From e7229ee7a4ea2a77d70df57c16920be903699be6 Mon Sep 17 00:00:00 2001
From: Robert Muir <rmuir@apache.org>
Date: Sun, 25 Sep 2011 21:10:50 +0000
Subject: [PATCH] LUCENE-3456: more use of MockTokenizer

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1175579 13f79535-47bb-0310-9956-ffa450edef68
---
 .../test-files/clustering/solr/conf/schema.xml   |  2 +-
 .../dih/solr/conf/dataimport-schema.xml          |  2 +-
 .../dih/solr/conf/dataimport-solr_id-schema.xml  |  2 +-
 .../test-files/extraction/solr/conf/schema.xml   |  6 +++---
 .../src/test-files/uima/solr/conf/schema.xml     |  4 ++--
 .../solr/conf/schema-copyfield-test.xml          |  6 +++---
 .../solr/conf/schema-required-fields.xml         |  6 +++---
 .../src/test-files/solr/conf/schema-trie.xml     |  2 +-
 solr/core/src/test-files/solr/conf/schema.xml    |  6 +++---
 solr/core/src/test-files/solr/conf/schema11.xml  |  2 +-
 solr/core/src/test-files/solr/conf/schema12.xml  |  6 +++---
 .../src/test-files/solr/conf/schemasurround.xml  |  6 +++---
 .../handler/FieldAnalysisRequestHandlerTest.java | 16 ++++++++--------
 .../src/test-files/solrj/solr/conf/schema.xml    |  6 +++---
 14 files changed, 36 insertions(+), 36 deletions(-)

diff --git a/solr/contrib/clustering/src/test-files/clustering/solr/conf/schema.xml b/solr/contrib/clustering/src/test-files/clustering/solr/conf/schema.xml
index 2484b947a28..3906fb1b0c6 100644
--- a/solr/contrib/clustering/src/test-files/clustering/solr/conf/schema.xml
+++ b/solr/contrib/clustering/src/test-files/clustering/solr/conf/schema.xml
@@ -227,7 +227,7 @@
         <!-- KeywordTokenizer does no actual tokenizing, so the entire
              input string is preserved as a single token
           -->
-        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
         <!-- The LowerCase TokenFilter does what you expect, which can be
              when you want your sorting to be case insensitive
           -->
diff --git a/solr/contrib/dataimporthandler/src/test-files/dih/solr/conf/dataimport-schema.xml b/solr/contrib/dataimporthandler/src/test-files/dih/solr/conf/dataimport-schema.xml
index b97678f65c0..65a855f9c4f 100644
--- a/solr/contrib/dataimporthandler/src/test-files/dih/solr/conf/dataimport-schema.xml
+++ b/solr/contrib/dataimporthandler/src/test-files/dih/solr/conf/dataimport-schema.xml
@@ -208,7 +208,7 @@
         <!-- KeywordTokenizer does no actual tokenizing, so the entire
              input string is preserved as a single token
           -->
-        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
         <!-- The LowerCase TokenFilter does what you expect, which can be
              when you want your sorting to be case insensitive
           -->
diff --git a/solr/contrib/dataimporthandler/src/test-files/dih/solr/conf/dataimport-solr_id-schema.xml b/solr/contrib/dataimporthandler/src/test-files/dih/solr/conf/dataimport-solr_id-schema.xml
index 1d479fb338a..33e4bfc7b53 100644
--- a/solr/contrib/dataimporthandler/src/test-files/dih/solr/conf/dataimport-solr_id-schema.xml
+++ b/solr/contrib/dataimporthandler/src/test-files/dih/solr/conf/dataimport-solr_id-schema.xml
@@ -208,7 +208,7 @@
         <!-- KeywordTokenizer does no actual tokenizing, so the entire
              input string is preserved as a single token
           -->
-        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
         <!-- The LowerCase TokenFilter does what you expect, which can be
              when you want your sorting to be case insensitive
           -->
diff --git a/solr/contrib/extraction/src/test-files/extraction/solr/conf/schema.xml b/solr/contrib/extraction/src/test-files/extraction/solr/conf/schema.xml
index 5bb950a419b..82a3d0f8449 100644
--- a/solr/contrib/extraction/src/test-files/extraction/solr/conf/schema.xml
+++ b/solr/contrib/extraction/src/test-files/extraction/solr/conf/schema.xml
@@ -143,7 +143,7 @@
       <analyzer><tokenizer class="solr.LowerCaseTokenizerFactory"/></analyzer>
     </fieldtype>
     <fieldtype name="keywordtok" class="solr.TextField">
-      <analyzer><tokenizer class="solr.KeywordTokenizerFactory"/></analyzer>
+      <analyzer><tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/></analyzer>
     </fieldtype>
     <fieldtype name="standardtok" class="solr.TextField">
       <analyzer><tokenizer class="solr.StandardTokenizerFactory"/></analyzer>
