diff --git a/conf/regex-urlfilter.txt b/conf/regex-urlfilter.txt index 78b2b31..e9b719a 100644 --- a/conf/regex-urlfilter.txt +++ b/conf/regex-urlfilter.txt @@ -30,7 +30,10 @@ -\.(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)$ # skip URLs containing certain characters as probable queries, etc. --[?*!@=] +# NOTE: ? and = were removed from this because we are using normalization to handle queries. +# This is due to needing to support use of the drupal pager, etc. +# Default: -[?*!@=] +-[*!@] # skip URLs with slash-delimited segment that repeats 3+ times, to break loops -.*(/[^/]+)/[^/]+\1/[^/]+\1/ diff --git a/conf/suffix-urlfilter.txt b/conf/suffix-urlfilter.txt index b510d4a..a90d58b 100644 --- a/conf/suffix-urlfilter.txt +++ b/conf/suffix-urlfilter.txt @@ -89,3 +89,11 @@ # disc-images .iso .bin + +# Apple disk images / etc. +.dmg +.smi +.sit +.dsk +.bin +.hqx