menekis/OCRmyPDF
Public Access
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'feature/drop-3.7'

Browse Source
This commit is contained in:
James R. Barlow
2022-09-20 22:32:59 -07:00
parent 1709e23701 6dbaebdc0c
commit 2ebc36fcec
38 changed files with 164 additions and 424 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/ocrmypdf/RELEASE.md
+2 -2
View File
@@ -17,11 +17,11 @@
- Check README.md
- Check setup.py
- Check pyproject.toml
- Are classifiers up to date?
- Is `python_requires` correct?
- Python 3.6 is EOL on December 2021-12. Could drop support then.
- Is it to drop support for older Pythons?
- Can we tighten any `install_requires` dependencies?
- Search for old version shims we can remove
src/ocrmypdf/__init__.py
-1
View File
@@ -21,7 +21,6 @@ from ocrmypdf.exceptions import (
InputFileError,
MissingDependencyError,
OutputFileAccessError,
PdfMergeFailedError,
PriorOcrFoundError,
SubprocessOutputError,
TesseractConfigError,
src/ocrmypdf/__main__.py
-2
View File
@@ -71,6 +71,4 @@ def run(args=None):
if __name__ == '__main__':
if sys.platform == 'darwin' and sys.version_info < (3, 8):
set_start_method('spawn') # see python bpo-33725
sys.exit(run())
src/ocrmypdf/_exec/ghostscript.py
+1 -27
View File
@@ -47,21 +47,6 @@ def version():
return get_version(GS)
def jpeg_passthrough_available() -> bool:
"""Returns True if the installed version of Ghostscript supports JPEG passthru
Prior to 9.23, Ghostscript decoded and re-encoded JPEGs internally. In 9.23
it gained the ability to keep JPEGs unmodified. However, the 9.23
implementation was buggy and would deletes the last two bytes of images in
some cases, as reported here.
https://bugs.ghostscript.com/show_bug.cgi?id=699216
The issue was fixed for 9.24, hence that is the first version we consider
the feature available. (Ghostscript 9.24 has its own problems is blacklisted.)
"""
return version() >= '9.24'
def _gs_error_reported(stream) -> bool:
match = re.search(r'error', stream, flags=re.IGNORECASE)
return bool(match)
@@ -201,19 +186,8 @@ def generate_pdfa(
]
strategy = 'LeaveColorUnchanged'
# Older versions of Ghostscript expect a leading slash in
# sColorConversionStrategy, newer ones should not have it. See Ghostscript
# git commit fe1c025d.
gs_version = version()
strategy = ('/' + strategy) if gs_version < '9.19' else strategy
if gs_version == '9.23':
# 9.23: added JPEG passthrough as a new feature, but with a bug that
# incorrectly formats some images. Fixed as of 9.24. So we disable this
# feature for 9.23.
# https://bugs.ghostscript.com/show_bug.cgi?id=699216
compression_args.append('-dPassThroughJPEGImages=false')
elif gs_version == '9.56.0':
if gs_version == '9.56.0':
# 9.56.0 breaks our OCR, should be fixed in 9.56.1
# https://bugs.ghostscript.com/show_bug.cgi?id=705187
compression_args.append('-dNEWPDF=false')
src/ocrmypdf/_exec/tesseract.py
+2 -11
View File
@@ -33,7 +33,7 @@ HOCR_TEMPLATE = """<?xml version="1.0" encoding="UTF-8"?>
<head>
<title></title>
<meta http-equiv="Content-Type" content="text/html;charset=utf-8" />
<meta name='ocr-system' content='tesseract 4.0.0' />
<meta name='ocr-system' content='tesseract 4.1.1' />
<meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
</head>
<body>
@@ -114,15 +114,6 @@ def version() -> str:
return get_version('tesseract', regex=r'tesseract\s(.+)')
def has_user_words() -> bool:
"""Does Tesseract have --user-words capability?
