Try to retain/copy xattrs

.github/workflows/build.yml

@@ -32,7 +32,7 @@ jobs:
             python: "3.9"
             tesseract5: true
           - os: ubuntu-latest
-            python: "3.12-dev"
+            python: "3.12"
             tesseract5: true
             #- os: ubuntu-latest
             #  python: "pypy3.9"
@@ -113,7 +113,7 @@ jobs:
     strategy:
       matrix:
         os: [macos-latest]
-        python: ["3.10", "3.11", "3.12-dev"]
+        python: ["3.10", "3.11", "3.12"]
 
     env:
       OS: ${{ matrix.os }}
@@ -133,6 +133,7 @@ jobs:
             ghostscript \
             jbig2enc \
             openjpeg \
+            openssl \
             pngquant \
             tesseract
 
@@ -170,7 +171,7 @@ jobs:
     strategy:
       matrix:
         os: [windows-latest]
-        python: ["3.10", "3.11", "3.12-dev"]
+        python: ["3.10", "3.11", "3.12"]
 
     env:
       OS: ${{ matrix.os }}

docs/batch.rst

@@ -152,7 +152,7 @@ The watcher service is included in the OCRmyPDF Docker image. To run it:
     docker run \
         --volume <path to files to convert>:/input \
         --volume <path to store results>:/output \
-        --volume <path to store processed originals>:/archive \
+        --volume <path to store processed originals>:/processed \
         --env OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1 \
         --env OCR_ON_SUCCESS_ARCHIVE=1 \
         --env OCR_DESKEW=1 \
@@ -163,7 +163,7 @@ The watcher service is included in the OCRmyPDF Docker image. To run it:
 
 This service will watch for a file that matches ``/input/\*.pdf``,
 convert it to a OCRed PDF in ``/output/``, and move the processed
-original to ``/archive``. The parameters to this image are:
+original to ``/processed``. The parameters to this image are:
 
 .. csv-table:: watcher.py parameters for Docker
     :header: "Parameter", "Description"
@@ -171,7 +171,7 @@ original to ``/archive``. The parameters to this image are:
 
     "``--volume <path to files to convert>:/input``", "Files placed in this location will be OCRed"
     "``--volume <path to store results>:/output``", "This is where OCRed files will be stored"
-    "``--volume <path to store processed originals>:/archive``", "Archive processed originals here"
+    "``--volume <path to store processed originals>:/processed``", "Archive processed originals here"
     "``--env OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1``", "Define environment variable ``OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1`` to place files in the output in ``{output}/{year}/{month}/{filename}``"
     "``--env OCR_ON_SUCCESS_ARCHIVE=1``", "Define environment variable ``OCR_ON_SUCCESS_ARCHIVE`` to move processed originals"
     "``--env OCR_DESKEW=1``", "Define environment variable ``OCR_DESKEW``  to apply deskew to crooked input PDFs"

docs/docker.rst

@@ -12,12 +12,12 @@ OCRmyPDF is also available in Docker images that packages recent
 versions of all dependencies.
 
 For users who already have Docker installed this may be an easy and
-convenient option. However, it is less performant than a system
+convenient option.
-installation and may require Docker engine configuration. OCRmyPDF
+
-needs a generous amount of RAM, CPU cores, temporary storage
+On platforms other than Linux, Docker runs in a virtual machine, and so may
-space, whether running in a Docker container or on its own. It may be
+be less performant. You may also want to adjust the Docker virtual machine's
-necessary to ensure the container is provisioned with additional
+memory and CPU allocation. On Linux, the Docker image runs natively and
-resources.
+performance is comparable to a system installation.
 
 .. _docker-install:
 

docs/release_notes.rst

@@ -28,6 +28,22 @@ tagged yet.
 
 .. |OCRmyPDF PyPI| image:: https://img.shields.io/pypi/v/ocrmypdf.svg
 
+v15.3.1
+=======
+
+-  Fixed an issue with logging settings for misc/watcher.py introduced in the
+   previous release. :issue:`1180`
+-  Updated documentation on Docker performance concerns.
+
+v15.3.0
+=======
+
+-  Update misc/watcher.py to improve command line interface using Typer, and
+   support ``.env`` specification of environment variables. Improved error
+   messages. Thanks to @mflagg2814 for the PR that prompted this improvement.
+-  Improved error message when a file cannot be read because we are running in
+   a snap container.
+
 v15.2.0
 =======
 

misc/watcher.py

@@ -5,107 +5,122 @@
 
 """Watch a directory for new PDFs and OCR them."""
 
