Try to retain/copy xattrs

.github/workflows/build.yml

@@ -133,6 +133,7 @@ jobs:
             ghostscript \
             jbig2enc \
             openjpeg \
+            openssl \
             pngquant \
             tesseract
 

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
-installation and may require Docker engine configuration. OCRmyPDF
-needs a generous amount of RAM, CPU cores, temporary storage
-space, whether running in a Docker container or on its own. It may be
-necessary to ensure the container is provisioned with additional
-resources.
+convenient option.
+
+On platforms other than Linux, Docker runs in a virtual machine, and so may
+be less performant. You may also want to adjust the Docker virtual machine's
+memory and CPU allocation. On Linux, the Docker image runs natively and
+performance is comparable to a system installation.
 
 .. _docker-install:
 

docs/release_notes.rst

@@ -28,6 +28,13 @@ 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
 =======
 

misc/watcher.py

@@ -260,12 +260,12 @@ def main(
     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_dir}\n"
@@ -285,7 +285,7 @@ def main(
         f"POLL_NEW_FILE_SECONDS: {poll_new_file_seconds}\n"
         f"RETRIES_LOADING_FILE: {retries_loading_file}\n"
         f"USE_POLLING: {use_polling}\n"
-        f"LOGLEVEL: {loglevel}"
+        f"LOGLEVEL: {loglevel.value}"
     )
 
     json_settings = json.loads(ocr_json_settings.read() if ocr_json_settings else '{}')

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
@@ -1090,14 +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
@@ -1116,5 +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)

tests/conftest.py

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