Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

PDF Input: Fix more characters that the PDF format encodes as two characters that are drawn on top of each other.

Browse Source
This commit is contained in:
John Schember 2010-09-04 17:09:10 -04:00
parent 87c92c5e40
commit 3e24b6a115
1 changed files with 48 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

73
src/calibre/ebooks/conversion/preprocess.py
View File

@ -142,55 +142,78 @@ class HTMLPreProcessor(object):
# Fix pdftohtml markup
PDFTOHTML = [
# Fix umlauts
(re.compile(u'¨\s*(<br.*?>)*\s*o', re.UNICODE), lambda match: u'ö'),
(re.compile(u'¨\s*(<br.*?>)*\s*O', re.UNICODE), lambda match: u'Ö'),
(re.compile(u'¨\s*(<br.*?>)*\s*u', re.UNICODE), lambda match: u'ü'),
(re.compile(u'¨\s*(<br.*?>)*\s*U', re.UNICODE), lambda match: u'Ü'),
# ¨
(re.compile(u'¨\s*(<br.*?>)*\s*a', re.UNICODE), lambda match: u'ä'),
(re.compile(u'¨\s*(<br.*?>)*\s*A', re.UNICODE), lambda match: u'Ä'),
(re.compile(u'¨\s*(<br.*?>)*\s*e', re.UNICODE), lambda match: u'ë'),
(re.compile(u'¨\s*(<br.*?>)*\s*E', re.UNICODE), lambda match: u'Ë'),
(re.compile(u'¨\s*(<br.*?>)*\s*i', re.UNICODE), lambda match: u'ï'),
(re.compile(u'¨\s*(<br.*?>)*\s*I', re.UNICODE), lambda match: u'Ï'),
(re.compile(u'¨\s*(<br.*?>)*\s*a', re.UNICODE), lambda match: u'ä'),
(re.compile(u'¨\s*(<br.*?>)*\s*A', re.UNICODE), lambda match: u'Ä'),
(re.compile(u'¨\s*(<br.*?>)*\s*o', re.UNICODE), lambda match: u'ö'),
(re.compile(u'¨\s*(<br.*?>)*\s*O', re.UNICODE), lambda match: u'Ö'),
(re.compile(u'¨\s*(<br.*?>)*\s*u', re.UNICODE), lambda match: u'ü'),
(re.compile(u'¨\s*(<br.*?>)*\s*U', re.UNICODE), lambda match: u'Ü'),
# Fix accents
(re.compile(u'`\s*(<br.*?>)*\s*o', re.UNICODE), lambda match: u'ò'),
(re.compile(u'`\s*(<br.*?>)*\s*O', re.UNICODE), lambda match: u'Ò'),
(re.compile(u'`\s*(<br.*?>)*\s*u', re.UNICODE), lambda match: u'ù'),
(re.compile(u'`\s*(<br.*?>)*\s*U', re.UNICODE), lambda match: u'Ù'),
# `
(re.compile(u'`\s*(<br.*?>)*\s*a', re.UNICODE), lambda match: u'à'),
(re.compile(u'`\s*(<br.*?>)*\s*A', re.UNICODE), lambda match: u'À'),
(re.compile(u'`\s*(<br.*?>)*\s*e', re.UNICODE), lambda match: u'è'),
(re.compile(u'`\s*(<br.*?>)*\s*E', re.UNICODE), lambda match: u'È'),
(re.compile(u'`\s*(<br.*?>)*\s*i', re.UNICODE), lambda match: u'ì'),
(re.compile(u'`\s*(<br.*?>)*\s*I', re.UNICODE), lambda match: u'Ì'),
(re.compile(u'`\s*(<br.*?>)*\s*a', re.UNICODE), lambda match: u'à'),
(re.compile(u'`\s*(<br.*?>)*\s*A', re.UNICODE), lambda match: u'À'),
(re.compile(u'`\s*(<br.*?>)*\s*o', re.UNICODE), lambda match: u'ò'),
(re.compile(u'`\s*(<br.*?>)*\s*O', re.UNICODE), lambda match: u'Ò'),
(re.compile(u'`\s*(<br.*?>)*\s*u', re.UNICODE), lambda match: u'ù'),
(re.compile(u'`\s*(<br.*?>)*\s*U', re.UNICODE), lambda match: u'Ù'),
(re.compile(u'´\s*(<br.*?>)*\s*o', re.UNICODE), lambda match: u'ó'),
(re.compile(u'´\s*(<br.*?>)*\s*O', re.UNICODE), lambda match: u'Ó'),
(re.compile(u'´\s*(<br.*?>)*\s*u', re.UNICODE), lambda match: u'ú'),
(re.compile(u'´\s*(<br.*?>)*\s*U', re.UNICODE), lambda match: u'Ú'),
# ´
(re.compile(u'´\s*(<br.*?>)*\s*a', re.UNICODE), lambda match: u'á'),
