be + mapped to Unicode (meaning it is readable to human eyes but + copy-pastes as gibberish). In these cases it recommends + `--force-ocr` to make the text searchable. + - PDFs containing vector objects are now rendered at more + appropriate resolution for OCR. + - We now exit with an error for PDFs that contain Adobe LiveCycle + Designer's dynamic XFA forms. Currently the open source community + does not have tools to work with these files. + - OCRmyPDF now warns when a PDF that contains Adobe AcroForms, since + such files probably do not need OCR. It can work with these files. + +- Added three new **experimental** features to improve OCR quality in + certain conditions. The name, syntax and behavior of these arguments + is subject to change. They may also be incompatible with some other + features. + + - `--remove-vectors` which strips out vector graphics. This can + improve OCR quality since OCR will not search artwork for readable + text; however, it currently removes "text as curves" as well. + - `--mask-barcodes` to detect and suppress barcodes in files. We + have observed that barcodes can interfere with OCR because they + are "text-like" but not actually textual. + - `--threshold` which uses a more sophisticated thresholding + algorithm than is currently in use in Tesseract OCR. This works + around a [known issue in Tesseract + 4.0](https://github.com/tesseract-ocr/tesseract/issues/1990) + with dark text on bright backgrounds. + +- Fixed an issue where an error message was not reported when the + installed Ghostscript was very old. + +- The PDF optimizer now saves files with object streams enabled when + the optimization level is `--optimize 1` or higher (the default). + This makes files a little bit smaller, but requires PDF 1.5. PDF 1.5 + was first released in 2003 and is broadly supported by PDF viewers, + but some rudimentary PDF parsers such as PyPDF2 do not understand + object streams. You can use the command line tool + `qpdf --object-streams=disable` or + [pikepdf](https://github.com/pikepdf/pikepdf) library to remove + them. + +- New dependency: pdfminer.six 20181108. Note this is a fork of the + Python 2-only pdfminer. + +- Deprecation notice: At the end of 2018, we will be ending support for + Python 3.5 and Tesseract 3.x. OCRmyPDF v7 will continue to work with + older versions. + +## v7.2.1 + +- Fixed compatibility with an API change in pikepdf 0.3.5. +- A kludge to support Leptonica versions older than 1.72 in the test + suite was dropped. Older versions of Leptonica are likely still + compatible. The only impact is that a portion of the test suite will + be skipped. + +## v7.2.0 + +**Lossy JBIG2 behavior change** + +A user reported that ocrmypdf was in fact using JBIG2 in **lossy** +compression mode. This was not the intended behavior. Users should +[review the technical concerns with JBIG2 in lossy +mode](https://abbyy.technology/en:kb:tip:jbig2_compression_and_ocr) +and decide if this is a concern for their use case. + +JBIG2 lossy mode does achieve higher compression ratios than any other +monochrome compression technology; for large text documents the savings +are considerable. JBIG2 lossless still gives great compression ratios +and is a major improvement over the older CCITT G4 standard. + +Only users who have reviewed the concerns with JBIG2 in lossy mode +should opt-in. As such, lossy mode JBIG2 is only turned on when the new +argument `--jbig2-lossy` is issued. This is independent of the setting +for `--optimize`. + +Users who did not install an optional JBIG2 encoder are unaffected. + +(Thanks to user 'bsdice' for reporting this issue.) + +**Other issues** + +- When the image optimizer quantizes an image to 1 bit per pixel, it + will now attempt to further optimize that image as CCITT or JBIG2, + instead of keeping it in the "flate" encoding which is not efficient + for 1 bpp images. + ({issue}`297`) +- Images in PDFs that are used as soft masks (i.e. transparency masks + or alpha channels) are now excluded from optimization. +- Fixed handling of Tesseract 4.0-rc1 which now accepts invalid + Tesseract configuration files, which broke the test suite. + +## v7.1.0 + +- Improve the performance of initial text extraction, which is done to + determine if a file contains existing text of some kind or not. On + large files, this initial processing is now about 20x times faster. + ({issue}`299`) +- pikepdf 0.3.3 is now required. +- Fixed {issue}`231`, a + problem with JPEG2000 images where image metadata was only available + inside the JPEG2000 file. +- Fixed some additional Ghostscript 9.25 compatibility issues. +- Improved handling of KeyboardInterrupt error messages. + ({issue}`301`) +- README.md is now served in GitHub markdown instead of + reStructuredText. + +## v7.0.6 + +- Blacklist Ghostscript 9.24, now that 9.25 is available and fixes many + regressions in 9.24. + +## v7.0.5 + +- Improve capability with Ghostscript 9.24, and enable the JPEG + passthrough feature when this version in installed. +- Ghostscript 9.24 lost the ability to set PDF title, author, subject + and keyword metadata to Unicode strings. OCRmyPDF will set ASCII + strings and warn when Unicode is suppressed. Other software may be + used to update metadata. This is a short term work around. +- PDFs generated by Kodak Capture Desktop, or generally PDFs that + contain indirect references to null objects in their table of + contents, would have an invalid table of contents after processing by + OCRmyPDF that might interfere with other viewers. This has been + fixed. +- Detect PDFs generated by Adobe LiveCycle, which can only be displayed + in Adobe Acrobat and Reader currently. When these are encountered, + exit with an error instead of performing OCR on the "Please wait" + error message page. + +## v7.0.4 + +- Fixed exception thrown when trying to optimize a certain type of PNG + embedded in a PDF with the `-O2` +- Update to pikepdf 0.3.2, to gain support for optimizing some + additional image types that were previously excluded from + optimization (CMYK and grayscale). Fixes + {issue}`285`. + +## v7.0.3 + +- Fixed {issue}`284`, an error + when parsing inline images that have are also image masks, by + upgrading pikepdf to 0.3.1 + +## v7.0.2 + +- Fixed a regression with `--rotate-pages` on pages that already had + rotations applied. + ({issue}`279`) +- Improve quality of page rotation in some cases by rasterizing a + higher quality preview image. + ({issue}`281`) + +## v7.0.1 + +- Fixed compatibility with img2pdf >= 0.3.0 by rejecting input images + that have an alpha channel +- Add forward compatibility for pikepdf 0.3.0 (unrelated to img2pdf) +- Various documentation updates for v7.0.0 changes + +## v7.0.0 + +- The core algorithm for combining OCR layers with existing PDF pages + has been rewritten and improved considerably. PDFs are no longer + split into single page PDFs for processing; instead, images are + rendered and the OCR results are grafted onto the input PDF. The new + algorithm uses less temporary disk space and is much more performant + especially for large files. + +- New dependency: [pikepdf](https://github.com/pikepdf/pikepdf). + pikepdf is a powerful new Python PDF library driving the latest + OCRmyPDF features, built on the QPDF C++ library (libqpdf). + +- New feature: PDF optimization with `-O` or `--optimize`. After + OCR, OCRmyPDF will perform image optimizations relevant to OCR PDFs. + + - If a JBIG2 encoder is available, then monochrome images will be + converted, with the potential for huge savings on large black and + white images, since JBIG2 is far more efficient than any other + monochrome (bi-level) compression. (All known US patents related + to JBIG2 have probably expired, but it remains the responsibility + of the user to supply a JBIG2 encoder such as + [jbig2enc](https://github.com/agl/jbig2enc). OCRmyPDF does not + implement JBIG2 encoding.) + - If `pngquant` is installed, OCRmyPDF will optionally use it to + perform lossy quantization and compression of PNG images. + - The quality of JPEGs can also be lowered, on the assumption that a + lower quality image may be suitable for storage after OCR. + - This image optimization component will eventually be offered as an + independent command line utility. + - Optimization ranges from `-O0` through `-O3`, where `0` + disables optimization and `3` implements all options. `1`, the + default, performs only safe and lossless optimizations. (This is + similar to GCC's optimization parameter.) The exact type of + optimizations performed will vary over time. + +- Small amounts of text in the margins of a page, such as watermarks, + page numbers, or digital stamps, will no longer prevent the rest of a + page from being OCRed when `--skip-text` is issued. This behavior + is based on a heuristic. + +- Removed features + + - The deprecated `--pdf-renderer tesseract` PDF renderer was + removed. + - `-g`, the option to generate debug text pages, was removed + because it was a maintenance burden and only worked in isolated + cases. HOCR pages can still be previewed by running the + hocrtransform.py with appropriate settings. + +- Removed dependencies + + - `PyPDF2` + - `defusedxml` + - `PyMuPDF` + +- The `sandwich` PDF renderer can be used with all supported versions + of Tesseract, including that those prior to v3.05 which don't support + `-c textonly`. (Tesseract v4.0.0 is recommended and more + efficient.) + +- `--pdf-renderer auto` option and the diagnostics used to select a + PDF renderer now work better with old versions, but may make + different decisions than past versions. + +- If everything succeeds but PDF/A conversion fails, a distinct return + code is now returned (`ExitCode.pdfa_conversion_failed (10)`) where + this situation previously returned + `ExitCode.invalid_output_pdf (4)`. The latter is now returned only + if there is some indication that the output file is invalid. + +- Notes for downstream packagers + + - There is also a new dependency on `python-xmp-toolkit` which in + turn depends on `libexempi3`. + - It may be necessary to separately `pip install pycparser` to + avoid [another Python 3.7 + issue](https://github.com/eliben/pycparser/pull/135). + +## v6.2.5 + +- Disable a failing test due to Tesseract 4.0rc1 behavior change. + Previously, Tesseract would exit with an error message if its + configuration was invalid, and OCRmyPDF would intercept this message. + Now Tesseract issues a warning, which OCRmyPDF v6.2.5 may relay or + ignore. (In v7.x, OCRmyPDF will respond to the warning.) +- This release branch no longer supports using the optional PyMuPDF + installation, since it was removed in v7.x. +- This release branch no longer supports macOS. macOS users should + upgrade to v7.x. + +## v6.2.4 + +- Backport Ghostscript 9.25 compatibility fixes, which removes support + for setting Unicode metadata +- Backport blacklisting Ghostscript 9.24 +- Older versions of Ghostscript are still supported + +## v6.2.3 + +- Fixed compatibility with img2pdf >= 0.3.0 by rejecting input images + that have an alpha channel +- This version will be included in Ubuntu 18.10 + +## v6.2.2 + +- Backport compatibility fixes for Python 3.7 and ruffus 2.7.0 from + v7.0.0 +- Backport fix to ignore masks when deciding what colors are on a page +- Backport some minor improvements from v7.0.0: better argument + validation and warnings about the Tesseract 4.0.0 `--user-words` + regression + +## v6.2.1 + +- Fixed recent versions of Tesseract (after 4.0.0-beta1) not being + detected as supporting the `sandwich` renderer ({issue}`271`). + +## v6.2.0 + +- **Docker**: The Docker image `ocrmypdf-tess4` has been removed. The + main Docker images, `ocrmypdf` and `ocrmypdf-polyglot` now use + Ubuntu 18.04 as a base image, and as such Tesseract 4.0.0-beta1 is + now the Tesseract version they use. There is no Docker image based on + Tesseract 3.05 anymore. +- Creation of PDF/A-3 is now supported. However, there is no ability to + attach files to PDF/A-3. +- Lists more reasons why the file size might grow. +- Fixed {issue}`262`, + `--remove-background` error on PDFs contained colormapped + (paletted) images. +- Fixed another XMP metadata validation issue, in cases where the input + file's creation date has no timezone and the creation date is not + overridden. + +## v6.1.5 + +- Fixed {issue}`253`, a + possible division by zero when using the `hocr` renderer. +- Fixed incorrectly formatted `` field inside XMP + metadata for PDF/As. veraPDF flags this as a PDF/A validation + failure. The error is caused the timezone and final digit of the + seconds of modified time to be omitted, so at worst the modification + time stamp is rounded to the nearest 10 seconds. + +## v6.1.4 + +- Fixed {issue}`248` + `--clean` argument may remove OCR from left column of text on + certain documents. We now set `--layout none` to suppress this. +- The test cache was updated to reflect the change above. +- Change test suite to accommodate Ghostscript 9.23's new ability to + insert JPEGs into PDFs without transcoding. +- XMP metadata in PDFs is now examined using `defusedxml` for safety. +- If an external process exits with a signal when asked to report its + version, we now print the system error message instead of suppressing + it. This occurred when the required executable was found but was + missing a shared library. +- qpdf 7.0.0 or newer is now required as the test suite can no longer + pass without it. + +### Notes + +- An apparent [regression in Ghostscript + 9.23](https://bugs.ghostscript.com/show_bug.cgi?id=699216) will + cause some ocrmypdf output files to become invalid in rare cases; the + workaround for the moment is to set `--force-ocr`. + +## v6.1.3 + +- Fixed {issue}`247`, + `/CreationDate` metadata not copied from input to output. +- A warning is now issued when Python 3.5 is used on files with a large + page count, as this case is known to regress to single core + performance. The cause of this problem is unknown. + +## v6.1.2 + +- Upgrade to PyMuPDF v1.12.5 which includes a more complete fix to + {issue}`239`. +- Add `defusedxml` dependency. + +## v6.1.1 + +- Fixed text being reported as found on all pages if PyMuPDF is not + installed. + +## v6.1.0 + +- PyMuPDF is now an optional but recommended dependency, to alleviate + installation difficulties on platforms that have less access to + PyMuPDF than the author anticipated. (For version 6.x only) install + OCRmyPDF with `pip install ocrmypdf[fitz]` to use it to its full + potential. +- Fixed `FileExistsError` that could occur if OCR timed out while it + was generating the output file. + ({issue}`218`) +- Fixed table of contents/bookmarks all being redirected to page 1 when + generating a PDF/A (with PyMuPDF). (Without PyMuPDF the table of + contents is removed in PDF/A mode.) +- Fixed "RuntimeError: invalid key in dict" when table of + contents/bookmarks titles contained the character `)`. + ({issue}`239`) +- Added a new argument `--skip-repair` to skip the initial PDF repair + step if the PDF is already well-formed (because another program + repaired it). + +## v6.0.0 + +- The software license has been changed to GPLv3 [it has since changed again]. + Test resource files and some individual sources may have other licenses. + +- OCRmyPDF now depends on + [PyMuPDF](https://pymupdf.readthedocs.io/en/latest/installation/). + Including PyMuPDF is the primary reason for the change to GPLv3. + +- Other backward incompatible changes + + - The `OCRMYPDF_TESSERACT`, `OCRMYPDF_QPDF`, `OCRMYPDF_GS` and + `OCRMYPDF_UNPAPER` environment variables are no longer used. + Change `PATH` if you need to override the external programs + OCRmyPDF uses. + - The `ocrmypdf` package has been moved to `src/ocrmypdf` to + avoid issues with accidental import. + - The function `ocrmypdf.exec.get_program` was removed. + - The deprecated module `ocrmypdf.pageinfo` was removed. + - The `--pdf-renderer tess4` alias for `sandwich` was removed. + +- Fixed an issue where OCRmyPDF failed to detect existing text on + pages, depending on how the text and fonts were encoded within the + PDF. ({issue}`233,232`) + +- Fixed an issue that caused dramatic inflation of file sizes when + `--skip-text --output-type pdf` was used. OCRmyPDF now removes + duplicate resources such as fonts, images and other objects that it + generates. ({issue}`237`) + +- Improved performance of the initial page splitting step. Originally + this step was not believed to be expensive and ran in a process. + Large file testing revealed it to be a bottleneck, so it is now + parallelized. On a 700 page file with quad core machine, this change + saves about 2 minutes. ({issue}`234`) + +- The test suite now includes a cache that can be used to speed up test + runs across platforms. This also does not require computing + checksums, so it's faster. ({issue}`217`) + +## v5.7.0 + +- Fixed an issue that caused poor CPU utilization on machines with more + than 4 cores when running Tesseract 4. (Related to {issue}`217`.) + +- The 'hocr' renderer has been improved. The 'sandwich' and 'tesseract' + renderers are still better for most use cases, but 'hocr' may be + useful for people who work with the PDF.js renderer in English/ASCII + languages. ({issue}`225`) + + - It now formats text in a matter that is easier for certain PDF + viewers to select and extract copy and paste text. This should + help macOS Preview and PDF.js in particular. + - The appearance of selected text and behavior of selecting text is + improved. + - The PDF content stream now uses relative moves, making it more + compact and easier for viewers to determine when two words on the + same line. + - It can now deal with text on a skewed baseline. + - Thanks to @cforcey for the pull request, @jbreiden for many + helpful suggestions, @ctbarbour for another round of improvements, + and @acaloiaro for an independent review. + +## v5.6.3 + +- Suppress two debug messages that were too verbose + +## v5.6.2 + +- Development branch accidentally tagged as release. Do not use. + +## v5.6.1 + +- Fixed {issue}`219`: change + how the final output file is created to avoid triggering permission + errors when the output is a special file such as `/dev/null` +- Fixed test suite failures due to a qpdf 8.0.0 regression and Python + 3.5's handling of symlink +- The "encrypted PDF" error message was different depending on the type + of PDF encryption. Now a single clear message appears for all types + of PDF encryption. +- ocrmypdf is now in Homebrew. Homebrew users are advised to the + version of ocrmypdf in the official homebrew-core formulas rather + than the private tap. +- Some linting + +## v5.6.0 + +- Fixed {issue}`216`: preserve + "text as curves" PDFs without rasterizing file +- Related to the above, messages about rasterizing are more consistent +- For consistency versions minor releases will now get the trailing .0 + they always should have had. + +## v5.5 + +- Add new argument `--max-image-mpixels`. Pillow 5.0 now raises an + exception when images may be decompression bombs. This argument can + be used to override the limit Pillow sets. +- Fixed output page cropped when using the sandwich renderer and OCR is + skipped on a rotated and image-processed page +- A warning is now issued when old versions of Ghostscript are used in + cases known to cause issues with non-Latin characters +- Fixed a few parameter validation checks for `-output-type pdfa-1` and + `pdfa-2` + +## v5.4.4 + +- Fixed {issue}`181`: fix + final merge failure for PDFs with more pages than the system file + handle limit (`ulimit -n`) +- Fixed {issue}`200`: an + uncommon syntax for formatting decimal numbers in a PDF would cause + qpdf to issue a warning, which ocrmypdf treated as an error. Now this + the warning is relayed. +- Fixed an issue where intermediate PDFs would be created at version 1.3 + instead of the version of the original file. It's possible but + unlikely this had side effects. +- A warning is now issued when older versions of qpdf are used since + issues like + {issue}`200` cause + qpdf to infinite-loop +- Address issue + {issue}`140`: if + Tesseract outputs invalid UTF-8, escape it and print its message + instead of aborting with a Unicode error +- Adding previously unlisted setup requirement, pytest-runner +- Update documentation: fix an error in the example script for Synology + with Docker images, improved security guidance, advised + `pip install --user` + +## v5.4.3 + +- If a subprocess fails to report its version when queried, exit + cleanly with an error instead of throwing an exception +- Added test to confirm that the system locale is Unicode-aware and + fail early if it's not +- Clarified some copyright information +- Updated pinned requirements.txt so the homebrew formula captures more + recent versions + +## v5.4.2 + +- Fixed a regression from v5.4.1 that caused sidecar files to be + created as empty files + +## v5.4.1 + +- Add workaround for Tesseract v4.00alpha crash when trying to obtain + orientation and the latest language packs are installed + +## v5.4 + +- Change wording of a deprecation warning