@@ -186,13 +186,13 @@
     </fieldtype>
     <fieldtype name="patternreplacefilt" class="solr.TextField">
       <analyzer type="index">
-        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
         <filter class="solr.PatternReplaceFilterFactory"
                 pattern="([^a-zA-Z])" replacement="_" replace="all"
         />
       </analyzer>
       <analyzer type="query">
-        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
       </analyzer>
     </fieldtype>
     <fieldtype name="porterfilt" class="solr.TextField">
diff --git a/solr/contrib/uima/src/test-files/uima/solr/conf/schema.xml b/solr/contrib/uima/src/test-files/uima/solr/conf/schema.xml
index 651a7364bba..a32265560e9 100644
--- a/solr/contrib/uima/src/test-files/uima/solr/conf/schema.xml
+++ b/solr/contrib/uima/src/test-files/uima/solr/conf/schema.xml
@@ -389,7 +389,7 @@
           KeywordTokenizer does no actual tokenizing, so the entire
           input string is preserved as a single token
         -->
-        <tokenizer class="solr.KeywordTokenizerFactory" />
+        <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
         <!--
           The LowerCase TokenFilter does what you expect, which can be
           when you want your sorting to be case insensitive
@@ -448,7 +448,7 @@
     <fieldType name="lowercase" class="solr.TextField"
       positionIncrementGap="100">
       <analyzer>
-        <tokenizer class="solr.KeywordTokenizerFactory" />
+        <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
         <filter class="solr.LowerCaseFilterFactory" />
       </analyzer>
     </fieldType>
diff --git a/solr/core/src/test-files/solr/conf/schema-copyfield-test.xml b/solr/core/src/test-files/solr/conf/schema-copyfield-test.xml
index 32c43cdd041..d3e09d9da57 100644
--- a/solr/core/src/test-files/solr/conf/schema-copyfield-test.xml
+++ b/solr/core/src/test-files/solr/conf/schema-copyfield-test.xml
@@ -135,7 +135,7 @@
       <analyzer><tokenizer class="solr.LowerCaseTokenizerFactory"/></analyzer>
     </fieldtype>
     <fieldtype name="keywordtok" class="solr.TextField">
-      <analyzer><tokenizer class="solr.KeywordTokenizerFactory"/></analyzer>
+      <analyzer><tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/></analyzer>
     </fieldtype>
     <fieldtype name="standardtok" class="solr.TextField">
       <analyzer><tokenizer class="solr.StandardTokenizerFactory"/></analyzer>
@@ -178,13 +178,13 @@
     </fieldtype>
     <fieldtype name="patternreplacefilt" class="solr.TextField">
       <analyzer type="index">
-        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
         <filter class="solr.PatternReplaceFilterFactory"
                 pattern="([^a-zA-Z])" replacement="_" replace="all"
         />
       </analyzer>
       <analyzer type="query">
-        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
       </analyzer>
     </fieldtype>
     <fieldtype name="porterfilt" class="solr.TextField">
diff --git a/solr/core/src/test-files/solr/conf/schema-required-fields.xml b/solr/core/src/test-files/solr/conf/schema-required-fields.xml
index 73e8877ea06..0945629690a 100644
--- a/solr/core/src/test-files/solr/conf/schema-required-fields.xml
+++ b/solr/core/src/test-files/solr/conf/schema-required-fields.xml
@@ -126,7 +126,7 @@
       <analyzer><tokenizer class="solr.LowerCaseTokenizerFactory"/></analyzer>
     </fieldtype>
     <fieldtype name="keywordtok" class="solr.TextField">
-      <analyzer><tokenizer class="solr.KeywordTokenizerFactory"/></analyzer>
+      <analyzer><tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/></analyzer>
     </fieldtype>
     <fieldtype name="standardtok" class="solr.TextField">
       <analyzer><tokenizer class="solr.StandardTokenizerFactory"/></analyzer>
@@ -169,13 +169,13 @@
     </fieldtype>
     <fieldtype name="patternreplacefilt" class="solr.TextField">
       <analyzer type="index">
-        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
         <filter class="solr.PatternReplaceFilterFactory"
                 pattern="([^a-zA-Z])" replacement="_" replace="all"
         />
       </analyzer>
       <analyzer type="query">
-        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
       </analyzer>
     </fieldtype>
     <fieldtype name="porterfilt" class="solr.TextField">
diff --git a/solr/core/src/test-files/solr/conf/schema-trie.xml b/solr/core/src/test-files/solr/conf/schema-trie.xml
