diff options
| author | bobzel <zzzman@gmail.com> | 2020-10-02 11:52:07 -0400 |
|---|---|---|
| committer | bobzel <zzzman@gmail.com> | 2020-10-02 11:52:07 -0400 |
| commit | 9f2eadb8696aa5b66e7e3fef9934d2b34ccd7d91 (patch) | |
| tree | 2d9d36667f2b9e207650b06ee25bc77aad1e2463 | |
| parent | 1dee63242684f02543cf7667b53baa00d10ab6c1 (diff) | |
switch to a wordGram tokenier for solr to support searching for possesives and hyphenated words
| -rw-r--r-- | solr-8.3.1/server/solr/dash/conf/schema.xml | 6 |
1 files changed, 5 insertions, 1 deletions
diff --git a/solr-8.3.1/server/solr/dash/conf/schema.xml b/solr-8.3.1/server/solr/dash/conf/schema.xml index e21f97e00..b1c147027 100644 --- a/solr-8.3.1/server/solr/dash/conf/schema.xml +++ b/solr-8.3.1/server/solr/dash/conf/schema.xml @@ -8,18 +8,22 @@ <fieldType name="text" class="solr.TextField" positionIncrementGap="100" multiValued="true"> <analyzer type="index"> <tokenizer class="solr.WhitespaceTokenizerFactory"/> - <!-- <tokenizer class="solr.StandardTokenizerFactory"/> --> <filter class="solr.StopFilterFactory" words="stopwords.txt"/> <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.WordDelimiterGraphFilterFactory" preserveOriginal="1" catenateWords="1"/> + <filter class="solr.FlattenGraphFilterFactory"/> <!-- required on index analyzers after graph filters --> + <!-- <tokenizer class="solr.StandardTokenizerFactory"/> --> <!-- <filter class="solr.PorterStemFilterFactory"/> <filter class="solr.NGramFilterFactory" minGramSize="2" maxGramSize="12"/> --> <!-- <filter catenateAll="0" catenateNumbers="0" catenateWords="0" class="solr.WordDelimiterFilterFactory" generateNumberParts="1" generateWordParts="1" splitOnCaseChange="1" types="characters.txt"/> --> </analyzer> <analyzer type="query"> <tokenizer class="solr.WhitespaceTokenizerFactory"/> + <!-- <tokenizer class="solr.EdgeNGramTokenizerFactory" minGramSize="2" maxGramSize="15"/> --> <!-- <tokenizer class="solr.StandardTokenizerFactory"/> --> <filter class="solr.StopFilterFactory" words="stopwords.txt"/> <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.WordDelimiterGraphFilterFactory" preserveOriginal="1" catenateWords="1"/> <!-- <filter class="solr.PorterStemFilterFactory"/> --> <!-- <filter catenateAll="0" catenateNumbers="0" catenateWords="0" class="solr.WordDelimiterFilterFactory" generateNumberParts="1" generateWordParts="1" splitOnCaseChange="1" types="characters.txt"/> --> </analyzer> |