- Timestamp:
- 2015-06-30T19:17:36+12:00 (9 years ago)
- File:
-
- 1 edited
Legend:
- Unmodified
- Added
- Removed
-
gs3-extensions/solr/trunk/src/collect/solr-jdbm-demo/etc/conf/schema.xml
r28092 r30001 46 46 --> 47 47 48 <schema name="example" version="1. 4">48 <schema name="example" version="1.5"> 49 49 <!-- attribute "name" is the name of this schema and is only used for display purposes. 50 Applications should change this to reflect the nature of the search collection. 51 version="1.4" is Solr's version number for the schema syntax and semantics. It should 52 not normally be changed by applications. 53 1.0: multiValued attribute did not exist, all fields are multiValued by nature 50 version="x.y" is Solr's version number for the schema syntax and 51 semantics. It should not normally be changed by applications. 52 53 1.0: multiValued attribute did not exist, all fields are multiValued 54 by nature 54 55 1.1: multiValued attribute introduced, false by default 55 1.2: omitTermFreqAndPositions attribute introduced, true by default except for text fields. 56 1.2: omitTermFreqAndPositions attribute introduced, true by default 57 except for text fields. 56 58 1.3: removed optional field compress feature 57 1.4: default auto-phrase (QueryParser feature) to off 59 1.4: autoGeneratePhraseQueries attribute introduced to drive QueryParser 60 behavior when a single string produces multiple tokens. Defaults 61 to off for version >= 1.4 62 1.5: omitNorms defaults to true for primitive field types 63 (int, float, boolean, string...) 58 64 --> 59 65 66 <fields> 67 <!-- Valid attributes for fields: 68 name: mandatory - the name for the field 69 type: mandatory - the name of a field type from the 70 <types> fieldType section 71 indexed: true if this field should be indexed (searchable or sortable) 72 stored: true if this field should be retrievable 73 docValues: true if this field should have doc values. Doc values are 74 useful for faceting, grouping, sorting and function queries. Although not 75 required, doc values will make the index faster to load, more 76 NRT-friendly and more memory-efficient. They however come with some 77 limitations: they are currently only supported by StrField, UUIDField 78 and all Trie*Fields, and depending on the field type, they might 79 require the field to be single-valued, be required or have a default 80 value (check the documentation of the field type you're interested in 81 for more information) 82 multiValued: true if this field may contain multiple values per document 83 omitNorms: (expert) set to true to omit the norms associated with 84 this field (this disables length normalization and index-time 85 boosting for the field, and saves some memory). Only full-text 86 fields or fields that need an index-time boost need norms. 87 Norms are omitted for primitive (non-analyzed) types by default. 88 termVectors: [false] set to true to store the term vector for a 89 given field. 90 When using MoreLikeThis, fields used for similarity should be 91 stored for best performance. 92 termPositions: Store position information with the term vector. 93 This will increase storage costs. 94 termOffsets: Store offset information with the term vector. This 95 will increase storage costs. 96 required: The field is required. It will throw an error if the 97 value does not exist 98 default: a value that should be used if no value is specified 99 when adding a document. 100 --> 101 102 <!-- field names should consist of alphanumeric or underscore characters only and 103 not start with a digit. This is not currently strictly enforced, 104 but other field names will not have first class support from all components 105 and back compatibility is not guaranteed. Names with both leading and 106 trailing underscores (e.g. _version_) are reserved. 107 --> 108 109 <!-- If you remove this field, you must _also_ disable the update log in solrconfig.xml 110 or Solr won't start. _version_ and update log are required for SolrCloud 111 --> 112 113 <field name="docOID" type="string" indexed="true" stored="true" required="true" /> 114 115 <field name="ZZ" type="text_en_splitting" indexed="true" stored="false" multiValued="true" /> 116 <field name="TX" type="text_en_splitting" indexed="true" stored="false" multiValued="true" /> 117 <field name="TI" type="text_en_splitting" indexed="true" stored="false" multiValued="true" /> 118 <field name="SU" type="text_en_splitting" indexed="true" stored="false" multiValued="true" /> 119 <field name="ORG" type="text_en_splitting" indexed="true" stored="false" multiValued="true" /> 120 121 122 <field name="_version_" type="long" indexed="true" stored="true"/> 123 124 <!-- points to the root document of a block of nested documents. Required for nested 125 document support, may be removed otherwise 126 --> 127 <field name="_root_" type="string" indexed="true" stored="false"/> 128 129 <!-- Only remove the "id" field if you have a very good reason to. While not strictly 130 required, it is highly recommended. A <uniqueKey> is present in almost all Solr 131 installations. See the <uniqueKey> declaration below where <uniqueKey> is set to "id". 132 --> 133 <!-- 134 <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" /> 135 --> 136 137 <!-- 138 <field name="sku" type="text_en_splitting_tight" indexed="true" stored="true" omitNorms="true"/> 139 <field name="name" type="text_general" indexed="true" stored="true"/> 140 <field name="manu" type="text_general" indexed="true" stored="true" omitNorms="true"/> 141 <field name="cat" type="string" indexed="true" stored="true" multiValued="true"/> 142 <field name="features" type="text_general" indexed="true" stored="true" multiValued="true"/> 143 <field name="includes" type="text_general" indexed="true" stored="true" termVectors="true" termPositions="true" termOffsets="true" /> 144 145 <field name="weight" type="float" indexed="true" stored="true"/> 146 <field name="price" type="float" indexed="true" stored="true"/> 147 <field name="popularity" type="int" indexed="true" stored="true" /> 148 <field name="inStock" type="boolean" indexed="true" stored="true" /> 149 --> 150 <field name="store" type="location" indexed="true" stored="true"/> 151 152 <!-- Common metadata fields, named specifically to match up with 153 SolrCell metadata when parsing rich documents such as Word, PDF. 154 Some fields are multiValued only because Tika currently may return 155 multiple values for them. Some metadata is parsed from the documents, 156 but there are some which come from the client context: 157 "content_type": From the HTTP headers of incoming stream 158 "resourcename": From SolrCell request param resource.name 159 --> 160 161 <!-- 162 <field name="title" type="text_general" indexed="true" stored="true" multiValued="true"/> 163 <field name="subject" type="text_general" indexed="true" stored="true"/> 164 <field name="description" type="text_general" indexed="true" stored="true"/> 165 <field name="comments" type="text_general" indexed="true" stored="true"/> 166 <field name="author" type="text_general" indexed="true" stored="true"/> 167 <field name="keywords" type="text_general" indexed="true" stored="true"/> 168 <field name="category" type="text_general" indexed="true" stored="true"/> 169 <field name="resourcename" type="text_general" indexed="true" stored="true"/> 170 <field name="url" type="text_general" indexed="true" stored="true"/> 171 <field name="content_type" type="string" indexed="true" stored="true" multiValued="true"/> 172 <field name="last_modified" type="date" indexed="true" stored="true"/> 173 <field name="links" type="string" indexed="true" stored="true" multiValued="true"/> 174 --> 175 176 <!-- Main body of document extracted by SolrCell. 177 NOTE: This field is not indexed by default, since it is also copied to "text" 178 using copyField below. This is to save space. Use this field for returning and 179 highlighting document content. Use the "text" field to search the content. --> 180 <field name="content" type="text_general" indexed="false" stored="true" multiValued="true"/> 181 182 183 <!-- catchall field, containing all other searchable text fields (implemented 184 via copyField further on in this schema --> 185 <field name="text" type="text_general" indexed="true" stored="false" multiValued="true"/> 186 187 <!-- catchall text field that indexes tokens both normally and in reverse for efficient 188 leading wildcard queries. --> 189 <field name="text_rev" type="text_general_rev" indexed="true" stored="false" multiValued="true"/> 190 191 <!-- non-tokenized version of manufacturer to make it easier to sort or group 192 results by manufacturer. copied from "manu" via copyField --> 193 <field name="manu_exact" type="string" indexed="true" stored="false"/> 194 195 <field name="payloads" type="payloads" indexed="true" stored="true"/> 196 197 198 <!-- 199 Some fields such as popularity and manu_exact could be modified to 200 leverage doc values: 201 <field name="popularity" type="int" indexed="true" stored="true" docValues="true" /> 202 <field name="manu_exact" type="string" indexed="false" stored="false" docValues="true" /> 203 <field name="cat" type="string" indexed="true" stored="true" docValues="true" multiValued="true"/> 204 205 206 Although it would make indexing slightly slower and the index bigger, it 207 would also make the index faster to load, more memory-efficient and more 208 NRT-friendly. 209 --> 210 211 <!-- Dynamic field definitions allow using convention over configuration 212 for fields via the specification of patterns to match field names. 213 EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i) 214 RESTRICTION: the glob-like pattern in the name attribute must have 215 a "*" only at the start or the end. --> 216 217 <dynamicField name="*_i" type="int" indexed="true" stored="true"/> 218 <dynamicField name="*_is" type="int" indexed="true" stored="true" multiValued="true"/> 219 <dynamicField name="*_s" type="string" indexed="true" stored="true" /> 220 <dynamicField name="*_ss" type="string" indexed="true" stored="true" multiValued="true"/> 221 <dynamicField name="*_l" type="long" indexed="true" stored="true"/> 222 <dynamicField name="*_ls" type="long" indexed="true" stored="true" multiValued="true"/> 223 <dynamicField name="*_t" type="text_general" indexed="true" stored="true"/> 224 <dynamicField name="*_txt" type="text_general" indexed="true" stored="true" multiValued="true"/> 225 <dynamicField name="*_en" type="text_en" indexed="true" stored="true" multiValued="true"/> 226 <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/> 227 <dynamicField name="*_bs" type="boolean" indexed="true" stored="true" multiValued="true"/> 228 <dynamicField name="*_f" type="float" indexed="true" stored="true"/> 229 <dynamicField name="*_fs" type="float" indexed="true" stored="true" multiValued="true"/> 230 <dynamicField name="*_d" type="double" indexed="true" stored="true"/> 231 <dynamicField name="*_ds" type="double" indexed="true" stored="true" multiValued="true"/> 232 233 <!-- Type used to index the lat and lon components for the "location" FieldType --> 234 <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false" /> 235 236 <dynamicField name="*_dt" type="date" indexed="true" stored="true"/> 237 <dynamicField name="*_dts" type="date" indexed="true" stored="true" multiValued="true"/> 238 <dynamicField name="*_p" type="location" indexed="true" stored="true"/> 239 240 <!-- some trie-coded dynamic fields for faster range queries --> 241 <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/> 242 <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/> 243 <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/> 244 <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/> 245 <dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/> 246 247 <dynamicField name="*_pi" type="pint" indexed="true" stored="true"/> 248 <dynamicField name="*_c" type="currency" indexed="true" stored="true"/> 249 250 <dynamicField name="ignored_*" type="ignored" multiValued="true"/> 251 <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/> 252 253 <dynamicField name="random_*" type="random" /> 254 255 <!-- dynamic field for sort/facet fields, which are strings by default. ie not tokenised --> 256 <dynamicField name="by*" type="string" indexed="true" stored="false" multiValued="false" /> 257 258 <!-- uncomment the following to ignore any fields that don't already match an existing 259 field name or dynamic field, rather than reporting them as an error. 260 alternately, change the type="ignored" to some other type e.g. "text" if you want 261 unknown fields indexed and/or stored by default --> 262 <!--dynamicField name="*" type="ignored" multiValued="true" /--> 263 264 </fields> 265 266 267 <!-- Field to use to determine and enforce document uniqueness. 268 Unless this field is marked with required="false", it will be a required field 269 --> 270 <uniqueKey>docOID</uniqueKey> 271 272 <!-- DEPRECATED: The defaultSearchField is consulted by various query parsers when 273 parsing a query string that isn't explicit about the field. Machine (non-user) 274 generated queries are best made explicit, or they can use the "df" request parameter 275 which takes precedence over this. 276 Note: Un-commenting defaultSearchField will be insufficient if your request handler 277 in solrconfig.xml defines "df", which takes precedence. That would need to be removed. 278 <defaultSearchField>text</defaultSearchField> --> 279 280 <!-- DEPRECATED: The defaultOperator (AND|OR) is consulted by various query parsers 281 when parsing a query string to determine if a clause of the query should be marked as 282 required or optional, assuming the clause isn't already marked by some operator. 283 The default is OR, which is generally assumed so it is not a good idea to change it 284 globally here. The "q.op" request parameter takes precedence over this. 285 <solrQueryParser defaultOperator="OR"/> --> 286 287 <!-- copyField commands copy one field to another at the time a document 288 is added to the index. It's used either to index the same field differently, 289 or to add multiple fields to the same field for easier/faster searching. --> 290 <!-- 291 <copyField source="cat" dest="text"/> 292 <copyField source="name" dest="text"/> 293 <copyField source="manu" dest="text"/> 294 <copyField source="features" dest="text"/> 295 <copyField source="includes" dest="text"/> 296 <copyField source="manu" dest="manu_exact"/> 297 --> 298 299 <!-- Copy the price into a currency enabled field (default USD) --> 300 <!-- 301 <copyField source="price" dest="price_c"/> 302 --> 303 304 <!