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

Conversion pipeline: When detecting chapters/toc links from HTML normalize spaces and increase maximum TOC title length to 1000 characters from 100 characters. Fixes #9363 (Shortening text on generating TOC.)

Browse Source
This commit is contained in:
Kovid Goyal 2011-03-15 14:51:22 -06:00
parent 2f4876f474
commit 428ed899fc
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/calibre/ebooks/oeb/transforms/structure.py
View File

@ -81,6 +81,7 @@ class DetectStructure(object):
page_break_after = 'display: block; page-break-after: always' page_break_after = 'display: block; page-break-after: always'
for item, elem in self.detected_chapters: for item, elem in self.detected_chapters:
text = xml2text(elem).strip() text = xml2text(elem).strip()
text = re.sub(r'\s+', ' ', text.strip())
self.log('\tDetected chapter:', text[:50]) self.log('\tDetected chapter:', text[:50])
if chapter_mark == 'none': if chapter_mark == 'none':
continue continue
@ -137,7 +138,8 @@ class DetectStructure(object):
text = elem.get('title', '') text = elem.get('title', '')
if not text: if not text:
text = elem.get('alt', '') text = elem.get('alt', '')
text = text[:100].strip() text = re.sub(r'\s+', ' ', text.strip())
text = text[:1000].strip()
id = elem.get('id', 'calibre_toc_%d'%counter) id = elem.get('id', 'calibre_toc_%d'%counter)
elem.set('id', id) elem.set('id', id)
href = '#'.join((item.href, id)) href = '#'.join((item.href, id))