You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by cp...@apache.org on 2017/03/30 17:25:18 UTC
[49/73] [abbrv] lucene-solr:jira/solr-6203: SOLR-10344: Update Solr
default/example and test configs to use WordDelimiterGraphFilterFactory
SOLR-10344: Update Solr default/example and test configs to use WordDelimiterGraphFilterFactory
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/b46b8278
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/b46b8278
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/b46b8278
Branch: refs/heads/jira/solr-6203
Commit: b46b8278c60102eeaeb45dddf239356746da7de8
Parents: cb20eae
Author: Steve Rowe <sa...@gmail.com>
Authored: Mon Mar 27 23:53:55 2017 -0400
Committer: Steve Rowe <sa...@gmail.com>
Committed: Mon Mar 27 23:53:55 2017 -0400
----------------------------------------------------------------------
solr/CHANGES.txt | 2 +
.../clustering/solr/collection1/conf/schema.xml | 23 +++++--
.../solr/collection1/conf/synonyms.txt | 2 +-
.../conf/dataimport-schema-no-unique-key.xml | 7 +-
.../solr/collection1/conf/dataimport-schema.xml | 17 +++--
.../conf/dataimport-solr_id-schema.xml | 23 +++++--
.../extraction/solr/collection1/conf/schema.xml | 40 ++++++++----
.../solr/collection1/conf/synonyms.txt | 2 +-
.../uima/solr/collection1/conf/schema.xml | 37 +++++++----
.../uima/solr/collection1/conf/synonyms.txt | 2 +-
.../test-files/uima/uima-tokenizers-schema.xml | 34 +++++++---
.../conf/schema-HighlighterMaxOffsetTest.xml | 5 +-
.../collection1/conf/schema-copyfield-test.xml | 29 ++++++---
.../collection1/conf/schema-docValuesJoin.xml | 5 +-
.../solr/collection1/conf/schema-folding.xml | 2 +-
.../solr/collection1/conf/schema-hash.xml | 59 ++++++++++++-----
.../collection1/conf/schema-psuedo-fields.xml | 5 +-
.../collection1/conf/schema-required-fields.xml | 18 ++++--
.../solr/collection1/conf/schema-rest.xml | 63 ++++++++++++------
.../conf/schema-single-dynamic-copy-field.xml | 63 ++++++++++++------
.../solr/collection1/conf/schema-sql.xml | 59 ++++++++++++-----
.../solr/collection1/conf/schema-trie.xml | 23 +++++--
.../test-files/solr/collection1/conf/schema.xml | 58 ++++++++++++-----
.../solr/collection1/conf/schema11.xml | 27 ++++++--
.../solr/collection1/conf/schema12.xml | 63 ++++++++++++------
.../solr/collection1/conf/schema15.xml | 63 ++++++++++++------
.../solr/collection1/conf/schema_latest.xml | 27 ++++++--
.../solr/collection1/conf/schemasurround.xml | 68 +++++++++++++-------
.../solr/collection1/conf/synonyms.txt | 2 +-
.../solr/collection1/conf/wdftypes.txt | 2 +-
.../configsets/cloud-dynamic/conf/schema.xml | 35 +++++++---
.../solr/configsets/doc-expiry/conf/schema.xml | 35 +++++++---
.../org/apache/solr/ConvertedLegacyTest.java | 2 +-
.../FieldAnalysisRequestHandlerTest.java | 14 ++--
.../solr/rest/schema/TestBulkSchemaAPI.java | 29 ++++++++-
.../example-DIH/solr/db/conf/managed-schema | 26 ++++++--
.../example-DIH/solr/db/conf/synonyms.txt | 2 +-
.../example-DIH/solr/mail/conf/managed-schema | 26 ++++++--
.../example-DIH/solr/mail/conf/synonyms.txt | 2 +-
.../example-DIH/solr/rss/conf/managed-schema | 31 ++++++---
.../example-DIH/solr/rss/conf/synonyms.txt | 2 +-
.../example-DIH/solr/solr/conf/managed-schema | 26 ++++++--
.../example-DIH/solr/solr/conf/synonyms.txt | 2 +-
.../example-DIH/solr/tika/conf/managed-schema | 23 +++++--
solr/example/files/conf/managed-schema | 20 ++++--
solr/example/files/conf/synonyms.txt | 2 +-
.../basic_configs/conf/managed-schema | 26 ++++++--
.../configsets/basic_configs/conf/synonyms.txt | 2 +-
.../conf/managed-schema | 26 ++++++--
.../conf/synonyms.txt | 2 +-
.../conf/managed-schema | 26 ++++++--
.../conf/synonyms.txt | 2 +-
.../solrj/solr/collection1/conf/schema-sql.xml | 59 ++++++++++++-----
.../solrj/solr/collection1/conf/schema.xml | 59 ++++++++++++-----
.../solr/configsets/streaming/conf/schema.xml | 56 +++++++++++-----
.../solr/client/solrj/request/SchemaTest.java | 2 +-
56 files changed, 984 insertions(+), 383 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b46b8278/solr/CHANGES.txt
----------------------------------------------------------------------
diff --git a/solr/CHANGES.txt b/solr/CHANGES.txt
