Solr5.5高级应用（基于tomcat9）

一．配置solr

1.配置

注意：要是想放到其它路径下，可以修改此路径下的web.xml配置文件

修改内容如下：

<!-- 将solrhome的绝对路径写入env-entry-value -->

<env-entry>

<env-entry-name>solr/home</env-entry-name>

<!--例如：E:/search11/solr/server/solr-->

<env-entry-value>你的core的上级路径</env-entry-value>

<env-entry-type>java.lang.String</env-entry-type>

</env-entry>

2.点击tomcat的bin目录下的startup.bat启动

3.在浏览器上输入http://你的ip:8080/solr/index.html#/ 查看

4.选择test-core，执行查看

二．配置HanLP分词器

1. 配置配置文件

从下载的HanLP中获取hanlp.properties配置文件，放置到下面的路径中。

2. 导入HanLP词典

从下载的HanLP中拷贝data到下图目录下，该data包含Hanlp中提供的词库和模型。

3. 导入jar包

把HanLP中的hanlp-1.5.0.jar和hanlp-1.5.0.sources.jar放到tomcat的该目录下

4. 修改hanlp.properties中的，改成data的上级目录

一、配置HanLP分词器

1.配置分词器

在使用该分词器的core中的managed-schema文件中添加

<fieldType name="text_cn" class="solr.TextField">

<analyzer type="index">

<tokenizer class="com.hankcs.lucene.HanLPTokenizerFactory"

enableIndexMode="true" enablePlaceRecognize="true" enableOrganizationRecognize="true"  customDictionaryPath="E:\search11\data\dictionary\custom\自定义词典.txt"/>

<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />

<filter class="solr.LowerCaseFilterFactory"/>

</analyzer>

<analyzer type="query">

<!-- 切记不要在query中开启index模式 -->

<tokenizer class="com.hankcs.lucene.HanLPTokenizerFactory"

enableIndexMode="false"  enablePlaceRecognize="true" enableOrganizationRecognize="true" customDictionaryPath="E:\search11\data\dictionary\custom\自定义词典.txt"/>

<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />

<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt"

ignoreCase="true" expand="true"/>

<filter class="solr.LowerCaseFilterFactory"/>

</analyzer>

</fieldType>

2.修改使用该分词器的字段

3.结果

三．配置Tika文档提取器

1. 首先在core中添加tika文档搜索

<requestHandler name="/update/extract" class="org.apache.solr.handler.extraction.ExtractingRequestHandler" startup="lazy">

<lst name="defaults">

<!-- All the main content goes into "text"... if you need to return

the extracted text or do highlighting, use a stored field. -->

<str name="fmap.content">text</str>

<str name="lowernames">false</str>

<str name="uprefix">ignored_</str>

<!-- capture link hrefs but ignore div attributes -->

</lst>

</requestHandler>

2. 配置tika解析文档的分类字段

<!-- Tika字段 -->

<field name="PK" type="string" indexed="true" stored="true" required="true" multiValued="false"/>

<field name="BT" type="string" indexed="true" stored="true" termVectors="true" multiValued="false"/>

<field name="ZZ" type="string" indexed="true" stored="true"  multiValued="true"/>

<field name="NR" type="text_cn" indexed="true" stored="true" termVectors="true" termPositions="true" termOffsets="true"/>

<field name="CJSJ" type="date" indexed="true" stored="true" />

3. 修改tomcat的server.xml配置

<Connector port="8080" protocol="HTTP/1.1"

connectionTimeout="20000"

redirectPort="8443"

maxHttpHeaderSize ="104857600" maxPostSize="0" />

注意：

maxHttpHeaderSize ：设置最大上传头大小

maxPostSize：解除post提交大小限制

4. 结果

四．配置HTML及相关样式过滤器

<fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">

<analyzer type="index">

<tokenizer class="solr.StandardTokenizerFactory"/>

<!-- 清除\n样式 -->

<charFilter class="solr.MappingCharFilterFactory"

mapping="mapping-FoldToASCII.txt"/>

<charFilter class="solr.HTMLStripCharFilterFactory"/><!-- 清除HTML样式 -->

<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />

<filter class="solr.LowerCaseFilterFactory"/>

</analyzer>

<analyzer type="query">

<tokenizer class="solr.StandardTokenizerFactory"/>

<charFilter class="solr.HTMLStripCharFilterFactory"/><!-- 清除HTML样式 -->

<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />

<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt"