to improve clarity +- Added option to generate PDF/A-1b output if desired + (`--output-type pdfa-1`); default remains PDF/A-2b generation +- Update documentation + +## v5.3.3 + +- Fixed missing error message that should occur when trying to force + `--pdf-renderer sandwich` on old versions of Tesseract +- Update copyright information in test files +- Set system `LANG` to UTF-8 in Dockerfiles to avoid UTF-8 encoding + errors + +## v5.3.2 + +- Fixed a broken test case related to language packs + +## v5.3.1 + +- Fixed wrong return code given for missing Tesseract language packs +- Fixed "brew audit" crashing on Travis when trying to auto-brew + +## v5.3 + +- Added `--user-words` and `--user-patterns` arguments which are + forwarded to Tesseract OCR as words and regular expressions + respective to use to guide OCR. Supplying a list of subject-domain + words should assist Tesseract with resolving words. + ({issue}`165`) +- Using a non Latin-1 language with the "hocr" renderer now warns about + possible OCR quality and recommends workarounds + ({issue}`176`) +- Output file path added to error message when that location is not + writable + ({issue}`175`) +- Otherwise valid PDFs with leading whitespace at the beginning of the + file are now accepted + +## v5.2 + +- When using Tesseract 3.05.01 or newer, OCRmyPDF will select the + "sandwich" PDF renderer by default, unless another PDF renderer is + specified with the `--pdf-renderer` argument. The previous behavior + was to select `--pdf-renderer=hocr`. +- The "tesseract" PDF renderer is now deprecated, since it can cause + problems with Ghostscript on Tesseract 3.05.00 +- The "tess4" PDF renderer has been renamed to "sandwich". "tess4" is + now a deprecated alias for "sandwich". + +## v5.1 + +- Files with pages larger than 200" (5080 mm) in either dimension are + now supported with `--output-type=pdf` with the page size preserved + (in the PDF specification this feature is called UserUnit scaling). + Due to Ghostscript limitations this is not available in conjunction + with PDF/A output. + +## v5.0.1 + +- Fixed {issue}`169`, + exception due to failure to create sidecar text files on some + versions of Tesseract 3.04, including the jbarlow83/ocrmypdf Docker + image + +## v5.0 + +- Backward incompatible changes + + > - Support for Python 3.4 dropped. Python 3.5 is now required. + > - Support for Tesseract 3.02 and 3.03 dropped. Tesseract 3.04 or + > newer is required. Tesseract 4.00 (alpha) is supported. + > - The OCRmyPDF.sh script was removed. + +- Add a new feature, `--sidecar`, which allows creating "sidecar" + text files which contain the OCR results in plain text. These OCR + text is more reliable than extracting text from PDFs. Closes + {issue}`126`. + +- New feature: `--pdfa-image-compression`, which allows overriding + Ghostscript's lossy-or-lossless image encoding heuristic and making + all images JPEG encoded or lossless encoded as desired. Fixes + {issue}`163`. + +- Fixed {issue}`143`, added + `--quiet` to suppress "INFO" messages + +- Fixed {issue}`164`, a typo + +- Removed the command line parameters `-n` and `--just-print` since + they have not worked for some time (reported as Ubuntu bug + [#1687308](https://bugs.launchpad.net/ubuntu/+source/ocrmypdf/+bug/1687308)) + +## v4.5.6 + +- Fixed {issue}`156`, + 'NoneType' object has no attribute 'getObject' on pages with no + optional /Contents record. This should resolve all issues related to + pages with no /Contents record. +- Fixed {issue}`158`, ocrmypdf + now stops and terminates if Ghostscript fails on an intermediate + step, as it is not possible to proceed. +- Fixed {issue}`160`, + exception thrown on certain invalid arguments instead of error + message + +## v4.5.5 + +- Automated update of macOS homebrew tap +- Fixed {issue}`154`, KeyError + '/Contents' when searching for text on blank pages that have no + /Contents record. Note: incomplete fix for this issue. + +## v4.5.4 + +- Fixed `--skip-big` raising an exception if a page contains no images + ({issue}`152`) (thanks + to @TomRaz) +- Fixed an issue where pages with no images might trigger "cannot write + mode P as JPEG" + ({issue}`151`) + +## v4.5.3 + +- Added a workaround for Ghostscript 9.21 and probably earlier versions + would fail with the error message "VMerror -25", due to a Ghostscript + bug in XMP metadata handling +- High Unicode characters (U+10000 and up) are no longer accepted for + setting metadata on the command line, as Ghostscript may not handle + them correctly. +- Fixed an issue where the `tess4` renderer would duplicate content + onto output pages if tesseract failed or timed out +- Fixed `tess4` renderer not recognized when lossless reconstruction + is possible + +## v4.5.2 + +- Fixed {issue}`147`, + `--pdf-renderer tess4 --clean` will produce an oversized page + containing the original image in the bottom left corner, due to loss + DPI information. +- Make "using Tesseract 4.0" warning less ominous +- Set up machinery for homebrew OCRmyPDF tap + +## v4.5.1 + +- Fixed {issue}`137`, + proportions of images with a non-square pixel aspect ratio would be + distorted in output for `--force-ocr` and some other combinations + of flags + +## v4.5 + +- PDFs containing "Form XObjects" are now supported (issue + {issue}`134`; PDF + reference manual 8.10), and images they contain are taken into + account when determining the resolution for rasterizing +- The Tesseract 4 Docker image no longer includes all languages, + because it took so long to build something would tend to fail +- OCRmyPDF now warns about using `--pdf-renderer tesseract` with + Tesseract 3.04 or lower due to issues with Ghostscript corrupting the + OCR text in these cases + +## v4.4.2 + +- The Docker images (ocrmypdf, ocrmypdf-polyglot, ocrmypdf-tess4) are + now based on Ubuntu 16.10 instead of Debian stretch + + - This makes supporting the Tesseract 4 image easier + - This could be a disruptive change for any Docker users who built + customized these images with their own changes, and made those + changes in a way that depends on Debian and not Ubuntu + +- OCRmyPDF now prevents running the Tesseract 4 renderer with Tesseract + 3.04, which was permitted in v4.4 and v4.4.1 but will not work + +## v4.4.1 + +- To prevent a [TIFF output + error](https://github.com/python-pillow/Pillow/issues/2206) caused + by img2pdf >= 0.2.1 and Pillow \<= 3.4.2, dependencies have been + tightened +- The Tesseract 4.00 simultaneous process limit was increased from 1 to + 2, since it was observed that 1 lowers performance +- Documentation improvements to describe the `--tesseract-config` + feature +- Added test cases and fixed error handling for `--tesseract-config` +- Tweaks to setup.py to deal with issues in the v4.4 release + +## v4.4 + +- Tesseract 4.00 is now supported on an experimental basis. + + - A new rendering option `--pdf-renderer tess4` exploits Tesseract + 4's new text-only output PDF mode. See the documentation on PDF + Renderers for details. + - The `--tesseract-oem` argument allows control over the Tesseract + 4 OCR engine mode (tesseract's `--oem`). Use + `--tesseract-oem 2` to enforce the new LSTM mode. + - Fixed poor performance with Tesseract 4.00 on Linux + +- Fixed an issue that caused corruption of output to stdout in some + cases + +- Removed test for Pillow JPEG and PNG support, as the minimum + supported version of Pillow now enforces this + +- OCRmyPDF now tests that the intended destination file is writable + before proceeding + +- The test suite now requires `pytest-helpers-namespace` to run (but + not install) + +- Significant code reorganization to make OCRmyPDF re-entrant and + improve performance. All changes should be backward compatible for + the v4.x series. + + - However, OCRmyPDF's dependency "ruffus" is not re-entrant, so no + Python API is available. Scripts should continue to use the + command line interface. + +## v4.3.5 + +- Update documentation to confirm Python 3.6.0 compatibility. No code + changes were needed, so many earlier versions are likely supported. + +## v4.3.4 + +- Fixed "decimal.InvalidOperation: quantize result has too many digits" + for high DPI images + +## v4.3.3 + +- Fixed PDF/A creation with Ghostscript 9.20 properly +- Fixed an exception on inline stencil masks with a missing optional + parameter + +## v4.3.2 + +- Fixed a PDF/A creation issue with Ghostscript 9.20 (note: this fix + did not actually work) + +## v4.3.1 + +- Fixed an issue where pages produced by the "hocr" renderer after a + Tesseract timeout would be rotated incorrectly if the input page was + rotated with a /Rotate marker +- Fixed a file handle leak in LeptonicaErrorTrap that would cause a + "too many open files" error for files around hundred pages of pages + long when `--deskew` or `--remove-background` or other Leptonica + based image processing features were in use, depending on the system + value of `ulimit -n` +- Ability to specify multiple languages for multilingual documents is + now advertised in documentation +- Reduced the file sizes of some test resources +- Cleaned up debug output +- Tesseract caching in test cases is now more cautious about false + cache hits and reproducing exact output, not that any problems were + observed + +## v4.3 + +- New feature `--remove-background` to detect and erase the + background of color and grayscale images + +- Better documentation + +- Fixed an issue with PDFs that draw images when the raster stack depth + is zero + +- ocrmypdf can now redirect its output to stdout for use in a shell + pipeline + + - This does not improve performance since temporary files are still + used for buffering + - Some output validation is disabled in this mode + +## v4.2.5 + +- Fixed an issue + ({issue}`100`) with + PDFs that omit the optional /BitsPerComponent parameter on images +- Removed non-free file milk.pdf + +## v4.2.4 + +- Fixed an error + ({issue}`90`) caused by + PDFs that use stencil masks properly +- Fixed handling of PDFs that try to draw images or stencil masks + without properly setting up the graphics state (such images are now + ignored for the purposes of calculating DPI) + +## v4.2.3 + +- Fixed an issue with PDFs that store page rotation (/Rotate) in an + indirect object + +- Integrated a few fixes to simplify downstream packaging (Debian) + + - The test suite no longer assumes it is installed + - If running Linux, skip a test that passes Unicode on the command + line + +- Added a test case to check explicit masks and stencil masks + +- Added a test case for indirect objects and linearized PDFs + +- Deprecated the OCRmyPDF.sh shell script + +## v4.2.2 + +- Improvements to documentation + +## v4.2.1 + +- Fixed an issue where PDF pages that contained stencil masks would + report an incorrect DPI and cause Ghostscript to abort +- Implemented stdin streaming + +## v4.2 + +- ocrmypdf will now try to convert single image files to PDFs if they + are provided as input + ({issue}`15`) + + - This is a basic convenience feature. It only supports a single + image and always makes the image fill the whole page. + - For better control over image to PDF conversion, use `img2pdf` + (one of ocrmypdf's dependencies) + +- New argument `--output-type {pdf|pdfa}` allows disabling + Ghostscript PDF/A generation + + - `pdfa` is the default, consistent with past behavior + - `pdf` provides a workaround for users concerned about the + increase in file size from Ghostscript forcing JBIG2 images to + CCITT and transcoding JPEGs + - `pdf` preserves as much as it can about the original file, + including problems that PDF/A conversion fixes + +- PDFs containing images with "non-square" pixel aspect ratios, such as + 200x100 DPI, are now handled and converted properly (fixing a bug + that caused to be cropped) + +- `--force-ocr` rasterizes pages even if they contain no images + + - supports users who want to use OCRmyPDF to reconstruct text + information in PDFs with damaged Unicode maps (copy and paste text + does not match displayed text) + - supports reinterpreting PDFs where text was rendered as curves for + printing, and text needs to be recovered + - fixes issue + {issue}`82` + +- Fixes an issue where, with certain settings, monochrome images in + PDFs would be converted to 8-bit grayscale, increasing file size + ({issue}`79`) + +- Support for Ubuntu 12.04 LTS "precise" has been dropped in favor of + (roughly) Ubuntu 14.04 LTS "trusty" + + - Some Ubuntu "PPAs" (backports) are needed to make it work + +- Support for some older dependencies dropped + + - Ghostscript 9.15 or later is now required (available in Ubuntu + trusty with backports) + - Tesseract 3.03 or later is now required (available in Ubuntu + trusty) + +- Ghostscript now runs in "safer" mode where possible + +## v4.1.4 + +- Bug fix: monochrome images with an ICC profile attached were + incorrectly converted to full color images if lossless reconstruction + was not possible due to other settings; consequence was increased + file size for these images + +## v4.1.3 + +- More helpful error message for PDFs with version 4 security handler +- Update usage instructions for Windows/Docker users +- Fixed order of operations for matrix multiplication (no effect on most + users) +- Add a few leptonica wrapper functions (no effect on most users) + +## v4.1.2 + +- Replace IEC sRGB ICC profile with Debian's sRGB (from + icc-profiles-free) which is more compatible with the MIT license +- More helpful error message for an error related to certain types of + malformed PDFs + +## v4.1 + +- `--rotate-pages` now only rotates pages when reasonably confidence + in the orientation. This behavior can be adjusted with the new + argument `--rotate-pages-threshold` +- Fixed problems in error checking if `unpaper` is uninstalled or + missing at run-time +- Fixed problems with "RethrownJobError" errors during error handling + that suppressed the useful error messages + +## v4.0.7 + +- Minor correction to Ghostscript output settings + +## v4.0.6 + +- Update install instructions +- Provide a sRGB profile instead of using Ghostscript's + +## v4.0.5 + +- Remove some verbose debug messages from v4.0.4 +- Fixed temporary that wasn't being deleted +- DPI is now calculated correctly for cropped images, along with other + image transformations +- Inline images are now checked during DPI calculation instead of + rejecting the image + +## v4.0.4 + +Released with verbose debug message turned on. Do not use. Skip to +v4.0.5. + +## v4.0.3 + +New features + +- Page orientations detected are now reported in a summary comment + +Fixes + +- Show stack trace if unexpected errors occur +- Treat "too few characters" error message from Tesseract as a reason + to skip that page rather than abort the file +- Docker: fix blank JPEG2000 issue by insisting on Ghostscript versions + that have this fixed + +## v4.0.2 + +Fixes + +- Fixed compatibility with Tesseract 3.04.01 release, particularly its + different way of outputting orientation information +- Improved handling of Tesseract errors and crashes +- Fixed use of chmod on Docker that broke most test cases + +## v4.0.1 + +Fixes + +- Fixed a KeyError if tesseract fails to find page orientation + information + +## v4.0 + +New features + +- Automatic page rotation (`-r`) is now available. It uses ignores + any prior rotation information on PDFs and sets rotation based on the + dominant orientation of detectable text. This feature is fairly + reliable but some false positives occur especially if there is not + much text to work with. + ({issue}`4`) +- Deskewing is now performed using Leptonica instead of unpaper. + Leptonica is faster and more reliable at image deskewing than + unpaper. + +Fixes + +- Fixed an issue where lossless reconstruction could cause some pages + to be appear incorrectly if the page was rotated by the user in + Acrobat after being scanned (specifically if it a /Rotate tag) +- Fixed an issue where lossless reconstruction could misalign the + graphics layer with respect to text layer if the page had been + cropped such that its origin is not (0, 0) + ({issue}`49`) + +Changes + +- Logging output is now much easier to read +- `--deskew` is now performed by Leptonica instead of unpaper + ({issue}`25`) +- libffi is now required +- Some changes were made to the Docker and Travis build environments to + support libffi +- `--pdf-renderer=tesseract` now displays a warning if the Tesseract + version is less than 3.04.01, the planned release that will include + fixes to an important OCR text rendering bug in Tesseract 3.04.00. + You can also manually install ./share/sharp2.ttf on top of pdf.ttf in + your Tesseract tessdata folder to correct the problem. + +## v3.2.1 + +Changes + +- Fixed {issue}`47` + "convert() got and unexpected keyword argument 'dpi'" by upgrading to + img2pdf 0.2 +- Tweaked the Dockerfiles + +## v3.2 + +New features + +- Lossless reconstruction: when possible, OCRmyPDF will inject text + layers without otherwise manipulating the content and layout of a PDF + page. For example, a PDF containing a mix of vector and raster + content would see the vector content preserved. Images may still be + transcoded during PDF/A conversion. (`--deskew` and + `--clean-final` disable this mode, necessarily.) +- New argument `--tesseract-pagesegmode` allows you to pass page + segmentation arguments to Tesseract OCR. This helps for two column + text and other situations that confuse Tesseract. +- Added a new "polyglot" version of the Docker image, that generates + Tesseract with all languages packs installed, for the polyglots among + us. It is much larger. + +Changes + +- JPEG transcoding quality is now 95 instead of the default 75. Bigger + file sizes for less degradation. + +## v3.1.1 + +Changes + +- Fixed bug that caused incorrect page size and DPI calculations on + documents with mixed page sizes + +## v3.1 + +Changes + +- Default output format is now PDF/A-2b instead of PDF/A-1b +- Python 3.5 and macOS El Capitan are now supported platforms - no + changes were needed to implement support +- Improved some error messages related to missing input files +- Fixed {issue}`20`: uppercase .PDF extension not accepted +- Fixed an issue where OCRmyPDF failed to text that certain pages + contained previously OCR'ed text, such as OCR text produced by + Tesseract 3.04 +- Inserts /Creator tag into PDFs so that errors can be traced back to + this project +- Added new option `--pdf-renderer=auto`, to let OCRmyPDF pick the + best PDF renderer. Currently it always chooses the 'hocrtransform' + renderer but that behavior may change. +- Set up Travis CI automatic integration testing + +## v3.0 + +New features + +- Easier installation with a Docker container or Python's `pip` + package manager +- Eliminated many external dependencies, so it's easier to setup +- Now installs `ocrmypdf` to `/usr/local/bin` or equivalent for + system-wide access and easier typing +- Improved command line syntax and usage help (`--help`) +- Tesseract 3.03+ PDF page rendering can be used instead for better + positioning of recognized text (`--pdf-renderer tesseract`) +- PDF metadata (title, author, keywords) are now transferred to the + output PDF +- PDF metadata can also be set from the command line (`--title`, + etc.) +- Automatic repairs malformed input PDFs if possible +- Added test cases to confirm everything is working +- Added option to skip extremely large pages that take too long to OCR + and are often not OCRable (e.g. large scanned maps or diagrams); + other pages are still processed (`--skip-big`) +- Added option to kill Tesseract OCR process if it seems to be taking + too long on a page, while still processing other pages + (`--tesseract-timeout`) +- Less common colorspaces (CMYK, palette) are now supported by + conversion to RGB +- Multiple images on the same PDF page are now supported + +Changes + +- New, robust rewrite in Python 3.4+ with + [ruffus](http://www.ruffus.org.uk/index.html) pipelines + +- Now uses Ghostscript 9.14's improved color conversion model to + preserve PDF colors + +- OCR text is now rendered in the PDF as invisible text. Previous + versions of OCRmyPDF incorrectly rendered visible text with an image + on top. + +- All "tasks" in the pipeline can be executed in parallel on any + available CPUs, increasing performance + +- The `-o DPI` argument has been phased out, in favor of + `--oversample DPI`, in case we need `-o OUTPUTFILE` in the future + +- Removed several dependencies, so it's easier to install. We no longer + use: + + - GNU [parallel](https://www.gnu.org/software/parallel/) + - [ImageMagick](http://www.imagemagick.org/script/index.php) + - Python 2.7 + - Poppler + - [MuPDF](http://mupdf.com/docs/) tools + - shell scripts + - Java and [JHOVE](http://jhove.sourceforge.net/) + - libxml2 + +- Some new external dependencies are required or optional, compared to + v2.x: + + - Ghostscript 9.14+ + - [qpdf](http://qpdf.sourceforge.net/) 5.0.0+ + - [Unpaper](https://github.com/Flameeyes/unpaper) 6.1 (optional) + - some automatically managed Python packages + +Release candidates^ + +- rc9: + + - Fix + {issue}`118`: + report error if ghostscript iccprofiles are missing + - fixed another issue related to + {issue}`111`: PDF + rasterized to palette file + - add support image files with a palette + - don't try to validate PDF file after an exception occurs + +- rc8: + + - Fix + {issue}`111`: + exception thrown if PDF is missing DocumentInfo dictionary + +- rc7: + + - fix error when installing direct from pip, "no such file + 'requirements.txt'" + +- rc6: + + - dropped libxml2 (Python lxml) since Python 3's internal XML parser + is sufficient + - set up Docker container + - fix Unicode errors if recognized text contains Unicode characters + and system locale is not UTF-8 + +- rc5: + + - dropped Java and JHOVE in favour of qpdf + - improved command line error output + - additional tests and bug fixes + - tested on Ubuntu 14.04 LTS + +- rc4: + + - dropped MuPDF in favour of qpdf + - fixed some installer issues and errors in installation + instructions + - improve performance: run Ghostscript with multithreaded rendering + - improve performance: use multiple cores by default + - bug fix: checking for wrong exception on process timeout + +- rc3: skipping version number intentionally to avoid confusion with + Tesseract + +- rc2: first release for public testing to test-PyPI, Github + +- rc1: testing release process + +## Compatibility notes + +- `./OCRmyPDF.sh` script is still available for now +- Stacking the verbosity option like `-vvv` is no longer supported +- The configuration file `config.sh` has been removed. Instead, you + can feed a file to the arguments for common settings: + +``` +ocrmypdf input.pdf output.pdf @settings.txt +``` + +where `settings.txt` contains *one argument per line*, for example: + +``` +-l +deu +--author +A. Merkel +--pdf-renderer +tesseract +``` + +Fixes + +- Handling of filenames containing spaces: fixed + +Notes and known issues + +- Some dependencies may work with lower versions than tested, so try + overriding dependencies if they are "in the way" to see if they work. +- `--pdf-renderer tesseract` will output files with an incorrect page + size in Tesseract 3.03, due to a bug in Tesseract. +- PDF files containing "inline images" are not supported and won't be + for the 3.0 release. Scanned images almost never contain inline + images. + +## v2.2-stable (2014-09-29) + +OCRmyPDF versions 1 and 2 were implemented as shell scripts. OCRmyPDF +3.0+ is a fork that gradually replaced all shell scripts with Python +while maintaining the existing command line arguments. No one is +maintaining old versions. + +For details on older versions, see the [final version of its release +notes](https://github.com/fritz-hh/OCRmyPDF/blob/7fd3dbdf42ca53a619412ce8add7532c5e81a9d1/RELEASE_NOTES.md). diff --git a/docs/release_notes.rst b/docs/release_notes.rst deleted file mode 100644 index ea358727..00000000 --- a/docs/release_notes.rst +++ /dev/null @@ -1,3043 +0,0 @@ -.. SPDX-FileCopyrightText: 2022 James R. Barlow -.. -.. SPDX-License-Identifier: CC-BY-SA-4.0 - -============= -Release notes -============= - -OCRmyPDF uses `semantic versioning `__ for its -command line interface and its public API. - -OCRmyPDF's output messages are not considered part of the stable interface - -that is, output messages may be improved at any release level, so parsing them -may be unreliable. Use the API to depend on precise behavior. - -The public API may be useful in scripts that launch OCRmyPDF processes or that -wish to use some of its features for working with PDFs. - -The most recent release of OCRmyPDF is |OCRmyPDF PyPI|. Any newer versions -referred to in these notes may exist the main branch but have not been -tagged yet. - -OCRmyPDF typically supports the three most recent Python versions. - -.. note:: - - Attention maintainers: these release notes may be updated with information - about a forthcoming release that has not been tagged yet. A release is only - official when it's tagged and posted to PyPI. - -.. |OCRmyPDF PyPI| image:: https://img.shields.io/pypi/v/ocrmypdf.svg - -v16.10.0 -======== - -- Added hocr textangle processing, improving handling of text at angles. - Thanks @0dinD :issue:`1467` -- Docker documentation updates related to podman. Thanks @rugk. :issue:`1489,1488` -- Dropped webservice.py's fragile use of ttyd. Instead, messages from ocrmypdf are - printed to the console. -- Fixed broken test test_hocrtransform_matches_sandwich, which had become - an invalid test. Thanks @QuLogic for reporting. -- Improved install instructions for Windows. Thanks @alex. - -v16.9.0 -======= - -- Added hocr caption processing. Thanks @0dinD :issue:`1466` -- ocrmypdf-alpine Docker image is now built with Alpine 3.21. -- Fixed error handling of PDFs that contain invalid images with both ImageMask - and ColorSpace defined. :issue:`1453` -- Fixed test suite regression when only older Ghostscripts are installed. -- Improved documetnation of _progressbar.py. Thanks @QuentinFuxa. :issue:`1456` -- Disabling building of documentation as PDF on ReadTheDocs, as this caused - complex build issues deemed not worth solving. - -v16.8.0 -======= - -- Upgraded webservice.py demonstration using streamlit. It's now possible to - exercise most of OCRmyPDF's functionality in a simple web UI. -- Added cache to Dockerfiles to improve build speed. -- Fixed numerous formatting errors in the documentation that prevented some - parts of documentation from generating correctly. -- Improved OCR text rendering by suppressing negative-width spaces. Thanks - @pajowu. :issue:`1446` -- Improved detecting of invisible text when using `--redo-ocr`. Thanks - @pajowu. :issue:`1448`` - -v16.7.0 -======= - -- Fixed further issues with Docker build and updated some versions. -- Main Docker image returned to Ubuntu 24.04 since the fix in v16.6.2 resolved - that concern. -- Code that previously sent Ghostscript output to stdout has been changed to - output to temporary files, since Ghostscript was doing that anyway internally. - This is a modest efficiency improvement. -- Fixed an issue with debug log output being parsed as rich markup. :issue:`1444` - -v16.6.2 -======= - -- Remove invalid hyperlink annotations to satisfy Ghostscript 10.x during PDF/A - conversion. :issue:`1425` - -v16.6.1 -======= - -- Fixed some issues with Docker build, such as removing unnecessary content and using - a stable Tesseract version. -- Reverted Docker image to Ubuntu 22.04 to access older/more stable Ghostscript - for now. -- Clarified batch commands in documentation. -- Fixed an issue with JSON serialization and pickling of HOCRResult. :issue:`1427` - -v16.6.0 -======= - -- Fixed an issue where damaged PDFs would fail with ``--redo-ocr``. :issue:`1403` -- Fixed an error that prevented JBIG2 optimization on Windows if the image - was optimized in an earlier step. :issue:`1396` -- Fixed an error detecting the version of unpaper 7.0.0. :issue:`1409` -- Fixed a performance regression when scanning pages. :issue:`1378`. Thanks @aliemjay. -- Fixed Alpine Docker image by enforcing Alpine 3.19. Alpine 3.20 includes a - defective version of Tesseract OCR and so is not usable. -- Upgraded Ubuntu Docker image to use Ubuntu 24.04. -- Build and test scripts/actions switched to uv. -- When running in a container, we now remind the user that temporary folders - are inside the container and may not be accessible. -- Fixed Linux test coverage matrix, which was missing some key versions. - -v16.5.0 -======= - -- Fixed issue with interpreting PDFs that have images with array masks. - :issue:`1377` -- Enabled testing on Python 3.13. -- Fixed a test that did not work correctly but still passed. :issue:`1382` -- Improved "PDF/A conversion failed" warning message to better describe implications. -- Updated documentation to better explain OCR_JSON_SETTINGS in batch processing. -- Build backend changed from setuptools to hatchling. - -v16.4.3 -======= - -- Work around pdfminer.six issue where a token on the buffer boundary is incorrectly - parsed as two tokens. :issue:`1361` -- New rules are applied to stencil masks and explicit masks when calculating the - optimal page DPI for rendering. :issue:`1362` -- Fixed attempts to use an incompatible jbig2.EXE provided by TeX Live. :issue:`1363` - -v16.4.2 -======= - -- Fixed order of filenames passed to Ghostscript for PDF/A generation. :issue:`1359` -- Suppressed missing jbig2dec warning message. :issue:`1358` -- Fixed calculation of image size when soft mask dimensions don't match image - dimension. :issue:`1351` -- Several fixes to documentation. Thanks to users Iris and JoKalliauer - who contributed these changes. -- Fixed error on processing PDFs that are missing certain image metadata. :issue:`1315` - -v16.4.1 -======= - -- Fixed calculation of image printed area (used in finding weighted DPI for OCR). - :issue:`1334` -- Fixed "NotImplementedError: not sure how to get colorspace" error - messages in logs which simply records a failure to optimize images with - print production colorspaces. :issue:`1315` - -v16.4.0 -======= - -- Selecting the ``osd`` and ``equ`` pseudo-languages with ``-l/--language`` now - exits with an error when using Tesseract OCR, because these are not - regular Tesseract languages but implementation details implemented. - Using them can cause Tesseract to crash. -- The hOCR renderer is more tolerant of extra whitespace in input files. -- watcher.py now changes the output file extension to .pdf when the input is not - .pdf. -- Improved handling of PDFs that contain circularly referenced Form XObjects. - :issue:`1321` -- Fixed Alpine Docker image for ARM64, which was not building correctly. -- Docker images now use pikepdf 9.0.0. -- Prevent use of Tesseract OCR 5.4.0, a version with known regressions. -- Disabled progressbar for "Linearizing" when ``--no-progress-bar`` set. -- Fixed some tests that warn about missing JBIG2 decoding via pikepdf, by - installing the necessary libraries during tests. - -v16.3.1 -======= - -- Fixed a test suite failure with Ghostscript 10.03.0+. :issue:`1316` -- Fixed an issue with the presentation of the "OCR" progress bar. :issue:`1313` - -v16.3.0 -======= - -- Fixed progress bar not displaying for Ghostscript PDF/A conversion. :issue:`1313` -- Added progress bar for linearization. :issue:`1313` -- If `--rotate-pages-threshold` issued without `--rotate-pages` we now exit with - an error since the user likely intended to use `--rotate-pages`. :issue:`1309` -- If Tesseract hOCR gives an invalid line box, print an error message instead of - exiting with an error. :issue:`1312` - -v16.2.0 -======= - -- Fixed issue 'NoneType' object has no attribute 'get' when optimizing certain PDFs. - :issue:`1293,1271` -- Switched formatting from black to ruff. -- Added support for sending sidecar output to io.BytesIO. -- Added support for converting HEIF/HEIC images (the native image of iPhones and - some other devices) to PDFs, when the appropriate pi-hief library is installed. - This library is marked as a dependency, but maintainers may opt out if needed. -- We now default to downsampling large images that would exceed Tesseract's internal - limits, but only if it cause processing to fail. Previously, this behavior only - occurred if specifically requested on command line. It can still be configured - and disabled. See the --tesseract command line options. -- Added Macports install instructions. Thanks @akierig. -- Improved logging output when an unexpected error occurs while trying to obtain - the version of a third party program. - -v16.1.2 -======= - -- Fixed test suite failure when using Ghostscript 10.3. -- Other minor corrections. - -v16.1.1 -======= - -- Fixed PyPy 3.10 support. - -v16.1.0 -======= - -- Improved hOCR renderer is now default for left to right languages. -- Improved handling of rotated pages. Previously, OCR text might be missing for - pages that were rotated with a /Rotate tag on the page entry. -- Improved handling of cropped pages. Previously, in some cases a page with a - crop box would not have its OCR applied correctly and misalignment between - OCR text and visible text coudl occur. -- Documentation improvements, especially installation instructions for less - common platforms. - -v16.0.4 -======= - -- Fixed some issues for left-to-right text with the new hOCR renderer. It is still - not default yet but will be made so soon. Right-to-left text is still in progress. -- Added an error to prevent use of several versions of Ghostscript that seem - corrupt existing text in input PDFs. Newly generated OCR is not affected. - For best results, use Ghostscript 10.02.1 or newer, which contains the fix - for the issue. - -v16.0.3 -======= - -- Changed minimum required Ghostscript to 9.54, to support users of RHEL 9 and its - derivatives, since that is the latest version available there. -- Removed warning message about CVE-2023-43115, on the assumption that most - distributions have backported the patch by now. - -v16.0.2 -======= - -- Temporarily changed PDF text renderer back to sandwich by default to address - regressions in macOS Preview. - -v16.0.1 -======= - -- Fixed text rendering issue with new hOCR text renderer - extraneous byte order - marks. -- Tightened dependencies. - -v16.0.0 -======= - -- Added OCR text renderer, combined the best ideas of Tesseract's PDF - generator and the older hOCR transformer renderer. The result is a hopefully - permanent fix for wordssmushedtogetherwithoutspaces issues in extracted text, - better registration/position of text on skewed baselines :issue:`1009`, - fixes to character output when the German Fraktur script is used :issue:`1191`, - proper rendering of right to left languages (Arabic, Hebrew, Persian) :issue:`1157`. - Asian languages may still have excessive word breaks compared to expectations. - The new renderer is the default; the old sandwich renderer is still available - using ``--pdf-renderer sandwich``; the old hOCR renderer is no more. -- The ``ocrmypdf.hocrtransform`` API has changed substantially. -- Support for Python 3.9 has been dropped. Python 3.10+ is now required. -- pikepdf >= 8.8.0 is now required. - - -v15.4.4 -======= - -- Fixed documentation for installing Ghostscript on Windows. :issue:`1198` -- Added warning message about security issue in older versions of Ghostscript. - -v15.4.3 -======= - -- Fixed deprecation warning in pikepdf older than 8.7.1; pikepdf >= 8.7.1 is - now required. - -v15.4.2 -======= - -- We now raise an exception on a certain class of PDFs that likely need an - explicit color conversion strategy selected to display correctly - for PDF/A conversion. -- Fixed an error that occurred while trying to write a log message after the - debug log handler was removed. - -v15.4.1 -======= - -- Fixed misc/watcher.py regressions: accept ``--ocr-json-settings`` as either - filename or JSON string, as previously; and argument count mismatch. - :issue:`1183,1185` -- We no longer attempt to set /ProcSet in the PDF output, since this is an - obsolete PDF feature. -- Documentation improvements. - -v15.4.0 -======= - -- Added new experimental APIs to support offline editing of the final text. - Specifically, one can now generate hOCR files with OCRmyPDF, edit them with - some other tool, and then finalize the PDF. They are experimental and - subject to change, including details of how the working folder is used. - There is no command line interface. -- Code reorganization: executors, progress bars, initialization and setup. -- Fixed test coverage in cases where the coverage tool did not properly trace - into threads or subprocesses. This code was still being tested but appeared - as not covered. -- In the test suite, reduced use of subprocesses and other techniques that - interfere with coverage measurement. -- Improved error check for when we appear to be running inside a snap container - and files are not available. -- Plugin specification now properly defines progress bars as a protocol rather - than defining them as "tqdm-like". -- We now default to using "forkserver" process creation on POSIX platforms - rather than fork, since this is method is more robust and avoids some - issues when threads are present. -- Fixed an instance where the user's request to ``--no-use-threads`` was ignored. -- If a PDF does not have language metadata on its top level object, we add - the OCR language. -- Replace some cryptic test error messages with more helpful ones. -- Debug messages for how OCRmyPDF picks the colorspace for a page are now - more descriptive. - -v15.3.1 -======= - -- Fixed an issue with logging settings for misc/watcher.py introduced in the - previous release. :issue:`1180` -- We now attempt to preserve the input's extended attributes when creating - the output file. -- For some reason, the macOS build now needs OpenSSL explicitly installed. -- Updated documentation on Docker performance concerns. - -v15.3.0 -======= - -- Update misc/watcher.py to improve command line interface using Typer, and - support ``.env`` specification of environment variables. Improved error - messages. Thanks to @mflagg2814 for the PR that prompted this improvement. -- Improved error message when a file cannot be read because we are running in - a snap container. - -v15.2.0 -======= - -- Added a Docker image based on Alpine Linux. This image is smaller than the - Ubuntu-based image and may be useful in some situations. Currently hosted at - jbarlow83/ocrmypdf-alpine. Currently not available in ARM flavor. -- The Ubuntu Docker is now aliased to jbarlow83/ocrmypdf-ubuntu. -- Updated Docker documentation. - -v15.1.0 -======= - -- We now require Pillow 10.0.1, due a serious security vulnerability in all earlier - versions of that dependency. The vulnerability concerns WebP images and could - be triggered in OCRmyPDF when creating a PDF from a malicious WebP image. -- Added some keyword arguments to ``ocrmypdf.ocr`` that were previously accepted - but undocumented. -- Documentation updates and typing improvements. - -v15.0.2 -======= - -- Added Python 3.12 to test matrix. -- Updated documentation for notes on Python 3.12, 32-bit support and some new - features in v15. - -v15.0.1 -======= - -- Wheels Python tag changed to py39. -- Marked as a expected fail a test that fails on recent Ghostscript versions. -- Clarified documentation and release notes around the extent of 32-bit support. -- Updated installation documentation to changes in v15. - -v15.0.0 -======= - -- Dropped support for Python 3.8. -- Dropped support some older dependencies, specifically ``coloredlogs`` and - ``tqdm`` in favor of rich - see ``pyproject.toml`` for details. - Generally speaking, Ubuntu 22.04 is our new baseline system. -- Tightened version requirements for some dependencies. -- Dropped support for 32-bit Linux wheels. We strongly recommend a 64-bit operating - system, and 64-bit versions of Python, Tesseract and Ghostscript to use OCRmyPDF. - Many of our dependencies are dropping 32-bit builds (e.g. Pillow), and we are - following suit. (Maintainers may still build 32-bit versions from source.) -- Changed to trusted release for PyPI publishing. -- pikepdf memory mapping is enabled again for improved performance, now that an - issue with feature in pikepdf is fixed. -- ``ocrmypdf.helpers.calculate_downsample`` previously had two variants, one - that took a ``PIL.Image`` and one that took a ``tuple[int, int]``. The latter - was removed. -- The snap version of ocrmypdf is now based on Ubuntu core22. -- We now account for situations where a small portion of an image on a page is drawn - at high DPI (resolution). Previously, the entire page would be rasterized at the - highest resolution of any feature, which caused performance problems. Now, - the page is rasterized - at a resolution based on the average DPI of the page, weighted by the area that - each feature occupies. Typically, small areas of high resolution in PDFs are - errors or quirks from the repeated use of assets and high resolution is not - beneficial. :issue:`1010,1104,1004,1079,1010` -- Ghostscript color conversion strategy is now configurable using - ``--color-conversion-strategy``. :issue:`1143` -- JBIG2 threshold for optimization is now configurable using - ``--jbig2-threshold``. :issue:`1133` - -v14.4.0 -======= - -- Digitally signed PDFs are now detected. If the PDF is signed, OCRmyPDF will - refuse to modify it. Previously, only encrypted PDFs were detected, not - those that were signed but not encrypted. :issue:`1040` -- In addition, ``--invalidate-digital-signatures`` can be used to override the - above behavior and modify the PDF anyway. :issue:`1040` -- tqdm progress bars replaced with "rich" progress bars. The rich library is - a new dependency. Certain APIs that used tqdm are now deprecated and will - be removed in the next major release. -- Improved integration with GitHub Releases. Thanks to @stumpylog. - -v14.3.0 -======= - -- Renamed master branch to main. -- Improve PDF rasterization accuracy by using the ``-dPDFSTOPONERROR`` option - to Ghostscript. Use ``--continue-on-soft-render-error`` if you want to render - the PDF anyway. The plugin specification