index b380e6b..3403c90 100644
--- a/solr/CHANGES.txt
+++ b/solr/CHANGES.txt
@@ -151,6 +151,8 @@ Other Changes
* SOLR-10352: bin/solr script now prints warning when available system entropy is lower than 300 (Esther Quansah via
Ishan Chattopadhyaya)
+
+* SOLR-10344: Update Solr default/example and test configs to use WordDelimiterGraphFilterFactory. (Steve Rowe)
================== 6.5.0 ==================
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b46b8278/solr/contrib/clustering/src/test-files/clustering/solr/collection1/conf/schema.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/clustering/src/test-files/clustering/solr/collection1/conf/schema.xml b/solr/contrib/clustering/src/test-files/clustering/solr/collection1/conf/schema.xml
index 0c06a48..02626a0 100644
--- a/solr/contrib/clustering/src/test-files/clustering/solr/collection1/conf/schema.xml
+++ b/solr/contrib/clustering/src/test-files/clustering/solr/collection1/conf/schema.xml
@@ -155,7 +155,7 @@
</analyzer>
</fieldType>
- <!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
+ <!-- A text field that uses WordDelimiterGraphFilter to enable splitting and matching of
words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
Synonyms and stopwords are customized by external files, and stemming is enabled.
@@ -174,18 +174,19 @@
ignoreCase="true"
words="stopwords.txt"
/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.MockTokenizerFactory"/>
<!--<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>-->
<!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
@@ -198,11 +199,23 @@
<!-- Less flexible matching, but less false matches. Probably not ideal for product names,
but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
<fieldType name="textTight" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
+ <analyzer type="index">
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <!--<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+ catenateNumbers="1" catenateAll="0"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <filter class="solr.EnglishMinimalStemFilterFactory"/>
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory" />
+ </analyzer>
+ <analyzer type="query">
<tokenizer class="solr.MockTokenizerFactory"/>
<!--<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
- <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.KeywordMarkerFilterFactory" protected="protwords.txt"/>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b46b8278/solr/contrib/clustering/src/test-files/clustering/solr/collection1/conf/synonyms.txt
----------------------------------------------------------------------
diff --git a/solr/contrib/clustering/src/test-files/clustering/solr/collection1/conf/synonyms.txt b/solr/contrib/clustering/src/test-files/clustering/solr/collection1/conf/synonyms.txt
index b0e31cb..26d237a 100644
--- a/solr/contrib/clustering/src/test-files/clustering/solr/collection1/conf/synonyms.txt
+++ b/solr/contrib/clustering/src/test-files/clustering/solr/collection1/conf/synonyms.txt
@@ -23,7 +23,7 @@ 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
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b46b8278/solr/contrib/dataimporthandler-extras/src/test-files/dihextras/solr/collection1/conf/dataimport-schema-no-unique-key.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/dataimporthandler-extras/src/test-files/dihextras/solr/collection1/conf/dataimport-schema-no-unique-key.xml b/solr/contrib/dataimporthandler-extras/src/test-files/dihextras/solr/collection1/conf/dataimport-schema-no-unique-key.xml
index 068322e..84d0dbe 100644
--- a/solr/contrib/dataimporthandler-extras/src/test-files/dihextras/solr/collection1/conf/dataimport-schema-no-unique-key.xml
+++ b/solr/contrib/dataimporthandler-extras/src/test-files/dihextras/solr/collection1/conf/dataimport-schema-no-unique-key.xml
@@ -158,7 +158,7 @@
</analyzer>
</fieldType>
- <!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
+ <!-- A text field that uses WordDelimiterGraphFilter to enable splitting and matching of
words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
Synonyms and stopwords are customized by external files, and stemming is enabled.
