设为首页 收藏本站
查看: 1158|回复: 0

[经验分享] solr的索引和查询顺序

[复制链接]
发表于 2016-12-15 08:57:45 | 显示全部楼层 |阅读模式
  拜读了solr的部分源码,却急于弄明白solr的索引顺序和查询顺序,如下是探访结果.
  所有的配置都在solr/example/solr/conf/schema.xml当中.

<!-- 如下是对text类型的处理 -->
<fieldType name="text" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
 <!-- 索引顺序1空格2同义词3过滤词4拆字5小写过滤6关键字7词干抽取算法-->
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-->
<!-- Case insensitive stop word removal.
add enablePositionIncrements=true in both the index and query
analyzers to leave a 'gap' for more accurate phrase queries.
-->
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="stopwords.txt"
enablePositionIncrements="true"
/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
<!-- 查询顺序1空格2同义词3过滤词4拆字5小写过滤6关键字7词干抽取算法-->
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="stopwords.txt"
enablePositionIncrements="true"
/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
</fieldType>

<!-- Less flexible matching, but less false matches.  Probably not ideal for product names,
but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
<!-- 针对textTight类型-->
<fieldType name="textTight" class="solr.TextField" positionIncrementGap="100" >
 <!-- 查询顺序1空格2同义词3过滤词4拆字5小写过滤6关键字7英文相近词8去除重复词
 -->
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.EnglishMinimalStemFilterFactory"/>
<!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
possible with WordDelimiterFilter in conjuncton with stemming. -->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>

<!-- A general unstemmed text field - good if one does not know the language of the field -->
 <!-- 针对textgen类型 -->
<fieldType name="textgen" class="solr.TextField" positionIncrementGap="100">
<!-- 索引顺序1空格2过滤词3拆字4小写过滤-->
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
<!-- 查询顺序1空格2同义词3过滤词4小写过滤-->
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="stopwords.txt"
enablePositionIncrements="true"
/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>

<!-- A general unstemmed text field that indexes tokens normally and also
reversed (via ReversedWildcardFilterFactory), to enable more efficient
leading wildcard queries. -->
<!-- 针对text_rev类型 -->
<fieldType name="text_rev" class="solr.TextField" positionIncrementGap="100">
<!-- 索引顺序1空格2过滤词3拆字4小写过滤6转义通配符-->
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
</analyzer>
 <!-- 查询顺序1空格2同义词3过滤词4拆字5小写过滤 -->
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="stopwords.txt"
enablePositionIncrements="true"
/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<!-- charFilter + WhitespaceTokenizer  -->
<!--
<fieldType name="textCharNorm" class="solr.TextField" positionIncrementGap="100" >
<analyzer>
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
</analyzer>
</fieldType>
-->
<!-- This is an example of using the KeywordTokenizer along
With various TokenFilterFactories to produce a sortable field
that does not include some properties of the source text
-->
<fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
<analyzer>
<!-- KeywordTokenizer does no actual tokenizing, so the entire
input string is preserved as a single token
-->
<tokenizer class="solr.KeywordTokenizerFactory"/>
<!-- The LowerCase TokenFilter does what you expect, which can be
when you want your sorting to be case insensitive
-->
<filter class="solr.LowerCaseFilterFactory" />
<!-- The TrimFilter removes any leading or trailing whitespace -->
<filter class="solr.TrimFilterFactory" />
<!-- The PatternReplaceFilter gives you the flexibility to use
Java Regular expression to replace any sequence of characters
matching a pattern with an arbitrary replacement string,
which may include back references to portions of the original
string matched by the pattern.
See the Java Regular Expression documentation for more
information on pattern and replacement string syntax.
http://java.sun.com/j2se/1.5.0/docs/api/java/util/regex/package-summary.html
-->
<filter class="solr.PatternReplaceFilterFactory"
pattern="([^a-z])" replacement="" replace="all"
/>
</analyzer>
</fieldType>
<fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
</analyzer>
</fieldtype>
<fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<!--
The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
a token of "foo|1.4"  would be indexed as "foo" with a payload of 1.4f
Attributes of the DelimitedPayloadTokenFilterFactory :
"delimiter" - a one character delimiter. Default is | (pipe)
"encoder" - how to encode the following value into a playload
float -> org.apache.lucene.analysis.payloads.FloatEncoder,
integer -> o.a.l.a.p.IntegerEncoder
identity -> o.a.l.a.p.IdentityEncoder
Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
-->
<filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
</analyzer>
</fieldtype>
<!-- lowercases the entire field value, keeping it as a single token.  -->
<fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.KeywordTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory" />
</analyzer>
</fieldType>