was adjusted to support this feature; - plugin authors may want to adapt PDF rasterizing and rendering - plugins. :issue:`1083` -- The calculated deskew angle is now recorded in the logged output. :issue:`1101` -- Metadata can now be unset by setting a metadata type such as ``--title`` to an - empty string. :issue:`1117,1059` -- Fixed random order of languages due to use of a set. This may have caused output - to vary when multiple languages were set for OCR. :issue:`1113` -- Clarified the optimization ratio reported in the log output. -- Documentation improvements. - -v14.2.1 -======= - -- Fixed :issue:`977`, where images inside Form XObjects were always excluded - from image optimization. - -v14.2.0 -======= - -- Added ``--tesseract-downsample-above`` to downsample larger images even when - they do not exceed Tesseract's internal limits. This can be used to speed - up OCR, possibly sacrificing accuracy. -- Fixed resampling AttributeError on older Pillow. :issue:`1096` -- Removed an error about using Ghostscript on PDFs with that have the /UserUnit - feature in use. Previously, Ghostscript would fail to process these PDFs, - but in all supported versions it is now supported, so the error is no longer - needed. -- Improved documentation around installing other language packs for Tesseract. - -v14.1.0 -======= - -- Added ``--tesseract-non-ocr-timeout``. This allows using Tesseract's deskew - and other non-OCR features while disabling OCR using ``--tesseract-timeout 0``. -- Added ``--tesseract-downsample-large-images``. This downsamples larges images - that exceed the maximum image size Tesseract can handle. Large images may still - take a long time to process, but this allows them to be processed if that - is desired. -- Fixed :issue:`1082`, an issue with snap packaged building. -- Change linter to ruff, fix lint errors, update documentation. - -v14.0.4 -======= - -- Fixed :issue:`1066, 1075`, an exception when processing certain malformed PDFs. - -v14.0.3 -======= - -- Fixed :issue:`1068`, avoid deleting /dev/null when running as root. -- Other documentation fixes. - -v14.0.2 -======= - -- Fixed :issue:`1052`, an exception on attempting to process certain nonconforming PDFs. -- Explicitly documented that Windows 32-bit is no longer supported. -- Fixed source installation instructions. -- Other documentation fixes. - -v14.0.1 -======= - -- Fixed some version checks done with smart version comparison. -- Added missing jbig2dec to Docker image. - -v14.0.0 -======= - -- Dropped support for Python 3.7. -- Dropped support generally speaking, all dependencies older than what Ubuntu 20.04 - provides. -- Ghostscript 9.50 or newer is now required. Shims to support old versions were - removed. -- Tesseract 4.1.1 or newer is now required. Shims to support old versions were - removed. -- Docker image now uses Tesseract 5. -- Dropped setup.cfg configuration for pyproject.toml. -- Removed deprecation exception PdfMergeFailedError. -- A few more public domain test files were removed or replaced. We are aiming for - 100% compliance with SPDX and generally towards simplifying copyright. - -v13.7.0 -======= - -- Fixed an exception when attempting to run and Tesseract is not installed. -- Changed to SPDX license tracking and information files. - -v13.6.2 -======= - -- Added a shim to prevent an "error during error handling" for Python 3.7 and 3.8. -- Modernized some type annotations. -- Improved annotations on our _windows module to help IDEs and mypy figure out what - we're doing. - -v13.6.1 -======= - -- Require setuptools-scm 7.0.5 to avoid possible issues with source distributions in - earlier versions of setuptools-scm. -- Suppress a spurious warning, improve tests, improve typing and other miscellany. - -v13.6.0 -======= - -- Added a new ``initialize`` plugin hook, making it possible to suppress built-in - plugins more easily, among other possibilities. -- Fixed an issue where unpaper would exit with a "wrong stream" error, probably - related to images with an odd integer width. :issue:`887, 665` - -v13.5.0 -======= - -- Added a new ``optimize_pdf`` plugin hook, making it possible to create plugins that - replace or enhance OCRmyPDF's PDF optimizer. -- Removed all max version restrictions. Our new policy is to blacklist known-bad releases - and only block known-bad versions of dependencies. -- The naming schema for object that holds all OCR text that OCRmyPDF inserts has - changed. This has always been an implementation detail (and remains so), but possibly, - someone was relying on it and would appreciate the heads-up. -- Cleanup. - -v13.4.7 -======= - -- Fixed PermissionError when cleaning up temporary files in rare cases. :issue:`974` -- Fixed PermissionError when calling ``os.nice`` on platforms that lack it. :issue:`973` -- Suppressed some warnings from libxmp during tests. - -v13.4.6 -======= - -- Convert error on corrupt ICC profiles into a warning. Thanks to @oscherler. - -v13.4.5 -======= - -- Remove upper bound on pdfminer.six version. -- Documentation. - -v13.4.4 -======= - -- Updated pdfminer.six version. -- Docker image changed to Ubuntu 22.04 now that it is released and provides the - dependencies we need. This seems more consistent than our recent change to - Debian. - -v13.4.3 -======= - -- Fix error on pytest.skip() with older versions of pytest. -- Documentation updates. - -v13.4.2 -======= - -- Worked around a - `major regression in Ghostscript 9.56.0 `__ - where **all OCR text is stripped out of the PDF**. It simply removes all text, - even generated by software other than OCRmyPDF. Fortunately, we can ask - Ghostscript 9.56.0 to use its old behavior that worked correctly for our purposes. - Users must avoid the combination (Ghostscript 9.56.0, ocrmypdf <13.4.2) since - older versions of OCRmyPDF have no way of detecting that this particular - version of Ghostscript removes all OCR text. -- Marked pdfminer 20220319 as supported. -- Fixed some deprecation warnings from recent versions of Pillow and pytest. -- Test suite now covers Python 3.10 (Python 3.10 worked fine before, but was not - being tested). -- Docker image now uses debian:bookworm-slim as the base image to fix the Docker - image build. - -v13.4.1 -======= - -- Temporarily make threads rather than processes the default executor worker, due - to a persistent deadlock issue when processes are used. Add a new command line - argument ``--no-use-threads`` to disable this. - -v13.4.0 -======= - -- Fixed test failures when using pikepdf 5.0.0. -- Various improvements to the optimizer. In particular, we now recognize PDF images - that are encoded with both deflate (PNG) and DCT (JPEG), and also produce PDF - with images compressed with deflate and DCT, since this often yields file size - improvements compared to plain DCT. - -v13.3.0 -======= - -- Made a harmless but "scary" exception after failing to optimize an image less scary. -- Added a warning if a page image is too large for unpaper to clean. The image is - passed through without cleaning. This is due to a hard-coded limitation in a - C library used by unpaper so it cannot be rectified easily. -- We now use better default settings when calling img2pdf. -- We no longer try to optimize images that we failed to save in certain situations. -- We now account for some differences in text output from Tesseract 5 compared to - Tesseract 4. -- Better handling of Ghostscript producing empty images when attempting to rasterize - page images. - -v13.2.0 -======= - -- Removed all runtime uses of distutils since it is deprecated in standard library. We - previous used ``distutils.version`` to examine version numbers of dependencies - at run time, and now use ``packaging.version`` for this. This is a new - dependency. -- Fixed an error message advising the user that Ghostscript was not installed being - suppressed when this condition actually happens. -- Fixed an issue with incorrect page number and totals being displayed in the progress - bar. This was purely a display/presentation issue. :issue:`876`. - -v13.1.1 -======= - -- Fixed issue with attempting to deskew a blank page on Tesseract 5. :issue:`868`. - -v13.1.0 -======= - -- Changed to using Python concurrent.futures-based parallel execution instead of - pools, since futures have now exceed pools in features. -- If a child worker is terminated (perhaps by the operating system or the user - killing it in a task manager), the parallel task will fail an error message. - Previously, the main ocrmypdf process would "hang" indefinitely, waiting for the - child to report. -- Added new argument ``--tesseract-thresholding`` to provide control over Tesseract 5's - threshold parameter. -- Documentation updates and changes. Better documentation for ``--output-type none``, - added a few releases ago. Removed some obsolete documentation. -- Improved bash completions - thanks to @FPille. - -v13.0.0 -======= - -**Breaking changes** - -- The deprecated module ``ocrmypdf.leptonica`` has been removed. -- We no longer depend on Leptonica (``liblept``) or CFFI (``libffi``, - ``python3-cffi``). (Note that Tesseract still requires Leptonica; OCRmyPDF no longer - directly uses this library.) -- The argument ``--remove-background`` is temporarily disabled while we search for an - alternative to the Leptonica implementation of this feature. -- The ``--threshold`` argument has been removed, since this also depended on Leptonica. - Tesseract 5.x has implemented improvements to thresholding, so this feature will be - redundant anyway. -- ``--deskew`` was previous calculated by a Leptonica algorithm. We now use a feature - of Tesseract to find the appropriate the angle to deskew a page. The deskew angle - according to Tesseract may differ from Leptonica's algorithm. At least in theory, - Tesseract's deskew angle is informed by a more complex analysis than Leptonica, - so this should improve results in general. We also use Pillow to perform the - deskewing, which may affect the appearance of the image compared to Leptonica. -- Support for Python 3.6 was dropped, since this release is approaching end of life. -- We now require pikepdf 4.0 or newer. This, in turn, means that OCRmyPDF requires - a system compatible with the manylinux2014 specification. This change was "forced" - by Pillow not releasing manylinux2010 wheels anymore. -- We no longer provide requirements.txt-style files. Use ``pip install ocrmypdf[...]`` - instead. -- Bumped required versions of several libraries. - -**Fixes** - -- Fixed an issue where OCRmyPDF failed to find Ghostscript on Windows even when - installed, and would exit with an error. -- By removing Leptonica, we fixed all issues related to Leptonica on Apple - Silicon or Leptonica failing to import on Windows. - -v12.7.2 -======= - -- Fixed "invalid version number" error for Tesseract packaging with nonstandard - version "5.0.0-rc1.20211030". -- Fixed use of deprecated ``importlib.resources.read_binary``. -- Replace some uses of string paths with ``pathlib.Path``. -- Fixed a leaked file handle when using ``--output-type none``. -- Removed shims to support versions of pikepdf that are no longer supported. - -v12.7.1 -======= - -- Declare support for pdfminer.six v20211012. - -v12.7.0 -======= - -- Fixed test suite failure when using pikepdf 3.2.0 that was compiled with pybind11 - 2.8.0. :issue:`843` -- Improve advice to user about using ``--max-image-mpixels`` if OCR fails for this - reason. -- Minor documentation fixes. (Thanks to @mara004.) -- Don't require importlib-metadata and importlib-resources backports on versions of - Python where the standard library implementation is sufficient. - (Thanks to Marco Genasci.) - -v12.6.0 -======= - -- Implemented ``--output-type=none`` to skip producing PDFs for applications that - only want sidecar files (:issue:`787`). -- Fixed ambiguities in descriptions of behavior of ``--jbig2-lossy``. -- Various improvements to documentation. - -v12.5.0 -======= - -- Fixed build failure for the combination of PyPy 3.6 and pikepdf 3.0. This - combination can work in a source build but does not work with wheels. -- Accepted bot that wanted to upgrade our deprecated requirements.txt. -- Documentation updates. -- Replace pkg_resources and install dependency on setuptools with - importlib-metadata and importlib-resources. -- Fixed regression in hocrtransform causing text to be omitted when this - renderer was used. -- Fixed some typing errors. - -v12.4.0 -======= - -- When grafting text layers, use pikepdf's ``unparse_content_stream`` if available. -- Confirmed support for pluggy 1.0. (Thanks @QuLogic.) -- Fixed some typing issues, improved pre-commit settings, and fixed issues - flagged by linters. -- PyPy 7.3.3 (=Python 3.6) is now supported. Note that PyPy does not necessarily - run faster, because the vast majority of OCRmyPDF's execution time is spent - running OCR or generally executing native code. However, PyPy may bring speed - improvements in some areas. - -v12.3.3 -======= - -- watcher.py: fixed interpretation of boolean env vars (:issue:`821`). -- Adjust CI scripts to test Tesseract 5 betas. -- Document our support for the Tesseract 5 betas. - -v12.3.2 -======= - -- Indicate support for flask 2.x, watcher 2.x (:issue:`815, 816`). - -v12.3.1 -======= - -- Fixed issue with selection of text when using the hOCR renderer (:issue:`813`). -- Fixed build errors with the Docker image by upgrading to a newer Ubuntu. - Also set the timezone of this image to UTC. - -v12.3.0 -======= - -- Fixed a regression introduced in Pillow 8.3.0. Pillow no longer rounds DPI - for image resolutions. We now account for this (:issue:`802`). -- We no longer use some API calls that are deprecated in the latest versions of - pikepdf. -- Improved error message when a language is requested that doesn't look like a - typical ISO 639-2 code. -- Fixed some tests that attempted to symlink on Windows, breaking tests on a - Windows desktop but not usually on CI. -- Documentation fixes (thanks to @mara004) - -v12.2.0 -======= - -- Fixed invalid Tesseract version number on Windows (:issue:`795`). -- Documentation tweaks. Documentation build now depends on sphinx-issues package. - -v12.1.0 -======= - -- For security reasons we now require Pillow >= 8.2.x. (Older versions will continue - to work if upgrading is not an option.) -- The build system was reorganized to rely on ``setup.cfg`` instead of ``setup.py``. - All changes should work with previously supported versions of setuptools. -- The files in ``requirements/*`` are now considered deprecated but will be retained for v12. - Instead use ``pip install ocrmypdf[test]`` instead of ``requirements/test.txt``, etc. - These files will be removed in v13. - -v12.0.3 -======= - -- Expand the list of languages supported by the hocr PDF renderer. - Several languages were previously considered not supported, particularly those - non-European languages that use the Latin alphabet. -- Fixed a case where the exception stack trace was suppressed in verbose mode. -- Improved documentation around commercial OCR. - -v12.0.2 -======= - -- Fixed exception thrown when using ``--remove-background`` on files containing small - images (:issue:`769`). -- Improve documentation for description of adding language packs to the Docker image - and corrected name of French language pack. - -v12.0.1 -======= - -- Fixed "invalid version number" for untagged tesseract versions (:issue:`770`). - -v12.0.0 -======= - -**Breaking changes** - -- Due to recent security issues in pikepdf, Pillow and reportlab, we now require - newer versions of these libraries and some of their dependencies. (If necessary, - package maintainers may override these versions at their discretion; lower - versions will often work.) -- We now use the "LeaveColorUnchanged" color conversion strategy when directing - Ghostscript to create a PDF/A. Generally this is faster than performing a - color conversion, which is not always necessary. -- OCR text is now packaged in a Form XObject. This makes it easier to isolate - OCR from other document content. However, some poorly implemented PDF text - extraction algorithms may fail to detect the text. -- Many API functions have stricter parameter checking or expect keyword arguments - were they previously did not. -- Some deprecated functions in ``ocrmypdf.optimize`` were removed. -- The ``ocrmypdf.leptonica`` module is now deprecated, due to difficulties with - the current strategy of ABI binding on newer platforms like Apple Silicon. - It will be removed and replaced, either by repackaging Leptonica as an - independent library using or using a different image processing library. -- Continuous integration moved to GitHub Actions. -- We no longer depend on ``pytest_helpers_namespace`` for testing. - -**New features** - -- New plugin hook: ``get_progressbar_class``, for progress reporting, - allowing developers to replace the standard console progress bar with some - other mechanism, such as updating a GUI progress bar. -- New plugin hook: ``get_executor``, for replacing the concurrency model. - This is primarily to support execution on AWS Lambda, which does not support - standard Python ``multiprocessing`` due to its lack of shared memory. -- New plugin hook: ``get_logging_console``, for replacing the standard - way OCRmyPDF outputs its messages. -- New plugin hook: ``filter_pdf_page``, for modifying individual PDF - pages produced by OCRmyPDF. -- OCRmyPDF now runs on nonstandard execution environments that do not have - interprocess semaphores, such as AWS Lambda and Android Termux. If the environment - does not have semaphores, OCRmyPDF will automatically select an alternate - process executor that does not use semaphores. -- Continuous integration moved to GitHub Actions. -- We now generate an ARM64-compatible Docker image alongside the x64 image. - Thanks to @andkrause for doing most of the work in a pull request several months - ago, which we were finally able to integrate now. Also thanks to @0x326 for - review comments. - -**Fixes** - -- Fixed a possible deadlock on attempting to flush ``sys.stderr`` when older - versions of Leptonica are in use. -- Some worker processes inherited resources from their parents such as log - handlers that may have also lead to deadlocks. These resources are now released. -- Improvements to test coverage. -- Removed vestiges of support for Tesseract versions older than 4.0.0-beta1 ( - which ships with Ubuntu 18.04). -- OCRmyPDF can now parse all of Tesseract version numbers, since several - schemes have been in use. -- Fixed an issue with parsing PDFs that contain images drawn at a scale of 0. (:issue:`761`) -- Removed a frequently repeated message about disabling mmap. - -v11.7.3 -======= - -- Exclude CCITT Group 3 images from being optimized. Some libraries - OCRmyPDF uses do not seem to handle this obscure compression format properly. - You may get errors or possible corrupted output images without this fix. - -v11.7.2 -======= - -- Updated pinned versions in main.txt, primarily to upgrade Pillow to 8.1.2, due - to recently disclosed security vulnerabilities in that software. -- The ``--sidecar`` parameter now causes an exception if set to the same file as - the input or output PDF. - -v11.7.1 -======= - -- Some exceptions while attempting image optimization were only logged at the debug - level, causing them to be suppressed. These errors are now logged appropriately. -- Improved the error message related to ``--unpaper-args``. -- Updated documentation to mention the new conda distribution. - -v11.7.0 -======= - -- We now support using ``--sidecar`` in conjunction with ``--pages``; these arguments - used to be mutually exclusive. (:issue:`735`) -- Fixed a possible issue with PDF/A-1b generation. Acrobat complained that our PDFs use - object streams. More robust PDF/A validators like veraPDF don't consider this a - problem, but we'll honor Acrobat's objection from here on. This may increase file - size of PDF/A-1b files. PDF/A-2b files will not be affected. - -v11.6.2 -======= - -- Fixed a regression where the wrong page orientation would be produced when using - arguments such as ``--deskew --rotate-pages`` (:issue:`730`). - -v11.6.1 -======= - -- Fixed an issue with attempting optimize unusually narrow-width images by excluding - these images from optimization (:issue:`732`). -- Remove an obsolete compatibility shim for a version of pikepdf that is no longer - supported. - -v11.6.0 -======= - -- OCRmyPDF will now automatically register plugins from the same virtual environment - with an appropriate setuptools entrypoint. -- Refactor the plugin manager to remove unnecessary complications and make plugin - registration more automatic. -- ``PageContext`` and ``PdfContext`` are now formally part of the API, as they - should have been, since they were part of ``ocrmypdf.pluginspec``. - -v11.5.0 -======= - -- Fixed an issue where the output page size might differ by a fractional amount - due to rounding, when ``--force-ocr`` was used and the page contained objects - with multiple resolutions. -- When determining the resolution at