From ed2b94ac9d98be1ed3564c36071b62e6335ea60d Mon Sep 17 00:00:00 2001 From: John Schember Date: Sat, 5 Feb 2011 10:46:32 -0500 Subject: [PATCH] Heuristics: Tweak italicize patterns to make them more robust. --- src/calibre/ebooks/conversion/utils.py | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/src/calibre/ebooks/conversion/utils.py b/src/calibre/ebooks/conversion/utils.py index 63eca10714..e8e2a82949 100644 --- a/src/calibre/ebooks/conversion/utils.py +++ b/src/calibre/ebooks/conversion/utils.py @@ -149,17 +149,17 @@ class HeuristicProcessor(object): ] ITALICIZE_STYLE_PATS = [ - r'(?msu)(?<=\s)_(?P\S[^_]{0,40}?\S)?_(?=[\s\.,\!\?])', - r'(?msu)(?<=\s)/(?P\S[^/]{0,40}?\S)?/(?=[\s\.,\!\?])', - r'(?msu)(?<=\s)~~(?P\S[^~]{0,40}?\S)?~~(?=[\s\.,\!\?])', - r'(?msu)(?<=\s)\*(?P\S[^\*]{0,40}?\S)?\*(?=[\s\.,\!\?])', - r'(?msu)(?<=\s)~(?P\S[^~]{0,40}?\S)?~(?=[\s\.,\!\?])', - r'(?msu)(?<=\s)_/(?P\S[^/_]{0,40}?\S)?/_(?=[\s\.,\!\?])', - r'(?msu)(?<=\s)_\*(?P\S[^\*_]{0,40}?\S)?\*_(?=[\s\.,\!\?])', - r'(?msu)(?<=\s)\*/(?P\S[^/\*]{0,40}?\S)?/\*(?=[\s\.,\!\?])', - r'(?msu)(?<=\s)_\*/(?P\S[^\*_]{0,40}?\S)?/\*_(?=[\s\.,\!\?])', - r'(?msu)(?<=\s)/:(?P\S[^:/]{0,40}?\S)?:/(?=[\s\.,\!\?])', - r'(?msu)(?<=\s)\|:(?P\S[^:\|]{0,40}?\S)?:\|(?=[\s\.,\!\?])', + r'(?msu)(?<=[\s>"])_(?P[^_]+)?_', + r'(?msu)(?<=[\s>"])/(?P[^/]+)?/', + r'(?msu)(?<=[\s>"])~~(?P[^~]+)?~~', + r'(?msu)(?<=[\s>"])\*(?P[^\*]+)?\*', + r'(?msu)(?<=[\s>"])~(?P[^~]+)?~', + r'(?msu)(?<=[\s>"])_/(?P[^/_]+)?/_', + r'(?msu)(?<=[\s>"])_\*(?P[^\*_]+)?\*_', + r'(?msu)(?<=[\s>"])\*/(?P[^/\*]+)?/\*', + r'(?msu)(?<=[\s>"])_\*/(?P[^\*_]+)?/\*_', + r'(?msu)(?<=[\s>"])/:(?P[^:/]+)?:/', + r'(?msu)(?<=[\s>"])\|:(?P[^:\|]+)?:\|', ] for word in ITALICIZE_WORDS: