Commit b128f1838c2fa9cbbf45c7c1689fc2c35e6f7c53
Committed by
Sergio Oliveira
1 parent
4a6abe7b
Exists in
master
and in
39 other branches
Changed folder to ci/solr_confs
Showing
5 changed files
with
281 additions
and
281 deletions
Show diff stats
.travis.yml
| ... | ... | @@ -16,8 +16,8 @@ install: |
| 16 | 16 | - psql -c "CREATE USER colab WITH PASSWORD 'colab' CREATEDB;" -U postgres |
| 17 | 17 | |
| 18 | 18 | before_script: |
| 19 | - - colab-admin build_solr_schema > solr_confs/schema.xml | |
| 20 | - - cat ci/install_solr.sh | SOLR_VERSION=4.10.3 SOLR_CONFS="solr_confs" bash | |
| 19 | + - colab-admin build_solr_schema > ci/solr_confs/schema.xml | |
| 20 | + - cat ci/install_solr.sh | SOLR_VERSION=4.10.3 SOLR_CONFS="ci/solr_confs" bash | |
| 21 | 21 | |
| 22 | 22 | script: |
| 23 | 23 | - python setup.py test | ... | ... |
| ... | ... | @@ -0,0 +1,225 @@ |
| 1 | +<?xml version="1.0" ?> | |
| 2 | +<!-- | |
| 3 | + Licensed to the Apache Software Foundation (ASF) under one or more | |
| 4 | + contributor license agreements. See the NOTICE file distributed with | |
| 5 | + this work for additional information regarding copyright ownership. | |
| 6 | + The ASF licenses this file to You under the Apache License, Version 2.0 | |
| 7 | + (the "License"); you may not use this file except in compliance with | |
| 8 | + the License. You may obtain a copy of the License at | |
| 9 | + | |
| 10 | + http://www.apache.org/licenses/LICENSE-2.0 | |
| 11 | + | |
| 12 | + Unless required by applicable law or agreed to in writing, software | |
| 13 | + distributed under the License is distributed on an "AS IS" BASIS, | |
| 14 | + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | |
| 15 | + See the License for the specific language governing permissions and | |
| 16 | + limitations under the License. | |
| 17 | +--> | |
| 18 | + | |
| 19 | +<schema name="default" version="1.5"> | |
| 20 | + <types> | |
| 21 | + <fieldtype name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/> | |
| 22 | + <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/> | |
| 23 | + <fieldtype name="binary" class="solr.BinaryField"/> | |
| 24 | + | |
| 25 | + <!-- Numeric field types that manipulate the value into | |
| 26 | + a string value that isn't human-readable in its internal form, | |
| 27 | + but with a lexicographic ordering the same as the numeric ordering, | |
| 28 | + so that range queries work correctly. --> | |
| 29 | + <fieldType name="int" class="solr.TrieIntField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/> | |
| 30 | + <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/> | |
| 31 | + <fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/> | |
| 32 | + <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/> | |
| 33 | + <fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/> | |
| 34 | + <fieldType name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/> | |
| 35 | + <fieldType name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/> | |
| 36 | + <fieldType name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/> | |
| 37 | + | |
| 38 | + <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/> | |
| 39 | + <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/> | |
| 40 | + <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/> | |
| 41 | + <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/> | |
| 42 | + | |
| 43 | + <fieldType name="date" class="solr.TrieDateField" omitNorms="true" precisionStep="0" positionIncrementGap="0"/> | |
| 44 | + <!-- A Trie based date field for faster date range queries and date faceting. --> | |
| 45 | + <fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" precisionStep="6" positionIncrementGap="0"/> | |
| 46 | + | |
| 47 | + <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/> | |
| 48 | + <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/> | |
| 49 | + <fieldtype name="geohash" class="solr.GeoHashField"/> | |
| 50 | + | |
| 51 | + <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100"> | |
| 52 | + <analyzer type="index"> | |
| 53 | + <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 54 | + <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" /> | |
