Compare commits
15
Commits
v4.2.3
..
continuous
| Author | SHA1 | Date | |
|---|---|---|---|
 FPille
|
b8fcd7cf83 | ||
|
FPille
|
0bcc5dcabb | ||
|
FPille
|
9f74f306e1 | ||
|
FPille
|
65bf748d59 | ||
|
FPille
|
65dba03703 | ||
|
FPille
|
cb1126b743 | ||
|
FPille
|
8ef928fcdd | ||
|
FPille
|
67fa41c39a | ||
|
FPille
|
1e14c2101f | ||
|
FPille
|
7f12775032 | ||
|
FPille
|
d3bee93ed5 | ||
|
FPille
|
7409cbed29 | ||
  FrankandGitHub
|
55a44f823a | ||
|
FrankandGitHub
|
8cd87bd26f | ||
|
FPille
|
03932e877a |
@@ -1,31 +0,0 @@
|
||||
*.ipynb
|
||||
*.pdf
|
||||
*.pyc
|
||||
*.rst
|
||||
*.sublime*
|
||||
*/*.pyc
|
||||
*/*/*.pyc
|
||||
*/*/*/*.pyc
|
||||
*/*/*/*/*.pyc
|
||||
*/*/*/*/*/*.pyc
|
||||
*/*/*/*/*/*/*.pyc
|
||||
*/*/*/*/*/*/*/*.pyc
|
||||
.cache/
|
||||
.git/
|
||||
.ipynb_checkpoints/
|
||||
.ruffus_history.sqlite
|
||||
bin/
|
||||
build/
|
||||
dist/
|
||||
htmlcov/
|
||||
include/
|
||||
lib/
|
||||
MANIFEST.in
|
||||
ocrmypdf.egg-info/
|
||||
staging/
|
||||
tests/cache/
|
||||
tests/output/
|
||||
tests/resources/private/
|
||||
tmp/
|
||||
venv-3.4/
|
||||
venv-3.5/
|
||||
@@ -1 +0,0 @@
|
||||
ref-names: $Format:%D$
|
||||
@@ -1,10 +0,0 @@
|
||||
# Always use Unix convention for new lines
|
||||
* text eol=lf
|
||||
|
||||
# These files are binary and should be left untouched
|
||||
# (binary is a macro for -text -diff)
|
||||
*.jar binary
|
||||
*.pdf binary
|
||||
*.PDF binary
|
||||
|
||||
.git_archival.txt export-subst
|
||||
@@ -1,3 +0,0 @@
|
||||
Please include the command line and (if needed) a test file with your issue report.
|
||||
|
||||
If possible, please use a test file that we can include in future test cases (no personal information, no copyrighted material).
|
||||
-30
@@ -1,30 +0,0 @@
|
||||
# Development environment
|
||||
*.pyc
|
||||
*.sublime-*
|
||||
venv-*/
|
||||
pyvenv.cfg
|
||||
|
||||
# Package building
|
||||
*.egg-info/
|
||||
.cache/
|
||||
.eggs/
|
||||
build/
|
||||
dist/
|
||||
wheelhouse/
|
||||
|
||||
# Automatically generated files
|
||||
ocrmypdf/lib/_*.py
|
||||
ocrmypdf/version.py
|
||||
|
||||
# Code coverage
|
||||
.coverage
|
||||
htmlcov/
|
||||
|
||||
# Testing
|
||||
log/
|
||||
/*.pdf
|
||||
.ipynb_checkpoints/
|
||||
tests/cache/
|
||||
tests/output/
|
||||
tests/resources/private/
|
||||
tmp/
|
||||
+22
-38
@@ -1,45 +1,29 @@
|
||||
|
||||
language: generic
|
||||
sudo: required
|
||||
dist: trusty
|
||||
language: python
|
||||
|
||||
cache: pip
|
||||
|
||||
cache:
|
||||
directories:
|
||||
- $HOME/.ccache
|
||||
- packages
|
||||
- tests/cache
|
||||
|
||||
python:
|
||||
- 3.4
|
||||
- 3.5
|
||||
|
||||
before_cache:
|
||||
- rm -f $HOME/.cache/pip/log/debug.log
|
||||
|
||||
before_install:
|
||||
# Ubuntu packages
|
||||
- sudo add-apt-repository ppa:vshn/ghostscript -y # for ghostscript 9.16 (trusty has 9.10)
|
||||
- sudo add-apt-repository ppa:heyarje/libav-11 -y # for libav11, which is for unpaper
|
||||
- sudo apt-get update -qq # must go after all add-apt-repo
|
||||
- sudo apt-get install -y ghostscript tesseract-ocr tesseract-ocr-deu tesseract-ocr-eng tesseract-ocr-fra qpdf poppler-utils libavformat56 libavcodec56 libavutil54 libffi-dev
|
||||
|
||||
# pip
|
||||
- pip install --upgrade pip
|
||||
|
||||
# Download, make and install unpaper (using ccache)
|
||||
- mkdir -p packages
|
||||
- "[ -f packages/unpaper_6.1-1.deb ] || wget -q https://dl.dropboxusercontent.com/u/28971240/unpaper_6.1-1.deb -O packages/unpaper_6.1-1.deb"
|
||||
- sudo dpkg -i packages/unpaper_6.1-1.deb
|
||||
|
||||
install:
|
||||
- pip install -r requirements.txt
|
||||
- pip install -r test_requirements.txt
|
||||
- sudo add-apt-repository ppa:heyarje/libav-11 -y
|
||||
- sudo add-apt-repository ppa:alex-p/tesseract-ocr -y
|
||||
- sudo add-apt-repository ppa:evl.ms/evil -y # for a newer version (2.5.0) of pngquant
|
||||
- sudo apt-get update -qq
|
||||
- sudo apt-get install libleptonica-dev -y # required to build jbig2enc
|
||||
- sudo apt-get install zlib1g-dev -y # required to build jbig2enc
|
||||
# - sudo apt-get install imagemagick -y # required to convert logo to desktop icon
|
||||
|
||||
script:
|
||||
- python setup.py clean
|
||||
- python setup.py install
|
||||
- python setup.py test
|
||||
- export OCRMYPDF_VERSION=8.3.2
|
||||
- bash build-appimage.sh
|
||||
# remove previous installed libraries to ensure that the tests use the libraries of the AppImage
|
||||
- sudo apt-get remove libleptonica-dev zlib1g-dev -y
|
||||
- bash test/test-appimage.sh
|
||||
- wget https://github.com/probonopd/uploadtool/raw/master/upload.sh
|
||||
|
||||
os:
|
||||
- linux
|
||||
after_success:
|
||||
- bash upload.sh OCRmyPDF*.AppImage
|
||||
|
||||
branches:
|
||||
except:
|
||||
# Do not build tags that we create when we upload to GitHub Releases
|
||||
- /^(?i:continuous)/
|
||||
|
||||
-91
@@ -1,91 +0,0 @@
|
||||
# OCRmyPDF
|
||||
#
|
||||
# VERSION 3.2
|
||||
FROM debian:stretch
|
||||
MAINTAINER James R. Barlow <jim@purplerock.ca>
|
||||
|
||||
# Add unprivileged user
|
||||
RUN useradd docker \
|
||||
&& mkdir /home/docker \
|
||||
&& chown docker:docker /home/docker
|
||||
|
||||
# Update system and install our dependencies
|
||||
# If this command takes too Docker hub's automated build will timeout,
|
||||
# so try it in portions
|
||||
RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||
locales \
|
||||
python3 \
|
||||
python3-pip \
|
||||
python3-venv \
|
||||
python3-reportlab \
|
||||
python3-pil \
|
||||
python3-wheel
|
||||
|
||||
RUN apt-get install -y --no-install-recommends \
|
||||
unpaper \
|
||||
qpdf \
|
||||
poppler-utils \
|
||||
tesseract-ocr \
|
||||
tesseract-ocr-deu tesseract-ocr-spa tesseract-ocr-eng tesseract-ocr-fra
|
||||
|
||||
RUN apt-get install -qy --no-install-recommends \
|
||||
libffi-dev \
|
||||
libpython3-dev \
|
||||
gcc
|
||||
|
||||
# Install Ghostscript from Debian sid to work around JPEG 2000 issue in
|
||||
# Debian stretch libgs9 or gs 9.16~dfsg-2.1
|
||||
|
||||
COPY ./share/etc-apt-sources.list /etc/apt/sources.list
|
||||
|
||||
RUN apt-get update && apt-get install -y ghostscript/sid
|
||||
|
||||
|
||||
# Enforce UTF-8
|
||||
# Borrowed from https://index.docker.io/u/crosbymichael/python/
|
||||
RUN dpkg-reconfigure locales && \
|
||||
locale-gen C.UTF-8 && \
|
||||
/usr/sbin/update-locale LANG=C.UTF-8
|
||||
ENV LC_ALL C.UTF-8
|
||||
|
||||
|
||||
# Set up a Python virtualenv and take all of the system packages, so we can
|
||||
# rely on the platform packages rather than importing GCC and compiling them
|
||||
RUN pyvenv /appenv \
|
||||
&& pyvenv --system-site-packages /appenv
|
||||
|
||||
COPY . /application/
|
||||
|
||||
# Replace stock Tesseract 3.04.00 font with improved sharp2.ttf that resolves
|
||||
# issues in many PDF viewers.
|
||||
# Discussion is in https://github.com/tesseract-ocr/tesseract/issues/182
|
||||
COPY ./share/sharp2.ttf /usr/share/tesseract-ocr/tessdata/pdf.ttf
|
||||
RUN chmod 644 /usr/share/tesseract-ocr/tessdata/pdf.ttf
|
||||
|
||||
# Set this here to force a docker version, allowing non-tagged versions to
|
||||
# be built
|
||||
# ENV SETUPTOOLS_SCM_PRETEND_VERSION=v3.3.0
|
||||
|
||||
# Install application and dependencies
|
||||
# In this arrangement Pillow and reportlab will be provided by the system
|
||||
# Even though ocrmypdf is locally present, pull from PyPI because
|
||||
# Dockerhub and setuptools_scm clash
|
||||
RUN . /appenv/bin/activate; \
|
||||
pip install --upgrade pip \
|
||||
&& pip install ocrmypdf \
|
||||
&& pip install --no-cache-dir -r /application/test_requirements.txt
|
||||
|
||||
# Remove the junk
|
||||
RUN apt-get remove -qy gcc
|
||||
RUN apt-get autoremove -y && apt-get clean -y
|
||||
RUN rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* /root/*
|
||||
|
||||
USER docker
|
||||
WORKDIR /home/docker
|
||||
|
||||
ENV OCRMYPDF_TEST_OUTPUT=/tmp/test-output
|
||||
ENV OCRMYPDF_SHARP_TTF=1
|
||||
|
||||
# Must use array form of ENTRYPOINT
|
||||
# Non-array form does not append other arguments, because that is "intuitive"
|
||||
ENTRYPOINT ["/application/docker-wrapper.sh"]
|
||||
@@ -1,16 +0,0 @@
|
||||
# OCRmyPDF polyglot
|
||||
#
|
||||
# VERSION 3.2
|
||||
FROM jbarlow83/ocrmypdf:latest
|
||||
MAINTAINER James R. Barlow <jim@purplerock.ca>
|
||||
|
||||
# Update system and install our dependencies
|
||||
USER root
|
||||
RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||
tesseract-ocr-all
|
||||
|
||||
USER docker
|
||||
|
||||
# Must use array form of ENTRYPOINT
|
||||
# Non-array form does not append other arguments, because that is "intuitive"
|
||||
ENTRYPOINT ["/application/docker-wrapper.sh"]
|
||||
-20
@@ -1,20 +0,0 @@
|
||||
Copyright (c) 2013-2016, The OCRmyPDF Authors
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a
|
||||
copy of this software and associated documentation files (the
|
||||
"Software"), to deal in the Software without restriction, including
|
||||
without limitation the rights to use, copy, modify, merge, publish,
|
||||
distribute, sublicense, and/or sell copies of the Software, and to
|
||||
permit persons to whom the Software is furnished to do so, subject to
|
||||
the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included
|
||||
in all copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
|
||||
OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
|
||||
IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
|
||||
CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
|
||||
TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
|
||||
SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
||||
-42
@@ -1,42 +0,0 @@
|
||||
# requirements
|
||||
include requirements.txt
|
||||
include test_requirements.txt
|
||||
include dev_requirements.txt
|
||||
|
||||
# git
|
||||
include .git_archival.txt
|
||||
|
||||
# docker
|
||||
include Dockerfile
|
||||
include Dockerfile.polyglot
|
||||
include .dockerignore
|
||||
|
||||
# tests
|
||||
include pytest.ini
|
||||
recursive-include tests *.jpg
|
||||
recursive-include tests *.pdf
|
||||
recursive-include tests *.py
|
||||
recursive-include tests *.rst
|
||||
recursive-include tests *.txt
|
||||
recursive-exclude tests/output *
|
||||
recursive-exclude tests/output_pageinfo *
|
||||
recursive-exclude tests/resources/private *
|
||||
recursive-exclude tests/cache *
|
||||
|
||||
# documentation
|
||||
include *.rst
|
||||
include pipeline.svg
|
||||
recursive-exclude .github *
|
||||
|
||||
# support files
|
||||
recursive-include ocrmypdf/data *
|
||||
recursive-include share *
|
||||
include *.py
|
||||
|
||||
# code
|
||||
recursive-include ocrmypdf *.py
|
||||
exclude ocrmypdf/lib/_leptonica.py
|
||||
include OCRmyPDF.sh
|
||||
include docker-wrapper.sh
|
||||
|
||||
|
||||
@@ -1,8 +0,0 @@
|
||||
#!/bin/sh
|
||||
##############################################################################
|
||||
# Copyright (c) 2013-14: fritz-hh from Github (https://github.com/fritz-hh)
|
||||
##############################################################################
|
||||
|
||||
echo "This script is deprecated. Use 'ocrmypdf' instead."
|
||||
|
||||
python3 -m ocrmypdf.main "$@"
|
||||
@@ -0,0 +1,40 @@
|
||||
# OCRmyPDF-AppImage [](https://travis-ci.com/FPille/OCRmyPDF-AppImage)
|
||||
[AppImage][APPIMAGE] for [OCRmyPDF][OCRMYPDF]
|
||||
|
||||
## Usage
|
||||
Download OCRmyPDF*.AppImage, make it executable and run it.
|
||||
```
|
||||
wget https://github.com/FPille/OCRmyPDF-AppImage/releases/download/continuous/OCRmyPDF-8.3.2-x86_64.AppImage
|
||||
chmod +x OCRmyPDF*.AppImage
|
||||
./OCRmyPDF*.AppImage --help
|
||||
```
|
||||
|
||||
Beside OCRmyPDF additional command line programs can be run with this AppImage like:
|
||||
* ghostscript
|
||||
* img2pdf
|
||||
* pngquant
|
||||
* python3.6
|
||||
* qpdf
|
||||
* tesseract
|
||||
* unpaper
|
||||
|
||||
Just use the program name as first parameter plus options:
|
||||
```
|
||||
./OCRmyPDF*.AppImage tesseract -v
|
||||
tesseract 4.1.0
|
||||
leptonica-1.76.0
|
||||
libjpeg 8d (libjpeg-turbo 1.3.0) : libpng 1.2.50 : libtiff 4.0.3 : zlib 1.2.11 : libwebp 0.4.0 : libopenjp2 2.3.0
|
||||
Found AVX2
|
||||
Found AVX
|
||||
Found SSE
|
||||
```
|
||||
Or create a symlink for the corresponding program:
|
||||
```
|
||||
ln -s OCRmyPDF*.AppImage tesseract
|
||||
./tesseract --list-langs
|
||||
```
|
||||
|
||||
|
||||
[APPIMAGE]: https://appimage.org
|
||||
[OCRMYPDF]: https://github.com/jbarlow83/OCRmyPDF
|
||||
|
||||
-374
@@ -1,374 +0,0 @@
|
||||
OCRmyPDF
|
||||
========
|
||||
|
||||
OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to
|
||||
be searched.
|
||||
|
||||
Main features
|
||||
-------------
|
||||
|
||||
- Generates a searchable
|
||||
`PDF/A <https://en.wikipedia.org/?title=PDF/A>`_ file from a regular PDF
|
||||
- Places OCR text accurately below the image to ease copy / paste
|
||||
- Keeps the exact resolution of the original embedded images
|
||||
- When possible, inserts OCR information as a "lossless" operation without rendering vector information
|
||||
- Keeps file size about the same
|
||||
- If requested deskews and/or cleans the image before performing OCR
|
||||
- Validates input and output files
|
||||
- Provides debug mode to enable easy verification of the OCR results
|
||||
- Processes pages in parallel when more than one CPU core is
|
||||
available
|
||||
- Uses `Tesseract OCR <https://github.com/tesseract-ocr/tesseract>`_ engine
|
||||
- Supports the `39 languages <https://code.google.com/p/tesseract-ocr/downloads/list>`_ recognized by Tesseract
|
||||
- Battle-tested on thousands of PDFs, a test suite and continuous integration
|
||||
|
||||
For details: please consult the `release notes <RELEASE_NOTES.rst>`_.
|
||||
|
||||
Motivation
|
||||
----------
|
||||
|
||||
I searched the web for a free command line tool to OCR PDF files on
|
||||
Linux/UNIX: I found many, but none of them were really satisfying.
|
||||
|
||||
- Either they produced PDF files with misplaced text under the image (making copy/paste impossible)
|
||||
- Or they did not handle accents and multilingual characters
|
||||
- Or they changed the resolution of the embedded images
|
||||
- Or they generated ridiculously large PDF files
|
||||
- Or they crashed when trying to OCR some of my PDF files
|
||||
- Or they did not produce valid PDF files (even though they were readable with my current PDF reader)
|
||||
- On top of that none of them produced PDF/A files (format dedicated for long time storage)
|
||||
|
||||
... so I decided to develop my own tool (using various existing scripts
|
||||
as an inspiration)
|
||||
|
||||
Installation
|
||||
------------
|
||||
|
||||
Download OCRmyPDF here: https://github.com/jbarlow83/OCRmyPDF/releases
|
||||
|
||||
These steps describe how to install OCRmyPDF on your system.
|
||||
|
||||
- `Installing on Debian and Ubuntu`_ (Debian stretch and Ubuntu 16.10 or later)
|
||||
- `Installing the Docker image`_
|
||||
- `Installing on Mac OS X`_
|
||||
- `Installing on Ubuntu 14.04 LTS`_
|
||||
- Installing and running on `Windows`_ using the Docker image
|
||||
|
||||
If you prefer to install from source or install OCRmyPDF to a Python virtual environment, see steps for `Installing HEAD revision from sources`_.
|
||||
|
||||
.. _Windows: `Installing on Windows`_
|
||||
|
||||
|
||||
Installing on Debian and Ubuntu
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
Users of Debian 9 or later or Ubuntu 16.10 or later may simply
|
||||
``apt-get install ocrmypdf``.
|
||||
|
||||
.. _Docker:
|
||||
|
||||
Installing the Docker image
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
For many users, installing the Docker image will be easier than installing all of OCRmyPDF's dependencies. For Windows, it is the only option.
|
||||
|
||||
If you have `Docker <https://docs.docker.com/>`_ installed on your system, you can install
|
||||
a Docker image of the latest release.
|
||||
|
||||
Follow the Docker installation instructions for your platform. If you can run this command
|
||||
successfully, your system is ready to download and execute the image:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
docker run hello-world
|
||||
|
||||
OCRmyPDF will use all available CPU cores. By default, the VirtualBox machine instance on Windows and OS X has only a single CPU core enabled. Use the VirtualBox Manager to determine the name of your Docker engine host, and then follow these optional steps to enable multiple CPUs:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
# Optional step for Mac OS X users
|
||||
docker-machine stop "yourVM"
|
||||
VBoxManage modifyvm "yourVM" --cpus 2 # or whatever number of core is desired
|
||||
docker-machine start "yourVM"
|
||||
eval $(docker-machine env "yourVM")
|
||||
|
||||
Assuming you have a Docker engine running somewhere, you can run these commands to download
|
||||
the image:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
docker pull jbarlow83/ocrmypdf
|
||||
|
||||
Then tag it to give a more convenient name, just ocrmypdf:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
docker tag jbarlow83/ocrmypdf ocrmypdf
|
||||
|
||||
This image contains language packs for English, French, Spanish and German. The alternative "polyglot" image provides `all available language packs <https://github.com/tesseract-ocr/tesseract/blob/master/doc/tesseract.1.asc#languages>`_:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
# Alternative step: If you need all language packs
|
||||
docker pull jbarlow83/ocrmypdf-polyglot
|
||||
docker tag jbarlow83/ocrmypdf-polyglot ocrmypdf
|
||||
|
||||
You can then run ocrmypdf using the command:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
docker run ocrmypdf --help
|
||||
|
||||
To execute the OCRmyPDF on a local file, you must `provide a writable volume to the Docker image <https://docs.docker.com/userguide/dockervolumes/>`_, such as this in this template:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
docker run -v "$(pwd):/home/docker" <other docker arguments> ocrmypdf <your arguments to ocrmypdf>
|
||||
|
||||
In this worked example, the current working directory contains an input file called ``test.pdf`` and the output will go to ``output.pdf``:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
docker run -v "$(pwd):/home/docker" ocrmypdf --skip-text test.pdf output.pdf
|
||||
|
||||
Note that ``ocrmypdf`` has its own separate ``-v VERBOSITYLEVEL`` argument to control debug verbosity. All Docker arguments should before the ``ocrmypdf`` image name and all arguments to ``ocrmypdf`` should be listed after.
|
||||
|
||||
|
||||
Installing on Mac OS X
|
||||
~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
These instructions probably work on all Mac OS X versions later than 10.7 (Lion). OCRmyPDF is known to work on Yosemite and El Capitan, and regularly tested on El Capitan.
|
||||
|
||||
If it's not already present, `install Homebrew <http://brew.sh/>`_.
|
||||
|
||||
Update Homebrew:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
brew update
|
||||
|
||||
Install or upgrade the required Homebrew packages, if any are missing:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
brew install libpng openjpeg jbig2dec libtiff # image libraries
|
||||
brew install qpdf
|
||||
brew install ghostscript
|
||||
brew install python3
|
||||
brew install libxml2 libffi leptonica
|
||||
brew install unpaper # optional
|
||||
|
||||
Install the required Tesseract OCR engine with the language packs you plan to use:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
brew install tesseract # Option 1: for English, French, German, Spanish
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
brew install tesseract --with-all-languages # Option 2: for all language packs
|
||||
|
||||
Update the homebrew pip and install Pillow:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
pip3 install --upgrade pip
|
||||
pip3 install --upgrade pillow
|
||||
|
||||
You can then install OCRmyPDF from PyPI:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
pip3 install ocrmypdf
|
||||
|
||||
The command line program should now be available:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
ocrmypdf --help
|
||||
|
||||
Installing on Ubuntu 14.04 LTS
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
Installing on Ubuntu 14.04 LTS (trusty) is more difficult than some other options, because of bugs in Python package installation.
|
||||
|
||||
Add new "apt" repositories needed for backports of Ghostscript 9.16 and libav-11, which supports unpaper 6.1. This will replace Ghostscript on your system.
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
sudo add-apt-repository ppa:vshn/ghostscript -y
|
||||
sudo add-apt-repository ppa:heyarje/libav-11 -y
|
||||
|
||||
Update apt-get:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
sudo apt-get update
|
||||
sudo apt-get upgrade
|
||||
|
||||
Install system dependencies:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
sudo apt-get install \
|
||||
zlib1g-dev \
|
||||
libjpeg-dev \
|
||||
libffi-dev \
|
||||
libavformat56 libavcodec56 libavutil54 \
|
||||
ghostscript \
|
||||
tesseract-ocr \
|
||||
qpdf \
|
||||
python3-pip \
|
||||
python3-pil \
|
||||
python3-pytest \
|
||||
python3-reportlab
|
||||
|
||||
If you wish install OCRmyPDF to the system Python, then install as follows (note this installs new packages
|
||||
into your system Python, which could interfere with other programs):
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
sudo pip3 install ocrmypdf
|
||||
|
||||
If you wish to install OCRmyPDF to a virtual environment to isolate the system Python, you can
|
||||
follow these steps. This includes a workaround `for a known, unresolved issue in Ubuntu 14.04's ensurepip
|
||||
package <http://www.thefourtheye.in/2014/12/Python-venv-problem-with-ensurepip-in-Ubuntu.html>`_:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
sudo apt-get install python3-venv
|
||||
python3 -m venv venv-ocrmypdf --without-pip
|
||||
source venv-ocrmypdf/bin/activate
|
||||
wget -O - -o /dev/null https://bootstrap.pypa.io/get-pip.py | python
|
||||
deactivate
|
||||
python3 -m venv --system-site-packages venv-ocrmypdf
|
||||
source venv-ocrmypdf/bin/activate
|
||||
pip install ocrmypdf
|
||||
|
||||
These installation instructions omit the optional dependency ``unpaper``, which is only available at version 0.4.2 in Ubuntu 14.04. The author could not find a backport of ``unpaper`` and is not motivated to figure how to set up a Ubuntu PPA to distribute it. You can create a .deb package to do the job of installing unpaper 6.1 (for x86 64-bit only):
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
wget -q https://dl.dropboxusercontent.com/u/28971240/unpaper_6.1-1.deb -O unpaper_6.1-1.deb
|
||||
sudo dpkg -i unpaper_6.1-1.deb
|
||||
|
||||
|
||||
Installing on Windows
|
||||
~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
Direct installation on Windows is not possible. Install the _`Docker` container as described above. Ensure that your command prompt can run the docker "hello world" container.
|
||||
|
||||
Running on Windows
|
||||
~~~~~~~~~~~~~~~~~~
|
||||
|
||||
The command line syntax to run ocrmypdf from a command prompt will resemble:
|
||||
|
||||
.. code-block:: bat
|
||||
|
||||
docker run -v /c/Users/sampleuser:/home/docker ocrmypdf --skip-text test.pdf output.pdf
|
||||
|
||||
where /c/Users/sampleuser is a Unix representation of the Windows path C:\\Users\\sampleuser, assuming a user named "sampleuser" is running ocrmypdf on a file in their home directory, and the files "test.pdf" and "output.pdf" are in the sampleuser folder. The Windows user must have read and write permissions.
|
||||
|
||||
Installing HEAD revision from sources
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
If you have ``git`` and ``python3.4`` or ``python3.5`` installed, you can install from source. When the ``pip`` installer runs,
|
||||
it will alert you if dependencies are missing.
|
||||
|
||||
To install the HEAD revision from sources in the current Python 3 environment:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
pip3 install git+https://github.com/jbarlow83/OCRmyPDF.git
|
||||
|
||||
Or, to install in `development mode <https://pythonhosted.org/setuptools/setuptools.html#development-mode>`_, allowing customization of OCRmyPDF, use the ``-e`` flag:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
pip3 install -e git+https://github.com/jbarlow83/OCRmyPDF.git
|
||||
|
||||
On certain Linux distributions such as Ubuntu, you may need to use
|
||||
run the install command as superuser:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
sudo pip3 install [-e] git+https://github.com/jbarlow83/OCRmyPDF.git
|
||||
|
||||
Note that this will alter your system's Python distribution. If you prefer
|
||||
to not install as superuser, you can install the package in a Python virtual environment:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
git clone -b master https://github.com/jbarlow83/OCRmyPDF.git
|
||||
python3 -m venv
|
||||
source venv/bin/activate
|
||||
cd OCRmyPDF
|
||||
pip3 install .
|
||||
|
||||
However, ``ocrmypdf`` will only be accessible on the system PATH after
|
||||
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.
|
||||
|
||||
Languages
|
||||
---------
|
||||
|
||||
OCRmyPDF uses Tesseract for OCR, and relies on its language packs. For Linux users,
|
||||
you can often find packages that provide language packs:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
# Display a list of all Tesseract language packs
|
||||
apt-cache search tesseract-ocr
|
||||
|
||||
# Debian/Ubuntu users
|
||||
sudo apt-get install tesseract-ocr-chi-sim # Example: Install Chinese Simplified language back
|
||||
|
||||
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.
|
||||
|
||||
Support
|
||||
-------
|
||||
|
||||
Once ocrmypdf is installed, the built-in help which explains the command syntax and options can be accessed via:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
ocrmypdf --help
|
||||
|
||||
The `Wiki <https://github.com/jbarlow83/OCRmyPDF/wiki>`_ page also contains some tips and suggests.
|
||||
|
||||
If you detect an issue, please:
|
||||
|
||||
- Check whether your issue is already known
|
||||
- If no problem report exists on github, please create one here:
|
||||
https://github.com/jbarlow83/OCRmyPDF/issues
|
||||
- Describe your problem thoroughly
|
||||
- Append the console output of the script when running the debug mode
|
||||
(``-v 1`` option)
|
||||
- If possible provide your input PDF file as well as the content of the
|
||||
temporary folder (using a file sharing service like Dropbox)
|
||||
|
||||
Press & Media
|
||||
-------------
|
||||
|
||||
- `c't 1-2014, page 59 <http://heise.de/-2279695>`_:
|
||||
Detailed presentation of OCRmyPDF v1.0 in the leading German IT
|
||||
magazine c't
|
||||
- `heise Open Source, 09/2014: Texterkennung mit
|
||||
OCRmyPDF <http://heise.de/-2356670>`_
|
||||
|
||||
Disclaimer
|
||||
----------
|
||||
|
||||
The software is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
|
||||
CONDITIONS OF ANY KIND, either express or implied.
|
||||
@@ -1,410 +0,0 @@
|
||||
RELEASE NOTES
|
||||
=============
|
||||
|
||||
OCRmyPDF uses `semantic versioning <http://semver.org/>`_.
