001/*
002 * Licensed to the Apache Software Foundation (ASF) under one or more
003 * contributor license agreements.  See the NOTICE file distributed with
004 * this work for additional information regarding copyright ownership.
005 * The ASF licenses this file to You under the Apache License, Version 2.0
006 * (the "License"); you may not use this file except in compliance with
007 * the License.  You may obtain a copy of the License at
008 *
009 *     http://www.apache.org/licenses/LICENSE-2.0
010 *
011 * Unless required by applicable law or agreed to in writing, software
012 * distributed under the License is distributed on an "AS IS" BASIS,
013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014 * See the License for the specific language governing permissions and
015 * limitations under the License.
016 */
017package org.apache.lucene.demo.xmlparser;
018
019import java.io.BufferedReader;
020import java.io.IOException;
021import java.io.InputStream;
022import java.io.InputStreamReader;
023import java.nio.charset.StandardCharsets;
024import java.util.Enumeration;
025import java.util.Properties;
026import java.util.StringTokenizer;
027
028import javax.servlet.RequestDispatcher;
029import javax.servlet.ServletConfig;
030import javax.servlet.ServletException;
031import javax.servlet.http.HttpServlet;
032import javax.servlet.http.HttpServletRequest;
033import javax.servlet.http.HttpServletResponse;
034
035import org.apache.lucene.analysis.Analyzer;
036import org.apache.lucene.analysis.standard.StandardAnalyzer;
037import org.apache.lucene.document.Document;
038import org.apache.lucene.document.Field;
039import org.apache.lucene.document.FieldType;
040import org.apache.lucene.document.TextField;
041import org.apache.lucene.index.DirectoryReader;
042import org.apache.lucene.index.IndexReader;
043import org.apache.lucene.index.IndexWriter;
044import org.apache.lucene.index.IndexWriterConfig;
045import org.apache.lucene.queryparser.xml.CorePlusExtensionsParser;
046import org.apache.lucene.queryparser.xml.QueryTemplateManager;
047import org.apache.lucene.search.IndexSearcher;
048import org.apache.lucene.search.Query;
049import org.apache.lucene.search.ScoreDoc;
050import org.apache.lucene.search.TopDocs;
051import org.apache.lucene.store.RAMDirectory;
052
053/**
054 * Example servlet that uses the XML queryparser.
055 * <p>
056 * NOTE: you must provide CSV data in <code>/WEB-INF/data.tsv</code>
057 * for the demo to work!
058 */
059public class FormBasedXmlQueryDemo extends HttpServlet {
060
061  private QueryTemplateManager queryTemplateManager;
062  private CorePlusExtensionsParser xmlParser;
063  private IndexSearcher searcher;
064  private Analyzer analyzer = new StandardAnalyzer();
065
066  /** for instantiation by the servlet container */
067  public FormBasedXmlQueryDemo() {}
068
069  @Override
070  public void init(ServletConfig config) throws ServletException {
071    super.init(config);
072    try {
073      openExampleIndex();
074
075      //load servlet configuration settings
076      String xslFile = config.getInitParameter("xslFile");
077      String defaultStandardQueryParserField = config.getInitParameter("defaultStandardQueryParserField");
078
079
080      //Load and cache choice of XSL query template using QueryTemplateManager
081      queryTemplateManager = new QueryTemplateManager(
082          getServletContext().getResourceAsStream("/WEB-INF/" + xslFile));
083
084      //initialize an XML Query Parser for use by all threads
085      xmlParser = new CorePlusExtensionsParser(defaultStandardQueryParserField, analyzer);
086    } catch (Exception e) {
087      throw new ServletException("Error loading query template", e);
088    }
089  }
090
091  @Override
092  protected void doPost(HttpServletRequest request, HttpServletResponse response) throws ServletException, IOException {
093    //Take all completed form fields and add to a Properties object
094    Properties completedFormFields = new Properties();
095    Enumeration<?> pNames = request.getParameterNames();
096    while (pNames.hasMoreElements()) {
097      String propName = (String) pNames.nextElement();
098      String value = request.getParameter(propName);
099      if ((value != null) && (value.trim().length() > 0)) {
100        completedFormFields.setProperty(propName, value);
101      }
102    }
103
104    try {
105      //Create an XML query by populating template with given user criteria
106      org.w3c.dom.Document xmlQuery = queryTemplateManager.getQueryAsDOM(completedFormFields);
107
108      //Parse the XML to produce a Lucene query
109      Query query = xmlParser.getQuery(xmlQuery.getDocumentElement());
110
111      //Run the query
112      TopDocs topDocs = searcher.search(query, 10);
113
114      //and package the results and forward to JSP
115      if (topDocs != null) {
116        ScoreDoc[] sd = topDocs.scoreDocs;
117        Document[] results = new Document[sd.length];
118        for (int i = 0; i < results.length; i++) {
119          results[i] = searcher.doc(sd[i].doc);
120          request.setAttribute("results", results);
121        }
122      }
123      RequestDispatcher dispatcher = getServletContext().getRequestDispatcher("/index.jsp");
124      dispatcher.forward(request, response);
125    }
126    catch (Exception e) {
127      throw new ServletException("Error processing query", e);
128    }
129  }
130
131  private void openExampleIndex() throws IOException {
132    //Create a RAM-based index from our test data file
133    RAMDirectory rd = new RAMDirectory();
134    IndexWriterConfig iwConfig = new IndexWriterConfig(analyzer);
135    IndexWriter writer = new IndexWriter(rd, iwConfig);
136    InputStream dataIn = getServletContext().getResourceAsStream("/WEB-INF/data.tsv");
137    BufferedReader br = new BufferedReader(new InputStreamReader(dataIn, StandardCharsets.UTF_8));
138    String line = br.readLine();
139    final FieldType textNoNorms = new FieldType(TextField.TYPE_STORED);
140    textNoNorms.setOmitNorms(true);
141    while (line != null) {
142      line = line.trim();
143      if (line.length() > 0) {
144        //parse row and create a document
145        StringTokenizer st = new StringTokenizer(line, "\t");
146        Document doc = new Document();
147        doc.add(new Field("location", st.nextToken(), textNoNorms));
148        doc.add(new Field("salary", st.nextToken(), textNoNorms));
149        doc.add(new Field("type", st.nextToken(), textNoNorms));
150        doc.add(new Field("description", st.nextToken(), textNoNorms));
151        writer.addDocument(doc);
152      }
153      line = br.readLine();
154    }
155    writer.close();
156
157    //open searcher
158    // this example never closes it reader!
159    IndexReader reader = DirectoryReader.open(rd);
160    searcher = new IndexSearcher(reader);
161  }
162}