@@ -172,18 +172,19 @@
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-->
<!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>-->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.MockTokenizerFactory"/>
<!--<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>-->
<!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b46b8278/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-schema.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-schema.xml b/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-schema.xml
index 8d62c84..86bd231 100644
--- a/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-schema.xml
+++ b/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-schema.xml
@@ -10,23 +10,32 @@
<fieldType name="text" class="solr.TextField" 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" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ <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" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="textTight" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
+ <analyzer type="index">
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+ catenateNumbers="1" catenateAll="0"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ <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"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b46b8278/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-solr_id-schema.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-solr_id-schema.xml b/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-solr_id-schema.xml
index 9a95797..da4bd39 100644
--- a/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-solr_id-schema.xml
+++ b/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-solr_id-schema.xml
@@ -156,7 +156,7 @@
</analyzer>
</fieldType>
- <!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
+ <!-- A text field that uses WordDelimiterGraphFilter to enable splitting and matching of
words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
Synonyms and stopwords are customized by external files, and stemming is enabled.
@@ -170,18 +170,19 @@
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-->
<!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>-->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.MockTokenizerFactory"/>
<!--<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>-->
<!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
@@ -194,11 +195,23 @@
<!-- Less flexible matching, but less false matches. Probably not ideal for product names,
but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
<fieldType name="textTight" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
+ <analyzer type="index">
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <!--<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>-->
+ <!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+ catenateNumbers="1" catenateAll="0"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <filter class="solr.EnglishMinimalStemFilterFactory"/>-->
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
<tokenizer class="solr.MockTokenizerFactory"/>
<!--<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>-->
<!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
- <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.KeywordMarkerFilterFactory" protected="protwords.txt"/>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b46b8278/solr/contrib/extraction/src/test-files/extraction/solr/collection1/conf/schema.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/extraction/src/test-files/extraction/solr/collection1/conf/schema.xml b/solr/contrib/extraction/src/test-files/extraction/solr/collection1/conf/schema.xml
index bd9adbe..b743ed8 100644
--- a/solr/contrib/extraction/src/test-files/extraction/solr/collection1/conf/schema.xml
+++ b/solr/contrib/extraction/src/test-files/extraction/solr/collection1/conf/schema.xml
@@ -55,26 +55,41 @@
<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.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.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"/>
</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"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
@@ -233,15 +248,16 @@
<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"/>
@@ -253,13 +269,14 @@
