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

Regex builder: Convert entities so people don't use them in building their regexes. Fixes #5549 (Not removing header/footer)

Browse Source
This commit is contained in:
Kovid Goyal 2010-06-01 18:40:12 -06:00
parent 900ff7204b
commit 7213c1e4b6
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/calibre/gui2/convert/regex_builder.py
View File

@ -14,6 +14,7 @@ from calibre.gui2.convert.regex_builder_ui import Ui_RegexBuilder
from calibre.gui2.convert.xexp_edit_ui import Ui_Form as Ui_Edit from calibre.gui2.convert.xexp_edit_ui import Ui_Form as Ui_Edit
from calibre.gui2 import error_dialog, choose_files from calibre.gui2 import error_dialog, choose_files
from calibre.ebooks.oeb.iterator import EbookIterator from calibre.ebooks.oeb.iterator import EbookIterator
from calibre.ebooks.conversion.preprocess import convert_entities
from calibre.gui2.dialogs.choose_format import ChooseFormatDialog from calibre.gui2.dialogs.choose_format import ChooseFormatDialog
class RegexBuilder(QDialog, Ui_RegexBuilder): class RegexBuilder(QDialog, Ui_RegexBuilder):
@ -87,8 +88,10 @@ class RegexBuilder(QDialog, Ui_RegexBuilder):
self.iterator = EbookIterator(pathtoebook) self.iterator = EbookIterator(pathtoebook)
self.iterator.__enter__(only_input_plugin=True) self.iterator.__enter__(only_input_plugin=True)
text = [u''] text = [u'']
ent_pat = re.compile(r'&(\S+?);')
for path in self.iterator.spine: for path in self.iterator.spine:
html = open(path, 'rb').read().decode('utf-8', 'replace') html = open(path, 'rb').read().decode('utf-8', 'replace')
html = ent_pat.sub(convert_entities, html)
text.append(html) text.append(html)
self.preview.setPlainText('\n---\n'.join(text)) self.preview.setPlainText('\n---\n'.join(text))