| 55 | + <!-- in this example, we will only use synonyms at query time | |
| 56 | + <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/> | |
| 57 | + --> | |
| 58 | + <filter class="solr.LowerCaseFilterFactory"/> | |
| 59 | + </analyzer> | |
| 60 | + <analyzer type="query"> | |
| 61 | + <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 62 | + <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" /> | |
| 63 | + <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> | |
| 64 | + <filter class="solr.LowerCaseFilterFactory"/> | |
| 65 | + </analyzer> | |
| 66 | + </fieldType> | |
| 67 | + | |
| 68 | + <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100"> | |
| 69 | + <analyzer type="index"> | |
| 70 | + <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 71 | + <filter class="solr.StopFilterFactory" | |
| 72 | + ignoreCase="true" | |
| 73 | + words="lang/stopwords_en.txt" | |
| 74 | + enablePositionIncrements="true" | |
| 75 | + /> | |
| 76 | + <filter class="solr.LowerCaseFilterFactory"/> | |
| 77 | + <filter class="solr.EnglishPossessiveFilterFactory"/> | |
| 78 | + <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> | |
| 79 | + <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory: | |
| 80 | + <filter class="solr.EnglishMinimalStemFilterFactory"/> | |
| 81 | + --> | |
| 82 | + <filter class="solr.PorterStemFilterFactory"/> | |
| 83 | + </analyzer> | |
| 84 | + <analyzer type="query"> | |
| 85 | + <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 86 | + <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> | |
| 87 | + <filter class="solr.StopFilterFactory" | |
| 88 | + ignoreCase="true" | |
| 89 | + words="lang/stopwords_en.txt" | |
| 90 | + enablePositionIncrements="true" | |
| 91 | + /> | |
| 92 | + <filter class="solr.LowerCaseFilterFactory"/> | |
| 93 | + <filter class="solr.EnglishPossessiveFilterFactory"/> | |
| 94 | + <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> | |
| 95 | + <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory: | |
| 96 | + <filter class="solr.EnglishMinimalStemFilterFactory"/> | |
| 97 | + --> | |
| 98 | + <filter class="solr.PorterStemFilterFactory"/> | |
| 99 | + </analyzer> | |
| 100 | + </fieldType> | |
| 101 | + | |
| 102 | + <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100"> | |
| 103 | + <analyzer> | |
| 104 | + <tokenizer class="solr.WhitespaceTokenizerFactory"/> | |
| 105 | + </analyzer> | |
| 106 | + </fieldType> | |
| 107 | + | |
| 108 | + <fieldType name="ngram" class="solr.TextField" > | |
| 109 | + <analyzer type="index"> | |
| 110 | + <tokenizer class="solr.KeywordTokenizerFactory"/> | |
| 111 | + <filter class="solr.LowerCaseFilterFactory"/> | |
| 112 | + <filter class="solr.NGramFilterFactory" minGramSize="3" maxGramSize="15" /> | |
| 113 | + </analyzer> | |
| 114 | + <analyzer type="query"> | |
| 115 | + <tokenizer class="solr.KeywordTokenizerFactory"/> | |
| 116 | + <filter class="solr.LowerCaseFilterFactory"/> | |
| 117 | + </analyzer> | |
| 118 | + </fieldType> | |
| 119 | + | |
| 120 | + <fieldType name="edge_ngram" class="solr.TextField" positionIncrementGap="1"> | |
| 121 | + <analyzer type="index"> | |
| 122 | + <tokenizer class="solr.WhitespaceTokenizerFactory" /> | |
| 123 | + <filter class="solr.LowerCaseFilterFactory" /> | |
| 124 | + <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/> | |
| 125 | + <filter class="solr.EdgeNGramFilterFactory" minGramSize="2" maxGramSize="15" side="front" /> | |
| 126 | + </analyzer> | |
| 127 | + <analyzer type="query"> | |
| 128 | + <tokenizer class="solr.WhitespaceTokenizerFactory" /> | |
| 129 | + <filter class="solr.LowerCaseFilterFactory" /> | |
| 130 | + <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/> | |
| 131 | + </analyzer> | |
| 132 | + </fieldType> | |
| 133 | + </types> | |
| 134 | + | |
| 135 | + <fields> | |
| 136 | + <!-- general --> | |
| 137 | + <field name="id" type="string" indexed="true" stored="true" multiValued="false" required="true"/> | |
| 138 | + <field name="django_ct" type="string" indexed="true" stored="true" multiValued="false"/> | |