-from __future__ import annotations
+# Do not enable annotations!
+# https://github.com/tiangolo/typer/discussions/598
+# from __future__ import annotations
 
 import json
 import logging
-import os
 import shutil
 import sys
 import time
 from datetime import datetime
+from enum import Enum
 from pathlib import Path
+from typing import Annotated, Any
 
 import pikepdf
+import typer
+from dotenv import load_dotenv
 from watchdog.events import PatternMatchingEventHandler
 from watchdog.observers import Observer
 from watchdog.observers.polling import PollingObserver
 
 import ocrmypdf
 
+load_dotenv()
+
+
 # pylint: disable=logging-format-interpolation
-
+app = typer.Typer(name="ocrmypdf-watcher")
-
-def getenv_bool(name: str, default: str = 'False'):
-    return os.getenv(name, default).lower() in ('true', 'yes', 'y', '1')
-
-
-INPUT_DIRECTORY = os.getenv('OCR_INPUT_DIRECTORY', '/input')
-OUTPUT_DIRECTORY = os.getenv('OCR_OUTPUT_DIRECTORY', '/output')
-ARCHIVE_DIRECTORY = os.getenv('OCR_ARCHIVE_DIRECTORY', '/processed')
-OUTPUT_DIRECTORY_YEAR_MONTH = getenv_bool('OCR_OUTPUT_DIRECTORY_YEAR_MONTH')
-ON_SUCCESS_DELETE = getenv_bool('OCR_ON_SUCCESS_DELETE')
-ON_SUCCESS_ARCHIVE = getenv_bool('OCR_ON_SUCCESS_ARCHIVE')
-DESKEW = getenv_bool('OCR_DESKEW')
-OCR_JSON_SETTINGS = json.loads(os.getenv('OCR_JSON_SETTINGS', '{}'))
-POLL_NEW_FILE_SECONDS = int(os.getenv('OCR_POLL_NEW_FILE_SECONDS', '1'))
-USE_POLLING = getenv_bool('OCR_USE_POLLING')
-RETRIES_LOADING_FILE = int(os.getenv('OCR_RETRIES_LOADING_FILE', '5'))
-LOGLEVEL = os.getenv('OCR_LOGLEVEL', 'INFO')
-PATTERNS = ['*.pdf', '*.PDF']
 
 log = logging.getLogger('ocrmypdf-watcher')
 
 
-def get_output_dir(root, basename):
+class LoggingLevelEnum(str, Enum):
-    if OUTPUT_DIRECTORY_YEAR_MONTH:
+    """Enum for logging levels."""
+
+    DEBUG = "DEBUG"
+    INFO = "INFO"
+    WARNING = "WARNING"
+    ERROR = "ERROR"
+    CRITICAL = "CRITICAL"
+
+
+def get_output_dir(root: Path, basename: str, output_dir_year_month: bool) -> Path:
+    if output_dir_year_month:
         today = datetime.today()
-        output_directory_year_month = (
+        output_directory_year_month = root / str(today.year) / f'{today.month:02d}'
-            Path(root) / str(today.year) / f'{today.month:02d}'
-        )
         if not output_directory_year_month.exists():
             output_directory_year_month.mkdir(parents=True, exist_ok=True)
         output_path = Path(output_directory_year_month) / basename
     else:
-        output_path = Path(OUTPUT_DIRECTORY) / basename
+        output_path = root / basename
     return output_path
 
 
-def wait_for_file_ready(file_path):
+def wait_for_file_ready(
+    file_path: Path, poll_new_file_seconds: int, retries_loading_file: int
+):
     # This loop waits to make sure that the file is completely loaded on
     # disk before attempting to read. Docker sometimes will publish the
     # watchdog event before the file is actually fully on disk, causing
     # pikepdf to fail.
 
