Java tutorial
package back; /* * 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.tartarus.snowball.ext.EnglishStemmer; import com.opencsv.CSVReader; import java.io.BufferedReader; import java.io.File; import java.io.FileInputStream; import java.io.FileReader; import java.io.IOException; import java.io.InputStreamReader; import java.util.Date; import java.util.List; import org.apache.lucene.analysis.Analyzer; import org.apache.lucene.analysis.standard.StandardAnalyzer; import org.apache.lucene.analysis.util.CharArraySet; import org.apache.lucene.document.Document; import org.apache.lucene.index.DirectoryReader; import org.apache.lucene.index.IndexReader; import org.apache.lucene.queryparser.classic.QueryParser; import org.apache.lucene.search.IndexSearcher; import org.apache.lucene.search.Query; import org.apache.lucene.search.ScoreDoc; import org.apache.lucene.search.TopDocs; import org.apache.lucene.store.FSDirectory; import org.apache.lucene.util.Version; import org.apache.lucene.analysis.en.EnglishAnalyzer; /** Simple command-line based search demo. */ public class Searcher { private Searcher() { } /** Simple command-line based search demo. */ public static void search(String query, boolean stopword, boolean stemming, int consulta) throws Exception { String index = null; Analyzer analyzer = null; if (!stopword && !stemming) { index = ".\\indexed"; analyzer = new StandardAnalyzer(Version.LUCENE_CURRENT, new CharArraySet(Version.LUCENE_CURRENT, 0, false)); System.out.println("Nenhum Marcado"); } else if (stopword && !stemming) { index = ".\\indexedNoStpWrd"; analyzer = new StandardAnalyzer(Version.LUCENE_CURRENT); System.out.println("Primeiro Marcado"); } else if (!stopword && stemming) { index = ".\\indexedStemming"; analyzer = new EnglishAnalyzer(Version.LUCENE_CURRENT, new CharArraySet(Version.LUCENE_CURRENT, 0, false)); System.out.println("Segundo Marcado"); } else if (stopword && stemming) { index = ".\\indexedTreated"; analyzer = new EnglishAnalyzer(Version.LUCENE_CURRENT); System.out.println("Dois Marcados"); } String field = "contents"; String queries = null; int repeat = 0; boolean raw = false; String queryString = query; int hitsPerPage = 200; CSVReader CSVreader = new CSVReader(new FileReader(".\\matriz.csv")); List<String[]> myEntries = CSVreader.readAll(); IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(index))); IndexSearcher searcher = new IndexSearcher(reader); BufferedReader in = null; if (queries != null) { in = new BufferedReader(new InputStreamReader(new FileInputStream(queries), "UTF-8")); } else { in = new BufferedReader(new InputStreamReader(System.in, "UTF-8")); } QueryParser parser = new QueryParser(Version.LUCENE_40, field, analyzer); while (true) { if (queries == null && queryString == null) { // prompt the user System.out.println("Enter query: "); } String line = queryString != null ? queryString : in.readLine(); if (line == null || line.length() == -1) { break; } line = line.trim(); if (line.length() == 0) { break; } Query query1 = parser.parse(line); System.out.println("Searching for: " + query1.toString(field)); if (repeat > 0) { // repeat & time as benchmark Date start = new Date(); for (int i = 0; i < repeat; i++) { searcher.search(query1, null, 100); } Date end = new Date(); System.out.println("Time: " + (end.getTime() - start.getTime()) + "ms"); } doPagingSearch(in, searcher, query1, hitsPerPage, raw, queries == null && queryString == null, myEntries, consulta); if (queryString != null) { break; } } reader.close(); } /** * This demonstrates a typical paging search scenario, where the search * engine presents pages of size n to the user. The user can then go to the * next page if interested in the next hits. * * When the query is executed for the first time, then only enough results * are collected to fill 5 result pages. If the user wants to page beyond * this limit, then the query is executed another time and all hits are * collected. * */ public static void doPagingSearch(BufferedReader in, IndexSearcher searcher, Query query, int hitsPerPage, boolean raw, boolean interactive, List<String[]> resu, int consulta) throws IOException { //Relevante para Mineracao int[] relevantes = new int[3]; relevantes[consulta - 1] = 0; for (int i = 0; i < 200; i++) { String[] lista = resu.get(consulta - 1); if (Integer.parseInt(lista[i]) == 1) { relevantes[consulta - 1]++; } } int recuperados; int relevantesRecuperados = 0; // Collect enough docs to show 5 pages TopDocs results = searcher.search(query, 5 * hitsPerPage); ScoreDoc[] hits = results.scoreDocs; int numTotalHits = results.totalHits; recuperados = numTotalHits; System.out.println(numTotalHits + " total matching documents"); int start = 0; int end = Math.min(numTotalHits, hitsPerPage); while (true) { if (end > hits.length) { System.out.println("Only results 1 - " + hits.length + " of " + numTotalHits + " total matching documents collected."); System.out.println("Collect more (y/n) ?"); String line = in.readLine(); if (line.length() == 0 || line.charAt(0) == 'n') { break; } hits = searcher.search(query, numTotalHits).scoreDocs; } end = Math.min(hits.length, start + hitsPerPage); //troquei end por numTotalHits //LAO PRINCIPAL for (int i = start; i < end; i++) { if (raw) { // output raw format System.out.println("doc=" + hits[i].doc + " score=" + hits[i].score); continue; } Document doc = searcher.doc(hits[i].doc); String path = doc.get("path"); if (path != null) { System.out.print((i + 1) + ". " + path); String title = doc.get("title"); if (title != null) { System.out.println(" Title: " + doc.get("title")); } int docEncontrado = 0; if (path != null) { String docNumberString = path.substring(path.indexOf('#') + 1, path.indexOf(".txt")); docEncontrado = Integer.parseInt(docNumberString); } if (consulta != 0) { String[] lista = resu.get(consulta - 1); if (Integer.parseInt(lista[docEncontrado - 1]) == 1) { System.out.print(" [RELEVANT]"); relevantesRecuperados++; } } System.out.println(); } else { System.out.println((i + 1) + ". " + "No path for this document"); } } //mais matematica para mineracao if (consulta != 0) { double precision = ((double) relevantesRecuperados) / ((double) recuperados); double recall = ((double) relevantesRecuperados) / ((double) relevantes[consulta - 1]); double fmeasure = 2 * (precision * recall) / (precision + recall); System.out.println("Using information of Relevancy Matrix Row " + consulta); System.out.println("Precision: " + precision + " | Recall: " + recall); System.out.println("F-Measure: " + fmeasure); } if (!interactive || end == 0) { break; } if (numTotalHits >= end) { boolean quit = false; while (true) { System.out.print("Press "); if (start - hitsPerPage >= 0) { System.out.print("(p)revious page, "); } if (start + hitsPerPage < numTotalHits) { System.out.print("(n)ext page, "); } System.out.println("(q)uit or enter number to jump to a page."); String line = in.readLine(); if (line.length() == 0 || line.charAt(0) == 'q') { quit = true; break; } if (line.charAt(0) == 'p') { start = Math.max(0, start - hitsPerPage); break; } else if (line.charAt(0) == 'n') { if (start + hitsPerPage < numTotalHits) { start += hitsPerPage; } break; } else { int page = Integer.parseInt(line); if ((page - 1) * hitsPerPage < numTotalHits) { start = (page - 1) * hitsPerPage; break; } else { System.out.println("No such page"); } } } if (quit) break; end = Math.min(numTotalHits, start + hitsPerPage); } } } }