|
||||
|
||||
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 (#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 #82
|
||||
|
||||
- Fixes an issue where, with certain settings, monochrome images in PDFs would be converted to 8-bit grayscale, increasing file size (#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
|
||||
- Fix 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. (#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) (#49)
|
||||
|
||||
|
||||
Changes
|
||||
-------
|
||||
|
||||
- Logging output is now much easier to read
|
||||
- ``--deskew`` is now performed by Leptonica instead of unpaper (#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 OS X 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
|
||||
|
||||
.. _ruffus: http://www.ruffus.org.uk/index.html
|
||||
.. _parallel: https://www.gnu.org/software/parallel/
|
||||
.. _ImageMagick: http://www.imagemagick.org/script/index.php
|
||||
.. _MuPDF: http://mupdf.com/docs/
|
||||
.. _qpdf: http://qpdf.sourceforge.net/
|
||||
.. _Unpaper: https://github.com/Flameeyes/unpaper
|
||||
.. _JHOVE: http://jhove.sourceforge.net/
|
||||
|
||||
Release candidates
|
||||
------------------
|
||||
|
||||
- rc9:
|
||||
|
||||
- fix issue #118: report error if ghostscript iccprofiles are missing
|
||||
- fixed another issue related to #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>`_.
|
||||
Executable
+105
@@ -0,0 +1,105 @@
|
||||
#! /bin/bash
|
||||
|
||||
HERE="$(dirname "$(readlink -f "${0}")")"
|
||||
|
||||
export PATH="$HERE/usr/bin:$HERE/usr/local/bin:$HERE/usr/python/bin:$PATH"
|
||||
export LD_PRELOAD="$HERE/usr/lib/liblept.so.5"
|
||||
export LD_LIBRARY_PATH="$HERE/usr/lib:$HERE/usr/lib/x86_64-linux-gnu:$LD_LIBRARY_PATH"
|
||||
export TESSDATA_PREFIX="$HERE/usr/share/tesseract-ocr/4.00/tessdata"
|
||||
export GS_LIB="$HERE/usr/share/ghostscript/9.26/lib:$HERE/usr/share/ghostscript/9.26/Resource:$HERE/usr/share/ghostscript/9.26/Resource/Init"
|
||||
|
||||
# Allow the AppImage to be symlinked to e.g., /usr/bin/commandname
|
||||
# or called with ./Some*.AppImage commandname ...
|
||||
# refer to https://github.com/AppImage/AppImageKit/wiki/Bundling-command-line-tools
|
||||
|
||||
if [ ! -z "$APPIMAGE" ] ; then
|
||||
BINARY_NAME=$(basename "$ARGV0")
|
||||
else
|
||||
BINARY_NAME=$(basename "$0")
|
||||
export APPDIR="$HERE" # required for the wrapper scripts of linuxdeploy-plugin-python
|
||||
fi
|
||||
|
||||
usage() {
|
||||
echo "
|
||||
==============================================================================
|
||||
AppImage for OCRmyPDF
|
||||
==============================================================================
|
||||
OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be
|
||||
searched or copy-pasted.
|
||||
|
||||
usage:
|
||||
$ARGV0 [ocrmypdf] [--help] [--list-programs]
|
||||
[--list-licenses] [--show-license]
|
||||
|
||||
ocrmypdf execute OCRmyPDF
|
||||
|
||||
--help show this help message
|
||||
|
||||
--list-programs list all programs contained in this AppImage
|
||||
|
||||
--list-licenses list all licenses contained in this AppImage
|
||||
|
||||
--show-license [LICENSE] show content of license file
|
||||
"
|
||||
}
|
||||
|
||||
if [ "$1" == "--help" ] ; then
|
||||
usage
|
||||
exit $?
|
||||
fi
|
||||
|
||||
if [ "$1" == "--list-programs" ] ; then
|
||||
pushd "$HERE"
|
||||
echo ""
|
||||
echo "Run \"$ARGV0\" with one of the following arguments to run the respective program."
|
||||
echo ""
|
||||
find . -type f -perm /111 ! -path '*/lib/*' -execdir basename {} ";" | sort -u | column
|
||||
echo ""
|
||||
exit $?
|
||||
fi
|
||||
|
||||
if [ "$1" == "--list-licenses" ] ; then
|
||||
pushd "$HERE"
|
||||
echo ""
|
||||
echo "Run \"$ARGV0\" with one of the following arguments to display the respective license file."
|
||||
echo ""
|
||||
find . -type f \( ! -path '*/tesseract-ocr-*' -o -path '*/tesseract-ocr-eng/*' \) \
|
||||
\( -iname "license*" -o -iname "*copyright*" -o -iname "*copying*" \) -printf "--show-license %P\n" | sort | column
|
||||
echo ""
|
||||
exit $?
|
||||
fi
|
||||
|
||||
if [ "$1" == "--show-license" ] ; then
|
||||
pushd "$HERE"
|
||||
shift
|
||||
if [ -f "$1" ] ; then
|
||||
less -N "$1"
|
||||
exit $?
|
||||
else
|
||||
echo "\"$1\" is not a valid license file path."
|
||||
exit 1
|
||||
fi
|
||||
fi
|
||||
|
||||
if [ ! -z "$1" ] && [ -e "$HERE/bin/$1" ] ; then
|
||||
MAIN="$HERE/bin/$1" ; shift
|
||||
elif [ ! -z "$1" ] && [ -e "$HERE/usr/bin/$1" ] ; then
|
||||
MAIN="$HERE/usr/bin/$1" ; shift
|
||||
elif [ ! -z "$1" ] && [ -e "$HERE/usr/python/bin/$1" ] ; then
|
||||
MAIN="$HERE/usr/python/bin/$1" ; shift
|
||||
elif [ ! -z "$1" ] && [ -e "$HERE/usr/local/bin/$1" ] ; then
|
||||
MAIN="$HERE/usr/local/bin/$1" ; shift
|
||||
elif [ -e "$HERE/bin/$BINARY_NAME" ] ; then
|
||||
MAIN="$HERE/bin/$BINARY_NAME"
|
||||
elif [ -e "$HERE/usr/bin/$BINARY_NAME" ] ; then
|
||||
MAIN="$HERE/usr/bin/$BINARY_NAME"
|
||||
elif [ -e "$HERE/usr/python/bin/$BINARY_NAME" ] ; then
|
||||
MAIN="$HERE/usr/python/bin/$BINARY_NAME"
|
||||
elif [ -e "$HERE/usr/local/bin/$BINARY_NAME" ] ; then
|
||||
MAIN="$HERE/usr/local/bin/$BINARY_NAME"
|
||||
else
|
||||
usage
|
||||
exit $?
|
||||
fi
|
||||
|
||||
exec "${MAIN}" "$@"
|
||||
@@ -0,0 +1,120 @@
|
||||
#! /bin/bash
|
||||
|
||||
set -x
|
||||
set -e
|
||||
|
||||
# use RAM disk if possible
|
||||
if [ "$CI" == "" ] && [ -d /dev/shm ]; then
|
||||
TEMP_BASE=/dev/shm
|
||||
else
|
||||
TEMP_BASE=/tmp
|
||||
fi
|
||||
|
||||
BUILD_DIR=$(mktemp -d -p "$TEMP_BASE" OCRmyPDF-AppImage-build-XXXXXX)
|
||||
|
||||
cleanup () {
|
||||
if [ -d "$BUILD_DIR" ]; then
|
||||
rm -rf "$BUILD_DIR"
|
||||
fi
|
||||
}
|
||||
|
||||
trap cleanup EXIT
|
||||
|
||||
# store repo root as variable
|
||||
REPO_ROOT=$(readlink -f "$(dirname "$(dirname "$0")")")
|
||||
OLD_CWD=$(readlink -f .)
|
||||
|
||||
pushd "$BUILD_DIR"
|
||||
|
||||
mkdir -p AppDir
|
||||
mkdir -p PackageDir
|
||||
mkdir -p jbig2
|
||||
|
||||
# download linuxdeploy AppImage and linuxdeploy-plugin-python AppImage
|
||||
wget https://github.com/TheAssassin/linuxdeploy/releases/download/continuous/linuxdeploy-x86_64.AppImage
|
||||
# wget https://github.com/niess/linuxdeploy-plugin-python/releases/download/continuous/linuxdeploy-plugin-python-x86_64.AppImage
|
||||
|
||||
# use adapted linuxdeploy-plugin-python instead of the original one (otherwise OCRmyPDF breaks)
|
||||
wget https://github.com/FPille/linuxdeploy-plugin-python/releases/download/continuous/linuxdeploy-plugin-python-x86_64.AppImage
|
||||
|
||||
chmod +x linuxdeploy*.AppImage
|
||||
|
||||
|
||||
ARCH=$(uname -i)
|
||||
export ARCH
|
||||
|
||||
|
||||
# .desktop file
|
||||
cat > ocrmypdf.desktop <<\EOF
|
||||
[Desktop Entry]
|
||||
Name=ocrmypdf
|
||||
Type=Application
|
||||
Exec=ocrmypdf
|
||||
Icon=ocrmypdf
|
||||
Terminal=true
|
||||
Comment=OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
|
||||
Categories=Graphics;Scanning;OCR;
|
||||
EOF
|
||||
|
||||
|
||||
# download logo and convert it to desktop icon
|
||||
# requires Imagemagick (convert)
|
||||
wget https://raw.githubusercontent.com/jbarlow83/OCRmyPDF/master/docs/images/logo-social.png
|
||||
convert logo-social.png -resize 512x512\> -size 512x512 xc:white +swap -gravity center -composite ocrmypdf.png
|
||||
|
||||
|
||||
# download and intsall packages required by OCRmyPDF
|
||||
pushd PackageDir
|
||||
packages=(tesseract-ocr tesseract-ocr-all libavformat56 ghostscript qpdf pngquant)
|
||||
|
||||
for i in "${packages[@]}"
|
||||
do
|
||||
apt-get -d -o dir::cache="$PWD" -o Debug::NoLocking=1 --reinstall install "$i" -y
|
||||
done
|
||||
|
||||
wget -q 'https://www.dropbox.com/s/vaq0kbwi6e6au80/unpaper_6.1-1.deb?raw=1' -O unpaper_6.1-1.deb
|
||||
|
||||
find . -type f -name \*.deb -exec dpkg-deb -X {} "$BUILD_DIR"/AppDir \;
|
||||
popd
|
||||
|
||||
|
||||
# compile and install jbig2
|
||||
# requires libleptonica-dev, zlib1g-dev
|
||||
wget -q https://github.com/agl/jbig2enc/archive/0.29.tar.gz -O - | \
|
||||
tar xz -C jbig2 --strip-components=1
|
||||
pushd jbig2
|
||||
./autogen.sh
|
||||
./configure --prefix="$BUILD_DIR"/AppDir/usr
|
||||
make && make install
|
||||
popd
|
||||
|
||||
pushd "$BUILD_DIR"/AppDir
|
||||
# add some tools to AppDir
|
||||
#cp -f /usr/bin/column ./usr/bin/
|
||||
#cp -f /bin/less ./usr/bin/
|
||||
|
||||
# remove unnecessary data from AppDir
|
||||
[ -d bin ] && rm -rf ./bin
|
||||
[ -d etc ] && rm -rf ./etc
|
||||
[ -d var ] && rm -rf ./var
|
||||
popd
|
||||
|
||||
|
||||
# export LD_LIBRARY_PATH so that dependencies of shared libraries can be deployed by linuxdeploy-x86_64.AppImage
|
||||
export LD_LIBRARY_PATH="$BUILD_DIR/AppDir/usr/lib:$BUILD_DIR/AppDir/usr/lib/x86_64-linux-gnu:$LD_LIBRARY_PATH"
|
||||
|
||||
#OCRMYPDF_VERSION=8.3.2 # exported in .travis.yml file
|
||||
export PIP_REQUIREMENTS="ocrmypdf==$OCRMYPDF_VERSION"
|
||||
export VERSION="$OCRMYPDF_VERSION"
|
||||
export OUTPUT=OCRmyPDF-"$VERSION"-"$ARCH".AppImage
|
||||
export PYTHON_SOURCE=https://www.python.org/ftp/python/3.6.8/Python-3.6.8.tgz
|
||||
|
||||
./linuxdeploy-x86_64.AppImage --appdir AppDir --plugin python \
|
||||
-d ocrmypdf.desktop -i ocrmypdf.png \
|
||||
--custom-apprun "$REPO_ROOT"/appimage/AppRun.sh --output appimage
|
||||
|
||||
|
||||
# move AppImage back to old CWD
|
||||
mv "$OUTPUT" "$OLD_CWD"/
|
||||
|
||||
popd
|
||||
@@ -1,4 +0,0 @@
|
||||
check-manifest>=0.33
|
||||
setuptools-scm>=1.11.1
|
||||
twine>=1.8.1
|
||||
coverage>=4.2
|
||||
@@ -1,5 +0,0 @@
|
||||
#!/bin/bash
|
||||
|
||||
. /appenv/bin/activate
|
||||
cd /home/docker
|
||||
exec ocrmypdf "$@"
|
||||
@@ -1,30 +0,0 @@
|
||||
from enum import IntEnum
|
||||
import os
|
||||
from collections.abc import Iterable
|
||||
|
||||
|
||||
class ExitCode(IntEnum):
|
||||
ok = 0
|
||||
bad_args = 1
|
||||
input_file = 2
|
||||
missing_dependency = 3
|
||||
invalid_output_pdf = 4
|
||||
file_access_error = 5
|
||||
already_done_ocr = 6
|
||||
child_process_error = 7
|
||||
encrypted_pdf = 8
|
||||
other_error = 15
|
||||
ctrl_c = 130
|
||||
|
||||
|
||||
def get_program(name):
|
||||
envvar = 'OCRMYPDF_' + name.upper()
|
||||
return os.environ.get(envvar, name)
|
||||
|
||||
|
||||
def page_number(input_file):
|
||||
return int(os.path.basename(input_file)[0:6])
|
||||
|
||||
|
||||
def is_iterable_notstr(thing):
|
||||
return isinstance(thing, Iterable) and not isinstance(thing, str)
|
||||
File diff suppressed because it is too large
Load Diff
Binary file not shown.
@@ -1,61 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
# © 2015 James R. Barlow: github.com/jbarlow83
|
||||
|
||||
from tempfile import NamedTemporaryFile
|
||||
from subprocess import Popen, PIPE, check_call
|
||||
from shutil import copy
|
||||
from . import get_program
|
||||
from .pdfa import SRGB_ICC_PROFILE
|
||||
|
||||
|
||||
def rasterize_pdf(input_file, output_file, xres, yres, raster_device, log,
|
||||
pageno=1):
|
||||
with NamedTemporaryFile(delete=True) as tmp:
|
||||
args_gs = [
|
||||
get_program('gs'),
|
||||
'-dQUIET',
|
||||
'-dSAFER',
|
||||
'-dBATCH',
|
||||
'-dNOPAUSE',
|
||||
'-sDEVICE=%s' % raster_device,
|
||||
'-dFirstPage=%i' % pageno,
|
||||
'-dLastPage=%i' % pageno,
|
||||
'-o', tmp.name,
|
||||
'-r{0}x{1}'.format(str(xres), str(yres)),
|
||||
input_file
|
||||
]
|
||||
|
||||
p = Popen(args_gs, close_fds=True, stdout=PIPE, stderr=PIPE,
|
||||
universal_newlines=True)
|
||||
stdout, stderr = p.communicate()
|
||||
if stdout:
|
||||
log.debug(stdout)
|
||||
if stderr:
|
||||
log.error(stderr)
|
||||
|
||||
if p.returncode == 0:
|
||||
copy(tmp.name, output_file)
|
||||
else:
|
||||
log.error('Ghostscript rendering failed')
|
||||
|
||||
|
||||
def generate_pdfa(pdf_pages, output_file, threads=1):
|
||||
with NamedTemporaryFile(delete=True) as gs_pdf:
|
||||
args_gs = [
|
||||
get_program("gs"),
|
||||
"-dQUIET",
|
||||
"-dBATCH",
|
||||
"-dNOPAUSE",
|
||||
'-dNumRenderingThreads=' + str(threads),
|
||||
"-sDEVICE=pdfwrite",
|
||||
"-dAutoRotatePages=/None",
|
||||
"-sColorConversionStrategy=/RGB",
|
||||
"-sProcessColorModel=DeviceRGB",
|
||||
"-dJPEGQ=95",
|
||||
"-dPDFA=2",
|
||||
"-sPDFACompatibilityPolicy=2",
|
||||
"-sOutputFile=" + gs_pdf.name,
|
||||
]
|
||||
args_gs.extend(pdf_pages)
|
||||
check_call(args_gs)
|
||||
copy(gs_pdf.name, output_file)
|
||||
@@ -1,230 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
##############################################################################
|
||||
# Copyright (c) 2013-14: fritz-hh from Github
|
||||
# (https://github.com/fritz-hh)
|
||||
#
|
||||
# Copyright (c) 2010: Jonathan Brinley from Github
|
||||
# (https://github.com/jbrinley/HocrConverter)
|
||||
# Initial version by Jonathan Brinley, jonathanbrinley@gmail.com
|
||||
##############################################################################
|
||||
from reportlab.pdfgen.canvas import Canvas
|
||||
from reportlab.lib.units import inch
|
||||
from xml.etree import ElementTree
|
||||
from PIL import Image
|
||||
from collections import namedtuple
|
||||
import re
|
||||
import argparse
|
||||
|
||||
|
||||
Rect = namedtuple('Rect', ['x1', 'y1', 'x2', 'y2'])
|
||||
|
||||
|
||||
class HocrTransformError(Exception):
|
||||
pass
|
||||
|
||||
|
||||
class HocrTransform():
|
||||
|
||||
"""
|
||||
A class for converting documents from the hOCR format.
|
||||
For details of the hOCR format, see:
|
||||
http://docs.google.com/View?docid=dfxcv4vc_67g844kf
|
||||
"""
|
||||
|
||||
def __init__(self, hocrFileName, dpi):
|
||||
self.dpi = dpi
|
||||
self.boxPattern = re.compile(r'bbox((\s+\d+){4})')
|
||||
|
||||
self.hocr = ElementTree.parse(hocrFileName)
|
||||
|
||||
# if the hOCR file has a namespace, ElementTree requires its use to
|
||||
# find elements
|
||||
matches = re.match(r'({.*})html', self.hocr.getroot().tag)
|
||||
self.xmlns = ''
|
||||
if matches:
|
||||
self.xmlns = matches.group(1)
|
||||
|
||||
# get dimension in pt (not pixel!!!!) of the OCRed image
|
||||
self.width, self.height = None, None
|
||||
for div in self.hocr.findall(
|
||||
".//%sdiv[@class='ocr_page']" % (self.xmlns)):
|
||||
coords = self.element_coordinates(div)
|
||||
pt_coords = self.pt_from_pixel(coords)
|
||||
self.width = pt_coords.x2 - pt_coords.x1
|
||||
self.height = pt_coords.y2 - pt_coords.y1
|
||||
# there shouldn't be more than one, and if there is, we don't want
|
||||
# it
|
||||
break
|
||||
if self.width is None or self.height is None:
|
||||
raise HocrTransformError("hocr file is missing page dimensions")
|
||||
|
||||
def __str__(self):
|
||||
"""
|
||||
Return the textual content of the HTML body
|
||||
"""
|
||||
if self.hocr is None:
|
||||
return ''
|
||||
body = self.hocr.find(".//%sbody" % (self.xmlns))
|
||||
if body:
|
||||
return self._get_element_text(body)
|
||||
else:
|
||||
return ''
|
||||
|
||||
def _get_element_text(self, element):
|
||||
"""
|
||||
Return the textual content of the element and its children
|
||||
"""
|
||||
text = ''
|
||||
if element.text is not None:
|
||||
text += element.text
|
||||
for child in element.getchildren():
|
||||
text += self._get_element_text(child)
|
||||
if element.tail is not None:
|
||||
text += element.tail
|
||||
return text
|
||||
|
||||
def element_coordinates(self, element):
|
||||
"""
|
||||
Returns a tuple containing the coordinates of the bounding box around
|
||||
an element
|
||||
"""
|
||||
out = (0, 0, 0, 0)
|
||||
if 'title' in element.attrib:
|
||||
matches = self.boxPattern.search(element.attrib['title'])
|
||||
if matches:
|
||||
coords = matches.group(1).split()
|
||||
out = Rect._make(int(coords[n]) for n in range(4))
|
||||
return out
|
||||
|
||||
def pt_from_pixel(self, pxl):
|
||||
"""
|
||||
Returns the quantity in PDF units (pt) given quantity in pixels
|
||||
"""
|
||||
return Rect._make(
|
||||
(c / self.dpi * inch) for c in pxl)
|
||||
|
||||
def replace_unsupported_chars(self, s):
|
||||
"""
|
||||
Given an input string, returns the corresponding string that:
|
||||
- is available in the helvetica facetype
|
||||
- does not contain any ligature (to allow easy search in the PDF file)
|
||||
"""
|
||||
# The 'u' before the character to replace indicates that it is a
|
||||
# unicode character
|
||||
s = s.replace(u"fl", "fl")
|
||||
s = s.replace(u"fi", "fi")
|
||||
return s
|
||||
|
||||
def to_pdf(self, outFileName, imageFileName=None, showBoundingboxes=False,
|
||||
fontname="Helvetica", invisibleText=False):
|
||||
"""
|
||||
Creates a PDF file with an image superimposed on top of the text.
|
||||
Text is positioned according to the bounding box of the lines in
|
||||
the hOCR file.
|
||||
The image need not be identical to the image used to create the hOCR
|
||||
file.
|
||||
It can have a lower resolution, different color mode, etc.
|
||||
"""
|
||||
# create the PDF file
|
||||
# page size in points (1/72 in.)
|
||||
pdf = Canvas(
|
||||
outFileName, pagesize=(self.width, self.height), pageCompression=1)
|
||||
|
||||
# draw bounding box for each paragraph
|
||||
# light blue for bounding box of paragraph
|
||||
pdf.setStrokeColorRGB(0, 1, 1)
|
||||
# light blue for bounding box of paragraph
|
||||
pdf.setFillColorRGB(0, 1, 1)
|
||||
pdf.setLineWidth(0) # no line for bounding box
|
||||
for elem in self.hocr.findall(
|
||||
".//%sp[@class='%s']" % (self.xmlns, "ocr_par")):
|
||||
|
||||
elemtxt = self._get_element_text(elem).rstrip()
|
||||
if len(elemtxt) == 0:
|
||||
continue
|
||||
|
||||
pxl_coords = self.element_coordinates(elem)
|
||||
pt = self.pt_from_pixel(pxl_coords)
|
||||
|
||||
# draw the bbox border
|
||||
if showBoundingboxes:
|
||||
pdf.rect(
|
||||
pt.x1, self.height - pt.y2, pt.x2 - pt.x1, pt.y2 - pt.y1,
|
||||
fill=1)
|
||||
|
||||
# check if element with class 'ocrx_word' are available
|
||||
# otherwise use 'ocr_line' as fallback
|
||||
elemclass = "ocr_line"
|
||||
if self.hocr.find(
|
||||
".//%sspan[@class='ocrx_word']" % (self.xmlns)) is not None:
|
||||
elemclass = "ocrx_word"
|
||||
|
||||
# itterate all text elements
|
||||
# light green for bounding box of word/line
|
||||
pdf.setStrokeColorRGB(1, 0, 0)
|
||||
pdf.setLineWidth(0.5) # bounding box line width
|
||||
pdf.setDash(6, 3) # bounding box is dashed
|
||||
pdf.setFillColorRGB(0, 0, 0) # text in black
|
||||
for elem in self.hocr.findall(
|
||||
".//%sspan[@class='%s']" % (self.xmlns, elemclass)):
|
||||
|
||||
elemtxt = self._get_element_text(elem).rstrip()
|
||||
|
||||
elemtxt = self.replace_unsupported_chars(elemtxt)
|
||||
|
||||
if len(elemtxt) == 0:
|
||||
continue
|
||||
|
||||
pxl_coords = self.element_coordinates(elem)
|
||||
pt = self.pt_from_pixel(pxl_coords)
|
||||
|
||||
# draw the bbox border
|
||||
if showBoundingboxes:
|
||||
pdf.rect(
|
||||
pt.x1, self.height - pt.y2, pt.x2 - pt.x1, pt.y2 - pt.y1,
|
||||
fill=0)
|
||||
|
||||
text = pdf.beginText()
|
||||
fontsize = pt.y2 - pt.y1
|
||||
text.setFont(fontname, fontsize)
|
||||
if invisibleText:
|
||||
text.setTextRenderMode(3) # Invisible (indicates OCR text)
|
||||
|
||||
# set cursor to bottom left corner of bbox (adjust for dpi)
|
||||
text.setTextOrigin(pt.x1, self.height - pt.y2)
|
||||
|
||||
# scale the width of the text to fill the width of the bbox
|
||||
text.setHorizScale(
|
||||
100 * (pt.x2 - pt.x1) / pdf.stringWidth(
|
||||
elemtxt, fontname, fontsize))
|
||||
|
||||
# write the text to the page
|
||||
text.textLine(elemtxt)
|
||||
pdf.drawText(text)
|
||||
|
||||
# put the image on the page, scaled to fill the page
|
||||
if imageFileName is not None:
|
||||
pdf.drawImage(imageFileName, 0, 0,
|
||||
width=self.width, height=self.height)
|
||||
|
||||
# finish up the page and save it
|
||||
pdf.showPage()
|
||||
pdf.save()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser(description='Convert hocr file to PDF')
|
||||
parser.add_argument('-b', '--boundingboxes', action="store_true",
|
||||
default=False, help='Show bounding boxes borders')
|
||||
parser.add_argument('-r', '--resolution', type=int,
|
||||
default=300,
|
||||
help='Resolution of the image that was OCRed')
|
||||
parser.add_argument('-i', '--image', default=None,
|
||||
help='Path to the image to be placed above the text')
|
||||
parser.add_argument('hocrfile', help='Path to the hocr file to be parsed')
|
||||
parser.add_argument(
|
||||
'outputfile', help='Path to the PDF file to be generated')
|
||||
args = parser.parse_args()
|
||||
|
||||
hocr = HocrTransform(args.hocrfile, args.resolution)
|
||||
hocr.to_pdf(args.outputfile, args.image, args.boundingboxes)
|
||||
@@ -1,511 +0,0 @@
|
||||
#!/usr/bin/env python2
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# © 2013-15: jbarlow83 from Github (https://github.com/jbarlow83)
|
||||
#
|
||||
#
|
||||
# Use Leptonica to detect find and remove page skew. Leptonica uses the method
|
||||
# of differential square sums, which its author claim is faster and more robust
|
||||
# than the Hough transform used by ImageMagick.
|
||||
|
||||
from __future__ import print_function, absolute_import, division
|
||||
import argparse
|
||||
import sys
|
||||
import os
|
||||
import logging
|
||||
from tempfile import TemporaryFile
|
||||
from ctypes.util import find_library
|
||||
from .lib._leptonica import ffi
|
||||
from functools import lru_cache
|
||||
from enum import Enum
|
||||
|
||||
lept = ffi.dlopen(find_library('lept'))
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def stderr(*objs):
|
||||
"""Python 2/3 compatible print to stderr.
|
||||
"""
|
||||
print("leptonica.py:", *objs, file=sys.stderr)
|
||||
|
||||
|
||||
class LeptonicaErrorTrap(object):
|
||||
"""Context manager to trap errors reported by Leptonica.
|
||||
|
||||
Leptonica's error return codes are unreliable to the point of being
|
||||
almost useless. It does, however, write errors to stderr provided that is
|
||||
not disabled at its compile time. Fortunately this is done using error
|
||||
macros so it is very self-consistent.
|
||||
|
||||
This context manager redirects stderr to a temporary file which is then
|
||||
read and parsed for error messages. As a side benefit, debug messages
|
||||
from Leptonica are also suppressed.
|
||||
|
||||
"""
|
||||
def __enter__(self):
|
||||
self.tmpfile = TemporaryFile()
|
||||
|
||||
# Save the old stderr, and redirect stderr to temporary file
|
||||
self.old_stderr_fileno = os.dup(sys.stderr.fileno())
|
||||
os.dup2(self.tmpfile.fileno(), sys.stderr.fileno())
|
||||
return
|
||||
|
||||
def __exit__(self, exc_type, exc_value, traceback):
|
||||
# Restore old stderr
|
||||
os.dup2(self.old_stderr_fileno, sys.stderr.fileno())
|
||||
|
||||
# Get data from tmpfile (in with block to ensure it is closed)
|
||||
with self.tmpfile as tmpfile:
|
||||
tmpfile.seek(0) # Cursor will be at end, so move back to beginning
|
||||
leptonica_output = tmpfile.read().decode(errors='replace')
|
||||
|
||||
# If there are Python errors, let them bubble up
|
||||
if exc_type:
|
||||
logger.warning(leptonica_output)
|
||||
return False
|
||||
|
||||
# If there are Leptonica errors, wrap them in Python excpetions
|
||||
if 'Error' in leptonica_output:
|
||||
if 'image file not found' in leptonica_output:
|
||||
raise FileNotFoundError()
|
||||
if 'pixWrite: stream not opened' in leptonica_output:
|
||||
raise LeptonicaIOError()
|
||||
raise LeptonicaError(leptonica_output)
|
||||
|
||||
return False
|
||||
|
||||
|
||||
class LeptonicaError(Exception):
|
||||
pass
|
||||
|
||||
|
||||
class LeptonicaIOError(LeptonicaError):
|
||||
pass
|
||||
|
||||
|
||||
class RemoveColormap(Enum):
|
||||
to_binary = 0
|
||||
to_grayscale = 1
|
||||
to_full_color = 2
|
||||
based_on_src = 3
|
||||
|
||||
|
||||
class Pix:
|
||||
"""Wrapper around leptonica's PIX object.