<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>
@@ -269,13 +286,14 @@
<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/b46b8278/solr/contrib/ltr/src/test-files/solr/collection1/conf/synonyms.txt
----------------------------------------------------------------------
diff --git a/solr/contrib/ltr/src/test-files/solr/collection1/conf/synonyms.txt b/solr/contrib/ltr/src/test-files/solr/collection1/conf/synonyms.txt
index 0ef0e8d..461ed4d 100644
--- a/solr/contrib/ltr/src/test-files/solr/collection1/conf/synonyms.txt
+++ b/solr/contrib/ltr/src/test-files/solr/collection1/conf/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
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b46b8278/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/schema.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/schema.xml b/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/schema.xml
index 5e0273e..89d44e6 100644
--- a/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/schema.xml
+++ b/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/schema.xml
@@ -191,7 +191,7 @@
</fieldType>
<!--
- A text field that uses WordDelimiterFilter to enable splitting and
+ A text field that uses WordDelimiterGraphFilter to enable splitting and
matching of words on case-change, alpha numeric boundaries, and
non-alphanumeric chars, so that a query of "wifi" or "wi fi" could
match a document containing "Wi-Fi". Synonyms and stopwords are
@@ -212,11 +212,11 @@
-->
<filter class="solr.StopFilterFactory" ignoreCase="true"
words="stopwords.txt" />
- <filter class="solr.WordDelimiterFilterFactory"
+ <filter class="solr.WordDelimiterGraphFilterFactory"
generateWordParts="1" generateNumberParts="1" catenateWords="1"
catenateNumbers="1" catenateAll="0" splitOnCaseChange="1" />
<filter class="solr.LowerCaseFilterFactory" />
-
+ <filter class="solr.FlattenGraphFilterFactory" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.MockTokenizerFactory" />
@@ -224,7 +224,7 @@
ignoreCase="true" expand="true" />
<filter class="solr.StopFilterFactory" ignoreCase="true"
words="stopwords.txt" />
- <filter class="solr.WordDelimiterFilterFactory"
+ <filter class="solr.WordDelimiterGraphFilterFactory"
generateWordParts="1" generateNumberParts="1" catenateWords="0"
catenateNumbers="0" catenateAll="0" splitOnCaseChange="1" />
<filter class="solr.LowerCaseFilterFactory" />
@@ -240,23 +240,36 @@
-->
<fieldType name="textTight" class="solr.TextField"
positionIncrementGap="100">
- <analyzer>
+ <analyzer type="index">
<tokenizer class="solr.MockTokenizerFactory" />
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt"
ignoreCase="true" expand="false" />
<filter class="solr.StopFilterFactory" ignoreCase="true"
words="stopwords.txt" />
- <filter class="solr.WordDelimiterFilterFactory"
+ <filter class="solr.WordDelimiterGraphFilterFactory"
generateWordParts="0" generateNumberParts="0" catenateWords="1"
catenateNumbers="1" catenateAll="0" />
<filter class="solr.LowerCaseFilterFactory" />
<!--
this filter can remove any duplicate tokens that appear at the
- same position - sometimes possible with WordDelimiterFilter in
+ same position - sometimes possible with WordDelimiterGraphFilter in
conjuncton with stemming.
-->
<filter class="solr.RemoveDuplicatesTokenFilterFactory" />
+ <filter class="solr.FlattenGraphFilterFactory" />
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.MockTokenizerFactory" />
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt"
+ ignoreCase="true" expand="false" />
+ <filter class="solr.StopFilterFactory" ignoreCase="true"
+ words="stopwords.txt" />
+ <filter class="solr.WordDelimiterGraphFilterFactory"
+ generateWordParts="0" generateNumberParts="0" catenateWords="1"
+ catenateNumbers="1" catenateAll="0" />
+ <filter class="solr.LowerCaseFilterFactory" />
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory" />
</analyzer>
</fieldType>
@@ -271,10 +284,11 @@
<tokenizer class="solr.MockTokenizerFactory" />
<filter class="solr.StopFilterFactory" ignoreCase="true"
words="stopwords.txt" />
- <filter class="solr.WordDelimiterFilterFactory"
+ <filter class="solr.WordDelimiterGraphFilterFactory"
generateWordParts="1" generateNumberParts="1" catenateWords="1"
catenateNumbers="1" catenateAll="0" splitOnCaseChange="0" />
