Permalink
Browse files

Merged text_icu field type from single core schema.xml

  • Loading branch information...
1 parent 6a2f5d8 commit cd313c5a81f71df514339d4dda8d68444a491034 @paulborgermans paulborgermans committed Mar 29, 2012
@@ -270,6 +270,45 @@
</analyzer>
</fieldType>
+ <fieldType name="text_icu" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+ <analyzer type="index">
+ <tokenizer class="solr.ICUTokenizerFactory"/>
+ <!-- in this example, we will only use synonyms at query time
+ <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+ -->
+ <!-- Case insensitive stop word removal.
+ add enablePositionIncrements=true in both the index and query
+ analyzers to leave a 'gap' for more accurate phrase queries.
+ -->
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="stopwords.txt"
+ enablePositionIncrements="true"
+ />
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
+ <filter class="solr.ICUFoldingFilterFactory"/>
+ <!-- <filter class="solr.ICUCollationKeyFilterFactory" locale="en" strength="primary"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/> -->
+ <!--<filter class="solr.EdgeNGramFilterFactory" minGramSize="3" maxGramSize="15" side="front"/> -->
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.ICUTokenizerFactory"/>
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="stopwords.txt"
+ enablePositionIncrements="true"
+ />
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+ <filter class="solr.ICUFoldingFilterFactory"/>
+ <!--<filter class="solr.ICUCollationKeyFilterFactory" locale="en" strength="primary"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/> -->
+
+ <!--<filter class="solr.EdgeNGramFilterFactory" minGramSize="3" maxGramSize="15" side="front"/> -->
+ </analyzer>
+ </fieldType>
+
+
<!-- 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. -->
@@ -270,6 +270,44 @@
</analyzer>
</fieldType>
+ <fieldType name="text_icu" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+ <analyzer type="index">
+ <tokenizer class="solr.ICUTokenizerFactory"/>
+ <!-- in this example, we will only use synonyms at query time
+ <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+ -->
+ <!-- Case insensitive stop word removal.
+ add enablePositionIncrements=true in both the index and query
+ analyzers to leave a 'gap' for more accurate phrase queries.
+ -->
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="stopwords.txt"
+ enablePositionIncrements="true"
+ />
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
+ <filter class="solr.ICUFoldingFilterFactory"/>
+ <!-- <filter class="solr.ICUCollationKeyFilterFactory" locale="en" strength="primary"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/> -->
+ <!--<filter class="solr.EdgeNGramFilterFactory" minGramSize="3" maxGramSize="15" side="front"/> -->
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.ICUTokenizerFactory"/>
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="stopwords.txt"
+ enablePositionIncrements="true"
+ />
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+ <filter class="solr.ICUFoldingFilterFactory"/>
+ <!--<filter class="solr.ICUCollationKeyFilterFactory" locale="en" strength="primary"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/> -->
+
+ <!--<filter class="solr.EdgeNGramFilterFactory" minGramSize="3" maxGramSize="15" side="front"/> -->
+ </analyzer>
+ </fieldType>
+
<!-- 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. -->
@@ -270,6 +270,45 @@
</analyzer>
</fieldType>
+ <fieldType name="text_icu" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+ <analyzer type="index">
+ <tokenizer class="solr.ICUTokenizerFactory"/>
+ <!-- in this example, we will only use synonyms at query time
+ <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+ -->
+ <!-- Case insensitive stop word removal.
+ add enablePositionIncrements=true in both the index and query
+ analyzers to leave a 'gap' for more accurate phrase queries.
+ -->
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="stopwords.txt"
+ enablePositionIncrements="true"
+ />
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
+ <filter class="solr.ICUFoldingFilterFactory"/>
+ <!-- <filter class="solr.ICUCollationKeyFilterFactory" locale="en" strength="primary"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/> -->
+ <!--<filter class="solr.EdgeNGramFilterFactory" minGramSize="3" maxGramSize="15" side="front"/> -->
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.ICUTokenizerFactory"/>
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="stopwords.txt"
+ enablePositionIncrements="true"
+ />
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+ <filter class="solr.ICUFoldingFilterFactory"/>
+ <!--<filter class="solr.ICUCollationKeyFilterFactory" locale="en" strength="primary"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/> -->
+
+ <!--<filter class="solr.EdgeNGramFilterFactory" minGramSize="3" maxGramSize="15" side="front"/> -->
+ </analyzer>
+ </fieldType>
+
+
<!-- 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. -->
@@ -270,7 +270,7 @@
</analyzer>
</fieldType>
- <fieldType name="text_icu" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+ <fieldType name="text_icu" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
<analyzer type="index">
<tokenizer class="solr.ICUTokenizerFactory"/>
<!-- in this example, we will only use synonyms at query time

0 comments on commit cd313c5

Please sign in to comment.