|
||||
|
||||
Leptonica uses referencing counting on PIX objects. Also, many Leptonica
|
||||
functions return the original object with an increased reference count
|
||||
if the operation had no effect (for example, image skew was found to be 0).
|
||||
This has complications for memory management in Python. Whenever Leptonica
|
||||
returns a PIX object (new or old), we wrap it in this class, which
|
||||
registers it with the FFI garbage collector. pixDestroy() decrements the
|
||||
reference count and only destroys when the last reference is removed.
|
||||
|
||||
Leptonica's reference counting is not threadsafe. This class can be used
|
||||
in a threadsafe manner if a Python threading.Lock protects the data.
|
||||
"""
|
||||
|
||||
def __init__(self, pix):
|
||||
self._pix = ffi.gc(pix, Pix._pix_destroy)
|
||||
|
||||
def __repr__(self):
|
||||
if self._pix:
|
||||
s = "<leptonica.Pix image size={0}x{1} depth={2} at 0x{3:x}>"
|
||||
return s.format(self._pix.w, self._pix.h, self._pix.d,
|
||||
int(ffi.cast("intptr_t", self._pix)))
|
||||
else:
|
||||
return "<leptonica.Pix image NULL>"
|
||||
|
||||
def __getstate__(self):
|
||||
data = ffi.new('l_uint32 **')
|
||||
size = ffi.new('size_t *')
|
||||
|
||||
err = lept.pixSerializeToMemory(self._pix, data, size)
|
||||
if err != 0:
|
||||
raise LeptonicaIOError("pixSerializeToMemory")
|
||||
|
||||
char_data = ffi.cast('char *', data[0])
|
||||
|
||||
# Copy from C bytes to python bytes()
|
||||
data_bytes = ffi.buffer(char_data, size[0])[:]
|
||||
|
||||
# Can now free C bytes
|
||||
lept.lept_free(char_data)
|
||||
return dict(data=data_bytes)
|
||||
|
||||
def __setstate__(self, state):
|
||||
cdata_bytes = ffi.new('char[]', state['data'])
|
||||
cdata_uint32 = ffi.cast('l_uint32 *', cdata_bytes)
|
||||
|
||||
pix = lept.pixDeserializeFromMemory(
|
||||
cdata_uint32, len(state['data']))
|
||||
Pix.__init__(self, pix)
|
||||
|
||||
@property
|
||||
def width(self):
|
||||
return self._pix.w
|
||||
|
||||
@property
|
||||
def height(self):
|
||||
return self._pix.h
|
||||
|
||||
@property
|
||||
def depth(self):
|
||||
return self._pix.d
|
||||
|
||||
@property
|
||||
def size(self):
|
||||
return (self._pix.w, self._pix.h)
|
||||
|
||||
@property
|
||||
def info(self):
|
||||
return {'dpi': (self._pix.xres, self._pix.yres)}
|
||||
|
||||
@property
|
||||
def mode(self):
|
||||
"Return mode like PIL.Image"
|
||||
if self.depth == 1:
|
||||
return '1'
|
||||
elif self.depth >= 16:
|
||||
return 'RGB'
|
||||
elif not self._pix.colormap:
|
||||
return 'L'
|
||||
else:
|
||||
return 'P'
|
||||
|
||||
@classmethod
|
||||
def read(cls, filename):
|
||||
"""Load an image file into a PIX object.
|
||||
|
||||
Leptonica can load TIFF, PNM (PBM, PGM, PPM), PNG, and JPEG. If
|
||||
loading fails then the object will wrap a C null pointer.
|
||||
"""
|
||||
with LeptonicaErrorTrap():
|
||||
return cls(lept.pixRead(
|
||||
filename.encode(sys.getfilesystemencoding())))
|
||||
|
||||
def write_implied_format(
|
||||
self, filename, jpeg_quality=0, jpeg_progressive=0):
|
||||
"""Write pix to the filename, with the extension indicating format.
|
||||
|
||||
jpeg_quality -- quality (iff JPEG; 1 - 100, 0 for default)
|
||||
jpeg_progressive -- (iff JPEG; 0 for baseline seq., 1 for progressive)
|
||||
"""
|
||||
with LeptonicaErrorTrap():
|
||||
lept.pixWriteImpliedFormat(
|
||||
filename.encode(sys.getfilesystemencoding()),
|
||||
self._pix, jpeg_quality, jpeg_progressive)
|
||||
|
||||
def topil(self):
|
||||
"Returns a PIL.Image version of this Pix"
|
||||
from PIL import Image
|
||||
|
||||
with LeptonicaErrorTrap():
|
||||
pix_swapped = Pix(lept.pixEndianByteSwapNew(self._pix))
|
||||
|
||||
size = (pix_swapped._pix.wpl * 4, pix_swapped._pix.h)
|
||||
buf = ffi.buffer(pix_swapped._pix.data, size[0] * size[1])
|
||||
|
||||
im_raw = Image.frombytes(self.mode, size, buf, 'raw')
|
||||
|
||||
# Leptonica stores images in 32-bit words
|
||||
# Need to crop the any trailing amount
|
||||
box = (0, 0, self.width, self.height)
|
||||
im = im_raw.crop(box)
|
||||
|
||||
return im
|
||||
|
||||
def show(self):
|
||||
return self.topil().show()
|
||||
|
||||
def deskew(self, reduction_factor=0):
|
||||
"""Returns the deskewed pix object.
|
||||
|
||||
A clone of the original is returned when the algorithm cannot find a
|
||||
skew angle with sufficient confidence.
|
||||
|
||||
reduction_factor -- amount to downsample (0 for default) when searching
|
||||
for skew angle
|
||||
"""
|
||||
with LeptonicaErrorTrap():
|
||||
return Pix(lept.pixDeskew(self._pix, reduction_factor))
|
||||
|
||||
def scale(self, scalex, scaley):
|
||||
"Returns the pix object rescaled according to the proportions given."
|
||||
with LeptonicaErrorTrap():
|
||||
return Pix(lept.pixScale(self._pix, scalex, scaley))
|
||||
|
||||
def rotate180(self):
|
||||
with LeptonicaErrorTrap():
|
||||
return Pix(lept.pixRotate180(ffi.NULL, self._pix))
|
||||
|
||||
def rotate_orth(self, quads):
|
||||
"Orthographic rotation, quads: 0-3, number of clockwise rotations"
|
||||
with LeptonicaErrorTrap():
|
||||
return Pix(lept.pixRotateOrth(self._pix, quads))
|
||||
|
||||
def find_skew(self):
|
||||
"""Returns a tuple (deskew angle in degrees, confidence value).
|
||||
|
||||
Returns (None, None) if no angle is available.
|
||||
"""
|
||||
with LeptonicaErrorTrap():
|
||||
angle = ffi.new('float *', 0.0)
|
||||
confidence = ffi.new('float *', 0.0)
|
||||
result = lept.pixFindSkew(self._pix, angle, confidence)
|
||||
if result == 0:
|
||||
return (angle[0], confidence[0])
|
||||
else:
|
||||
return (None, None)
|
||||
|
||||
def convert_rgb_to_luminance(self):
|
||||
with LeptonicaErrorTrap():
|
||||
gray_pix = lept.pixConvertRGBToLuminance(self._pix)
|
||||
if gray_pix:
|
||||
return Pix(gray_pix)
|
||||
return None
|
||||
|
||||
def remove_colormap(self, removal_type):
|
||||
"""Remove a palette
|
||||
|
||||
removal_type - RemovalColormap()
|
||||
"""
|
||||
|
||||
with LeptonicaErrorTrap():
|
||||
return Pix(lept.pixRemoveColormap(self._pix, removal_type))
|
||||
|
||||
def otsu_adaptive_threshold(
|
||||
self, tile_size=(300, 300), kernel_size=(4, 4), scorefract=0.1):
|
||||
with LeptonicaErrorTrap():
|
||||
sx, sy = tile_size
|
||||
smoothx, smoothy = kernel_size
|
||||
p_pix = ffi.new('PIX **')
|
||||
|
||||
result = lept.pixOtsuAdaptiveThreshold(
|
||||
self._pix,
|
||||
sx, sy,
|
||||
smoothx, smoothy,
|
||||
scorefract,
|
||||
ffi.NULL,
|
||||
p_pix)
|
||||
if result == 0:
|
||||
return Pix(p_pix[0])
|
||||
else:
|
||||
return None
|
||||
|
||||
def otsu_threshold_on_background_norm(
|
||||
self, mask=None, tile_size=(10, 15), thresh=100, mincount=50,
|
||||
bgval=255, kernel_size=(2, 2), scorefract=0.1):
|
||||
with LeptonicaErrorTrap():
|
||||
sx, sy = tile_size
|
||||
smoothx, smoothy = kernel_size
|
||||
if mask is None:
|
||||
mask = ffi.NULL
|
||||
if isinstance(mask, Pix):
|
||||
mask = mask._pix
|
||||
|
||||
thresh_pix = lept.pixOtsuThreshOnBackgroundNorm(
|
||||
self._pix,
|
||||
mask,
|
||||
sx, sy,
|
||||
thresh, mincount, bgval,
|
||||
smoothx, smoothy,
|
||||
scorefract,
|
||||
ffi.NULL
|
||||
)
|
||||
if thresh_pix == ffi.NULL:
|
||||
return None
|
||||
return Pix(thresh_pix)
|
||||
|
||||
def crop_to_foreground(
|
||||
self, threshold=128, mindist=70, erasedist=30, pagenum=0,
|
||||
showmorph=0, display=0, pdfdir=ffi.NULL):
|
||||
with LeptonicaErrorTrap():
|
||||
cropbox = Box(lept.pixFindPageForeground(
|
||||
self._pix,
|
||||
threshold,
|
||||
mindist,
|
||||
erasedist,
|
||||
pagenum,
|
||||
showmorph,
|
||||
display,
|
||||
pdfdir))
|
||||
|
||||
print(repr(cropbox))
|
||||
|
||||
cropped_pix = lept.pixClipRectangle(
|
||||
self._pix,
|
||||
cropbox._box,
|
||||
ffi.NULL)
|
||||
|
||||
return Pix(cropped_pix)
|
||||
|
||||
def clean_background_to_white(
|
||||
self, mask=None, grayscale=None, gamma=1.0, black=0, white=255):
|
||||
with LeptonicaErrorTrap():
|
||||
return Pix(lept.pixCleanBackgroundToWhite(
|
||||
self._pix,
|
||||
mask or ffi.NULL,
|
||||
grayscale or ffi.NULL,
|
||||
gamma,
|
||||
black,
|
||||
white))
|
||||
|
||||
@staticmethod
|
||||
@lru_cache(maxsize=1)
|
||||
def make_pixel_sum_tab8():
|
||||
return lept.makePixelSumTab8()
|
||||
|
||||
@staticmethod
|
||||
def correlation_binary(pix1, pix2):
|
||||
if get_leptonica_version() < 'leptonica-1.72':
|
||||
# Older versions of Leptonica (pre-1.72) have a buggy
|
||||
# implementation of pixCorrelationBinary that overflows on larger
|
||||
# images. Ubuntu trusty has 1.70. Ubuntu PPA
|
||||
# ppa:rebuntu16/avidemux+unofficial has "leptonlib" 1.73.
|
||||
pix1_count = ffi.new('l_int32 *')
|
||||
pix2_count = ffi.new('l_int32 *')
|
||||
pixn_count = ffi.new('l_int32 *')
|
||||
tab8 = Pix.make_pixel_sum_tab8()
|
||||
|
||||
lept.pixCountPixels(pix1._pix, pix1_count, tab8)
|
||||
lept.pixCountPixels(pix2._pix, pix2_count, tab8)
|
||||
pixn = Pix(lept.pixAnd(ffi.NULL, pix1._pix, pix2._pix))
|
||||
lept.pixCountPixels(pixn._pix, pixn_count, tab8)
|
||||
|
||||
# Python converts these int32s to larger units as needed
|
||||
# to avoid overflow. Overflow happens easily here.
|
||||
correlation = (
|
||||
(pixn_count[0] * pixn_count[0]) /
|
||||
(pix1_count[0] * pix2_count[0])
|
||||
)
|
||||
return correlation
|
||||
else:
|
||||
correlation = ffi.new('float *', 0.0)
|
||||
result = lept.pixCorrelationBinary(pix1._pix, pix2._pix,
|
||||
correlation)
|
||||
if result != 0:
|
||||
raise LeptonicaError("Correlation failed")
|
||||
return correlation[0]
|
||||
|
||||
@staticmethod
|
||||
def _pix_destroy(pix):
|
||||
p_pix = ffi.new('PIX **', pix)
|
||||
lept.pixDestroy(p_pix)
|
||||
# print('pix destroy ' + repr(pix))
|
||||
|
||||
|
||||
class Box:
|
||||
"""Wrapper around Leptonica's BOX objects.
|
||||
|
||||
See class Pix for notes about reference counting.
|
||||
"""
|
||||
|
||||
def __init__(self, box):
|
||||
self._box = ffi.gc(box, Box._box_destroy)
|
||||
|
||||
def __repr__(self):
|
||||
if self._box:
|
||||
return '<leptonica.Box x={0} y={1} w={2} h={3}>'.format(
|
||||
self.x, self.y, self.w, self.h)
|
||||
return '<leptonica.Box NULL>'
|
||||
|
||||
@property
|
||||
def x(self):
|
||||
return self._box.x
|
||||
|
||||
@property
|
||||
def y(self):
|
||||
return self._box.y
|
||||
|
||||
@property
|
||||
def w(self):
|
||||
return self._box.w
|
||||
|
||||
@property
|
||||
def h(self):
|
||||
return self._box.h
|
||||
|
||||
@staticmethod
|
||||
def _box_destroy(box):
|
||||
p_box = ffi.new('BOX **', box)
|
||||
lept.boxDestroy(p_box)
|
||||
|
||||
|
||||
@lru_cache(maxsize=1)
|
||||
def get_leptonica_version():
|
||||
"""Get Leptonica version string.
|
||||
|
||||
Caveat: Leptonica expects the caller to free this memory. We don't,
|
||||
since that would involve binding to libc to access libc.free(),
|
||||
a pointless effort to reclaim 100 bytes of memory.
|
||||
"""
|
||||
return ffi.string(lept.getLeptonicaVersion()).decode()
|
||||
|
||||
|
||||
def deskew(infile, outfile, dpi):
|
||||
try:
|
||||
pix_source = Pix.read(infile)
|
||||
except LeptonicaIOError:
|
||||
raise LeptonicaIOError("Failed to open file: %s" % infile)
|
||||
|
||||
if dpi < 150:
|
||||
reduction_factor = 1 # Don't downsample too much if DPI is already low
|
||||
else:
|
||||
reduction_factor = 0 # Use default
|
||||
pix_deskewed = pix_source.deskew(reduction_factor)
|
||||
|
||||
try:
|
||||
pix_deskewed.write_implied_format(outfile)
|
||||
except LeptonicaIOError:
|
||||
raise LeptonicaIOError("Failed to open destination file: %s" % outfile)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
parser = argparse.ArgumentParser(
|
||||
description="Python wrapper to access Leptonica")
|
||||
|
||||
subparsers = parser.add_subparsers(title='commands',
|
||||
description='supported operations')
|
||||
|
||||
parser_deskew = subparsers.add_parser('deskew')
|
||||
parser_deskew.add_argument('-r', '--dpi', dest='dpi', action='store',
|
||||
type=int, default=300, help='input resolution')
|
||||
parser_deskew.add_argument('infile', help='image to deskew')
|
||||
parser_deskew.add_argument('outfile', help='deskewed output image')
|
||||
parser_deskew.set_defaults(func=deskew)
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
if get_leptonica_version() != u'leptonica-1.69':
|
||||
print("Unexpected leptonica version: %s" % getLeptonicaVersion())
|
||||
|
||||
args.func(args)
|
||||
|
||||
|
||||
def test_skew_angle():
|
||||
from PIL import Image, ImageDraw
|
||||
from tempfile import NamedTemporaryFile
|
||||
|
||||
im = Image.new(mode='1', size=(1000, 1000), color=1)
|
||||
|
||||
draw = ImageDraw.Draw(im)
|
||||
for n in range(20):
|
||||
draw.line([(50, 25 + 50*n), (950, 25 + 50*n)], width=1)
|
||||
del draw
|
||||
|
||||
test_angles = [0.1 * ang for ang in range(1, 10)] + \
|
||||
[float(ang) for ang in range(1, 7)]
|
||||
test_angles += [-ang for ang in test_angles]
|
||||
test_angles = sorted(test_angles)
|
||||
|
||||
for rotate_angle in test_angles:
|
||||
rotated_im = im.rotate(rotate_angle)
|
||||
with NamedTemporaryFile(prefix='lept-skew', suffix='.png', delete=True) as tmpfile:
|
||||
rotated_im.save(tmpfile)
|
||||
pix = pixRead(tmpfile.name)
|
||||
angle, confidence = pixFindSkew(pix)
|
||||
print('{0} {1} {2}'.format(rotate_angle, angle, confidence), file=sys.stderr)
|
||||
|
||||
|
||||
@@ -1,142 +0,0 @@
|
||||
from cffi import FFI
|
||||
|
||||
ffi = FFI()
|
||||
ffi.set_source("ocrmypdf.lib._leptonica", None)
|
||||
ffi.cdef("""
|
||||
typedef signed char l_int8;
|
||||
typedef unsigned char l_uint8;
|
||||
typedef short l_int16;
|
||||
typedef unsigned short l_uint16;
|
||||
typedef int l_int32;
|
||||
typedef unsigned int l_uint32;
|
||||
typedef float l_float32;
|
||||
typedef double l_float64;
|
||||
typedef long long l_int64;
|
||||
typedef unsigned long long l_uint64;
|
||||
|
||||
struct Pix
|
||||
{
|
||||
l_uint32 w; /* width in pixels */
|
||||
l_uint32 h; /* height in pixels */
|
||||
l_uint32 d; /* depth in bits (bpp) */
|
||||
l_uint32 spp; /* number of samples per pixel */
|
||||
l_uint32 wpl; /* 32-bit words/line */
|
||||
l_uint32 refcount; /* reference count (1 if no clones) */
|
||||
l_int32 xres; /* image res (ppi) in x direction */
|
||||
/* (use 0 if unknown) */
|
||||
l_int32 yres; /* image res (ppi) in y direction */
|
||||
/* (use 0 if unknown) */
|
||||
l_int32 informat; /* input file format, IFF_* */
|
||||
l_int32 special; /* special instructions for I/O, etc */
|
||||
char *text; /* text string associated with pix */
|
||||
struct PixColormap *colormap; /* colormap (may be null) */
|
||||
l_uint32 *data; /* the image data */
|
||||
};
|
||||
typedef struct Pix PIX;
|
||||
|
||||
struct PixColormap
|
||||
{
|
||||
void *array; /* colormap table (array of RGBA_QUAD) */
|
||||
l_int32 depth; /* of pix (1, 2, 4 or 8 bpp) */
|
||||
l_int32 nalloc; /* number of color entries allocated */
|
||||
l_int32 n; /* number of color entries used */
|
||||
};
|
||||
typedef struct PixColormap PIXCMAP;
|
||||
|
||||
struct Box
|
||||
{
|
||||
l_int32 x;
|
||||
l_int32 y;
|
||||
l_int32 w;
|
||||
l_int32 h;
|
||||
l_uint32 refcount; /* reference count (1 if no clones) */
|
||||
|
||||
};
|
||||
typedef struct Box BOX;
|
||||
|
||||
""")
|
||||
|
||||
ffi.cdef("""
|
||||
PIX * pixRead ( const char *filename );
|
||||
PIX * pixScale ( PIX *pixs, l_float32 scalex, l_float32 scaley );
|
||||
l_int32 pixFindSkew ( PIX *pixs, l_float32 *pangle, l_float32 *pconf );
|
||||
l_int32 pixWriteImpliedFormat ( const char *filename, PIX *pix, l_int32 quality, l_int32 progressive );
|
||||
void pixDestroy ( PIX **ppix );
|
||||
|
||||
PIX *
|
||||
pixEndianByteSwapNew(PIX *pixs);
|
||||
|
||||
PIX * pixDeskew ( PIX *pixs, l_int32 redsearch );
|
||||
char * getLeptonicaVersion ( );
|
||||
l_int32 pixCorrelationBinary(PIX *pix1, PIX *pix2, l_float32 *pval);
|
||||
PIX *pixRotate180(PIX *pixd, PIX *pixs);
|
||||
PIX *
|
||||
pixRotateOrth(PIX *pixs,
|
||||
l_int32 quads);
|
||||
|
||||
l_int32 pixCountPixels ( PIX *pix, l_int32 *pcount, l_int32 *tab8 );
|
||||
PIX * pixAnd ( PIX *pixd, PIX *pixs1, PIX *pixs2 );
|
||||
l_int32 * makePixelSumTab8 ( void );
|
||||
|
||||
PIX * pixDeserializeFromMemory ( const l_uint32 *data, size_t nbytes );
|
||||
l_int32 pixSerializeToMemory ( PIX *pixs, l_uint32 **pdata, size_t *pnbytes );
|
||||
|
||||
PIX * pixConvertRGBToLuminance(PIX *pixs);
|
||||
|
||||
PIX * pixRemoveColormap(PIX *pixs, l_int32 type);
|
||||
|
||||
l_int32
|
||||
pixOtsuAdaptiveThreshold(PIX *pixs,
|
||||
l_int32 sx,
|
||||
l_int32 sy,
|
||||
l_int32 smoothx,
|
||||
l_int32 smoothy,
|
||||
l_float32 scorefract,
|
||||
PIX **ppixth,
|
||||
PIX **ppixd);
|
||||
|
||||
PIX *
|
||||
pixOtsuThreshOnBackgroundNorm(PIX *pixs,
|
||||
PIX *pixim,
|
||||
l_int32 sx,
|
||||
l_int32 sy,
|
||||
l_int32 thresh,
|
||||
l_int32 mincount,
|
||||
l_int32 bgval,
|
||||
l_int32 smoothx,
|
||||
l_int32 smoothy,
|
||||
l_float32 scorefract,
|
||||
l_int32 *pthresh);
|
||||
|
||||
PIX *
|
||||
pixCleanBackgroundToWhite(PIX *pixs,
|
||||
PIX *pixim,
|
||||
PIX *pixg,
|
||||
l_float32 gamma,
|
||||
l_int32 blackval,
|
||||
l_int32 whiteval);
|
||||
|
||||
BOX *
|
||||
pixFindPageForeground(PIX *pixs,
|
||||
l_int32 threshold,
|
||||
l_int32 mindist,
|
||||
l_int32 erasedist,
|
||||
l_int32 pagenum,
|
||||
l_int32 showmorph,
|
||||
l_int32 display,
|
||||
const char *pdfdir);
|
||||
|
||||
PIX *
|
||||
pixClipRectangle(PIX *pixs,
|
||||
BOX *box,
|
||||
BOX **pboxc);
|
||||
|
||||
void
|
||||
boxDestroy(BOX **pbox);
|
||||
|
||||
void lept_free(void *ptr);
|
||||
""")
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
ffi.compile()
|
||||
@@ -1,7 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
# © 2015-16 James R. Barlow: github.com/jbarlow83
|
||||
|
||||
# This file is now an alias for __main__
|
||||
# Consider removing in future releases
|
||||
|
||||
from ocrmypdf.__main__ import *
|
||||
@@ -1,368 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
# © 2015 James R. Barlow: github.com/jbarlow83
|
||||
|
||||
from subprocess import Popen, PIPE
|
||||
from decimal import Decimal, getcontext
|
||||
from math import hypot
|
||||
import re
|
||||
import sys
|
||||
import PyPDF2 as pypdf
|
||||
from collections import namedtuple
|
||||
|
||||
matrix_mult = pypdf.pdf.utils.matrixMultiply
|
||||
|
||||
FRIENDLY_COLORSPACE = {
|
||||
'/DeviceGray': 'gray',
|
||||
'/CalGray': 'gray',
|
||||
'/DeviceRGB': 'rgb',
|
||||
'/CalRGB': 'rgb',
|
||||
'/DeviceCMYK': 'cmyk',
|
||||
'/Lab': 'lab',
|
||||
'/ICCBased': 'icc',
|
||||
'/Indexed': 'index',
|
||||
'/Separation': 'sep',
|
||||
'/DeviceN': 'devn',
|
||||
'/Pattern': '-',
|
||||
'/G': 'gray', # Abbreviations permitted in inline images
|
||||
'/RGB': 'rgb',
|
||||
'/CMYK': 'cmyk',
|
||||
'/I': 'index',
|
||||
}
|
||||
|
||||
FRIENDLY_ENCODING = {
|
||||
'/CCITTFaxDecode': 'ccitt',
|
||||
'/DCTDecode': 'jpeg',
|
||||
'/JPXDecode': 'jpx',
|
||||
'/JBIG2Decode': 'jbig2',
|
||||
'/CCF': 'ccitt', # Abbreviations permitted in inline images
|
||||
'/DCT': 'jpeg',
|
||||
'/AHx': 'asciihex',
|
||||
'/A85': 'ascii85',
|
||||
'/LZW': 'lzw',
|
||||
'/Fl': 'flate',
|
||||
'/RL': 'runlength'
|
||||
}
|
||||
|
||||
FRIENDLY_COMP = {
|
||||
'gray': 1,
|
||||
'rgb': 3,
|
||||
'cmyk': 4,
|
||||
'lab': 3,
|
||||
'index': 1
|
||||
}
|
||||
|
||||
|
||||
def _matrix_from_shorthand(shorthand):
|
||||
"""Convert from PDF matrix shorthand to full matrix
|
||||
|
||||
PDF 1.7 spec defines a shorthand for describing the entries of a matrix
|
||||
since the last column is always (0, 0, 1).
|
||||
"""
|
||||
|
||||
a, b, c, d, e, f = map(float, shorthand)
|
||||
return ((a, b, 0),
|
||||
(c, d, 0),
|
||||
(e, f, 1))
|
||||
|
||||
|
||||
def _shorthand_from_matrix(matrix):
|
||||
"""Convert from transformation matrix to PDF shorthand."""
|
||||
a, b = matrix[0][0], matrix[0][1]
|
||||
c, d = matrix[1][0], matrix[1][1]
|
||||
e, f = matrix[2][0], matrix[2][1]
|
||||
return tuple(map(float, (a, b, c, d, e, f)))
|
||||
|
||||
|
||||
ContentsInfo = namedtuple('ContentsInfo', ['raster_settings', 'inline_images'])
|
||||
|
||||
|
||||
def _interpret_contents(contentstream):
|
||||
operations = contentstream.operations
|
||||
stack = []
|
||||
ctm = _matrix_from_shorthand((1, 0, 0, 1, 0, 0))
|
||||
image_raster_settings = []
|
||||
inline_images = []
|
||||
|
||||
for op in operations:
|
||||
operands, command = op
|
||||
if command == b'q':
|
||||
stack.append(ctm)
|
||||
if len(stack) > 32:
|
||||
raise RuntimeError("PDF graphics stack overflow")
|
||||
elif command == b'Q':
|
||||
ctm = stack.pop()
|
||||
elif command == b'cm':
|
||||
ctm = matrix_mult(
|
||||
_matrix_from_shorthand(operands), ctm)
|
||||
elif command == b'Do':
|
||||
image_name = operands[0]
|
||||
image_raster_settings.append(
|
||||
(image_name, _shorthand_from_matrix(ctm)))
|
||||
elif command == b'INLINE IMAGE':
|
||||
settings = operands['settings']
|
||||
inline_images.append(
|
||||
(settings, _shorthand_from_matrix(ctm)))
|
||||
|
||||
return ContentsInfo(
|
||||
raster_settings=image_raster_settings,
|
||||
inline_images=inline_images)
|
||||
|
||||
|
||||
def _get_dpi(ctm_shorthand, image_size):
|
||||
"""Given the transformation matrix and image size, find the image DPI.
|
||||
|
||||
PDFs do not include image resolution information within image data.
|
||||
Instead, the PDF page content stream describes the location where the
|
||||
image will be rasterized, and the effective resolution is the ratio of the
|
||||
pixel size to raster target size.
|
||||
|
||||
Normally a scanned PDF has the paper size set appropriately but this is
|
||||
not guaranteed. The most common case is a cropped image will change the
|
||||
page size (/CropBox) without altering the page content stream. That means
|
||||
it is not sufficient to assume that the image fills the page, even though
|
||||
that is the most common case.
|
||||
|
||||
A PDF image may be scaled (always), cropped, translated, rotated in place
|
||||
to an arbitrary angle (rarely) and skewed. Only equal area mappings can
|
||||
be expressed, that is, it is not necessary to consider distortions where
|
||||
the effective DPI varies with position.
|
||||
|
||||
To determine the image scale, transform an offset axis vector v0 (0, 0),
|
||||
width-axis vector v0 (1, 0), height-axis vector vh (0, 1) with the matrix,
|
||||
which gives the dimensions of the image in PDF units. From there we can
|
||||
compare to actual image dimensions. PDF uses
|
||||
row vector * matrix_tranposed unlike the traditional
|
||||
matrix * column vector.
|
||||
|
||||
The offset, width and height vectors can be combined in a matrix and
|
||||
multiplied by the transform matrix. Then we want to calculated
|
||||
magnitude(width_vector - offset_vector)
|
||||
and
|
||||
magnitude(height_vector - offset_vector)
|
||||
|
||||
When the above is worked out algebraically, the effect of translation
|
||||
cancels out, and the vector magnitudes become functions of the nonzero
|
||||
transformation matrix indices. The results of the derivation are used
|
||||
in this code.
|
||||
|
||||
pdfimages -list does calculate the DPI in some way that is not completely
|
||||
naive, but it does not get the DPI of rotated images right, so cannot be
|
||||
used anymore to validate this. Photoshop works, or using Acrobat to
|
||||
rotate the image back to normal.