| 139 | + <field name="django_id" type="string" indexed="true" stored="true" multiValued="false"/> | |
| 140 | + <field name="_version_" type="long" indexed="true" stored ="true"/> | |
| 141 | + | |
| 142 | + <dynamicField name="*_i" type="int" indexed="true" stored="true"/> | |
| 143 | + <dynamicField name="*_s" type="string" indexed="true" stored="true"/> | |
| 144 | + <dynamicField name="*_l" type="long" indexed="true" stored="true"/> | |
| 145 | + <dynamicField name="*_t" type="text_en" indexed="true" stored="true"/> | |
| 146 | + <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/> | |
| 147 | + <dynamicField name="*_f" type="float" indexed="true" stored="true"/> | |
| 148 | + <dynamicField name="*_d" type="double" indexed="true" stored="true"/> | |
| 149 | + <dynamicField name="*_dt" type="date" indexed="true" stored="true"/> | |
| 150 | + <dynamicField name="*_p" type="location" indexed="true" stored="true"/> | |
| 151 | + <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false"/> | |
| 152 | + | |
| 153 | + | |
| 154 | + <field name="username" type="text_en" indexed="true" stored="false" multiValued="false" /> | |
| 155 | + | |
| 156 | + <field name="google_talk" type="text_en" indexed="true" stored="false" multiValued="false" /> | |
| 157 | + | |
| 158 | + <field name="description" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 159 | + | |
| 160 | + <field name="title" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 161 | + | |
| 162 | + <field name="webpage" type="text_en" indexed="true" stored="false" multiValued="false" /> | |
| 163 | + | |
| 164 | + <field name="text" type="text_en" indexed="true" stored="false" multiValued="false" /> | |
| 165 | + | |
| 166 | + <field name="institution" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 167 | + | |
| 168 | + <field name="message_count" type="long" indexed="true" stored="false" multiValued="false" /> | |
| 169 | + | |
| 170 | + <field name="url" type="string" indexed="false" stored="true" multiValued="false" /> | |
| 171 | + | |
| 172 | + <field name="icon_name" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 173 | + | |
| 174 | + <field name="role" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 175 | + | |
| 176 | + <field name="contribution_count" type="long" indexed="true" stored="false" multiValued="false" /> | |
| 177 | + | |
| 178 | + <field name="type" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 179 | + | |
| 180 | + <field name="email" type="text_en" indexed="true" stored="false" multiValued="false" /> | |
| 181 | + | |
| 182 | + <field name="name" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 183 | + | |
| 184 | + <field name="fullname_and_username" type="text_en" indexed="true" stored="false" multiValued="false" /> | |
| 185 | + | |
| 186 | + <field name="modified_by_url" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 187 | + | |
| 188 | + <field name="collaborators" type="text_en" indexed="true" stored="false" multiValued="false" /> | |
| 189 | + | |
| 190 | + <field name="tag" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 191 | + | |
| 192 | + <field name="fullname" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 193 | + | |
| 194 | + <field name="mailinglist_url" type="string" indexed="false" stored="true" multiValued="false" /> | |
| 195 | + | |
| 196 | + <field name="latest_description" type="string" indexed="false" stored="true" multiValued="false" /> | |
| 197 | + | |
| 198 | + <field name="hits" type="long" indexed="true" stored="true" multiValued="false" /> | |
| 199 | + | |
| 200 | + <field name="modified_by" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 201 | + | |
| 202 | + <field name="created" type="date" indexed="true" stored="true" multiValued="false" /> | |
| 203 | + | |
| 204 | + <field name="modified" type="date" indexed="true" stored="true" multiValued="false" /> | |
| 205 | + | |
| 206 | + <field name="latest_message_pk" type="long" indexed="false" stored="true" multiValued="false" /> | |
| 207 | + | |
| 208 | + <field name="score" type="long" indexed="true" stored="true" multiValued="false" /> | |
| 209 | + | |
