From 274e522f851824e1aa26b85dd91220cbde06fdc4 Mon Sep 17 00:00:00 2001 From: gojomo Date: Fri, 2 Jul 2010 17:47:41 +0000 Subject: [PATCH] [HER-1793] BOM in seeds.txt confuses heritrix * RegexpLineIterator.java ignore \ufeff along with leading whitespace --- .../main/java/org/archive/util/iterator/RegexLineIterator.java | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/commons/src/main/java/org/archive/util/iterator/RegexLineIterator.java b/commons/src/main/java/org/archive/util/iterator/RegexLineIterator.java index 2103891c..b6200780 100644 --- a/commons/src/main/java/org/archive/util/iterator/RegexLineIterator.java +++ b/commons/src/main/java/org/archive/util/iterator/RegexLineIterator.java @@ -44,7 +44,7 @@ extends TransformingIteratorWrapper { public static final String COMMENT_LINE = "\\s*(#.*)?"; public static final String NONWHITESPACE_ENTRY_TRAILING_COMMENT = - "^\\s*(\\S+)\\s*(#.*)?$"; + "^[\\s\ufeff]*(\\S+)\\s*(#.*)?$"; public static final String TRIMMED_ENTRY_TRAILING_COMMENT = "^\\s*([^#]+?)\\s*(#.*)?$";