-- Text fields from SolrCell to search by default in our catch-all field --> 305 <!-- 306 <copyField source="title" dest="text"/> 307 <copyField source="author" dest="text"/> 308 <copyField source="description" dest="text"/> 309 <copyField source="keywords" dest="text"/> 310 <copyField source="content" dest="text"/> 311 <copyField source="content_type" dest="text"/> 312 <copyField source="resourcename" dest="text"/> 313 <copyField source="url" dest="text"/> 314 --> 315 316 <!-- Create a string version of author for faceting --> 317 <!-- 318 <copyField source="author" dest="author_s"/> 319 --> 320 321 <!-- Above, multiple source fields are copied to the [text] field. 322 Another way to map multiple source fields to the same 323 destination field is to use the dynamic field syntax. 324 copyField also supports a maxChars to copy setting. --> 325 326 <!-- <copyField source="*_t" dest="text" maxChars="3000"/> --> 327 328 <!-- copy name to alphaNameSort, a field designed for sorting by name --> 329 <!-- <copyField source="name" dest="alphaNameSort"/> --> 330 60 331 <types> 61 332 <!-- field type definitions. The "name" attribute is … … 63 334 attribute and any other attributes determine the real 64 335 behavior of the fieldType. 65 Class names starting with "solr" refer to java classes in the66 org.apache.solr.analysis package.336 Class names starting with "solr" refer to java classes in a 337 standard package such as org.apache.solr.analysis 67 338 --> 68 339 69 <!-- The StrField type is not analyzed, but indexed/stored verbatim. --> 70 <fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/> 340 <!-- The StrField type is not analyzed, but indexed/stored verbatim. 341 It supports doc values but in that case the field needs to be 342 single-valued and either required or have a default value. 343 --> 344 <fieldType name="string" class="solr.StrField" sortMissingLast="true" /> 71 345 72 346 <!-- boolean type: "true" or "false" --> 73 <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>74 <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings --> 75 < fieldtype name="binary" class="solr.BinaryField"/>76 77 <!-- The optional sortMissingLast and sortMissingFirst attributes are78 currently supported on types that are sorted internally as strings. 79 This includes "string","boolean","sint","slong","sfloat","sdouble","pdate"347 <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/> 348 349 <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are 350 currently supported on types that are sorted internally as strings 351 and on numeric types. 352 This includes "string","boolean", and, as of 3.5 (and 4.x), 353 int, float, long, date, double, including the "Trie" variants. 80 354 - If sortMissingLast="true", then a sort on this field will cause documents 81 355 without the field to come after documents with the field, … … 91 365 <!-- 92 366 Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types. 367 368 These fields support doc values, but they require the field to be 369 single-valued and either be required or have a default value. 93 370 --> 94 <fieldType name="int" class="solr.TrieIntField" precisionStep="0" omitNorms="true"positionIncrementGap="0"/>95 <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" omitNorms="true"positionIncrementGap="0"/>96 <fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true"positionIncrementGap="0"/>97 <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true"positionIncrementGap="0"/>371 <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/> 372 <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/> 373 <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/> 374 <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/> 98 375 99 376 <!-- … … 107 384 A precisionStep of 0 disables indexing at different precision levels. 108 385 --> 109 <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" omitNorms="true"positionIncrementGap="0"/>110 <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" omitNorms="true"positionIncrementGap="0"/>111 <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" omitNorms="true"positionIncrementGap="0"/>112 <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" omitNorms="true"positionIncrementGap="0"/>386 <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/> 387 <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/> 388 <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/> 389 <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/> 113 390 114 391 <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and … … 134 411 Note: For faster range queries, consider the tdate type 135 412 --> 136 <fieldType name="date" class="solr.TrieDateField" omitNorms="true"precisionStep="0" positionIncrementGap="0"/>413 <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/> 137 414 138 415 <!-- A Trie based date field for faster date range queries and date faceting. --> 139 <fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" precisionStep="6" positionIncrementGap="0"/> 140 416 <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/> 417 418 419 <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings --> 420 <fieldtype name="binary" class="solr.BinaryField"/> 141 421 142 422 <!-- 143 423 Note: 144 These should only be used for compatibility with existing indexes (created with older Solr versions)145 or if "sortMissingFirst" or "sortMissingLast" functionality is needed. Use Trie based fields instead.146 424 These should only be used for compatibility with existing indexes (created with lucene or older Solr versions). 425 Use Trie based fields instead. As of Solr 3.5 and 4.x, Trie based fields support sortMissingFirst/Last 426 147 427 Plain numeric field types that store and index the text 148 value verbatim (and hence don't support range queries, since the428 value verbatim (and hence don't correctly support range queries, since the 149 429 lexicographic ordering isn't equal to the numeric ordering) 150 430 --> 151 <fieldType name="pint" class="solr.IntField" omitNorms="true"/> 152 <fieldType name="plong" class="solr.LongField" omitNorms="true"/> 153 <fieldType name="pfloat" class="solr.FloatField" omitNorms="true"/> 154 <fieldType name="pdouble" class="solr.DoubleField" omitNorms="true"/> 155 <fieldType name="pdate" class="solr.DateField" sortMissingLast="true" omitNorms="true"/> 156 157 158 <!-- 159 Note: 160 These should only be used for compatibility with existing indexes (created with older Solr versions) 161 or if "sortMissingFirst" or "sortMissingLast" functionality is needed. Use Trie based fields instead. 162 163 Numeric field types that manipulate the value into 164 a string value that isn't human-readable in its internal form, 165 but with a lexicographic ordering the same as the numeric ordering, 166 so that range queries work correctly. 167 --> 168 <fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/> 169 <fieldType name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/> 170 <fieldType name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/> 171 <fieldType name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/> 172 431 <fieldType name="pint" class="solr.IntField"/> 432 <fieldType name="plong" class="solr.LongField"/> 433 <fieldType name="pfloat" class="solr.FloatField"/> 434 <fieldType name="pdouble" class="solr.DoubleField"/> 435 <fieldType name="pdate" class="solr.DateField" sortMissingLast="true"/> 173 436 174 437 <!