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

Fix indents.

Browse Source
This commit is contained in:
John Schember 2011-01-06 20:57:03 -05:00
parent b5599f8ff2
commit c7332d3651
1 changed files with 20 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
src/calibre/ebooks/conversion/utils.py
View File

@ -113,24 +113,24 @@ class PreProcessor(object):
# some lit files don't have any <p> tags or equivalent (generally just plain text between # some lit files don't have any <p> tags or equivalent (generally just plain text between
# <pre> tags), check and mark up line endings if required before proceeding # <pre> tags), check and mark up line endings if required before proceeding
if self.no_markup(html, 0.1): if self.no_markup(html, 0.1):
self.log("not enough paragraph markers, adding now") self.log("not enough paragraph markers, adding now")
# check if content is in pre tags, use txt processor to mark up if so # check if content is in pre tags, use txt processor to mark up if so
pre = re.compile(r'<pre>', re.IGNORECASE) pre = re.compile(r'<pre>', re.IGNORECASE)
if len(pre.findall(html)) == 1: if len(pre.findall(html)) == 1:
self.log("Running Text Processing") self.log("Running Text Processing")
from calibre.ebooks.txt.processor import convert_basic, preserve_spaces, \ from calibre.ebooks.txt.processor import convert_basic, preserve_spaces, \
separate_paragraphs_single_line separate_paragraphs_single_line
outerhtml = re.compile(r'.*?(?<=<pre>)(?P<text>.*)(?=</pre>).*', re.IGNORECASE|re.DOTALL) outerhtml = re.compile(r'.*?(?<=<pre>)(?P<text>.*)(?=</pre>).*', re.IGNORECASE|re.DOTALL)
html = outerhtml.sub('\g<text>', html) html = outerhtml.sub('\g<text>', html)
html = separate_paragraphs_single_line(html) html = separate_paragraphs_single_line(html)
html = preserve_spaces(html) html = preserve_spaces(html)
html = convert_basic(html, epub_split_size_kb=0) html = convert_basic(html, epub_split_size_kb=0)
else: else:
# Add markup naively # Add markup naively
# TODO - find out if there are cases where there are more than one <pre> tag or # TODO - find out if there are cases where there are more than one <pre> tag or
# other types of unmarked html and handle them in some better fashion # other types of unmarked html and handle them in some better fashion
add_markup = re.compile('(?<!>)(\n)') add_markup = re.compile('(?<!>)(\n)')
html = add_markup.sub('</p>\n<p>', html) html = add_markup.sub('</p>\n<p>', html)
###### Mark Indents/Cleanup ###### ###### Mark Indents/Cleanup ######
# #
@ -164,8 +164,8 @@ class PreProcessor(object):
self.log("deleting blank lines") self.log("deleting blank lines")
html = blankreg.sub('', html) html = blankreg.sub('', html)
elif float(len(blanklines)) / float(len(lines)) > 0.40: elif float(len(blanklines)) / float(len(lines)) > 0.40:
blanks_between_paragraphs = True blanks_between_paragraphs = True
#print "blanks between paragraphs is marked True" #print "blanks between paragraphs is marked True"
else: else:
blanks_between_paragraphs = False blanks_between_paragraphs = False
#self.dump(html, 'before_chapter_markup') #self.dump(html, 'before_chapter_markup')