diff options
| -rw-r--r-- | conf/solr/schema-fr.xml | 166 | ||||
| -rw-r--r-- | conf/solr/schema.xml | 168 |
2 files changed, 334 insertions, 0 deletions
diff --git a/conf/solr/schema-fr.xml b/conf/solr/schema-fr.xml new file mode 100644 index 0000000..68605c8 --- /dev/null +++ b/conf/solr/schema-fr.xml @@ -0,0 +1,166 @@ +<?xml version="1.0" ?> +<!-- + Licensed to the Apache Software Foundation (ASF) under one or more + contributor license agreements. See the NOTICE file distributed with + this work for additional information regarding copyright ownership. + The ASF licenses this file to You under the Apache License, Version 2.0 + (the "License"); you may not use this file except in compliance with + the License. You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. +--> + +<schema name="default" version="1.4"> + <types> + <fieldtype name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/> + <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/> + <fieldtype name="binary" class="solr.BinaryField"/> + + <!-- Numeric field types that manipulate the value into + a string value that isn't human-readable in its internal form, + but with a lexicographic ordering the same as the numeric ordering, + so that range queries work correctly. --> + <fieldType name="int" class="solr.TrieIntField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/> + <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/> + <fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/> + <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/> + + <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/> + <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/> + <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/> + <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/> + + <fieldType name="date" class="solr.TrieDateField" omitNorms="true" precisionStep="0" positionIncrementGap="0"/> + <!-- A Trie based date field for faster date range queries and date faceting. --> + <fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" precisionStep="6" positionIncrementGap="0"/> + + <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/> + <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/> + <fieldtype name="geohash" class="solr.GeoHashField"/> + + <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100"> + <analyzer type="index"> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" /> + <!-- in this example, we will only use synonyms at query time + <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/> + --> + <filter class="solr.LowerCaseFilterFactory"/> + </analyzer> + <analyzer type="query"> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" /> + <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> + <filter class="solr.LowerCaseFilterFactory"/> + </analyzer> + </fieldType> + + <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100"> + <analyzer type="index"> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.StopFilterFactory" + ignoreCase="true" + words="lang/stopwords_fr.txt" + enablePositionIncrements="true" + /> + <filter class="solr.LowerCaseFilterFactory"/> + + <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" enablePositionIncrements="true"/> + <filter class="solr.FrenchLightStemFilterFactory"/> + </analyzer> + <analyzer type="query"> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.StopFilterFactory" + ignoreCase="true" + words="lang/stopwords_fr.txt" + enablePositionIncrements="true" + /> + <filter class="solr.LowerCaseFilterFactory"/> + + <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" enablePositionIncrements="true"/> + <filter class="solr.FrenchLightStemFilterFactory"/> + </analyzer> + </fieldType> + + <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.WhitespaceTokenizerFactory"/> + </analyzer> + </fieldType> + + <fieldType name="ngram" class="solr.TextField" > + <analyzer type="index"> + <tokenizer class="solr.KeywordTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.NGramFilterFactory" minGramSize="3" maxGramSize="15" /> + </analyzer> + <analyzer type="query"> + <tokenizer class="solr.KeywordTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory"/> + </analyzer> + </fieldType> + + <fieldType name="edge_ngram" class="solr.TextField" positionIncrementGap="1"> + <analyzer type="index"> + <tokenizer class="solr.WhitespaceTokenizerFactory" /> + <filter class="solr.LowerCaseFilterFactory" /> + <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/> + <filter class="solr.EdgeNGramFilterFactory" minGramSize="2" maxGramSize="15" side="front" /> + </analyzer> + <analyzer type="query"> + <tokenizer class="solr.WhitespaceTokenizerFactory" /> + <filter class="solr.LowerCaseFilterFactory" /> + <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/> + </analyzer> + </fieldType> + </types> + + <fields> + <!-- general --> + <field name="id" type="string" indexed="true" stored="true" multiValued="false" required="true"/> + <field name="django_ct" type="string" indexed="true" stored="true" multiValued="false"/> + <field name="django_id" type="string" indexed="true" stored="true" multiValued="false"/> + + <dynamicField name="*_i" type="int" indexed="true" stored="true"/> + <dynamicField name="*_s" type="string" indexed="true" stored="true"/> + <dynamicField name="*_l" type="long" indexed="true" stored="true"/> + <dynamicField name="*_t" type="text_fr" indexed="true" stored="true"/> + <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/> + <dynamicField name="*_f" type="float" indexed="true" stored="true"/> + <dynamicField name="*_d" type="double" indexed="true" stored="true"/> + <dynamicField name="*_dt" type="date" indexed="true" stored="true"/> + <dynamicField name="*_p" type="location" indexed="true" stored="true"/> + <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false"/> + + + <field name="text" type="text_fr" indexed="true" stored="true" multiValued="false" /> + + <field name="location" type="location" indexed="true" stored="true" multiValued="false" /> + + <field name="categories" type="text_fr" indexed="true" stored="true" multiValued="true" /> + + <field name="content_auto" type="edge_ngram" indexed="true" stored="true" multiValued="false" /> + + </fields> + + <!-- field to use to determine and enforce document uniqueness. --> + <uniqueKey>id</uniqueKey> + + <!-- field for the QueryParser to use when an explicit fieldname is absent --> + <defaultSearchField>text</defaultSearchField> + + <!-- SolrQueryParser configuration: defaultOperator="AND|OR" --> + <solrQueryParser defaultOperator="AND"/> +</schema> + + diff --git a/conf/solr/schema.xml b/conf/solr/schema.xml new file mode 100644 index 0000000..ba25e5c --- /dev/null +++ b/conf/solr/schema.xml @@ -0,0 +1,168 @@ +<?xml version="1.0" ?