<filter class="solr.LowerCaseFilterFactory" />
+ <filter class="solr.FlattenGraphFilterFactory" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.MockTokenizerFactory" />
@@ -282,7 +296,7 @@
ignoreCase="true" expand="true" />
<filter class="solr.StopFilterFactory" ignoreCase="true"
words="stopwords.txt" />
- <filter class="solr.WordDelimiterFilterFactory"
+ <filter class="solr.WordDelimiterGraphFilterFactory"
generateWordParts="1" generateNumberParts="1" catenateWords="0"
catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" />
<filter class="solr.LowerCaseFilterFactory" />
@@ -301,13 +315,14 @@
<tokenizer class="solr.MockTokenizerFactory" />
<filter class="solr.StopFilterFactory" ignoreCase="true"
words="stopwords.txt" />
- <filter class="solr.WordDelimiterFilterFactory"
+ <filter class="solr.WordDelimiterGraphFilterFactory"
generateWordParts="1" generateNumberParts="1" catenateWords="1"
catenateNumbers="1" catenateAll="0" splitOnCaseChange="0" />
<filter class="solr.LowerCaseFilterFactory" />
<filter class="solr.ReversedWildcardFilterFactory"
withOriginal="true" maxPosAsterisk="3" maxPosQuestion="2"
maxFractionAsterisk="0.33" />
+ <filter class="solr.FlattenGraphFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.MockTokenizerFactory" />
@@ -315,7 +330,7 @@
ignoreCase="true" expand="true" />
<filter class="solr.StopFilterFactory" ignoreCase="true"
words="stopwords.txt" />
- <filter class="solr.WordDelimiterFilterFactory"
+ <filter class="solr.WordDelimiterGraphFilterFactory"
generateWordParts="1" generateNumberParts="1" catenateWords="0"
catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" />
<filter class="solr.LowerCaseFilterFactory" />
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b46b8278/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/synonyms.txt
----------------------------------------------------------------------
diff --git a/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/synonyms.txt b/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/synonyms.txt
index b0e31cb..26d237a 100644
--- a/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/synonyms.txt
+++ b/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/synonyms.txt
@@ -23,7 +23,7 @@ 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
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b46b8278/solr/contrib/uima/src/test-files/uima/uima-tokenizers-schema.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/uima/src/test-files/uima/uima-tokenizers-schema.xml b/solr/contrib/uima/src/test-files/uima/uima-tokenizers-schema.xml
index 0007be7..229d69b 100644
--- a/solr/contrib/uima/src/test-files/uima/uima-tokenizers-schema.xml
+++ b/solr/contrib/uima/src/test-files/uima/uima-tokenizers-schema.xml
@@ -191,7 +191,7 @@
</fieldType>
<!--
- A text field that uses WordDelimiterFilter to enable splitting and
+ A text field that uses WordDelimiterGraphFilter to enable splitting and
matching of words on case-change, alpha numeric boundaries, and
non-alphanumeric chars, so that a query of "wifi" or "wi fi" could
match a document containing "Wi-Fi". Synonyms and stopwords are
@@ -210,16 +210,18 @@
<!--
Case insensitive stop word removal. add
-->
- <filter class="solr.WordDelimiterFilterFactory"
+ <filter class="solr.WordDelimiterGraphFilterFactory"
generateWordParts="1" generateNumberParts="1" catenateWords="1"
catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
+
</analyzer>
<analyzer type="query">
<tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory"
+ <filter class="solr.WordDelimiterGraphFilterFactory"
generateWordParts="1" generateNumberParts="1" catenateWords="0"
catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
@@ -235,19 +237,29 @@
-->
<fieldType name="textTight" class="solr.TextField"
positionIncrementGap="100">
- <analyzer>
+ <analyzer type="index">
<tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory"
+ <filter class="solr.WordDelimiterGraphFilterFactory"
generateWordParts="0" generateNumberParts="0" catenateWords="1"
catenateNumbers="1" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<!--
this filter can remove any duplicate tokens that appear at the
- same position - sometimes possible with WordDelimiterFilter in
+ same position - sometimes possible with WordDelimiterGraphFilter in
conjuncton with stemming.
