From 5f7858455d6b980bd1303dec26fe2e069b16b582 Mon Sep 17 00:00:00 2001 From: Miroslav Stampar Date: Tue, 7 Jun 2011 05:57:21 +0000 Subject: [PATCH] fix for a bug reported by l0rda@l0rda.biz --- lib/request/comparison.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/lib/request/comparison.py b/lib/request/comparison.py index 653a81064..d164e841e 100644 --- a/lib/request/comparison.py +++ b/lib/request/comparison.py @@ -72,9 +72,9 @@ def comparison(page, getRatioValue=False, pageLength=None): # Preventing "Unicode equal comparison failed to convert both arguments to Unicode" # (e.g. if one page is PDF and the other is HTML) if isinstance(seqMatcher.a, str) and isinstance(page, unicode): - page = page.encode(kb.pageEncoding or DEFAULT_PAGE_ENCODING) + page = page.encode(kb.pageEncoding or DEFAULT_PAGE_ENCODING, 'ignore') elif isinstance(seqMatcher.a, unicode) and isinstance(page, str): - seqMatcher.a = seqMatcher.a.encode(kb.pageEncoding or DEFAULT_PAGE_ENCODING) + seqMatcher.a = seqMatcher.a.encode(kb.pageEncoding or DEFAULT_PAGE_ENCODING, 'ignore') seqMatcher.set_seq1(getFilteredPageContent(seqMatcher.a, True) if conf.textOnly else seqMatcher.a) seqMatcher.set_seq2(getFilteredPageContent(page, True) if conf.textOnly else page)