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

Adopt ruff and fix prelim lints

Browse Source
This commit is contained in:
James R. Barlow
2023-04-14 00:19:17 -07:00
parent 42c0d0f48f
commit b7eb93eb79
9 changed files with 31 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/conf.py
+2 -1
View File
@@ -2,6 +2,8 @@
# SPDX-FileCopyrightText: 2022 James R. Barlow
# SPDX-License-Identifier: CC-BY-SA-4.0
# ruff: noqa: E402
# ocrmypdf documentation build configuration file, created by
# sphinx-quickstart on Sun Sep 4 14:29:43 2016.
#
@@ -78,7 +80,6 @@ author = 'James R. Barlow'
import os
from importlib.metadata import version as package_version
on_rtd = os.environ.get('READTHEDOCS') == 'True'
if on_rtd:
pyproject.toml
+7
View File
@@ -188,3 +188,10 @@ ignore_missing_imports = true
good-names = ["i", "j", "k", "ex", "Run", "_", "e", "p", "im", "w", "h", "m", "x", "y", "a", "b", "fp", "n", "f", "s", "v", "q", "dx", "dy"]
logging-format-style = "old"
disable = ["raw-checker-failed", "bad-inline-option", "locally-disabled", "file-ignored", "suppressed-message", "useless-suppression", "deprecated-pragma", "use-symbolic-message-instead", "logging-fstring-interpolation", "missing-function-docstring", "too-few-public-methods"]
[tool.ruff]
src = ["src"]
select = ["E"]
[tool.ruff.pydocstyle]
convention = "google"
src/ocrmypdf/_exec/tesseract.py
+4 -2
View File
@@ -34,10 +34,12 @@ HOCR_TEMPLATE = """<?xml version="1.0" encoding="UTF-8"?>
<title></title>
<meta http-equiv="Content-Type" content="text/html;charset=utf-8" />
<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'/>
<meta name='ocr-capabilities'
content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
</head>
<body>
<div class='ocr_page' id='page_1' title='image "_blank.png"; bbox 0 0 {0} {1}; ppageno 0'>
<div class='ocr_page' id='page_1'
title='image "_blank.png"; bbox 0 0 {0} {1}; ppageno 0'>
</div>
</body>
</html>
src/ocrmypdf/_graft.py
+2 -1
View File
@@ -131,7 +131,8 @@ class OcrGrafter:
text_misaligned = (text_rotation - content_rotation) % 360
log.debug(
f"Text rotation: (text, autorotate, content) -> text misalignment = "
f"({text_rotation}, {autorotate_correction}, {content_rotation}) -> {text_misaligned}"
f"({text_rotation}, {autorotate_correction}, {content_rotation}) -> "
f"{text_misaligned}"
)
if textpdf and self.font:
src/ocrmypdf/_pipeline.py
+2 -2
View File
@@ -315,8 +315,8 @@ def is_ocr_required(page_context: PageContext) -> bool:
log.warning(
"page has no images - "
"all vector content will be "
f"rasterized at {VECTOR_PAGE_DPI} DPI, losing some resolution and likely "
"increasing file size. Use --oversample to adjust the "
f"rasterized at {VECTOR_PAGE_DPI} DPI, losing some resolution and "
"likely increasing file size. Use --oversample to adjust the "
"DPI."
)
else:
src/ocrmypdf/_validation.py
+5 -6
View File
@@ -109,12 +109,10 @@ def check_options_output(options: Namespace) -> None:
def check_options_sidecar(options: Namespace) -> None:
if options.sidecar == '\0':
if options.output_file == '-':
raise BadArgsError(
"--sidecar filename must be specified when output file is stdout."
)
raise BadArgsError("--sidecar filename needed when output file is stdout.")
elif options.output_file == os.devnull:
raise BadArgsError(
"--sidecar filename must be specified when output file is /dev/null or NUL."
"--sidecar filename needed when output file is /dev/null or NUL."
)
options.sidecar = options.output_file + '.txt'
if options.sidecar == options.input_file or options.sidecar == options.output_file:
@@ -276,7 +274,8 @@ def create_input_file(options: Namespace, work_folder: Path) -> tuple[Path, str]
"permissions correctly.\n"
"You may find it easier to use stdin/stdout:"
"\n"
"\tdocker run -i --rm jbarlow83/ocrmypdf - - <input.pdf >output.pdf\n"
"\tdocker run -i --rm jbarlow83/ocrmypdf - - <input.pdf >output.pdf"
"\n"
)
raise InputFileError(msg) from e
@@ -333,7 +332,7 @@ def report_output_file_size(
for arg in image_preproc:
if getattr(options, arg, False):
reasons.append(
f"The argument --{arg.replace('_', '-')} was issued, causing transcoding."
f"--{arg.replace('_', '-')} was issued, causing transcoding."
)
reasons.extend(optimize_messages)
tests/plugins/tesseract_debug_rotate.py
+4 -2
View File
@@ -28,13 +28,15 @@ HOCR_TEMPLATE = '''<?xml version="1.0" encoding="UTF-8"?>
<title></title>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<meta name='ocr-system' content='tesseract 4.1.1' />
<meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word'/>
<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 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>
tests/plugins/tesseract_noop.py
+4 -2
View File
@@ -26,13 +26,15 @@ HOCR_TEMPLATE = '''<?xml version="1.0" encoding="UTF-8"?>
<title></title>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<meta name='ocr-system' content='tesseract 4.1.1' />
<meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word'/>
<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 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>
tests/test_validation.py
+1 -1
View File
@@ -219,7 +219,7 @@ def test_version_comparison():
vd.check_external_program(
program="tesseract",
package="tesseract",
version_checker=lambda: 'v4.1.1.20181030', # Some Windows builds use this format
version_checker=lambda: 'v4.1.1.20181030', # Used in some Windows builds
need_version='4.1.1',
version_parser=TesseractVersion,
)