Author: snagel
Date: Wed Oct 10 21:54:37 2012
New Revision: 1396817
URL: http://svn.apache.org/viewvc?rev=1396817&view=rev
Log:
NUTCH-706 (applied correct patch)
Modified:
nutch/trunk/conf/regex-normalize.xml.template
nutch/trunk/src/plugin/urlnormalizer-regex/sample/regex-normalize-default.test
nutch/trunk/src/plugin/urlnormalizer-regex/sample/regex-normalize-default.xml
Modified: nutch/trunk/conf/regex-normalize.xml.template
URL:
http://svn.apache.org/viewvc/nutch/trunk/conf/regex-normalize.xml.template?rev=1396817&r1=1396816&r2=1396817&view=diff
==============================================================================
--- nutch/trunk/conf/regex-normalize.xml.template (original)
+++ nutch/trunk/conf/regex-normalize.xml.template Wed Oct 10 21:54:37 2012
@@ -29,7 +29,7 @@
<!-- removes session ids from urls (such as jsessionid and PHPSESSID) -->
<regex>
-
<pattern>([;_]?\b((?i)l|j|bv_)?((?i)sid|phpsessid|sessionid)=.*?)(\?|&|#|$)</pattern>
+
<pattern>(?i)(;?\b_?(l|j|bv_)?(sid|phpsessid|sessionid)=.*?)(\?|&|#|$)</pattern>
<substitution>$4</substitution>
</regex>
Modified:
nutch/trunk/src/plugin/urlnormalizer-regex/sample/regex-normalize-default.test
URL:
http://svn.apache.org/viewvc/nutch/trunk/src/plugin/urlnormalizer-regex/sample/regex-normalize-default.test?rev=1396817&r1=1396816&r2=1396817&view=diff
==============================================================================
---
nutch/trunk/src/plugin/urlnormalizer-regex/sample/regex-normalize-default.test
(original)
+++
nutch/trunk/src/plugin/urlnormalizer-regex/sample/regex-normalize-default.test
Wed Oct 10 21:54:37 2012
@@ -11,8 +11,13 @@ http://www.foo.com/foo.html;jsessionid=1
http://www.foo.com/foo.html?param=1&another=2;jsessionid=1E6FEC0D14D044541DD84D2D013D29ED
http://www.foo.com/foo.html?param=1&another=2
http://www.foo.com/foo.html;jsessionid=1E6FEC0D14D044541DD84D2D013D29ED?param=1&another=2
http://www.foo.com/foo.html?param=1&another=2
http://www.foo.com/foo.php?&x=1&sid=xyz&something=1
http://www.foo.com/foo.php?x=1&something=1
-# but NewsId is not a session id (NUTCH-706, NUTCH-1328)
+http://www.foo.com/foo.html?_sessionID=824A6C0A13a7e11205wxN28F44E3
http://www.foo.com/foo.html
+http://www.foo.com/foo.php?_sessionid=qmyrcedt&outputformat=html&path=/3_images/foo
http://www.foo.com/foo.php?outputformat=html&path=/3_images/foo
+http://www.foo.com/foo.php?_pid=2&_spid=0&lang=en&_sessionid=e36902d5bb2d0d922fc24b43
http://www.foo.com/foo.php?_pid=2&_spid=0&lang=en
+http://www.foo.com/foo.php?app=content&content=overview&lang=en&_sid=587fba8f825b05844526519fdb7d75c8&b=35&m=47
http://www.foo.com/foo.php?app=content&content=overview&lang=en&b=35&m=47
+# but NewsId (and similar) is not a session id (NUTCH-706, NUTCH-1328)
http://www.foo.com/fa/newsdetail.aspx?NewsID=1567539
http://www.foo.com/fa/newsdetail.aspx?NewsID=1567539
+http://www.foo.com/home.cfm?language=en&country=uk&addressid=250646&pagingpos=0
http://www.foo.com/home.cfm?language=en&country=uk&addressid=250646&pagingpos=0
# test removal default pages
http://www.foo.com/home/index.html http://www.foo.com/home/
Modified:
nutch/trunk/src/plugin/urlnormalizer-regex/sample/regex-normalize-default.xml
URL:
http://svn.apache.org/viewvc/nutch/trunk/src/plugin/urlnormalizer-regex/sample/regex-normalize-default.xml?rev=1396817&r1=1396816&r2=1396817&view=diff
==============================================================================
---
nutch/trunk/src/plugin/urlnormalizer-regex/sample/regex-normalize-default.xml
(original)
+++
nutch/trunk/src/plugin/urlnormalizer-regex/sample/regex-normalize-default.xml
Wed Oct 10 21:54:37 2012
@@ -13,7 +13,7 @@
<!-- removes session ids from urls (such as jsessionid and PHPSESSID) -->
<regex>
-
<pattern>([;_]?\b((?i)l|j|bv_)?((?i)sid|phpsessid|sessionid)=.*?)(\?|&|#|$)</pattern>
+
<pattern>(?i)(;?\b_?(l|j|bv_)?(sid|phpsessid|sessionid)=.*?)(\?|&|#|$)</pattern>
<substitution>$4</substitution>
</regex>