|
||||
|
||||
It does not matter if the image is partially cropped, or even out of the
|
||||
/MediaBox.
|
||||
|
||||
"""
|
||||
|
||||
a, b, c, d, _, _ = ctm_shorthand
|
||||
|
||||
# Calculate the width and height of the image in PDF units
|
||||
image_drawn_width = hypot(a, b)
|
||||
image_drawn_height = hypot(c, d)
|
||||
|
||||
# The scale of the image is pixels per PDF unit (1/72")
|
||||
scale_w = image_size[0] / image_drawn_width
|
||||
scale_h = image_size[1] / image_drawn_height
|
||||
|
||||
# DPI = scale * 72
|
||||
dpi_w = scale_w * 72.0
|
||||
dpi_h = scale_h * 72.0
|
||||
|
||||
return (dpi_w, dpi_h)
|
||||
|
||||
|
||||
def _find_page_inline_images(page, pageinfo, contentsinfo):
|
||||
"Find inline images on the page"
|
||||
|
||||
for n, im in enumerate(contentsinfo.inline_images):
|
||||
settings, shorthand = im
|
||||
image = {}
|
||||
image['name'] = str('inline-%02d' % n)
|
||||
image['width'] = settings['/W']
|
||||
image['height'] = settings['/H']
|
||||
image['bpc'] = settings['/BPC']
|
||||
image['color'] = FRIENDLY_COLORSPACE.get(settings['/CS'], '-')
|
||||
image['comp'] = FRIENDLY_COMP.get(image['color'], '?')
|
||||
if '/F' in settings:
|
||||
filter_ = settings['/F']
|
||||
if isinstance(filter_, pypdf.generic.ArrayObject):
|
||||
filter_ = filter_[0]
|
||||
image['enc'] = FRIENDLY_ENCODING.get(filter_, 'image')
|
||||
else:
|
||||
image['enc'] = 'image'
|
||||
|
||||
dpi_w, dpi_h = _get_dpi(shorthand, (image['width'], image['height']))
|
||||
image['dpi_w'], image['dpi_h'] = Decimal(dpi_w), Decimal(dpi_h)
|
||||
yield image
|
||||
|
||||
|
||||
def _find_page_regular_images(page, pageinfo, contentsinfo):
|
||||
"Find images stored in XObject resources"
|
||||
|
||||
try:
|
||||
page['/Resources']['/XObject']
|
||||
except KeyError:
|
||||
return
|
||||
for xobj in page['/Resources']['/XObject']:
|
||||
# PyPDF2 returns the keys as an iterator
|
||||
pdfimage = page['/Resources']['/XObject'][xobj]
|
||||
if pdfimage['/Subtype'] != '/Image':
|
||||
continue
|
||||
image = {}
|
||||
image['name'] = str(xobj)
|
||||
image['width'] = pdfimage['/Width']
|
||||
image['height'] = pdfimage['/Height']
|
||||
image['bpc'] = pdfimage['/BitsPerComponent']
|
||||
|
||||
# Fixme: this is incorrectly treats explicit masks as stencil masks,
|
||||
# but good enough for now. Explicit masks have /ImageMask true but are
|
||||
# never called for in content stream, instead are drawn as a /Mask on
|
||||
# other images. For our purposes finding out the details of /Mask
|
||||
# will seldom matter.
|
||||
if '/ImageMask' in pdfimage:
|
||||
image['type'] = 'stencil' if pdfimage['/ImageMask'].value \
|
||||
else 'image'
|
||||
else:
|
||||
image['type'] = 'image'
|
||||
if '/Filter' in pdfimage:
|
||||
filter_ = pdfimage['/Filter']
|
||||
if isinstance(filter_, pypdf.generic.ArrayObject):
|
||||
filter_ = filter_[0]
|
||||
image['enc'] = FRIENDLY_ENCODING.get(filter_, 'image')
|
||||
else:
|
||||
image['enc'] = 'image'
|
||||
if '/ColorSpace' in pdfimage:
|
||||
cs = pdfimage['/ColorSpace']
|
||||
if isinstance(cs, pypdf.generic.ArrayObject):
|
||||
cs = cs[0]
|
||||
image['color'] = FRIENDLY_COLORSPACE.get(cs, '-')
|
||||
else:
|
||||
image['color'] = 'jpx' if image['enc'] == 'jpx' else '?'
|
||||
|
||||
image['comp'] = FRIENDLY_COMP.get(image['color'], '?')
|
||||
|
||||
# Bit of a hack... infer grayscale if component count is uncertain
|
||||
# but encoding must be monochrome. This happens if a monochrome image
|
||||
# has an ICC profile attached. Better solution would be to examine
|
||||
# the ICC profile.
|
||||
if image['comp'] == '?' and image['enc'] in ('ccitt', 'jbig2'):
|
||||
image['comp'] = FRIENDLY_COMP['gray']
|
||||
|
||||
image['dpi_w'] = image['dpi_h'] = 0
|
||||
|
||||
for raster in contentsinfo.raster_settings:
|
||||
# Loop in case the same image is display multiple times on a page
|
||||
if raster[0] != image['name']:
|
||||
continue
|
||||
shorthand = raster[1]
|
||||
|
||||
if image['type'] == 'stencil':
|
||||
# Stencil masks are implicitly scaled over the whole page
|
||||
# Images that are used in explicit masks are not drawn directly
|
||||
# but drawn by the image they mask over, so they will never
|
||||
# be called for in raster settings
|
||||
if shorthand != (1, 0, 0, 1, 0, 0):
|
||||
raise NotImplementedError(
|
||||
"Don't know how to handle "
|
||||
"stencil masks when graphics stack depth > 0.")
|
||||
page_w = float(pageinfo['width_inches']) * 72.0
|
||||
page_h = float(pageinfo['height_inches']) * 72.0
|
||||
shorthand = (page_w, 0.0, 0.0,
|
||||
page_h, 0.0, 0.0)
|
||||
|
||||
dpi_w, dpi_h = _get_dpi(
|
||||
shorthand, (image['width'], image['height']))
|
||||
|
||||
# When image is used multiple times take the highest DPI it is
|
||||
# rendered at
|
||||
image['dpi_w'] = max(dpi_w, image.get('dpi_w', 0))
|
||||
image['dpi_h'] = max(dpi_h, image.get('dpi_h', 0))
|
||||
|
||||
image['dpi_w'] = Decimal(image['dpi_w'])
|
||||
image['dpi_h'] = Decimal(image['dpi_h'])
|
||||
image['dpi'] = (image['dpi_w'] * image['dpi_h']) ** Decimal(0.5)
|
||||
yield image
|
||||
|
||||
|
||||
def _find_page_images(page, pageinfo, contentsinfo):
|
||||
yield from _find_page_inline_images(page, pageinfo, contentsinfo)
|
||||
yield from _find_page_regular_images(page, pageinfo, contentsinfo)
|
||||
|
||||
|
||||
def _page_has_text(pdf, page):
|
||||
# Simple test
|
||||
text = page.extractText()
|
||||
if text.strip() != '':
|
||||
return True
|
||||
|
||||
# More nuanced test to deal with quirks of Tesseract PDF generation
|
||||
# Check if there's a Glyphless font
|
||||
try:
|
||||
font = page['/Resources']['/Font']
|
||||
except KeyError:
|
||||
pass
|
||||
else:
|
||||
font_objects = list(font.keys())
|
||||
for font_object in font_objects:
|
||||
basefont = font[font_object]['/BaseFont']
|
||||
if basefont.endswith('GlyphLessFont'):
|
||||
return True
|
||||
|
||||
return False
|
||||
|
||||
|
||||
def _pdf_get_pageinfo(infile, pageno: int):
|
||||
pageinfo = {}
|
||||
pageinfo['pageno'] = pageno
|
||||
pageinfo['images'] = []
|
||||
|
||||
pdf = pypdf.PdfFileReader(infile)
|
||||
page = pdf.pages[pageno]
|
||||
|
||||
pageinfo['has_text'] = _page_has_text(pdf, page)
|
||||
|
||||
width_pt = page.mediaBox.getWidth()
|
||||
height_pt = page.mediaBox.getHeight()
|
||||
pageinfo['width_inches'] = width_pt / Decimal(72.0)
|
||||
pageinfo['height_inches'] = height_pt / Decimal(72.0)
|
||||
|
||||
try:
|
||||
contentstream = pypdf.pdf.ContentStream(page.getContents(), pdf)
|
||||
except AttributeError as e:
|
||||
return pageinfo
|
||||
|
||||
contentsinfo = _interpret_contents(contentstream)
|
||||
pageinfo['images'] = [im for im in _find_page_images(
|
||||
page, pageinfo, contentsinfo)]
|
||||
|
||||
if pageinfo['images']:
|
||||
xres = max(image['dpi_w'] for image in pageinfo['images'])
|
||||
yres = max(image['dpi_h'] for image in pageinfo['images'])
|
||||
pageinfo['xres'], pageinfo['yres'] = xres, yres
|
||||
pageinfo['width_pixels'] = \
|
||||
int(round(xres * pageinfo['width_inches']))
|
||||
pageinfo['height_pixels'] = \
|
||||
int(round(yres * pageinfo['height_inches']))
|
||||
|
||||
return pageinfo
|
||||
|
||||
|
||||
def pdf_get_all_pageinfo(infile):
|
||||
pdf = pypdf.PdfFileReader(infile)
|
||||
getcontext().prec = 6
|
||||
return [_pdf_get_pageinfo(infile, n) for n in range(pdf.numPages)]
|
||||
|
||||
|
||||
def main():
|
||||
import argparse
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument('infile')
|
||||
args = parser.parse_args()
|
||||
info = pdf_get_all_pageinfo(args.infile)
|
||||
from pprint import pprint
|
||||
pprint(info)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
@@ -1,159 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
# © 2015 James R. Barlow: github.com/jbarlow83
|
||||
#
|
||||
# Generate a PDFA_def.ps file for Ghostscript >= 9.14
|
||||
|
||||
from __future__ import print_function, absolute_import, division
|
||||
from string import Template
|
||||
import codecs
|
||||
import pkg_resources
|
||||
import PyPDF2 as pypdf
|
||||
|
||||
ICC_PROFILE_RELPATH = 'data/sRGB.icc'
|
||||
|
||||
SRGB_ICC_PROFILE = pkg_resources.resource_filename(
|
||||
'ocrmypdf', ICC_PROFILE_RELPATH)
|
||||
|
||||
|
||||
# This is a template written in PostScript which is needed to create PDF/A
|
||||
# files, from the Ghostscript documentation. Lines beginning with % are
|
||||
# comments. Python substitution variables have a '$' prefix.
|
||||
pdfa_def_template = u"""%!
|
||||
% This is a sample prefix file for creating a PDF/A document.
|
||||
% Feel free to modify entries marked with "Customize".
|
||||
% This assumes an ICC profile to reside in the file (ISO Coated sb.icc),
|
||||
% unless the user modifies the corresponding line below.
|
||||
|
||||
% Define entries in the document Info dictionary :
|
||||
/ICCProfile ($icc_profile)
|
||||
def
|
||||
|
||||
[ /Title <$title>
|
||||
/Author <$author>
|
||||
/Subject <$subject>
|
||||
/Keywords <$keywords>
|
||||
/Creator <$creator>
|
||||
/DOCINFO pdfmark
|
||||
|
||||
% Define an ICC profile :
|
||||
|
||||
[/_objdef {icc_PDFA} /type /stream /OBJ pdfmark
|
||||
[{icc_PDFA}
|
||||
<<
|
||||
/N currentpagedevice /ProcessColorModel known {
|
||||
currentpagedevice /ProcessColorModel get dup /DeviceGray eq
|
||||
{pop 1} {
|
||||
/DeviceRGB eq
|
||||
{3}{4} ifelse
|
||||
} ifelse
|
||||
} {
|
||||
(ERROR, unable to determine ProcessColorModel) == flush
|
||||
} ifelse
|
||||
>> /PUT pdfmark
|
||||
[{icc_PDFA} ICCProfile (r) file /PUT pdfmark
|
||||
|
||||
% Define the output intent dictionary :
|
||||
|
||||
[/_objdef {OutputIntent_PDFA} /type /dict /OBJ pdfmark
|
||||
[{OutputIntent_PDFA} <<
|
||||
/Type /OutputIntent % Must be so (the standard requires).
|
||||
/S /GTS_PDFA1 % Must be so (the standard requires).
|
||||
/DestOutputProfile {icc_PDFA} % Must be so (see above).
|
||||
/OutputConditionIdentifier ($icc_identifier)
|
||||
>> /PUT pdfmark
|
||||
[{Catalog} <</OutputIntents [ {OutputIntent_PDFA} ]>> /PUT pdfmark
|
||||
"""
|
||||
|
||||
|
||||
def encode_text_string(s: str) -> str:
|
||||
'''Encode text string to hex string for use in a PDF
|
||||
|
||||
From PDF 32000-1:2008 a string object may be included in hexademical form
|
||||
if it is enclosed in angle brackets. For general Unicode the string should
|
||||
be UTF-16 (big endian) with byte order marks. A non-hexademical
|
||||
representation is doable but this is preferable since it allows the output
|
||||
Postscript file to be completely ASCII and no escaping of Postscript
|
||||
characters is necessary.
|
||||
'''
|
||||
|
||||
# Sometimes lazy C programmer leave their NULs at the end of strings
|
||||
# tests/resources/aspect.pdf is one example (created by ImageMagick)
|
||||
s = s.replace('\x00', '')
|
||||
|
||||
if s == '':
|
||||
return ''
|
||||
|
||||
utf16_bytes = s.encode('utf-16be')
|
||||
ascii_hex_bytes = codecs.encode(b'\xfe\xff' + utf16_bytes, 'hex')
|
||||
ascii_hex_str = ascii_hex_bytes.decode('ascii').lower()
|
||||
return ascii_hex_str
|
||||
|
||||
|
||||
def _get_pdfa_def(icc_profile, icc_identifier, pdfmark):
|
||||
pdfmark_utf16 = {k: encode_text_string(v) for k, v in pdfmark.items()}
|
||||
|
||||
t = Template(pdfa_def_template)
|
||||
result = t.substitute(icc_profile=icc_profile,
|
||||
icc_identifier=icc_identifier,
|
||||
title=pdfmark_utf16.get('/Title', ''),
|
||||
author=pdfmark_utf16.get('/Author', ''),
|
||||
subject=pdfmark_utf16.get('/Subject', ''),
|
||||
creator=pdfmark_utf16.get('/Creator', ''),
|
||||
keywords=pdfmark_utf16.get('/Keywords', ''))
|
||||
return result
|
||||
|
||||
|
||||
def generate_pdfa_def(target_filename, pdfmark, icc='sRGB'):
|
||||
if icc == 'sRGB':
|
||||
icc_profile = SRGB_ICC_PROFILE
|
||||
else:
|
||||
raise NotImplementedError("Only supporting sRGB")
|
||||
|
||||
ps = _get_pdfa_def(icc_profile, icc, pdfmark)
|
||||
|
||||
# We should have encoded everything to pure ASCII by this point, and
|
||||
# to be safe, only allow ASCII in PostScript
|
||||
with open(target_filename, 'w', encoding='ascii') as f:
|
||||
f.write(ps)
|
||||
|
||||
|
||||
def file_claims_pdfa(filename):
|
||||
"""Determines if the file claims to be PDF/A compliant
|
||||
|
||||
Checking if a file is a truly compliant PDF/A is a massive undertaking
|
||||
that no open source tool does properly. Some commercial tools are
|
||||
generally reliable (Acrobat).
|
||||
|
||||
This checks if the XMP metadata contains a PDF/A marker.
|
||||
"""
|
||||
|
||||
pdf = pypdf.PdfFileReader(filename)
|
||||
xmp = pdf.getXmpMetadata()
|
||||
|
||||
try:
|
||||
pdfa_nodes = xmp.getNodesInNamespace(
|
||||
aboutUri='',
|
||||
namespace='http://www.aiim.org/pdfa/ns/id/')
|
||||
except AttributeError:
|
||||
return {'pass': False, 'output': 'pdf',
|
||||
'conformance': 'No XMP metadata'}
|
||||
|
||||
pdfa_dict = {attr.localName: attr.value for attr in pdfa_nodes}
|
||||
pdfa_dict['pass'] = False
|
||||
pdfa_dict['output'] = 'pdf'
|
||||
if pdfa_dict:
|
||||
part_conformance = pdfa_dict['part'] + pdfa_dict['conformance']
|
||||
valid_part_conforms = {'1A', '1B', '2A', '2B', '2U', '3A', '3B', '3U'}
|
||||
|
||||
conformance = 'PDF/A-{}'.format(
|
||||
part_conformance)
|
||||
|
||||
if part_conformance in valid_part_conforms:
|
||||
pdfa_dict['pass'] = True
|
||||
pdfa_dict['output'] = 'pdfa'
|
||||
pdfa_dict['conformance'] = conformance
|
||||
else:
|
||||
pdfa_dict['conformance'] = 'PDF'
|
||||
|
||||
return pdfa_dict
|
||||
|
||||
@@ -1,119 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
# © 2015 James R. Barlow: github.com/jbarlow83
|
||||
|
||||
from subprocess import CalledProcessError, check_output, STDOUT, check_call
|
||||
from functools import lru_cache
|
||||
import sys
|
||||
import os
|
||||
import re
|
||||
|
||||
from . import ExitCode, get_program
|
||||
|
||||
|
||||
@lru_cache(maxsize=1)
|
||||
def version():
|
||||
args_qpdf = [
|
||||
get_program('qpdf'),
|
||||
'--version'
|
||||
]
|
||||
try:
|
||||
versions = check_output(
|
||||
args_qpdf, close_fds=True, universal_newlines=True,
|
||||
stderr=STDOUT)
|
||||
except CalledProcessError:
|
||||
print("Could not find qpdf executable on system PATH.")
|
||||
sys.exit(ExitCode.missing_dependency)
|
||||
|
||||
qpdf_version = re.match(r'qpdf version (.+)', versions).group(1)
|
||||
return qpdf_version
|
||||
|
||||
|
||||
def check(input_file, log):
|
||||
args_qpdf = [
|
||||
get_program('qpdf'),
|
||||
'--check',
|
||||
input_file
|
||||
]
|
||||
|
||||
try:
|
||||
check_output(args_qpdf, stderr=STDOUT, universal_newlines=True)
|
||||
except CalledProcessError as e:
|
||||
if e.returncode == 2:
|
||||
log.error("{0}: not a valid PDF, and could not repair it.".format(
|
||||
input_file))
|
||||
log.error("Details:")
|
||||
log.error(e.output)
|
||||
elif e.returncode == 3:
|
||||
log.info("qpdf --check returned warnings:")
|
||||
log.info(e.output)
|
||||
else:
|
||||
log.warning(e.output)
|
||||
return False
|
||||
return True
|
||||
|
||||
|
||||
def repair(input_file, output_file, log):
|
||||
args_qpdf = [
|
||||
get_program('qpdf'), input_file, output_file
|
||||
]
|
||||
try:
|
||||
check_output(args_qpdf, stderr=STDOUT, universal_newlines=True)
|
||||
except CalledProcessError as e:
|
||||
if e.returncode == 3 and e.output.find("operation succeeded"):
|
||||
log.debug('qpdf found and fixed errors: ' + e.output)
|
||||
log.debug(e.output)
|
||||
return
|
||||
|
||||
if e.returncode == 2 and e.output.find("invalid password"):
|
||||
log.error("{0}: this PDF is password-protected - password must "
|
||||
"be removed for OCR".format(input_file))
|
||||
sys.exit(ExitCode.input_file)
|
||||
elif e.returncode == 2:
|
||||
log.error("{0}: not a valid PDF, and could not repair it.".format(
|
||||
input_file))
|
||||
log.error("Details: " + e.output)
|
||||
sys.exit(ExitCode.input_file)
|
||||
else:
|
||||
log.error("{0}: unknown error".format(
|
||||
input_file))
|
||||
log.error(e.output)
|
||||
sys.exit(ExitCode.unknown)
|
||||
|
||||
|
||||
def get_npages(input_file, log):
|
||||
try:
|
||||
pages = check_output(
|
||||
[get_program('qpdf'), '--show-npages', input_file],
|
||||
universal_newlines=True, close_fds=True)
|
||||
except CalledProcessError as e:
|
||||
if e.returncode == 2 and e.output.find('No such file'):
|
||||
log.error(e.output)
|
||||
sys.exit(ExitCode.input_file)
|
||||
return int(pages)
|
||||
|
||||
|
||||
def split_pages(input_file, work_folder, npages):
|
||||
"""Split multipage PDF into individual pages.
|
||||
|
||||
Incredibly enough, this multiple process approach is about 70 times
|
||||
faster than using Ghostscript.
|
||||
"""
|
||||
for n in range(int(npages)):
|
||||
args_qpdf = [
|
||||
get_program('qpdf'), input_file,
|
||||
'--pages', input_file, '{0}'.format(n + 1), '--',
|
||||
os.path.join(work_folder, '{0:06d}.page.pdf'.format(n + 1))
|
||||
]
|
||||
check_call(args_qpdf)
|
||||
|
||||
|
||||
def merge(input_files, output_file):
|
||||
"""Merge the list of input files (all filenames) into the output file.
|
||||
|
||||
The input files may contain one or more pages.
|
||||
"""
|
||||
args_qpdf = [
|
||||
get_program('qpdf'), input_files[0], '--pages'
|
||||
] + input_files + ['--', output_file]
|
||||
check_call(args_qpdf)
|
||||
|
||||
@@ -1,256 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
# © 2015 James R. Barlow: github.com/jbarlow83
|
||||
|
||||
import sys
|
||||
import os
|
||||
import re
|
||||
import shutil
|
||||
from functools import lru_cache
|
||||
from . import ExitCode, get_program, page_number
|
||||
from collections import namedtuple
|
||||
|
||||
from subprocess import Popen, PIPE, CalledProcessError, \
|
||||
TimeoutExpired, check_output, STDOUT, DEVNULL
|
||||
|
||||
|
||||
OrientationConfidence = namedtuple(
|
||||
'OrientationConfidence',
|
||||
('angle', 'confidence'))
|
||||
|
||||
HOCR_TEMPLATE = '''<?xml version="1.0" encoding="UTF-8"?>
|
||||
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
|
||||
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
|
||||
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
|
||||
<head>
|
||||
<title></title>
|
||||
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
|
||||
<meta name='ocr-system' content='tesseract 3.02.02' />
|
||||
<meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word'/>
|
||||
</head>
|
||||
<body>
|
||||
<div class='ocr_page' id='page_1' title='image "x.tif"; bbox 0 0 {0} {1}; ppageno 0'>
|
||||
<div class='ocr_carea' id='block_1_1' title="bbox 0 1 {0} {1}">
|
||||
<p class='ocr_par' dir='ltr' id='par_1' title="bbox 0 1 {0} {1}">
|
||||
<span class='ocr_line' id='line_1' title="bbox 0 1 {0} {1}"><span class='ocrx_word' id='word_1' title="bbox 0 1 {0} {1}"> </span>
|
||||
</span>
|
||||
</p>
|
||||
</div>
|
||||
</div>
|
||||
</body>
|
||||
</html>'''
|
||||
|
||||
|
||||
@lru_cache(maxsize=1)
|
||||
def version():
|
||||
args_tess = [
|
||||
get_program('tesseract'),
|
||||
'--version'
|
||||
]
|
||||
try:
|
||||
versions = check_output(
|
||||
args_tess, close_fds=True, universal_newlines=True,
|
||||
stderr=STDOUT)
|
||||
except CalledProcessError:
|
||||
print("Could not find Tesseract executable on system PATH.")
|
||||
sys.exit(ExitCode.missing_dependency)
|
||||
|
||||
tesseract_version = re.match(r'tesseract\s(.+)', versions).group(1)
|
||||
return tesseract_version
|
||||
|
||||
|
||||
@lru_cache(maxsize=1)
|
||||
def languages():
|
||||
args_tess = [
|
||||
get_program('tesseract'),
|
||||
'--list-langs'
|
||||
]
|
||||
try:
|
||||
langs = check_output(
|
||||
args_tess, close_fds=True, universal_newlines=True,
|
||||
stderr=STDOUT)
|
||||
except CalledProcessError as e:
|
||||
print("Tesseract failed to report available languages.")
|
||||
print("Output from Tesseract:")
|
||||
print("-" * 40)
|
||||
print(e.output)
|
||||
sys.exit(ExitCode.missing_dependency)
|
||||
return set(lang.strip() for lang in langs.splitlines()[1:])
|
||||
|
||||
|
||||
def get_orientation(input_file, language: list, timeout: float, log):
|
||||
args_tesseract = [
|
||||
get_program('tesseract'),
|
||||
'-l', '+'.join(language),
|
||||
'-psm', '0',
|
||||
input_file,
|
||||
'stdout'
|
||||
]
|
||||
|
||||
try:
|
||||
stdout = check_output(
|
||||
args_tesseract, close_fds=True, stderr=STDOUT,
|
||||
universal_newlines=True, timeout=timeout)
|
||||
except TimeoutExpired:
|
||||
return OrientationConfidence(angle=0, confidence=0.0)
|
||||
except CalledProcessError as e:
|
||||
tesseract_log_output(log, e.output, input_file)
|
||||
if ('Too few characters. Skipping this page' in e.output or
|
||||
'Image too large' in e.output):
|
||||
return OrientationConfidence(0, 0)
|
||||
raise e from e
|
||||
else:
|
||||
osd = {}
|
||||
for line in stdout.splitlines():
|
||||
line = line.strip()
|
||||
parts = line.split(':', maxsplit=2)
|
||||
if len(parts) == 2:
|
||||
osd[parts[0].strip()] = parts[1].strip()
|
||||
|
||||
angle = int(osd.get('Orientation in degrees', 0))
|
||||
if 'Orientation' in osd:
|
||||
# Tesseract < 3.04.01
|
||||
# reports "Orientation in degrees" as a counterclockwise angle
|
||||
# We keep it clockwise
|
||||
assert 'Rotate' not in osd
|
||||
angle = -angle % 360
|
||||
else:
|
||||
# Tesseract == 3.04.01, hopefully also Tesseract > 3.04.01
|
||||
# reports "Orientation in degrees" as a clockwise angle
|
||||
assert 'Rotate' in osd
|
||||
|
||||
oc = OrientationConfidence(
|
||||
angle=angle,
|
||||
confidence=float(osd.get('Orientation confidence', 0)))
|
||||
return oc
|
||||
|
||||
|
||||
def tesseract_log_output(log, stdout, input_file):
|
||||
lines = stdout.splitlines()
|
||||
prefix = "{0:4d}: [tesseract] ".format(page_number(input_file))
|
||||
for line in lines:
|
||||
if line.startswith("Tesseract Open Source"):
|
||||
continue
|
||||
elif line.startswith("Warning in pixReadMem"):
|
||||
continue
|
||||
elif 'diacritics' in line:
|
||||
log.warning(prefix + "lots of diacritics - possibly poor OCR")
|
||||
elif line.startswith('OSD: Weak margin'):
|
||||
log.warning(prefix + "unsure about page orientation")
|
||||
elif 'error' in line.lower() or 'exception' in line.lower():
|
||||
log.error(prefix + line.strip())
|
||||
else:
|
||||
log.info(prefix + line.strip())
|
||||
|
||||
|
||||
def page_timedout(log, input_file):
|
||||
prefix = "{0:4d}: [tesseract] ".format(page_number(input_file))
|
||||
log.warning(prefix + " took too long to OCR - skipping")
|
||||
|
||||
|
||||
def _generate_null_hocr(output_hocr, pageinfo):
|
||||
with open(output_hocr, 'w', encoding="utf-8") as f:
|
||||
f.write(HOCR_TEMPLATE.format(
|
||||
pageinfo['width_pixels'],
|
||||
pageinfo['height_pixels']))
|
||||
|
||||
|
||||
def generate_hocr(input_file, output_hocr, language: list, tessconfig: list,
|
||||
timeout: float, pageinfo_getter, pagesegmode: int, log):
|
||||
|
||||
badxml = os.path.splitext(output_hocr)[0] + '.badxml'
|
||||
|
||||
args_tesseract = [
|
||||
get_program('tesseract'),
|
||||
'-l', '+'.join(language)
|
||||
]
|
||||
|
||||
if pagesegmode is not None:
|
||||
args_tesseract.extend(['-psm', str(pagesegmode)])
|
||||
|
||||
args_tesseract.extend([
|
||||
input_file,
|
||||
badxml,
|
||||
'hocr'
|
||||
] + tessconfig)
|
||||
try:
|
||||
stdout = check_output(
|
||||
args_tesseract, close_fds=True, stderr=STDOUT,
|
||||
universal_newlines=True, timeout=timeout)
|
||||
except TimeoutExpired:
|
||||
# Generate a HOCR file with no recognized text if tesseract times out
|
||||
# Temporary workaround to hocrTransform not being able to function if
|
||||
# it does not have a valid hOCR file.
|
||||
page_timedout(log, input_file)
|
||||
_generate_null_hocr(output_hocr, pageinfo_getter())
|
||||
except CalledProcessError as e:
|
||||
tesseract_log_output(log, e.output, input_file)
|
||||
if 'Image too large' in e.output:
|
||||
_generate_null_hocr(output_hocr, pageinfo_getter())
|
||||
return
|
||||
|
||||
raise e from e
|
||||
else:
|
||||
tesseract_log_output(log, stdout, input_file)
|
||||
if os.path.exists(badxml + '.html'):
|
||||
# Tesseract 3.02 appends suffix ".html" on its own (.badxml.html)
|
||||
shutil.move(badxml + '.html', badxml)
|
||||
elif os.path.exists(badxml + '.hocr'):
|
||||
# Tesseract 3.03 appends suffix ".hocr" on its own (.badxml.hocr)
|
||||
shutil.move(badxml + '.hocr', badxml)
|
||||
|
||||
# Tesseract 3.03 inserts source filename into hocr file without
|
||||
# escaping it, creating invalid XML and breaking the parser.
|
||||
# As a workaround, rewrite the hocr file, replacing the filename
|
||||
# with a space. Don't know if Tesseract 3.02 does the same.
|
||||
|
||||
regex_nested_single_quotes = re.compile(
|
||||
r"""title='image "([^"]*)";""")
|
||||
with open(badxml, mode='r', encoding='utf-8') as f_in, \
|
||||
open(output_hocr, mode='w', encoding='utf-8') as f_out:
|
||||
for line in f_in:
|
||||
line = regex_nested_single_quotes.sub(
|
||||
r"""title='image " ";""", line)
|
||||
f_out.write(line)
|
||||
|
||||
|
||||
def generate_pdf(input_image, skip_pdf, output_pdf, language: list,
|
||||
tessconfig: list, timeout: float, pagesegmode: int, log):
|
||||
'''Use Tesseract to render a PDF.