-    retries = RETRIES_LOADING_FILE
+    tries = retries_loading_file + 1
-    while retries:
+    while tries:
         try:
-            pdf = pikepdf.open(file_path)
+            with pikepdf.Pdf.open(file_path) as pdf:
-        except (FileNotFoundError, pikepdf.PdfError) as e:
+                log.debug(f"{file_path} ready with {pdf.pages} pages")
+                return True
+        except (FileNotFoundError, OSError) as e:
             log.info(f"File {file_path} is not ready yet")
             log.debug("Exception was", exc_info=e)
-            time.sleep(POLL_NEW_FILE_SECONDS)
+            time.sleep(poll_new_file_seconds)
-            retries -= 1
+            tries -= 1
-        else:
+        except pikepdf.PdfError as e:
-            pdf.close()
+            log.info(f"File {file_path} is not full written yet")
-            return True
+            log.debug("Exception was", exc_info=e)
+            time.sleep(poll_new_file_seconds)
+            tries -= 1
 
     return False
 
 
-def execute_ocrmypdf(file_path):
+def execute_ocrmypdf(
-    file_path = Path(file_path)
+    *,
-    output_path = get_output_dir(OUTPUT_DIRECTORY, file_path.name)
+    file_path: Path,
+    archive_dir: Path,
+    output_dir: Path,
+    deskew: bool,
+    ocrmypdf_kwargs: dict[str, Any],
+    on_success_delete: bool,
+    on_success_archive: bool,
+    poll_new_file_seconds: int,
+    retries_loading_file: int,
+    output_dir_year_month: bool,
+):
+    output_path = get_output_dir(output_dir, file_path.name, output_dir_year_month)
 
     log.info("-" * 20)
-    log.info(f'New file: {file_path}. Waiting until fully loaded...')
+    log.info(f'New file: {file_path}. Waiting until fully written...')
-    if not wait_for_file_ready(file_path):
+    if not wait_for_file_ready(file_path, poll_new_file_seconds, retries_loading_file):
         log.info(f"Gave up waiting for {file_path} to become ready")
         return
     log.info(f'Attempting to OCRmyPDF to: {output_path}')
     exit_code = ocrmypdf.ocr(
         input_file=file_path,
         output_file=output_path,
-        deskew=DESKEW,
+        deskew=deskew,
-        **OCR_JSON_SETTINGS,
+        **ocrmypdf_kwargs,
     )
     if exit_code == 0:
-        if ON_SUCCESS_DELETE:
+        if on_success_delete:
             log.info(f'OCR is done. Deleting: {file_path}')
             file_path.unlink()
-        elif ON_SUCCESS_ARCHIVE:
+        elif on_success_archive:
-            log.info(f'OCR is done. Archiving {file_path.name} to {ARCHIVE_DIRECTORY}')
+            log.info(f'OCR is done. Archiving {file_path.name} to {archive_dir}')
-            shutil.move(file_path, f'{ARCHIVE_DIRECTORY}/{file_path.name}')
+            shutil.move(file_path, f'{archive_dir}/{file_path.name}')
         else:
             log.info('OCR is done')
     else:
@@ -113,61 +128,202 @@ def execute_ocrmypdf(file_path):
 
 
 class HandleObserverEvent(PatternMatchingEventHandler):
+    def __init__(
+        self,
+        patterns=None,
+        ignore_patterns=None,
+        ignore_directories=False,
+        case_sensitive=False,
+        settings={},
+    ):
+        super().__init__(
+            patterns=patterns,
+            ignore_patterns=ignore_patterns,
+            ignore_directories=ignore_directories,
+            case_sensitive=case_sensitive,
+        )
+        self._settings = settings
+
     def on_any_event(self, event):
         if event.event_type in ['created']:
-            execute_ocrmypdf(event.src_path)
+            execute_ocrmypdf(event.src_path, **self._settings)
 
