schema.xml 27 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572
  1. <?xml version="1.0" encoding="UTF-8" ?>
  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. http://www.apache.org/licenses/LICENSE-2.0
  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. <schema name="example" version="1.5">
  17. <fields>
  18. <field name="_version_" type="long" indexed="true" stored="true"/>
  19. <!-- REPLACE FIELDS -->
  20. </fields>
  21. <uniqueKey><!-- REPLACE UNIQUE KEY --></uniqueKey>
  22. <types>
  23. <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
  24. <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
  25. <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
  26. <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
  27. <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
  28. <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
  29. <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
  30. <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
  31. <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
  32. <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
  33. <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
  34. <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
  35. <fieldtype name="binary" class="solr.BinaryField"/>
  36. <fieldType name="pint" class="solr.TrieIntField"/>
  37. <fieldType name="plong" class="solr.TrieLongField"/>
  38. <fieldType name="pfloat" class="solr.TrieFloatField"/>
  39. <fieldType name="pdouble" class="solr.TrieDoubleField"/>
  40. <fieldType name="pdate" class="solr.TrieDateField" sortMissingLast="true"/>
  41. <fieldType name="random" class="solr.RandomSortField" indexed="true" />
  42. <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
  43. <analyzer>
  44. <tokenizer class="solr.WhitespaceTokenizerFactory"/>
  45. </analyzer>
  46. </fieldType>
  47. <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
  48. <analyzer type="index">
  49. <tokenizer class="solr.StandardTokenizerFactory"/>
  50. <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
  51. <filter class="solr.LowerCaseFilterFactory"/>
  52. </analyzer>
  53. <analyzer type="query">
  54. <tokenizer class="solr.StandardTokenizerFactory"/>
  55. <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
  56. <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
  57. <filter class="solr.LowerCaseFilterFactory"/>
  58. </analyzer>
  59. </fieldType>
  60. <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
  61. <analyzer type="index">
  62. <tokenizer class="solr.StandardTokenizerFactory"/>
  63. <filter class="solr.StopFilterFactory"
  64. ignoreCase="true"
  65. words="lang/stopwords_en.txt"
  66. />
  67. <filter class="solr.LowerCaseFilterFactory"/>
  68. <filter class="solr.EnglishPossessiveFilterFactory"/>
  69. <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
  70. <filter class="solr.PorterStemFilterFactory"/>
  71. </analyzer>
  72. <analyzer type="query">
  73. <tokenizer class="solr.StandardTokenizerFactory"/>
  74. <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
  75. <filter class="solr.StopFilterFactory"
  76. ignoreCase="true"
  77. words="lang/stopwords_en.txt"
  78. />
  79. <filter class="solr.LowerCaseFilterFactory"/>
  80. <filter class="solr.EnglishPossessiveFilterFactory"/>
  81. <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
  82. <filter class="solr.PorterStemFilterFactory"/>
  83. </analyzer>
  84. </fieldType>
  85. <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
  86. <analyzer type="index">
  87. <tokenizer class="solr.WhitespaceTokenizerFactory"/>
  88. <filter class="solr.StopFilterFactory"
  89. ignoreCase="true"
  90. words="lang/stopwords_en.txt"
  91. />
  92. <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
  93. <filter class="solr.LowerCaseFilterFactory"/>
  94. <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
  95. <filter class="solr.PorterStemFilterFactory"/>
  96. </analyzer>
  97. <analyzer type="query">
  98. <tokenizer class="solr.WhitespaceTokenizerFactory"/>
  99. <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
  100. <filter class="solr.StopFilterFactory"
  101. ignoreCase="true"
  102. words="lang/stopwords_en.txt"
  103. />
  104. <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
  105. <filter class="solr.LowerCaseFilterFactory"/>
  106. <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
  107. <filter class="solr.PorterStemFilterFactory"/>
  108. </analyzer>
  109. </fieldType>
  110. <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
  111. <analyzer>
  112. <tokenizer class="solr.WhitespaceTokenizerFactory"/>
  113. <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
  114. <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
  115. <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
  116. <filter class="solr.LowerCaseFilterFactory"/>
  117. <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
  118. <filter class="solr.EnglishMinimalStemFilterFactory"/>
  119. <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
  120. </analyzer>
  121. </fieldType>
  122. <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
  123. <analyzer type="index">
  124. <tokenizer class="solr.StandardTokenizerFactory"/>
  125. <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
  126. <filter class="solr.LowerCaseFilterFactory"/>
  127. <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
