anserini-solr-plugin/solr/schema-additions.xml at master · elsevierlabs-os/anserini-solr-plugin · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
<!-- following XML blocks must be copy-pasted inside the schema element of managed-schema.
     Don't care about ordering, managed-schema is regenerated by Solr and everything will
     be rearranged anyway.
     This needs to be done before setting up the fields.
-->

  <similarity class="solr.SchemaSimilarityFactory">
    <str name="defaultSimFromFieldType">text_bm</str>
  </similarity>

  <fieldType name="text_bm" class="solr.TextField" positionIncrementGap="100" multiValued="true">
    <analyzer type="index">
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
      <filter class="solr.LowerCaseFilterFactory"/>
    </analyzer>
    <analyzer type="query">
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
      <filter class="solr.SynonymGraphFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
      <filter class="solr.LowerCaseFilterFactory"/>
    </analyzer>
    <similarity class="solr.BM25SimilarityFactory">
      <str name="b">0.75</str>
      <str name="k1">1.2</str>
    </similarity>
  </fieldType>

  <fieldType name="text_ql" class="solr.TextField" positionIncrementGap="100" multiValued="true">
    <analyzer type="index">
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
      <filter class="solr.LowerCaseFilterFactory"/>
    </analyzer>
    <analyzer type="query">
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
      <filter class="solr.SynonymGraphFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
      <filter class="solr.LowerCaseFilterFactory"/>
    </analyzer>
    <similarity class="solr.LMDirichletSimilarityFactory">
      <str name="mu">2000</str>
    </similarity>
  </fieldType>