 
-def main():
+@app.command()
+def main(
+    input_dir: Annotated[
+        Path,
+        typer.Argument(
+            envvar='OCR_INPUT_DIRECTORY',
+            exists=True,
+            file_okay=False,
+            dir_okay=True,
+            readable=True,
+            resolve_path=True,
+        ),
+    ] = '/input',
+    output_dir: Annotated[
+        Path,
+        typer.Argument(
+            envvar='OCR_OUTPUT_DIRECTORY',
+            exists=True,
+            file_okay=False,
+            dir_okay=True,
+            writable=True,
+            resolve_path=True,
+        ),
+    ] = '/output',
+    archive_dir: Annotated[
+        Path,
+        typer.Argument(
+            envvar='OCR_ARCHIVE_DIRECTORY',
+            exists=True,
+            file_okay=False,
+            dir_okay=True,
+            writable=True,
+            resolve_path=True,
+        ),
+    ] = '/processed',
+    output_dir_year_month: Annotated[
+        bool,
+        typer.Option(
+            envvar='OCR_OUTPUT_DIRECTORY_YEAR_MONTH',
+            help='Create a subdirectory in the output directory for each year and month',
+        ),
+    ] = False,
+    on_success_delete: Annotated[
+        bool,
+        typer.Option(
+            envvar='OCR_ON_SUCCESS_DELETE',
+            help='Delete the input file after successful OCR',
+        ),
+    ] = False,
+    on_success_archive: Annotated[
+        bool,
+        typer.Option(
+            envvar='OCR_ON_SUCCESS_ARCHIVE',
+            help='Archive the input file after successful OCR',
+        ),
+    ] = False,
+    deskew: Annotated[
+        bool,
+        typer.Option(
+            envvar='OCR_DESKEW',
+            help='Deskew the input file before OCR',
+        ),
+    ] = False,
+    ocr_json_settings: Annotated[
+        typer.FileText,
+        typer.Option(
+            envvar='OCR_JSON_SETTINGS',
+            help='JSON settings to pass to OCRmyPDF',
+        ),
+    ] = None,
+    poll_new_file_seconds: Annotated[
+        int,
+        typer.Option(
+            envvar='OCR_POLL_NEW_FILE_SECONDS',
+            help='Seconds to wait before polling a new file',
+            min=0,
+        ),
+    ] = 1,
+    use_polling: Annotated[
+        bool,
+        typer.Option(
+            envvar='OCR_USE_POLLING',
+            help='Use polling instead of filesystem events',
+        ),
+    ] = False,
+    retries_loading_file: Annotated[
+        int,
+        typer.Option(
+            envvar='OCR_RETRIES_LOADING_FILE',
+            help='Number of times to retry loading a file before giving up',
+            min=0,
+        ),
+    ] = 5,
+    loglevel: Annotated[
+        LoggingLevelEnum,
+        typer.Option(
+            envvar='OCR_LOGLEVEL',
+            help='Logging level',
+        ),
+    ] = LoggingLevelEnum.INFO,
+    patterns: Annotated[
+        str,
+        typer.Option(
+            envvar='OCR_PATTERNS',
+            help='File patterns to watch',
+        ),
+    ] = '*.pdf,*.PDF',
+):
     ocrmypdf.configure_logging(
         verbosity=(
             ocrmypdf.Verbosity.default
-            if LOGLEVEL != 'DEBUG'
+            if loglevel != LoggingLevelEnum.DEBUG
             else ocrmypdf.Verbosity.debug
         ),
         manage_root_logger=True,
     )
-    log.setLevel(LOGLEVEL)
+    log.setLevel(loglevel.value)
     log.info(
         f"Starting OCRmyPDF watcher with config:\n"
-        f"Input Directory: {INPUT_DIRECTORY}\n"
+        f"Input Directory: {input_dir}\n"
-        f"Output Directory: {OUTPUT_DIRECTORY}\n"
+        f"Output Directory: {output_dir}\n"
-        f"Output Directory Year & Month: {OUTPUT_DIRECTORY_YEAR_MONTH}\n"
+        f"Output Directory Year & Month: {output_dir_year_month}\n"
-        f"Archive Directory: {ARCHIVE_DIRECTORY}"
+        f"Archive Directory: {archive_dir}"
     )
     log.debug(
-        f"INPUT_DIRECTORY: {INPUT_DIRECTORY}\n"
+        f"INPUT_DIRECTORY: {input_dir}\n"
-        f"OUTPUT_DIRECTORY: {OUTPUT_DIRECTORY}\n"
+        f"OUTPUT_DIRECTORY: {output_dir}\n"
-        f"OUTPUT_DIRECTORY_YEAR_MONTH: {OUTPUT_DIRECTORY_YEAR_MONTH}\n"
+        f"OUTPUT_DIRECTORY_YEAR_MONTH: {output_dir_year_month}\n"
-        f"ARCHIVE_DIRECTORY: {ARCHIVE_DIRECTORY}\n"
+        f"ARCHIVE_DIRECTORY: {archive_dir}\n"
-        f"ON_SUCCESS_DELETE: {ON_SUCCESS_DELETE}\n"
+        f"ON_SUCCESS_DELETE: {on_success_delete}\n"
-        f"ON_SUCCESS_ARCHIVE: {ON_SUCCESS_ARCHIVE}\n"
+        f"ON_SUCCESS_ARCHIVE: {on_success_archive}\n"
-        f"DESKEW: {DESKEW}\n"
+        f"DESKEW: {deskew}\n"
-        f"ARGS: {OCR_JSON_SETTINGS}\n"
+        f"ARGS: {ocr_json_settings}\n"
-        f"POLL_NEW_FILE_SECONDS: {POLL_NEW_FILE_SECONDS}\n"
+        f"POLL_NEW_FILE_SECONDS: {poll_new_file_seconds}\n"
-        f"RETRIES_LOADING_FILE: {RETRIES_LOADING_FILE}\n"
+        f"RETRIES_LOADING_FILE: {retries_loading_file}\n"
-        f"USE_POLLING: {USE_POLLING}\n"
+        f"USE_POLLING: {use_polling}\n"
-        f"LOGLEVEL: {LOGLEVEL}"
+        f"LOGLEVEL: {loglevel.value}"
     )
 