Not available in 4.0, but available in 4.1. Also available in 3.x, but
we no longer support 3.x.
"""
return version() >= '4.1'
def has_thresholding() -> bool:
"""Does Tesseract have -c thresholding method capability?"""
return version() >= '5.0'
@@ -244,7 +235,7 @@ def get_deskew(
def tesseract_log_output(stream: bytes) -> None:
tlog = TesseractLoggerAdapter(
log, extra=log.extra if hasattr(log, 'extra') else None
log, extra=log.extra if hasattr(log, 'extra') else None # type: ignore
)
if not stream:
src/ocrmypdf/_exec/unpaper.py
+6 -4
View File
@@ -1,12 +1,10 @@
# SPDX-FileCopyrightText: 2022 James R. Barlow
# SPDX-License-Identifier: MPL-2.0
from __future__ import annotations
# unpaper documentation:
# https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md
"""Interface to unpaper executable"""
from __future__ import annotations
import logging
import os
import shlex
@@ -22,6 +20,10 @@ from PIL import Image
from ocrmypdf.exceptions import MissingDependencyError, SubprocessOutputError
from ocrmypdf.subprocess import get_version, run
# unpaper documentation:
# https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md
if sys.version_info >= (3, 10):
from tempfile import TemporaryDirectory
else:
src/ocrmypdf/_sync.py
+1 -1
View File
@@ -207,7 +207,7 @@ def exec_page_sync(page_context: PageContext) -> PageResult:
filtered_image = page_context.plugin_manager.hook.filter_page_image(
page=page_context, image_filename=visible_image_out
)
if filtered_image:
if filtered_image is not None: # None if no hook is present
visible_image_out = filtered_image
pdf_page_from_image_out = create_pdf_page_from_image(
visible_image_out, page_context, orientation_correction
src/ocrmypdf/_validation.py
+2 -2
View File
@@ -134,7 +134,7 @@ def check_options_preprocessing(options: Namespace) -> None:
package='unpaper',
version_checker=unpaper.version,
need_version='6.1',
required_for=['--clean, --clean-final'],
required_for="--clean, --clean-final", # Problem arguments
)
try:
if options.unpaper_args:
@@ -221,7 +221,7 @@ def check_options_metadata(options: Namespace) -> None:
def check_options_pillow(options: Namespace) -> None:
PIL.Image.MAX_IMAGE_PIXELS = int(options.max_image_mpixels * 1_000_000)
if PIL.Image.MAX_IMAGE_PIXELS == 0:
PIL.Image.MAX_IMAGE_PIXELS = None
PIL.Image.MAX_IMAGE_PIXELS = None # type: ignore
def _check_plugin_invariant_options(options: Namespace) -> None:
src/ocrmypdf/_version.py
+1 -4
View File
@@ -8,10 +8,7 @@ OCRmyPDF uses setuptools_scm to derive version from git tags.
from __future__ import annotations
try:
from importlib.metadata import version as _package_version
except ImportError:
from importlib_metadata import version as _package_version # type: ignore
from importlib.metadata import version as _package_version
PROGRAM_NAME = 'ocrmypdf'
src/ocrmypdf/api.py
+4 -12
View File
@@ -15,6 +15,9 @@ from pathlib import Path
from typing import AnyStr, BinaryIO, Iterable, Union
from warnings import warn
import coloredlogs
from humanfriendly.terminal import enable_ansi_support
from ocrmypdf._logging import PageNumberFilter, TqdmConsole
from ocrmypdf._plugin_manager import get_plugin_manager
from ocrmypdf._sync import run_pipeline
@@ -22,15 +25,6 @@ from ocrmypdf._validation import check_options
from ocrmypdf.cli import ArgumentParser, get_parser
from ocrmypdf.helpers import is_iterable_notstr
try:
import coloredlogs
except ModuleNotFoundError:
coloredlogs = None # pylint: disable=invalid-name
if coloredlogs:
from humanfriendly.terminal import enable_ansi_support
StrPath = Union[Path, AnyStr]
PathOrIO = Union[BinaryIO, StrPath]
@@ -121,7 +115,7 @@ def configure_logging(
use_colors = progress_bar_friendly
formatter = None
if coloredlogs and use_colors:
if use_colors:
use_colors = enable_ansi_support()
if use_colors:
use_colors = coloredlogs.terminal_supports_colors()
@@ -284,8 +278,6 @@ def ocr( # pylint: disable=unused-argument
``"-"``, some final validation steps are not performed (we do not read
back the stream after it is written).
