[HER-1793] BOM in seeds.txt confuses heritrix

* RegexpLineIterator.java
    ignore \ufeff along with leading whitespace
This commit is contained in:
gojomo
2010-07-02 17:47:41 +00:00
parent f75f95648a
commit 274e522f85
@@ -44,7 +44,7 @@ extends TransformingIteratorWrapper<String,String> {
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*(#.*)?$";