-- The "RandomSortField" is not used to store or search any 175 438 data. You can declare fields of this type it in your schema 176 439 to generate pseudo-random orderings of your docs for sorting 177 purposes. The ordering is generated based on the field name178 and the version of the index,As long as the index version440 or function purposes. The ordering is generated based on the field 441 name and the version of the index. As long as the index version 179 442 remains unchanged, and the same field name is reused, 180 443 the ordering of the docs will be consistent. 181 444 If you want different psuedo-random orderings of documents, 182 445 for the same version of the index, use a dynamicField and 183 change the name446 change the field name in the request. 184 447 --> 185 448 <fieldType name="random" class="solr.RandomSortField" indexed="true" /> … … 198 461 199 462 <!-- One can also specify an existing Analyzer class that has a 200 default constructor via the class attribute on the analyzer element 463 default constructor via the class attribute on the analyzer element. 464 Example: 201 465 <fieldType name="text_greek" class="solr.TextField"> 202 466 <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/> … … 219 483 <analyzer type="index"> 220 484 <tokenizer class="solr.StandardTokenizerFactory"/> 221 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true"/>485 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" /> 222 486 <!-- in this example, we will only use synonyms at query time 223 487 <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/> … … 227 491 <analyzer type="query"> 228 492 <tokenizer class="solr.StandardTokenizerFactory"/> 229 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true"/>493 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" /> 230 494 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> 231 495 <filter class="solr.LowerCaseFilterFactory"/> … … 235 499 <!-- A text field with defaults appropriate for English: it 236 500 tokenizes with StandardTokenizer, removes English stop words 237 ( stopwords_en.txt), down cases, protects words from protwords.txt, and501 (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and 238 502 finally applies Porter's stemming. The query time analyzer 239 503 also applies synonyms from synonyms.txt. --> … … 245 509 --> 246 510 <!-- Case insensitive stop word removal. 247 add enablePositionIncrements=true in both the index and query248 analyzers to leave a 'gap' for more accurate phrase queries.249 511 --> 250 512 <filter class="solr.StopFilterFactory" 251 513 ignoreCase="true" 252 words="stopwords_en.txt" 253 enablePositionIncrements="true" 514 words="lang/stopwords_en.txt" 254 515 /> 255 516 <filter class="solr.LowerCaseFilterFactory"/> … … 259 520 <filter class="solr.EnglishMinimalStemFilterFactory"/> 260 521 --> 261 <filter class="solr.PorterStemFilterFactory"/> 522 <!--<filter class="solr.PorterStemFilterFactory"/>--> 523 <filter class="solr.EnglishMinimalStemFilterFactory"/> 262 524 </analyzer> 263 525 <analyzer type="query"> … … 266 528 <filter class="solr.StopFilterFactory" 267 529 ignoreCase="true" 268 words="stopwords_en.txt" 269 enablePositionIncrements="true" 530 words="lang/stopwords_en.txt" 270 531 /> 271 532 <filter class="solr.LowerCaseFilterFactory"/> … … 275 536 <filter class="solr.EnglishMinimalStemFilterFactory"/> 276 537 --> 277 <filter class="solr.PorterStemFilterFactory"/> 538 <!--<filter class="solr.PorterStemFilterFactory"/>--> 539 <filter class="solr.EnglishMinimalStemFilterFactory"/> 278 540 </analyzer> 279 541 </fieldType> … … 286 548 non-alphanumeric chars. This means certain compound word 287 549 cases will work, for example query "wi fi" will match 288 document "WiFi" or "wi-fi". However, other cases will still 289 not match, for example if the query is "wifi" and the 290 document is "wi fi" or if the query is "wi-fi" and the 291 document is "wifi". 550 document "WiFi" or "wi-fi". 292 551 --> 293 552 <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true"> … … 298 557 --> 299 558 <!-- Case insensitive stop word removal. 300 add enablePositionIncrements=true in both the index and query301 analyzers to leave a 'gap' for more accurate phrase queries.302 559 --> 303 560 <filter class="solr.StopFilterFactory" 304 561 ignoreCase="true" 305 words="stopwords_en.txt" 306 enablePositionIncrements="true" 562 words="lang/stopwords_en.txt" 307 563 /> 308 564 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/> 309 565 <filter class="solr.LowerCaseFilterFactory"/> 310 566 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> 311 <filter class="solr.PorterStemFilterFactory"/> 567 <!--<filter class="solr.PorterStemFilterFactory"/>--> 568 <filter class="solr.EnglishMinimalStemFilterFactory"/> 312 569 </analyzer> 313 570 <analyzer type="query"> … … 316 573 <filter class="solr.StopFilterFactory" 317 574 ignoreCase="true" 318 words="stopwords_en.txt" 319 enablePositionIncrements="true" 575 words="lang/stopwords_en.txt" 320 576 /> 321 577 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/> 322 578 <filter class="solr.LowerCaseFilterFactory"/> 323 579 <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> 324 <filter class="solr.PorterStemFilterFactory"/> 580 <!--<filter class="solr.PorterStemFilterFactory"/>--> 581 <filter class="solr.EnglishMinimalStemFilterFactory"/> 325 582 </analyzer> 326 583 </fieldType> … … 332 589 <tokenizer class="solr.WhitespaceTokenizerFactory"/> 333 590 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/> 334 <filter class="solr.StopFilterFactory" ignoreCase="true" words=" stopwords_en.txt"/>591 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/> 335 592 <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/> 336 593 <filter class="solr.LowerCaseFilterFactory"/> … … 348 605 <analyzer type="index"> 349 606 <tokenizer class="solr.StandardTokenizerFactory"/> 350 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true"/>607 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" /> 351 608 <filter class="solr.LowerCaseFilterFactory"/> 352 609 <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true" … … 356 613 <tokenizer class="solr.StandardTokenizerFactory"/> 357 614 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> 358 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true"/>615 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" /> 359 616 <filter class="solr.LowerCaseFilterFactory"/> 360 617 </analyzer> … … 396 653 information on pattern and replacement string syntax. 397 654 398 http://java.sun.com/j2se/1. 5.0/docs/api/java/util/regex/package-summary.html655 http://java.sun.com/j2se/1.6.0/docs/api/java/util/regex/package-summary.html 399 656 --> 400 657 <filter class="solr.PatternReplaceFilterFactory" … … 437 694 </fieldType> 438 695 439 <fieldType name="text_path" class="solr.TextField" positionIncrementGap="100"> 440 <analyzer> 441 <tokenizer class="solr.PathHierarchyTokenizerFactory"/> 696 <!-- 697 Example of using PathHierarchyTokenizerFactory at index time, so 698 queries for paths match documents at that path, or in descendent paths 699 --> 700 <fieldType name="descendent_path" class="solr.TextField"> 701 <analyzer type="index"> 702 <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" /> 703 </analyzer> 704 <analyzer type="query"> 705 <tokenizer class="solr.KeywordTokenizerFactory" /> 706 </analyzer> 707 </fieldType> 708 <!