Raises:
ocrmypdf.PdfMergeFailedError: If the input PDF is malformed, preventing merging
with the OCR layer.
ocrmypdf.MissingDependencyError: If a required dependency program is missing or
was not found on PATH.
ocrmypdf.UnsupportedImageFormatError: If the input file type was an image that
src/ocrmypdf/builtin_plugins/ghostscript.py
+2 -20
View File
@@ -21,37 +21,19 @@ def check_options(options):
program='gs',
package='ghostscript',
version_checker=ghostscript.version,
need_version='9.15', # limited by Travis CI / Ubuntu 14.04 backports
need_version='9.50', # Ubuntu 20.04's version
)
gs_version = ghostscript.version()
if gs_version in ('9.24', '9.51'):
if gs_version in ('9.51',):
raise MissingDependencyError(
f"Ghostscript {gs_version} contains serious regressions and is not "
"supported. Please upgrade to a newer version, or downgrade to the "
"previous version."
)
# We have these constraints to check for.
# 1. Ghostscript < 9.20 mangles multibyte Unicode
# 2. hocr doesn't work on non-Latin languages (so don't select it)
is_latin = options.languages.issubset(HOCR_OK_LANGS)
if gs_version < '9.20' and options.output_type != 'pdf' and not is_latin:
# https://bugs.ghostscript.com/show_bug.cgi?id=696874
# Ghostscript < 9.20 fails to encode multibyte characters properly
log.warning(
f"The installed version of Ghostscript ({gs_version}) does not work "
"correctly with the OCR languages you specified. Use --output-type pdf or "
"upgrade to Ghostscript 9.20 or later to avoid this issue."
)
if options.output_type == 'pdfa':
options.output_type = 'pdfa-2'
if options.output_type == 'pdfa-3' and ghostscript.version() < '9.19':
raise MissingDependencyError(
"--output-type pdfa-3 requires Ghostscript 9.19 or later"
)
@hookimpl
def rasterize_pdf_page(
src/ocrmypdf/builtin_plugins/tesseract_ocr.py
+2 -7
View File
@@ -43,7 +43,7 @@ def add_options(parser):
metavar='MODE',
choices=range(0, 4),
help=(
"Set Tesseract 4.0+ OCR engine mode: "
"Set Tesseract 4+ OCR engine mode: "
"0 - original Tesseract only; "
"1 - neural nets LSTM only; "
"2 - Tesseract + LSTM; "
@@ -93,7 +93,7 @@ def check_options(options):
program='tesseract',
package={'linux': 'tesseract-ocr'},
version_checker=tesseract.version,
need_version='4.0.0-beta.1', # using backport for Travis CI
need_version='4.1.1', # Ubuntu 20.04 version
version_parser=tesseract.TesseractVersion,
)
@@ -101,11 +101,6 @@ def check_options(options):
if options.pdf_renderer == 'auto':
options.pdf_renderer = 'sandwich'
if not tesseract.has_user_words() and (options.user_words or options.user_patterns):
log.warning(
"Tesseract 4.0 (which you have installed) ignores --user-words and "
"--user-patterns, so these arguments have no effect."
