NUTCH-2035 urlfilter-regex case insensitive rules

apache · Dec 15, 2017 · df14c8a · df14c8a
1 parent 0e3036b
commit df14c8a
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/conf/regex-urlfilter.txt.template b/conf/regex-urlfilter.txt.template
@@ -27,7 +27,7 @@
 
 # skip image and other suffixes we can't yet parse
 # for a more extensive coverage use the urlfilter-suffix plugin
--\.(gif|GIF|jpg|JPG|png|PNG|ico|ICO|css|CSS|sit|SIT|eps|EPS|wmf|WMF|zip|ZIP|ppt|PPT|mpg|MPG|xls|XLS|gz|GZ|rpm|RPM|tgz|TGZ|mov|MOV|exe|EXE|jpeg|JPEG|bmp|BMP|js|JS)$
+-(?i)\.(gif|jpg|png|ico|css|sit|eps|wmf|zip|ppt|mpg|xls|gz|rpm|tgz|mov|exe|jpeg|bmp|js)$
 
 # skip URLs containing certain characters as probable queries, etc.
 -[?*!@=]