|
||||
|
||||
input_image -- image to analyze
|
||||
skip_pdf -- if we time out, use this file as output
|
||||
language -- list of languages to consider
|
||||
tessconfig -- tesseract configuration
|
||||
timeout -- timeout (seconds)
|
||||
log -- logger object
|
||||
'''
|
||||
|
||||
args_tesseract = [
|
||||
get_program('tesseract'),
|
||||
'-l', '+'.join(language)
|
||||
]
|
||||
|
||||
if pagesegmode is not None:
|
||||
args_tesseract.extend(['-psm', str(pagesegmode)])
|
||||
|
||||
args_tesseract.extend([
|
||||
input_image,
|
||||
os.path.splitext(output_pdf)[0], # Tesseract appends suffix
|
||||
'pdf'
|
||||
] + tessconfig)
|
||||
|
||||
try:
|
||||
stdout = check_output(
|
||||
args_tesseract, close_fds=True, stderr=STDOUT,
|
||||
universal_newlines=True, timeout=timeout)
|
||||
except TimeoutExpired:
|
||||
page_timedout(log, input_image)
|
||||
shutil.copy(skip_pdf, output_pdf)
|
||||
except CalledProcessError as e:
|
||||
tesseract_log_output(log, e.output, input_image)
|
||||
if 'Image too large' in e.output:
|
||||
shutil.copy(skip_pdf, output_pdf)
|
||||
return
|
||||
raise e from e
|
||||
else:
|
||||
tesseract_log_output(log, stdout, input_image)
|
||||
@@ -1,103 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
# © 2015 James R. Barlow: github.com/jbarlow83
|
||||
# unpaper documentation:
|
||||
# https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md
|
||||
|
||||
from subprocess import CalledProcessError, STDOUT, check_output, check_call
|
||||
from tempfile import NamedTemporaryFile
|
||||
import sys
|
||||
import os
|
||||
from functools import lru_cache
|
||||
from . import ExitCode, get_program
|
||||
|
||||
|
||||
@lru_cache(maxsize=1)
|
||||
def version():
|
||||
args_unpaper = [
|
||||
get_program('unpaper'),
|
||||
'--version'
|
||||
]
|
||||
version = check_output(
|
||||
args_unpaper, close_fds=True, universal_newlines=True,
|
||||
stderr=STDOUT, timeout=5)
|
||||
return version.strip()
|
||||
|
||||
|
||||
try:
|
||||
from PIL import Image
|
||||
except ImportError:
|
||||
print("Could not find Python3 imaging library", file=sys.stderr)
|
||||
raise
|
||||
|
||||
|
||||
def run(input_file, output_file, dpi, log, mode_args):
|
||||
args_unpaper = [
|
||||
get_program('unpaper'),
|
||||
'-v',
|
||||
'--dpi', str(dpi)
|
||||
] + mode_args
|
||||
|
||||
SUFFIXES = {'1': '.pbm', 'L': '.pgm', 'RGB': '.ppm'}
|
||||
|
||||
im = Image.open(input_file)
|
||||
if im.mode not in SUFFIXES.keys():
|
||||
log.info("Converting image to other colorspace")
|
||||
try:
|
||||
if im.mode == 'P' and len(im.getcolors()) == 2:
|
||||
im = im.convert(mode='1')
|
||||
else:
|
||||
im = im.convert(mode='RGB')
|
||||
except IOError:
|
||||
log.error(
|
||||
"Could not convert image with type " + im.mode)
|
||||
sys.exit(ExitCode.missing_dependency)
|
||||
|
||||
try:
|
||||
suffix = SUFFIXES[im.mode]
|
||||
except KeyError:
|
||||
log.error(
|
||||
"Failed to convert image to a supported format.")
|
||||
sys.exit(ExitCode.missing_dependency)
|
||||
|
||||
with NamedTemporaryFile(suffix=suffix) as input_pnm, \
|
||||
NamedTemporaryFile(suffix=suffix, mode="r+b") as output_pnm:
|
||||
im.save(input_pnm, format='PPM')
|
||||
im.close()
|
||||
|
||||
os.unlink(output_pnm.name)
|
||||
|
||||
args_unpaper.extend([input_pnm.name, output_pnm.name])
|
||||
try:
|
||||
stdout = check_output(
|
||||
args_unpaper, close_fds=True,
|
||||
universal_newlines=True, stderr=STDOUT,
|
||||
)
|
||||
except CalledProcessError as e:
|
||||
log.debug(e.output)
|
||||
raise e from e
|
||||
else:
|
||||
log.debug(stdout)
|
||||
Image.open(output_pnm.name).save(output_file)
|
||||
|
||||
|
||||
def deskew(input_file, output_file, dpi, log):
|
||||
run(input_file, output_file, dpi, log, [
|
||||
'--mask-scan-size', '100', # don't blank out narrow columns
|
||||
'--no-border-align', # don't align visible content to borders
|
||||
'--no-mask-center', # don't center visible content within page
|
||||
'--no-grayfilter', # don't remove light gray areas
|
||||
'--no-blackfilter', # don't remove solid black areas
|
||||
'--no-noisefilter', # don't remove salt and pepper noise
|
||||
'--no-blurfilter' # don't remove blurry objects/debris
|
||||
])
|
||||
|
||||
|
||||
def clean(input_file, output_file, dpi, log):
|
||||
run(input_file, output_file, dpi, log, [
|
||||
'--mask-scan-size', '100', # don't blank out narrow columns
|
||||
'--no-border-align', # don't align visible content to borders
|
||||
'--no-mask-center', # don't center visible content within page
|
||||
'--no-grayfilter', # don't remove light gray areas
|
||||
'--no-blackfilter', # don't remove solid black areas
|
||||
'--no-deskew', # don't deskew
|
||||
])
|
||||
-338
@@ -1,338 +0,0 @@
|
||||
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
|
||||
<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN"
|
||||
"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
|
||||
<!-- Generated by graphviz version 2.38.0 (20140413.2041)
|
||||
-->
|
||||
<!-- Title: Pipeline: Pages: 1 -->
|
||||
<svg width="1444pt" height="973pt"
|
||||
viewBox="0.00 0.00 1444.00 973.18" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
|
||||
<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 969.181)">
|
||||
<title>Pipeline:</title>
|
||||
<polygon fill="white" stroke="none" points="-4,4 -4,-969.181 1440,-969.181 1440,4 -4,4"/>
|
||||
<g id="clust1" class="cluster"><title>clustertasks</title>
|
||||
<polygon fill="none" stroke="black" points="8,-8 8,-957.181 1428,-957.181 1428,-8 8,-8"/>
|
||||
<text text-anchor="middle" x="718" y="-929.181" font-family="Times,serif" font-size="30.00" fill="#ff3232">Pipeline:</text>
|
||||
</g>
|
||||
<!-- t0 -->
|
||||
<g id="node1" class="node"><title>t0</title>
|
||||
<polygon fill="#efa03b" stroke="black" points="1219.77,-911.181 1034.23,-911.181 1030.23,-907.181 1030.23,-875.181 1215.77,-875.181 1219.77,-879.181 1219.77,-911.181"/>
|
||||
<polyline fill="none" stroke="black" points="1215.77,-907.181 1030.23,-907.181 "/>
|
||||
<polyline fill="none" stroke="black" points="1215.77,-907.181 1215.77,-875.181 "/>
|
||||
<polyline fill="none" stroke="black" points="1215.77,-907.181 1219.77,-911.181 "/>
|
||||
<text text-anchor="middle" x="1125" y="-887.181" font-family="Times,serif" font-size="20.00">triage</text>
|
||||
</g>
|
||||
<!-- t1 -->
|
||||
<g id="node2" class="node"><title>t1</title>
|
||||
<polygon fill="#efa03b" stroke="black" points="1238.54,-853.181 1015.46,-853.181 1011.46,-849.181 1011.46,-817.181 1234.54,-817.181 1238.54,-821.181 1238.54,-853.181"/>
|
||||
<polyline fill="none" stroke="black" points="1234.54,-849.181 1011.46,-849.181 "/>
|
||||
<polyline fill="none" stroke="black" points="1234.54,-849.181 1234.54,-817.181 "/>
|
||||
<polyline fill="none" stroke="black" points="1234.54,-849.181 1238.54,-853.181 "/>
|
||||
<text text-anchor="middle" x="1125" y="-829.181" font-family="Times,serif" font-size="20.00">repair_pdf</text>
|
||||
</g>
|
||||
<!-- t0->t1 -->
|
||||
<g id="edge1" class="edge"><title>t0->t1</title>
|
||||
<path fill="none" stroke="#0044a0" d="M1125,-875.075C1125,-871.384 1125,-867.394 1125,-863.424"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="1128.5,-863.182 1125,-853.182 1121.5,-863.182 1128.5,-863.182"/>
|
||||
</g>
|
||||
<!-- t2 -->
|
||||
<g id="node3" class="node"><title>t2</title>
|
||||
<polygon fill="#efa03b" stroke="black" points="1329.11,-774.253 1125,-791.156 920.888,-774.253 921.078,-746.905 1328.92,-746.905 1329.11,-774.253"/>
|
||||
<polygon fill="none" stroke="black" points="1333.13,-777.932 1125,-795.167 916.866,-777.932 917.11,-742.906 1332.89,-742.906 1333.13,-777.932"/>
|
||||
<text text-anchor="middle" x="1125" y="-760.694" font-family="Times,serif" font-size="20.00">split_pages</text>
|
||||
</g>
|
||||
<!-- t1->t2 -->
|
||||
<g id="edge2" class="edge"><title>t1->t2</title>
|
||||
<path fill="none" stroke="#0044a0" d="M1125,-817.059C1125,-813.44 1125,-809.484 1125,-805.438"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="1128.5,-805.334 1125,-795.334 1121.5,-805.334 1128.5,-805.334"/>
|
||||
</g>
|
||||
<!-- t15 -->
|
||||
<g id="node17" class="node"><title>t15</title>
|
||||
<polygon fill="#efa03b" stroke="black" points="632.082,-716.208 293.918,-716.208 289.918,-712.208 289.918,-680.208 628.082,-680.208 632.082,-684.208 632.082,-716.208"/>
|
||||
<polyline fill="none" stroke="black" points="628.082,-712.208 289.918,-712.208 "/>
|
||||
<polyline fill="none" stroke="black" points="628.082,-712.208 628.082,-680.208 "/>
|
||||
<polyline fill="none" stroke="black" points="628.082,-712.208 632.082,-716.208 "/>
|
||||
<text text-anchor="middle" x="461" y="-692.208" font-family="Times,serif" font-size="20.00">generate_postscript_stub</text>
|
||||
</g>
|
||||
<!-- t1->t15 -->
|
||||
<g id="edge23" class="edge"><title>t1->t15</title>
|
||||
<path fill="none" stroke="#0044a0" d="M1026.3,-817.165C989.157,-810.572 946.587,-802.788 908,-795.181 781.899,-770.319 636.479,-738.51 546.633,-718.49"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="547.289,-715.05 536.767,-716.289 545.765,-721.882 547.289,-715.05"/>
|
||||
</g>
|
||||
<!-- t18 -->
|
||||
<g id="node19" class="node"><title>t18</title>
|
||||
<polygon fill="#efa03b" stroke="black" points="1025.79,-156.452 1221,-129.134 1416.21,-156.452 1416.03,-200.654 1025.97,-200.654 1025.79,-156.452"/>
|
||||
<polygon fill="none" stroke="black" points="1021.78,-152.971 1221,-125.091 1420.22,-152.971 1420.01,-204.657 1021.99,-204.657 1021.78,-152.971"/>
|
||||
<text text-anchor="middle" x="1221" y="-162.669" font-family="Times,serif" font-size="20.00">merge_pages_qpdf</text>
|
||||
</g>
|
||||
<!-- t1->t18 -->
|
||||
<g id="edge33" class="edge"><title>t1->t18</title>
|
||||
<path fill="none" stroke="#0044a0" d="M1238.67,-826.639C1321.4,-814.236 1419,-782.049 1419,-699.208 1419,-699.208 1419,-699.208 1419,-319.208 1419,-280.294 1424,-263.161 1398,-234.208 1389.64,-224.894 1379.82,-216.923 1369.17,-210.101"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="1370.83,-207.019 1360.46,-204.872 1367.23,-213.02 1370.83,-207.019"/>
|
||||
</g>
|
||||
<!-- t3 -->
|
||||
<g id="node4" class="node"><title>t3</title>
|
||||
<polygon fill="#efa03b" stroke="black" points="1186.88,-716.208 905.117,-716.208 901.117,-712.208 901.117,-680.208 1182.88,-680.208 1186.88,-684.208 1186.88,-716.208"/>
|
||||
<polyline fill="none" stroke="black" points="1182.88,-712.208 901.117,-712.208 "/>
|
||||
<polyline fill="none" stroke="black" points="1182.88,-712.208 1182.88,-680.208 "/>
|
||||
<polyline fill="none" stroke="black" points="1182.88,-712.208 1186.88,-716.208 "/>
|
||||
<text text-anchor="middle" x="1044" y="-692.208" font-family="Times,serif" font-size="20.00">rasterize_preview</text>
|
||||
</g>
|
||||
<!-- t2->t3 -->
|
||||
<g id="edge3" class="edge"><title>t2->t3</title>
|
||||
<path fill="none" stroke="#0044a0" d="M1097.12,-742.813C1089.24,-736.345 1080.66,-729.296 1072.73,-722.788"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="1074.71,-719.888 1064.76,-716.249 1070.27,-725.299 1074.71,-719.888"/>
|
||||
</g>
|
||||
<!-- t4 -->
|
||||
<g id="node5" class="node"><title>t4</title>
|
||||
<polygon fill="#efa03b" stroke="black" points="1258.15,-658.208 1023.85,-658.208 1019.85,-654.208 1019.85,-622.208 1254.15,-622.208 1258.15,-626.208 1258.15,-658.208"/>
|
||||
<polyline fill="none" stroke="black" points="1254.15,-654.208 1019.85,-654.208 "/>
|
||||
<polyline fill="none" stroke="black" points="1254.15,-654.208 1254.15,-622.208 "/>
|
||||
<polyline fill="none" stroke="black" points="1254.15,-654.208 1258.15,-658.208 "/>
|
||||
<text text-anchor="middle" x="1139" y="-634.208" font-family="Times,serif" font-size="20.00">orient_page</text>
|
||||
</g>
|
||||
<!-- t2->t4 -->
|
||||
<g id="edge5" class="edge"><title>t2->t4</title>
|
||||
<path fill="none" stroke="#0044a0" d="M1171.65,-742.795C1181.42,-735.692 1190.44,-726.864 1196,-716.208 1203.4,-702.023 1203.46,-694.36 1196,-680.208 1192.84,-674.222 1188.31,-668.98 1183.15,-664.445"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="1185.3,-661.676 1175.25,-658.302 1181,-667.203 1185.3,-661.676"/>
|
||||
</g>
|
||||
<!-- t3->t4 -->
|
||||
<g id="edge4" class="edge"><title>t3->t4</title>
|
||||
<path fill="none" stroke="#0044a0" d="M1073.02,-680.102C1081.95,-674.836 1091.92,-668.963 1101.34,-663.407"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="1103.32,-666.302 1110.16,-658.209 1099.77,-660.272 1103.32,-666.302"/>
|
||||
</g>
|
||||
<!-- t5 -->
|
||||
<g id="node6" class="node"><title>t5</title>
|
||||
<polygon fill="#efa03b" stroke="black" points="1271.3,-600.208 920.701,-600.208 916.701,-596.208 916.701,-564.208 1267.3,-564.208 1271.3,-568.208 1271.3,-600.208"/>
|
||||
<polyline fill="none" stroke="black" points="1267.3,-596.208 916.701,-596.208 "/>
|
||||
<polyline fill="none" stroke="black" points="1267.3,-596.208 1267.3,-564.208 "/>
|
||||
<polyline fill="none" stroke="black" points="1267.3,-596.208 1271.3,-600.208 "/>
|
||||
<text text-anchor="middle" x="1094" y="-576.208" font-family="Times,serif" font-size="20.00">rasterize_with_ghostscript</text>
|
||||
</g>
|
||||
<!-- t4->t5 -->
|
||||
<g id="edge6" class="edge"><title>t4->t5</title>
|
||||
<path fill="none" stroke="#0044a0" d="M1125.25,-622.102C1121.76,-617.759 1117.94,-613.003 1114.21,-608.353"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="1116.65,-605.812 1107.66,-600.209 1111.2,-610.197 1116.65,-605.812"/>
|
||||
</g>
|
||||
<!-- t10 -->
|
||||
<g id="node12" class="node"><title>t10</title>
|
||||
<polygon fill="#00cc66" stroke="black" points="334,-348.208 35.7812,-320.208 334,-292.208 632.219,-320.208 334,-348.208"/>
|
||||
<text text-anchor="middle" x="334" y="-314.208" font-family="Times,serif" font-size="20.00">select_image_layer</text>
|
||||
</g>
|
||||
<!-- t4->t10 -->
|
||||
<g id="edge15" class="edge"><title>t4->t10</title>
|
||||
<path fill="none" stroke="#0044a0" d="M1019.87,-634.085C799.18,-622.991 349,-592.156 349,-525.208 349,-525.208 349,-525.208 349,-465.208 349,-428.606 344.147,-387.052 339.961,-358.022"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="343.393,-357.303 338.46,-347.926 336.469,-358.332 343.393,-357.303"/>
|
||||
</g>
|
||||
<!-- t16 -->
|
||||
<g id="node15" class="node"><title>t16</title>
|
||||
<polygon fill="#efa03b" stroke="black" points="1380.34,-270.208 1159.66,-270.208 1155.66,-266.208 1155.66,-234.208 1376.34,-234.208 1380.34,-238.208 1380.34,-270.208"/>
|
||||
<polyline fill="none" stroke="black" points="1376.34,-266.208 1155.66,-266.208 "/>
|
||||
<polyline fill="none" stroke="black" points="1376.34,-266.208 1376.34,-234.208 "/>
|
||||
<polyline fill="none" stroke="black" points="1376.34,-266.208 1380.34,-270.208 "/>
|
||||
<text text-anchor="middle" x="1268" y="-246.208" font-family="Times,serif" font-size="20.00">skip_page</text>
|
||||
</g>
|
||||
<!-- t4->t16 -->
|
||||
<g id="edge20" class="edge"><title>t4->t16</title>
|
||||
<path fill="none" stroke="#0044a0" d="M1258.35,-631.473C1326.7,-619.809 1399,-591.745 1399,-525.208 1399,-525.208 1399,-525.208 1399,-397.208 1399,-350.33 1418.37,-328.748 1389,-292.208 1383.58,-285.469 1376.99,-279.879 1369.71,-275.244"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="1371.3,-272.123 1360.88,-270.231 1367.85,-278.211 1371.3,-272.123"/>
|
||||
</g>
|
||||
<!-- t14 -->
|
||||
<g id="node16" class="node"><title>t14</title>
|
||||
<polygon fill="#66ccff" stroke="black" points="1380.24,-338.208 999.76,-338.208 995.76,-334.208 995.76,-302.208 1376.24,-302.208 1380.24,-306.208 1380.24,-338.208"/>
|
||||
<polyline fill="none" stroke="black" points="1376.24,-334.208 995.76,-334.208 "/>
|
||||
<polyline fill="none" stroke="black" points="1376.24,-334.208 1376.24,-302.208 "/>
|
||||
<polyline fill="none" stroke="black" points="1376.24,-334.208 1380.24,-338.208 "/>
|
||||
<text text-anchor="middle" x="1188" y="-314.208" font-family="Times,serif" font-size="20.00">tesseract_ocr_and_render_pdf</text>
|
||||
</g>
|
||||
<!-- t4->t14 -->
|
||||
<g id="edge22" class="edge"><title>t4->t14</title>
|
||||
<path fill="none" stroke="#0044a0" d="M1244.5,-622.179C1297.25,-607.003 1350,-578.503 1350,-525.208 1350,-525.208 1350,-525.208 1350,-465.208 1350,-422.752 1366.76,-403.169 1340,-370.208 1330.4,-358.377 1317.91,-349.368 1304.22,-342.513"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="1305.62,-339.304 1295.07,-338.313 1302.7,-345.666 1305.62,-339.304"/>
|
||||
</g>
|
||||
<!-- t6 -->
|
||||
<g id="node7" class="node"><title>t6</title>
|
||||
<polygon fill="#efa03b" stroke="black" points="1074.74,-542.208 779.258,-542.208 775.258,-538.208 775.258,-506.208 1070.74,-506.208 1074.74,-510.208 1074.74,-542.208"/>
|
||||
<polyline fill="none" stroke="black" points="1070.74,-538.208 775.258,-538.208 "/>
|
||||
<polyline fill="none" stroke="black" points="1070.74,-538.208 1070.74,-506.208 "/>
|
||||
<polyline fill="none" stroke="black" points="1070.74,-538.208 1074.74,-542.208 "/>
|
||||
<text text-anchor="middle" x="925" y="-518.208" font-family="Times,serif" font-size="20.00">preprocess_deskew</text>
|
||||
</g>
|
||||
<!-- t5->t6 -->
|
||||
<g id="edge7" class="edge"><title>t5->t6</title>
|
||||
<path fill="none" stroke="#0044a0" d="M1042.38,-564.102C1024.52,-558.185 1004.35,-551.5 985.823,-545.362"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="986.901,-542.032 976.308,-542.209 984.699,-548.677 986.901,-542.032"/>
|
||||
</g>
|
||||
<!-- t9 -->
|
||||
<g id="node11" class="node"><title>t9</title>
|
||||
<polygon fill="#efa03b" stroke="black" points="1013,-426.208 694.762,-398.208 1013,-370.208 1331.24,-398.208 1013,-426.208"/>
|
||||
<text text-anchor="middle" x="1013" y="-392.208" font-family="Times,serif" font-size="20.00">select_image_for_pdf</text>
|
||||
</g>
|
||||
<!-- t5->t9 -->
|
||||
<g id="edge13" class="edge"><title>t5->t9</title>
|
||||
<path fill="none" stroke="#0044a0" d="M1093.89,-563.996C1093.29,-548.44 1091.11,-525.146 1084,-506.208 1073.94,-479.426 1056.13,-452.609 1040.86,-432.521"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="1043.62,-430.369 1034.72,-424.619 1038.09,-434.663 1043.62,-430.369"/>
|
||||
</g>
|
||||
<!-- t7 -->
|
||||
<g id="node8" class="node"><title>t7</title>
|
||||
<polygon fill="#efa03b" stroke="black" points="993.95,-484.208 716.05,-484.208 712.05,-480.208 712.05,-448.208 989.95,-448.208 993.95,-452.208 993.95,-484.208"/>
|
||||
<polyline fill="none" stroke="black" points="989.95,-480.208 712.05,-480.208 "/>
|
||||
<polyline fill="none" stroke="black" points="989.95,-480.208 989.95,-448.208 "/>
|
||||
<polyline fill="none" stroke="black" points="989.95,-480.208 993.95,-484.208 "/>
|
||||
<text text-anchor="middle" x="853" y="-460.208" font-family="Times,serif" font-size="20.00">preprocess_clean</text>
|
||||
</g>
|
||||
<!-- t6->t7 -->
|
||||
<g id="edge8" class="edge"><title>t6->t7</title>
|
||||
<path fill="none" stroke="#0044a0" d="M903.006,-506.102C896.726,-501.216 889.771,-495.807 883.095,-490.615"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="884.901,-487.586 874.859,-484.209 880.604,-493.111 884.901,-487.586"/>
|
||||
</g>
|
||||
<!-- t6->t9 -->
|
||||
<g id="edge12" class="edge"><title>t6->t9</title>
|
||||
<path fill="none" stroke="#0044a0" d="M977.454,-506.003C987.329,-500.504 996.562,-493.377 1003,-484.208 1012.67,-470.441 1015.74,-452.229 1016.16,-436.195"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="1019.66,-436.018 1016.09,-426.041 1012.66,-436.063 1019.66,-436.018"/>
|
||||
</g>
|
||||
<!-- t8 -->
|
||||
<g id="node9" class="node"><title>t8</title>
|
||||
<polygon fill="#00cc66" stroke="black" points="676.666,-416.208 387.334,-416.208 383.334,-412.208 383.334,-380.208 672.666,-380.208 676.666,-384.208 676.666,-416.208"/>
|
||||
<polyline fill="none" stroke="black" points="672.666,-412.208 383.334,-412.208 "/>
|
||||
<polyline fill="none" stroke="black" points="672.666,-412.208 672.666,-380.208 "/>
|
||||
<polyline fill="none" stroke="black" points="672.666,-412.208 676.666,-416.208 "/>
|
||||
<text text-anchor="middle" x="530" y="-392.208" font-family="Times,serif" font-size="20.00">ocr_tesseract_hocr</text>
|
||||
</g>
|
||||
<!-- t7->t8 -->
|
||||
<g id="edge9" class="edge"><title>t7->t8</title>
|
||||
<path fill="none" stroke="#0044a0" d="M769.399,-448.125C724.645,-438.98 669.394,-427.691 623.252,-418.262"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="623.748,-414.791 613.25,-416.219 622.347,-421.65 623.748,-414.791"/>
|
||||
</g>
|
||||
<!-- t7->t9 -->
|
||||
<g id="edge11" class="edge"><title>t7->t9</title>
|
||||
<path fill="none" stroke="#0044a0" d="M894.62,-448.039C911.413,-441.112 931.162,-432.966 949.666,-425.333"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="951.009,-428.565 958.918,-421.516 948.339,-422.094 951.009,-428.565"/>
|
||||
</g>
|
||||
<!-- t11 -->
|
||||
<g id="node10" class="node"><title>t11</title>
|
||||
<polygon fill="#00cc66" stroke="black" points="938.109,-338.208 653.891,-338.208 649.891,-334.208 649.891,-302.208 934.109,-302.208 938.109,-306.208 938.109,-338.208"/>
|
||||
<polyline fill="none" stroke="black" points="934.109,-334.208 649.891,-334.208 "/>
|
||||
<polyline fill="none" stroke="black" points="934.109,-334.208 934.109,-302.208 "/>
|
||||
<polyline fill="none" stroke="black" points="934.109,-334.208 938.109,-338.208 "/>
|
||||
<text text-anchor="middle" x="794" y="-314.208" font-family="Times,serif" font-size="20.00">render_hocr_page</text>
|
||||
</g>
|
||||
<!-- t8->t11 -->
|
||||
<g id="edge10" class="edge"><title>t8->t11</title>
|
||||
<path fill="none" stroke="#0044a0" d="M589.247,-380.152C629.442,-368.58 682.727,-353.241 724.863,-341.111"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="725.853,-344.468 734.495,-338.338 723.917,-337.741 725.853,-344.468"/>
|
||||
</g>
|
||||
<!-- t12 -->
|
||||
<g id="node14" class="node"><title>t12</title>
|
||||
<polygon fill="#00cc66" stroke="black" points="1118.49,-270.208 775.514,-270.208 771.514,-266.208 771.514,-234.208 1114.49,-234.208 1118.49,-238.208 1118.49,-270.208"/>
|
||||
<polyline fill="none" stroke="black" points="1114.49,-266.208 771.514,-266.208 "/>
|
||||
<polyline fill="none" stroke="black" points="1114.49,-266.208 1114.49,-234.208 "/>
|
||||
<polyline fill="none" stroke="black" points="1114.49,-266.208 1118.49,-270.208 "/>
|
||||
<text text-anchor="middle" x="945" y="-246.208" font-family="Times,serif" font-size="20.00">render_hocr_debug_page</text>
|
||||
</g>
|
||||
<!-- t8->t12 -->
|
||||
<g id="edge19" class="edge"><title>t8->t12</title>
|
||||
<path fill="none" stroke="#0044a0" d="M620.537,-380.161C641.947,-376.512 664.736,-372.939 686,-370.208 714.866,-366.5 927.304,-369.633 947,-348.208 963.502,-330.256 960.281,-301.363 954.611,-280.149"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="957.925,-279.012 951.707,-270.433 951.218,-281.017 957.925,-279.012"/>
|
||||
</g>
|
||||
<!-- t13 -->
|
||||
<g id="node13" class="node"><title>t13</title>
|
||||
<polygon fill="#00cc66" stroke="black" points="753.082,-270.208 494.918,-270.208 490.918,-266.208 490.918,-234.208 749.082,-234.208 753.082,-238.208 753.082,-270.208"/>
|
||||
<polyline fill="none" stroke="black" points="749.082,-266.208 490.918,-266.208 "/>
|
||||
<polyline fill="none" stroke="black" points="749.082,-266.208 749.082,-234.208 "/>
|
||||
<polyline fill="none" stroke="black" points="749.082,-266.208 753.082,-270.208 "/>
|
||||
<text text-anchor="middle" x="622" y="-246.208" font-family="Times,serif" font-size="20.00">add_text_layer</text>
|
||||
</g>
|
||||
<!-- t11->t13 -->
|
||||
<g id="edge16" class="edge"><title>t11->t13</title>
|
||||
<path fill="none" stroke="#0044a0" d="M749.258,-302.039C726.862,-293.446 699.574,-282.975 676.019,-273.936"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="677.108,-270.605 666.518,-270.29 674.6,-277.14 677.108,-270.605"/>
|
||||
</g>
|
||||
<!-- t9->t10 -->
|
||||
<g id="edge14" class="edge"><title>t9->t10</title>
|
||||
<path fill="none" stroke="#0044a0" d="M877.633,-382.056C761.19,-369.023 593.788,-350.286 475.578,-337.054"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="475.697,-333.546 465.37,-335.912 474.919,-340.503 475.697,-333.546"/>
|
||||
</g>
|
||||
<!-- t9->t12 -->
|
||||
<g id="edge18" class="edge"><title>t9->t12</title>
|
||||
<path fill="none" stroke="#0044a0" d="M998.887,-371.447C994.931,-364.003 990.702,-355.831 987,-348.208 983.822,-341.663 967.96,-305.616 956.669,-279.865"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="959.82,-278.337 952.601,-270.582 953.409,-281.146 959.82,-278.337"/>
|
||||
</g>
|
||||
<!-- t9->t14 -->
|
||||
<g id="edge21" class="edge"><title>t9->t14</title>
|
||||
<path fill="none" stroke="#0044a0" d="M1065.03,-374.611C1088.59,-364.381 1116.27,-352.359 1139.4,-342.314"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="1140.9,-345.479 1148.68,-338.285 1138.11,-339.058 1140.9,-345.479"/>
|
||||
</g>
|
||||
<!-- t10->t13 -->
|
||||
