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

comments and minor tweak

Browse Source
This commit is contained in:
ldolse 2010-09-13 09:18:45 +10:00
parent cdb696f63b
commit 548417ea6b
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/calibre/ebooks/conversion/utils.py
View File

@ -111,7 +111,7 @@ class PreProcessor(object):
html = add_markup.sub('</p>\n<p>', html)
# detect chapters/sections to match xpath or splitting logic
heading = re.compile('<h(1|2)[^>]*>', re.IGNORECASE)
heading = re.compile('<h[1-3][^>]*>', re.IGNORECASE)
self.html_preprocess_sections = len(heading.findall(html))
self.log("found " + str(self.html_preprocess_sections) + " pre-existing headings")
#
@ -134,7 +134,7 @@ class PreProcessor(object):
self.log("Unwrapping Lines")
# Some OCR sourced files have line breaks in the html using a combination of span & p tags
# span are used for hard line breaks, p for new paragraphs. Determine which is used so
# that lines can be wrapped across page boundaries
# that lines can be un-wrapped across page boundaries
paras_reg = re.compile('<p[^>]*>', re.IGNORECASE)
spans_reg = re.compile('<span[^>]*>', re.IGNORECASE)
paras = len(paras_reg.findall(html))