[solr] - spell check

solr提供了一个spell check，又叫suggestions，可以用于查询输入的自动完成功能auto-complete。

参考文献：

https://cwiki.apache.org/confluence/display/solr/Spell+Checking

http://www.cnblogs.com/ibook360/archive/2011/11/30/2269077.html

方法：

---

修改core的solrconfig.xml

加入这段到<config />内

    <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
      <lst name="spellchecker">
        <str name="name">wordbreak</str>
        <str name="classname">org.apache.solr.spelling.suggest.Suggester</str>
        <str name="lookupImpl">org.apache.solr.spelling.suggest.tst.TSTLookup</str>
        <str name="field">content</str>
        <str name="combineWords">true</str>
        <str name="breakWords">true</str>
        <int name="maxChanges">10</int>
      </lst>
    </searchComponent>
    <requestHandler name="/spellcheck" class="org.apache.solr.handler.component.SearchHandler">
      <lst name="defaults">
        <str name="spellcheck">true</str>
        <str name="spellcheck.dictionary">wordbreak</str>
        <str name="spellcheck.count">20</str>
      </lst>
      <arr name="last-components">
        <str>spellcheck</str>
      </arr>
    </requestHandler>

schema.xml配置：

<?xml version="1.0" ?>
<schema name="my core" version="1.1">

    <fieldtype name="string"  class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
    <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
    <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
    <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
    <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
    <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
    <fieldtype name="binary" class="solr.BinaryField"/>
    <fieldType name="text_cn" class="solr.TextField">
        <analyzer type="index" class="org.wltea.analyzer.lucene.IKAnalyzer" />
        <analyzer type="query" class="org.wltea.analyzer.lucene.IKAnalyzer" />
        <analyzer>
            <tokenizer class="solr.KeywordTokenizerFactory"/>
            <filter class="solr.LowerCaseFilterFactory"/>
        </analyzer>
    </fieldType>

    <!-- general -->
    <field name="id" type="long" indexed="true" stored="true" multiValued="false" required="true"/>
    <field name="subject" type="text_cn" indexed="true" stored="true" />
    <field name="content" type="text_cn" indexed="true" stored="true" />
    <field name="category_id" type="long" indexed="true" stored="true" />
    <field name="category_name" type="text_cn" indexed="true" stored="true" />
    <field name="last_update_time" type="tdate" indexed="true" stored="true" />
    <field name="_version_" type="long" indexed="true" stored="true"/>

     <!-- field to use to determine and enforce document uniqueness. -->
     <uniqueKey>id</uniqueKey>

     <!-- field for the QueryParser to use when an explicit fieldname is absent -->
     <defaultSearchField>subject</defaultSearchField>

     <!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
     <solrQueryParser defaultOperator="OR"/>
</schema>

关键在于这句：

        <analyzer>
            <tokenizer class="solr.KeywordTokenizerFactory"/>
            <filter class="solr.LowerCaseFilterFactory"/>
        </analyzer>

意思是词组搜索

设置完xml，重启tomcat，在浏览器中运行：

http://localhost:8899/solr/mycore/spellcheck?spellcheck.build=true

运行结果：

然后在浏览器中运行：

http://localhost:8899/solr/mycore/spellcheck?q=中央&rows=0

运行结果：

Java代码：

---

Java bean:

package com.my.entity;

import java.util.Date;

import org.apache.solr.client.solrj.beans.Field;

public class Item {
    @Field
    private long id;
    @Field
    private String subject;
    @Field
    private String content;
    @Field("category_id")
    private long categoryId;
    @Field("category_name")
    private String categoryName;
    @Field("last_update_time")
    private Date lastUpdateTime;

    public long getId() {
        return id;
    }
    public void setId(long id) {
        this.id = id;
    }
    public String getSubject() {
        return subject;
    }
    public void setSubject(String subject) {
        this.subject = subject;
    }
    public String getContent() {
        return content;
    }
    public void setContent(String content) {
        this.content = content;
    }
    public long getCategoryId() {
        return categoryId;
    }
    public void setCategoryId(long categoryId) {
        this.categoryId = categoryId;
    }
    public String getCategoryName() {
        return categoryName;
    }
    public void setCategoryName(String categoryName) {
        this.categoryName = categoryName;
    }
    public Date getLastUpdateTime() {
        return lastUpdateTime;
    }
    public void setLastUpdateTime(Date lastUpdateTime) {
        this.lastUpdateTime = lastUpdateTime;
    }
}

测试代码：

package com.my.solr;

import java.io.IOException;
import java.util.ArrayList;
import java.util.Date;
import java.util.List;
import java.util.Map;

import org.apache.solr.client.solrj.SolrQuery;
import org.apache.solr.client.solrj.SolrServerException;
import org.apache.solr.client.solrj.impl.HttpSolrServer;
import org.apache.solr.client.solrj.impl.XMLResponseParser;
import org.apache.solr.client.solrj.response.QueryResponse;
import org.apache.solr.client.solrj.response.SpellCheckResponse;
import org.apache.solr.client.solrj.response.SpellCheckResponse.Collation;
import org.apache.solr.client.solrj.response.SpellCheckResponse.Correction;
import org.apache.solr.client.solrj.response.SpellCheckResponse.Suggestion;

import com.my.entity.Item;

public class TestSolr {

    public static void main(String[] args) throws IOException, SolrServerException {
        String url = "http://localhost:8899/solr/mycore";
        HttpSolrServer core = new HttpSolrServer(url);
        core.setMaxRetries(1);
        core.setConnectionTimeout(5000);
        core.setParser(new XMLResponseParser()); // binary parser is used by default
        core.setSoTimeout(1000); // socket read timeout
        core.setDefaultMaxConnectionsPerHost(100);
        core.setMaxTotalConnections(100);
        core.setFollowRedirects(false); // defaults to false
        core.setAllowCompression(true);