  128. maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
  129. </analyzer>
  130. <analyzer type="query">
  131. <tokenizer class="solr.StandardTokenizerFactory"/>
  132. <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
  133. <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
  134. <filter class="solr.LowerCaseFilterFactory"/>
  135. </analyzer>
  136. </fieldType>
  137. <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
  138. <analyzer>
  139. <tokenizer class="solr.KeywordTokenizerFactory"/>
  140. <filter class="solr.LowerCaseFilterFactory" />
  141. <filter class="solr.TrimFilterFactory" />
  142. <filter class="solr.PatternReplaceFilterFactory"
  143. pattern="([^a-z])" replacement="" replace="all"
  144. />
  145. </analyzer>
  146. </fieldType>
  147. <fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
  148. <analyzer>
  149. <tokenizer class="solr.StandardTokenizerFactory"/>
  150. <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
  151. </analyzer>
  152. </fieldtype>
  153. <fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
  154. <analyzer>
  155. <tokenizer class="solr.WhitespaceTokenizerFactory"/>
  156. <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
  157. </analyzer>
  158. </fieldtype>
  159. <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
  160. <analyzer>
  161. <tokenizer class="solr.KeywordTokenizerFactory"/>
  162. <filter class="solr.LowerCaseFilterFactory" />
  163. </analyzer>
  164. </fieldType>
  165. <fieldType name="descendent_path" class="solr.TextField">
  166. <analyzer type="index">
  167. <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
  168. </analyzer>
  169. <analyzer type="query">
  170. <tokenizer class="solr.KeywordTokenizerFactory" />
  171. </analyzer>
  172. </fieldType>
  173. <fieldType name="ancestor_path" class="solr.TextField">
  174. <analyzer type="index">
  175. <tokenizer class="solr.KeywordTokenizerFactory" />
  176. </analyzer>
  177. <analyzer type="query">
  178. <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
  179. </analyzer>
  180. </fieldType>
  181. <fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
  182. <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
  183. <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
  184. <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
  185. <!-- Arabic -->
  186. <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
  187. <analyzer>
  188. <tokenizer class="solr.StandardTokenizerFactory"/>
  189. <!-- for any non-arabic -->
  190. <filter class="solr.LowerCaseFilterFactory"/>
  191. <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
  192. <!-- normalizes ﻯ to ﻱ, etc -->
  193. <filter class="solr.ArabicNormalizationFilterFactory"/>
  194. <filter class="solr.ArabicStemFilterFactory"/>
  195. </analyzer>
  196. </fieldType>
  197. <!-- Bulgarian -->
  198. <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
  199. <analyzer>
  200. <tokenizer class="solr.StandardTokenizerFactory"/>
  201. <filter class="solr.LowerCaseFilterFactory"/>
  202. <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" />
  203. <filter class="solr.BulgarianStemFilterFactory"/>
  204. </analyzer>
  205. </fieldType>
  206. <!-- Catalan -->
  207. <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
  208. <analyzer>
  209. <tokenizer class="solr.StandardTokenizerFactory"/>
  210. <!-- removes l', etc -->
  211. <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
  212. <filter class="solr.LowerCaseFilterFactory"/>
  213. <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" />
  214. <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
  215. </analyzer>
  216. </fieldType>
  217. <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
  218. <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
  219. <analyzer>
  220. <tokenizer class="solr.StandardTokenizerFactory"/>
  221. <!-- normalize width before bigram, as e.g. half-width dakuten combine -->
  222. <filter class="solr.CJKWidthFilterFactory"/>
  223. <!-- for any non-CJK -->
  224. <filter class="solr.LowerCaseFilterFactory"/>
  225. <filter class="solr.CJKBigramFilterFactory"/>
  226. </analyzer>
  227. </fieldType>
  228. <!-- Czech -->
  229. <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
  230. <analyzer>
  231. <tokenizer class="solr.StandardTokenizerFactory"/>
  232. <filter class="solr.LowerCaseFilterFactory"/>
  233. <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" />
  234. <filter class="solr.CzechStemFilterFactory"/>
  235. </analyzer>
  236. </fieldType>
  237. <!-- Danish -->
  238. <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
  239. <analyzer>
  240. <tokenizer class="solr.StandardTokenizerFactory"/>
  241. <filter class="solr.LowerCaseFilterFactory"/>
  242. <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
  243. <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
  244. </analyzer>
  245. </fieldType>
  246. <!-- German -->
  247. <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
  248. <analyzer>
  249. <tokenizer class="solr.StandardTokenizerFactory"/>
  250. <filter class="solr.LowerCaseFilterFactory"/>
  251. <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" />
  252. <filter class="solr.GermanNormalizationFilterFactory"/>
  253. <filter class="solr.GermanLightStemFilterFactory"/>
  254. <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