index 35a2e6ac768..5c7b4cce0a4 100644
--- a/solr/core/src/test-files/solr/conf/schema-trie.xml
+++ b/solr/core/src/test-files/solr/conf/schema-trie.xml
@@ -217,7 +217,7 @@
         <!-- KeywordTokenizer does no actual tokenizing, so the entire
              input string is preserved as a single token
           -->
-        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
         <!-- The LowerCase TokenFilter does what you expect, which can be
              when you want your sorting to be case insensitive
           -->
diff --git a/solr/core/src/test-files/solr/conf/schema.xml b/solr/core/src/test-files/solr/conf/schema.xml
index 563fe11e382..30369809232 100644
--- a/solr/core/src/test-files/solr/conf/schema.xml
+++ b/solr/core/src/test-files/solr/conf/schema.xml
@@ -156,7 +156,7 @@
       <analyzer><tokenizer class="solr.LowerCaseTokenizerFactory"/></analyzer>
     </fieldtype>
     <fieldtype name="keywordtok" class="solr.TextField">
-      <analyzer><tokenizer class="solr.KeywordTokenizerFactory"/></analyzer>
+      <analyzer><tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/></analyzer>
     </fieldtype>
     <fieldtype name="standardtok" class="solr.TextField">
       <analyzer><tokenizer class="solr.StandardTokenizerFactory"/></analyzer>
@@ -207,13 +207,13 @@
     </fieldtype>
     <fieldtype name="patternreplacefilt" class="solr.TextField">
       <analyzer type="index">
-        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
         <filter class="solr.PatternReplaceFilterFactory"
                 pattern="([^a-zA-Z])" replacement="_" replace="all"
         />
       </analyzer>
       <analyzer type="query">
-        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
       </analyzer>
     </fieldtype>
     <fieldtype name="patterntok" class="solr.TextField">
diff --git a/solr/core/src/test-files/solr/conf/schema11.xml b/solr/core/src/test-files/solr/conf/schema11.xml
index 0994620451a..02cc2b51dc2 100755
--- a/solr/core/src/test-files/solr/conf/schema11.xml
+++ b/solr/core/src/test-files/solr/conf/schema11.xml
@@ -208,7 +208,7 @@
         <!-- KeywordTokenizer does no actual tokenizing, so the entire
              input string is preserved as a single token
           -->
-        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
         <!-- The LowerCase TokenFilter does what you expect, which can be
              when you want your sorting to be case insensitive
           -->
diff --git a/solr/core/src/test-files/solr/conf/schema12.xml b/solr/core/src/test-files/solr/conf/schema12.xml
index f530ebd3b46..818d52f4ab6 100755
--- a/solr/core/src/test-files/solr/conf/schema12.xml
+++ b/solr/core/src/test-files/solr/conf/schema12.xml
@@ -191,7 +191,7 @@
       <analyzer><tokenizer class="solr.LowerCaseTokenizerFactory"/></analyzer>
     </fieldtype>
     <fieldtype name="keywordtok" class="solr.TextField">
-      <analyzer><tokenizer class="solr.KeywordTokenizerFactory"/></analyzer>
+      <analyzer><tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/></analyzer>
     </fieldtype>
     <fieldtype name="standardtok" class="solr.TextField">
       <analyzer><tokenizer class="solr.StandardTokenizerFactory"/></analyzer>
@@ -234,13 +234,13 @@
     </fieldtype>
     <fieldtype name="patternreplacefilt" class="solr.TextField">
       <analyzer type="index">
-        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
         <filter class="solr.PatternReplaceFilterFactory"
                 pattern="([^a-zA-Z])" replacement="_" replace="all"
         />
       </analyzer>
       <analyzer type="query">
-        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
       </analyzer>
     </fieldtype>
     <fieldtype name="porterfilt" class="solr.TextField">
diff --git a/solr/core/src/test-files/solr/conf/schemasurround.xml b/solr/core/src/test-files/solr/conf/schemasurround.xml
index 13fd7201237..6020cf1073f 100644
--- a/solr/core/src/test-files/solr/conf/schemasurround.xml
+++ b/solr/core/src/test-files/solr/conf/schemasurround.xml
@@ -191,7 +191,7 @@
       <analyzer><tokenizer class="solr.LowerCaseTokenizerFactory"/></analyzer>
     </fieldtype>
     <fieldtype name="keywordtok" class="solr.TextField">
-      <analyzer><tokenizer class="solr.KeywordTokenizerFactory"/></analyzer>