  大致的索引顺序会是:
  1.空格..............................solr.WhitespaceTokenizerFactory
  2同义词............................solr.SynonymFilterFactory
  3过滤词...........................solr.StopFilterFactory
  4拆字..............................solr.WordDelimiterFilterFactory
  5小写过滤.....................solr.LowerCaseFilterFactory
  6关键字.........................solr.KeywordMarkerFilterFactory
  7词干抽取算法............solr.PorterStemFilterFactory
  大致的搜素顺序是:
  1.空格..............................solr.WhitespaceTokenizerFactory
  2同义词............................solr.SynonymFilterFactory
  3过滤词...........................solr.StopFilterFactory
  4拆字..............................solr.WordDelimiterFilterFactory
  5小写过滤.....................solr.LowerCaseFilterFactory
  6关键字.........................solr.KeywordMarkerFilterFactory
  7英文相近词..................solr.EnglishMinimalStemFilterFactory
  8去除重复词.................solr.RemoveDuplicatesTokenFilterFactory
  当然了,你可以根据自己的权重来重新分配索引和搜素顺序

运维网声明 1、欢迎大家加入本站运维交流群:群②:261659950 群⑤:202807635 群⑦870801961 群⑧679858003
2、本站所有主题由该帖子作者发表,该帖子作者与运维网享有帖子相关版权
3、所有作品的著作权均归原作者享有,请您和我们一样尊重他人的著作权等合法权益。如果您对作品感到满意,请购买正版
4、禁止制作、复制、发布和传播具有反动、淫秽、色情、暴力、凶杀等内容的信息,一经发现立即删除。若您因此触犯法律,一切后果自负,我们对此不承担任何责任
5、所有资源均系网友上传或者通过网络收集,我们仅提供一个展示、介绍、观摩学习的平台,我们不对其内容的准确性、可靠性、正当性、安全性、合法性等负责,亦不承担任何法律责任
6、所有作品仅供您个人学习、研究或欣赏,不得用于商业或者其他用途,否则,一切后果均由您自己承担,我们对此不承担任何法律责任
7、如涉及侵犯版权等问题,请您及时通知我们,我们将立即采取措施予以解决
8、联系人Email:admin@iyunv.com 网址:www.yunweiku.com

所有资源均系网友上传或者通过网络收集,我们仅提供一个展示、介绍、观摩学习的平台,我们不对其承担任何法律责任,如涉及侵犯版权等问题,请您及时通知我们,我们将立即处理,联系人Email:kefu@iyunv.com,QQ:1061981298 本贴地址:https://www.yunweiku.com/thread-314479-1-1.html 上篇帖子: 配置Solr UUID时出现的异常 下篇帖子: solr 简单的分布式布署[转]
您需要登录后才可以回帖 登录 | 立即注册

本版积分规则

扫码加入运维网微信交流群X

扫码加入运维网微信交流群

扫描二维码加入运维网微信交流群,最新一手资源尽在官方微信交流群!快快加入我们吧...

扫描微信二维码查看详情

客服E-mail:kefu@iyunv.com 客服QQ:1061981298


QQ群⑦:运维网交流群⑦ QQ群⑧:运维网交流群⑧ k8s群:运维网kubernetes交流群


提醒:禁止发布任何违反国家法律、法规的言论与图片等内容;本站内容均来自个人观点与网络等信息,非本站认同之观点.


本站大部分资源是网友从网上搜集分享而来,其版权均归原作者及其网站所有,我们尊重他人的合法权益,如有内容侵犯您的合法权益,请及时与我们联系进行核实删除!



合作伙伴: 青云cloud

快速回复 返回顶部 返回列表