<g id="edge17" class="edge"><title>t10->t13</title>
|
||||
<path fill="none" stroke="#0044a0" d="M417.688,-300.029C455.345,-291.399 499.718,-281.231 537.473,-272.578"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="538.461,-275.943 547.427,-270.297 536.898,-269.12 538.461,-275.943"/>
|
||||
</g>
|
||||
<!-- t17 -->
|
||||
<g id="node18" class="node"><title>t17</title>
|
||||
<polygon fill="#efa03b" stroke="black" points="540.724,-156.455 770,-129.143 999.276,-156.455 999.062,-200.646 540.938,-200.646 540.724,-156.455"/>
|
||||
<polygon fill="none" stroke="black" points="536.704,-152.903 770,-125.112 1003.3,-152.903 1003.05,-204.648 536.954,-204.648 536.704,-152.903"/>
|
||||
<text text-anchor="middle" x="770" y="-162.669" font-family="Times,serif" font-size="20.00">merge_pages_ghostscript</text>
|
||||
</g>
|
||||
<!-- t13->t17 -->
|
||||
<g id="edge27" class="edge"><title>t13->t17</title>
|
||||
<path fill="none" stroke="#0044a0" d="M653.026,-234.114C665.992,-226.971 681.653,-218.343 697.24,-209.755"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="699.319,-212.606 706.388,-204.715 695.941,-206.475 699.319,-212.606"/>
|
||||
</g>
|
||||
<!-- t13->t18 -->
|
||||
<g id="edge31" class="edge"><title>t13->t18</title>
|
||||
<path fill="none" stroke="#0044a0" d="M753.329,-235.235C756.584,-234.884 759.812,-234.541 763,-234.208 873.497,-222.668 902.059,-228.201 1012,-212.208 1023.74,-210.5 1035.81,-208.554 1047.95,-206.456"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="1048.91,-209.84 1058.16,-204.659 1047.7,-202.946 1048.91,-209.84"/>
|
||||
</g>
|
||||
<!-- t12->t17 -->
|
||||
<g id="edge28" class="edge"><title>t12->t17</title>
|
||||
<path fill="none" stroke="#0044a0" d="M908.314,-234.114C892.552,-226.77 873.424,-217.858 854.484,-209.033"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="855.759,-205.766 845.216,-204.715 852.803,-212.111 855.759,-205.766"/>
|
||||
</g>
|
||||
<!-- t12->t18 -->
|
||||
<g id="edge32" class="edge"><title>t12->t18</title>
|
||||
<path fill="none" stroke="#0044a0" d="M1002.86,-234.114C1029.07,-226.37 1061.19,-216.881 1092.64,-207.59"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="1093.77,-210.905 1102.37,-204.715 1091.79,-204.192 1093.77,-210.905"/>
|
||||
</g>
|
||||
<!-- t16->t17 -->
|
||||
<g id="edge24" class="edge"><title>t16->t17</title>
|
||||
<path fill="none" stroke="#0044a0" d="M1155.57,-234.546C1111.13,-227.821 1059.63,-219.853 1013,-212.208 1001.53,-210.326 989.752,-208.365 977.872,-206.363"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="978.316,-202.888 967.872,-204.672 977.149,-209.79 978.316,-202.888"/>
|
||||
</g>
|
||||
<!-- t16->t18 -->
|
||||
<g id="edge29" class="edge"><title>t16->t18</title>
|
||||
<path fill="none" stroke="#0044a0" d="M1258.03,-233.915C1254.58,-227.933 1250.55,-220.928 1246.43,-213.785"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="1249.24,-211.645 1241.21,-204.729 1243.17,-215.141 1249.24,-211.645"/>
|
||||
</g>
|
||||
<!-- t14->t17 -->
|
||||
<g id="edge26" class="edge"><title>t14->t17</title>
|
||||
<path fill="none" stroke="#0044a0" d="M1172.36,-302.154C1164.33,-293.013 1154.66,-281.362 1147,-270.208 1136.64,-255.121 1141.88,-244.862 1127,-234.208 1125.19,-232.915 1055.67,-220.232 978.45,-206.446"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="978.964,-202.982 968.505,-204.672 977.735,-209.874 978.964,-202.982"/>
|
||||
</g>
|
||||
<!-- t14->t18 -->
|
||||
<g id="edge30" class="edge"><title>t14->t18</title>
|
||||
<path fill="none" stroke="#0044a0" d="M1310.22,-302.184C1345.8,-294.579 1378.07,-284.119 1389,-270.208 1408.78,-245.028 1391.25,-224.765 1361.2,-209.211"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="1362.48,-205.944 1351.96,-204.742 1359.44,-212.246 1362.48,-205.944"/>
|
||||
</g>
|
||||
<!-- t15->t17 -->
|
||||
<g id="edge25" class="edge"><title>t15->t17</title>
|
||||
<path fill="none" stroke="#0044a0" d="M289.656,-684.797C164.646,-670.853 17,-641.95 17,-583.208 17,-583.208 17,-583.208 17,-319.208 17,-213.417 306.554,-181.327 526.553,-172.213"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="526.794,-175.706 536.646,-171.808 526.514,-168.711 526.794,-175.706"/>
|
||||
</g>
|
||||
<!-- t19 -->
|
||||
<g id="node20" class="node"><title>t19</title>
|
||||
<polygon fill="#efa03b" stroke="black" points="844.361,-47.3406 995,-20.006 1145.64,-47.3406 1145.5,-91.5689 844.501,-91.5689 844.361,-47.3406"/>
|
||||
<polygon fill="none" stroke="black" points="840.355,-43.9965 995,-15.9349 1149.65,-43.9965 1149.48,-95.5749 840.519,-95.5749 840.355,-43.9965"/>
|
||||
<text text-anchor="middle" x="995" y="-53.565" font-family="Times,serif" font-size="20.00">copy_final</text>
|
||||
</g>
|
||||
<!-- t17->t19 -->
|
||||
<g id="edge35" class="edge"><title>t17->t19</title>
|
||||
<path fill="none" stroke="#0044a0" d="M841.81,-133.486C864.177,-122.839 889.024,-111.011 912.085,-100.034"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="913.64,-103.17 921.165,-95.7118 910.631,-96.8497 913.64,-103.17"/>
|
||||
</g>
|
||||
<!-- t18->t19 -->
|
||||
<g id="edge34" class="edge"><title>t18->t19</title>
|
||||
<path fill="none" stroke="#0044a0" d="M1151.35,-134.66C1128.23,-123.705 1102.26,-111.399 1078.23,-100.009"/>
|
||||
<polygon fill="#0044a0" stroke="#0044a0" points="1079.66,-96.8131 1069.12,-95.6933 1076.66,-103.139 1079.66,-96.8131"/>
|
||||
</g>
|
||||
</g>
|
||||
</svg>
|
||||
|
Before Width: | Height: | Size: 23 KiB |
@@ -1,2 +0,0 @@
|
||||
[pytest]
|
||||
norecursedirs = lib .pc
|
||||
@@ -1,9 +0,0 @@
|
||||
# requirements.txt can be used to replicate the developer's build environment
|
||||
# setup.py lists a separate set of requirements that are looser to simplify
|
||||
# installation
|
||||
ruffus==2.6.3
|
||||
Pillow==3.3.0
|
||||
reportlab==3.2.0
|
||||
PyPDF2==1.26
|
||||
img2pdf==0.2.1
|
||||
cffi==1.5.2
|
||||
@@ -1,9 +0,0 @@
|
||||
[bdist_wheel]
|
||||
python-tag = py34
|
||||
|
||||
[aliases]
|
||||
test=pytest
|
||||
|
||||
[check-manifest]
|
||||
ignore =
|
||||
.github
|
||||
@@ -1,235 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
# © 2015 James R. Barlow: github.com/jbarlow83
|
||||
|
||||
from __future__ import print_function, unicode_literals
|
||||
|
||||
import sys
|
||||
if sys.version_info < (3, 4):
|
||||
print("Python 3.4 or newer is required", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
from setuptools import setup # nopep8
|
||||
from subprocess import STDOUT, check_output, CalledProcessError # nopep8
|
||||
from collections.abc import Mapping # nopep8
|
||||
import re # nopep8
|
||||
|
||||
|
||||
missing_program = '''
|
||||
The program '{program}' could not be executed or was not found on your
|
||||
system PATH.
|
||||
'''
|
||||
|
||||
unknown_version = '''
|
||||
OCRmyPDF requires '{program}' {need_version} or higher. Your system has
|
||||
'{program}' but we cannot tell what version is installed. Contact the
|
||||
package maintainer.
|
||||
'''
|
||||
|
||||
old_version = '''
|
||||
OCRmyPDF requires '{program}' {need_version} or higher. Your system appears
|
||||
to have {found_version}. Please update this program.
|
||||
'''
|
||||
|
||||
okay_its_optional = '''
|
||||
This program is OPTIONAL, so installation of OCRmyPDF can proceed, but
|
||||
some functionality may be missing.
|
||||
'''
|
||||
|
||||
not_okay_its_required = '''
|
||||
This program is REQUIRED for OCRmyPDF to work. Installation will abort.
|
||||
'''
|
||||
|
||||
osx_install_advice = '''
|
||||
If you have homebrew installed, try these command to install the missing
|
||||
packages:
|
||||
brew update
|
||||
brew upgrade
|
||||
brew install {package}
|
||||
'''
|
||||
|
||||
linux_install_advice = '''
|
||||
On systems with the aptitude package manager (Debian, Ubuntu), try these
|
||||
commands:
|
||||
sudo apt-get update
|
||||
sudo apt-get install {package}
|
||||
|
||||
On RPM-based systems (Red Hat, Fedora), search for instructions on
|
||||
installing the RPM for {program}.
|
||||
'''
|
||||
|
||||
|
||||
def get_platform():
|
||||
if sys.platform.startswith('freebsd'):
|
||||
return 'freebsd'
|
||||
elif sys.platform.startswith('linux'):
|
||||
return 'linux'
|
||||
return sys.platform
|
||||
|
||||
|
||||
def _error_trailer(program, package, optional, **kwargs):
|
||||
if optional:
|
||||
print(okay_its_optional.format(**locals()), file=sys.stderr)
|
||||
else:
|
||||
print(not_okay_its_required.format(**locals()), file=sys.stderr)
|
||||
|
||||
if isinstance(package, Mapping):
|
||||
package = package[get_platform()]
|
||||
|
||||
if get_platform() == 'darwin':
|
||||
print(osx_install_advice.format(**locals()), file=sys.stderr)
|
||||
elif get_platform() == 'linux':
|
||||
print(linux_install_advice.format(**locals()), file=sys.stderr)
|
||||
|
||||
|
||||
def error_missing_program(
|
||||
program,
|
||||
package,
|
||||
optional
|
||||
):
|
||||
print(missing_program.format(**locals()), file=sys.stderr)
|
||||
_error_trailer(**locals())
|
||||
|
||||
|
||||
def error_unknown_version(
|
||||
program,
|
||||
package,
|
||||
optional,
|
||||
need_version
|
||||
):
|
||||
print(unknown_version.format(**locals()), file=sys.stderr)
|
||||
_error_trailer(**locals())
|
||||
|
||||
|
||||
def error_old_version(
|
||||
program,
|
||||
package,
|
||||
optional,
|
||||
need_version,
|
||||
found_version
|
||||
):
|
||||
print(old_version.format(**locals()), file=sys.stderr)
|
||||
_error_trailer(**locals())
|
||||
|
||||
|
||||
def check_external_program(
|
||||
program,
|
||||
need_version,
|
||||
package,
|
||||
version_check_args=['--version'],
|
||||
version_scrape_regex=re.compile(r'(\d+\.\d+(?:\.\d+)?)'),
|
||||
optional=False):
|
||||
|
||||
print('Checking for {program} >= {need_version}...'.format(
|
||||
program=program, need_version=need_version))
|
||||
try:
|
||||
result = check_output(
|
||||
[program] + version_check_args,
|
||||
universal_newlines=True, stderr=STDOUT)
|
||||
except (CalledProcessError, FileNotFoundError):
|
||||
error_missing_program(program, package, optional)
|
||||
if not optional:
|
||||
sys.exit(1)
|
||||
print('Continuing install without {program}'.format(program=program))
|
||||
return
|
||||
|
||||
try:
|
||||
found_version = version_scrape_regex.search(result).group(1)
|
||||
except AttributeError:
|
||||
error_unknown_version(program, package, optional, need_version)
|
||||
sys.exit(1)
|
||||
|
||||
if found_version < need_version:
|
||||
error_old_version(program, package, optional, need_version,
|
||||
found_version)
|
||||
|
||||
print('Found {program} {found_version}'.format(
|
||||
program=program, found_version=found_version))
|
||||
|
||||
|
||||
command = next((arg for arg in sys.argv[1:] if not arg.startswith('-')), '')
|
||||
|
||||
|
||||
if command.startswith('install') or \
|
||||
command in ['check', 'test', 'nosetests', 'easy_install']:
|
||||
check_external_program(
|
||||
program='tesseract',
|
||||
need_version='3.03', # limited by Travis CI / Ubuntu 12.04 backports
|
||||
package={'darwin': 'tesseract', 'linux': 'tesseract-ocr'}
|
||||
)
|
||||
check_external_program(
|
||||
program='gs',
|
||||
need_version='9.15', # limited by Travis CI / Ubuntu 12.04 backports
|
||||
package='ghostscript'
|
||||
)
|
||||
check_external_program(
|
||||
program='unpaper',
|
||||
need_version='6.1', # latest sane version
|
||||
package='unpaper',
|
||||
optional=True
|
||||
)
|
||||
check_external_program(
|
||||
program='qpdf',
|
||||
need_version='5.0.0', # limited by Travis CI / Ubuntu 12.04 backports
|
||||
package='qpdf',
|
||||
version_check_args=['--version']
|
||||
)
|
||||
|
||||
|
||||
if 'upload' in sys.argv[1:]:
|
||||
print('Use twine to upload the package - setup.py upload is insecure')
|
||||
sys.exit(1)
|
||||
|
||||
tests_require = open('test_requirements.txt').read().splitlines()
|
||||
|
||||
setup(
|
||||
name='ocrmypdf',
|
||||
description='OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched',
|
||||
url='https://github.com/jbarlow83/OCRmyPDF',
|
||||
author='James R. Barlow',
|
||||
author_email='jim@purplerock.ca',
|
||||
license='Public Domain',
|
||||
packages=['ocrmypdf'],
|
||||
keywords=['PDF', 'OCR', 'optical character recognition', 'PDF/A', 'scanning'],
|
||||
classifiers=[
|
||||
"Programming Language :: Python :: 3",
|
||||
"Development Status :: 5 - Production/Stable",
|
||||
"Environment :: Console",
|
||||
"Intended Audience :: End Users/Desktop",
|
||||
"Intended Audience :: Science/Research",
|
||||
"Intended Audience :: System Administrators",
|
||||
"License :: OSI Approved :: MIT License",
|
||||
"Operating System :: MacOS :: MacOS X",
|
||||
"Operating System :: POSIX",
|
||||
"Operating System :: POSIX :: BSD",
|
||||
"Operating System :: POSIX :: Linux",
|
||||
"Topic :: Scientific/Engineering :: Image Recognition",
|
||||
"Topic :: Text Processing :: Indexing",
|
||||
"Topic :: Text Processing :: Linguistic",
|
||||
],
|
||||
setup_requires=[
|
||||
'setuptools_scm',
|
||||
'cffi>=1.5.0',
|
||||
'pytest-runner'
|
||||
],
|
||||
use_scm_version={'version_scheme': 'post-release'},
|
||||
cffi_modules=[
|
||||
'ocrmypdf/lib/compile_leptonica.py:ffi'
|
||||
],
|
||||
install_requires=[
|
||||
'ruffus==2.6.3', # pinned - ocrmypdf implements a 2.6.3 workaround
|
||||
'Pillow>=3.1.0', # Pillow is pretty stable
|
||||
'reportlab>=3.2.0', # oldest released version with sane image handling
|
||||
'PyPDF2>=1.26', # pure Python, so track HEAD closely
|
||||
'img2pdf>=0.2.1', # pure Python, so track HEAD closely
|
||||
'cffi>=1.5.0' # oldest version ever tested
|
||||
],
|
||||
tests_require=tests_require,
|
||||
entry_points={
|
||||
'console_scripts': [
|
||||
'ocrmypdf = ocrmypdf.__main__:run_pipeline'
|
||||
],
|
||||
},
|
||||
package_data={'ocrmypdf': ['data/sRGB.icc']},
|
||||
include_package_data=True,
|
||||
zip_safe=False)
|
||||
@@ -1,4 +0,0 @@
|
||||
deb http://httpredir.debian.org/debian stretch main
|
||||
deb http://httpredir.debian.org/debian stretch-updates main
|
||||
deb http://security.debian.org stretch/updates main
|
||||
deb http://ftp.de.debian.org/debian sid main contrib non-free
|
||||
Binary file not shown.
@@ -1,101 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
# © 2016 James R. Barlow: github.com/jbarlow83
|
||||
# Release sanity checking
|
||||
|
||||
import argparse
|
||||
from subprocess import run, PIPE, DEVNULL, STDOUT, CalledProcessError
|
||||
from git import Repo, Remote
|
||||
import logging
|
||||
import re
|
||||
import sys
|
||||
import os
|
||||
|
||||
|
||||
def test_repo(repo):
|
||||
assert not repo.is_dirty(), "Repository is dirty"
|
||||
if repo.untracked_files:
|
||||
logging.warning('Some files are untracked:')
|
||||
logging.warning('\n' + '\n'.join(repo.untracked_files))
|
||||
assert repo.active_branch.name == 'master', 'Not on branch master'
|
||||
|
||||
|
||||
def travis(args):
|
||||
repo = Repo('.')
|
||||
test_repo(repo)
|
||||
|
||||
git_describe = repo.git.describe()
|
||||
|
||||
try:
|
||||
env = os.environ.copy()
|
||||
env['SETUPTOOLS_SCM_PRETEND_VERSION'] = git_describe
|
||||
proc = run(['check-manifest'], check=True, universal_newlines=True, stdout=PIPE, stderr=STDOUT, env=env)
|
||||
logging.info(proc.stdout)
|
||||
except CalledProcessError as e:
|
||||
logging.error('MANIFEST.in error')
|
||||
logging.error(e.stdout)
|
||||
sys.exit(1)
|
||||
|
||||
run(['python3', 'setup.py', 'build'], check=True)
|
||||
|
||||
origin = Remote(repo, 'jbarlow')
|
||||
result = origin.push(refspec='master:master')[0]
|
||||
if result.flags & (1024|4|8|32|16):
|
||||
logging.error(result.summary)
|
||||
else:
|
||||
logging.info(result.summary)
|
||||
|
||||
logging.info("Pushed to Travis CI")
|
||||
logging.info("If this passes, git tag and release")
|
||||
|
||||
|
||||
def release(args):
|
||||
repo = Repo('.')
|
||||
test_repo(repo)
|
||||
|
||||
git_describe = repo.git.describe()
|
||||
|
||||
assert not git_describe.startswith('v') and not '-' in git_describe and not '+ng' in git_describe, \
|
||||
"Not tagged properly for release: " + git_describe
|
||||
|
||||
plain_version = git_describe[1:] # without 'v' prefix
|
||||
|
||||
with open('RELEASE_NOTES.rst') as f:
|
||||
notes = f.read()
|
||||
assert plain_version in notes, "Version not mentioned in release notes"
|
||||
|
||||
proc = run(['python3', 'setup.py', 'sdist', 'bdist_wheel'], universal_newlines=True, check=True, stdout=PIPE, stderr=STDOUT)
|
||||
logging.info(proc.stdout)
|
||||
|
||||
|
||||
origin = Remote(repo, 'jbarlow')
|
||||
result = origin.push(refspec='master:master', tags=True)[0]
|
||||
if result.flags & (1024|4|8|32|16):
|
||||
logging.error(result.summary)
|
||||
else:
|
||||
logging.info(result.summary)
|
||||
|
||||
run(['twine', 'upload', '-r', 'pypitest',
|
||||
'dist/ocrmypdf-{}.tar.gz'.format(plain_version),
|
||||
'dist/ocrmypdf-{}-py34-none-any.whl'.format(plain_version)], check=True, universal_newlines=True, stdout=PIPE)
|
||||
|
||||
|
||||
parser = argparse.ArgumentParser(description="ocrmypdf release tasks")
|
||||
subparsers = parser.add_subparsers()
|
||||
|
||||
push_travis = subparsers.add_parser(
|
||||
'push-travis', description="Push master to travis for testing")
|
||||
push_travis.set_defaults(func=travis)
|
||||
|
||||
release_parser = subparsers.add_parser(
|
||||
'release', description="Release to PyPI etc")
|
||||
release_parser.set_defaults(func=release)
|
||||
|
||||
|
||||
def main():
|
||||
args = parser.parse_args()
|
||||
args.func(args)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
@@ -0,0 +1,53 @@
|
||||
#! /bin/bash
|
||||
|
||||
set -x
|
||||
set -e
|
||||
|
||||
chmod +x OCRmyPDF*.AppImage
|
||||
|
||||
# run OCRmyPDF to test if the AppImage can ocr a test file
|
||||
run_appimage()
|
||||
{
|
||||
echo ""
|
||||
./OCRmyPDF*.AppImage --help
|
||||
echo ""
|
||||
./OCRmyPDF*.AppImage --list-programs
|
||||
echo ""
|
||||
./OCRmyPDF*.AppImage --list-licenses
|
||||
echo ""
|
||||
./OCRmyPDF*.AppImage ocrmypdf -l deu -s -d --jbig2-lossy --optimize 1 "$TRAVIS_BUILD_DIR"/test/test.pdf output.pdf
|
||||
echo ""
|
||||
}
|
||||
|
||||
|
||||
# check AppImage for common issues
|
||||
run_appimagelint()
|
||||
{
|
||||
wget https://github.com/TheAssassin/appimagelint/releases/download/continuous/appimagelint-x86_64.AppImage
|
||||
chmod +x appimagelint-x86_64.AppImage
|
||||
./appimagelint-x86_64.AppImage OCRmyPDF*.AppImage
|
||||
}
|
||||
|
||||
|
||||
# extract the OCRmyPDF AppImage, install pytest & test requirements and run pytest
|
||||
run_pytest()
|
||||
{
|
||||
git clone --depth=1 --branch "v$OCRMYPDF_VERSION" https://github.com/jbarlow83/OCRmyPDF.git
|
||||
./OCRmyPDF*.AppImage --appimage-extract
|
||||
|
||||
pushd squashfs-root
|
||||
./AppRun python3 -m pip install pytest
|
||||
./AppRun python3 -m pip install -r ../OCRmyPDF/requirements/test.txt
|
||||
./AppRun python3 -m pytest ../OCRmyPDF -n auto
|
||||
popd
|
||||
}
|
||||
|
||||
|
||||
run_appimage
|
||||
|
||||
run_appimagelint
|
||||
|
||||
# run_pytest
|
||||
|
||||
|
||||
|
||||
Binary file not shown.
@@ -1 +0,0 @@
|
||||
pytest>=2.7.2
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 1.4 MiB |
@@ -1,85 +0,0 @@
|
||||
These test files are used in OCRmyPDF's test suite. They do not necessarily produce OCR results
|
||||
at all and are not meant as examples of OCR output. Some are even invalid PDFs that might
|
||||
crash certain PDF viewers.
|
||||
|
||||
|
||||
Files derived from free sources
|
||||
===============================
|
||||
|
||||
These test resources come from free sources, under either public domain or Creative Commons licenses.
|
||||
In some cases they were converted from one image format to another without other changes.
|
||||
|
||||
+---------------------+--------------------------------------------------------------------------------+
|
||||
| File | Source |
|
||||
+=====================+================================================================================+
|
||||
| c02-22.pdf | `Project Gutenberg`_, Adventures of Huckleberry Finn, page 22 |
|
||||
+---------------------+--------------------------------------------------------------------------------+
|
||||
| congress.jpg | `US Congressional Records`_ (Public Domain) |
|
||||
+---------------------+--------------------------------------------------------------------------------+
|
||||
| graph.pdf | `Wikimedia: Pandas text analysis.png`_ (Public Domain) |
|
||||
+---------------------+--------------------------------------------------------------------------------+
|
||||
| lichtenstein.pdf | `Wikimedia: JPEG2000 Lichtenstein`_ (Creative Commons BY-SA 3.0) |
|
||||
+---------------------+--------------------------------------------------------------------------------+
|
||||
| LinnSequencer.jpg, | `Wikimedia: LinnSequencer`_ (Creative Commons BY-SA 3.0) |
|
||||
| linn.pdf, linn.txt | |
|
||||
+---------------------+--------------------------------------------------------------------------------+
|
||||
|
||||
|
||||
Files generated for this project
|
||||
================================
|
||||
|
||||
The following test resources were crafted specifically for this project, and can be used
|
||||
under the terms of the license in LICENSE.rst.
|
||||
|
||||
+---------------------+-----------------------+---------------------------------------------------------+
|
||||
| File | Contributor | Purpose |
|
||||
+---------------------+-----------------------+---------------------------------------------------------+
|
||||
| aspect.pdf | @jbarlow83 | test image with 200 x 100 DPI resolution |
|
||||
+---------------------+-----------------------+---------------------------------------------------------+
|
||||
| blank.pdf | @jbarlow83 | blank PDF |
|
||||
+---------------------+-----------------------+---------------------------------------------------------+
|
||||
| cmyk.pdf | @jbarlow83 | a CMYK image created in Photoshop |
|
||||
+---------------------+-----------------------+---------------------------------------------------------+
|
||||
| enormous.pdf | @jbarlow83 | very large PDF page |
|
||||
+---------------------+-----------------------+---------------------------------------------------------+
|
||||
| francais.pdf | @jbarlow83 | a page containing French accents (diacritics) |
|
||||
+---------------------+-----------------------+---------------------------------------------------------+
|
||||
| hugemono.pdf | @jbarlow83 | large monochrome 35000x35000 image in JBIG2 encoding |
|
||||
+---------------------+-----------------------+---------------------------------------------------------+
|
||||
| invalid.pdf | @jbarlow83 | a PDF file header followed by EOF marker |
|
||||
+---------------------+-----------------------+---------------------------------------------------------+
|
||||
| masks.pdf | @supergrobi | file containing stencil masks; printout of a German |
|
||||
| | | Wikipedia article (Creative Commons BY-SA) |
|
||||
+---------------------+-----------------------+---------------------------------------------------------+
|
||||
| milk.pdf | @lowesjam | linearized PDF containing some indirect objects |
|
||||
+---------------------+-----------------------+---------------------------------------------------------+
|
||||
| missing_docinfo.pdf | @jbarlow83 | PDF file with no /DocumentInfo section |
|
||||
+---------------------+-----------------------+---------------------------------------------------------+
|
||||
|
||||
Assemblies
|
||||
==========
|
||||
|
||||
These test resources are assemblies from other previously mentioned files, released under the same license terms as their input files.
|
||||
|
||||
- cardinal.pdf (four cardinal directions, rotated copies of LinnSequencer.jpg)
|
||||
- ccitt.pdf (LinnSequencer.jpg, converted to CCITT encoding)
|
||||
- encrypted_algo4.pdf (congress.jpg, encrypted with algorithm 4 - not supported by PyPDF2)
|
||||
- graph_ocred.pdf (from graph.pdf)
|
||||
- jbig2.pdf (congress.jpg, converted to JBIG2 encoding)
|
||||
- multipage.pdf (from several other files)
|
||||
- palette.pdf (congress.jpg, converted to a 256-color palette)
|
||||
- skew.pdf (from c02-22.pdf)
|
||||
- skew-encrypted.pdf (skew.pdf with encryption - access supported by PyPDF2)
|
||||
|
||||
|
||||
.. _`Wikimedia: LinnSequencer`: https://upload.wikimedia.org/wikipedia/en/b/b7/LinnSequencer_hardware_MIDI_sequencer_brochure_page_2_300dpi.jpg
|
||||
|
||||
.. _`Project Gutenberg`: https://www.gutenberg.org/files/76/76-h/76-h.htm#c2
|
||||
|
||||
.. _`US Congressional Records`: http://www.baxleystamps.com/litho/meiji/courts_1871.jpg
|
||||
|
||||
.. _`Wikimedia: Pandas text analysis.png`: https://en.wikipedia.org/wiki/File:Pandas_text_analysis.png
|
||||
|
||||
.. _`Wikimedia: JPEG2000 Lichtenstein`: https://en.wikipedia.org/wiki/JPEG_2000#/media/File:Jpeg2000_2-level_wavelet_transform-lichtenstein.png
|
||||
|
||||
.. _`Linux (Wikipedia Article)`: https://de.wikipedia.org/wiki/Linux
|
||||
Binary file not shown.