-- 709 Example of using PathHierarchyTokenizerFactory at query time, so 710 queries for paths match documents at that path, or in ancestor paths 711 --> 712 <fieldType name="ancestor_path" class="solr.TextField"> 713 <analyzer type="index"> 714 <tokenizer class="solr.KeywordTokenizerFactory" /> 715 </analyzer> 716 <analyzer type="query"> 717 <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" /> 442 718 </analyzer> 443 719 </fieldType> … … 463 739 <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/> 464 740 465 <!-- 466 A Geohash is a compact representation of a latitude longitude pair in a single field. 467 See http://wiki.apache.org/solr/SpatialSearch 741 <!-- An alternative geospatial field type new to Solr 4. It supports multiValued and polygon shapes. 742 For more information about this and other Spatial fields new to Solr 4, see: 743 http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4 744 --> 745 <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType" 746 geo="true" distErrPct="0.025" maxDistErr="0.000009" units="degrees" /> 747 748 <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType 749 Parameters: 750 defaultCurrency: Specifies the default currency if none specified. Defaults to "USD" 751 precisionStep: Specifies the precisionStep for the TrieLong field used for the amount 752 providerClass: Lets you plug in other exchange provider backend: 753 solr.FileExchangeRateProvider is the default and takes one parameter: 754 currencyConfig: name of an xml file holding exchange rates 755 solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org: 756 ratesFileLocation: URL or path to rates JSON file (default latest.json on the web) 757 refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60) 468 758 --> 469 <fieldtype name="geohash" class="solr.GeoHashField"/> 759 <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" /> 760 761 762 763 <!-- some examples for different languages (generally ordered by ISO code) --> 764 765 <!-- Arabic --> 766 <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100"> 767 <analyzer> 768 <tokenizer class="solr.StandardTokenizerFactory"/> 769 <!-- for any non-arabic --> 770 <filter class="solr.LowerCaseFilterFactory"/> 771 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" /> 772 <!-- normalizes ﻯ to ï»±, etc --> 773 <filter class="solr.ArabicNormalizationFilterFactory"/> 774 <filter class="solr.ArabicStemFilterFactory"/> 775 </analyzer> 776 </fieldType> 777 778 <!-- Bulgarian --> 779 <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100"> 780 <analyzer> 781 <tokenizer class="solr.StandardTokenizerFactory"/> 782 <filter class="solr.LowerCaseFilterFactory"/> 783 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" /> 784 <filter class="solr.BulgarianStemFilterFactory"/> 785 </analyzer> 786 </fieldType> 787 788 <!-- Catalan --> 789 <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100"> 790 <analyzer> 791 <tokenizer class="solr.StandardTokenizerFactory"/> 792 <!-- removes l', etc --> 793 <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/> 794 <filter class="solr.LowerCaseFilterFactory"/> 795 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" /> 796 <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/> 797 </analyzer> 798 </fieldType> 799 800 <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) --> 801 <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100"> 802 <analyzer> 803 <tokenizer class="solr.StandardTokenizerFactory"/> 804 <!-- normalize width before bigram, as e.g. half-width dakuten combine --> 805 <filter class="solr.CJKWidthFilterFactory"/> 806 <!-- for any non-CJK --> 807 <filter class="solr.LowerCaseFilterFactory"/> 808 <filter class="solr.CJKBigramFilterFactory"/> 809 </analyzer> 810 </fieldType> 811 812 <!-- Kurdish --> 813 <fieldType name="text_ckb" class="solr.TextField" positionIncrementGap="100"> 814 <analyzer> 815 <tokenizer class="solr.StandardTokenizerFactory"/> 816 <filter class="solr.SoraniNormalizationFilterFactory"/> 817 <!-- for any latin text --> 818 <filter class="solr.LowerCaseFilterFactory"/> 819 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ckb.txt"/> 820 <filter class="solr.SoraniStemFilterFactory"/> 821 </analyzer> 822 </fieldType> 823 824 <!-- Czech --> 825 <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100"> 826 <analyzer> 827 <tokenizer class="solr.StandardTokenizerFactory"/> 828 <filter class="solr.LowerCaseFilterFactory"/> 829 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" /> 830 <filter class="solr.CzechStemFilterFactory"/> 831 </analyzer> 832 </fieldType> 833 834 <!-- Danish --> 835 <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100"> 836 <analyzer> 837 <tokenizer class="solr.StandardTokenizerFactory"/> 838 <filter class="solr.LowerCaseFilterFactory"/> 839 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" /> 840 <filter class="solr.SnowballPorterFilterFactory" language="Danish"/> 841 </analyzer> 842 </fieldType> 843 844 <!-- German --> 845 <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100"> 846 <analyzer> 847 <tokenizer class="solr.StandardTokenizerFactory"/> 848 <filter class="solr.LowerCaseFilterFactory"/> 849 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" /> 850 <filter class="solr.GermanNormalizationFilterFactory"/> 851 <filter class="solr.GermanLightStemFilterFactory"/> 852 <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> --> 853 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> --> 854 </analyzer> 855 </fieldType> 856 857 <!-- Greek --> 858 <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100"> 859 <analyzer> 860 <tokenizer class="solr.StandardTokenizerFactory"/> 861 <!-- greek specific lowercase for sigma --> 862 <filter class="solr.GreekLowerCaseFilterFactory"/> 863 <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" /> 864 <filter class="solr.GreekStemFilterFactory"/> 865 </analyzer> 866 </fieldType> 867 868 <!-- Spanish --> 869 <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100"> 870 <analyzer> 871 <tokenizer class="solr.StandardTokenizerFactory"/> 872 <filter class="solr.LowerCaseFilterFactory"/> 873 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" /> 874 <filter class="solr.SpanishLightStemFilterFactory"/> 875 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> --> 876 </analyzer> 877 </fieldType> 878 879 <!-- Basque --> 880 <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100"> 881 <analyzer> 882 <tokenizer class="solr.StandardTokenizerFactory"/> 883 <filter class="solr.LowerCaseFilterFactory"/> 884 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" /> 885 <filter class="solr.SnowballPorterFilterFactory" language="Basque"/> 886 </analyzer> 887 </fieldType> 888 889 <!-- Persian --> 890 <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100"> 891 <analyzer> 892 <!-- for ZWNJ --> 893 <charFilter class="solr.PersianCharFilterFactory"/> 894 <tokenizer class="solr.StandardTokenizerFactory"/> 895 <filter class="solr.LowerCaseFilterFactory"/> 896 <filter class="solr.ArabicNormalizationFilterFactory"/> 897 <filter class="solr.PersianNormalizationFilterFactory"/> 898 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" /> 899 </analyzer> 900 </fieldType> 901 902 <!