Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-31 14:33:54 -04:00
Code Issues Packages Projects Releases Wiki Activity

LIT Input: Fix smarten punctuation not working for text (as opposed to HTML) based LIT files. Fixes #1460998 [Private bug](https://bugs.launchpad.net/calibre/+bug/1460998)

Browse Source
This commit is contained in:
Kovid Goyal 2015-06-04 08:18:59 +05:30
parent dd1c304626
commit cce2f70507
1 changed files with 7 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
src/calibre/ebooks/conversion/plugins/lit_input.py
View File

@ -26,7 +26,8 @@ class LITInput(InputFormatPlugin):
from calibre.ebooks.oeb.base import XHTML_NS, XPath, XHTML from calibre.ebooks.oeb.base import XHTML_NS, XPath, XHTML
for item in oeb.spine: for item in oeb.spine:
root = item.data root = item.data
if not hasattr(root, 'xpath'): continue if not hasattr(root, 'xpath'):
continue
for bad in ('metadata', 'guide'): for bad in ('metadata', 'guide'):
metadata = XPath('//h:'+bad)(root) metadata = XPath('//h:'+bad)(root)
if metadata: if metadata:
@ -42,11 +43,16 @@ class LITInput(InputFormatPlugin):
from calibre.ebooks.chardet import xml_to_unicode from calibre.ebooks.chardet import xml_to_unicode
from lxml import etree from lxml import etree
import copy import copy
self.log('LIT file with all text in singe <pre> tag detected')
html = separate_paragraphs_single_line(pre.text) html = separate_paragraphs_single_line(pre.text)
html = convert_basic(html).replace('<html>', html = convert_basic(html).replace('<html>',
'<html xmlns="%s">'%XHTML_NS) '<html xmlns="%s">'%XHTML_NS)
html = xml_to_unicode(html, strip_encoding_pats=True, html = xml_to_unicode(html, strip_encoding_pats=True,
resolve_entities=True)[0] resolve_entities=True)[0]
if opts.smarten_punctuation:
# SmartyPants skips text inside <pre> tags
from calibre.ebooks.conversion.preprocess import smarten_punctuation
html = smarten_punctuation(html, self.log)
root = etree.fromstring(html) root = etree.fromstring(html)
body = XPath('//h:body')(root) body = XPath('//h:body')(root)
pre.tag = XHTML('div') pre.tag = XHTML('div')