[solr] - Facet - autocomplete

Solr的facet可以用于一般性的前缀式自动完成功能，当然，它的主要功能是用于做统计、分类、区间等。

统计、分类、区间功能，可参考下文：

http://hongweiyi.com/2013/03/apache-solr-facet-introduction/

下面例子是使用Facet做前缀式自动完成功能。

 

schema.xml

<?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" />
    </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>

 

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：

package com.my.solr;

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

import org.apache.solr.client.solrj.SolrQuery;
import org.apache.solr.client.solrj.SolrQuery.ORDER;
import org.apache.solr.client.solrj.SolrQuery.SortClause;
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.FacetField;
import org.apache.solr.client.solrj.response.FacetField.Count;
import org.apache.solr.client.solrj.response.QueryResponse;

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"));
        core.addBeans(items);
        // commit
        core.commit();

        // ------------------------------------------------------
        // search
        // ------------------------------------------------------
        SolrQuery query = new SolrQuery();
        query.setQuery("*:*");
        query.setStart(0);    // query的开始行数(分页使用)
        query.setRows(0);    // query的返回行数(分页使用)
        query.setFacet(true);    // 设置使用facet
        query.setFacetMinCount(1);    // 设置facet最少的统计数量
        query.setFacetLimit(10);    // facet结果的返回行数
        query.addFacetField("category_name");    // facet的字段
        query.setFacetPrefix("cpu");    // facet字段值
        query.addSort(new SortClause("id", ORDER.asc));    // 排序
        QueryResponse response = core.query(query);
        List<Item> items_rep = response.getBeans(Item.class);
        List<FacetField> facetFields = response.getFacetFields();
        // 因为上面的start和rows均设置为0，所以这里不会有query结果输出
        for (Item i : items_rep) {
            System.out.println("id=" + i.getId() + "\tcontent=" + i.getContent());
        }
        // 打印所有facet
        for(FacetField ff : facetFields) {
            System.out.println("name=" + ff.getName() + "\tcount=" + ff.getValueCount());
            System.out.println("--------------------");
            for(Count count: ff.getValues() ) {
                System.out.println("name=" + count.getName() + "\tvalue=" + count.getCount());
            }
        }
    }
    
    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;
    }
}

 

输出结果：