| 210 | + <field name="author_url" type="string" indexed="false" stored="true" multiValued="false" /> | |
| 211 | + | |
| 212 | + <field name="author" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 213 | + | |
| 214 | + </fields> | |
| 215 | + | |
| 216 | + <!-- field to use to determine and enforce document uniqueness. --> | |
| 217 | + <uniqueKey>id</uniqueKey> | |
| 218 | + | |
| 219 | + <!-- field for the QueryParser to use when an explicit fieldname is absent --> | |
| 220 | + <defaultSearchField>text</defaultSearchField> | |
| 221 | + | |
| 222 | + <!-- SolrQueryParser configuration: defaultOperator="AND|OR" --> | |
| 223 | + <solrQueryParser defaultOperator="AND"/> | |
| 224 | +</schema> | |
| 225 | + | ... | ... |
| ... | ... | @@ -0,0 +1,54 @@ |
| 1 | +# Licensed to the Apache Software Foundation (ASF) under one or more | |
| 2 | +# contributor license agreements. See the NOTICE file distributed with | |
| 3 | +# this work for additional information regarding copyright ownership. | |
| 4 | +# The ASF licenses this file to You under the Apache License, Version 2.0 | |
| 5 | +# (the "License"); you may not use this file except in compliance with | |
| 6 | +# the License. You may obtain a copy of the License at | |
| 7 | +# | |
| 8 | +# http://www.apache.org/licenses/LICENSE-2.0 | |
| 9 | +# | |
| 10 | +# Unless required by applicable law or agreed to in writing, software | |
| 11 | +# distributed under the License is distributed on an "AS IS" BASIS, | |
| 12 | +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | |
| 13 | +# See the License for the specific language governing permissions and | |
| 14 | +# limitations under the License. | |
| 15 | + | |
| 16 | +# a couple of test stopwords to test that the words are really being | |
| 17 | +# configured from this file: | |
| 18 | +stopworda | |
| 19 | +stopwordb | |
| 20 | + | |
| 21 | +# Standard english stop words taken from Lucene's StopAnalyzer | |
| 22 | +a | |
| 23 | +an | |
| 24 | +and | |
| 25 | +are | |
| 26 | +as | |
| 27 | +at | |
| 28 | +be | |
| 29 | +but | |
| 30 | +by | |
| 31 | +for | |
| 32 | +if | |
| 33 | +in | |
| 34 | +into | |
| 35 | +is | |
| 36 | +it | |
| 37 | +no | |
| 38 | +not | |
| 39 | +of | |
| 40 | +on | |
| 41 | +or | |
| 42 | +such | |
| 43 | +that | |
| 44 | +the | |
| 45 | +their | |
| 46 | +then | |
| 47 | +there | |
| 48 | +these | |
| 49 | +they | |
| 50 | +this | |
| 51 | +to | |
| 52 | +was | |
| 53 | +will | |
| 54 | +with | ... | ... |
solr_confs/schema.xml
| ... | ... | @@ -1,225 +0,0 @@ |
| 1 | -<?xml version="1.0" ?> | |
| 2 | -<!-- | |
| 3 | - Licensed to the Apache Software Foundation (ASF) under one or more | |
| 4 | - contributor license agreements. See the NOTICE file distributed with | |
| 5 | - this work for additional information regarding copyright ownership. | |
| 6 | - The ASF licenses this file to You under the Apache License, Version 2.0 | |
| 7 | - (the "License"); you may not use this file except in compliance with | |
| 8 | - the License. You may obtain a copy of the License at | |
| 9 | - | |
| 10 | - http://www.apache.org/licenses/LICENSE-2.0 | |
| 11 | - | |
| 12 | - Unless required by applicable law or agreed to in writing, software | |
| 13 | - distributed under the License is distributed on an "AS IS" BASIS, | |
| 14 | - WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | |
| 15 | - See the License for the specific language governing permissions and | |
| 16 | - limitations under the License. | |
| 17 | ---> | |
| 18 | - | |
| 19 | -<schema name="default" version="1.5"> | |
| 20 | - <types> | |
| 21 | - <fieldtype name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/> | |
| 22 | - <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/> | |
| 23 | - <fieldtype name="binary" class="solr.BinaryField"/> | |
| 24 | - | |
| 25 | - <!-- Numeric field types that manipulate the value into | |
| 26 | - a string value that isn't human-readable in its internal form, | |
| 27 | - but with a lexicographic ordering the same as the numeric ordering, | |
| 28 | - so that range queries work correctly. --> | |
