You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@ofbiz.apache.org by sh...@apache.org on 2015/08/30 15:27:14 UTC
svn commit: r1700119 [4/26] - in /ofbiz/trunk: ./ runtime/indexes/
specialpurpose/ specialpurpose/solr/ specialpurpose/solr/conf/
specialpurpose/solr/config/ specialpurpose/solr/entitydef/
specialpurpose/solr/lib/ specialpurpose/solr/lib/compile/ speci...
Added: ofbiz/trunk/specialpurpose/solr/solrdefault/conf/lang/stopwords_tr.txt
URL: http://svn.apache.org/viewvc/ofbiz/trunk/specialpurpose/solr/solrdefault/conf/lang/stopwords_tr.txt?rev=1700119&view=auto
==============================================================================
--- ofbiz/trunk/specialpurpose/solr/solrdefault/conf/lang/stopwords_tr.txt (added)
+++ ofbiz/trunk/specialpurpose/solr/solrdefault/conf/lang/stopwords_tr.txt Sun Aug 30 13:27:07 2015
@@ -0,0 +1,212 @@
+# Turkish stopwords from LUCENE-559
+# merged with the list from "Information Retrieval on Turkish Texts"
+# (http://www.users.muohio.edu/canf/papers/JASIST2008offPrint.pdf)
+acaba
+altmıÅ
+altı
+ama
+ancak
+arada
+aslında
+ayrıca
+bana
+bazı
+belki
+ben
+benden
+beni
+benim
+beri
+beÅ
+bile
+bin
+bir
+birçok
+biri
+birkaç
+birkez
+birÅey
+birÅeyi
+biz
+bize
+bizden
+bizi
+bizim
+böyle
+böylece
+bu
+buna
+bunda
+bundan
+bunlar
+bunları
+bunların
+bunu
+bunun
+burada
+çok
+çünkü
+da
+daha
+dahi
+de
+defa
+deÄil
+diÄer
+diye
+doksan
+dokuz
+dolayı
+dolayısıyla
+dört
+edecek
+eden
+ederek
+edilecek
+ediliyor
+edilmesi
+ediyor
+eÄer
+elli
+en
+etmesi
+etti
+ettiÄi
+ettiÄini
+gibi
+göre
+halen
+hangi
+hatta
+hem
+henüz
+hep
+hepsi
+her
+herhangi
+herkesin
+hiç
+hiçbir
+için
+iki
+ile
+ilgili
+ise
+iÅte
+itibaren
+itibariyle
+kadar
+karÅın
+katrilyon
+kendi
+kendilerine
+kendini
+kendisi
+kendisine
+kendisini
+kez
+ki
+kim
+kimden
+kime
+kimi
+kimse
+kırk
+milyar
+milyon
+mu
+mü
+mı
+nasıl
+ne
+neden
+nedenle
+nerde
+nerede
+nereye
+niye
+niçin
+o
+olan
+olarak
+oldu
+olduÄu
+olduÄunu
+olduklarını
+olmadı
+olmadıÄı
+olmak
+olması
+olmayan
+olmaz
+olsa
+olsun
+olup
+olur
+olursa
+oluyor
+on
+ona
+ondan
+onlar
+onlardan
+onları
+onların
+onu
+onun
+otuz
+oysa
+öyle
+pek
+raÄmen
+sadece
+sanki
+sekiz
+seksen
+sen
+senden
+seni
+senin
+siz
+sizden
+sizi
+sizin
+Åey
+Åeyden
+Åeyi
+Åeyler
+Åöyle
+Åu
+Åuna
+Åunda
+Åundan
+Åunları
+Åunu
+tarafından
+trilyon
+tüm
+üç
+üzere
+var
+vardı
+ve
+veya
+ya
+yani
+yapacak
+yapılan
+yapılması
+yapıyor
+yapmak
+yaptı
+yaptıÄı
+yaptıÄını
+yaptıkları
+yedi
+yerine
+yetmiÅ
+yine
+yirmi
+yoksa
+yüz
+zaten
Propchange: ofbiz/trunk/specialpurpose/solr/solrdefault/conf/lang/stopwords_tr.txt
------------------------------------------------------------------------------
svn:eol-style = native
Propchange: ofbiz/trunk/specialpurpose/solr/solrdefault/conf/lang/stopwords_tr.txt
------------------------------------------------------------------------------
svn:keywords = Date Rev Author URL Id
Propchange: ofbiz/trunk/specialpurpose/solr/solrdefault/conf/lang/stopwords_tr.txt
------------------------------------------------------------------------------
svn:mime-type = text/plain
Added: ofbiz/trunk/specialpurpose/solr/solrdefault/conf/lang/userdict_ja.txt
URL: http://svn.apache.org/viewvc/ofbiz/trunk/specialpurpose/solr/solrdefault/conf/lang/userdict_ja.txt?rev=1700119&view=auto
==============================================================================
--- ofbiz/trunk/specialpurpose/solr/solrdefault/conf/lang/userdict_ja.txt (added)
+++ ofbiz/trunk/specialpurpose/solr/solrdefault/conf/lang/userdict_ja.txt Sun Aug 30 13:27:07 2015
@@ -0,0 +1,29 @@
+#
+# This is a sample user dictionary for Kuromoji (JapaneseTokenizer)
+#
+# Add entries to this file in order to override the statistical model in terms
+# of segmentation, readings and part-of-speech tags. Notice that entries do
+# not have weights since they are always used when found. This is by-design
+# in order to maximize ease-of-use.
+#
+# Entries are defined using the following CSV format:
+# <text>,<token 1> ... <token n>,<reading 1> ... <reading n>,<part-of-speech tag>
+#
+# Notice that a single half-width space separates tokens and readings, and
+# that the number tokens and readings must match exactly.
+#
+# Also notice that multiple entries with the same <text> is undefined.
+#
+# Whitespace only lines are ignored. Comments are not allowed on entry lines.
+#
+
+# Custom segmentation for kanji compounds
+æ¥æ¬çµæ¸æ°è,æ¥æ¬ çµæ¸ æ°è,ããã³ ã±ã¤ã¶ã¤ ã·ã³ãã³,ã«ã¹ã¿ã åè©
+é¢è¥¿å½é空港,é¢è¥¿ å½é 空港,ã«ã³ãµã¤ ã³ã¯ãµã¤ ã¯ã¦ã³ã¦,ã«ã¹ã¿ã åè©
+
+# Custom segmentation for compound katakana
+ãã¼ãããã°,ãã¼ã ããã°,ãã¼ã ããã°,ããã«ãåè©
+ã·ã§ã«ãã¼ããã°,ã·ã§ã«ãã¼ ããã°,ã·ã§ã«ãã¼ ããã°,ããã«ãåè©
+
+# Custom reading for former sumo wrestler
+æéé¾,æéé¾,ã¢ãµã·ã§ã¦ãªã¥ã¦,ã«ã¹ã¿ã 人å
Propchange: ofbiz/trunk/specialpurpose/solr/solrdefault/conf/lang/userdict_ja.txt
------------------------------------------------------------------------------
svn:eol-style = native
Propchange: ofbiz/trunk/specialpurpose/solr/solrdefault/conf/lang/userdict_ja.txt
------------------------------------------------------------------------------
svn:keywords = Date Rev Author URL Id
Propchange: ofbiz/trunk/specialpurpose/solr/solrdefault/conf/lang/userdict_ja.txt
------------------------------------------------------------------------------
svn:mime-type = text/plain