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

When reading metadata from very large HTML files, do not search the entire file for the metadata, as this can be very slow

Browse Source
This commit is contained in:
Kovid Goyal 2012-02-14 20:14:35 +05:30
parent 20e46a53c6
commit 7895652c76
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
src/calibre/ebooks/metadata/html.py
View File

@ -34,6 +34,7 @@ def get_metadata_(src, encoding=None):
# Title # Title
title = None title = None
pat = re.compile(r'<!--.*?TITLE=(?P<q>[\'"])(.+?)(?P=q).*?-->', re.DOTALL) pat = re.compile(r'<!--.*?TITLE=(?P<q>[\'"])(.+?)(?P=q).*?-->', re.DOTALL)
src = src[:150000] # Searching shouldn't take too long
match = pat.search(src) match = pat.search(src)
if match: if match:
title = match.group(2) title = match.group(2)