| 29 | - <fieldType name="int" class="solr.TrieIntField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/> | |
| 30 | - <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/> | |
| 31 | - <fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/> | |
| 32 | - <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/> | |
| 33 | - <fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/> | |
| 34 | - <fieldType name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/> | |
| 35 | - <fieldType name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/> | |
| 36 | - <fieldType name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/> | |
| 37 | - | |
| 38 | - <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/> | |
| 39 | - <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/> | |
| 40 | - <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/> | |
| 41 | - <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/> | |
| 42 | - | |
| 43 | - <fieldType name="date" class="solr.TrieDateField" omitNorms="true" precisionStep="0" positionIncrementGap="0"/> | |
| 44 | - <!-- A Trie based date field for faster date range queries and date faceting. --> | |
| 45 | - <fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" precisionStep="6" positionIncrementGap="0"/> | |
| 46 | - | |
| 47 | - <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/> | |
| 48 | - <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/> | |
| 49 | - <fieldtype name="geohash" class="solr.GeoHashField"/> | |
| 50 | - | |
| 51 | - <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100"> | |
| 52 | - <analyzer type="index"> | |
| 53 | - <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 54 | - <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" /> | |
| 55 | - <!-- in this example, we will only use synonyms at query time | |
| 56 | - <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/> | |
| 57 | - --> | |
| 58 | - <filter class="solr.LowerCaseFilterFactory"/> | |
| 59 | - </analyzer> | |
| 60 | - <analyzer type="query"> | |
| 61 | - <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 62 | - <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" /> | |
| 63 | - <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> | |
| 64 | - <filter class="solr.LowerCaseFilterFactory"/> | |
| 65 | - </analyzer> | |
| 66 | - </fieldType> | |
| 67 | - | |
| 68 | - <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100"> | |
| 69 | - <analyzer type="index"> | |
| 70 | - <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 71 | - <filter class="solr.StopFilterFactory" | |
| 72 | - ignoreCase="true" | |
| 73 | - words="lang/stopwords_en.txt" | |
| 74 | - enablePositionIncrements="true" | |
| 75 | - /> | |
| 76 | - <filter class="solr.LowerCaseFilterFactory"/> | |
| 77 | - <filter class="solr.EnglishPossessiveFilterFactory"/> | |
| 78 | - <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> | |
| 79 | - <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory: | |
| 80 | - <filter class="solr.EnglishMinimalStemFilterFactory"/> | |
| 81 | - --> | |
| 82 | - <filter class="solr.PorterStemFilterFactory"/> | |
| 83 | - </analyzer> | |
| 84 | - <analyzer type="query"> | |
| 85 | - <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 86 | - <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> | |
| 87 | - <filter class="solr.StopFilterFactory" | |
| 88 | - ignoreCase="true" | |
| 89 | - words="lang/stopwords_en.txt" | |
| 90 | - enablePositionIncrements="true" | |
| 91 | - /> | |
| 92 | - <filter class="solr.LowerCaseFilterFactory"/> | |
| 93 | - <filter class="solr.EnglishPossessiveFilterFactory"/> | |
| 94 | - <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> | |
| 95 | - <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory: | |
| 96 | - <filter class="solr.EnglishMinimalStemFilterFactory"/> | |
| 97 | - --> | |
| 98 | - <filter class="solr.PorterStemFilterFactory"/> | |
| 99 | - </analyzer> | |
| 100 | - </fieldType> | |
| 101 | - | |
| 102 | - <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100"> | |
| 103 | - <analyzer> | |
| 104 | - <tokenizer class="solr.WhitespaceTokenizerFactory"/> | |
| 105 | - </analyzer> | |