which to rasterize a page, we now consider - printed text on the page as requiring a higher resolution. This fixes issues - with certain pages being rendered with unacceptably low resolution text, but - may increase output file sizes in some workflows where low resolution text - is acceptable. -- Added a workaround to fix an exception that occurs when trying to - ``import ocrmypdf.leptonica`` on Apple ARM silicon (or potentially, other - platforms that do not permit write+executable memory). - -v11.4.5 -======= - -- Fixed an issue where files may not be closed when the API is used. -- Improved ``setup.cfg`` with better settings for test coverage. - -v11.4.4 -======= - -- Fixed ``AttributeError: 'NoneType' object has no attribute 'userunit'`` (:issue:`700`), - related to OCRmyPDF not properly forwarded an error message from pdfminer.six. -- Adjusted typing of some arguments. -- ``ocrmypdf.ocr`` now takes a ``threading.Lock`` for reasons outlined in the - documentation. - -v11.4.3 -======= - -- Removed a redundant debug message. -- Test suite now asserts that most patched functions are called when they should be. -- Test suite now skips a test that fails on two particular versions of piekpdf. - -v11.4.2 -======= - -- Fixed support for Cygwin, hopefully. -- watcher.py: Fixed an issue with the OCR_LOGLEVEL not being interpreted. - -v11.4.1 -======= - -- Fixed an issue where invalid pages ranges passed using the ``pages`` argument, - such as "1-0" would cause unhandled exceptions. -- Accepted a user-contributed to the Synology demo script in misc/synology.py. -- Clarified documentation about change of temporary file location ``ocrmypdf.io``. -- Fixed Python wheel tag which was incorrectly set to py35 even though we long - since dropped support for Python 3.5. - -v11.4.0 -======= - -- When looking for Tesseract and Ghostscript, we now check the Windows Registry to - see if their installers registered the location of their executables. This should - help Windows users who have installed these programs to non-standard - locations. -- We now report on the progress of PDF/A conversion, since this operation is - sometimes slow. -- Improved command line completions. -- The prefix of the temporary folder OCRmyPDF creates has been changed from - ``com.github.ocrmypdf`` to ``ocrmypdf.io``. Scripts that chose to depend on this - prefix may need to be adjusted. (This has always been an implementation detail so is - not considered part of the semantic versioning "contract".) -- Fixed :issue:`692`, where a particular file with malformed fonts would flood an - internal message cue by generating so many debug messages. -- Fixed an exception on processing hOCR files with no page record. Tesseract - is not known to generate such files. - -v11.3.4 -======= - -- Fixed an error message 'called readLinearizationData for file that is not - linearized' that may occur when pikepdf 2.1.0 is used. (Upgrading to pikepdf - 2.1.1 also fixes the issue.) -- File watcher now automatically includes ``.PDF`` in addition to ``.pdf`` to - better support case sensitive file systems. -- Some documentation and comment improvements. - -v11.3.3 -======= - -- If unpaper outputs non-UTF-8 data, quietly fix this rather than choke on the - conversion. (Possibly addresses :issue:`671`.) - -v11.3.2 -======= - -- Explicitly require pikepdf 2.0.0 or newer when running on Python 3.9. (There are - concerns about the stability of pybind11 2.5.x with Python 3.9, which is used in - pikepdf 1.x.) -- Fixed another issue related to page rotation. -- Fixed an issue where image marked as image masks were not properly considered - as optimization candidates. -- On some systems, unpaper seems to be unable to process the PNGs we offer it - as input. We now convert the input to PNM format, which unpaper always accepts. - Fixes :issue:`665` and :issue:`667`. -- DPI sent to unpaper is now rounded to a more reasonable number of decimal digits. -- Debug and error messages from unpaper were being suppressed. -- Some documentation tweaks. - -v11.3.1 -======= - -- Declare support for new versions: pdfminer.six 20201018 and pikepdf 2.x -- Fixed warning related to ``--pdfa-image-compression`` that appears at the wrong - time. - -v11.3.0 -======= - -- The "OCR" step is describing as "Image processing" in the output messages when - OCR is disabled, to better explain the application's behavior. -- Debug logs are now only created when run as a command line, and not when OCR - is performed for an API call. It is the calling application's responsibility - to set up logging. -- For PDFs with a low number of pages, we gathered information about the input PDF - in a thread rather than process (when there are more pages). When run as a - thread, we did not close the file handle to the working PDF, leaking one file - handle per call of ``ocrmypdf.ocr``. -- Fixed an issue where debug messages send by child worker processes did not match - the log settings of parent process, causing messages to be dropped. This affected - macOS and Windows only where the parent process is not forked. -- Fixed the hookspec of rasterize_pdf_page to remove default parameters that - were not handled in an expected way by pluggy. -- Fixed another issue with automatic page rotation (:issue:`658`) due to the issue above. - -v11.2.1 -======= - -- Fixed an issue where optimization of a 1-bit image with a color palette or - associated ICC that was optimized to JBIG2 could have its colors inverted. - -v11.2.0 -======= - -- Fixed an issue with optimizing PNG-type images that had soft masks or image masks. - This is a regression introduced in (or about) v11.1.0. -- Improved type checking of the ``plugins`` parameter for the ``ocrmypdf.ocr`` - API call. - -v11.1.2 -======= - -- Fixed hOCR renderer writing the text in roughly reverse order. This should not - affect reasonably smart PDF readers that properly locate the position of all - text, but may confuse those that rely on the order of objects in the content - stream. (:issue:`642`) - -v11.1.1 -======= - -- We now avoid using named temporary files when using pngquant allowing containerized - pngquant installs to be used. -- Clarified an error message. -- Highest number of 1's in a release ever! - -v11.1.0 -======= - -- Fixed page rotation issues: :issue:`634,589`. -- Fixed some cases where optimization created an invalid image such as a - 1-bit "RGB" image: :issue:`629,620`. -- Page numbers are now displayed in debug logs when pages are being grafted. -- ocrmypdf.optimize.rewrite_png and ocrmypdf.optimize.rewrite_png_as_g4 were - marked deprecated. Strictly speaking these should have been internal APIs, - but they were never hidden. -- As a precaution, pikepdf mmap-based file access has been disabled due to a - rare race condition that causes a crash when certain objects are deallocated. - The problem is likely in pikepdf's dependency pybind11. -- Extended the example plugin to demonstrate conversion to mono. - -v11.0.2 -======= - -- Fixed :issue:`612`, TypeError exception. Fixed by eliminating unnecessary repair of - input PDF metadata in memory. - -v11.0.1 -======= - -- Blacklist pdfminer.six 20200720, which has a regression fixed in 20200726. -- Approve img2pdf 0.4 as it passes tests. -- Clarify that the GPL-3 portion of pdfa.py was removed with the changes in v11.0.0; - the debian/copyright file did not properly annotate this change. - -v11.0.0 -======= - -- Project license changed to Mozilla Public License 2.0. Some miscellaneous - code is now under MIT license and non-code content/media remains under - CC-BY-SA 4.0. License changed with approval of all people who were found - to have contributed to GPLv3 licensed sections of the project. (:issue:`600`) -- Because the license changed, this is being treated as a major version number - change; however, there are no known breaking changes in functional behavior - or API compared to v10.x. - -v10.3.3 -======= - -- Fixed a "KeyError: 'dpi'" error message when using ``--threshold`` on an image. - (:issue:`607`) - -v10.3.2 -======= - -- Fixed a case where we reported "no reason" for a file size increase, when we - could determine the reason. -- Enabled support for pdfminer.six 20200726. - -v10.3.1 -======= - -- Fixed a number of test suite failures with pdfminer.six older than version 20200402. -- Enabled support for pdfminer.six 20200720. - -v10.3.0 -======= - -- Fixed an issue where we would consider images that were already JBIG2-encoded - for optimization, potentially producing a less optimized image than the original. - We do not believe this issue would ever cause an image to loss fidelity. -- Where available, pikepdf memory mapping is now used. This improves performance. -- When Leptonica 1.79+ is installed, use its new error handling API to avoid - a "messy" redirection of stderr which was necessary to capture its error - messages. -- For older versions of Leptonica, added a new thread level lock. This fixes a - possible race condition in handling error conditions in Leptonica (although - there is no evidence it ever caused issues in practice). -- Documentation improvements and more type hinting. - -v10.2.1 -======= - -- Disabled calculation of text box order with pdfminer. We never needed this result - and it is expensive to calculate on files with complex pre-existing text. -- Fixed plugin manager to accept ``Path(plugin)`` as a path to a plugin. -- Fixed some typing errors. -- Documentation improvements. - -v10.2.0 -======= - -- Update Docker image to use Ubuntu 20.04. -- Fixed issue PDF/A acquires title "Untitled" after conversion. (:issue:`582`) -- Fixed a problem where, when using ``--pdf-renderer hocr``, some text would - be missing from the output when using a more recent version of Tesseract. - Tesseract began adding more detailed markup about the semantics of text - that our HOCR transform did not recognize, so it ignored them. This option is - not the default. If necessary ``--redo-ocr`` also redoing OCR to fix such issues. -- Fixed an error in Python 3.9 beta, due to removal of deprecated - ``Element.getchildren()``. (:issue:`584`) -- Implemented support using the API with ``BytesIO`` and other file stream objects. - (:issue:`545`) - -v10.1.1 -======= - -- Fixed ``OMP_THREAD_LIMIT`` set to invalid value error messages on some input - files. (The error was harmless, apart from less than optimal performance in - some cases.) - -v10.1.0 -======= - -- Previously, we ``--clean-final`` would cause an unpaper-cleaned page image to - be produced twice, which was necessary in some cases but not in general. We - now take this optimization opportunity and reuse the image if possible. -- We now provide PNG files as input to unpaper, since it accepts them, instead - of generating PPM files which can be very large. This can improve performance - and temporary disk usage. -- Documentation updated for plugins. - -v10.0.1 -======= - -- Fixed regression when ``-l lang1+lang2`` is used from command line. - -v10.0.0 -======= - -**Breaking changes** - -- Support for pdfminer.six version 20181108 has been dropped, along with a - monkeypatch that made this version work. -- Output messages are now displayed in color (when supported by the terminal) - and prefixes describing the severity of the message are removed. As such - programs that parse OCRmyPDF's log message will need to be revised. (Please - consider using OCRmyPDF as a library instead.) -- The minimum version for certain dependencies has increased. -- Many API changes; see developer changes. -- The Python libraries pluggy and coloredlogs are now required. - -**New features and improvements** - -- PDF page scanning is now parallelized across CPUs, speeding up this phase - dramatically for files with a high page counts. -- PDF page scanning is optimized, addressing some performance regressions. -- PDF page scanning is no longer run on pages that are not selected when the - ``--pages`` argument is used. -- PDF page scanning is now independent of Ghostscript, ending our past reliance - on this occasionally unstable feature in Ghostscript. -- A plugin architecture has been added, currently allowing one to more easily - use a different OCR engine or PDF renderer from Tesseract and Ghostscript, - respectively. A plugin can also override some decisions, such changing - the OCR settings after initial scanning. -- Colored log messages. - -**Developer changes** - -- The test spoofing mechanism, used to test correct handling of failures in - Tesseract and Ghostscript, has been removed in favor of using plugins for - testing. The spoofing mechanism was fairly complex and required many special - hacks for Windows. -- Code describing the resolution in DPI of images was refactored into a - ``ocrmypdf.helpers.Resolution`` class. -- The module ``ocrmypdf._exec`` is now private to OCRmyPDF. -- The ``ocrmypdf.hocrtransform`` module has been updated to follow PEP8 naming - conventions. -- Ghostscript is no longer used for finding the location of text in PDFs, and - APIs related to this feature have been removed. -- Lots of internal reorganization to support plugins. - -v9.8.2 -====== - -- Fixed an issue where OCRmyPDF would ignore text inside Form XObject when - making certain decisions about whether a document already had text. -- Fixed file size increase warning to take overhead of small files into account. -- Added instructions for installing on Cygwin. - -v9.8.1 -====== - -- Fixed an issue where unexpected files in the ``%PROGRAMFILES%\gs`` directory - (Windows) caused an exception. -- Mark pdfminer.six 20200517 as supported. -- If jbig2enc is missing and optimization is requested, a warning is issued - instead of an error, which was the intended behavior. -- Documentation updates. - -v9.8.0 -====== - -- Fixed issue where only the first PNG (FlateDecode) image in a file would be - considered for optimization. File sizes should be improved from here on. -- Fixed a startup crash when the chosen language was Japanese (:issue:`543`). -- Added options to configure polling and log level to watcher.py. - -v9.7.2 -====== - -- Fixed an issue with ``ocrmypdf.ocr(...language=)`` not accepting a list of - languages as documented. -- Updated setup.py to confirm that pdfminer.six version 20200402 is supported. - -v9.7.1 -====== - -- Fixed version check failing when used with qpdf 10.0.0. -- Added some missing type annotations. -- Updated documentation to warn about need for "ifmain" guard and Windows. - -v9.7.0 -====== - -- Fixed an error in watcher.py if ``OCR_JSON_SETTINGS`` was not defined. -- Ghostscript 9.51 is now blacklisted, due to numerous problems with this version. -- Added a workaround for a problem with "txtwrite" in Ghostscript 9.52. -- Fixed an issue where the incorrect number of threads used was shown when - ``OMP_THREAD_LIMIT`` was manipulated. -- Removed a possible performance bottlenecks for files that use hundreds to - thousands of images on the same page. -- Documentation improvements. -- Optimization will now be applied to some monochrome images that have a color - profile defined instead of only black and white. -- ICC profiles are consulted when determining the simplified colorspace of an - image. - -v9.6.1 -====== - -- Documentation improvements - thanks to many users for their contributions! - - - Fixed installation instructions for ArchLinux (@pigmonkey) - - Updated installation instructions for FreeBSD and other OSes (@knobix) - - Added instructions for using Docker Compose with watchdog (@ianalexander, - @deisi) - - Other miscellany (@mb720, @toy, @caiofacchinato) - - Some scripts provided in the documentation have been migrated out so that - they can be copied out as whole files, and to ensure syntax checking - is maintained. - -- Fixed an error that caused bash completions to fail on macOS. (:issue:`502,504`; - @AlexanderWillner) -- Fixed a rare case where OCRmyPDF threw an exception while processing a PDF - with the wrong object type in its ``/Trailer /Info``. The error is now logged - and incorrect object is ignored. (:issue:`497`) -- Removed potentially non-free file ``enron1.pdf`` and simplified the test that - used it. -- Removed potentially non-free file ``misc/media/logo.afdesign``. - -v9.6.0 -====== - -- Fixed a regression with transferring metadata from the input PDF to the output - PDF in certain situations. -- pdfminer.six is now supported up to version 2020-01-24. -- Messages are explaining page rotation decisions are now shown at the standard - verbosity level again when ``--rotate-pages``. In some previous version they - were set to debug level messages that only appeared with the parameter ``-v1``. -- Improvements to ``misc/watcher.py``. Thanks to @ianalexander and @svenihoney. -- Documentation improvements. - -v9.5.0 -====== - -- Added API functions to measure OCR quality. -- Modest improvements to handling PDFs with difficult/non compliant metadata. - -v9.4.0 -====== - -- Updated recommended dependency versions. -- Improvements to test coverage and changes to facilitate better measurement of - test coverage, such as when tests run in subprocesses. -- Improvements to error messages when Leptonica is not installed correctly. -- Fixed use of pytest "session scope" that may have caused some intermittent - CI failures. -- When the argument ``--keep-temporary-files`` or verbosity is set to ``-v1``, - a debug log file is generated in the working temporary folder. - -v9.3.0 -====== - -- Improved native Windows support: we now check in the obvious places in - the "Program Files" folders installations of Tesseract and Ghostscript, - rather than relying on the user to edit ``PATH`` to specify their location. - The ``PATH`` environment variable can still be used to differentiate when - multiple installations are present or the programs are installed to non- - standard locations. -- Fixed an exception on parsing Ghostscript error messages. -- Added an improved example demonstrating how to set up a watched folder - for automated OCR processing (thanks to @ianalexander for the contribution). - -v9.2.0 -====== - -- Native Windows is now supported. -- Continuous integration moved to Azure Pipelines. -- Improved test coverage and speed of tests. -- Fixed an issue where a page that was originally a JPEG would be saved as a - PNG, increasing file size. This occurred only when a preprocessing option - was selected along with ``--output-type=pdf`` and all images on the original - page were JPEGs. Regression since v7.0.0. -- OCRmyPDF no longer depends on the QPDF executable ``qpdf`` or ``libqpdf``. - It uses pikepdf (which in turn depends on ``libqpdf``). Package maintainers - should adjust dependencies so that OCRmyPDF no longer calls for libqpdf on - its own. For users of Python binary wheels, this change means a separate - installation of QPDF is no longer necessary. This change is mainly to - simplify installation on Windows. -- Fixed a rare case where log messages from Tesseract would be discarded. -- Fixed incorrect function signature for pixFindPageForeground, causing - exceptions on certain platforms/Leptonica versions. - -v9.1.1 -====== - -- Expand the range of pdfminer.six versions that are supported. -- Fixed Docker build when using pikepdf 1.7.0. -- Fixed documentation to recommend using pip from get-pip.py. - -v9.1.0 -====== - -- Improved diagnostics when file size increases at output. Now warns if JBIG2 - or pngquant were not available. -- pikepdf 1.7.0 is now required, to pick up changes that remove the need for - a source install on Linux systems running Python 3.8. - -v9.0.5 -====== - -- The Alpine Docker image (jbarlow83/ocrmypdf-alpine) has been dropped due to - the difficulties of supporting Alpine Linux. -- The primary Docker image (jbarlow83/ocrmypdf) has been improved to take on - the extra features that used to be exclusive to the Alpine image. -- No changes to application code. -- pdfminer.six version 20191020 is now supported. - -v9.0.4 -====== - -- Fixed compatibility with Python 3.8 (but requires source install for the moment). -- Fixed Tesseract settings for ``--user-words`` and ``--user-patterns``. -- Changed to pikepdf 1.6.5 (for Python 3.8). -- Changed to Pillow 6.2.0 (to mitigate a security vulnerability in earlier Pillow). -- A debug message now mentions when English is automatically selected if the locale - is not English. - -v9.0.3 -====== - -- Embed an encoded version of the sRGB ICC profile in the intermediate - Postscript file (used for PDF/A conversion). Previously we included the - filename, which required Postscript to run with file access enabled. For - security, Ghostscript 9.28 enables ``-dSAFER`` and as such, no longer - permits access to any file by default. This fix is necessary for - compatibility with Ghostscript 9.28. -- Exclude a test that sometimes times out and fails in continuous integration - from the standard test suite. - -v9.0.2 -====== - -- The image optimizer now skips optimizing flate (PNG) encoded images in some - situations where the optimization effort was likely wasted. -- The image optimizer now ignores images that specify arbitrary decode arrays, - since these are rare. -- Fixed an issue that caused inversion of black and white in monochrome images. - We are not certain but the problem seems to be linked to Leptonica 1.76.0 and - older. -- Fixed some cases where the test suite failed if - English or German Tesseract language packs were not installed. -- Fixed a runtime error if the Tesseract English language is not installed. -- Improved explicit closing of Pillow images after use. -- Actually fixed of Alpine Docker image build. -- Changed to pikepdf 1.6.3. - -v9.0.1 -====== - -- Fixed test suite failing when either of optional dependencies unpaper and - pngquant were missing. -- Attempted fix of Alpine Docker image build. -- Documented that FreeBSD ports are now available. -- Changed to pikepdf 1.6.1. - -v9.0.0 -====== - -**Breaking changes** - -- The ``--mask-barcodes`` experimental feature has been dropped due to poor - reliability and occasional crashes, both due to the underlying library that - implements this feature (Leptonica). -- The ``-v`` (verbosity level) parameter now accepts only ``0``, ``1``, and - ``2``. -- Dropped support for Tesseract 4.00.00-alpha releases. Tesseract 4.0 beta and - later remain supported. -- Dropped the ``ocrmypdf-polyglot`` and ``ocrmypdf-webservice`` images. - -**New features** - -- Added a high level API for applications that want to integrate OCRmyPDF. - Special thanks to Martin Wind (@mawi1988) whose made significant contributions - to this effort. -- Added progress bars for long-running steps. ■■■■■■■□□ -- We now create linearized ("fast web view") PDFs by default. The new parameter - ``--fast-web-view`` provides control over when this feature is applied. -- Added a new ``--pages`` feature to limit OCR to only a specific page range. - The list may contain commas or single pages, such as ``1, 3, 5-11``. -- When the number of pages is small compared to the number of allowed jobs, we - run Tesseract in multithreaded (OpenMP) mode when available. This should - improve performance on files with low page counts. -- Removed dependency on ``ruffus``, and with that, the non-reentrancy - restrictions that previous made an API impossible. -- Output and logging messages overhauled so that ocrmypdf may be integrated - into applications that use the logging module. -- pikepdf 1.6.0 is required. -- Added a logo. 