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
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,
)