IKAnalyzer分词器 下载IKAnalyzer2012FF_u1.jar

<?xml version="1.0" encoding="UTF-8" ?> <!-- Licensed to the Apache Software Foundation (ASF) under one or more contributor license agreements. See the NOTICE file distributed with this work for additional information regarding copyright ownership. The ASF licenses this file to You under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License. --> <!-- This is the Solr schema file. This file should be named "schema.xml" and should be in the conf directory under the solr home (i.e. ./solr/conf/schema.xml by default) or located where the classloader for the Solr webapp can find it. This example schema is the recommended starting point for users. It should be kept correct and concise, usable out-of-the-box. For more information, on how to customize this file, please see http://wiki.apache.org/solr/SchemaXml PERFORMANCE NOTE: this schema includes many optional features and should not be used for benchmarking. To improve performance one could - set stored="false" for all fields possible (esp large fields) when you only need to search on the field but don't need to return the original value. - set indexed="false" if you don't need to search on the field, but only return the field as a result of searching on other indexed fields. - remove all unneeded copyField statements - for best index size and searching performance, set "index" to false for all general text fields, use copyField to copy them to the catchall "text" field, and use that for searching. - For maximum indexing performance, use the ConcurrentUpdateSolrServer java client. - Remember to run the JVM in server mode, and use a higher logging level that avoids logging every request --> <schema name="example" version="1.5"> <!-- attribute "name" is the name of this schema and is only used for display purposes. version="x.y" is Solr's version number for the schema syntax and semantics. It should not normally be changed by applications. 1.0: multiValued attribute did not exist, all fields are multiValued by nature 1.1: multiValued attribute introduced, false by default 1.2: omitTermFreqAndPositions attribute introduced, true by default except for text fields. 1.3: removed optional field compress feature 1.4: autoGeneratePhraseQueries attribute introduced to drive QueryParser behavior when a single string produces multiple tokens. Defaults to off for version >= 1.4 1.5: omitNorms defaults to true for primitive field types (int, float, boolean, string...) --> <!-- Valid attributes for fields: name: mandatory - the name for the field type: mandatory - the name of a field type from the <types> fieldType section indexed: true if this field should be indexed (searchable or sortable) stored: true if this field should be retrievable docValues: true if this field should have doc values. Doc values are useful for faceting, grouping, sorting and function queries. Although not required, doc values will make the index faster to load, more NRT-friendly and more memory-efficient. They however come with some limitations: they are currently only supported by StrField, UUIDField and all Trie*Fields, and depending on the field type, they might require the field to be single-valued, be required or have a default value (check the documentation of the field type you're interested in for more information) multiValued: true if this field may contain multiple values per document omitNorms: (expert) set to true to omit the norms associated with this field (this disables length normalization and index-time boosting for the field, and saves some memory). Only full-text fields or fields that need an index-time boost need norms. Norms are omitted for primitive (non-analyzed) types by default. termVectors: [false] set to true to store the term vector for a given field. When using MoreLikeThis, fields used for similarity should be stored for best performance. termPositions: Store position information with the term vector. This will increase storage costs. termOffsets: Store offset information with the term vector. This will increase storage costs. required: The field is required. It will throw an error if the value does not exist default: a value that should be used if no value is specified when adding a document. --> <!-- field names should consist of alphanumeric or underscore characters only and not start with a digit. This is not currently strictly enforced, but other field names will not have first class support from all components and back compatibility is not guaranteed. Names with both leading and trailing underscores (e.g. _version_) are reserved. --> <!-- If you remove this field, you must _also_ disable the update log in solrconfig.xml or Solr won't start. _version_ and update log are required for SolrCloud --> <field name="_version_" type="long" indexed="true" stored="true"/> <!-- points to the root document of a block of nested documents. Required for nested document support, may be removed otherwise --> <field name="_root_" type="string" indexed="true" stored="false"/> <!-- Only remove the "id" field if you have a very good reason to. While not strictly required, it is highly recommended. A <uniqueKey> is present in almost all Solr installations. See the <uniqueKey> declaration below where <uniqueKey> is set to "id". --> <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" /> <field name="sku" type="text_en_splitting_tight" indexed="true" stored="true" omitNorms="true"/> <field name="name" type="text_general" indexed="true" stored="true"/> <field name="manu" type="text_general" indexed="true" stored="true" omitNorms="true"/> <field name="cat" type="string" indexed="true" stored="true" multiValued="true"/> <field name="features" type="text_general" indexed="true" stored="true" multiValued="true"/> <field name="includes" type="text_general" indexed="true" stored="true" termVectors="true" termPositions="true" termOffsets="true" /> <field name="weight" type="float" indexed="true" stored="true"/> <field name="price" type="float" indexed="true" stored="true"/> <field name="popularity" type="int" indexed="true" stored="true" /> <field name="inStock" type="boolean" indexed="true" stored="true" /> <field name="store" type="location" indexed="true" stored="true"/> <!-- Common metadata fields, named specifically to match up with SolrCell metadata when parsing rich documents such as Word, PDF. Some fields are multiValued only because Tika currently may return multiple values for them. Some metadata is parsed from the documents, but there are some which come from the client context: "content_type": From the HTTP headers of incoming stream "resourcename": From SolrCell request param resource.name --> <field name="title" type="text_general" indexed="true" stored="true" multiValued="true"/> <field name="subject"