  255. <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
  256. </analyzer>
  257. </fieldType>
  258. <!-- Greek -->
  259. <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
  260. <analyzer>
  261. <tokenizer class="solr.StandardTokenizerFactory"/>
  262. <!-- greek specific lowercase for sigma -->
  263. <filter class="solr.GreekLowerCaseFilterFactory"/>
  264. <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
  265. <filter class="solr.GreekStemFilterFactory"/>
  266. </analyzer>
  267. </fieldType>
  268. <!-- Spanish -->
  269. <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
  270. <analyzer>
  271. <tokenizer class="solr.StandardTokenizerFactory"/>
  272. <filter class="solr.LowerCaseFilterFactory"/>
  273. <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
  274. <filter class="solr.SpanishLightStemFilterFactory"/>
  275. <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
  276. </analyzer>
  277. </fieldType>
  278. <!-- Basque -->
  279. <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
  280. <analyzer>
  281. <tokenizer class="solr.StandardTokenizerFactory"/>
  282. <filter class="solr.LowerCaseFilterFactory"/>
  283. <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" />
  284. <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
  285. </analyzer>
  286. </fieldType>
  287. <!-- Persian -->
  288. <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
  289. <analyzer>
  290. <!-- for ZWNJ -->
  291. <charFilter class="solr.PersianCharFilterFactory"/>
  292. <tokenizer class="solr.StandardTokenizerFactory"/>
  293. <filter class="solr.LowerCaseFilterFactory"/>
  294. <filter class="solr.ArabicNormalizationFilterFactory"/>
  295. <filter class="solr.PersianNormalizationFilterFactory"/>
  296. <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" />
  297. </analyzer>
  298. </fieldType>
  299. <!-- Finnish -->
  300. <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
  301. <analyzer>
  302. <tokenizer class="solr.StandardTokenizerFactory"/>
  303. <filter class="solr.LowerCaseFilterFactory"/>
  304. <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
  305. <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
  306. <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
  307. </analyzer>
  308. </fieldType>
  309. <!-- French -->
  310. <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
  311. <analyzer>
  312. <tokenizer class="solr.StandardTokenizerFactory"/>
  313. <!-- removes l', etc -->
  314. <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
  315. <filter class="solr.LowerCaseFilterFactory"/>
  316. <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
  317. <filter class="solr.FrenchLightStemFilterFactory"/>
  318. <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
  319. <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
  320. </analyzer>
  321. </fieldType>
  322. <!-- Irish -->
  323. <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
  324. <analyzer>
  325. <tokenizer class="solr.StandardTokenizerFactory"/>
  326. <!-- removes d', etc -->
  327. <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
  328. <!-- removes n-, etc. position increments is intentionally false! -->
  329. <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
  330. <filter class="solr.IrishLowerCaseFilterFactory"/>
  331. <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/>
  332. <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
  333. </analyzer>
  334. </fieldType>
  335. <!-- Galician -->
  336. <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
  337. <analyzer>
  338. <tokenizer class="solr.StandardTokenizerFactory"/>
  339. <filter class="solr.LowerCaseFilterFactory"/>
  340. <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" />
  341. <filter class="solr.GalicianStemFilterFactory"/>
  342. <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
  343. </analyzer>
  344. </fieldType>
  345. <!-- Hindi -->
  346. <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
  347. <analyzer>
  348. <tokenizer class="solr.StandardTokenizerFactory"/>
  349. <filter class="solr.LowerCaseFilterFactory"/>
  350. <!-- normalizes unicode representation -->
  351. <filter class="solr.IndicNormalizationFilterFactory"/>
  352. <!-- normalizes variation in spelling -->
  353. <filter class="solr.HindiNormalizationFilterFactory"/>
  354. <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
  355. <filter class="solr.HindiStemFilterFactory"/>
  356. </analyzer>
  357. </fieldType>
  358. <!-- Hungarian -->
  359. <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
  360. <analyzer>
  361. <tokenizer class="solr.StandardTokenizerFactory"/>
  362. <filter class="solr.LowerCaseFilterFactory"/>
  363. <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
  364. <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
  365. </analyzer>
  366. </fieldType>
  367. <!-- Armenian -->
  368. <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
  369. <analyzer>
  370. <tokenizer class="solr.StandardTokenizerFactory"/>
  371. <filter class="solr.LowerCaseFilterFactory"/>
  372. <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" />
  373. <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
  374. </analyzer>
  375. </fieldType>
  376. <!-- Indonesian -->
  377. <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
  378. <analyzer>
  379. <tokenizer class="solr.StandardTokenizerFactory"/>
