v13.2.0 release notes

Closes #868

docs/api.rst

@@ -68,6 +68,14 @@ OCRmyPDF, use processes.
     not take at least one of these steps, process semantics will prevent
     OCRmyPDF from working correctly.
 
+.. warning::
+
+    On macOS with Python 3.7, you must call
+    :func:`multiprocessing.set_start_method("spawn")`. Without this, multiprocessing
+    will be unstable. From the command line, OCRmyPDF does this automatically,
+    but as an API user you must do this. See Python bpo-33725 for details.
+    Python 3.8+ also resolve this automatically.
+
 Logging
 -------
 

docs/release_notes.rst

@@ -18,6 +18,23 @@ wish to use some of its features for working with PDFs.
    for Python 3.6 but might release fixes for critical issues if necessary before that
    date.
 
+v13.2.0
+=======
+
+-  Removed all runtime uses of distutils since it is deprecated in standard library. We
+   previous used ``distutils.version`` to examine version numbers of dependencies
+   at run time, and now use ``packaging.version`` for this. This is a new
+   dependency.
+-  Fixed an error message advising the user that Ghostscript was not installed being
+   suppressed when this condition actually happens.
+-  Fixed an issue with incorrect page number and totals being displayed in the progress
+   bar. This was purely a display/presentation issue. :issue:`876`.
+
+v13.1.1
+=======
+
+-  Fixed issue with attempting to deskew a blank page on Tesseract 5. :issue:`868`.
+
 v13.1.0
 =======
 

setup.cfg

@@ -48,6 +48,7 @@ install_requires =
     Pillow>=8.2.0
     coloredlogs>=14.0  # strictly optional
     img2pdf>=0.3.0,<0.5  # pure Python
+    packaging>=20
     pdfminer.six!=20200720,>=20191110,<=20211012
     pikepdf>=4.0.0
     pluggy>=0.13.0,<2

src/ocrmypdf/_exec/tesseract.py

@@ -9,13 +9,13 @@
 
 import logging
 import re
-from distutils.version import StrictVersion
 from math import pi
 from os import fspath
 from pathlib import Path
 from subprocess import PIPE, STDOUT, CalledProcessError, TimeoutExpired
 from typing import Dict, Iterator, List, Optional
 
+from packaging.version import Version
 from PIL import Image
 
 from ocrmypdf.exceptions import (
@@ -60,25 +60,54 @@ class TesseractLoggerAdapter(logging.LoggerAdapter):
         return '[tesseract] %s' % (msg), kwargs
 
 
-class TesseractVersion(StrictVersion):
-
-    version_re = re.compile(
-        r'''
-        ^(\d+) \. (\d+) (\. (\d+))?  # groups: 1/major, 2/minor, 3/[skip], 4/patch
-        [-]?  # optional hyphen separator
-        (?: ((?:alpha|beta|rc|dev)\d*)? [.\-\ ]? (\d+)? )?  # 5/prerelease, 6/prerelease_num
-        (?:(?:-\d+)?-g[0-9a-f]+)?  # untagged git version
-        $
-        ''',
-        re.VERBOSE | re.ASCII,
+TESSERACT_VERSION_PATTERN = r"""
+    v?
+    (?:
+        (?:(?P<epoch>[0-9]+)!)?                           # epoch
+        (?P<release>[0-9]+(?:\.[0-9]+)*)                  # release segment
+        (?P<pre>                                          # pre-release
+            [-_\.]?
+            (?P<pre_l>(a|b|c|rc|alpha|beta|pre|preview))
+            [-_\.]?
+            (?P<pre_n>[0-9]+)?
+        )?
+        (?P<post>                                         # post release
+            (?:-(?P<post_n1>[0-9]+))
+            |
+            (?:
+                [-_\.]?
+                (?P<post_l>post|rev|r)
+                [-_\.]?
+                (?P<post_n2>[0-9]+)?
+            )
+        )?
+        (?P<dev>                                          # dev release
+            [-_\.]?
+            (?P<dev_l>dev)
+            [-_\.]?
+            (?P<dev_n>[0-9]+)?
+        )?
+        (?P<date>
+            [-_\.]
+            (?:20[0-9][0-9] [0-1][0-9] [0-3][0-9])       # yyyy mm dd
+        )?
+        (?P<gitcount>
+            [-_\.]?
+            [0-9]+
+        )?
+        (?P<gitcommit>
+            [-_\.]?
+            g[0-9a-f]{2,10}
+        )?
     )
+    (?:\+(?P<local>[a-z0-9]+(?:[-_\.][a-z0-9]+)*))?       # local version
+"""
 
-    def parse(self, vstring):
-        try:
-            super().parse(vstring)
-        except TypeError as e:
-            if 'int() argument must be a string' in str(e):
-                super().parse(vstring + '-0')
+
+class TesseractVersion(Version):
+    _regex = re.compile(
+        r"^\s*" + TESSERACT_VERSION_PATTERN + r"\s*$", re.VERBOSE | re.IGNORECASE
+    )
 
 
 def version() -> str:
@@ -200,7 +229,9 @@ def get_deskew(
     except CalledProcessError as e:
         tesseract_log_output(e.stdout)
         tesseract_log_output(e.stderr)
-        if b'Empty page!!' in e.output:  # Not enough info for a skew angle
+        if b'Empty page!!' in e.output or (
+            e.output == b'' and e.returncode == 1
+        ):  # Not enough info for a skew angle - Tess 4 and 5 return different errors
             return 0.0
 
         raise SubprocessOutputError() from e

src/ocrmypdf/builtin_plugins/concurrency.py

@@ -134,7 +134,6 @@ class StandardExecutor(Executor):
                 for future in as_completed(futures):
                     result = future.result()
                     task_finished(result, pbar)
-                    pbar.update()
             except KeyboardInterrupt:
                 # Terminate pool so we exit instantly
                 executor.shutdown(wait=False, cancel_futures=True)

src/ocrmypdf/builtin_plugins/ghostscript.py

@@ -18,13 +18,13 @@ log = logging.getLogger(__name__)
 
