001 package org.apache.lucene.demo; 002 003 /* 004 * Licensed to the Apache Software Foundation (ASF) under one or more 005 * contributor license agreements. See the NOTICE file distributed with 006 * this work for additional information regarding copyright ownership. 007 * The ASF licenses this file to You under the Apache License, Version 2.0 008 * (the "License"); you may not use this file except in compliance with 009 * the License. You may obtain a copy of the License at 010 * 011 * http://www.apache.org/licenses/LICENSE-2.0 012 * 013 * Unless required by applicable law or agreed to in writing, software 014 * distributed under the License is distributed on an "AS IS" BASIS, 015 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 016 * See the License for the specific language governing permissions and 017 * limitations under the License. 018 */ 019 020 import java.io.BufferedReader; 021 import java.io.File; 022 import java.io.FileInputStream; 023 import java.io.IOException; 024 import java.io.InputStreamReader; 025 import java.util.Date; 026 027 import org.apache.lucene.analysis.Analyzer; 028 import org.apache.lucene.analysis.standard.StandardAnalyzer; 029 import org.apache.lucene.document.Document; 030 import org.apache.lucene.index.DirectoryReader; 031 import org.apache.lucene.index.IndexReader; 032 import org.apache.lucene.queryparser.classic.QueryParser; 033 import org.apache.lucene.search.IndexSearcher; 034 import org.apache.lucene.search.Query; 035 import org.apache.lucene.search.ScoreDoc; 036 import org.apache.lucene.search.TopDocs; 037 import org.apache.lucene.store.FSDirectory; 038 import org.apache.lucene.util.Version; 039 040 /** Simple command-line based search demo. */ 041 public class SearchFiles { 042 043 private SearchFiles() {} 044 045 /** Simple command-line based search demo. */ 046 public static void main(String[] args) throws Exception { 047 String usage = 048 "Usage:\tjava org.apache.lucene.demo.SearchFiles [-index dir] [-field f] [-repeat n] [-queries file] [-query string] [-raw] [-paging hitsPerPage]\n\nSee http://lucene.apache.org/core/4_1_0/demo/ for details."; 049 if (args.length > 0 && ("-h".equals(args[0]) || "-help".equals(args[0]))) { 050 System.out.println(usage); 051 System.exit(0); 052 } 053 054 String index = "index"; 055 String field = "contents"; 056 String queries = null; 057 int repeat = 0; 058 boolean raw = false; 059 String queryString = null; 060 int hitsPerPage = 10; 061 062 for(int i = 0;i < args.length;i++) { 063 if ("-index".equals(args[i])) { 064 index = args[i+1]; 065 i++; 066 } else if ("-field".equals(args[i])) { 067 field = args[i+1]; 068 i++; 069 } else if ("-queries".equals(args[i])) { 070 queries = args[i+1]; 071 i++; 072 } else if ("-query".equals(args[i])) { 073 queryString = args[i+1]; 074 i++; 075 } else if ("-repeat".equals(args[i])) { 076 repeat = Integer.parseInt(args[i+1]); 077 i++; 078 } else if ("-raw".equals(args[i])) { 079 raw = true; 080 } else if ("-paging".equals(args[i])) { 081 hitsPerPage = Integer.parseInt(args[i+1]); 082 if (hitsPerPage <= 0) { 083 System.err.println("There must be at least 1 hit per page."); 084 System.exit(1); 085 } 086 i++; 087 } 088 } 089 090 IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(index))); 091 IndexSearcher searcher = new IndexSearcher(reader); 092 // :Post-Release-Update-Version.LUCENE_XY: 093 Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_47); 094 095 BufferedReader in = null; 096 if (queries != null) { 097 in = new BufferedReader(new InputStreamReader(new FileInputStream(queries), "UTF-8")); 098 } else { 099 in = new BufferedReader(new InputStreamReader(System.in, "UTF-8")); 100 } 101 // :Post-Release-Update-Version.LUCENE_XY: 102 QueryParser parser = new QueryParser(Version.LUCENE_47, field, analyzer); 103 while (true) { 104 if (queries == null && queryString == null) { // prompt the user 