😊 - -**Bug fixes** - -- Pages with vector artwork are treated as full color. Previously, vectors - were ignored when considering the colorspace needed to cover a page, which - could cause loss of color under certain settings. -- Test suite now spawns processes less frequently, allowing more accurate - measurement of code coverage. -- Improved test coverage. -- Fixed a rare division by zero (if optimization produced an invalid file). -- Updated Docker images to use newer versions. -- Fixed images encoded as JBIG2 with a colorspace other than ``/DeviceGray`` - were not interpreted correctly. -- Fixed a OCR text-image registration (i.e. alignment) problem when the page - when MediaBox had a nonzero corner. - -v8.3.2 -====== - -- Dropped workaround for macOS that allowed it work without pdfminer.six, - now a proper sdist release of pdfminer.six is available. - -- pikepdf 1.5.0 is now required. - -v8.3.1 -====== - -- Fixed an issue where PDFs with malformed metadata would be rendered as - blank pages. :issue:`398`. - -v8.3.0 -====== - -- Improved the strategy for updating pages when a new image of the page - was produced. We now attempt to preserve more content from the - original file, for annotations in particular. -- For PDFs with more than 100 pages and a sequence where one PDF page - was replaced and one or more subsequent ones were skipped, an - intermediate file would be corrupted while grafting OCR text, causing - processing to fail. This is a regression, likely introduced in - v8.2.4. -- Previously, we resized the images produced by Ghostscript by a small - number of pixels to ensure the output image size was an exactly what - we wanted. Having discovered a way to get Ghostscript to produce the - exact image sizes we require, we eliminated the resizing step. -- Command line completions for ``bash`` are now available, in addition - to ``fish``, both in ``misc/completion``. Package maintainers, please - install these so users can take advantage. -- Updated requirements. -- pikepdf 1.3.0 is now required. - -v8.2.4 -====== - -- Fixed a false positive while checking for a certain type of PDF that - only Acrobat can read. We now more accurately detect Acrobat-only - PDFs. -- OCRmyPDF holds fewer open file handles and is more prompt about - releasing those it no longer needs. -- Minor optimization: we no longer traverse the table of contents to - ensure all references in it are resolved, as changes to libqpdf have - made this unnecessary. -- pikepdf 1.2.0 is now required. - -v8.2.3 -====== - -- Fixed that ``--mask-barcodes`` would occasionally leave a unwanted - temporary file named ``junkpixt`` in the current working folder. -- Fixed (hopefully) handling of Leptonica errors in an environment - where a non-standard ``sys.stderr`` is present. -- Improved help text for ``--verbose``. - -v8.2.2 -====== - -- Fixed a regression from v8.2.0, an exception that occurred while - attempting to report that ``unpaper`` or another optional dependency - was unavailable. -- In some cases, ``ocrmypdf [-c|--clean]`` failed to exit with an error - when ``unpaper`` is not installed. - -v8.2.1 -====== - -- This release was canceled. - -v8.2.0 -====== - -- A major improvement to our Docker image is now available thanks to - hard work contributed by @mawi12345. The new Docker image, - ocrmypdf-alpine, is based on Alpine Linux, and includes most of the - functionality of three existed images in a smaller package. This - image will replace the main Docker image eventually but for now all - are being built. `See documentation for - details `__. -- Documentation reorganized especially around the use of Docker images. -- Fixed a problem with PDF image optimization, where the optimizer - would unnecessarily decompress and recompress PNG images, in some - cases losing the benefits of the quantization it just had just - performed. The optimizer is now capable of embedding PNG images into - PDFs without transcoding them. -- Fixed a minor regression with lossy JBIG2 image optimization. All - JBIG2 candidates images were incorrectly placed into a single - optimization group for the whole file, instead of grouping pages - together. This usually makes a larger JBIG2Globals dictionary and - results in inferior compression, so it worked less well than - designed. However, quality would not be impacted. Lossless JBIG2 was - entirely unaffected. -- Updated dependencies, including pikepdf to 1.1.0. This fixes - :issue:`358`. -- The install-time version checks for certain external programs have - been removed from setup.py. These tests are now performed at - run-time. -- The non-standard option to override install-time checks - (``setup.py install --force``) is now deprecated and prints a - warning. It will be removed in a future release. - -v8.1.0 -====== - -- Added a feature, ``--unpaper-args``, which allows passing arbitrary - arguments to ``unpaper`` when using ``--clean`` or ``--clean-final``. - The default, very conservative unpaper settings are suppressed. -- The argument ``--clean-final`` now implies ``--clean``. It was - possible to issue ``--clean-final`` on its before this, but it would - have no useful effect. -- Fixed an exception on traversing corrupt table of contents entries - (specifically, those with invalid destination objects) -- Fixed an issue when using ``--tesseract-timeout`` and image - processing features on a file with more than 100 pages. - :issue:`347` -- OCRmyPDF now always calls ``os.nice(5)`` to signal to operating - systems that it is a background process. - -v8.0.1 -====== - -- Fixed an exception when parsing PDFs that are missing a required - field. :issue:`325` -- pikepdf 1.0.5 is now required, to address some other PDF parsing - issues. - -v8.0.0 -====== - -No major features. The intent of this release is to sever support for -older versions of certain dependencies. - -**Breaking changes** - -- Dropped support for Tesseract 3.x. Tesseract 4.0 or newer is now - required. -- Dropped support for Python 3.5. -- Some ``ocrmypdf.pdfa`` APIs that were deprecated in v7.x were - removed. This functionality has been moved to pikepdf. - -**Other changes** - -- Fixed an unhandled exception when attempting to mask barcodes. - :issue:`322` -- It is now possible to use ocrmypdf without pdfminer.six, to support - distributions that do not have it or cannot currently use it (e.g. - Homebrew). Downstream maintainers should include pdfminer.six if - possible. -- A warning is now issue when PDF/A conversion removes some XMP - metadata from the input PDF. (Only a "whitelist" of certain XMP - metadata types are allowed in PDF/A.) -- Fixed several issues that caused PDF/As to be produced with - nonconforming XMP metadata (would fail validation with veraPDF). -- Fixed some instances where invalid DocumentInfo from a PDF cause XMP - metadata creation to fail. -- Fixed a few documentation problems. -- pikepdf 1.0.2 is now required. - -v7.4.0 -====== - -- ``--force-ocr`` may now be used with the new ``--threshold`` and - ``--mask-barcodes`` features -- pikepdf >= 0.9.1 is now required. -- Changed metadata handling to pikepdf 0.9.1. As a result, metadata - handling of non-ASCII characters in Ghostscript 9.25 or later is - fixed. -- chardet >= 3.0.4 is temporarily listed as required. pdfminer.six - depends on it, but the most recent release does not specify this - requirement. - (:issue:`326`) -- python-xmp-toolkit and libexempi are no longer required. -- A new Docker image is now being provided for users who wish to access - OCRmyPDF over a simple HTTP interface, instead of the command line. -- Increase tolerance of PDFs that overflow or underflow the PDF - graphics stack. - (:issue:`325`) - -v7.3.1 -====== - -- Fixed performance regression from v7.3.0; fast page analysis was not - selected when it should be. -- Fixed a few exceptions related to the new ``--mask-barcodes`` feature - and improved argument checking -- Added missing detection of TrueType fonts that lack a Unicode mapping - -v7.3.0 -====== - -- Added a new feature ``--redo-ocr`` to detect existing OCR in a file, - remove it, and redo the OCR. This may be particularly helpful for - anyone who wants to take advantage of OCR quality improvements in - Tesseract 4.0. Note that OCR added by OCRmyPDF before version 3.0 - cannot be detected since it was not properly marked as invisible text - in the earliest versions. OCR that constructs a font from visible - text, such as Adobe Acrobat's ClearScan. -- OCRmyPDF's content detection is generally more sophisticated. It - learns more about the contents of each PDF and makes better - recommendations: - - - OCRmyPDF can now detect when a PDF contains text that cannot be - mapped to Unicode (meaning it is readable to human eyes but - copy-pastes as gibberish). In these cases it recommends - ``--force-ocr`` to make the text searchable. - - PDFs containing vector objects are now rendered at more - appropriate resolution for OCR. - - We now exit with an error for PDFs that contain Adobe LiveCycle - Designer's dynamic XFA forms. Currently the open source community - does not have tools to work with these files. - - OCRmyPDF now warns when a PDF that contains Adobe AcroForms, since - such files probably do not need OCR. It can work with these files. - -- Added three new **experimental** features to improve OCR quality in - certain conditions. The name, syntax and behavior of these arguments - is subject to change. They may also be incompatible with some other - features. - - - ``--remove-vectors`` which strips out vector graphics. This can - improve OCR quality since OCR will not search artwork for readable - text; however, it currently removes "text as curves" as well. - - ``--mask-barcodes`` to detect and suppress barcodes in files. We - have observed that barcodes can interfere with OCR because they - are "text-like" but not actually textual. - - ``--threshold`` which uses a more sophisticated thresholding - algorithm than is currently in use in Tesseract OCR. This works - around a `known issue in Tesseract - 4.0 `__ - with dark text on bright backgrounds. - -- Fixed an issue where an error message was not reported when the - installed Ghostscript was very old. -- The PDF optimizer now saves files with object streams enabled when - the optimization level is ``--optimize 1`` or higher (the default). - This makes files a little bit smaller, but requires PDF 1.5. PDF 1.5 - was first released in 2003 and is broadly supported by PDF viewers, - but some rudimentary PDF parsers such as PyPDF2 do not understand - object streams. You can use the command line tool - ``qpdf --object-streams=disable`` or - `pikepdf `__ library to remove - them. -- New dependency: pdfminer.six 20181108. Note this is a fork of the - Python 2-only pdfminer. -- Deprecation notice: At the end of 2018, we will be ending support for - Python 3.5 and Tesseract 3.x. OCRmyPDF v7 will continue to work with - older versions. - -v7.2.1 -====== - -- Fixed compatibility with an API change in pikepdf 0.3.5. -- A kludge to support Leptonica versions older than 1.72 in the test - suite was dropped. Older versions of Leptonica are likely still - compatible. The only impact is that a portion of the test suite will - be skipped. - -v7.2.0 -====== - -**Lossy JBIG2 behavior change** - -A user reported that ocrmypdf was in fact using JBIG2 in **lossy** -compression mode. This was not the intended behavior. Users should -`review the technical concerns with JBIG2 in lossy -mode `__ -and decide if this is a concern for their use case. - -JBIG2 lossy mode does achieve higher compression ratios than any other -monochrome compression technology; for large text documents the savings -are considerable. JBIG2 lossless still gives great compression ratios -and is a major improvement over the older CCITT G4 standard. - -Only users who have reviewed the concerns with JBIG2 in lossy mode -should opt-in. As such, lossy mode JBIG2 is only turned on when the new -argument ``--jbig2-lossy`` is issued. This is independent of the setting -for ``--optimize``. - -Users who did not install an optional JBIG2 encoder are unaffected. - -(Thanks to user 'bsdice' for reporting this issue.) - -**Other issues** - -- When the image optimizer quantizes an image to 1 bit per pixel, it - will now attempt to further optimize that image as CCITT or JBIG2, - instead of keeping it in the "flate" encoding which is not efficient - for 1 bpp images. - (:issue:`297`) -- Images in PDFs that are used as soft masks (i.e. transparency masks - or alpha channels) are now excluded from optimization. -- Fixed handling of Tesseract 4.0-rc1 which now accepts invalid - Tesseract configuration files, which broke the test suite. - -v7.1.0 -====== - -- Improve the performance of initial text extraction, which is done to - determine if a file contains existing text of some kind or not. On - large files, this initial processing is now about 20x times faster. - (:issue:`299`) -- pikepdf 0.3.3 is now required. -- Fixed :issue:`231`, a - problem with JPEG2000 images where image metadata was only available - inside the JPEG2000 file. -- Fixed some additional Ghostscript 9.25 compatibility issues. -- Improved handling of KeyboardInterrupt error messages. - (:issue:`301`) -- README.md is now served in GitHub markdown instead of - reStructuredText. - -v7.0.6 -====== - -- Blacklist Ghostscript 9.24, now that 9.25 is available and fixes many - regressions in 9.24. - -v7.0.5 -====== - -- Improve capability with Ghostscript 9.24, and enable the JPEG - passthrough feature when this version in installed. -- Ghostscript 9.24 lost the ability to set PDF title, author, subject - and keyword metadata to Unicode strings. OCRmyPDF will set ASCII - strings and warn when Unicode is suppressed. Other software may be - used to update metadata. This is a short term work around. -- PDFs generated by Kodak Capture Desktop, or generally PDFs that - contain indirect references to null objects in their table of - contents, would have an invalid table of contents after processing by - OCRmyPDF that might interfere with other viewers. This has been - fixed. -- Detect PDFs generated by Adobe LiveCycle, which can only be displayed - in Adobe Acrobat and Reader currently. When these are encountered, - exit with an error instead of performing OCR on the "Please wait" - error message page. - -v7.0.4 -====== - -- Fixed exception thrown when trying to optimize a certain type of PNG - embedded in a PDF with the ``-O2`` -- Update to pikepdf 0.3.2, to gain support for optimizing some - additional image types that were previously excluded from - optimization (CMYK and grayscale). Fixes - :issue:`285`. - -v7.0.3 -====== - -- Fixed :issue:`284`, an error - when parsing inline images that have are also image masks, by - upgrading pikepdf to 0.3.1 - -v7.0.2 -====== - -- Fixed a regression with ``--rotate-pages`` on pages that already had - rotations applied. - (:issue:`279`) -- Improve quality of page rotation in some cases by rasterizing a - higher quality preview image. - (:issue:`281`) - -v7.0.1 -====== - -- Fixed compatibility with img2pdf >= 0.3.0 by rejecting input images - that have an alpha channel -- Add forward compatibility for pikepdf 0.3.0 (unrelated to img2pdf) -- Various documentation updates for v7.0.0 changes - -v7.0.0 -====== - -- The core algorithm for combining OCR layers with existing PDF pages - has been rewritten and improved considerably. PDFs are no longer - split into single page PDFs for processing; instead, images are - rendered and the OCR results are grafted onto the input PDF. The new - algorithm uses less temporary disk space and is much more performant - especially for large files. -- New dependency: `pikepdf `__. - pikepdf is a powerful new Python PDF library driving the latest - OCRmyPDF features, built on the QPDF C++ library (libqpdf). -- New feature: PDF optimization with ``-O`` or ``--optimize``. After - OCR, OCRmyPDF will perform image optimizations relevant to OCR PDFs. - - - If a JBIG2 encoder is available, then monochrome images will be - converted, with the potential for huge savings on large black and - white images, since JBIG2 is far more efficient than any other - monochrome (bi-level) compression. (All known US patents related - to JBIG2 have probably expired, but it remains the responsibility - of the user to supply a JBIG2 encoder such as - `jbig2enc `__. OCRmyPDF does not - implement JBIG2 encoding.) - - If ``pngquant`` is installed, OCRmyPDF will optionally use it to - perform lossy quantization and compression of PNG images. - - The quality of JPEGs can also be lowered, on the assumption that a - lower quality image may be suitable for storage after OCR. - - This image optimization component will eventually be offered as an - independent command line utility. - - Optimization ranges from ``-O0`` through ``-O3``, where ``0`` - disables optimization and ``3`` implements all options. ``1``, the - default, performs only safe and lossless optimizations. (This is - similar to GCC's optimization parameter.) The exact type of - optimizations performed will vary over time. - -- Small amounts of text in the margins of a page, such as watermarks, - page numbers, or digital stamps, will no longer prevent the rest of a - page from being OCRed when ``--skip-text`` is issued. This behavior - is based on a heuristic. -- Removed features - - - The deprecated ``--pdf-renderer tesseract`` PDF renderer was - removed. - - ``-g``, the option to generate debug text pages, was removed - because it was a maintenance burden and only worked in isolated - cases. HOCR pages can still be previewed by running the - hocrtransform.py with appropriate settings. - -- Removed dependencies - - - ``PyPDF2`` - - ``defusedxml`` - - ``PyMuPDF`` - -- The ``sandwich`` PDF renderer can be used with all supported versions - of Tesseract, including that those prior to v3.05 which don't support - ``-c textonly``. (Tesseract v4.0.0 is recommended and more - efficient.) -- ``--pdf-renderer auto`` option and the diagnostics used to select a - PDF renderer now work better with old versions, but may make - different decisions than past versions. -- If everything succeeds but PDF/A conversion fails, a distinct return - code is now returned (``ExitCode.pdfa_conversion_failed (10)``) where - this situation previously returned - ``ExitCode.invalid_output_pdf (4)``. The latter is now returned only - if there is some indication that the output file is invalid. -- Notes for downstream packagers - - - There is also a new dependency on ``python-xmp-toolkit`` which in - turn depends on ``libexempi3``. - - It may be necessary to separately ``pip install pycparser`` to - avoid `another Python 3.7 - issue `__. - -v6.2.5 -====== - -- Disable a failing test due to Tesseract 