| 106 | - </fieldType> | |
| 107 | - | |
| 108 | - <fieldType name="ngram" class="solr.TextField" > | |
| 109 | - <analyzer type="index"> | |
| 110 | - <tokenizer class="solr.KeywordTokenizerFactory"/> | |
| 111 | - <filter class="solr.LowerCaseFilterFactory"/> | |
| 112 | - <filter class="solr.NGramFilterFactory" minGramSize="3" maxGramSize="15" /> | |
| 113 | - </analyzer> | |
| 114 | - <analyzer type="query"> | |
| 115 | - <tokenizer class="solr.KeywordTokenizerFactory"/> | |
| 116 | - <filter class="solr.LowerCaseFilterFactory"/> | |
| 117 | - </analyzer> | |
| 118 | - </fieldType> | |
| 119 | - | |
| 120 | - <fieldType name="edge_ngram" class="solr.TextField" positionIncrementGap="1"> | |
| 121 | - <analyzer type="index"> | |
| 122 | - <tokenizer class="solr.WhitespaceTokenizerFactory" /> | |
| 123 | - <filter class="solr.LowerCaseFilterFactory" /> | |
| 124 | - <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/> | |
| 125 | - <filter class="solr.EdgeNGramFilterFactory" minGramSize="2" maxGramSize="15" side="front" /> | |
| 126 | - </analyzer> | |
| 127 | - <analyzer type="query"> | |
| 128 | - <tokenizer class="solr.WhitespaceTokenizerFactory" /> | |
| 129 | - <filter class="solr.LowerCaseFilterFactory" /> | |
| 130 | - <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/> | |
| 131 | - </analyzer> | |
| 132 | - </fieldType> | |
| 133 | - </types> | |
| 134 | - | |
| 135 | - <fields> | |
| 136 | - <!-- general --> | |
| 137 | - <field name="id" type="string" indexed="true" stored="true" multiValued="false" required="true"/> | |
| 138 | - <field name="django_ct" type="string" indexed="true" stored="true" multiValued="false"/> | |
| 139 | - <field name="django_id" type="string" indexed="true" stored="true" multiValued="false"/> | |
| 140 | - <field name="_version_" type="long" indexed="true" stored ="true"/> | |
| 141 | - | |
| 142 | - <dynamicField name="*_i" type="int" indexed="true" stored="true"/> | |
| 143 | - <dynamicField name="*_s" type="string" indexed="true" stored="true"/> | |
| 144 | - <dynamicField name="*_l" type="long" indexed="true" stored="true"/> | |
| 145 | - <dynamicField name="*_t" type="text_en" indexed="true" stored="true"/> | |
| 146 | - <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/> | |
| 147 | - <dynamicField name="*_f" type="float" indexed="true" stored="true"/> | |
| 148 | - <dynamicField name="*_d" type="double" indexed="true" stored="true"/> | |
| 149 | - <dynamicField name="*_dt" type="date" indexed="true" stored="true"/> | |
| 150 | - <dynamicField name="*_p" type="location" indexed="true" stored="true"/> | |
| 151 | - <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false"/> | |
| 152 | - | |
| 153 | - | |
| 154 | - <field name="username" type="text_en" indexed="true" stored="false" multiValued="false" /> | |
| 155 | - | |
| 156 | - <field name="google_talk" type="text_en" indexed="true" stored="false" multiValued="false" /> | |
| 157 | - | |
| 158 | - <field name="description" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 159 | - | |
| 160 | - <field name="title" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 161 | - | |
| 162 | - <field name="webpage" type="text_en" indexed="true" stored="false" multiValued="false" /> | |
| 163 | - | |
| 164 | - <field name="text" type="text_en" indexed="true" stored="false" multiValued="false" /> | |
| 165 | - | |
| 166 | - <field name="institution" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 167 | - | |
| 168 | - <field name="message_count" type="long" indexed="true" stored="false" multiValued="false" /> | |
| 169 | - | |
| 170 | - <field name="url" type="string" indexed="false" stored="true" multiValued="false" /> | |
| 171 | - | |
| 172 | - <field name="icon_name" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 173 | - | |
| 174 | - <field name="role" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 175 | - | |
| 176 | - <field name="contribution_count" type="long" indexed="true" stored="false" multiValued="false" /> | |
| 177 | - | |
| 178 | - <field name="type" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 179 | - | |
