mirror of
https://github.com/internetarchive/heritrix3.git
synced 2026-11-15 10:20:47 +00:00
[HER-1793] BOM in seeds.txt confuses heritrix
* RegexpLineIterator.java
ignore \ufeff along with leading whitespace
This commit is contained in:
1 parent
f75f95648a
commit
274e522f85
1 file changed
+1
-1
@@ -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*(#.*)?$";
|
||||
|
||||
|
||||
Reference in new issue
Block a user