+      <analyzer><tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/></analyzer>
     </fieldtype>
     <fieldtype name="standardtok" class="solr.TextField">
       <analyzer><tokenizer class="solr.StandardTokenizerFactory"/></analyzer>
@@ -234,13 +234,13 @@
     </fieldtype>
     <fieldtype name="patternreplacefilt" class="solr.TextField">
       <analyzer type="index">
-        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
         <filter class="solr.PatternReplaceFilterFactory"
                 pattern="([^a-zA-Z])" replacement="_" replace="all"
         />
       </analyzer>
       <analyzer type="query">
-        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
       </analyzer>
     </fieldtype>
     <fieldtype name="porterfilt" class="solr.TextField">
diff --git a/solr/core/src/test/org/apache/solr/handler/FieldAnalysisRequestHandlerTest.java b/solr/core/src/test/org/apache/solr/handler/FieldAnalysisRequestHandlerTest.java
index ba05631e89e..a62644b37b4 100644
--- a/solr/core/src/test/org/apache/solr/handler/FieldAnalysisRequestHandlerTest.java
+++ b/solr/core/src/test/org/apache/solr/handler/FieldAnalysisRequestHandlerTest.java
@@ -291,18 +291,18 @@ public class FieldAnalysisRequestHandlerTest extends AnalysisRequestHandlerTestB
 
     indexPart = keywordtok.get("index");
     assertNotNull("expecting an index token analysis for field 'keywordtok'", indexPart);
-    assertEquals("expecting only KeywordTokenizer to be applied", 1, indexPart.size());
-    tokenList = indexPart.get(KeywordTokenizer.class.getName());
-    assertNotNull("expecting only KeywordTokenizer to be applied", tokenList);
-    assertEquals("expecting KeywordTokenizer to produce 1 token", 1, tokenList.size());
+    assertEquals("expecting only MockTokenizer to be applied", 1, indexPart.size());
+    tokenList = indexPart.get(MockTokenizer.class.getName());
+    assertNotNull("expecting only MockTokenizer to be applied", tokenList);
+    assertEquals("expecting MockTokenizer to produce 1 token", 1, tokenList.size());
     assertToken(tokenList.get(0), new TokenInfo("the quick red fox jumped over the lazy brown dogs", null, "word", 0, 49, 1, new int[]{1}, null, false));
 
     queryPart = keywordtok.get("query");
     assertNotNull("expecting a query token analysis for field 'keywordtok'", queryPart);
-    assertEquals("expecting only KeywordTokenizer to be applied", 1, queryPart.size());
-    tokenList = queryPart.get(KeywordTokenizer.class.getName());
-    assertNotNull("expecting only KeywordTokenizer to be applied", tokenList);
-    assertEquals("expecting KeywordTokenizer to produce 1 token", 1, tokenList.size());
+    assertEquals("expecting only MockTokenizer to be applied", 1, queryPart.size());
+    tokenList = queryPart.get(MockTokenizer.class.getName());
+    assertNotNull("expecting only MockTokenizer to be applied", tokenList);
+    assertEquals("expecting MockTokenizer to produce 1 token", 1, tokenList.size());
     assertToken(tokenList.get(0), new TokenInfo("fox brown", null, "word", 0, 9, 1, new int[]{1}, null, false));
 
   }
diff --git a/solr/solrj/src/test-files/solrj/solr/conf/schema.xml b/solr/solrj/src/test-files/solrj/solr/conf/schema.xml
index f549869b8e1..cabe040435c 100644
--- a/solr/solrj/src/test-files/solrj/solr/conf/schema.xml
+++ b/solr/solrj/src/test-files/solrj/solr/conf/schema.xml
@@ -156,7 +156,7 @@
       <analyzer><tokenizer class="solr.LowerCaseTokenizerFactory"/></analyzer>
     </fieldtype>
     <fieldtype name="keywordtok" class="solr.TextField">
-      <analyzer><tokenizer class="solr.KeywordTokenizerFactory"/></analyzer>
+      <analyzer><tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/></analyzer>
     </fieldtype>
     <fieldtype name="standardtok" class="solr.TextField">
       <analyzer><tokenizer class="solr.StandardTokenizerFactory"/></analyzer>
@@ -207,13 +207,13 @@
     </fieldtype>
     <fieldtype name="patternreplacefilt" class="solr.TextField">
       <analyzer type="index">
-        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
         <filter class="solr.PatternReplaceFilterFactory"
                 pattern="([^a-zA-Z])" replacement="_" replace="all"
         />
       </analyzer>
       <analyzer type="query">
-        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
       </analyzer>
     </fieldtype>
     <fieldtype name="patterntok" class="solr.TextField">