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

tesseract.py: update canned HOCR template to tess 3.05 output

Browse Source 
Seems better to not claim the existence of several entities that don’t
exist as the older one does
This commit is contained in:
James R. Barlow
2017-05-14 23:40:09 -07:00
parent 65b89687a9
commit 131a5b741d
1 changed files with 9 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ocrmypdf/exec/tesseract.py
+9 -13
View File
@@ -21,27 +21,23 @@ OrientationConfidence = namedtuple(
'OrientationConfidence',
('angle', 'confidence'))
HOCR_TEMPLATE = '''<?xml version="1.0" encoding="UTF-8"?>
HOCR_TEMPLATE = """<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
<head>
<title></title>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<meta name='ocr-system' content='tesseract 3.02.02' />
<meta http-equiv="Content-Type" content="text/html;charset=utf-8" />
<meta name='ocr-system' content='tesseract 3.05.00' />
<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>
</p>
</div>
</head>
<body>
<div class='ocr_page' id='page_1' title='image "_blank.png"; bbox 0 0 {0} {1}; ppageno 0'>
</div>
</body>
</html>'''
</html>
"""
@lru_cache(maxsize=1)
def version():