(re.compile(u'´\s*(<br.*?>)*\s*A', re.UNICODE), lambda match: u'Á'),
(re.compile(u'´\s*(<br.*?>)*\s*c', re.UNICODE), lambda match: u'ć'),
(re.compile(u'´\s*(<br.*?>)*\s*C', re.UNICODE), lambda match: u'Ć'),
(re.compile(u'´\s*(<br.*?>)*\s*e', re.UNICODE), lambda match: u'é'),
(re.compile(u'´\s*(<br.*?>)*\s*E', re.UNICODE), lambda match: u'É'),
(re.compile(u'´\s*(<br.*?>)*\s*i', re.UNICODE), lambda match: u'í'),
(re.compile(u'´\s*(<br.*?>)*\s*I', re.UNICODE), lambda match: u'Í'),
(re.compile(u'´\s*(<br.*?>)*\s*a', re.UNICODE), lambda match: u'á'),
(re.compile(u'´\s*(<br.*?>)*\s*A', re.UNICODE), lambda match: u'Á'),
(re.compile(u'´\s*(<br.*?>)*\s*o', re.UNICODE), lambda match: u'ó'),
(re.compile(u'´\s*(<br.*?>)*\s*O', re.UNICODE), lambda match: u'Ó'),
(re.compile(u'´\s*(<br.*?>)*\s*n', re.UNICODE), lambda match: u'ń'),
(re.compile(u'´\s*(<br.*?>)*\s*N', re.UNICODE), lambda match: u'Ń'),
(re.compile(u'´\s*(<br.*?>)*\s*s', re.UNICODE), lambda match: u'ś'),
(re.compile(u'´\s*(<br.*?>)*\s*S', re.UNICODE), lambda match: u'Ś'),
(re.compile(u'´\s*(<br.*?>)*\s*u', re.UNICODE), lambda match: u'ú'),
(re.compile(u'´\s*(<br.*?>)*\s*U', re.UNICODE), lambda match: u'Ú'),
(re.compile(u'´\s*(<br.*?>)*\s*z', re.UNICODE), lambda match: u'ź'),
(re.compile(u'´\s*(<br.*?>)*\s*Z', re.UNICODE), lambda match: u'Ź'),
(re.compile(u'ˆ\s*(<br.*?>)*\s*o', re.UNICODE), lambda match: u'ô'),
(re.compile(u'ˆ\s*(<br.*?>)*\s*O', re.UNICODE), lambda match: u'Ô'),
(re.compile(u'ˆ\s*(<br.*?>)*\s*u', re.UNICODE), lambda match: u'û'),
(re.compile(u'ˆ\s*(<br.*?>)*\s*U', re.UNICODE), lambda match: u'Û'),
# ˆ
(re.compile(u'ˆ\s*(<br.*?>)*\s*a', re.UNICODE), lambda match: u'â'),
(re.compile(u'ˆ\s*(<br.*?>)*\s*A', re.UNICODE), lambda match: u'Â'),
(re.compile(u'ˆ\s*(<br.*?>)*\s*e', re.UNICODE), lambda match: u'ê'),
(re.compile(u'ˆ\s*(<br.*?>)*\s*E', re.UNICODE), lambda match: u'Ê'),
(re.compile(u'ˆ\s*(<br.*?>)*\s*i', re.UNICODE), lambda match: u'î'),
(re.compile(u'ˆ\s*(<br.*?>)*\s*I', re.UNICODE), lambda match: u'Î'),
(re.compile(u'ˆ\s*(<br.*?>)*\s*a', re.UNICODE), lambda match: u'â'),
(re.compile(u'ˆ\s*(<br.*?>)*\s*A', re.UNICODE), lambda match: u'Â'),
(re.compile(u'ˆ\s*(<br.*?>)*\s*o', re.UNICODE), lambda match: u'ô'),
(re.compile(u'ˆ\s*(<br.*?>)*\s*O', re.UNICODE), lambda match: u'Ô'),
(re.compile(u'ˆ\s*(<br.*?>)*\s*u', re.UNICODE), lambda match: u'û'),
(re.compile(u'ˆ\s*(<br.*?>)*\s*U', re.UNICODE), lambda match: u'Û'),
# Fix more special characters
# ¸
(re.compile(u'¸\s*(<br.*?>)*\s*c', re.UNICODE), lambda match: u'ç'),
(re.compile(u'¸\s*(<br.*?>)*\s*C', re.UNICODE), lambda match: u'Ç'),
# ˛
(re.compile(u'˛\s*(<br.*?>)*\s*a', re.UNICODE), lambda match: u'ą'),
(re.compile(u'˛\s*(<br.*?>)*\s*A', re.UNICODE), lambda match: u'Ą'),
(re.compile(u'˛\s*(<br.*?>)*\s*e', re.UNICODE), lambda match: u'ę'),
(re.compile(u'˛\s*(<br.*?>)*\s*E', re.UNICODE), lambda match: u'Ę'),
# ˙
(re.compile(u'˙\s*(<br.*?>)*\s*z', re.UNICODE), lambda match: u'ż'),
(re.compile(u'˙\s*(<br.*?>)*\s*Z', re.UNICODE), lambda match: u'Ż'),
# Remove page links
(re.compile(r'<a name=\d+></a>', re.IGNORECASE), lambda match: ''),
# Remove <hr> tags