-    if 'input_file' in OCR_JSON_SETTINGS or 'output_file' in OCR_JSON_SETTINGS:
+    json_settings = json.loads(ocr_json_settings.read() if ocr_json_settings else '{}')
-        log.error('OCR_JSON_SETTINGS should not specify input file or output file')
+
+    if 'input_file' in json_settings or 'output_file' in json_settings:
+        log.error(
+            'OCR_JSON_SETTINGS (--ocr-json-settings) may not specify input/output file'
+        )
         sys.exit(1)
 
-    handler = HandleObserverEvent(patterns=PATTERNS)
+    handler = HandleObserverEvent(
-    if USE_POLLING:
+        patterns=patterns.split(','),
+        settings={
+            'archive_dir': archive_dir,
+            'output_dir': output_dir,
+            'deskew': deskew,
+            'ocrmypdf_kwargs': json_settings,
+            'on_success_delete': on_success_delete,
+            'on_success_archive': on_success_archive,
+            'poll_new_file_seconds': poll_new_file_seconds,
+            'retries_loading_file': retries_loading_file,
+            'output_dir_year_month': output_dir_year_month,
+        },
+    )
+    if use_polling:
         observer = PollingObserver()
     else:
         observer = Observer()
-    observer.schedule(handler, INPUT_DIRECTORY, recursive=True)
+    observer.schedule(handler, input_dir, recursive=True)
     observer.start()
+    typer.echo(f"Watching {input_dir} for new PDFs. Press Ctrl+C to exit.")
     try:
         while True:
-            time.sleep(1)
+            time.sleep(30)
     except KeyboardInterrupt:
         observer.stop()
     observer.join()
 
 
 if __name__ == "__main__":
-    main()
+    app()

pyproject.toml

@@ -61,7 +61,7 @@ test = [
   "types-Pillow",
   "types-humanfriendly",
 ]
-watcher = ["watchdog>=1.0.2"]
+watcher = ["watchdog>=1.0.2", "typer[all]", "python-dotenv"]
 webservice = ["Flask>=2.0.1"]
 
 [project.scripts]

src/ocrmypdf/_exec/tesseract.py

@@ -7,6 +7,7 @@ from __future__ import annotations
 
 import logging
 import re
+from contextlib import suppress
 from math import pi
 from os import fspath
 from pathlib import Path
@@ -350,7 +351,7 @@ def generate_hocr(
         tesseract_log_output(stdout)
         # The sidecar text file will get the suffix .txt; rename it to
         # whatever caller wants it named
-        if prefix.with_suffix('.txt').exists():
+        with suppress(FileNotFoundError):
             prefix.with_suffix('.txt').replace(output_text)
 
 
@@ -406,7 +407,7 @@ def generate_pdf(
     try:
         p = run(args_tesseract, stdout=PIPE, stderr=STDOUT, timeout=timeout, check=True)
         stdout = p.stdout
-        if prefix.with_suffix('.txt').exists():
+        with suppress(FileNotFoundError):
             prefix.with_suffix('.txt').replace(output_text)
     except TimeoutExpired:
         page_timedout(timeout)

src/ocrmypdf/_pipeline.py

@@ -14,7 +14,7 @@ from collections.abc import Iterable, Iterator, Sequence
 from contextlib import suppress
 from datetime import datetime, timezone
 from pathlib import Path
-from shutil import copyfileobj
+from shutil import copyfileobj, copystat
 from typing import Any, BinaryIO, TypeVar, cast
 