4.0rc1 behavior change. - Previously, Tesseract would exit with an error message if its - configuration was invalid, and OCRmyPDF would intercept this message. - Now Tesseract issues a warning, which OCRmyPDF v6.2.5 may relay or - ignore. (In v7.x, OCRmyPDF will respond to the warning.) -- This release branch no longer supports using the optional PyMuPDF - installation, since it was removed in v7.x. -- This release branch no longer supports macOS. macOS users should - upgrade to v7.x. - -v6.2.4 -====== - -- Backport Ghostscript 9.25 compatibility fixes, which removes support - for setting Unicode metadata -- Backport blacklisting Ghostscript 9.24 -- Older versions of Ghostscript are still supported - -v6.2.3 -====== - -- Fixed compatibility with img2pdf >= 0.3.0 by rejecting input images - that have an alpha channel -- This version will be included in Ubuntu 18.10 - -v6.2.2 -====== - -- Backport compatibility fixes for Python 3.7 and ruffus 2.7.0 from - v7.0.0 -- Backport fix to ignore masks when deciding what colors are on a page -- Backport some minor improvements from v7.0.0: better argument - validation and warnings about the Tesseract 4.0.0 ``--user-words`` - regression - -v6.2.1 -====== - -- Fixed recent versions of Tesseract (after 4.0.0-beta1) not being - detected as supporting the ``sandwich`` renderer (:issue:`271`). - -v6.2.0 -====== - -- **Docker**: The Docker image ``ocrmypdf-tess4`` has been removed. The - main Docker images, ``ocrmypdf`` and ``ocrmypdf-polyglot`` now use - Ubuntu 18.04 as a base image, and as such Tesseract 4.0.0-beta1 is - now the Tesseract version they use. There is no Docker image based on - Tesseract 3.05 anymore. -- Creation of PDF/A-3 is now supported. However, there is no ability to - attach files to PDF/A-3. -- Lists more reasons why the file size might grow. -- Fixed :issue:`262`, - ``--remove-background`` error on PDFs contained colormapped - (paletted) images. -- Fixed another XMP metadata validation issue, in cases where the input - file's creation date has no timezone and the creation date is not - overridden. - -v6.1.5 -====== - -- Fixed :issue:`253`, a - possible division by zero when using the ``hocr`` renderer. -- Fixed incorrectly formatted ```` field inside XMP - metadata for PDF/As. veraPDF flags this as a PDF/A validation - failure. The error is caused the timezone and final digit of the - seconds of modified time to be omitted, so at worst the modification - time stamp is rounded to the nearest 10 seconds. - -v6.1.4 -====== - -- Fixed :issue:`248` - ``--clean`` argument may remove OCR from left column of text on - certain documents. We now set ``--layout none`` to suppress this. -- The test cache was updated to reflect the change above. -- Change test suite to accommodate Ghostscript 9.23's new ability to - insert JPEGs into PDFs without transcoding. -- XMP metadata in PDFs is now examined using ``defusedxml`` for safety. -- If an external process exits with a signal when asked to report its - version, we now print the system error message instead of suppressing - it. This occurred when the required executable was found but was - missing a shared library. -- qpdf 7.0.0 or newer is now required as the test suite can no longer - pass without it. - -Notes ------ - -- An apparent `regression in Ghostscript - 9.23 `__ will - cause some ocrmypdf output files to become invalid in rare cases; the - workaround for the moment is to set ``--force-ocr``. - -v6.1.3 -====== - -- Fixed :issue:`247`, - ``/CreationDate`` metadata not copied from input to output. -- A warning is now issued when Python 3.5 is used on files with a large - page count, as this case is known to regress to single core - performance. The cause of this problem is unknown. - -v6.1.2 -====== - -- Upgrade to PyMuPDF v1.12.5 which includes a more complete fix to - :issue:`239`. -- Add ``defusedxml`` dependency. - -v6.1.1 -====== - -- Fixed text being reported as found on all pages if PyMuPDF is not - installed. - -v6.1.0 -====== - -- PyMuPDF is now an optional but recommended dependency, to alleviate - installation difficulties on platforms that have less access to - PyMuPDF than the author anticipated. (For version 6.x only) install - OCRmyPDF with ``pip install ocrmypdf[fitz]`` to use it to its full - potential. -- Fixed ``FileExistsError`` that could occur if OCR timed out while it - was generating the output file. - (:issue:`218`) -- Fixed table of contents/bookmarks all being redirected to page 1 when - generating a PDF/A (with PyMuPDF). (Without PyMuPDF the table of - contents is removed in PDF/A mode.) -- Fixed "RuntimeError: invalid key in dict" when table of - contents/bookmarks titles contained the character ``)``. - (:issue:`239`) -- Added a new argument ``--skip-repair`` to skip the initial PDF repair - step if the PDF is already well-formed (because another program - repaired it). - -v6.0.0 -====== - -- The software license has been changed to GPLv3 [it has since changed again]. - Test resource files and some individual sources may have other licenses. -- OCRmyPDF now depends on - `PyMuPDF `__. - Including PyMuPDF is the primary reason for the change to GPLv3. -- Other backward incompatible changes - - - The ``OCRMYPDF_TESSERACT``, ``OCRMYPDF_QPDF``, ``OCRMYPDF_GS`` and - ``OCRMYPDF_UNPAPER`` environment variables are no longer used. - Change ``PATH`` if you need to override the external programs - OCRmyPDF uses. - - The ``ocrmypdf`` package has been moved to ``src/ocrmypdf`` to - avoid issues with accidental import. - - The function ``ocrmypdf.exec.get_program`` was removed. - - The deprecated module ``ocrmypdf.pageinfo`` was removed. - - The ``--pdf-renderer tess4`` alias for ``sandwich`` was removed. - -- Fixed an issue where OCRmyPDF failed to detect existing text on - pages, depending on how the text and fonts were encoded within the - PDF. (:issue:`233,232`) -- Fixed an issue that caused dramatic inflation of file sizes when - ``--skip-text --output-type pdf`` was used. OCRmyPDF now removes - duplicate resources such as fonts, images and other objects that it - generates. (:issue:`237`) -- Improved performance of the initial page splitting step. Originally - this step was not believed to be expensive and ran in a process. - Large file testing revealed it to be a bottleneck, so it is now - parallelized. On a 700 page file with quad core machine, this change - saves about 2 minutes. (:issue:`234`) -- The test suite now includes a cache that can be used to speed up test - runs across platforms. This also does not require computing - checksums, so it's faster. (:issue:`217`) - -v5.7.0 -====== - -- Fixed an issue that caused poor CPU utilization on machines with more - than 4 cores when running Tesseract 4. (Related to :issue:`217`.) -- The 'hocr' renderer has been improved. The 'sandwich' and 'tesseract' - renderers are still better for most use cases, but 'hocr' may be - useful for people who work with the PDF.js renderer in English/ASCII - languages. (:issue:`225`) - - - It now formats text in a matter that is easier for certain PDF - viewers to select and extract copy and paste text. This should - help macOS Preview and PDF.js in particular. - - The appearance of selected text and behavior of selecting text is - improved. - - The PDF content stream now uses relative moves, making it more - compact and easier for viewers to determine when two words on the - same line. - - It can now deal with text on a skewed baseline. - - Thanks to @cforcey for the pull request, @jbreiden for many - helpful suggestions, @ctbarbour for another round of improvements, - and @acaloiaro for an independent review. - -v5.6.3 -====== - -- Suppress two debug messages that were too verbose - -v5.6.2 -====== - -- Development branch accidentally tagged as release. Do not use. - -v5.6.1 -====== - -- Fixed :issue:`219`: change - how the final output file is created to avoid triggering permission - errors when the output is a special file such as ``/dev/null`` -- Fixed test suite failures due to a qpdf 8.0.0 regression and Python - 3.5's handling of symlink -- The "encrypted PDF" error message was different depending on the type - of PDF encryption. Now a single clear message appears for all types - of PDF encryption. -- ocrmypdf is now in Homebrew. Homebrew users are advised to the - version of ocrmypdf in the official homebrew-core formulas rather - than the private tap. -- Some linting - -v5.6.0 -====== - -- Fixed :issue:`216`: preserve - "text as curves" PDFs without rasterizing file -- Related to the above, messages about rasterizing are more consistent -- For consistency versions minor releases will now get the trailing .0 - they always should have had. - -v5.5 -==== - -- Add new argument ``--max-image-mpixels``. Pillow 5.0 now raises an - exception when images may be decompression bombs. This argument can - be used to override the limit Pillow sets. -- Fixed output page cropped when using the sandwich renderer and OCR is - skipped on a rotated and image-processed page -- A warning is now issued when old versions of Ghostscript are used in - cases known to cause issues with non-Latin characters -- Fixed a few parameter validation checks for ``-output-type pdfa-1`` and - ``pdfa-2`` - -v5.4.4 -====== - -- Fixed :issue:`181`: fix - final merge failure for PDFs with more pages than the system file - handle limit (``ulimit -n``) -- Fixed :issue:`200`: an - uncommon syntax for formatting decimal numbers in a PDF would cause - qpdf to issue a warning, which ocrmypdf treated as an error. Now this - the warning is relayed. -- Fixed an issue where intermediate PDFs would be created at version 1.3 - instead of the version of the original file. It's possible but - unlikely this had side effects. -- A warning is now issued when older versions of qpdf are used since - issues like - :issue:`200` cause - qpdf to infinite-loop -- Address issue - :issue:`140`: if - Tesseract outputs invalid UTF-8, escape it and print its message - instead of aborting with a Unicode error -- Adding previously unlisted setup requirement, pytest-runner -- Update documentation: fix an error in the example script for Synology - with Docker images, improved security guidance, advised - ``pip install --user`` - -v5.4.3 -====== - -- If a subprocess fails to report its version when queried, exit - cleanly with an error instead of throwing an exception -- Added test to confirm that the system locale is Unicode-aware and - fail early if it's not -- Clarified some copyright information -- Updated pinned requirements.txt so the homebrew formula captures more - recent versions - -v5.4.2 -====== - -- Fixed a regression from v5.4.1 that caused sidecar files to be - created as empty files - -v5.4.1 -====== - -- Add workaround for Tesseract v4.00alpha crash when trying to obtain - orientation and the latest language packs are installed - -v5.4 -==== - -- Change wording of a deprecation warning to improve clarity -- Added option to generate PDF/A-1b output if desired - (``--output-type pdfa-1``); default remains PDF/A-2b generation -- Update documentation - -v5.3.3 -====== - -- Fixed missing error message that should occur when trying to force - ``--pdf-renderer sandwich`` on old versions of Tesseract -- Update copyright information in test files -- Set system ``LANG`` to UTF-8 in Dockerfiles to avoid UTF-8 encoding - errors - -v5.3.2 -====== - -- Fixed a broken test case related to language packs - -v5.3.1 -====== - -- Fixed wrong return code given for missing Tesseract language packs -- Fixed "brew audit" crashing on Travis when trying to auto-brew - -v5.3 -==== - -- Added ``--user-words`` and ``--user-patterns`` arguments which are - forwarded to Tesseract OCR as words and regular expressions - respective to use to guide OCR. Supplying a list of subject-domain - words should assist Tesseract with resolving words. - (:issue:`165`) -- Using a non Latin-1 language with the "hocr" renderer now warns about - possible OCR quality and recommends workarounds - (:issue:`176`) -- Output file path added to error message when that location is not - writable - (:issue:`175`) -- Otherwise valid PDFs with leading whitespace at the beginning of the - file are now accepted - -v5.2 -==== - -- When using Tesseract 3.05.01 or newer, OCRmyPDF will select the - "sandwich" PDF renderer by default, unless another PDF renderer is - specified with the ``--pdf-renderer`` argument. The previous behavior - was to select ``--pdf-renderer=hocr``. -- The "tesseract" PDF renderer is now deprecated, since it can cause - problems with Ghostscript on Tesseract 3.05.00 -- The "tess4" PDF renderer has been renamed to "sandwich". "tess4" is - now a deprecated alias for "sandwich". - -v5.1 -==== - -- Files with pages larger than 200" (5080 mm) in either dimension are - now supported with ``--output-type=pdf`` with the page size preserved - (in the PDF specification this feature is called UserUnit scaling). - Due to Ghostscript limitations this is not available in conjunction - with PDF/A output. - -v5.0.1 -====== - -- Fixed :issue:`169`, - exception due to failure to create sidecar text files on some - versions of Tesseract 3.04, including the jbarlow83/ocrmypdf Docker - image - -v5.0 -==== - -- Backward incompatible changes - - - Support for Python 3.4 dropped. Python 3.5 is now required. - - Support for Tesseract 3.02 and 3.03 dropped. Tesseract 3.04 or - newer is required. Tesseract 4.00 (alpha) is supported. - - The OCRmyPDF.sh script was removed. - -- Add a new feature, ``--sidecar``, which allows creating "sidecar" - text files which contain the OCR results in plain text. These OCR - text is more reliable than extracting text from PDFs. Closes - :issue:`126`. - -- New feature: ``--pdfa-image-compression``, which allows overriding - Ghostscript's lossy-or-lossless image encoding heuristic and making - all images JPEG encoded or lossless encoded as desired. Fixes - :issue:`163`. - -- Fixed :issue:`143`, added - ``--quiet`` to suppress "INFO" messages - -- Fixed :issue:`164`, a typo - -- Removed the command line parameters ``-n`` and ``--just-print`` since - they have not worked for some time (reported as Ubuntu bug - `#1687308 `__) - -v4.5.6 -====== - -- Fixed :issue:`156`, - 'NoneType' object has no attribute 'getObject' on pages with no - optional /Contents record. This should resolve all issues related to - pages with no /Contents record. -- Fixed :issue:`158`, ocrmypdf - now stops and terminates if Ghostscript fails on an intermediate - step, as it is not possible to proceed. -- Fixed :issue:`160`, - exception thrown on certain invalid arguments instead of error - message - -v4.5.5 -====== - -- Automated update of macOS homebrew tap -- Fixed :issue:`154`, KeyError - '/Contents' when searching for text on blank pages that have no - /Contents record. Note: incomplete fix for this issue. - -v4.5.4 -====== - -- Fixed ``--skip-big`` raising an exception if a page contains no images - (:issue:`152`) (thanks - to @TomRaz) -- Fixed an issue where pages with no images might trigger "cannot write - mode P as JPEG" - (:issue:`151`) - -v4.5.3 -====== - -- Added a workaround for Ghostscript 9.21 and probably earlier versions - would fail with the error message "VMerror -25", due to a Ghostscript - bug in XMP metadata handling -- High Unicode characters (U+10000 and up) are no longer accepted for - setting metadata on the command line, as Ghostscript may not handle - them correctly. -- Fixed an issue where the ``tess4`` renderer would duplicate content - onto output pages if tesseract failed or timed out -- Fixed ``tess4`` renderer not recognized when lossless reconstruction - is possible - -v4.5.2 -====== - -- Fixed :issue:`147`, - ``--pdf-renderer tess4 --clean`` will produce an oversized page - containing the original image in the bottom left corner, due to loss - DPI information. -- Make "using Tesseract 4.0" warning less ominous -- Set up machinery for homebrew OCRmyPDF tap - -v4.5.1 -====== - -- Fixed :issue:`137`, - proportions of images with a non-square pixel aspect ratio would be - distorted in output for ``--force-ocr`` and some other combinations - of flags - -v4.5 -==== - -- PDFs containing "Form XObjects" are now supported (issue - :issue:`134`; PDF - reference manual 8.10), and images they contain are taken into - account when determining the resolution for rasterizing -- The Tesseract 4 Docker image no longer includes all languages, - because it took so long to build something would tend to fail -- OCRmyPDF now warns about using ``--pdf-renderer tesseract`` with - Tesseract 3.04 or lower due to issues with Ghostscript corrupting the - OCR text in these cases - -v4.4.2 -====== - -- The Docker images (ocrmypdf, ocrmypdf-polyglot, ocrmypdf-tess4) are - now based on Ubuntu 16.10 instead of Debian stretch - - - This makes supporting the Tesseract 4 image easier - - This could be a disruptive change for any Docker users who built - customized these images with their own changes, and made those - changes in a way that depends on Debian and not Ubuntu - -- OCRmyPDF now prevents running the Tesseract 4 renderer with Tesseract - 3.04, which was permitted in v4.4 and v4.4.1 but will not work - -v4.4.1 -====== - -- To prevent a `TIFF output - error `__ caused - by img2pdf >= 0.2.1 and Pillow <= 3.4.2, dependencies have been - tightened -- The Tesseract 4.00 simultaneous process limit was increased from 1 to - 2, since it was observed that 1 lowers performance -- Documentation improvements to describe the ``--tesseract-config`` - feature -- Added test cases and fixed error handling for ``--tesseract-config`` -- Tweaks to setup.py to deal with issues in the v4.4 release - -v4.4 -==== - -- Tesseract 4.00 is now supported on an experimental basis. - - - A new rendering option ``--pdf-renderer tess4`` exploits Tesseract - 4's new text-only output PDF mode. See the documentation on PDF - Renderers for details. - - The ``--tesseract-oem`` argument allows control over the Tesseract - 4 OCR engine mode (tesseract's ``--oem``). Use - ``--tesseract-oem 2`` to enforce the new LSTM mode. - - Fixed poor performance with Tesseract 4.00 on Linux - -- Fixed an issue that caused corruption of output to stdout in some - cases -- Removed test for Pillow JPEG and PNG support, as the minimum - supported version of Pillow now enforces this -- OCRmyPDF now tests that the intended destination file is writable - before proceeding -- The test suite now requires ``pytest-helpers-namespace`` to run (but - not install) -- Significant code reorganization to make OCRmyPDF re-entrant and - improve performance. All changes should be backward compatible for - the v4.x series. - - - However, OCRmyPDF's dependency "ruffus" is not re-entrant, so no - Python API is available. Scripts should continue to use the - command line interface. - -v4.3.5 -====== - -- Update documentation to confirm Python 3.6.0 compatibility. No code - changes were needed, so many earlier versions are likely supported. - -v4.3.4 -====== - -- Fixed "decimal.InvalidOperation: quantize result has too many digits" - for high DPI images - -v4.3.3 -====== - -- Fixed PDF/A creation with Ghostscript 9.20 properly -- Fixed an exception on inline stencil masks with a missing optional - parameter - -v4.3.2 -====== - -- Fixed a PDF/A creation issue with Ghostscript 9.20 (note: this fix - did not actually work) - -v4.3.1 -====== - -- Fixed an issue where pages produced by the "hocr" renderer after a - Tesseract timeout would be rotated incorrectly if the input page was - rotated with a /Rotate marker -- Fixed a file handle leak in LeptonicaErrorTrap that would cause a - "too many open files" error for files around hundred pages of pages - long when ``--deskew`` or ``--remove-background`` or other Leptonica - based image processing features were in use, depending on the system - value of ``ulimit -n`` -- Ability to specify multiple languages for multilingual documents is - now advertised in documentation -- Reduced the file sizes of some test resources -- Cleaned up debug output -- Tesseract caching in test cases is now more cautious about false - cache hits and reproducing exact output, not that any problems were - observed - -v4.3 -==== - -- New feature ``--remove-background`` to detect and erase the - background of color and grayscale images -- Better documentation -- Fixed an issue with PDFs that draw images when the raster stack depth - is zero -- ocrmypdf can now redirect its output to stdout for use in a shell - pipeline - - - This does not improve performance since temporary files are still - used for buffering - - Some output validation is disabled in this mode - -v4.2.5 -====== - -- Fixed an issue - (:issue:`100`) with - PDFs that omit the optional /BitsPerComponent parameter on images -- Removed non-free file milk.pdf - -v4.2.4 -====== - -- Fixed an error - (:issue:`90`) caused by - PDFs that use stencil masks properly -- Fixed handling of PDFs that try to draw images or stencil masks - without properly setting up the graphics state (such images are now - ignored for the purposes of calculating DPI) - -v4.2.3 -====== - -- Fixed an issue with PDFs that store page rotation (/Rotate) in an - indirect object -- Integrated a few fixes to simplify downstream packaging (Debian) - - - The test suite no longer assumes it is installed - - If running Linux, skip a test that passes Unicode on the command - line - -- Added a test case to check explicit masks and stencil masks -- Added a test case for indirect objects and linearized PDFs -- Deprecated the OCRmyPDF.sh shell script - -v4.2.2 -====== - -- Improvements to documentation - -v4.2.1 -====== - -- Fixed an issue where PDF pages that contained stencil masks would - report an incorrect DPI and cause Ghostscript to abort -- Implemented stdin streaming - -v4.2 -==== - -- ocrmypdf will now try to convert single image files to PDFs if they - are provided as input - (:issue:`15`) - - - This is a basic convenience feature. It only supports a single - image and always makes the image fill the whole page. - - For better control over image to PDF conversion, use ``img2pdf`` - (one of ocrmypdf's dependencies) - -- New argument ``--output-type {pdf|pdfa}`` allows disabling - Ghostscript PDF/A generation - - - ``pdfa`` is the default, consistent with past behavior - - ``pdf`` provides a workaround for users concerned about the - increase in file size from Ghostscript forcing JBIG2 images to - CCITT and transcoding JPEGs - - ``pdf`` preserves as much as it can about the original file, - including problems that PDF/A conversion fixes - -- PDFs containing images with "non-square" pixel aspect ratios, such as - 200x100 DPI, are now handled and converted properly (fixing a bug - that caused to be cropped) -- ``--force-ocr`` rasterizes pages even if they contain no images - - - supports users who want to use OCRmyPDF to reconstruct text - information in PDFs with damaged Unicode maps (copy and paste text - does not match displayed text) - - supports reinterpreting PDFs where text was rendered as curves for - printing, and text needs to be recovered - - fixes issue - :issue:`82` - -- Fixes an issue where, with certain settings, monochrome images in - PDFs would be converted to 8-bit grayscale, increasing file size - (:issue:`79`) -- Support for Ubuntu 12.04 LTS "precise" has been dropped in favor of - (roughly) Ubuntu 14.04 LTS "trusty" - - - Some Ubuntu "PPAs" (backports) are needed to make it work - -- Support for some older dependencies dropped - - - Ghostscript 9.15 or later is now required (available in Ubuntu - trusty with backports) - - Tesseract 3.03 or later is now required (available in Ubuntu - trusty) - -- Ghostscript now runs in "safer" mode where possible - -v4.1.4 -====== - -- Bug fix: monochrome images with an ICC profile attached were - incorrectly converted to full color images if lossless reconstruction - was not possible due to other settings; consequence was increased - file size for these images - -v4.1.3 -====== - -- More helpful error message for PDFs with version 4 security handler -- Update usage instructions for Windows/Docker users -- Fixed order of operations for matrix multiplication (no effect on most - users) -- Add a few leptonica wrapper functions (no effect on most users) - -v4.1.2 -====== - -- Replace IEC sRGB ICC profile with Debian's sRGB (from - icc-profiles-free) which is more compatible with the MIT license -- More helpful error message for an error related to certain types of - malformed PDFs - -v4.1 -==== - -- ``--rotate-pages`` now only rotates pages when reasonably confidence - in the orientation. This behavior can be adjusted with the new - argument ``--rotate-pages-threshold`` -- Fixed problems in error checking if ``unpaper`` is uninstalled or - missing at run-time -- Fixed problems with "RethrownJobError" errors during error handling - that suppressed the useful error messages - -v4.0.7 -====== - -- Minor correction to Ghostscript output settings - -v4.0.6 -====== - -- Update install instructions -- Provide a sRGB profile instead of using Ghostscript's - -v4.0.5 -====== - -- Remove some verbose debug messages from v4.0.4 -- Fixed temporary that wasn't being deleted -- DPI is now calculated correctly for cropped images, along with other - image transformations -- Inline images are now checked during DPI calculation instead of - rejecting the image - -v4.0.4 -====== - -Released with verbose debug message turned on. Do not use. Skip to -v4.0.5. - -v4.0.3 -====== - -New features - -- Page orientations detected are now reported in a summary comment - -Fixes - -- Show stack trace if unexpected errors occur -- Treat "too few characters" error message from Tesseract as a reason - to skip that page rather than abort the file -- Docker: fix blank JPEG2000 issue by insisting on Ghostscript versions - that have this fixed - -v4.0.2 -====== - -Fixes - -- Fixed compatibility with Tesseract 3.04.01 release, particularly its - different way of outputting orientation information -- Improved handling of Tesseract errors and crashes -- Fixed use of chmod on Docker that broke most test cases - -v4.0.1 -====== - -Fixes - -- Fixed a KeyError if tesseract fails to find page orientation - information - -v4.0 -==== - -New features - -- Automatic page rotation (``-r``) is now available. It uses ignores - any prior rotation information on PDFs and sets rotation based on the - dominant orientation of detectable text. This feature is fairly - reliable but some false positives occur especially if there is not - much text to work with. - (:issue:`4`) -- Deskewing is now performed using Leptonica instead of unpaper. - Leptonica is faster and more reliable at image deskewing than - unpaper. - -Fixes - -- Fixed an issue where lossless reconstruction could cause some pages - to be appear incorrectly if the page was rotated by the user in - Acrobat after being scanned (specifically if it a /Rotate tag) -- Fixed an issue where lossless reconstruction could misalign the - graphics layer with respect to text layer if the page had been - cropped such that its origin is not (0, 0) - (:issue:`49`) - -Changes - -- Logging output is now much easier to read -- ``--deskew`` is now performed by Leptonica instead of unpaper - (:issue:`25`) -- libffi is now required -- Some changes were made to the Docker and Travis build environments to - support libffi -- ``--pdf-renderer=tesseract`` now displays a warning if the Tesseract - version is less than 3.04.01, the planned release that will include - fixes to an important OCR text rendering bug in Tesseract 3.04.00. - You can also manually install ./share/sharp2.ttf on top of pdf.ttf in - your Tesseract tessdata folder to correct the problem. - -v3.2.1 -====== - -Changes - -- Fixed :issue:`47` - "convert() got and unexpected keyword argument 'dpi'" by upgrading to - img2pdf 0.2 -- Tweaked the Dockerfiles - -v3.2 -==== - -New features - -- Lossless reconstruction: when possible, OCRmyPDF will inject text - layers without otherwise manipulating the content and layout of a PDF - page. For example, a PDF containing a mix of vector and raster - content would see the vector content preserved. Images may still be - transcoded during PDF/A conversion. (``--deskew`` and - ``--clean-final`` disable this mode, necessarily.) -- New argument ``--tesseract-pagesegmode`` allows you to pass page - segmentation arguments to Tesseract OCR. This helps for two column - text and other situations that confuse Tesseract. -- Added a new "polyglot" version of the Docker image, that generates - Tesseract with all languages packs installed, for the polyglots among - us. It is much larger. - -Changes - -- JPEG transcoding quality is now 95 instead of the default 75. Bigger - file sizes for less degradation. - -v3.1.1 -====== - -Changes - -- Fixed bug that caused incorrect page size and DPI calculations on - documents with mixed page sizes - -v3.1 -==== - -Changes - -- Default output format is now PDF/A-2b instead of PDF/A-1b -- Python 3.5 and macOS El Capitan are now supported platforms - no - changes were needed to implement support -- Improved some error messages related to missing input files -- Fixed :issue:`20`: uppercase .PDF extension not accepted -- Fixed an issue where OCRmyPDF failed to text that certain pages - contained previously OCR'ed text, such as OCR text produced by - Tesseract 3.04 -- Inserts /Creator tag into PDFs so that errors can be traced back to - this project -- Added new option ``--pdf-renderer=auto``, to let OCRmyPDF pick the - best PDF renderer. Currently it always chooses the 'hocrtransform' - renderer but that behavior may change. -- Set up Travis CI automatic integration testing - -v3.0 -==== - -New features - -- Easier installation with a Docker container or Python's ``pip`` - package manager -- Eliminated many external dependencies, so it's easier to setup -- Now installs ``ocrmypdf`` to ``/usr/local/bin`` or equivalent for - system-wide access and easier typing -- Improved command line syntax and usage help (``--help``) -- Tesseract 3.03+ PDF page rendering can be used instead for better - positioning of recognized text (``--pdf-renderer tesseract``) -- PDF metadata (title, author, keywords) are now transferred to the - output PDF -- PDF metadata can also be set from the command line (``--title``, - etc.) -- Automatic repairs malformed input PDFs if possible -- Added test cases to confirm everything is working -- Added option to skip extremely large pages that take too long to OCR - and are often not OCRable (e.g. large scanned maps or diagrams); - other pages are still processed (``--skip-big``) -- Added option to kill Tesseract OCR process if it seems to be taking - too long on a page, while still processing other pages - (``--tesseract-timeout``) -- Less common colorspaces (CMYK, palette) are now supported by - conversion to RGB -- Multiple images on the same PDF page are now supported - -Changes - -- New, robust rewrite in Python 3.4+ with - `ruffus `__ pipelines -- Now uses Ghostscript 9.14's improved color conversion model to - preserve PDF colors -- OCR text is now rendered in the PDF as invisible text. Previous - versions of OCRmyPDF incorrectly rendered visible text with an image - on top. -- All "tasks" in the pipeline can be executed in parallel on any - available CPUs, increasing performance -- The ``-o DPI`` argument has been phased out, in favor of - ``--oversample DPI``, in case we need ``-o OUTPUTFILE`` in the future -- Removed several dependencies, so it's easier to install. We no longer - use: - - - GNU `parallel `__ - - `ImageMagick `__ - - Python 2.7 - - Poppler - - `MuPDF `__ tools - - shell scripts - - Java and `JHOVE `__ - - libxml2 - -- Some new external dependencies are required or optional, compared to - v2.x: - - - Ghostscript 9.14+ - - `qpdf `__ 5.0.0+ - - `Unpaper `__ 6.1 (optional) - - some automatically managed Python packages - -Release candidates^ - -- rc9: - - - Fix - :issue:`118`: - report error if ghostscript iccprofiles are missing - - fixed another issue related to - :issue:`111`: PDF - rasterized to palette file - - add support image files with a palette - - don't try to validate PDF file after an exception occurs - -- rc8: - - - Fix - :issue:`111`: - exception thrown if PDF is missing DocumentInfo dictionary - -- rc7: - - - fix error when installing direct from pip, "no such file - 'requirements.txt'" - -- rc6: - - - dropped libxml2 (Python lxml) since Python 3's internal XML parser - is sufficient - - set up Docker container - - fix Unicode errors if recognized text contains Unicode characters - and system locale is not UTF-8 - -- rc5: - - - dropped Java and JHOVE in favour of qpdf - - improved command line error output - - additional tests and bug fixes - - tested on Ubuntu 14.04 LTS - -- rc4: - - - dropped MuPDF in favour of qpdf - - fixed some installer issues and errors in installation - instructions - - improve performance: run Ghostscript with multithreaded rendering - - improve performance: use multiple cores by default - - bug fix: checking for wrong exception on process timeout - -- rc3: skipping version number intentionally to avoid confusion with - Tesseract -- rc2: first release for public testing to test-PyPI, Github -- rc1: testing release process - -Compatibility notes -=================== - -- ``./OCRmyPDF.sh`` script is still available for now -- Stacking the verbosity option like ``-vvv`` is no longer supported -- The configuration file ``config.sh`` has been removed. Instead, you - can feed a file to the arguments for common settings: - -:: - - ocrmypdf input.pdf output.pdf @settings.txt - -where ``settings.txt`` contains *one argument per line*, for example: - -:: - - -l - deu - --author - A. Merkel - --pdf-renderer - tesseract - -Fixes - -- Handling of filenames containing spaces: fixed - -Notes and known issues - -- Some dependencies may work with lower versions than tested, so try - overriding dependencies if they are "in the way" to see if they work. -- ``--pdf-renderer tesseract`` will output files with an incorrect page - size in Tesseract 3.03, due to a bug in Tesseract. -- PDF files containing "inline images" are not supported and won't be - for the 3.0 release. Scanned images almost never contain inline - images. - -v2.2-stable (2014-09-29) -======================== - -OCRmyPDF versions 1 and 2 were implemented as shell scripts. OCRmyPDF -3.0+ is a fork that gradually replaced all shell scripts with Python -while maintaining the existing command line arguments. No one is -maintaining old versions. - -For details on older versions, see the `final version of its release -notes `__. From e4a8f7a3546c57f9e6ebfcfe8098c4d9d8a0de32 Mon Sep 17 00:00:00 2001 From: "James R. Barlow" Date: Thu, 17 Apr 2025 15:10:59 -0700 Subject: [PATCH 4/5] Remove redundant optimizer content --- docs/cookbook.md | 41 ++++------------------------------------- docs/optimizer.md | 23 +++++++++++++++++------ 2 files changed, 21 insertions(+), 43 deletions(-) diff --git a/docs/cookbook.md b/docs/cookbook.md index 29201b9b..06941a97 100644 --- a/docs/cookbook.md +++ b/docs/cookbook.md @@ -283,8 +283,7 @@ as little as possible: ocrmypdf --pages 1 --output-type pdf --optimize 0 input.pdf output.pdf ``` -Redo existing OCR ------------------ +## Redo existing OCR To redo OCR on a file OCRed with other OCR software or a previous version of OCRmyPDF and/or Tesseract, you may use the `--redo-ocr` @@ -330,8 +329,7 @@ OCR quality will suffer if the resolution of input images is not correct (since the range of pixel sizes that will be checked for possible fonts will also be incorrect). -PDF optimization ----------------- +## PDF optimization By default OCRmyPDF will attempt to perform lossless optimizations on the images inside PDFs after OCR is complete. Optimization is performed @@ -339,40 +337,9 @@ even if no OCR text is found. The `--optimize N` (short form `-O`) argument controls optimization, where `N` ranges from 0 to 3 inclusive, analogous to the optimization -levels in the GCC compiler. +levels in the GCC compiler. `-O1` is the default. -:::{list-table} ---- -widths: auto -header-rows: 1 ---- - -* - Level - - Comments -* - ``--optimize=0`` - - Disables optimization. -* - ``--optimize 1`` - - Enables lossless optimizations, such as transcoding images to more - efficient formats. Also compress other uncompressed objects in the - PDF and enables the more efficient "object streams" within the PDF. - (If ``--jbig2-lossy`` is issued, then lossy JBIG2 optimization is used. - The decision to use lossy JBIG2 is separate from standard optimization - settings.) -* - ``--optimize 2`` - - All of the above, and enables lossy optimizations and color quantization. -* - ``--optimize 3`` - - All of the above, and enables more aggressive optimizations and targets lower image quality. -::: - -Optimization is improved when a JBIG2 encoder is available and when -`pngquant` is installed. If either of these components are missing, then -some types of images cannot be optimized. - -The types of optimization available may expand over time. By default, -OCRmyPDF compresses data streams inside PDFs, and will change -inefficient compression modes to more modern versions. A program like -`qpdf` can be used to change encodings, e.g. to inspect the internals -for a PDF. +For further details, see the section on [PDF optimization](optimizer). ```bash ocrmypdf --optimize 3 in.pdf out.pdf # Make it small diff --git a/docs/optimizer.md b/docs/optimizer.md index aeda78a8..5c7b28cd 100644 --- a/docs/optimizer.md +++ b/docs/optimizer.md @@ -25,17 +25,23 @@ header-rows: 1 - Disable most optimizations. * - ``--optimize 1`` (default) - ``-O1`` - - Safe and lossless optimizations. + - Enables lossless optimizations, such as transcoding images to more + efficient formats. Also compress other uncompressed objects in the + PDF and enables the more efficient "object streams" within the PDF. + (If ``--jbig2-lossy`` is issued, then lossy JBIG2 optimization is used. + The decision to use lossy JBIG2 is separate from standard optimization + settings.) * - ``--optimize 2`` - ``-O2`` - - Safe and lossy optimizations. + - All of the above, and enables lossy optimizations and color quantization. * - ``--optimize 3`` - ``-O3`` - - Aggressive lossy optimizations. + - All of the above, and enables more aggressive optimizations and targets lower + image quality. ::: The exact type of optimizations performed will vary over time, and -depend on the availability of third-party tools. +depend on what third party tools are installed. Despite optimizations, OCRmyPDF might still increase the overall file size, since it must embed information about the recognized text, and @@ -83,8 +89,13 @@ objects more aggressively. ## Lossy optimizations -At optimization level `-O2` and `-O3`, OCRmyPDF will some attempt lossy -image optimization. +At optimization level `-O1`, `-O2` and `-O3`, OCRmyPDF will some attempt +loss image optimization. + +If Ghostscript is used to create a PDF/A (the default), Ghostscript will +optimize some images by converting them to JPEG, which are lossy. If +`--output-type pdf` is used, there are no lossy optimizations. Ghostscript's +JPEG conversion is quite safe. If `pngquant` is installed, OCRmyPDF will use it to perform quantize paletted images to reduce their size. From 3304498bdc7d70028d31fa53261cc6f5d7f1a530 Mon Sep 17 00:00:00 2001 From: "James R. Barlow" Date: Thu, 17 Apr 2025 15:43:36 -0700 Subject: [PATCH 5/5] Fix some anchors and markdown quirks --- docs/advanced.md | 1 - docs/cloud.md | 4 ++-- docs/conf.py | 12 +++--------- docs/introduction.md | 7 ------- docs/pdfsecurity.md | 2 +- 5 files changed, 6 insertions(+), 20 deletions(-) diff --git a/docs/advanced.md b/docs/advanced.md index 505067b5..65aacfc2 100644 --- a/docs/advanced.md +++ b/docs/advanced.md @@ -401,7 +401,6 @@ stable user interface. They may be imported from ``` (tmpdir)= - ## Changing temporary storage location OCRmyPDF generates many temporary files during processing. diff --git a/docs/cloud.md b/docs/cloud.md index 520df176..612ddeed 100644 --- a/docs/cloud.md +++ b/docs/cloud.md @@ -1,7 +1,7 @@ % SPDX-FileCopyrightText: 2025 James R. Barlow % SPDX-License-Identifier: CC-BY-SA-4.0 -{#ocr-service} +(ocr-service)= # Online deployments @@ -53,7 +53,7 @@ depending on the command line given. A rule of thumb would be to allow cloud servers or small VM partitions should be provisioned with plenty of extra space, if say, a 500 page file might be sent. -To change the temporary directory, see [tmpdir](advanced#tmpdir). +To change the temporary directory, see [tmpdir](#tmpdir). On Amazon Web Services or other cloud vendors, consider setting your temporary directory to [empheral diff --git a/docs/conf.py b/docs/conf.py index 301154ee..be811169 100755 --- a/docs/conf.py +++ b/docs/conf.py @@ -26,9 +26,7 @@ # -- General configuration ------------------------------------------------ -# If your documentation needs a minimal Sphinx version, state it here. -# -# needs_sphinx = '1.0' +needs_sphinx = '8' import datetime @@ -58,10 +56,6 @@ templates_path = ['_templates'] # The suffix(es) of source filenames. source_suffix = {'.rst': 'restructuredtext', '.md': 'markdown', '.txt': 'markdown'} -# The encoding of source files. -# -# source_encoding = 'utf-8-sig' - # The master toctree document. master_doc = 'index' @@ -70,8 +64,8 @@ project = 'ocrmypdf' year = str(datetime.date.today().year) copyright = ( - f'{year}, James R. Barlow. ', - 'Licensed under Creative Commons Attribution-ShareAlike 4.0.', + f'{year}, James R. Barlow. ' + + 'Licensed under Creative Commons Attribution-ShareAlike 4.0' ) author = 'James R. Barlow' diff --git a/docs/introduction.md b/docs/introduction.md index 45c38fc7..acc5c9d1 100644 --- a/docs/introduction.md +++ b/docs/introduction.md @@ -1,10 +1,3 @@ ---- -substitutions: - image: |- - ```{image} images/bitmap_vs_svg.svg - ``` ---- - % SPDX-FileCopyrightText: 2022 James R. Barlow % SPDX-License-Identifier: CC-BY-SA-4.0 diff --git a/docs/pdfsecurity.md b/docs/pdfsecurity.md index 73eb628e..4e0edfd1 100644 --- a/docs/pdfsecurity.md +++ b/docs/pdfsecurity.md @@ -1,4 +1,4 @@ -{#security} +(security)= # PDF security issues