Author: ssmiweve
Date: 2008-01-22 13:01:43 +0100 (Tue, 22 Jan 2008)
New Revision: 6000
Modified:
trunk/query-api/src/main/javacc/QueryParserImpl.jj
Log:
SEARCH-3787 - Better url-matching in query parser
Modified: trunk/query-api/src/main/javacc/QueryParserImpl.jj
===================================================================
--- trunk/query-api/src/main/javacc/QueryParserImpl.jj 2008-01-22 12:01:04 UTC
(rev 5999)
+++ trunk/query-api/src/main/javacc/QueryParserImpl.jj 2008-01-22 12:01:43 UTC
(rev 6000)
@@ -93,7 +93,10 @@
/* ‐ ‑ ‒ – — ― */
<DEFAULT,EMAIL_DISABLED,PHONE_NUMBER_DISABLED,NUMBER_GROUP_DISABLED,QUOTED_WORD_DISABLED>
-TOKEN : { <URL: "http://"<WORD>(("/")?(<WORD>)?("?"(<WORD>("="<WORD>)?))?)*> }
+// https?://([-\\w\\.]+)+(:\\d+)?(/~?([\\w/_\\.]*(\\?\\S+)?)?)?
+TOKEN : { <URL:
"http"("s")?"://"<WORD>(":"<INTEGER>)?(<URL_WORD>)*(("?"<URL_WORD>)?)*("#"<URL_WORD>)?>
+ | <#URL_WORD: (<WORD>|<ENCODED_CHAR>|"-"|"_"|"~"|"/")+>
+ | <#ENCODED_CHAR:
"%"(<DIGIT>|"A"|"a"|"B"|"b"|"C"|"c"|"D"|"d"|"E"|"e"|"F"|"f"){2}>}
<DEFAULT,URL_DISABLED,PHONE_NUMBER_DISABLED,NUMBER_GROUP_DISABLED,QUOTED_WORD_DISABLED>
TOKEN : { <EMAIL: <WORD>"@"<WORD>"."<WORD>> }
_______________________________________________
Kernel-commits mailing list
[email protected]
http://sesat.no/mailman/listinfo/kernel-commits