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

LIT Input: Handle LIT files that are really TXT files, by simply splitting the text into pararaphs at blank lines.

Browse Source
This commit is contained in:
Kovid Goyal 2009-12-01 18:43:31 +00:00
parent 1e1bd8c742
commit ce5f89c2b4
1 changed files with 22 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
src/calibre/ebooks/lit/input.py
View File

@ -21,4 +21,26 @@ class LITInput(InputFormatPlugin):
from calibre.ebooks.conversion.plumber import create_oebbook
return create_oebbook(log, stream, options, self, reader=LitReader)
def postprocess_book(self, oeb, opts, log):
from calibre.ebooks.oeb.base import XHTML_NS, XPath, XHTML
for item in oeb.spine:
root = item.data
if not hasattr(root, 'xpath'): continue
body = XPath('//h:body')(root)
if body:
body = body[0]
if len(body) == 1 and body[0].tag == XHTML('pre'):
pre = body[0]
from calibre.ebooks.txt.processor import convert_basic
from lxml import etree
import copy
html = convert_basic(pre.text).replace('<html>',
'<html xmlns="%s">'%XHTML_NS)
root = etree.fromstring(html)
body = XPath('//h:body')(root)
pre.tag = XHTML('div')
pre.text = ''
for elem in body:
ne = copy.deepcopy(elem)
pre.append(ne)