You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by sa...@apache.org on 2017/03/28 03:54:41 UTC
[5/8] lucene-solr:branch_6x: SOLR-10344: Update Solr default/example
and test configs to use WordDelimiterGraphFilterFactory
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4b45c272/solr/solrj/src/test-files/solrj/solr/collection1/conf/schema.xml
----------------------------------------------------------------------
diff --git a/solr/solrj/src/test-files/solrj/solr/collection1/conf/schema.xml b/solr/solrj/src/test-files/solrj/solr/collection1/conf/schema.xml
index 49f08b8..fb1a1ac 100644
--- a/solr/solrj/src/test-files/solrj/solr/collection1/conf/schema.xml
+++ b/solr/solrj/src/test-files/solrj/solr/collection1/conf/schema.xml
@@ -47,26 +47,41 @@
<fieldType name="failtype1" class="solr.TextField">
<analyzer type="index">
<tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
catenateNumbers="0" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
</analyzer>
</fieldType>
<!-- Demonstrating ignoreCaseChange -->
<fieldType name="wdf_nocase" class="solr.TextField">
- <analyzer>
+ <analyzer type="index">
<tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+ catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="wdf_preserve" class="solr.TextField">
- <analyzer>
+ <analyzer type="index">
<tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
+ catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
@@ -166,9 +181,16 @@
</analyzer>
</fieldType>
<fieldType name="lowerpunctfilt" class="solr.TextField">
- <analyzer>
+ <analyzer type="index">
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+ catenateNumbers="1" catenateAll="1" splitOnCaseChange="1"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
<tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
catenateNumbers="1" catenateAll="1" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
@@ -240,15 +262,16 @@
<fieldType name="subword" class="solr.TextField" multiValued="true" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
catenateNumbers="1" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory"/>
<filter class="solr.PorterStemFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
catenateNumbers="0" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory"/>
@@ -260,15 +283,16 @@
<analyzer type="index">
<tokenizer class="solr.MockTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1"
+ <filter class="solr.WordDelimiterGraphFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1"
generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
<filter class="solr.StopFilterFactory"/>
<filter class="solr.PorterStemFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.MockTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1"
+ <filter class="solr.WordDelimiterGraphFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1"
generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter class="solr.StopFilterFactory"/>
<filter class="solr.PorterStemFilterFactory"/>
@@ -279,8 +303,9 @@
<analyzer type="index">
<tokenizer class="solr.MockTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1"
+ <filter class="solr.WordDelimiterGraphFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1"
generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.MockTokenizerFactory"/>
@@ -293,13 +318,14 @@
<fieldType name="skutype1" class="solr.TextField">
<analyzer type="index">
<tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
catenateNumbers="1" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
catenateNumbers="1" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
@@ -309,13 +335,14 @@
<fieldType name="skutype2" class="solr.TextField">
<analyzer type="index">
<tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
catenateNumbers="1" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
catenateNumbers="1" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4b45c272/solr/solrj/src/test-files/solrj/solr/configsets/streaming/conf/schema.xml
----------------------------------------------------------------------
diff --git a/solr/solrj/src/test-files/solrj/solr/configsets/streaming/conf/schema.xml b/solr/solrj/src/test-files/solrj/solr/configsets/streaming/conf/schema.xml
index b61a2e9..a3b6a4e 100644
--- a/solr/solrj/src/test-files/solrj/solr/configsets/streaming/conf/schema.xml
+++ b/solr/solrj/src/test-files/solrj/solr/configsets/streaming/conf/schema.xml
@@ -73,24 +73,37 @@
<fieldtype name="failtype1" class="solr.TextField">
<analyzer type="index">
<tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
</analyzer>
</fieldtype>
<!-- Demonstrating ignoreCaseChange -->
<fieldtype name="wdf_nocase" class="solr.TextField">
- <analyzer>
+ <analyzer type="index">
<tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldtype>
<fieldtype name="wdf_preserve" class="solr.TextField">
- <analyzer>
+ <analyzer type="index">
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
<tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldtype>
@@ -179,9 +192,15 @@
</analyzer>
</fieldtype>
<fieldtype name="lowerpunctfilt" class="solr.TextField">
- <analyzer>
+ <analyzer type="index">
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="1" splitOnCaseChange="1"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
<tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="1" splitOnCaseChange="1"/>
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="1" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldtype>
@@ -252,14 +271,15 @@
<fieldtype name="subword" class="solr.TextField" multiValued="true" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory"/>
<filter class="solr.PorterStemFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory"/>
<filter class="solr.PorterStemFilterFactory"/>
@@ -270,14 +290,15 @@
<analyzer type="index">
<tokenizer class="solr.MockTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
+ <filter class="solr.WordDelimiterGraphFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
<filter class="solr.StopFilterFactory"/>
<filter class="solr.PorterStemFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.MockTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+ <filter class="solr.WordDelimiterGraphFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter class="solr.StopFilterFactory"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
@@ -287,7 +308,8 @@
<analyzer type="index">
<tokenizer class="solr.MockTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
+ <filter class="solr.WordDelimiterGraphFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.MockTokenizerFactory"/>
@@ -300,12 +322,13 @@
<fieldtype name="skutype1" class="solr.TextField">
<analyzer type="index">
<tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldtype>
@@ -314,12 +337,13 @@
<fieldtype name="skutype2" class="solr.TextField">
<analyzer type="index">
<tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldtype>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4b45c272/solr/solrj/src/test/org/apache/solr/client/solrj/request/SchemaTest.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/test/org/apache/solr/client/solrj/request/SchemaTest.java b/solr/solrj/src/test/org/apache/solr/client/solrj/request/SchemaTest.java
index 3e8d001..983476e 100644
--- a/solr/solrj/src/test/org/apache/solr/client/solrj/request/SchemaTest.java
+++ b/solr/solrj/src/test/org/apache/solr/client/solrj/request/SchemaTest.java
@@ -529,7 +529,7 @@ public class SchemaTest extends RestTestBase {
tokenizerAttributes.put("class", "solr.WhitespaceTokenizerFactory");
analyzerDefinition.setTokenizer(tokenizerAttributes);
Map<String, Object> filterAttributes = new LinkedHashMap<>();
- filterAttributes.put("class", "solr.WordDelimiterFilterFactory");
+ filterAttributes.put("class", "solr.WordDelimiterGraphFilterFactory");
filterAttributes.put("preserveOriginal", "0");
analyzerDefinition.setFilters(Collections.singletonList(filterAttributes));
fieldTypeDefinition.setAnalyzer(analyzerDefinition);