solr - Solr API，如何访问文档？

Question

我正在使用 solr api 开发自定义请求处理程序。作为参考，我将“MoreLikeThis”作为参考。

我可以使用“getDocList”API 访问文档，然后获取“迭代器”的对象，但它只给了我文档 ID。

如何访问文档的每个字段？

package org.apache.solr.handler.ext;

import org.apache.solr.request.*;
import org.apache.solr.response.*;
import org.apache.solr.handler.*;
import org.apache.solr.core.*;
import org.apache.solr.schema.*;
import org.apache.lucene.analysis.*;
import org.apache.solr.common.params.*;
import org.apache.solr.search.*;
import org.apache.lucene.search.*;
import org.apache.solr.search.SolrIndexSearcher.*;

import org.apache.lucene.document.Document;
import org.apache.lucene.index.IndexReader;

import java.util.*;
import java.io.*;

public class MyRequestHandler extends RequestHandlerBase{


@Override
  public void handleRequestBody(SolrQueryRequest req, SolrQueryResponse rsp)
      throws Exception {

    System.out.println("I am in My Handler");

    /**
     *  Working with core
     */
    SolrCore core = req.getCore();
    System.out.println("Core is " + "" + core.getDescription());
    System.out.println("Data directory is " + "" + core.getDataDir());
    System.out.println("Index directory is " + "" + core.getIndexDir());


    /**
     *  Working with schema
     */
    IndexSchema schema = core.getSchema();
    SchemaField field = schema.getField("country");

    System.out.println(field.isRequired());

    /**
     *  Create Map
     */

    IndexSchema schemaObj = req.getSchema();

    Map<String , SchemaField>map = req.getSchema().getFields();

    // Iterate over keys
    for (String str : map.keySet()){
        System.out.println(str);
    }

    // Iterate over SchemaField

    for (SchemaField schemaFieldObj: map.values()){

        System.out.println(schemaFieldObj.isRequired());
    }

    /**
     *  Find the Unique Key Field
     */

    field = schemaObj.getUniqueKeyField();
    System.out.println(field.getName());

    System.out.println(schemaObj.getQueryParserDefaultOperator());



    /**
     *   Working with request parameters
     */

    SolrParams reqParams = req.getParams();
    String q = reqParams.get(CommonParams.Q);
    System.out.println(reqParams.get(CommonParams.Q));

    String defType = reqParams.get(QueryParsing.DEFTYPE , QParserPlugin.DEFAULT_QTYPE);
    System.out.println(defType);


    /**
     *  Working with QParser
     */
    QParser queryParser = QParser.getParser(q, defType, req);
    Query query = queryParser.getQuery();


    /**
     *   Now get searcher 
     */

    SolrIndexSearcher indexSearcher = req.getSearcher();
    DocList matchDocs = indexSearcher.getDocList(query, null, null, 1, 100000,10000);

    // Number of documents matched
    System.out.println(matchDocs.matches());
    // Get Iterator
        // get documentreader
        Reader reader;
    IndexReader readDoc;
    Document doc;
    DocIterator iterator = matchDocs.iterator();
    while (iterator.hasNext()){
    Integer id = iterator.nextDoc();
    System.out.println("Here I am " + id);


         /*   HOW TO ACCESS ALL FIELDS OF DOCUMENT */


    }

}

  @Override
  public String getDescription() {
    return "My Search Handler";
  }

  @Override
  public String getSource() {
    return "$Source$";
  }


  @Override
  public String getVersion() {
    return "$Revision$";
  }

}

Answer 1

好吧，我得到了答案..这是帮助我进入每个领域的代码..

package org.apache.solr.handler.ext;


public class MyRequestHandler extends RequestHandlerBase{


@Override
  public void handleRequestBody(SolrQueryRequest req, SolrQueryResponse rsp)
      throws Exception {

    System.out.println("I am in My Handler");

    /**
     *  Working with core
     */
    SolrCore core = req.getCore();
    System.out.println("Core is " + "" + core.getDescription());
    System.out.println("Data directory is " + "" + core.getDataDir());
    System.out.println("Index directory is " + "" + core.getIndexDir());


    /**
     *  Working with schema
     */
    IndexSchema schema = core.getSchema();
    SchemaField field = schema.getField("country");

    System.out.println(field.isRequired());

    /**
     *  Create Map
     */

    IndexSchema schemaObj = req.getSchema();

    Map<String , SchemaField>map = req.getSchema().getFields();

    // Iterate over keys
    for (String str : map.keySet()){
        System.out.println(str);
    }

    // Iterate over SchemaField

    for (SchemaField schemaFieldObj: map.values()){

        System.out.println(schemaFieldObj.isRequired());
    }

    /**
     *  Find the Unique Key Field
     */

    field = schemaObj.getUniqueKeyField();
    System.out.println(field.getName());

    System.out.println(schemaObj.getQueryParserDefaultOperator());



    /**
     *   Working with request parameters
     */

    SolrParams reqParams = req.getParams();
    String q = reqParams.get(CommonParams.Q);
    System.out.println(reqParams.get(CommonParams.Q));

    String defType = reqParams.get(QueryParsing.DEFTYPE , QParserPlugin.DEFAULT_QTYPE);
    System.out.println(defType);


    /**
     *  Working with QParser
     */
    QParser queryParser = QParser.getParser(q, defType, req);
    Query query = queryParser.getQuery();


    /**
     *   Now get searcher 
     */

    SolrIndexSearcher indexSearcher = req.getSearcher();
    IndexReader reader = indexSearcher.getIndexReader();
    DocList matchDocs = indexSearcher.getDocList(query, null, null, 1, 100000,10000);

    // Number of documents matched
    System.out.println(matchDocs.matches());
    // Get Iterator
        // get documentreader

    Document doc;
    String[] DocFields;

    DocIterator iterator = matchDocs.iterator();
    while (iterator.hasNext()){
    Integer id = iterator.nextDoc();
    System.out.println("Here I am " + id);
    doc = reader.document(id);
    DocFields = doc.getValues("state");

    for(int i=0;i<DocFields.length;i++){
        System.out.println(DocFields[i]);
    }

    }

}

  @Override
  public String getDescription() {
    return "My Search Handler";
  }

  @Override
  public String getSource() {
    return "$Source$";
  }


  @Override
  public String getVersion() {
    return "$Revision$";
  }

}

简而言之，我们要访问文档，我们需要“阅读器”一个“IndexReader”类的对象，然后从 'reader' 调用方法 'getValues(' YOUR FIELD NAME')' 。它将返回字符串数组。