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

E-book viewer: When doing a search do not match text in comments and element attributes

Browse Source
This commit is contained in:
Kovid Goyal 2015-11-13 00:34:07 +05:30
parent eced07af18
commit 5f9e987b27
1 changed files with 20 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
src/calibre/ebooks/oeb/iterator/book.py
View File

@ -19,8 +19,7 @@ from calibre.ebooks.metadata.opf2 import OPF
from calibre.ptempfile import TemporaryDirectory from calibre.ptempfile import TemporaryDirectory
from calibre.utils.config import DynamicConfig from calibre.utils.config import DynamicConfig
from calibre.utils.logging import default_log from calibre.utils.logging import default_log
from calibre import (guess_type, prepare_string_for_xml, from calibre import guess_type, prepare_string_for_xml
xml_replace_entities)
from calibre.ebooks.oeb.transforms.cover import CoverManager from calibre.ebooks.oeb.transforms.cover import CoverManager
from calibre.ebooks.oeb.iterator.spine import (SpineItem, create_indexing_data) from calibre.ebooks.oeb.iterator.spine import (SpineItem, create_indexing_data)
from calibre.ebooks.oeb.iterator.bookmarks import BookmarksMixin from calibre.ebooks.oeb.iterator.bookmarks import BookmarksMixin
@ -61,19 +60,32 @@ class EbookIterator(BookmarksMixin):
self.ebook_ext = ext.replace('original_', '') self.ebook_ext = ext.replace('original_', '')
def search(self, text, index, backwards=False): def search(self, text, index, backwards=False):
text = prepare_string_for_xml(text.lower()) from calibre.ebooks.oeb.polish.parsing import parse
pmap = [(i, path) for i, path in enumerate(self.spine)] pmap = [(i, path) for i, path in enumerate(self.spine)]
if backwards: if backwards:
pmap.reverse() pmap.reverse()
q = text.lower()
for i, path in pmap: for i, path in pmap:
if (backwards and i < index) or (not backwards and i > index): if (backwards and i < index) or (not backwards and i > index):
with open(path, 'rb') as f: with open(path, 'rb') as f:
raw = f.read().decode(path.encoding) raw = f.read().decode(path.encoding)
try: root = parse(raw)
raw = xml_replace_entities(raw) fragments = []
except: def serialize(elem):
pass if elem.text:
if text in raw.lower(): fragments.append(elem.text.lower())
if elem.tail:
fragments.append(elem.tail.lower())
for child in elem.iterchildren():
if hasattr(getattr(child, 'tag', None), 'rpartition') and child.tag.rpartition('}')[-1] not in {'script', 'style', 'del'}:
serialize(child)
elif getattr(child, 'tail', None):
fragments.append(child.tail.lower())
for body in root.xpath('//*[local-name() = "body"]'):
body.tail = None
serialize(body)
if q in ''.join(fragments):
return i return i
def __enter__(self, processed=False, only_input_plugin=False, def __enter__(self, processed=False, only_input_plugin=False,