File diff suppressed because it is too large
Load Diff
Binary file not shown.
Binary file not shown.
Binary file not shown.
File diff suppressed because one or more lines are too long
Binary file not shown.
|
Before Width: | Height: | Size: 188 KiB |
Binary file not shown.
Binary file not shown.
File diff suppressed because one or more lines are too long
Binary file not shown.
Binary file not shown.
Binary file not shown.
@@ -1,3 +0,0 @@
|
||||
%PDF-1.3
|
||||
This is not a valid PDF file
|
||||
%%EOF
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
@@ -1,123 +0,0 @@
|
||||
The LinnSequencer
|
||||
32 Track MIDI Sequence Recorder
|
||||
|
||||
The LinnSequencer is a state—of—the-art composition and performance tool for the professional musician. It is
|
||||
|
||||
extremely powerful, yet amazingly simple to learn and use. It’s many remarkable features include:
|
||||
|
||||
0 Operation is similar to multi-track tape recorder with PLAY, STOP, RECORD, FAST
|
||||
FORWARD, REWIND, and LOCATE controls.
|
||||
|
||||
0 Each of the 100 sequences contains 32 simultaneous, polyphonic tracks. Each track may
|
||||
be assigned to one of 16 MIDI channels. Simultaneously plays up to 16 polyphonic
|
||||
|
||||
synthesizers !
|
||||
|
||||
0 Ultra-fast 3 1/2 ” disk drive stores complex songs in seconds and holds over 110,000 notes
|
||||
|
||||
per disk!
|
||||
|
||||
0 One or all tracks may be TRANSPOSED at the touch of a key.
|
||||
0 Exclusive real—time ERASE function makes editing FAST.
|
||||
0 Exclusive REPEAT function automatically repeats any held notes at a pre-selected
|
||||
|
||||
rhythmic value.
|
||||
|
||||
0 TIMING CORRECTION works during playback and operates without ‘chopping’ notes.
|
||||
|
||||
0 Optional SMPTE time code synchronization.
|
||||
|
||||
0 Optional remote control.
|
||||
|
||||
Recording a Sequence
|
||||
|
||||
To record a sequence, simply press RECORD and PLAY,
|
||||
then play your MIDI keyboard in time to the Sequencer’s
|
||||
click track. When the sequence loops back around to bar 1,
|
||||
you’ll hear what you played—only all timing errors will be
|
||||
|
||||
corrected! (Timing correction may be adjusted 0r defeated).
|
||||
|
||||
Any additional notes played will be added into the track
|
||||
—existing notes are not erased while recording!
|
||||
|
||||
FAST FORWARD, REWIND, and LOCATE controls
|
||||
may be used at any time to quickly access any location in
|
||||
your sequence for spot-recording. To overdub a new part,
|
||||
select a different track and start recording—while you
|
||||
record, the first‘track will play in perfect sync (unless you
|
||||
MUTE it, or SOLO another track). In this way, up to 32
|
||||
tracks may be overdubbed! All MIDI effects are recorded
|
||||
including pitch bend, modulation, velocity, aftertouch,
|
||||
sustain pedal, and program changes!
|
||||
|
||||
Editing
|
||||
|
||||
To erase a wrong note, simply hold ERASE and press
|
||||
the note to be erased just before it plays in the sequence-—
|
||||
when played back, it will be gone. Notes may also be
|
||||
|
||||
added, erased, or changed using the SINGLE STEP func-
|
||||
tion. To overdub notes at specific points within a sequence,
|
||||
|
||||
Additional Features
|
||||
|
||||
simply use LOCATE, FAST FORWARD, or REWIND to
|
||||
find the desired bar number, then start recording.
|
||||
|
||||
The INSERT/ COPY function allows you to move bars
|
||||
from one location to another—in the same sequence or a
|
||||
different one. For example, you might insert a copy of the
|
||||
first verse between the second chorus and the bridge.
|
||||
DELETE BARS operates the same way to remove
|
||||
unwanted sections.
|
||||
|
||||
Creating a Song
|
||||
|
||||
One way to create a song is to record each track all the
|
||||
way through (up to 999 bars). Another way is to record
|
||||
each basic section (verse, chorus, etc.) in individual
|
||||
sequences, then use the CREATE SONG function to “chain”
|
||||
them together. CREATE SONG will then automatically
|
||||
copy all the parts into a new sequence. If desired, you can
|
||||
even set the last few bars to repeat infinitely, for a fadeout.
|
||||
|
||||
Composition Without Compromise
|
||||
|
||||
The technology you use should never be so complex that
|
||||
it interferes with the creative process. That’s precisely why
|
||||
the LinnSequencer is designed to let you compose, record
|
||||
and edit while devoting your undivided attention to your
|
||||
music. See your Linn dealer today for a demonstration!
|
||||
|
||||
0 Simple, easy to learn operation—the 32 character LCD display clearly guides you through all operations. If needed, the
|
||||
|
||||
HELP button displays additional explanations.
|
||||
|
||||
0 Non-destructive recording—existing notes are not erased while recording.
|
||||
0 Two FOOTSWIT CH INPUTS may be assigned to remotely control many of the commonly used functions, including
|
||||
|
||||
ERASE, REPEAT, PLAY/ STOP, or LOCATE.
|
||||
|
||||
0 Two TRIGGER OUTPUTS may be programmed to output pulses at any selected note value.
|
||||
|
||||
0 Will sync to standard LinnDrum or Linn 9000 sync tone.
|
||||
|
||||
0 Utilizes ultra high—speed, 8 MHZ 80186 16 bit computer internally for FAST operation.
|
||||
0 TEMPO may be specified in BEATS-PER—MINUTE or FRAMES-PER—BEAT at 24, 25, or 30 frames per second,
|
||||
|
||||
(even drop frame!)
|
||||
|
||||
0 TEMPO may be entered numerically, adjustable in tenths of a Beat-Per-Minute increments, or by tapping quarter notes
|
||||
|
||||
on the TAP TEMPO button.
|
||||
|
||||
0 TEMPO CHANGES may be programmed into a sequence, with smooth transitions if desired.
|
||||
0 Any TIME SIGNATURE may be used, and may be changed within a song.
|
||||
|
||||
EDI]
|
||||
Linn Electronics, Inc.
|
||||
|
||||
18720 Oxnard Street, Tarzana, CA 91356
|
||||
(818) 708-8131 TELEX #298949 LINN UR
|
||||
|
||||
Binary file not shown.
Binary file not shown.
@@ -1,41 +0,0 @@
|
||||
%PDF-1.3
|
||||
%¿÷¢þ
|
||||
1 0 obj
|
||||
<< /Outlines 2 0 R /PageMode /UseNone /Pages 3 0 R /Type /Catalog >>
|
||||
endobj
|
||||
2 0 obj
|
||||
<< /Count 0 /Type /Outlines >>
|
||||
endobj
|
||||
3 0 obj
|
||||
<< /Count 1 /Kids [ 4 0 R ] /Type /Pages >>
|
||||
endobj
|
||||
4 0 obj
|
||||
<< /Contents 5 0 R /MediaBox [ 0 0 595.2756 841.8898 ] /Parent 3 0 R /Resources << /Font 6 0 R /ProcSet [ /PDF /Text /ImageB /ImageC /ImageI ] >> /Rotate 0 /Trans << >> /Type /Page >>
|
||||
endobj
|
||||
5 0 obj
|
||||
<< /Length 104 /Filter /FlateDecode >>
|
||||
stream
|
||||
xœ-Œ1
|
||||
ƒ@{O1e´ˆûEI ¢ Xþ è⢉»[¨÷Wƒ<˜bž`ÎÉŸÖÃ[ÉA
|
||||
Ô!å³D;jMN/w*Æðª êyè4¯¸y™ú•É?Ñî~ [\dX¢ý¥èÍ®’™… endstream
|
||||
endobj
|
||||
6 0 obj
|
||||
<< /F1 7 0 R >>
|
||||
endobj
|
||||
7 0 obj
|
||||
<< /BaseFont /Helvetica /Encoding /WinAnsiEncoding /Name /F1 /Subtype /Type1 /Type /Font >>
|
||||
endobj
|
||||
xref
|
||||
0 8
|
||||
0000000000 65535 f
|
||||
0000000015 00000 n
|
||||
0000000099 00000 n
|
||||
0000000145 00000 n
|
||||
0000000204 00000 n
|
||||
0000000403 00000 n
|
||||
0000000578 00000 n
|
||||
0000000609 00000 n
|
||||
trailer << /Root 1 0 R /Size 8 /ID [<85bf6c3c41ed927eb43bdfdfff4c0cb5><0304c5f87e589cb7b06f6f52dc6e6707>] >>
|
||||
startxref
|
||||
716
|
||||
%%EOF
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
@@ -1,11 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
import sys
|
||||
|
||||
|
||||
def main():
|
||||
print('qpdf dummy')
|
||||
sys.exit(2)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
@@ -1,44 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
import sys
|
||||
|
||||
|
||||
VERSION_STRING = '''tesseract 3.04.00
|
||||
leptonica-1.72
|
||||
libjpeg 8d : libpng 1.6.19 : libtiff 4.0.6 : zlib 1.2.5
|
||||
SPOOFED: return error claiming image too big
|
||||
'''
|
||||
|
||||
"""Simulates an error of Tesseract failing on attempts to process large images
|
||||
|
||||
"""
|
||||
|
||||
|
||||
def main():
|
||||
if sys.argv[1] == '--version':
|
||||
print(VERSION_STRING, file=sys.stderr)
|
||||
sys.exit(0)
|
||||
elif sys.argv[1] == '--list-langs':
|
||||
print('List of available languages (1):\neng', file=sys.stderr)
|
||||
sys.exit(0)
|
||||
elif sys.argv[-1] == 'hocr':
|
||||
print("Image too large: (33830, 14959)\n"
|
||||
"Error during processing.", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
elif sys.argv[-1] == 'pdf':
|
||||
print("Image too large: (33830, 14959)\n"
|
||||
"Error during processing.", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
elif sys.argv[-1] == 'stdout':
|
||||
print("Image too large: (33830, 14959)\n"
|
||||
"Error during processing.", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
else:
|
||||
print("Spoof doesn't understand arguments", file=sys.stderr)
|
||||
print(sys.argv, file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
sys.exit(0)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
@@ -1,137 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
import sys
|
||||
import os
|
||||
import hashlib
|
||||
import shutil
|
||||
import subprocess
|
||||
|
||||
|
||||
"""Cache output of tesseract to speed up test suite
|
||||
|
||||
The cache is keyed by a hash that includes the tesseract version, some of
|
||||
the command line, and the binary dump of the input file. The output file,
|
||||
stdout, and stderr are replicated on a cache hit.
|
||||
|
||||
Page orientation checks are also cached (-psm 0 stdout)
|
||||
|
||||
Errors and crashes are not cached.
|
||||
|
||||
Things not checked:
|
||||
-changes to tesseract installation that don't affect --version
|
||||
|
||||
Will fail on Tesseract 3.02.02 in "hocr" mode because it doesn't produce
|
||||
the incorrect file extension.
|
||||
|
||||
"""
|
||||
|
||||
|
||||
CACHE_PATH = os.path.abspath(os.path.join(
|
||||
os.path.dirname(__file__), '..', 'cache'))
|
||||
|
||||
|
||||
def real_tesseract():
|
||||
tess_args = ['tesseract'] + sys.argv[1:]
|
||||
os.execvp("tesseract", tess_args)
|
||||
return # Not reachable
|
||||
|
||||
def main():
|
||||
operation = sys.argv[-1]
|
||||
# For anything unexpected operation, defer to real tesseract binary
|
||||
if operation != 'hocr' and operation != 'pdf' and operation != 'stdout':
|
||||
real_tesseract()
|
||||
return # Not reachable
|
||||
|
||||
try:
|
||||
os.makedirs(CACHE_PATH)
|
||||
except FileExistsError:
|
||||
pass
|
||||
|
||||
m = hashlib.sha1()
|
||||
|
||||
version = subprocess.check_output(
|
||||
['tesseract', '--version'],
|
||||
stderr=subprocess.STDOUT)
|
||||
|
||||
m.update(version)
|
||||
m.update(operation.encode())
|
||||
|
||||
try:
|
||||
lang = sys.argv[sys.argv.index('-l') + 1]
|
||||
m.update(lang.encode())
|
||||
except ValueError:
|
||||
pass
|
||||
try:
|
||||
psm = sys.argv[sys.argv.index('-psm') + 1]
|
||||
m.update(psm.encode())
|
||||
except ValueError:
|
||||
pass
|
||||
|
||||
if operation == 'stdout' and psm != '0':
|
||||
real_tesseract()
|
||||
return
|
||||
|
||||
if operation == 'stdout':
|
||||
input_file = sys.argv[-2]
|
||||
output_file = 'stdout'
|
||||
else:
|
||||
input_file = sys.argv[-3]
|
||||
output_file = sys.argv[-2]
|
||||
|
||||
if operation == 'hocr':
|
||||
output_file += '.hocr'
|
||||
elif operation == 'pdf':
|
||||
output_file += '.pdf'
|
||||
|
||||
with open(input_file, 'rb') as f:
|
||||
m.update(f.read())
|
||||
cache_name = os.path.join(CACHE_PATH, m.hexdigest())
|
||||
print(cache_name)
|
||||
if os.path.exists(cache_name):
|
||||
# Cache hit
|
||||
print("Tesseract cache hit", file=sys.stderr)
|
||||
if operation != 'stdout':
|
||||
shutil.copy(cache_name, output_file)
|
||||
|
||||
# Replicate output
|
||||
with open(cache_name + '.stdout', 'r') as f:
|
||||
print(f.read(), end='')
|
||||
with open(cache_name + '.stderr', 'r') as f:
|
||||
print(f.read(), end='', file=sys.stderr)
|
||||
sys.exit(0)
|
||||
|
||||
# Cache miss
|
||||
print("Tesseract cache miss", file=sys.stderr)
|
||||
|
||||
# Call tesseract
|
||||
p = subprocess.Popen(
|
||||
['tesseract'] + sys.argv[1:],
|
||||
stdout=subprocess.PIPE, stderr=subprocess.PIPE,
|
||||
universal_newlines=True)
|
||||
stdout, stderr = p.communicate()
|
||||
|
||||
if p.returncode != 0:
|
||||
# Do not cache errors or crashes
|
||||
print("Tesseract error", file=sys.stderr)
|
||||
print(stdout, end='')
|
||||
print(stderr, end='', file=sys.stderr)
|
||||
return p.returncode
|
||||
|
||||
with open(cache_name + '.stdout', 'w') as f:
|
||||
f.write(stdout)
|
||||
with open(cache_name + '.stderr', 'w') as f:
|
||||
f.write(stderr)
|
||||
print(stdout, end='')
|
||||
print(stderr, end='', file=sys.stderr)
|
||||
|
||||
# Insert file into cache
|
||||
if output_file != 'stdout':
|
||||
if os.path.exists(output_file):
|
||||
shutil.copy(output_file, cache_name)
|
||||
else:
|
||||
print("Could not find output file", file=sys.stderr)
|
||||
else:
|
||||
open(cache_name, 'w').close()
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
@@ -1,50 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
import sys
|
||||
import os
|
||||
import signal
|
||||
|
||||
|
||||
VERSION_STRING = '''tesseract 3.04.00
|
||||
leptonica-1.72
|
||||
libjpeg 8d : libpng 1.6.19 : libtiff 4.0.6 : zlib 1.2.5
|
||||
SPOOFED: CRASH ON OCR or -psm 0
|
||||
'''
|
||||
|
||||
"""Simulates a Tesseract crash when asked to run OCR
|
||||
|
||||
It isn't strictly necessary to crash the process and that has unwanted
|
||||
side effects like triggering core dumps or error reporting, logging and such.
|
||||
It's enough to dump some text to stderr and return an error code.
|
||||
|
||||
Follows the POSIX(?) convention of returning 128 + signal number.
|
||||
|
||||
"""
|
||||
|
||||
|
||||
def main():
|
||||
if sys.argv[1] == '--version':
|
||||
print(VERSION_STRING, file=sys.stderr)
|
||||
sys.exit(0)
|
||||
elif sys.argv[1] == '--list-langs':
|
||||
print('List of available languages (1):\neng', file=sys.stderr)
|
||||
sys.exit(0)
|
||||
elif sys.argv[-1] == 'hocr':
|
||||
print("KABOOM! Tesseract failed for some reason", file=sys.stderr)
|
||||
sys.exit(128 + signal.SIGSEGV)
|
||||
elif sys.argv[-1] == 'pdf':
|
||||
print("KABOOM! Tesseract failed for some reason", file=sys.stderr)
|
||||
sys.exit(128 + signal.SIGSEGV)
|
||||
elif sys.argv[-1] == 'stdout':
|
||||
print("libc++abi.dylib: terminating with uncaught exception of type "
|
||||
"std::bad_alloc: std::bad_alloc", file=sys.stderr)
|
||||
sys.exit(128 + signal.SIGABRT)
|
||||
else:
|
||||
print("Spoof doesn't understand arguments", file=sys.stderr)
|
||||
print(sys.argv, file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
sys.exit(0)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
@@ -1,84 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
import sys
|
||||
import img2pdf
|
||||
from PIL import Image
|
||||
|
||||
|
||||
"""Tesseract no-op spoof
|
||||
|
||||
To quickly run tests where getting OCR output is not necessary.
|
||||
|
||||
In 'hocr' mode, create a .hocr file that specifies no text found.
|
||||
|
||||
In 'pdf' mode, convert the image to PDF using another program.
|
||||
|
||||
In orientation check mode, report the orientation is upright.
|
||||
"""
|
||||
|
||||
|
||||
VERSION_STRING = '''tesseract 3.04.00
|
||||
leptonica-1.72
|
||||
libjpeg 8d : libpng 1.6.19 : libtiff 4.0.6 : zlib 1.2.5
|
||||
SPOOFED
|
||||
'''
|
||||
|
||||
HOCR_TEMPLATE = '''<?xml version="1.0" encoding="UTF-8"?>
|
||||
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
|
||||
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
|
||||
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
|
||||
<head>
|
||||
<title></title>
|
||||
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
|
||||
<meta name='ocr-system' content='tesseract 3.02.02' />
|
||||
<meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word'/>
|
||||
</head>
|
||||
<body>
|
||||
<div class='ocr_page' id='page_1' title='image "x.tif"; bbox 0 0 {0} {1}; ppageno 0'>
|
||||
<div class='ocr_carea' id='block_1_1' title="bbox 0 1 {0} {1}">
|
||||
<p class='ocr_par' dir='ltr' id='par_1' title="bbox 0 1 {0} {1}">
|
||||
<span class='ocr_line' id='line_1' title="bbox 0 1 {0} {1}"><span class='ocrx_word' id='word_1' title="bbox 0 1 {0} {1}"> </span>
|
||||
</span>
|
||||
</p>
|
||||
</div>
|
||||
</div>
|
||||
</body>
|
||||
</html>'''
|
||||
|
||||
|
||||
def main():
|
||||
if sys.argv[1] == '--version':
|
||||
print(VERSION_STRING, file=sys.stderr)
|
||||
sys.exit(0)
|
||||
elif sys.argv[1] == '--list-langs':
|
||||
print('List of available languages (1):\neng', file=sys.stderr)
|
||||
sys.exit(0)
|
||||
elif sys.argv[-1] == 'hocr':
|
||||
inputf = sys.argv[-3]
|
||||
output = sys.argv[-2]
|
||||
with Image.open(inputf) as im, \
|
||||
open(output + '.hocr', 'w', encoding='utf-8') as f:
|
||||
w, h = im.size
|
||||
f.write(HOCR_TEMPLATE.format(str(w), str(h)))
|
||||
elif sys.argv[-1] == 'pdf':
|
||||
inputf = sys.argv[-3]
|
||||
output = sys.argv[-2]
|
||||
pdf_bytes = img2pdf.convert([inputf], dpi=300)
|
||||
with open(output + '.pdf', 'wb') as f:
|
||||
f.write(pdf_bytes)
|
||||
elif sys.argv[-1] == 'stdout':
|
||||
inputf = sys.argv[-2]
|
||||
print("""Orientation: 0
|
||||
Orientation in degrees: 0
|
||||
Orientation confidence: 100.00
|
||||
Script: 1
|
||||
Script confidence: 100.00""", file=sys.stderr)
|
||||
else:
|
||||
print("Spoof doesn't understand arguments", file=sys.stderr)
|
||||
print(sys.argv, file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
sys.exit(0)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
@@ -1,14 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
import sys
|
||||
|
||||
def main():
|
||||
if sys.argv[1] == '--version':
|
||||
print('0.5')
|
||||
sys.exit(0)
|
||||
|
||||
print("Only supports --version")
|
||||
sys.exit(1)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
@@ -1,61 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
# © 2015 James R. Barlow: github.com/jbarlow83
|
||||
|
||||
from ocrmypdf import hocrtransform
|
||||
from ocrmypdf.tesseract import HOCR_TEMPLATE
|
||||
from reportlab.pdfgen.canvas import Canvas
|
||||
from PIL import Image
|
||||
from tempfile import NamedTemporaryFile
|
||||
from contextlib import suppress
|
||||
import os
|
||||
import shutil
|
||||
import pytest
|
||||
import img2pdf
|
||||
import pytest
|
||||
import sys
|
||||
|
||||
|
||||
if sys.version_info.major < 3:
|
||||
print("Requires Python 3.4+")
|
||||
sys.exit(1)
|
||||
|
||||
TESTS_ROOT = os.path.abspath(os.path.dirname(__file__))
|
||||
SPOOF_PATH = os.path.join(TESTS_ROOT, 'spoof')
|
||||
PROJECT_ROOT = os.path.dirname(TESTS_ROOT)
|
||||
OCRMYPDF = os.path.join(PROJECT_ROOT, 'OCRmyPDF.sh')
|
||||
TEST_RESOURCES = os.path.join(PROJECT_ROOT, 'tests', 'resources')
|
||||
TEST_OUTPUT = os.environ.get(
|
||||
'OCRMYPDF_TEST_OUTPUT',
|
||||
default=os.path.join(PROJECT_ROOT, 'tests', 'output', 'hocrtransform'))
|
||||
|
||||
|
||||
def setup_module():
|
||||
with suppress(FileNotFoundError):
|
||||
shutil.rmtree(TEST_OUTPUT)
|
||||
with suppress(FileExistsError):
|
||||
os.makedirs(TEST_OUTPUT)
|
||||
with open(_make_output('blank.hocr'), 'w') as f:
|
||||
f.write(HOCR_TEMPLATE)
|
||||
|
||||
|
||||
def _make_input(input_basename):
|
||||
return os.path.join(TEST_RESOURCES, input_basename)
|
||||
|
||||
|
||||
def _make_output(output_basename):
|
||||
return os.path.join(TEST_OUTPUT, output_basename)
|
||||
|
||||
|
||||
def test_mono_image():
|
||||
im = Image.new('1', (8, 8), 0)
|
||||
for n in range(8):
|
||||
im.putpixel((n, n), 1)
|
||||
im.save(_make_output('mono.tif'), format='TIFF')
|
||||
|
||||
hocr = hocrtransform.HocrTransform(_make_output('blank.hocr'), 300)
|
||||
hocr.to_pdf(_make_output('mono.pdf'), imageFileName=_make_output('mono.tif'))
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -1,638 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
# © 2015 James R. Barlow: github.com/jbarlow83
|
||||
|
||||
from __future__ import print_function
|
||||
from subprocess import Popen, PIPE, check_output, check_call, DEVNULL
|
||||
import os
|
||||
import shutil
|
||||
from contextlib import suppress
|
||||
import sys
|
||||
import pytest
|
||||
from ocrmypdf.pageinfo import pdf_get_all_pageinfo
|
||||
import PyPDF2 as pypdf
|
||||
from ocrmypdf import ExitCode
|
||||
from ocrmypdf import leptonica
|
||||
from ocrmypdf.pdfa import file_claims_pdfa
|
||||
import platform
|
||||
|
||||
|
||||
if sys.version_info.major < 3:
|
||||
print("Requires Python 3.4+")
|
||||
sys.exit(1)
|
||||
|
||||
TESTS_ROOT = os.path.abspath(os.path.dirname(__file__))
|
||||
SPOOF_PATH = os.path.join(TESTS_ROOT, 'spoof')
|
||||
PROJECT_ROOT = os.path.dirname(TESTS_ROOT)
|
||||
TEST_RESOURCES = os.path.join(PROJECT_ROOT, 'tests', 'resources')
|
||||
TEST_OUTPUT = os.environ.get(
|
||||
'OCRMYPDF_TEST_OUTPUT',
|
||||
default=os.path.join(PROJECT_ROOT, 'tests', 'output', 'main'))
|
||||
OCRMYPDF = [sys.executable, '-m', 'ocrmypdf']
|
||||
|
||||
|
||||
def running_in_docker():
|
||||
# Docker creates a file named /.dockerinit
|
||||
return os.path.exists('/.dockerinit')
|
||||
|
||||
|
||||
def is_linux():
|
||||
return platform.system() == 'Linux'
|
||||
|
||||
|
||||
def setup_module():
|
||||
with suppress(FileNotFoundError):
|
||||
shutil.rmtree(TEST_OUTPUT)
|
||||
with suppress(FileExistsError):
|
||||
os.makedirs(TEST_OUTPUT)
|
||||
|
||||
|
||||
def _infile(input_basename):
|
||||
return os.path.join(TEST_RESOURCES, input_basename)
|
||||
|
||||
|
||||
def _outfile(output_basename):
|
||||
return os.path.join(TEST_OUTPUT, os.path.basename(output_basename))
|
||||
|
||||
|
||||
def check_ocrmypdf(input_basename, output_basename, *args, env=None):
|
||||
"Run ocrmypdf and confirmed that a valid file was created"
|
||||
input_file = _infile(input_basename)
|
||||
output_file = _outfile(output_basename)
|
||||
|
||||
p, out, err = run_ocrmypdf(input_basename, output_basename, *args, env=env)
|
||||
if p.returncode != 0:
|
||||
print('stdout\n======')
|
||||
print(out)
|
||||
print('stderr\n======')
|
||||
print(err)
|
||||
assert p.returncode == 0
|
||||
assert os.path.exists(output_file), "Output file not created"
|
||||
assert os.stat(output_file).st_size > 100, "PDF too small or empty"
|
||||
return output_file
|
||||
|
||||
|
||||
def run_ocrmypdf(input_basename, output_basename, *args, env=None):
|
||||
"Run ocrmypdf and let caller deal with results"
|
||||
input_file = _infile(input_basename)
|
||||
output_file = _outfile(output_basename)
|
||||
|
||||
if env is None:
|
||||
env = os.environ
|
||||
|
||||
p_args = OCRMYPDF + list(args) + [input_file, output_file]
|
||||
p = Popen(
|
||||
p_args, close_fds=True, stdout=PIPE, stderr=PIPE,
|
||||
universal_newlines=True, env=env)
|
||||
out, err = p.communicate()
|
||||
return p, out, err
|
||||
|
||||
|
||||
def spoof(replace_program, with_spoof):
|
||||
"""Modify environment variables to override subprocess executables
|
||||
|
||||
Before running any executable, ocrmypdf checks the environment variable
|
||||
OCRMYPDF_PROGRAMNAME to override default program name/location, e.g.
|
||||
OCRMYPDF_GS redirects from the system path Ghostscript ("gs") to elsewhere.