)
if not tesseract.has_thresholding() and options.tesseract_thresholding != 0:
log.warning(
"The installed version of Tesseract does not support changes to its "
src/ocrmypdf/exceptions.py
-20
View File
@@ -47,26 +47,6 @@ class BadArgsError(ExitCodeException):
exit_code = ExitCode.bad_args
class PdfMergeFailedError(ExitCodeException): # deprecated
"""An intermediate PDF can't be merged.
No longer in use.
"""
exit_code = ExitCode.input_file
message = dedent(
'''\
Failed to merge PDF image layer with OCR layer
Usually this happens because the input PDF file is malformed and
ocrmypdf cannot correct the problem on its own.
Try using
ocrmypdf --pdf-renderer sandwich [..other args..]
'''
)
class MissingDependencyError(ExitCodeException):
"""A third-party dependency is missing."""
src/ocrmypdf/helpers.py
-18
View File
@@ -12,7 +12,6 @@ import shutil
import warnings
from collections.abc import Iterable
from contextlib import suppress
from functools import wraps
from io import StringIO
from math import isclose, isfinite
from pathlib import Path
@@ -291,20 +290,3 @@ def pikepdf_enable_mmap():
# Fix is not in pybind11 2.6.0
# log.debug("pikepdf mmap disabled")
return
def deprecated(func):
"""Warn that function is deprecated."""
@wraps(func)
def new_func(*args, **kwargs):
warnings.simplefilter('always', DeprecationWarning) # turn off filter
warnings.warn(
f"Call to deprecated function {func.__name__}.",
category=DeprecationWarning,
stacklevel=2,
)
warnings.simplefilter('default', DeprecationWarning) # reset filter
return func(*args, **kwargs)
return new_func
src/ocrmypdf/hocrtransform.py
+2 -1
View File
@@ -14,10 +14,11 @@ import re
import warnings
from math import atan, cos, sin
from pathlib import Path
from typing import Any, NamedTuple, Optional, Tuple, Union
from typing import Any, NamedTuple
from xml.etree import ElementTree
with warnings.catch_warnings():
# reportlab uses deprecated load_module
warnings.filterwarnings(
'ignore', category=DeprecationWarning, message=r".*load_module.*"
)
src/ocrmypdf/pluginspec.py
-4
View File
@@ -278,10 +278,6 @@ def filter_page_image(page: PageContext, image_filename: Path) -> Path:
will occur. The return value should be a path to a file in the same folder
as ``image_filename``.
Implementation detail: If the value returned is falsy, OCRmyPDF will ignore
the return value and assume the input file was unmodified. This is deprecated.
To leave the image unmodified, ``image_filename`` should be returned.
Note:
This hook will be called from child processes. Modifying global state
will not affect the main process or other child processes.
src/ocrmypdf/subprocess/__init__.py
+2 -5
View File
@@ -314,7 +314,7 @@ def check_external_program(
program: The name of the program to test.
package: The name of a software package that typically supplies this program.
Usually the same as program.
version_check: A callable without arguments that retrieves the installed
version_checker: A callable without arguments that retrieves the installed
version of program.
need_version: The minimum required version.
required_for: The name of an argument of feature that requires this program.
@@ -325,10 +325,7 @@ def check_external_program(
"""
try:
if callable(version_checker):
found_version = version_checker()
else: # deprecated
found_version = version_checker
found_version = version_checker()
except (CalledProcessError, FileNotFoundError) as e:
_error_missing_program(program, package, required_for, recommended)
if not recommended:
src/ocrmypdf/subprocess/_windows.py
-5
View File
@@ -171,11 +171,6 @@ SHIMS = [
def fix_windows_args(program: str, args, env):
"""Adjust our desired program and command line arguments for use on Windows"""
if sys.version_info < (3, 8):
# bpo-33617 - Windows needs manual Path -> str conversion
args = [os.fspath(arg) for arg in args]
program = os.fspath(program)
# If we are running a .py on Windows, ensure we call it with this Python
# (to support test suite shims)
if program.lower().endswith('.py'):