  380. <filter class="solr.LowerCaseFilterFactory"/>
  381. <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" />
  382. <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
  383. <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
  384. </analyzer>
  385. </fieldType>
  386. <!-- Italian -->
  387. <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
  388. <analyzer>
  389. <tokenizer class="solr.StandardTokenizerFactory"/>
  390. <!-- removes l', etc -->
  391. <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
  392. <filter class="solr.LowerCaseFilterFactory"/>
  393. <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
  394. <filter class="solr.ItalianLightStemFilterFactory"/>
  395. <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
  396. </analyzer>
  397. </fieldType>
  398. <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
  399. <analyzer>
  400. <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
  401. <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
  402. <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
  403. <filter class="solr.JapaneseBaseFormFilterFactory"/>
  404. <!-- Removes tokens with certain part-of-speech tags -->
  405. <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
  406. <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
  407. <filter class="solr.CJKWidthFilterFactory"/>
  408. <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
  409. <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" />
  410. <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
  411. <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
  412. <!-- Lower-cases romaji characters -->
  413. <filter class="solr.LowerCaseFilterFactory"/>
  414. </analyzer>
  415. </fieldType>
  416. <!-- Latvian -->
  417. <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
  418. <analyzer>
  419. <tokenizer class="solr.StandardTokenizerFactory"/>
  420. <filter class="solr.LowerCaseFilterFactory"/>
  421. <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" />
  422. <filter class="solr.LatvianStemFilterFactory"/>
  423. </analyzer>
  424. </fieldType>
  425. <!-- Dutch -->
  426. <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
  427. <analyzer>
  428. <tokenizer class="solr.StandardTokenizerFactory"/>
  429. <filter class="solr.LowerCaseFilterFactory"/>
  430. <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
  431. <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
  432. <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
  433. </analyzer>
  434. </fieldType>
  435. <!-- Norwegian -->
  436. <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
  437. <analyzer>
  438. <tokenizer class="solr.StandardTokenizerFactory"/>
  439. <filter class="solr.LowerCaseFilterFactory"/>
  440. <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
  441. <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
  442. <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory" variant="nb"/> -->
  443. <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory" variant="nb"/> -->
  444. <!-- The "light" and "minimal" stemmers support variants: nb=Bokmål, nn=Nynorsk, no=Both -->
  445. </analyzer>
  446. </fieldType>
  447. <!-- Portuguese -->
  448. <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
  449. <analyzer>
  450. <tokenizer class="solr.StandardTokenizerFactory"/>
  451. <filter class="solr.LowerCaseFilterFactory"/>
  452. <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
  453. <filter class="solr.PortugueseLightStemFilterFactory"/>
  454. <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
  455. <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
  456. <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
  457. </analyzer>
  458. </fieldType>
  459. <!-- Romanian -->
  460. <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
  461. <analyzer>
  462. <tokenizer class="solr.StandardTokenizerFactory"/>
  463. <filter class="solr.LowerCaseFilterFactory"/>
  464. <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" />
  465. <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
  466. </analyzer>
  467. </fieldType>
  468. <!-- Russian -->
  469. <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
  470. <analyzer>
  471. <tokenizer class="solr.StandardTokenizerFactory"/>
  472. <filter class="solr.LowerCaseFilterFactory"/>
  473. <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
  474. <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
  475. <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
  476. </analyzer>
  477. </fieldType>
  478. <!-- Swedish -->
  479. <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
  480. <analyzer>
  481. <tokenizer class="solr.StandardTokenizerFactory"/>
  482. <filter class="solr.LowerCaseFilterFactory"/>
  483. <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
  484. <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
  485. <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
  486. </analyzer>
  487. </fieldType>
  488. <!-- Turkish -->
  489. <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
  490. <analyzer>
  491. <tokenizer class="solr.StandardTokenizerFactory"/>
  492. <filter class="solr.TurkishLowerCaseFilterFactory"/>
  493. <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
  494. <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
  495. </analyzer>
  496. </fieldType>
  497. </types>
  498. </schema>