|
||||
"""
|
||||
env = os.environ.copy()
|
||||
spoofer = os.path.join(SPOOF_PATH, with_spoof)
|
||||
if not os.access(spoofer, os.X_OK):
|
||||
os.chmod(spoofer, 0o755)
|
||||
env['OCRMYPDF_' + replace_program.upper()] = spoofer
|
||||
return env
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def spoof_tesseract_noop():
|
||||
return spoof('tesseract', 'tesseract_noop.py')
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def spoof_tesseract_cache():
|
||||
if running_in_docker():
|
||||
return os.environ.copy()
|
||||
return spoof('tesseract', "tesseract_cache.py")
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def spoof_tesseract_crash():
|
||||
return spoof('tesseract', 'tesseract_crash.py')
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def spoof_tesseract_big_image_error():
|
||||
return spoof('tesseract', 'tesseract_big_image_error.py')
|
||||
|
||||
|
||||
def test_quick(spoof_tesseract_noop):
|
||||
check_ocrmypdf('c02-22.pdf', 'test_quick.pdf', env=spoof_tesseract_noop)
|
||||
|
||||
|
||||
def test_deskew(spoof_tesseract_noop):
|
||||
# Run with deskew
|
||||
deskewed_pdf = check_ocrmypdf(
|
||||
'skew.pdf', 'test_deskew.pdf', '-d', '-v', '1', env=spoof_tesseract_noop)
|
||||
|
||||
# Now render as an image again and use Leptonica to find the skew angle
|
||||
# to confirm that it was deskewed
|
||||
from ocrmypdf.ghostscript import rasterize_pdf
|
||||
import logging
|
||||
log = logging.getLogger()
|
||||
|
||||
deskewed_png = _outfile('deskewed.png')
|
||||
|
||||
rasterize_pdf(
|
||||
deskewed_pdf,
|
||||
deskewed_png,
|
||||
xres=150,
|
||||
yres=150,
|
||||
raster_device='pngmono',
|
||||
log=log)
|
||||
|
||||
from ocrmypdf.leptonica import Pix
|
||||
pix = Pix.read(deskewed_png)
|
||||
skew_angle, skew_confidence = pix.find_skew()
|
||||
|
||||
print(skew_angle)
|
||||
assert -0.5 < skew_angle < 0.5, "Deskewing failed"
|
||||
|
||||
|
||||
def test_clean(spoof_tesseract_noop):
|
||||
check_ocrmypdf('skew.pdf', 'test_clean.pdf', '-c',
|
||||
env=spoof_tesseract_noop)
|
||||
|
||||
|
||||
# This will run 5 * 2 * 2 = 20 test cases
|
||||
@pytest.mark.parametrize(
|
||||
"pdf",
|
||||
['palette.pdf', 'cmyk.pdf', 'ccitt.pdf', 'jbig2.pdf', 'lichtenstein.pdf'])
|
||||
@pytest.mark.parametrize("renderer", ['hocr', 'tesseract'])
|
||||
@pytest.mark.parametrize("output_type", ['pdf', 'pdfa'])
|
||||
def test_exotic_image(spoof_tesseract_cache, pdf, renderer, output_type):
|
||||
check_ocrmypdf(
|
||||
pdf,
|
||||
'test_{0}_{1}.pdf'.format(pdf, renderer),
|
||||
'-dc',
|
||||
'-v', '1',
|
||||
'--output-type', output_type,
|
||||
'--pdf-renderer', renderer, env=spoof_tesseract_cache)
|
||||
|
||||
|
||||
@pytest.mark.parametrize("output_type", [
|
||||
'pdfa', 'pdf'
|
||||
])
|
||||
def test_preserve_metadata(spoof_tesseract_noop, output_type):
|
||||
pdf_before = pypdf.PdfFileReader(_infile('graph.pdf'))
|
||||
|
||||
output = check_ocrmypdf('graph.pdf', 'test_metadata_preserve.pdf',
|
||||
'--output-type', output_type,
|
||||
env=spoof_tesseract_noop)
|
||||
|
||||
pdf_after = pypdf.PdfFileReader(output)
|
||||
|
||||
for key in ('/Title', '/Author'):
|
||||
assert pdf_before.documentInfo[key] == pdf_after.documentInfo[key]
|
||||
|
||||
pdfa_info = file_claims_pdfa(output)
|
||||
assert pdfa_info['output'] == output_type
|
||||
|
||||
|
||||
@pytest.mark.skipif(
|
||||
is_linux() and not running_in_docker(),
|
||||
reason="likely to fail if Linux locale is not configured correctly")
|
||||
@pytest.mark.parametrize("output_type", [
|
||||
'pdfa', 'pdf'
|
||||
])
|
||||
def test_override_metadata(spoof_tesseract_noop, output_type):
|
||||
input_file = _infile('c02-22.pdf')
|
||||
output_file = _outfile('test_override_metadata.pdf')
|
||||
|
||||
german = 'Du siehst den Wald vor lauter Bäumen nicht.'
|
||||
chinese = '孔子'
|
||||
high_unicode = 'U+1030C is: 𐌌'
|
||||
|
||||
p, out, err = run_ocrmypdf(
|
||||
input_file, output_file,
|
||||
'--title', german,
|
||||
'--author', chinese,
|
||||
'--subject', high_unicode,
|
||||
'--output-type', output_type,
|
||||
env=spoof_tesseract_noop)
|
||||
|
||||
assert p.returncode == ExitCode.ok
|
||||
|
||||
pdf = output_file
|
||||
|
||||
out_pdfinfo = check_output(['pdfinfo', pdf], universal_newlines=True)
|
||||
lines_pdfinfo = out_pdfinfo.splitlines()
|
||||
pdfinfo = {}
|
||||
for line in lines_pdfinfo:
|
||||
k, v = line.strip().split(':', maxsplit=1)
|
||||
pdfinfo[k.strip()] = v.strip()
|
||||
|
||||
assert pdfinfo['Title'] == german
|
||||
assert pdfinfo['Author'] == chinese
|
||||
assert pdfinfo['Subject'] == high_unicode
|
||||
assert pdfinfo.get('Keywords', '') == ''
|
||||
|
||||
pdfa_info = file_claims_pdfa(output_file)
|
||||
assert pdfa_info['output'] == output_type
|
||||
|
||||
|
||||
@pytest.mark.parametrize('renderer', [
|
||||
'hocr',
|
||||
'tesseract',
|
||||
])
|
||||
def test_oversample(spoof_tesseract_cache, renderer):
|
||||
oversampled_pdf = check_ocrmypdf(
|
||||
'skew.pdf', 'test_oversample_%s.pdf' % renderer, '--oversample', '350',
|
||||
'-f',
|
||||
'--pdf-renderer', renderer, env=spoof_tesseract_cache)
|
||||
|
||||
pdfinfo = pdf_get_all_pageinfo(oversampled_pdf)
|
||||
|
||||
print(pdfinfo[0]['xres'])
|
||||
assert abs(pdfinfo[0]['xres'] - 350) < 1
|
||||
|
||||
|
||||
def test_repeat_ocr():
|
||||
p, _, _ = run_ocrmypdf('graph_ocred.pdf', 'wontwork.pdf')
|
||||
assert p.returncode != 0
|
||||
|
||||
|
||||
def test_force_ocr(spoof_tesseract_cache):
|
||||
out = check_ocrmypdf('graph_ocred.pdf', 'test_force.pdf', '-f',
|
||||
env=spoof_tesseract_cache)
|
||||
pdfinfo = pdf_get_all_pageinfo(out)
|
||||
assert pdfinfo[0]['has_text']
|
||||
|
||||
|
||||
def test_skip_ocr(spoof_tesseract_cache):
|
||||
check_ocrmypdf('graph_ocred.pdf', 'test_skip.pdf', '-s',
|
||||
env=spoof_tesseract_cache)
|
||||
|
||||
|
||||
def test_argsfile(spoof_tesseract_noop):
|
||||
with open(_outfile('test_argsfile.txt'), 'w') as argsfile:
|
||||
print('--title', 'ArgsFile Test', '--author', 'Test Cases',
|
||||
sep='\n', end='\n', file=argsfile)
|
||||
check_ocrmypdf('graph.pdf', 'test_argsfile.pdf',
|
||||
'@' + _outfile('test_argsfile.txt'),
|
||||
env=spoof_tesseract_noop)
|
||||
|
||||
|
||||
def check_monochrome_correlation(
|
||||
reference_pdf, reference_pageno, test_pdf, test_pageno):
|
||||
|
||||
import ocrmypdf.ghostscript as ghostscript
|
||||
import logging
|
||||
|
||||
gslog = logging.getLogger()
|
||||
|
||||
reference_png = _outfile('{}.ref{:04d}.png'.format(
|
||||
reference_pdf, reference_pageno))
|
||||
test_png = _outfile('{}.test{:04d}.png'.format(
|
||||
test_pdf, test_pageno))
|
||||
|
||||
def rasterize(pdf, pageno, png):
|
||||
if os.path.exists(png):
|
||||
print(png)
|
||||
return
|
||||
ghostscript.rasterize_pdf(
|
||||
pdf,
|
||||
png,
|
||||
xres=100, yres=100,
|
||||
raster_device='pngmono', log=gslog, pageno=pageno)
|
||||
|
||||
rasterize(reference_pdf, reference_pageno, reference_png)
|
||||
rasterize(test_pdf, test_pageno, test_png)
|
||||
|
||||
pix_ref = leptonica.Pix.read(reference_png)
|
||||
pix_test = leptonica.Pix.read(test_png)
|
||||
|
||||
return leptonica.Pix.correlation_binary(pix_ref, pix_test)
|
||||
|
||||
|
||||
def test_monochrome_correlation():
|
||||
# Verify leptonica: check that an incorrect rotated image has poor
|
||||
# correlation with reference
|
||||
corr = check_monochrome_correlation(
|
||||
reference_pdf=_infile('cardinal.pdf'),
|
||||
reference_pageno=1, # north facing page
|
||||
test_pdf=_infile('cardinal.pdf'),
|
||||
test_pageno=3, # south facing page
|
||||
)
|
||||
assert corr < 0.10
|
||||
corr = check_monochrome_correlation(
|
||||
reference_pdf=_infile('cardinal.pdf'),
|
||||
reference_pageno=2,
|
||||
test_pdf=_infile('cardinal.pdf'),
|
||||
test_pageno=2,
|
||||
)
|
||||
assert corr > 0.90
|
||||
|
||||
|
||||
@pytest.mark.parametrize('renderer', [
|
||||
'hocr',
|
||||
'tesseract',
|
||||
])
|
||||
def test_autorotate(spoof_tesseract_cache, renderer):
|
||||
# cardinal.pdf contains four copies of an image rotated in each cardinal
|
||||
# direction - these ones are "burned in" not tagged with /Rotate
|
||||
out = check_ocrmypdf('cardinal.pdf', 'test_autorotate_%s.pdf' % renderer,
|
||||
'-r', '-v', '1', env=spoof_tesseract_cache)
|
||||
for n in range(1, 4+1):
|
||||
correlation = check_monochrome_correlation(
|
||||
reference_pdf=_infile('cardinal.pdf'),
|
||||
reference_pageno=1,
|
||||
test_pdf=out,
|
||||
test_pageno=n)
|
||||
assert correlation > 0.80
|
||||
|
||||
|
||||
def test_autorotate_threshold_low(spoof_tesseract_cache):
|
||||
out = check_ocrmypdf('cardinal.pdf', 'test_autorotate_threshold_low.pdf',
|
||||
'--rotate-pages-threshold', '1',
|
||||
'-r', '-v', '1', env=spoof_tesseract_cache)
|
||||
|
||||
# Low threshold -> always rotate -> expect high correlation between
|
||||
# reference page and test page
|
||||
correlation = check_monochrome_correlation(
|
||||
reference_pdf=_infile('cardinal.pdf'),
|
||||
reference_pageno=1,
|
||||
test_pdf=out,
|
||||
test_pageno=3)
|
||||
assert correlation > 0.80
|
||||
|
||||
|
||||
def test_autorotate_threshold_high(spoof_tesseract_cache):
|
||||
out = check_ocrmypdf('cardinal.pdf', 'test_autorotate_threshold_high.pdf',
|
||||
'--rotate-pages-threshold', '99',
|
||||
'-r', '-v', '1', env=spoof_tesseract_cache)
|
||||
|
||||
# High threshold -> never rotate -> expect low correlation since
|
||||
# test page will not be rotated
|
||||
correlation = check_monochrome_correlation(
|
||||
reference_pdf=_infile('cardinal.pdf'),
|
||||
reference_pageno=1,
|
||||
test_pdf=out,
|
||||
test_pageno=3)
|
||||
assert correlation < 0.10
|
||||
|
||||
|
||||
@pytest.mark.parametrize('renderer', [
|
||||
'hocr',
|
||||
'tesseract',
|
||||
])
|
||||
def test_ocr_timeout(renderer):
|
||||
out = check_ocrmypdf('skew.pdf', 'test_timeout_%s.pdf' % renderer,
|
||||
'--tesseract-timeout', '1.0')
|
||||
pdfinfo = pdf_get_all_pageinfo(out)
|
||||
assert not pdfinfo[0]['has_text']
|
||||
|
||||
|
||||
def test_skip_big(spoof_tesseract_cache):
|
||||
out = check_ocrmypdf('enormous.pdf', 'test_enormous.pdf',
|
||||
'--skip-big', '10', env=spoof_tesseract_cache)
|
||||
pdfinfo = pdf_get_all_pageinfo(out)
|
||||
assert not pdfinfo[0]['has_text']
|
||||
|
||||
|
||||
@pytest.mark.parametrize('renderer', ['hocr', 'tesseract'])
|
||||
@pytest.mark.parametrize('output_type', ['pdf', 'pdfa'])
|
||||
def test_maximum_options(spoof_tesseract_cache, renderer, output_type):
|
||||
check_ocrmypdf(
|
||||
'multipage.pdf', 'test_multipage%s.pdf' % renderer,
|
||||
'-d', '-c', '-i', '-g', '-f', '-k', '--oversample', '300',
|
||||
'--skip-big', '10', '--title', 'Too Many Weird Files',
|
||||
'--author', 'py.test', '--pdf-renderer', renderer,
|
||||
'--output-type', output_type,
|
||||
env=spoof_tesseract_cache)
|
||||
|
||||
|
||||
def test_tesseract_missing_tessdata():
|
||||
env = os.environ.copy()
|
||||
env['TESSDATA_PREFIX'] = '/tmp'
|
||||
|
||||
p, _, err = run_ocrmypdf(
|
||||
'graph_ocred.pdf', 'not_a_pdfa.pdf', '-v', '1', '--skip-text', env=env)
|
||||
assert p.returncode == ExitCode.missing_dependency, err
|
||||
|
||||
|
||||
def test_invalid_input_pdf():
|
||||
p, out, err = run_ocrmypdf(
|
||||
'invalid.pdf', 'wont_be_created.pdf')
|
||||
assert p.returncode == ExitCode.input_file, err
|
||||
|
||||
|
||||
def test_blank_input_pdf():
|
||||
p, out, err = run_ocrmypdf(
|
||||
'blank.pdf', 'still_blank.pdf')
|
||||
assert p.returncode == ExitCode.ok
|
||||
|
||||
|
||||
def test_force_ocr_on_pdf_with_no_images(spoof_tesseract_crash):
|
||||
# As a correctness test, make sure that --force-ocr on a PDF with no
|
||||
# content still triggers tesseract. If tesseract crashes, then it was
|
||||
# called.
|
||||
p, _, err = run_ocrmypdf(
|
||||
'blank.pdf', 'wont_be_created.pdf', '--force-ocr',
|
||||
env=spoof_tesseract_crash)
|
||||
assert p.returncode == ExitCode.child_process_error, err
|
||||
assert not os.path.exists(_outfile('wontwork.pdf'))
|
||||
|
||||
|
||||
def test_french(spoof_tesseract_cache):
|
||||
p, out, err = run_ocrmypdf(
|
||||
'francais.pdf', 'francais.pdf', '-l', 'fra', env=spoof_tesseract_cache)
|
||||
assert p.returncode == ExitCode.ok, \
|
||||
"This test may fail if Tesseract language packs are missing"
|
||||
|
||||
|
||||
def test_klingon():
|
||||
p, out, err = run_ocrmypdf(
|
||||
'francais.pdf', 'francais.pdf', '-l', 'klz')
|
||||
assert p.returncode == ExitCode.bad_args
|
||||
|
||||
|
||||
def test_missing_docinfo(spoof_tesseract_noop):
|
||||
p, out, err = run_ocrmypdf(
|
||||
'missing_docinfo.pdf', 'missing_docinfo.pdf', '-l', 'eng', '-c',
|
||||
env=spoof_tesseract_noop)
|
||||
assert p.returncode == ExitCode.ok, err
|
||||
|
||||
|
||||
@pytest.mark.skipif(running_in_docker(),
|
||||
reason="writes to tests/resources")
|
||||
def test_uppercase_extension(spoof_tesseract_noop):
|
||||
shutil.copy(_infile("skew.pdf"), _infile("UPPERCASE.PDF"))
|
||||
try:
|
||||
check_ocrmypdf("UPPERCASE.PDF", "UPPERCASE_OUT.PDF",
|
||||
env=spoof_tesseract_noop)
|
||||
finally:
|
||||
os.unlink(_infile("UPPERCASE.PDF"))
|
||||
|
||||
|
||||
def test_input_file_not_found():
|
||||
input_file = "does not exist.pdf"
|
||||
p, out, err = run_ocrmypdf(
|
||||
_infile(input_file),
|
||||
_outfile("will not happen.pdf"))
|
||||
assert p.returncode == ExitCode.input_file
|
||||
assert (input_file in out or input_file in err)
|
||||
|
||||
|
||||
def test_input_file_not_a_pdf():
|
||||
input_file = __file__ # Try to OCR this file
|
||||
p, out, err = run_ocrmypdf(
|
||||
_infile(input_file),
|
||||
_outfile("will not happen.pdf"))
|
||||
assert p.returncode == ExitCode.input_file
|
||||
assert (input_file in out or input_file in err)
|
||||
|
||||
|
||||
def test_qpdf_repair_fails():
|
||||
env = os.environ.copy()
|
||||
env['OCRMYPDF_QPDF'] = os.path.abspath('./spoof/qpdf_dummy_return2.py')
|
||||
p, out, err = run_ocrmypdf(
|
||||
'-v', '1',
|
||||
'c02-22.pdf', 'wont_be_created.pdf', env=env)
|
||||
print(out)
|
||||
print(err)
|
||||
assert p.returncode == ExitCode.input_file
|
||||
|
||||
|
||||
def test_encrypted():
|
||||
p, out, err = run_ocrmypdf('skew-encrypted.pdf', 'wont_be_created.pdf')
|
||||
assert p.returncode == ExitCode.input_file
|
||||
assert out.find('password')
|
||||
|
||||
|
||||
@pytest.mark.parametrize('renderer', [
|
||||
'hocr',
|
||||
'tesseract',
|
||||
])
|
||||
def test_pagesegmode(renderer, spoof_tesseract_cache):
|
||||
check_ocrmypdf(
|
||||
'skew.pdf', 'test_psm_%s.pdf' % renderer,
|
||||
'--tesseract-pagesegmode', '7',
|
||||
'-v', '1',
|
||||
'--pdf-renderer', renderer, env=spoof_tesseract_cache)
|
||||
|
||||
|
||||
@pytest.mark.parametrize('renderer', [
|
||||
'hocr',
|
||||
'tesseract',
|
||||
])
|
||||
def test_tesseract_crash(renderer, spoof_tesseract_crash):
|
||||
p, out, err = run_ocrmypdf(
|
||||
'ccitt.pdf', 'wontwork.pdf', '-v', '1',
|
||||
'--pdf-renderer', renderer, env=spoof_tesseract_crash)
|
||||
assert p.returncode == ExitCode.child_process_error
|
||||
assert not os.path.exists(_outfile('wontwork.pdf'))
|
||||
assert "ERROR" in err
|
||||
|
||||
|
||||
def test_tesseract_crash_autorotate(spoof_tesseract_crash):
|
||||
p, out, err = run_ocrmypdf(
|
||||
'ccitt.pdf', 'wontwork.pdf',
|
||||
'-r', env=spoof_tesseract_crash)
|
||||
assert p.returncode == ExitCode.child_process_error
|
||||
assert not os.path.exists(_outfile('wontwork.pdf'))
|
||||
assert "ERROR" in err
|
||||
print(out)
|
||||
print(err)
|
||||
|
||||
|
||||
@pytest.mark.parametrize('renderer', [
|
||||
'hocr',
|
||||
'tesseract',
|
||||
])
|
||||
def test_tesseract_image_too_big(renderer, spoof_tesseract_big_image_error):
|
||||
check_ocrmypdf(
|
||||
'hugemono.pdf', 'hugemono_%s.pdf' % renderer, '-r',
|
||||
'--pdf-renderer', renderer, env=spoof_tesseract_big_image_error)
|
||||
|
||||
|
||||
def test_no_unpaper():
|
||||
env = os.environ.copy()
|
||||
env['OCRMYPDF_UNPAPER'] = os.path.abspath('./spoof/no_unpaper_here.py')
|
||||
p, out, err = run_ocrmypdf(
|
||||
'c02-22.pdf', 'wont_be_created.pdf', '--clean', env=env)
|
||||
assert p.returncode == ExitCode.missing_dependency
|
||||
|
||||
|
||||
def test_old_unpaper():
|
||||
env = os.environ.copy()
|
||||
env['OCRMYPDF_UNPAPER'] = os.path.abspath('./spoof/unpaper_oldversion.py')
|
||||
p, out, err = run_ocrmypdf(
|
||||
'c02-22.pdf', 'wont_be_created.pdf', '--clean', env=env)
|
||||
assert p.returncode == ExitCode.missing_dependency
|
||||
|
||||
|
||||
def test_algo4():
|
||||
p, _, _ = run_ocrmypdf('encrypted_algo4.pdf', 'wontwork.pdf')
|
||||
assert p.returncode == ExitCode.encrypted_pdf
|
||||
|
||||
|
||||
@pytest.mark.parametrize('renderer', [
|
||||
'hocr']) # tesseract cannot pass this test - resamples to square image
|
||||
def test_non_square_resolution(renderer, spoof_tesseract_cache):
|
||||
# Confirm input image is non-square resolution
|
||||
in_pageinfo = pdf_get_all_pageinfo(_infile('aspect.pdf'))
|
||||
assert in_pageinfo[0]['xres'] != in_pageinfo[0]['yres']
|
||||
|
||||
out = 'aspect_%s.pdf' % renderer
|
||||
check_ocrmypdf(
|
||||
'aspect.pdf', out,
|
||||
'--pdf-renderer', renderer, env=spoof_tesseract_cache)
|
||||
|
||||
out_pageinfo = pdf_get_all_pageinfo(_outfile(out))
|
||||
|
||||
# Confirm resolution was kept the same
|
||||
assert in_pageinfo[0]['xres'] == out_pageinfo[0]['xres']
|
||||
assert in_pageinfo[0]['yres'] == out_pageinfo[0]['yres']
|
||||
|
||||
|
||||
def test_image_to_pdf(spoof_tesseract_noop):
|
||||
check_ocrmypdf(
|
||||
'LinnSequencer.jpg', 'image_to_pdf.pdf', '--image-dpi', '200',
|
||||
env=spoof_tesseract_noop)
|
||||
|
||||
|
||||
def test_jbig2_passthrough(spoof_tesseract_cache):
|
||||
out = check_ocrmypdf(
|
||||
'jbig2.pdf', 'jbig2_out.pdf',
|
||||
'--output-type', 'pdf',
|
||||
'--pdf-renderer', 'hocr',
|
||||
env=spoof_tesseract_cache)
|
||||
|
||||
out_pageinfo = pdf_get_all_pageinfo(out)
|
||||
assert out_pageinfo[0]['images'][0]['enc'] == 'jbig2'
|
||||
|
||||
|
||||
def test_stdin(spoof_tesseract_noop):
|
||||
input_file = _infile('francais.pdf')
|
||||
output_file = _outfile('test_stdin.pdf')
|
||||
|
||||
# Runs: cat testfile.pdf | ocrmypdf - output.pdf
|
||||
|
||||
p1_args = ['cat', input_file]
|
||||
p1 = Popen(p1_args, close_fds=True, stdin=DEVNULL, stdout=PIPE)
|
||||
|
||||
p2_args = OCRMYPDF + ['-', output_file]
|
||||
p2 = Popen(
|
||||
p2_args, close_fds=True, stdout=PIPE, stderr=PIPE,
|
||||
stdin=p1.stdout, env=spoof_tesseract_noop)
|
||||
p1.stdout.close()
|
||||
out, err = p2.communicate()
|
||||
|
||||
assert p2.returncode == ExitCode.ok
|
||||
|
||||
|
||||
def test_masks(spoof_tesseract_noop):
|
||||
check_ocrmypdf('masks.pdf', 'test_masks.pdf', env=spoof_tesseract_noop)
|
||||
|
||||
|
||||
def test_linearized_pdf_and_indirect_object(spoof_tesseract_noop):
|
||||
check_ocrmypdf('milk.pdf', 'test_milk.pdf', env=spoof_tesseract_noop)
|
||||
@@ -1,139 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
# © 2015 James R. Barlow: github.com/jbarlow83
|
||||
|
||||
from ocrmypdf import pageinfo
|
||||
from reportlab.pdfgen.canvas import Canvas
|
||||
from PIL import Image
|
||||
from tempfile import NamedTemporaryFile
|
||||
from contextlib import suppress
|
||||
import os
|
||||
import shutil
|
||||
import pytest
|
||||
import img2pdf
|
||||
import pytest
|
||||
import sys
|
||||
|
||||
|
||||
if sys.version_info.major < 3:
|
||||
print("Requires Python 3.4+")
|
||||
sys.exit(1)
|
||||
|
||||
TESTS_ROOT = os.path.abspath(os.path.dirname(__file__))
|
||||
SPOOF_PATH = os.path.join(TESTS_ROOT, 'spoof')
|
||||
PROJECT_ROOT = os.path.dirname(TESTS_ROOT)
|
||||
OCRMYPDF = os.path.join(PROJECT_ROOT, 'OCRmyPDF.sh')
|
||||
TEST_RESOURCES = os.path.join(PROJECT_ROOT, 'tests', 'resources')
|
||||
TEST_OUTPUT = os.environ.get(
|
||||
'OCRMYPDF_TEST_OUTPUT',
|
||||
default=os.path.join(PROJECT_ROOT, 'tests', 'output', 'pageinfo'))
|
||||
|
||||
|
||||
def setup_module():
|
||||
with suppress(FileNotFoundError):
|
||||
shutil.rmtree(TEST_OUTPUT)
|
||||
with suppress(FileExistsError):
|
||||
os.makedirs(TEST_OUTPUT)
|
||||
|
||||
|
||||
def _make_input(input_basename):
|
||||
return os.path.join(TEST_RESOURCES, input_basename)
|
||||
|
||||
|
||||
def _make_output(output_basename):
|
||||
return os.path.join(TEST_OUTPUT, output_basename)
|
||||
|
||||
|
||||
def test_single_page_text():
|
||||
filename = os.path.join(TEST_OUTPUT, 'text.pdf')
|
||||
pdf = Canvas(filename, pagesize=(8*72, 6*72))
|
||||
text = pdf.beginText()
|
||||
text.setFont('Helvetica', 12)
|
||||
text.setTextOrigin(1*72, 3*72)
|
||||
text.textLine("Methink'st thou art a general offence and every"
|
||||
" man should beat thee.")
|
||||
pdf.drawText(text)
|
||||
pdf.showPage()
|
||||
pdf.save()
|
||||
|
||||
pdfinfo = pageinfo.pdf_get_all_pageinfo(filename)
|
||||
|
||||
assert len(pdfinfo) == 1
|
||||
page = pdfinfo[0]
|
||||
|
||||
assert page['has_text']
|
||||
assert len(page['images']) == 0
|
||||
|
||||
|
||||
def test_single_page_image():
|
||||
filename = os.path.join(TEST_OUTPUT, 'image-mono.pdf')
|
||||
|
||||
with NamedTemporaryFile(mode='wb+', suffix='.png') as im_tmp:
|
||||
im = Image.new('1', (8, 8), 0)
|
||||
for n in range(8):
|
||||
im.putpixel((n, n), 1)
|
||||
im.save(im_tmp.name, format='PNG')
|
||||
|
||||
imgsize = ((img2pdf.ImgSize.dpi, 8), (img2pdf.ImgSize.dpi, 8))
|
||||
layout_fun = img2pdf.get_layout_fun(None, imgsize, None, None, None)
|
||||
|
||||
im_tmp.seek(0)
|
||||
im_bytes = im_tmp.read()
|
||||
pdf_bytes = img2pdf.convert(
|
||||
im_bytes, producer="img2pdf", with_pdfrw=False,
|
||||
layout_fun=layout_fun)
|
||||
|
||||
with open(filename, 'wb') as pdf:
|
||||
pdf.write(pdf_bytes)
|
||||
|
||||
pdfinfo = pageinfo.pdf_get_all_pageinfo(filename)
|
||||
|
||||
assert len(pdfinfo) == 1
|
||||
page = pdfinfo[0]
|
||||
|
||||
assert not page['has_text']
|
||||
assert len(page['images']) == 1
|
||||
|
||||
pdfimage = page['images'][0]
|
||||
assert pdfimage['width'] == 8
|
||||
assert pdfimage['color'] == 'gray'
|
||||
|
||||
# While unexpected, this is correct
|
||||
# PDF spec says /FlateDecode image must have /BitsPerComponent 8
|
||||
# So mono images get upgraded to 8-bit
|
||||
assert pdfimage['bpc'] == 8
|
||||
|
||||
# DPI in a 1"x1" is the image width
|
||||
assert abs(pdfimage['dpi_w'] - 8) < 1e-5
|
||||
assert abs(pdfimage['dpi_h'] - 8) < 1e-5
|
||||
|
||||
|
||||
def test_single_page_inline_image():
|
||||
filename = os.path.join(TEST_OUTPUT, 'image-mono-inline.pdf')
|
||||
pdf = Canvas(filename, pagesize=(8*72, 6*72))
|
||||
with NamedTemporaryFile() as im_tmp:
|
||||
im = Image.new('1', (8, 8), 0)
|
||||
for n in range(8):
|
||||
im.putpixel((n, n), 1)
|
||||
im.save(im_tmp.name, format='PNG')
|
||||
# Draw image in a 72x72 pt or 1"x1" area
|
||||
pdf.drawInlineImage(im_tmp.name, 0, 0, width=72, height=72)
|
||||
pdf.showPage()
|
||||
pdf.save()
|
||||
|
||||
pdfinfo = pageinfo.pdf_get_all_pageinfo(filename)
|
||||
print(pdfinfo)
|
||||
pdfimage = pdfinfo[0]['images'][0]
|
||||
assert (pdfimage['dpi_w'] - 8) < 1e-5
|
||||
assert pdfimage['color'] != '-'
|
||||
assert pdfimage['width'] == 8
|
||||
|
||||
|
||||
def test_jpeg():
|
||||
filename = _make_input('c02-22.pdf')
|
||||
|
||||
pdfinfo = pageinfo.pdf_get_all_pageinfo(filename)
|
||||
|
||||
pdfimage = pdfinfo[0]['images'][0]
|
||||
assert pdfimage['enc'] == 'jpeg'
|
||||
assert (pdfimage['dpi_w'] - 150) < 1e-5
|
||||
|
||||
Reference in New Issue
Block a user