| 180 | - <field name="email" type="text_en" indexed="true" stored="false" multiValued="false" /> | |
| 181 | - | |
| 182 | - <field name="name" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 183 | - | |
| 184 | - <field name="fullname_and_username" type="text_en" indexed="true" stored="false" multiValued="false" /> | |
| 185 | - | |
| 186 | - <field name="modified_by_url" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 187 | - | |
| 188 | - <field name="collaborators" type="text_en" indexed="true" stored="false" multiValued="false" /> | |
| 189 | - | |
| 190 | - <field name="tag" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 191 | - | |
| 192 | - <field name="fullname" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 193 | - | |
| 194 | - <field name="mailinglist_url" type="string" indexed="false" stored="true" multiValued="false" /> | |
| 195 | - | |
| 196 | - <field name="latest_description" type="string" indexed="false" stored="true" multiValued="false" /> | |
| 197 | - | |
| 198 | - <field name="hits" type="long" indexed="true" stored="true" multiValued="false" /> | |
| 199 | - | |
| 200 | - <field name="modified_by" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 201 | - | |
| 202 | - <field name="created" type="date" indexed="true" stored="true" multiValued="false" /> | |
| 203 | - | |
| 204 | - <field name="modified" type="date" indexed="true" stored="true" multiValued="false" /> | |
| 205 | - | |
| 206 | - <field name="latest_message_pk" type="long" indexed="false" stored="true" multiValued="false" /> | |
| 207 | - | |
| 208 | - <field name="score" type="long" indexed="true" stored="true" multiValued="false" /> | |
| 209 | - | |
| 210 | - <field name="author_url" type="string" indexed="false" stored="true" multiValued="false" /> | |
| 211 | - | |
| 212 | - <field name="author" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 213 | - | |
| 214 | - </fields> | |
| 215 | - | |
| 216 | - <!-- field to use to determine and enforce document uniqueness. --> | |
| 217 | - <uniqueKey>id</uniqueKey> | |
| 218 | - | |
| 219 | - <!-- field for the QueryParser to use when an explicit fieldname is absent --> | |
| 220 | - <defaultSearchField>text</defaultSearchField> | |
| 221 | - | |
| 222 | - <!-- SolrQueryParser configuration: defaultOperator="AND|OR" --> | |
| 223 | - <solrQueryParser defaultOperator="AND"/> | |
| 224 | -</schema> | |
| 225 | - |
solr_confs/stopwords_en.txt
| ... | ... | @@ -1,54 +0,0 @@ |
| 1 | -# Licensed to the Apache Software Foundation (ASF) under one or more | |
| 2 | -# contributor license agreements. See the NOTICE file distributed with | |
| 3 | -# this work for additional information regarding copyright ownership. | |
| 4 | -# The ASF licenses this file to You under the Apache License, Version 2.0 | |
| 5 | -# (the "License"); you may not use this file except in compliance with | |
| 6 | -# the License. You may obtain a copy of the License at | |
| 7 | -# | |
| 8 | -# http://www.apache.org/licenses/LICENSE-2.0 | |
| 9 | -# | |
| 10 | -# Unless required by applicable law or agreed to in writing, software | |
| 11 | -# distributed under the License is distributed on an "AS IS" BASIS, | |
| 12 | -# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | |
| 13 | -# See the License for the specific language governing permissions and | |
| 14 | -# limitations under the License. | |
| 15 | - | |
| 16 | -# a couple of test stopwords to test that the words are really being | |
| 17 | -# configured from this file: | |
| 18 | -stopworda | |
| 19 | -stopwordb | |
| 20 | - | |
| 21 | -# Standard english stop words taken from Lucene's StopAnalyzer | |
| 22 | -a | |
| 23 | -an | |
| 24 | -and | |
| 25 | -are | |
| 26 | -as | |
| 27 | -at | |
| 28 | -be | |
| 29 | -but | |
| 30 | -by | |
| 31 | -for | |
| 32 | -if | |
| 33 | -in | |
| 34 | -into | |
| 35 | -is | |
| 36 | -it | |
| 37 | -no | |
| 38 | -not | |
| 39 | -of | |
| 40 | -on | |
| 41 | -or | |
| 42 | -such | |
| 43 | -that | |
| 44 | -the | |
| 45 | -their | |
| 46 | -then | |
| 47 | -there | |
| 48 | -these | |
| 49 | -they | |
| 50 | -this | |
| 51 | -to | |
| 52 | -was | |
| 53 | -will | |
| 54 | -with |