-- Finnish --> 903 <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100"> 904 <analyzer> 905 <tokenizer class="solr.StandardTokenizerFactory"/> 906 <filter class="solr.LowerCaseFilterFactory"/> 907 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" /> 908 <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/> 909 <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> --> 910 </analyzer> 911 </fieldType> 912 913 <!-- French --> 914 <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100"> 915 <analyzer> 916 <tokenizer class="solr.StandardTokenizerFactory"/> 917 <!-- removes l', etc --> 918 <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/> 919 <filter class="solr.LowerCaseFilterFactory"/> 920 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" /> 921 <filter class="solr.FrenchLightStemFilterFactory"/> 922 <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> --> 923 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> --> 924 </analyzer> 925 </fieldType> 926 927 <!-- Irish --> 928 <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100"> 929 <analyzer> 930 <tokenizer class="solr.StandardTokenizerFactory"/> 931 <!-- removes d', etc --> 932 <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/> 933 <!-- removes n-, etc. position increments is intentionally false! --> 934 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt"/> 935 <filter class="solr.IrishLowerCaseFilterFactory"/> 936 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/> 937 <filter class="solr.SnowballPorterFilterFactory" language="Irish"/> 938 </analyzer> 939 </fieldType> 940 941 <!-- Galician --> 942 <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100"> 943 <analyzer> 944 <tokenizer class="solr.StandardTokenizerFactory"/> 945 <filter class="solr.LowerCaseFilterFactory"/> 946 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" /> 947 <filter class="solr.GalicianStemFilterFactory"/> 948 <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> --> 949 </analyzer> 950 </fieldType> 951 952 <!-- Hindi --> 953 <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100"> 954 <analyzer> 955 <tokenizer class="solr.StandardTokenizerFactory"/> 956 <filter class="solr.LowerCaseFilterFactory"/> 957 <!-- normalizes unicode representation --> 958 <filter class="solr.IndicNormalizationFilterFactory"/> 959 <!-- normalizes variation in spelling --> 960 <filter class="solr.HindiNormalizationFilterFactory"/> 961 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" /> 962 <filter class="solr.HindiStemFilterFactory"/> 963 </analyzer> 964 </fieldType> 965 966 <!-- Hungarian --> 967 <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100"> 968 <analyzer> 969 <tokenizer class="solr.StandardTokenizerFactory"/> 970 <filter class="solr.LowerCaseFilterFactory"/> 971 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" /> 972 <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/> 973 <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> --> 974 </analyzer> 975 </fieldType> 976 977 <!-- Armenian --> 978 <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100"> 979 <analyzer> 980 <tokenizer class="solr.StandardTokenizerFactory"/> 981 <filter class="solr.LowerCaseFilterFactory"/> 982 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" /> 983 <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/> 984 </analyzer> 985 </fieldType> 986 987 <!-- Indonesian --> 988 <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100"> 989 <analyzer> 990 <tokenizer class="solr.StandardTokenizerFactory"/> 991 <filter class="solr.LowerCaseFilterFactory"/> 992 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" /> 993 <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false --> 994 <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/> 995 </analyzer> 996 </fieldType> 997 998 <!-- Italian --> 999 <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100"> 1000 <analyzer> 1001 <tokenizer class="solr.StandardTokenizerFactory"/> 1002 <!-- removes l', etc --> 1003 <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/> 1004 <filter class="solr.LowerCaseFilterFactory"/> 1005 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" /> 1006 <filter class="solr.ItalianLightStemFilterFactory"/> 1007 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> --> 1008 </analyzer> 1009 </fieldType> 1010 1011 <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming) 1012 1013 NOTE: If you want to optimize search for precision, use default operator AND in your query 1014 parser config with <solrQueryParser defaultOperator="AND"/> further down in this file. Use 1015 OR if you would like to optimize for recall (default). 1016 --> 1017 <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false"> 1018 <analyzer> 1019 <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer) 1020 1021 Kuromoji has a search mode (default) that does segmentation useful for search. A heuristic 1022 is used to segment compounds into its parts and the compound itself is kept as synonym. 1023 1024 Valid values for attribute mode are: 1025 normal: regular segmentation 1026 search: segmentation useful for search with synonyms compounds (default) 1027 extended: same as search mode, but unigrams unknown words (experimental) 1028 1029 For some applications it might be good to use search mode for indexing and normal mode for 1030 queries to reduce recall and prevent parts of compounds from being matched and highlighted. 1031 Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query. 1032 1033 Kuromoji also has a convenient user dictionary feature that allows overriding the statistical 1034 model with your own entries for segmentation, part-of-speech tags and readings without a need 1035 to specify weights. Notice that user dictionaries have not been subject to extensive testing. 1036 1037 User dictionary attributes are: 1038 userDictionary: user dictionary filename 1039 userDictionaryEncoding: user dictionary encoding (default is UTF-8) 1040 1041 See lang/userdict_ja.txt for a sample user dictionary file. 1042 1043 Punctuation characters are discarded by default. Use discardPunctuation="false" to keep them. 1044 1045 See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support. 1046 --> 1047 <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/> 1048 <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>--> 1049 <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (èŸæžåœ¢) --> 1050 <filter class="solr.JapaneseBaseFormFilterFactory"/> 1051 <!-- Removes tokens with certain part-of-speech tags --> 1052 <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" /> 1053 <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) --> 1054 <filter class="solr.CJKWidthFilterFactory"/> 1055 <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking --> 1056 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" /> 1057 <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) --> 1058 <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/> 1059 <!-- Lower-cases romaji characters --> 1060 <filter class="solr.LowerCaseFilterFactory"/> 1061 </analyzer> 1062 </fieldType> 1063 1064 <!