lucene-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From rm...@apache.org
Subject svn commit: r1241960 - in /lucene/dev/trunk: modules/analysis/common/src/resources/org/apache/lucene/analysis/ar/ modules/analysis/common/src/resources/org/apache/lucene/analysis/el/ modules/analysis/common/src/resources/org/apache/lucene/analysis/fa/ ...
Date Wed, 08 Feb 2012 16:27:47 GMT
Author: rmuir
Date: Wed Feb  8 16:27:47 2012
New Revision: 1241960

URL: http://svn.apache.org/viewvc?rev=1241960&view=rev
Log:
SOLR-3056: document expectations in these files

Modified:
    lucene/dev/trunk/modules/analysis/common/src/resources/org/apache/lucene/analysis/ar/stopwords.txt
    lucene/dev/trunk/modules/analysis/common/src/resources/org/apache/lucene/analysis/el/stopwords.txt
    lucene/dev/trunk/modules/analysis/common/src/resources/org/apache/lucene/analysis/fa/stopwords.txt
    lucene/dev/trunk/modules/analysis/common/src/resources/org/apache/lucene/analysis/hi/stopwords.txt
    lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_ar.txt
    lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_el.txt
    lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_fa.txt
    lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_hi.txt

Modified: lucene/dev/trunk/modules/analysis/common/src/resources/org/apache/lucene/analysis/ar/stopwords.txt
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/resources/org/apache/lucene/analysis/ar/stopwords.txt?rev=1241960&r1=1241959&r2=1241960&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/resources/org/apache/lucene/analysis/ar/stopwords.txt
(original)
+++ lucene/dev/trunk/modules/analysis/common/src/resources/org/apache/lucene/analysis/ar/stopwords.txt
Wed Feb  8 16:27:47 2012
@@ -2,6 +2,8 @@
 # See http://members.unine.ch/jacques.savoy/clef/index.html.
 # Also see http://www.opensource.org/licenses/bsd-license.html
 # Cleaned on October 11, 2009 (not normalized, so use before normalization)
+# This means that when modifying this list, you might need to add some 
+# redundant entries, for example containing forms with both أ and ا
 من
 ومن
 منها

Modified: lucene/dev/trunk/modules/analysis/common/src/resources/org/apache/lucene/analysis/el/stopwords.txt
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/resources/org/apache/lucene/analysis/el/stopwords.txt?rev=1241960&r1=1241959&r2=1241960&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/resources/org/apache/lucene/analysis/el/stopwords.txt
(original)
+++ lucene/dev/trunk/modules/analysis/common/src/resources/org/apache/lucene/analysis/el/stopwords.txt
Wed Feb  8 16:27:47 2012
@@ -1,4 +1,6 @@
 # Lucene Greek Stopwords list
+# Note: by default this file is used after GreekLowerCaseFilter,
+# so when modifying this file use 'σ' instead of 'ς' 
 ο
 η
 το

Modified: lucene/dev/trunk/modules/analysis/common/src/resources/org/apache/lucene/analysis/fa/stopwords.txt
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/resources/org/apache/lucene/analysis/fa/stopwords.txt?rev=1241960&r1=1241959&r2=1241960&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/resources/org/apache/lucene/analysis/fa/stopwords.txt
(original)
+++ lucene/dev/trunk/modules/analysis/common/src/resources/org/apache/lucene/analysis/fa/stopwords.txt
Wed Feb  8 16:27:47 2012
@@ -1,6 +1,8 @@
 # This file was created by Jacques Savoy and is distributed under the BSD license.
 # See http://members.unine.ch/jacques.savoy/clef/index.html.
 # Also see http://www.opensource.org/licenses/bsd-license.html
+# Note: by default this file is used after normalization, so when adding entries
+# to this file, use the arabic 'ي' instead of 'ی'
 انان
 نداشته
 سراسر

Modified: lucene/dev/trunk/modules/analysis/common/src/resources/org/apache/lucene/analysis/hi/stopwords.txt
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/resources/org/apache/lucene/analysis/hi/stopwords.txt?rev=1241960&r1=1241959&r2=1241960&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/resources/org/apache/lucene/analysis/hi/stopwords.txt
(original)
+++ lucene/dev/trunk/modules/analysis/common/src/resources/org/apache/lucene/analysis/hi/stopwords.txt
Wed Feb  8 16:27:47 2012
@@ -1,6 +1,10 @@
 # Also see http://www.opensource.org/licenses/bsd-license.html
 # See http://members.unine.ch/jacques.savoy/clef/index.html.
 # This file was created by Jacques Savoy and is distributed under the BSD license.
+# Note: by default this file also contains forms normalized by HindiNormalizer 
+# for spelling variation (see section below), such that it can be used whether or 
+# not you enable that feature. When adding additional entries to this list,
+# please add the normalized form as well. 
 अंदर
 अत
 अपना

Modified: lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_ar.txt
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_ar.txt?rev=1241960&r1=1241959&r2=1241960&view=diff
==============================================================================
--- lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_ar.txt (original)
+++ lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_ar.txt Wed Feb  8 16:27:47 2012
@@ -2,6 +2,8 @@
 # See http://members.unine.ch/jacques.savoy/clef/index.html.
 # Also see http://www.opensource.org/licenses/bsd-license.html
 # Cleaned on October 11, 2009 (not normalized, so use before normalization)
+# This means that when modifying this list, you might need to add some 
+# redundant entries, for example containing forms with both أ and ا
 من
 ومن
 منها

Modified: lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_el.txt
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_el.txt?rev=1241960&r1=1241959&r2=1241960&view=diff
==============================================================================
--- lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_el.txt (original)
+++ lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_el.txt Wed Feb  8 16:27:47 2012
@@ -1,4 +1,6 @@
 # Lucene Greek Stopwords list
+# Note: by default this file is used after GreekLowerCaseFilter,
+# so when modifying this file use 'σ' instead of 'ς' 
 ο
 η
 το

Modified: lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_fa.txt
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_fa.txt?rev=1241960&r1=1241959&r2=1241960&view=diff
==============================================================================
--- lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_fa.txt (original)
+++ lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_fa.txt Wed Feb  8 16:27:47 2012
@@ -1,6 +1,8 @@
 # This file was created by Jacques Savoy and is distributed under the BSD license.
 # See http://members.unine.ch/jacques.savoy/clef/index.html.
 # Also see http://www.opensource.org/licenses/bsd-license.html
+# Note: by default this file is used after normalization, so when adding entries
+# to this file, use the arabic 'ي' instead of 'ی'
 انان
 نداشته
 سراسر

Modified: lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_hi.txt
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_hi.txt?rev=1241960&r1=1241959&r2=1241960&view=diff
==============================================================================
--- lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_hi.txt (original)
+++ lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_hi.txt Wed Feb  8 16:27:47 2012
@@ -1,6 +1,10 @@
 # Also see http://www.opensource.org/licenses/bsd-license.html
 # See http://members.unine.ch/jacques.savoy/clef/index.html.
 # This file was created by Jacques Savoy and is distributed under the BSD license.
+# Note: by default this file also contains forms normalized by HindiNormalizer 
+# for spelling variation (see section below), such that it can be used whether or 
+# not you enable that feature. When adding additional entries to this list,
+# please add the normalized form as well. 
 अंदर
 अत
 अपना



Mime
View raw message