-->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+
+ <filter class="solr.FlattenGraphFilterFactory" />
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.WordDelimiterGraphFilterFactory"
+ generateWordParts="0" generateNumberParts="0" catenateWords="1"
+ catenateNumbers="1" catenateAll="0"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
@@ -277,14 +289,15 @@
positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory"
+ <filter class="solr.WordDelimiterGraphFilterFactory"
generateWordParts="1" generateNumberParts="1" catenateWords="1"
catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory"
+ <filter class="solr.WordDelimiterGraphFilterFactory"
generateWordParts="1" generateNumberParts="1" catenateWords="0"
catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
@@ -301,17 +314,18 @@
positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory"
+ <filter class="solr.WordDelimiterGraphFilterFactory"
generateWordParts="1" generateNumberParts="1" catenateWords="1"
catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.ReversedWildcardFilterFactory"
withOriginal="true" maxPosAsterisk="3" maxPosQuestion="2"
maxFractionAsterisk="0.33"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory"
+ <filter class="solr.WordDelimiterGraphFilterFactory"
generateWordParts="1" generateNumberParts="1" catenateWords="0"
catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b46b8278/solr/core/src/test-files/solr/collection1/conf/schema-HighlighterMaxOffsetTest.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/collection1/conf/schema-HighlighterMaxOffsetTest.xml b/solr/core/src/test-files/solr/collection1/conf/schema-HighlighterMaxOffsetTest.xml
index 808453c..122d4ce 100644
--- a/solr/core/src/test-files/solr/collection1/conf/schema-HighlighterMaxOffsetTest.xml
+++ b/solr/core/src/test-files/solr/collection1/conf/schema-HighlighterMaxOffsetTest.xml
@@ -67,16 +67,17 @@ Test for HighlighterMaxOffsetTest which requires the use of ReversedWildcardFilt
<fieldType name="text_stx" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b46b8278/solr/core/src/test-files/solr/collection1/conf/schema-copyfield-test.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/collection1/conf/schema-copyfield-test.xml b/solr/core/src/test-files/solr/collection1/conf/schema-copyfield-test.xml
index 47ddeb2..a9df7f8 100644
--- a/solr/core/src/test-files/solr/collection1/conf/schema-copyfield-test.xml
+++ b/solr/core/src/test-files/solr/collection1/conf/schema-copyfield-test.xml
@@ -60,17 +60,25 @@
<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.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+ catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory" />
+ </analyzer>
+ <analyzer type="query">
<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"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
@@ -229,15 +237,16 @@
<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"/>
@@ -249,13 +258,14 @@
<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>
@@ -265,13 +275,14 @@
<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/b46b8278/solr/core/src/test-files/solr/collection1/conf/schema-docValuesJoin.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/collection1/conf/schema-docValuesJoin.xml b/solr/core/src/test-files/solr/collection1/conf/schema-docValuesJoin.xml
index 1d559bb..baed872 100644
--- a/solr/core/src/test-files/solr/collection1/conf/schema-docValuesJoin.xml
+++ b/solr/core/src/test-files/solr/collection1/conf/schema-docValuesJoin.xml
@@ -42,11 +42,12 @@
ignoreCase="true"
words="stopwords.txt"
/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.MockTokenizerFactory"/>
@@ -55,7 +56,7 @@
ignoreCase="true"
words="stopwords.txt"
/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b46b8278/solr/core/src/test-files/solr/collection1/conf/schema-folding.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/collection1/conf/schema-folding.xml b/solr/core/src/test-files/solr/collection1/conf/schema-folding.xml
index cc9cae3..2b0bf32 100644
--- a/solr/core/src/test-files/solr/collection1/conf/schema-folding.xml
+++ b/solr/core/src/test-files/solr/collection1/conf/schema-folding.xml
@@ -47,7 +47,7 @@
</analyzer>
<analyzer type="multiterm"> <!-- Intentionally different to test that these are kept distinct -->
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.ASCIIFoldingFilterFactory"/>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b46b8278/solr/core/src/test-files/solr/collection1/conf/schema-hash.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/collection1/conf/schema-hash.xml b/solr/core/src/test-files/solr/collection1/conf/schema-hash.xml
index b132473..6a7987c 100644