-- Latvian --> 1065 <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100"> 1066 <analyzer> 1067 <tokenizer class="solr.StandardTokenizerFactory"/> 1068 <filter class="solr.LowerCaseFilterFactory"/> 1069 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" /> 1070 <filter class="solr.LatvianStemFilterFactory"/> 1071 </analyzer> 1072 </fieldType> 1073 1074 <!-- Dutch --> 1075 <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100"> 1076 <analyzer> 1077 <tokenizer class="solr.StandardTokenizerFactory"/> 1078 <filter class="solr.LowerCaseFilterFactory"/> 1079 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" /> 1080 <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/> 1081 <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/> 1082 </analyzer> 1083 </fieldType> 1084 1085 <!-- Norwegian --> 1086 <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100"> 1087 <analyzer> 1088 <tokenizer class="solr.StandardTokenizerFactory"/> 1089 <filter class="solr.LowerCaseFilterFactory"/> 1090 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" /> 1091 <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/> 1092 <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory" variant="nb"/> --> 1093 <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory" variant="nb"/> --> 1094 <!-- The "light" and "minimal" stemmers support variants: nb=BokmÃ¥l, nn=Nynorsk, no=Both --> 1095 </analyzer> 1096 </fieldType> 1097 1098 <!-- Portuguese --> 1099 <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100"> 1100 <analyzer> 1101 <tokenizer class="solr.StandardTokenizerFactory"/> 1102 <filter class="solr.LowerCaseFilterFactory"/> 1103 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" /> 1104 <filter class="solr.PortugueseLightStemFilterFactory"/> 1105 <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> --> 1106 <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> --> 1107 <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> --> 1108 </analyzer> 1109 </fieldType> 1110 1111 <!-- Romanian --> 1112 <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100"> 1113 <analyzer> 1114 <tokenizer class="solr.StandardTokenizerFactory"/> 1115 <filter class="solr.LowerCaseFilterFactory"/> 1116 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" /> 1117 <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/> 1118 </analyzer> 1119 </fieldType> 1120 1121 <!-- Russian --> 1122 <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100"> 1123 <analyzer> 1124 <tokenizer class="solr.StandardTokenizerFactory"/> 1125 <filter class="solr.LowerCaseFilterFactory"/> 1126 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" /> 1127 <filter class="solr.SnowballPorterFilterFactory" language="Russian"/> 1128 <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> --> 1129 </analyzer> 1130 </fieldType> 1131 <!-- Russian with morphology--> 1132 <fieldType name="text_ru_morph" class="solr.TextField" positionIncrementGap="100"> 1133 <analyzer> 1134 <tokenizer class="solr.StandardTokenizerFactory"/> 1135 <filter class="solr.LowerCaseFilterFactory"/> 1136 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" /> 1137 <filter class="org.apache.lucene.morphology.russian.RussianFilterFactory"/> 1138 </analyzer> 1139 </fieldType> 1140 1141 <!-- Swedish --> 1142 <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100"> 1143 <analyzer> 1144 <tokenizer class="solr.StandardTokenizerFactory"/> 1145 <filter class="solr.LowerCaseFilterFactory"/> 1146 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" /> 1147 <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/> 1148 <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> --> 1149 </analyzer> 1150 </fieldType> 1151 1152 <!-- Thai --> 1153 <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100"> 1154 <analyzer> 1155 <tokenizer class="solr.StandardTokenizerFactory"/> 1156 <filter class="solr.LowerCaseFilterFactory"/> 1157 <filter class="solr.ThaiWordFilterFactory"/> 1158 <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" /> 1159 </analyzer> 1160 </fieldType> 1161 1162 <!-- Turkish --> 1163 <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100"> 1164 <analyzer> 1165 <tokenizer class="solr.StandardTokenizerFactory"/> 1166 <filter class="solr.TurkishLowerCaseFilterFactory"/> 1167 <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" /> 1168 <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/> 1169 </analyzer> 1170 </fieldType> 1171 470 1172 </types> 471 472 473 <fields> 474 <!-- Valid attributes for fields: 475 name: mandatory - the name for the field 476 type: mandatory - the name of a previously defined type from the 477 <types> section 478 indexed: true if this field should be indexed (searchable or sortable) 479 stored: true if this field should be retrievable 480 multiValued: true if this field may contain multiple values per document 481 omitNorms: (expert) set to true to omit the norms associated with 482 this field (this disables length normalization and index-time 483 boosting for the field, and saves some memory). Only full-text 484 fields or fields that need an index-time boost need norms. 485 termVectors: [false] set to true to store the term vector for a 486 given field. 487 When using MoreLikeThis, fields used for similarity should be 488 stored for best performance. 489 termPositions: Store position information with the term vector. 490 This will increase storage costs. 491 termOffsets: Store offset information with the term vector. This 492 will increase storage costs. 493 default: a value that should be used if no value is specified 494 when adding a document. 495 --> 496 497 <field name="docOID" type="string" indexed="true" stored="true" required="true" /> 498 499 <field name="ZZ" type="text_en_splitting" indexed="true" stored="false" multiValued="true" /> 500 <field name="TX" type="text_en_splitting" indexed="true" stored="false" multiValued="true" /> 501 <field name="TI" type="text_en_splitting" indexed="true" stored="false" multiValued="true" /> 502 <field name="SU" type="text_en_splitting" indexed="true" stored="false" multiValued="true" /> 503 <field name="ORG" type="text_en_splitting" indexed="true" stored="false" multiValued="true" /> 504 505 <!-- 506 <field name="sku" type="text_en_splitting_tight" indexed="true" stored="true" omitNorms="true"/> 507 <field name="name" type="text_general" indexed="true" stored="true"/> 508 <field name="alphaNameSort" type="alphaOnlySort" indexed="true" stored="false"/> 509 <field name="manu" type="text_general" indexed="true" stored="true" omitNorms="true"/> 510 <field name="cat" type="string" indexed="true" stored="true" multiValued="true"/> 511 <field name="features" type="text_general" indexed="true" stored="true" multiValued="true"/> 512 <field name="includes" type="text_general" indexed="true" stored="true" termVectors="true" termPositions="true" termOffsets="true" /> 513 514 <field name="weight" type="float" indexed="true" stored="true"/> 515 <field name="price" type="float" indexed="true" stored="true"/> 516 <field name="popularity" type="int" indexed="true" stored="true" /> 517 <field name="inStock" type="boolean" indexed="true" stored="true" /> 518 --> 519 520 <!-- 521 The following store examples are used to demonstrate the various ways one might _CHOOSE_ to 522 implement spatial. It is highly unlikely that you would ever have ALL of these fields defined. 1173 1174 <!