/**
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

import java.io.BufferedReader;
import java.io.FileReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.Date;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.FilterIndexReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.queryParser.MultiFieldQueryParser;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.BooleanClause;
import org.apache.lucene.search.HitCollector;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.Searcher;
import org.apache.lucene.search.TopDocCollector;

/** Simple command-line based search demo. */
public class SearchFiles {

  /** Use the norms from one field for all fields.  Norms are read into memory,
   * using a byte of memory per document per searched field.  This can cause
   * search of large collections with a large number of fields to run out of
   * memory.  If all of the fields contain only a single token, then the norms
   * are all identical, then single norm vector may be shared. */
  private static class OneNormsReader extends FilterIndexReader {
    private String field;

    public OneNormsReader(IndexReader in, String field) {
      super(in);
      this.field = field;
    }

    public byte[] norms(String field) throws IOException {
      return in.norms(this.field);
    }
  }

  private SearchFiles() {}

  /** Simple command-line based search demo. */
  public static void main(String[] args) throws Exception {
    String index = "index";
    String field = "content";
    boolean multipleFields = true;
    IndexReader reader = IndexReader.open(index);//IndexReader 根据 index 指定的路径 访问索引，扫描索引。
    Searcher searcher = new IndexSearcher(reader);
    Analyzer analyzer = new StandardAnalyzer();
    BufferedReader in =new BufferedReader(new InputStreamReader(System.in, "UTF-8"));
    while (true) {
   System.out.println("Enter query: ");
   String line = in.readLine();
   if (line == null || line.length() == -1)
    break;
   line = line.trim();
   if (line.length() == 0)
    break;
   if (!multipleFields) {
    QueryParser parser = new QueryParser(field, analyzer);
    Query query = parser.parse(field);// 根据指定的单个field查询
    parser.setDefaultOperator(parser.OR_OPERATOR.OR);
    //多个字符串以空格份格时，OR  : a b  含有a或b均可。
    //AND   a b 必须含有 a和b。
    doPagingSearch(searcher, query);
    
   } else {

    String[] fields = new String[2];
    fields[0] = "contents";
    fields[1] = "name";
    BooleanClause.Occur[] flags = new BooleanClause.Occur[] {
      BooleanClause.Occur.SHOULD, BooleanClause.Occur.SHOULD };
    //根据多个field查询时。should,should查询字段在 name或是contents任何一个中，均做为一条记录返回。
    //must,must .必须 即在 name 中，又在contents 中。
    Query query = MultiFieldQueryParser.parse(line, fields, flags,
      analyzer);
    doPagingSearch(searcher, query);
   }
  }
    reader.close();
  }
 
  /**
   * This method uses a custom HitCollector implementation which simply prints out
   * the docId and score of every matching document.
   *
   *  This simulates the streaming search use case, where all hits are supposed to
   *  be processed, regardless of their relevance.
   */

  public static void doPagingSearch( Searcher searcher, Query query) throws IOException {
 
    // Collect enough docs to show 5 pages
    TopDocCollector collector = new TopDocCollector(20);//最多结果集个数。
    searcher.search(query, collector);
    ScoreDoc[] hits = collector.topDocs().scoreDocs;
    int numTotalHits = collector.getTotalHits();//搜索到的符合条件的记录总条数。
    System.out.println(numTotalHits + " total matching documents");

    for(int i=0;i<numTotalHits;i++){
        Document doc = searcher.doc(hits[i].doc);
        System.out.println("path.."+doc.get("path"));
        System.out.println("modified.."+doc.get("modified"));
        System.out.println("name.."+doc.get("name"));
        System.out.println("parent"+doc.get("parent"));
        System.out.println("content..."+doc.get("content"));
    }
  }
}

/**
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.index.IndexWriter;

import java.io.File;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.util.Date;

/** Index all text files under a directory. */
public class IndexFiles {
 
  private IndexFiles() {}

  static final File INDEX_DIR = new File("index");//索引止录。建在当前目录的/index下
 
  /** Index all text files under a directory. */
  public static void main(String[] args) {//args[0] 文件路径.  main 方法：对args[0]指定的文件路径下的所有文件建立索引。
  final File docDir = new File(args[0]);
  if (!docDir.exists() || !docDir.canRead()) {
   System.out .println("Document directory '" + docDir.getAbsolutePath() + "' does not exist or is not readable, please check the path");
   System.exit(1);
  }
   
    Date start = new Date();
    try {
   IndexWriter writer = new IndexWriter(INDEX_DIR, new StandardAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
   //IndexWriter负责创建和维护索引
   //IndexWriter(String path, Analyzer a, boolean create, IndexWriter.MaxFieldLength mfl)
   //path:路径 Analyzer:文本分析器  create:是否创建新索引  mfl 最大field数量
   System.out.println("Indexing to directory '" + INDEX_DIR + "'...");
   indexDocs(writer, docDir);
   System.out.println("Optimizing...");
   writer.optimize();//优化索引
   writer.close();//关闭
   Date end = new Date();
   System.out.println(end.getTime() - start.getTime() + " total milliseconds");
  } catch (IOException e) {
   System.out.println(" caught a " + e.getClass()
     + "\n with message: " + e.getMessage());
  }
  }

  static void indexDocs(IndexWriter writer, File file) throws IOException {
  // do not try to index files that cannot be read
  if (file.canRead()) {
   if (file.isDirectory()) {
    String[] files = file.list();
    // an IO error could occur
    if (files != null) {
     for (int i = 0; i < files.length; i++) {
      indexDocs(writer, new File(file, files[i]));
     }
    }
   } else {
    System.out.println("adding " + file);
    try {
     writer.addDocument(FileDocument.Document(file));
    }
    // at least on windows, some temporary files raise this
    // exception with an "access denied" message
    // checking if the file can be read doesn't help
    catch (FileNotFoundException fnfe) {
     ;
    }
   }
  }
 }
}