 import img2pdf
@@ -33,6 +33,7 @@ from ocrmypdf.exceptions import (
     EncryptedPdfError,
     InputFileError,
     PriorOcrFoundError,
+    TaggedPDFError,
     UnsupportedImageFormatError,
 )
 from ocrmypdf.helpers import IMG2PDF_KWARGS, Resolution, safe_symlink
@@ -218,6 +219,16 @@ def validate_pdfinfo_options(context: PdfContext) -> None:
                     "form and all filled form fields. The output PDF will be "
                     "'flattened' and will no longer be fillable."
                 )
+    if pdfinfo.is_tagged:
+        if options.force_ocr or options.skip_text or options.redo_ocr:
+            log.warning(
+                "This PDF is marked as a Tagged PDF. This often indicates "
+                "that the PDF was generated from an office document and does "
+                "not need OCR. PDF pages processed by OCRmyPDF may not be "
+                "tagged correctly."
+            )
+        else:
+            raise TaggedPDFError()
     context.plugin_manager.hook.validate(pdfinfo=pdfinfo, options=options)
 
 
@@ -1079,14 +1090,14 @@ def merge_sidecars(txt_files: Iterable[Path | None], context: PdfContext) -> Pat
 
 
 def copy_final(
-    input_file: Path, output_file: str | Path | BinaryIO, _context: PdfContext
+    input_file: Path, output_file: str | Path | BinaryIO, context: PdfContext
 ) -> None:
     """Copy the final temporary file to the output destination.
 
     Args:
-        input_file (Path): The input file to copy.
+        input_file (Path): The intermediate input file to copy.
         output_file (str | Path | BinaryIO): The output file to copy to.
-        _context (PdfContext): The PDF context.
+        context (PdfContext): The PDF context.
 
     Returns:
         None
@@ -1105,5 +1116,11 @@ def copy_final(
             # At this point we overwrite the output_file specified by the user
             # use copyfileobj because then we use open() to create the file and
             # get the appropriate umask, ownership, etc.
-            with open(output_file, 'wb') as output_stream:
+            with open(output_file, 'w+b') as output_stream:
                 copyfileobj(input_stream, output_stream)
+            # Attempt to copy file attributes from input to output
+            with suppress(OSError):
+                # Copy original file's permissions, ownership, etc. if possible
+                copystat(context.options.input_file, output_file)
+                # Set output file's modification time to now
+                Path(output_file).touch(exist_ok=True)

src/ocrmypdf/_validation.py

@@ -245,6 +245,18 @@ def check_options(options: Namespace, plugin_manager: PluginManager) -> None:
     _check_plugin_options(options, plugin_manager)
 
 
+def _in_docker():
+    return Path('/.dockerenv').exists()
+
+
+def _in_snap():
+    try:
+        cgroup_text = Path('/proc/self/cgroup').read_text()
+        return 'snap.ocrmypdf' in cgroup_text
+    except FileNotFoundError:
+        return False
+
+
 def create_input_file(options: Namespace, work_folder: Path) -> tuple[Path, str]:
     if options.input_file == '-':
         # stdin
@@ -268,7 +280,7 @@ def create_input_file(options: Namespace, work_folder: Path) -> tuple[Path, str]
             return target, os.fspath(options.input_file)
         except FileNotFoundError as e:
             msg = f"File not found - {options.input_file}"
-            if Path('/.dockerenv').exists():  # pragma: no cover
+            if _in_docker():  # pragma: no cover
                 msg += (
                     "\nDocker cannot your working directory unless you "
                     "explicitly share it with the Docker container and set up"
@@ -278,6 +290,15 @@ def create_input_file(options: Namespace, work_folder: Path) -> tuple[Path, str]
                     "\tdocker run -i --rm jbarlow83/ocrmypdf - - <input.pdf >output.pdf"
                     "\n"
                 )
+            elif _in_snap():  # pragma: no cover
+                msg += (
+                    "\nSnap applications cannot access files outside of "
+                    "your home directory unless you explicitly allow it. "
+                    "You may find it easier to use stdin/stdout:"
+                    "\n"
+                    "\tsnap run ocrmypdf - - <input.pdf >output.pdf"
+                    "\n"
+                )
             raise InputFileError(msg) from e
 
 

src/ocrmypdf/exceptions.py

@@ -108,10 +108,16 @@ class EncryptedPdfError(ExitCodeException):
     )
 
 
-class DigitalSignatureError(ExitCodeException):
+class TesseractConfigError(ExitCodeException):
+    """Tesseract config can't be parsed."""
+
+    exit_code = ExitCode.invalid_config
+    message = "Error occurred while parsing a Tesseract configuration file"
+
+
+class DigitalSignatureError(InputFileError):
     """PDF has a digital signature."""
 
