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

Remove code duplication

Browse Source
This commit is contained in:
Kovid Goyal 2011-01-12 12:55:15 -07:00
parent a9c671efaf
commit 24e60cc357
1 changed files with 6 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
src/calibre/ebooks/txt/processor.py
View File

@ -1,4 +1,8 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
__license__ = 'GPL v3'
__copyright__ = '2009, John Schember <john@nachtimwald.com>'
__docformat__ = 'restructuredtext en'
''' '''
Read content from txt file. Read content from txt file.
@ -10,10 +14,7 @@ from calibre import prepare_string_for_xml, isbytestring
from calibre.ebooks.metadata.opf2 import OPFCreator from calibre.ebooks.metadata.opf2 import OPFCreator
from calibre.ebooks.txt.heuristicprocessor import TXTHeuristicProcessor from calibre.ebooks.txt.heuristicprocessor import TXTHeuristicProcessor
from calibre.ebooks.conversion.preprocess import DocAnalysis from calibre.ebooks.conversion.preprocess import DocAnalysis
from calibre.utils.cleantext import clean_ascii_chars
__license__ = 'GPL v3'
__copyright__ = '2009, John Schember <john@nachtimwald.com>'
__docformat__ = 'restructuredtext en'
HTML_TEMPLATE = u'<html><head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"/><title>%s</title></head><body>\n%s\n</body></html>' HTML_TEMPLATE = u'<html><head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"/><title>%s</title></head><body>\n%s\n</body></html>'
@ -33,9 +34,7 @@ def clean_txt(txt):
# Remove excessive line breaks. # Remove excessive line breaks.
txt = re.sub('\n{3,}', '\n\n', txt) txt = re.sub('\n{3,}', '\n\n', txt)
#remove ASCII invalid chars : 0 to 8 and 11-14 to 24 #remove ASCII invalid chars : 0 to 8 and 11-14 to 24
chars = list(range(8)) + [0x0B, 0x0E, 0x0F] + list(range(0x10, 0x19)) txt = clean_ascii_chars(txt)
illegal_chars = re.compile(u'|'.join(map(unichr, chars)))
txt = illegal_chars.sub('', txt)
return txt return txt