> +<!-- + Licensed to the Apache Software Foundation (ASF) under one or more + contributor license agreements. See the NOTICE file distributed with + this work for additional information regarding copyright ownership. + The ASF licenses this file to You under the Apache License, Version 2.0 + (the "License"); you may not use this file except in compliance with + the License. You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. +--> + +<schema name="default" version="1.4"> + <types> + <fieldtype name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/> + <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/> + <fieldtype name="binary" class="solr.BinaryField"/> + + <!-- Numeric field types that manipulate the value into + a string value that isn't human-readable in its internal form, + but with a lexicographic ordering the same as the numeric ordering, + so that range queries work correctly. --> + <fieldType name="int" class="solr.TrieIntField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/> + <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/> + <fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/> + <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/> + + <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/> + <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/> + <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/> + <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/> + + <fieldType name="date" class="solr.TrieDateField" omitNorms="true" precisionStep="0" positionIncrementGap="0"/> + <!-- A Trie based date field for faster date range queries and date faceting. --> + <fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" precisionStep="6" positionIncrementGap="0"/> + + <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/> + <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/> + <fieldtype name="geohash" class="solr.GeoHashField"/> + + <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100"> + <analyzer type="index"> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" /> + <!-- in this example, we will only use synonyms at query time + <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/> + --> + <filter class="solr.LowerCaseFilterFactory"/> + </analyzer> + <analyzer type="query"> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" /> + <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> + <filter class="solr.LowerCaseFilterFactory"/> + </analyzer> + </fieldType> + + <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100"> + <analyzer type="index"> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.StopFilterFactory" + ignoreCase="true" + words="stopwords_en.txt" + enablePositionIncrements="true" + /> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.EnglishPossessiveFilterFactory"/> + <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> + <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory: + <filter class="solr.EnglishMinimalStemFilterFactory"/> + --> + <filter class="solr.PorterStemFilterFactory"/> + </analyzer> + <analyzer type="query"> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> + <filter class="solr.StopFilterFactory" + ignoreCase="true" + words="stopwords_en.txt" + enablePositionIncrements="true" + /> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.EnglishPossessiveFilterFactory"/> + <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> + <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory: + <filter class="solr.EnglishMinimalStemFilterFactory"/> + --> + <filter class="solr.PorterStemFilterFactory"/> + </analyzer> + </fieldType> + + <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.WhitespaceTokenizerFactory"/> + </analyzer> + </fieldType> + + <fieldType name="ngram" class="solr.TextField" > + <analyzer type="index"> + <tokenizer class="solr.KeywordTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.NGramFilterFactory" minGramSize="3" maxGramSize="15" /> + </analyzer> + <analyzer type="query"> + <tokenizer class="solr.KeywordTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory"/> + </analyzer> + </fieldType> + + <fieldType name="edge_ngram" class="solr.TextField" positionIncrementGap="1"> + <analyzer type="index"> + <tokenizer class="solr.WhitespaceTokenizerFactory" /> + <filter class="solr.LowerCaseFilterFactory" /> + <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/> + <filter class="solr.EdgeNGramFilterFactory" minGramSize="2" maxGramSize="15" side="front" /> + </analyzer> + <analyzer type="query"> + <tokenizer class="solr.WhitespaceTokenizerFactory" /> + <filter class="solr.LowerCaseFilterFactory" /> + <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/> + </analyzer> + </fieldType> + </types> + + <fields> + <!-- general --> + <field name="id" type="string" indexed="true" stored="true" multiValued="false" required="true"/> + <field name="django_ct" type="string" indexed="true" stored="true" multiValued="false"/> + <field name="django_id" type="string" indexed="true" stored="true" multiValued="false"/> + + <dynamicField name="*_i" type="int" indexed="true" stored="true"/> + <dynamicField name="*_s" type="string" indexed="true" stored="true"/> + <dynamicField name="*_l" type="long" indexed="true" stored="true"/> + <dynamicField name="*_t" type="text_en" indexed="true" stored="true"/> + <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/> + <dynamicField name="*_f" type="float" indexed="true" stored="true"/> + <dynamicField name="*_d" type="double" indexed="true" stored="true"/> + <dynamicField name="*_dt" type="date" indexed="true" stored="true"/> + <dynamicField name="*_p" type="location" indexed="true" stored="true"/> + <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false"/> + + + <field name="text" type="text_en" indexed="true" stored="true" multiValued="false" /> + + <field name="location" type="location" indexed="true" stored="true" multiValued="false" /> + + <field name="categories" type="text_en" indexed="true" stored="true" multiValued="true" /> + + <field name="content_auto" type="edge_ngram" indexed="true" stored="true" multiValued="false" /> + + </fields> + + <!-- field to use to determine and enforce document uniqueness. --> + <uniqueKey>id</uniqueKey> + + <!-- field for the QueryParser to use when an explicit fieldname is absent --> + <defaultSearchField>text</defaultSearchField> + + <!-- SolrQueryParser configuration: defaultOperator="AND|OR" --> + <solrQueryParser defaultOperator="AND"/> +</schema> + |