-- Similarity is the scoring routine for each document vs. a query. 1175 A custom Similarity or SimilarityFactory may be specified here, but 1176 the default is fine for most applications. 1177 For more info: http://wiki.apache.org/solr/SchemaXml#Similarity 523 1178 --> 524 <field name="store" type="location" indexed="true" stored="true"/> 525 526 <!-- Common metadata fields, named specifically to match up with 527 SolrCell metadata when parsing rich documents such as Word, PDF. 528 Some fields are multiValued only because Tika currently may return 529 multiple values for them. 530 --> 531 <!-- 532 <field name="title" type="text_general" indexed="true" stored="true" multiValued="true"/> 533 <field name="subject" type="text_general" indexed="true" stored="true"/> 534 <field name="description" type="text_general" indexed="true" stored="true"/> 535 <field name="comments" type="text_general" indexed="true" stored="true"/> 536 <field name="author" type="text_general" indexed="true" stored="true"/> 537 <field name="keywords" type="text_general" indexed="true" stored="true"/> 538 <field name="category" type="text_general" indexed="true" stored="true"/> 539 <field name="content_type" type="string" indexed="true" stored="true" multiValued="true"/> 540 <field name="last_modified" type="date" indexed="true" stored="true"/> 541 <field name="links" type="string" indexed="true" stored="true" multiValued="true"/> 542 --> 543 544 545 <!-- catchall field, containing all other searchable text fields (implemented 546 via copyField further on in this schema --> 547 <field name="text" type="text_general" indexed="true" stored="false" multiValued="true"/> 548 549 <!-- catchall text field that indexes tokens both normally and in reverse for efficient 550 leading wildcard queries. --> 551 <field name="text_rev" type="text_general_rev" indexed="true" stored="false" multiValued="true"/> 552 553 <!-- non-tokenized version of manufacturer to make it easier to sort or group 554 results by manufacturer. copied from "manu" via copyField --> 555 <field name="manu_exact" type="string" indexed="true" stored="false"/> 556 557 <field name="payloads" type="payloads" indexed="true" stored="true"/> 558 559 <!-- Uncommenting the following will create a "timestamp" field using 560 a default value of "NOW" to indicate when each document was indexed. 561 --> 562 <!-- 563 <field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/> 564 --> 565 566 567 <!-- Dynamic field definitions. If a field name is not found, dynamicFields 568 will be used if the name matches any of the patterns. 569 RESTRICTION: the glob-like pattern in the name attribute must have 570 a "*" only at the start or the end. 571 EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i) 572 Longer patterns will be matched first. if equal size patterns 573 both match, the first appearing in the schema will be used. --> 574 <dynamicField name="*_i" type="int" indexed="true" stored="true"/> 575 <dynamicField name="*_s" type="string" indexed="true" stored="true"/> 576 <dynamicField name="*_l" type="long" indexed="true" stored="true"/> 577 <dynamicField name="*_t" type="text_general" indexed="true" stored="true"/> 578 <dynamicField name="*_txt" type="text_general" indexed="true" stored="true" multiValued="true"/> 579 <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/> 580 <dynamicField name="*_f" type="float" indexed="true" stored="true"/> 581 <dynamicField name="*_d" type="double" indexed="true" stored="true"/> 582 583 <!-- Type used to index the lat and lon components for the "location" FieldType --> 584 <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false"/> 585 586 <dynamicField name="*_dt" type="date" indexed="true" stored="true"/> 587 <dynamicField name="*_p" type="location" indexed="true" stored="true"/> 588 589 <!-- some trie-coded dynamic fields for faster range queries --> 590 <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/> 591 <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/> 592 <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/> 593 <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/> 594 <dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/> 595 596 <dynamicField name="*_pi" type="pint" indexed="true" stored="true"/> 597 598 <dynamicField name="ignored_*" type="ignored" multiValued="true"/> 599 <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/> 600 601 <dynamicField name="random_*" type="random" /> 602 <!-- dynamic field for sort/facet fields, which are strings by default. ie not tokenised. Can't be multivalued - ie can only have one value per document --> 603 <dynamicField name="by*" type="string" indexed="true" stored="false" multiValued="false" /> 604 <!-- uncomment the following to ignore any fields that don't already match an existing 605 field name or dynamic field, rather than reporting them as an error. 606 alternately, change the type="ignored" to some other type e.g. "text" if you want 607 unknown fields indexed and/or stored by default --> 608 <!--dynamicField name="*" type="ignored" multiValued="true" /--> 609 610 </fields> 611 612 <!-- Field to use to determine and enforce document uniqueness. 613 Unless this field is marked with required="false", it will be a required field 614 --> 615 <uniqueKey>docOID</uniqueKey> 616 617 <!-- field for the QueryParser to use when an explicit fieldname is absent --> 618 <defaultSearchField>text</defaultSearchField> 619 620 <!-- SolrQueryParser configuration: defaultOperator="AND|OR" --> 621 <solrQueryParser defaultOperator="OR"/> 622 623 <!-- copyField commands copy one field to another at the time a document 624 is added to the index. It's used either to index the same field differently, 625 or to add multiple fields to the same field for easier/faster searching. --> 626 627 <!-- 628 <copyField source="cat" dest="text"/> 629 <copyField source="name" dest="text"/> 630 <copyField source="manu" dest="text"/> 631 <copyField source="features" dest="text"/> 632 <copyField source="includes" dest="text"/> 633 <copyField source="manu" dest="manu_exact"/> 634 --> 635 636 <!-- Above, multiple source fields are copied to the [text] field. 637 Another way to map multiple source fields to the same 638 destination field is to use the dynamic field syntax. 639 copyField also supports a maxChars to copy setting. --> 640 641 <!-- <copyField source="*_t" dest="text" maxChars="3000"/> --> 642 643 <!-- copy name to alphaNameSort, a field designed for sorting by name --> 644 <!-- <copyField source="name" dest="alphaNameSort"/> --> 645 646 647 <!-- Similarity is the scoring routine for each document vs. a query. 648 A custom similarity may be specified here, but the default is fine 649 for most applications. --> 650 <!-- <similarity class="org.apache.lucene.search.DefaultSimilarity"/> --> 651 <!-- ... OR ... 652 Specify a SimilarityFactory class name implementation 653 allowing parameters to be used. 654 --> 655 <!-- 656 <similarity class="com.example.solr.CustomSimilarityFactory"> 657 <str name="paramkey">param value</str> 658 </similarity> 659 --> 660 1179 <!-- 1180 <similarity class="com.example.solr.CustomSimilarityFactory"> 1181 <str name="paramkey">param value</str> 1182 </similarity> 1183 --> 661 1184 662 1185 </schema>
Note:
See TracChangeset
for help on using the changeset viewer.