        // ------------------------------------------------------
        // remove all data
        // ------------------------------------------------------
        core.deleteByQuery("*:*");
        List<Item> items = new ArrayList<Item>();
        items.add(makeItem(1, "cpu", "this is intel cpu", 1, "cpu-intel"));
        items.add(makeItem(2, "cpu AMD", "this is AMD cpu", 2, "cpu-AMD"));
        items.add(makeItem(3, "cpu intel", "this is intel-I7 cpu", 1, "cpu-intel"));
        items.add(makeItem(4, "cpu AMD", "this is AMD 5000x cpu", 2, "cpu-AMD"));
        items.add(makeItem(5, "cpu intel I6", "this is intel-I6 cpu", 1, "cpu-intel-I6"));
        items.add(makeItem(6, "处理器", "中央处理器英特儿", 1, "cpu-intel"));
        items.add(makeItem(7, "处理器AMD", "中央处理器AMD", 2, "cpu-AMD"));
        items.add(makeItem(8, "中央处理器", "中央处理器Intel", 1, "cpu-intel"));
        items.add(makeItem(9, "中央空调格力", "格力中央空调", 3, "air"));
        items.add(makeItem(10, "中央空调海尔", "海尔中央空调", 3, "air"));
        items.add(makeItem(11, "中央空调美的", "美的中央空调", 3, "air"));
        core.addBeans(items);
        // commit
        core.commit();

        // ------------------------------------------------------
        // search
        // ------------------------------------------------------
        SolrQuery query = new SolrQuery();
        String token = "中央";
        query.set("qt", "/spellcheck");
        query.set("q", token);
        query.set("spellcheck", "on");
        query.set("spellcheck.build", "true");
        query.set("spellcheck.onlyMorePopular", "true");

        query.set("spellcheck.count", "100");
        query.set("spellcheck.alternativeTermCount", "4");
        query.set("spellcheck.onlyMorePopular", "true");

        query.set("spellcheck.extendedResults", "true");
        query.set("spellcheck.maxResultsForSuggest", "5");

        query.set("spellcheck.collate", "true");
        query.set("spellcheck.collateExtendedResults", "true");
        query.set("spellcheck.maxCollationTries", "5");
        query.set("spellcheck.maxCollations", "3");

        QueryResponse response = null;

        try {
            response = core.query(query);
            System.out.println("查询耗时：" + response.getQTime());
        } catch (SolrServerException e) {
            System.err.println(e.getMessage());
            e.printStackTrace();
        } catch (Exception e) {
            System.err.println(e.getMessage());
            e.printStackTrace();
        } finally {
            core.shutdown();
        }

        SpellCheckResponse spellCheckResponse = response.getSpellCheckResponse();
        if (spellCheckResponse != null) {
            List<Suggestion> suggestionList = spellCheckResponse.getSuggestions();
            for (Suggestion suggestion : suggestionList) {
                System.out.println("Suggestions NumFound: " + suggestion.getNumFound());
                System.out.println("Token: " + suggestion.getToken());
                System.out.print("Suggested: ");
                List<String> suggestedWordList = suggestion.getAlternatives();
                for (String word : suggestedWordList) {
                    System.out.println(word + ", ");
                }
                System.out.println();
            }
            System.out.println();
            Map<String, Suggestion> suggestedMap = spellCheckResponse.getSuggestionMap();
            for (Map.Entry<String, Suggestion> entry : suggestedMap.entrySet()) {
                System.out.println("suggestionName: " + entry.getKey());
                Suggestion suggestion = entry.getValue();
                System.out.println("NumFound: " + suggestion.getNumFound());
                System.out.println("Token: " + suggestion.getToken());
                System.out.print("suggested: ");

                List<String> suggestedList = suggestion.getAlternatives();
                for (String suggestedWord : suggestedList) {
                    System.out.print(suggestedWord + ", ");
                }
                System.out.println("\n\n");
            }

            Suggestion suggestion = spellCheckResponse.getSuggestion(token);
            System.out.println("NumFound: " + suggestion.getNumFound());
            System.out.println("Token: " + suggestion.getToken());
            System.out.print("suggested: ");
            List<String> suggestedList = suggestion.getAlternatives();
            for (String suggestedWord : suggestedList) {
                System.out.print(suggestedWord + ", ");
            }
            System.out.println("\n\n");

            System.out.println("The First suggested word for solr is : " + spellCheckResponse.getFirstSuggestion(token));
            System.out.println("\n\n");

            List<Collation> collatedList = spellCheckResponse.getCollatedResults();
            if (collatedList != null) {
                for (Collation collation : collatedList) {
                    System.out.println("collated query String: " + collation.getCollationQueryString());
                    System.out.println("collation Num: " + collation.getNumberOfHits());
                    List<Correction> correctionList = collation.getMisspellingsAndCorrections();
                    for (Correction correction : correctionList) {
                        System.out.println("original: " + correction.getOriginal());
                        System.out.println("correction: " + correction.getCorrection());
                    }
                    System.out.println();
                }
            }
            System.out.println();
            System.out.println("The Collated word: " + spellCheckResponse.getCollatedResult());
            System.out.println();
        }

        System.out.println("查询耗时：" + response.getQTime());
    }

    private static Item makeItem(long id, String subject, String content, long categoryId, String categoryName) {
        Item item = new Item();
        item.setId(id);
        item.setSubject(subject);
        item.setContent(content);
        item.setLastUpdateTime(new Date());
        item.setCategoryId(categoryId);
        item.setCategoryName(categoryName);
        return item;
    }
}

测试结果：

这种方式可以使用于对现在数据内容的查询拼写检查。