Upgraded Solr config files with the ones provided by Solr release

Fixes #292

defaults/solr/elevate.xml

@@ -24,15 +24,19 @@
 
 -->
 <elevate>
+ <!-- Query elevation examples
   <query text="foo bar">
     <doc id="1" />
     <doc id="2" />
     <doc id="3" />
   </query>
 
+for use with techproducts example
+ 
   <query text="ipod">
-   <doc id="MA147LL/A" />  <!-- put the actual ipod at the top -->
-   <doc id="IW-02" exclude="true" /> <!-- exclude this cable -->
+    <doc id="MA147LL/A" />  put the actual ipod at the top 
+    <doc id="IW-02" exclude="true" /> exclude this cable
   </query>
+-->
 
 </elevate>

defaults/solr/lang/contractions_fr.txt

@@ -7,3 +7,9 @@ qu
 n
 s
 j
+d
+c
+jusqu
+quoiqu
+lorsqu
+puisqu

defaults/solr/lang/stopwords_da.txt

@@ -4,6 +4,8 @@
  | Also see http://www.opensource.org/licenses/bsd-license.html
  |  - Encoding was converted to UTF-8.
  |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
 
  | A Danish stop word list. Comments begin with vertical bar. Each stop
  | word is at the start of a line.

defaults/solr/lang/stopwords_de.txt

@@ -4,6 +4,8 @@
  | Also see http://www.opensource.org/licenses/bsd-license.html
  |  - Encoding was converted to UTF-8.
  |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
 
  | A German stop word list. Comments begin with vertical bar. Each stop
  | word is at the start of a line.

defaults/solr/lang/stopwords_es.txt

@@ -4,6 +4,8 @@
  | Also see http://www.opensource.org/licenses/bsd-license.html
  |  - Encoding was converted to UTF-8.
  |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
 
  | A Spanish stop word list. Comments begin with vertical bar. Each stop
  | word is at the start of a line.

defaults/solr/lang/stopwords_fi.txt

@@ -4,6 +4,8 @@
  | Also see http://www.opensource.org/licenses/bsd-license.html
  |  - Encoding was converted to UTF-8.
  |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
  
 | forms of BE
 

defaults/solr/lang/stopwords_fr.txt

@@ -4,6 +4,8 @@
  | Also see http://www.opensource.org/licenses/bsd-license.html
  |  - Encoding was converted to UTF-8.
  |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
 
  | A French stop word list. Comments begin with vertical bar. Each stop
  | word is at the start of a line.
@@ -167,7 +169,8 @@ eussent
 
                | Later additions (from Jean-Christophe Deschamps)
 ceci           |  this
-celà           |  that
+cela           |  that
+celà           |  that
 cet            |  this
 cette          |  this
 ici            |  here

defaults/solr/lang/stopwords_hu.txt

@@ -4,6 +4,8 @@
  | Also see http://www.opensource.org/licenses/bsd-license.html
  |  - Encoding was converted to UTF-8.
  |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
  
 | Hungarian stop word list
 | prepared by Anna Tordai

defaults/solr/lang/stopwords_it.txt

@@ -4,6 +4,8 @@
  | Also see http://www.opensource.org/licenses/bsd-license.html
  |  - Encoding was converted to UTF-8.
  |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
 
  | An Italian stop word list. Comments begin with vertical bar. Each stop
  | word is at the start of a line.

defaults/solr/lang/stopwords_nl.txt

@@ -4,6 +4,8 @@
  | Also see http://www.opensource.org/licenses/bsd-license.html
  |  - Encoding was converted to UTF-8.
  |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
 
  | A Dutch stop word list. Comments begin with vertical bar. Each stop
  | word is at the start of a line.

defaults/solr/lang/stopwords_no.txt

@@ -4,6 +4,8 @@
  | Also see http://www.opensource.org/licenses/bsd-license.html
  |  - Encoding was converted to UTF-8.
  |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
 
  | A Norwegian stop word list. Comments begin with vertical bar. Each stop
  | word is at the start of a line.

defaults/solr/lang/stopwords_pt.txt

@@ -4,6 +4,8 @@
  | Also see http://www.opensource.org/licenses/bsd-license.html
  |  - Encoding was converted to UTF-8.
  |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
 
  | A Portuguese stop word list. Comments begin with vertical bar. Each stop
  | word is at the start of a line.

defaults/solr/lang/stopwords_ru.txt

@@ -4,6 +4,8 @@
  | Also see http://www.opensource.org/licenses/bsd-license.html
  |  - Encoding was converted to UTF-8.
  |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
 
  | a russian stop word list. comments begin with vertical bar. each stop
  | word is at the start of a line.

defaults/solr/lang/stopwords_sv.txt

@@ -4,6 +4,8 @@
  | Also see http://www.opensource.org/licenses/bsd-license.html
  |  - Encoding was converted to UTF-8.
  |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
 
  | A Swedish stop word list. Comments begin with vertical bar. Each stop
  | word is at the start of a line.

defaults/solr/lang/userdict_ja.txt

@@ -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
+日本経済新聞,日本 経済 新聞,ニホン ケイザイ シンブン,カスタム名詞
+関西国際空港,関西 国際 空港,カンサイ コクサイ クウコウ,カスタム名詞
+
+# Custom segmentation for compound katakana
+トートバッグ,トート バッグ,トート バッグ,かずカナ名詞
+ショルダーバッグ,ショルダー バッグ,ショルダー バッグ,かずカナ名詞
+
+# Custom reading for former sumo wrestler
+朝青龍,朝青龍,アサショウリュウ,カスタム人名

defaults/solr/synonyms.txt

@@ -21,7 +21,7 @@ fooaaa,baraaa,bazaaa
 GB,gib,gigabyte,gigabytes
 MB,mib,megabyte,megabytes
 Television, Televisions, TV, TVs
-#notice we use "gib" instead of "GiB" so any WordDelimiterFilter coming
+#notice we use "gib" instead of "GiB" so any WordDelimiterGraphFilter coming
 #after us won't split it into two words.
 
 # Synonym mappings can be used for spelling correction too