ignoreCase="true" expand="true"/>

<filter class="solr.LowerCaseFilterFactory"/>

</analyzer>

</fieldType>

五．配置MLT文档相识度搜索

1.添加配置

<!-- Solr More like this 文件相似度搜索用到此配置 -->

<requestHandler name="/mlt" class="solr.MoreLikeThisHandler">

<lst name="defaults">

<!-- wt即writer type,即返回的数据的MIME类型，如json,xml等等 -->

<str name="wt">json</str>

<str name="fl">

ZSYBS,ZSYWT,ZSYDA,ZSBS,XH,ZSDZT,CZRBS,ZZBM,DQBM,FJFZBS,

SCJBS,ZSYWB,YXQ,YDHS,GDMB,ZSLX,CZSJ,CJSJ</str><!-- 需要返回的字段 -->

<str name="mlt.qf"> <!-- 设置 mlt.fl中的各个字段的权重 -->

ZSYWT^2.0 ZSYWB^1.0

</str>

<str name="mlt.fl">ZSYWT,ZSYWB</str><!-- 指定用于判断是否相似的字段 -->

<str name="mlt.match.include">true</str>

<!-- 指定最小的分词频率,小于此频率的分词将不会被计算在内 -->

<str name="mlt.mintf">1</str>

<!-- 指定最小的文档频率,分词所在文档的个数小于此值的话将会被忽略 -->

<str name="mlt.mindf">1</str>

<!-- 指定分词的最小长度,小于此长度的单词将被忽略。 -->

<str name="mlt.minwl">2</str>

<!-- 默认值5. 设置返回的相似的文档数 -->

<int name="mlt.count">10</int>

<str name="df">ZSYBS</str>

<str name="q.op">AND</str>

</lst>

</requestHandler>

2.测试结果

六．配置SolrJ高亮展示

1. 高亮的默认配置

<!-- Highlighting defaults -->

<str name="hl">on</str>

<str name="hl.fl">content features title name</str>

<str name="hl.preserveMulti">true</str>

<str name="hl.encoder">html</str>

<str name="hl.simple.pre"><b></str>

<str name="hl.simple.post"></b></str>

<str name="f.title.hl.fragsize">0</str>

<str name="f.title.hl.alternateField">title</str>

<str name="f.name.hl.fragsize">0</str>

<str name="f.name.hl.alternateField">name</str>

<str name="f.content.hl.snippets">3</str>

<str name="f.content.hl.fragsize">200</str>

<str name="f.content.hl.alternateField">content</str>

<str name="f.content.hl.maxAlternateFieldLength">750</str>

2. 启用高亮

SolrQuery solrQuery = new SolrQuery();

solrQuery.setQuery("ZSYWT:交易电价"); //设置查询关键字

solrQuery.setHighlight(true); //开启高亮

solrQuery.addHighlightField("ZSYWT"); //高亮字段

solrQuery.addHighlightField("ZSYWB"); //高亮字段

solrQuery.setHighlightSimplePre("<font color='red'>"); //高亮单词的前缀

solrQuery.setHighlightSimplePost("</font>"); //高亮单词的后缀

solrQuery.setParam("hl.fl", "ZSYWT");

七．配置搜索关键词自动补全（汉字，拼音）

1. 添加配置

<searchComponent name="suggest" class="solr.SuggestComponent">

<lst name="suggester">

<str name="name">mySuggester</str>

<str name="lookupImpl">FuzzyLookupFactory</str>

<str name="dictionaryImpl">DocumentDictionaryFactory</str>

<str name="field">ZSYWT_PINYIN</str><!--匹配字段，可以使用copyField实现多列-->

<!--权重，用于排序-->

<!--<str name="weightField">ZSYWB</str>-->

<str name="suggestAnalyzerFieldType">text_cn</str>

</lst>

</searchComponent>

<requestHandler name="/suggest" class="solr.SearchHandler" startup="lazy">

<lst name="defaults">

<str name="suggest">true</str>

<str name="suggest.build">true</str>

<str name="suggest.dictionary">mySuggester</str><!--与上面保持一致-->

<str name="suggest.count">10</str>

</lst>

<arr name="components">

<str>suggest</str>

</arr>

</requestHandler>

2.设置搜索字段

<!-- 设置自动补全 -->

<field name="ZSYWT_PINYIN" type="text_cn" indexed="true"

stored="true" multiValued="true"/>

<copyField source="PINYIN" dest="ZSYWT_PINYIN"/>

<copyField source="ZSYWT" dest="ZSYWT_PINYIN"/>

3.测试结果

八．搜索关键词自动纠错

代码实现：

public Collection<List<String>> getAutomaticErrorCorrection(String content)

throws SolrServerException, IOException {

HttpSolrServer server = new HttpSolrServer(url);

SolrQuery params = new SolrQuery();

params.set("qt", "/suggest");

//全部转换为拼音

StringBuilder sb = new StringBuilder();

char[] array = content.toCharArray();

for(int j=0;j<array.length;j++){

if(isChineseByBlockStyle(array[j])){

List<Pinyin> pinyinMidList = HanLP.convertToPinyinList(""+array[j]);

for (Pinyin pinyin : pinyinMidList)

{

sb.append(pinyin.getPinyinWithoutTone());

}

}else{

sb.append(array[j]);

}

}

params.setQuery(sb.toString());

QueryResponse response = null;

response = server.query(params);

SuggesterResponse suggest = response.getSuggesterResponse();

Collection<List<String>> collection = suggest.getSuggestedTerms().values();

server.close();

return collection;

}