--- a/solr/core/src/test-files/solr/collection1/conf/schema-hash.xml
+++ b/solr/core/src/test-files/solr/collection1/conf/schema-hash.xml
@@ -72,26 +72,41 @@
<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>
@@ -191,9 +206,16 @@
</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>
@@ -265,15 +287,16 @@
<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"/>
@@ -285,15 +308,16 @@
<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"/>
@@ -304,8 +328,9 @@
<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"/>
@@ -318,13 +343,14 @@
<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>
@@ -334,13 +360,14 @@
<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/b46b8278/solr/core/src/test-files/solr/collection1/conf/schema-psuedo-fields.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/collection1/conf/schema-psuedo-fields.xml b/solr/core/src/test-files/solr/collection1/conf/schema-psuedo-fields.xml
index 20f2d2d..8491ce8 100644
--- a/solr/core/src/test-files/solr/collection1/conf/schema-psuedo-fields.xml
+++ b/solr/core/src/test-files/solr/collection1/conf/schema-psuedo-fields.xml
@@ -50,11 +50,12 @@
ignoreCase="true"
words="stopwords.txt"
/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.MockTokenizerFactory"/>
@@ -63,7 +64,7 @@
ignoreCase="true"
words="stopwords.txt"
/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b46b8278/solr/core/src/test-files/solr/collection1/conf/schema-required-fields.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/collection1/conf/schema-required-fields.xml b/solr/core/src/test-files/solr/collection1/conf/schema-required-fields.xml
index d3a7818..c92b901 100644
--- a/solr/core/src/test-files/solr/collection1/conf/schema-required-fields.xml
+++ b/solr/core/src/test-files/solr/collection1/conf/schema-required-fields.xml
@@ -60,9 +60,10 @@
<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>
@@ -219,15 +220,16 @@
<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"/>
@@ -239,13 +241,14 @@
<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>
@@ -255,13 +258,14 @@
<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/b46b8278/solr/core/src/test-files/solr/collection1/conf/schema-rest.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/collection1/conf/schema-rest.xml b/solr/core/src/test-files/solr/collection1/conf/schema-rest.xml
index 8bd603b..7d9bf02 100644
--- a/solr/core/src/test-files/solr/collection1/conf/schema-rest.xml
+++ b/solr/core/src/test-files/solr/collection1/conf/schema-rest.xml
@@ -45,26 +45,41 @@
<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.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.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"/>
</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"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
@@ -90,11 +105,12 @@
ignoreCase="true"
words="stopwords.txt"
/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.MockTokenizerFactory"/>
@@ -103,7 +119,7 @@
ignoreCase="true"
words="stopwords.txt"
/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
@@ -153,11 +169,12 @@
ignoreCase="true"
words="stopwords.txt"
/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.MockTokenizerFactory"/>
@@ -166,7 +183,7 @@
ignoreCase="true"
words="stopwords.txt"
/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
@@ -300,15 +317,16 @@
<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"/>
@@ -320,16 +338,17 @@
<analyzer type="index">
<tokenizer class="solr.MockTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" protected="protwords.txt" splitOnNumerics="0"
+ <filter class="solr.WordDelimiterGraphFilterFactory" protected="protwords.txt" 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" protected="protwords.txt" splitOnNumerics="0"
+ <filter class="solr.WordDelimiterGraphFilterFactory" protected="protwords.txt" splitOnNumerics="0"
splitOnCaseChange="0" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1"
catenateAll="0"/>
<filter class="solr.StopFilterFactory"/>
@@ -341,9 +360,10 @@
<analyzer type="index">
<tokenizer class="solr.MockTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" protected="protwords.txt" splitOnNumerics="0"
+ <filter class="solr.WordDelimiterGraphFilterFactory" protected="protwords.txt" 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"/>
@@ -356,13 +376,14 @@
<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>
@@ -372,13 +393,14 @@
<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>
@@ -401,16 +423,17 @@
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-->
<!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.PorterStemFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.MockTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.PorterStemFilterFactory"/>