105 System.out.println("Enter query: "); 106 } 107 108 String line = queryString != null ? queryString : in.readLine(); 109 110 if (line == null || line.length() == -1) { 111 break; 112 } 113 114 line = line.trim(); 115 if (line.length() == 0) { 116 break; 117 } 118 119 Query query = parser.parse(line); 120 System.out.println("Searching for: " + query.toString(field)); 121 122 if (repeat > 0) { // repeat & time as benchmark 123 Date start = new Date(); 124 for (int i = 0; i < repeat; i++) { 125 searcher.search(query, null, 100); 126 } 127 Date end = new Date(); 128 System.out.println("Time: "+(end.getTime()-start.getTime())+"ms"); 129 } 130 131 doPagingSearch(in, searcher, query, hitsPerPage, raw, queries == null && queryString == null); 132 133 if (queryString != null) { 134 break; 135 } 136 } 137 reader.close(); 138 } 139 140 /** 141 * This demonstrates a typical paging search scenario, where the search engine presents 142 * pages of size n to the user. The user can then go to the next page if interested in 143 * the next hits. 144 * 145 * When the query is executed for the first time, then only enough results are collected 146 * to fill 5 result pages. If the user wants to page beyond this limit, then the query 147 * is executed another time and all hits are collected. 148 * 149 */ 150 public static void doPagingSearch(BufferedReader in, IndexSearcher searcher, Query query, 151 int hitsPerPage, boolean raw, boolean interactive) throws IOException { 152 153 // Collect enough docs to show 5 pages 154 TopDocs results = searcher.search(query, 5 * hitsPerPage); 155 ScoreDoc[] hits = results.scoreDocs; 156 157 int numTotalHits = results.totalHits; 158 System.out.println(numTotalHits + " total matching documents"); 159 160 int start = 0; 161 int end = Math.min(numTotalHits, hitsPerPage); 162 163 while (true) { 164 if (end > hits.length) { 165 System.out.println("Only results 1 - " + hits.length +" of " + numTotalHits + " total matching documents collected."); 166 System.out.println("Collect more (y/n) ?"); 167 String line = in.readLine(); 168 if (line.length() == 0 || line.charAt(0) == 'n') { 169 break; 170 } 171 172 hits = searcher.search(query, numTotalHits).scoreDocs; 173 } 174 175 end = Math.min(hits.length, start + hitsPerPage); 176 177 for (int i = start; i < end; i++) { 178 if (raw) { // output raw format 179 System.out.println("doc="+hits[i].doc+" score="+hits[i].score); 180 continue; 181 } 182 183 Document doc = searcher.doc(hits[i].doc); 184 String path = doc.get("path"); 185 if (path != null) { 186 System.out.println((i+1) + ". " + path); 187 String title = doc.get("title"); 188 if (title != null) { 189 System.out.println(" Title: " + doc.get("title")); 190 } 191 } else { 192 System.out.println((i+1) + ". " + "No path for this document"); 193 } 194 195 } 196 197 if (!interactive || end == 0) { 198 break; 199 } 200 201 if (numTotalHits >= end) { 202 boolean quit = false; 203 while (true) { 204 System.out.print("Press "); 205 if (start - hitsPerPage >= 0) { 206 System.out.print("(p)revious page, "); 207 } 208 if (start + hitsPerPage < numTotalHits) { 209 System.out.print("(n)ext page, "); 210 } 211 System.out.println("(q)uit or enter number to jump to a page."); 212 213 String line = in.readLine(); 214 if (line.length() == 0 || line.charAt(0)=='q') { 215 quit = true; 216 break; 217 } 218 if (line.charAt(0) == 'p') { 219 start = Math.max(0, start - hitsPerPage); 220 break; 221 } else if (line.charAt(0) == 'n') { 222 if (start + hitsPerPage < numTotalHits) { 223 start+=hitsPerPage; 224 } 225 break; 226 } else { 227 int page = Integer.parseInt(line); 228 if ((page - 1) * hitsPerPage < numTotalHits) { 229 start = (page - 1) * hitsPerPage; 230 break; 231 } else { 232 System.out.println("No such page"); 233 } 234 } 235 } 236 if (quit) break; 237 end = Math.min(numTotalHits, start + hitsPerPage); 238 } 239 } 240 } 241 }