-    exit_code = ExitCode.input_file
     message = dedent(
         """\
         Input PDF has a digital signature. OCR would alter the document,
@@ -120,8 +126,14 @@ class DigitalSignatureError(ExitCodeException):
     )
 
 
-class TesseractConfigError(ExitCodeException):
+class TaggedPDFError(InputFileError):
-    """Tesseract config can't be parsed."""
+    """PDF is tagged."""
 
-    exit_code = ExitCode.invalid_config
+    message = dedent(
-    message = "Error occurred while parsing a Tesseract configuration file"
+        """\
+        This PDF is marked as a Tagged PDF. This often indicates
+        that the PDF was generated from an office document and does
+        not need OCR. Use --force-ocr, --skip-text or --redo-ocr to
+        override this error.
+        """
+    )

src/ocrmypdf/helpers.py

@@ -321,8 +321,10 @@ def remove_all_log_handlers(logger: logging.Logger) -> None:
 def pikepdf_enable_mmap() -> None:
     """Enable pikepdf mmap."""
     try:
-        if pikepdf._core.set_access_default_mmap(True):
+        pikepdf._core.set_access_default_mmap(True)
-            log.debug("pikepdf mmap enabled")
+        log.debug(
+            "pikepdf mmap "
+            + ('enabled' if pikepdf._core.get_access_default_mmap() else 'disabled')
+        )
     except AttributeError:
         log.debug("pikepdf mmap not available")
-    log.debug("pikepdf mmap disabled")

src/ocrmypdf/pdfinfo/info.py

@@ -1038,7 +1038,11 @@ DEFAULT_EXECUTOR = SerialExecutor()
 
 
 class PdfInfo:
-    """Get summary information about a PDF."""
+    """Extract summary information about a PDF without retaining the PDF itself.
+
+    Crucially this lets us get the information in a pure Python format so that
+    it can be pickled and passed to a worker process.
+    """
 
     _has_acroform: bool = False
     _has_signature: bool = False
@@ -1078,6 +1082,9 @@ class PdfInfo:
                 elif Name.XFA in pdf.Root.AcroForm:
                     self._has_acroform = True
                 self._has_signature = bool(pdf.Root.AcroForm.get(Name.SigFlags, 0) & 1)
+            self._is_tagged = bool(
+                pdf.Root.get(Name.MarkInfo, {}).get(Name.Marked, False)
+            )
 
     @property
     def pages(self) -> Sequence[PageInfo | None]:
@@ -1105,6 +1112,11 @@ class PdfInfo:
         """Return True if the document annotations has a digital signature."""
         return self._has_signature
 
+    @property
+    def is_tagged(self) -> bool:
+        """Return True if the document catalog indicates this is a Tagged PDF."""
+        return self._is_tagged
+
     @property
     def filename(self) -> str | Path:
         """Return filename of PDF."""

tests/conftest.py

@@ -25,9 +25,8 @@ def is_macos():
 
 
 def running_in_docker():
-    # Docker creates a file named /.dockerenv (newer versions) or
+    # Docker creates a file named /.dockerenv in all supported versions
-    # /.dockerinit (older) -- this is undocumented, not an offical test
+    return Path('/.dockerenv').exists()
-    return Path('/.dockerenv').exists() or Path('/.dockerinit').exists()
 
 
 def have_unpaper():

tests/test_tagged.py

@@ -0,0 +1,26 @@
+# SPDX-FileCopyrightText: 2023 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+from __future__ import annotations
+
+import argparse
+
+import pytest
+
+import ocrmypdf
+
+
+def test_block_tagged(resources):
+    with pytest.raises(ocrmypdf.exceptions.TaggedPDFError):
+        ocrmypdf.ocr(resources / 'tagged.pdf', '_.pdf')
+
+
+def test_force_tagged_warns(resources, outpdf, caplog):
+    caplog.set_level('WARNING')
+    ocrmypdf.ocr(
+        resources / 'tagged.pdf',
+        outpdf,
+        force_ocr=True,
+        plugins=['tests/plugins/tesseract_noop.py'],
+    )
+    assert 'marked as a Tagged PDF' in caplog.text