 @hookimpl
 def check_options(options):
-    gs_version = ghostscript.version()
     check_external_program(
         program='gs',
         package='ghostscript',
-        version_checker=gs_version,
+        version_checker=ghostscript.version,
         need_version='9.15',  # limited by Travis CI / Ubuntu 14.04 backports
     )
+    gs_version = ghostscript.version()
     if gs_version in ('9.24', '9.51'):
         raise MissingDependencyError(
             f"Ghostscript {gs_version} contains serious regressions and is not "

src/ocrmypdf/subprocess/__init__.py

@@ -13,12 +13,13 @@ import re
 import sys
 from collections.abc import Mapping
 from contextlib import suppress
-from distutils.version import LooseVersion, Version
 from functools import lru_cache
 from subprocess import PIPE, STDOUT, CalledProcessError, CompletedProcess, Popen
 from subprocess import run as subprocess_run
 from typing import Callable, Optional, Type, Union
 
+from packaging.version import Version
+
 from ocrmypdf.exceptions import MissingDependencyError
 
 # pylint: disable=logging-format-interpolation
@@ -266,11 +267,11 @@ def check_external_program(
     *,
     program: str,
     package: str,
-    version_checker: Union[str, Callable],
+    version_checker: Callable,
     need_version: str,
     required_for: Optional[str] = None,
     recommended=False,
-    version_parser: Type[Version] = LooseVersion,
+    version_parser: Type[Version] = Version,
 ):
     """Check for required version of external program and raise exception if not.
 
@@ -291,7 +292,7 @@ def check_external_program(
     try:
         if callable(version_checker):
             found_version = version_checker()
-        else:
+        else:  # deprecated
             found_version = version_checker
     except (CalledProcessError, FileNotFoundError, MissingDependencyError):
         _error_missing_program(program, package, required_for, recommended)

src/ocrmypdf/subprocess/_windows.py

@@ -8,7 +8,6 @@ import logging
 import os
 import shutil
 import sys
-from distutils.version import LooseVersion
 from itertools import chain
 from pathlib import Path
 from typing import Any, Callable, Iterable, Iterator, Set, Tuple, TypeVar
@@ -23,6 +22,17 @@ log = logging.getLogger(__name__)
 T = TypeVar('T')
 
 
+def ghostscript_version_key(s: str) -> Tuple[int, int, int]:
+    """Compare Ghostscript version numbers."""
+    try:
+        release = [int(elem) for elem in s.split('.', maxsplit=3)]
+        while len(release) < 3:
+            release.append(0)
+        return (release[0], release[1], release[2])
+    except ValueError:
+        return (0, 0, 0)
+
+
 def registry_enum(
     key: winreg.HKEYType, enum_fn: Callable[[winreg.HKEYType, int], T]
 ) -> Iterator[T]:
@@ -51,7 +61,9 @@ def registry_path_ghostscript(env=None) -> Iterator[Path]:
         with winreg.OpenKey(
             winreg.HKEY_LOCAL_MACHINE, r"SOFTWARE\Artifex\GPL Ghostscript"
         ) as k:
-            latest_gs = max(registry_subkeys(k), key=LooseVersion, default='0')
+            latest_gs = max(
+                registry_subkeys(k), key=ghostscript_version_key, default=(0, 0, 0)
+            )
         with winreg.OpenKey(
             winreg.HKEY_LOCAL_MACHINE, fr"SOFTWARE\Artifex\GPL Ghostscript\{latest_gs}"
         ) as k:

tests/cache/manifest.jsonl

@@ -80,3 +80,5 @@
 {"tesseract_version": "4.1.1", "system": "Linux", "python": "3.9.5", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/trivial.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
 {"tesseract_version": "4.1.1", "system": "Linux", "python": "3.9.5", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/trivial.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
 {"tesseract_version": "4.1.1", "system": "Linux", "python": "3.9.5", "argv_slug": "__-l__eng__--oem__1__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/trivial.pdf", "args": ["-l", "eng", "--oem", "1", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.0.0", "system": "Linux", "python": "3.9.5", "argv_slug": "__-l__eng__thresholding_method=1__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/trivial.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "-c", "thresholding_method=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.0.0", "system": "Linux", "python": "3.9.5", "argv_slug": "__-l__eng__thresholding_method=2__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/trivial.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "-c", "thresholding_method=2", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}

tests/test_preprocessing.py

@@ -40,6 +40,11 @@ def test_deskew(resources, outdir):
     assert -0.5 < skew_angle < 0.5, "Deskewing failed"
 
 
+def test_deskew_blank_page(resources, outpdf):
+    # Tesseract doesn't like blank pages - make sure we can get through
+    check_ocrmypdf(resources / 'blank.pdf', outpdf, '--deskew')
+
+
 @pytest.mark.xfail(reason="remove background disabled")
 def test_remove_background(resources, outdir):
     # Ensure the input image does not contain pure white/black