cs571.proj1.IndexFiles.java Source code

Java tutorial

Introduction

Here is the source code for cs571.proj1.IndexFiles.java

Source

package cs571.proj1;
/*
 * 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.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.FieldType;
import org.apache.lucene.document.LongField;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.IndexOptions;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig.OpenMode;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

import java.io.BufferedReader;
import java.io.ByteArrayInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.nio.charset.StandardCharsets;
import java.nio.file.FileVisitResult;
import java.nio.file.Files;
import java.nio.file.Path;
import java.nio.file.Paths;
import java.nio.file.SimpleFileVisitor;
import java.nio.file.attribute.BasicFileAttributes;
import java.util.Arrays;
import java.util.Date;
import java.util.HashSet;
import java.util.Set;

/** Index all text files under a directory.
 * <p>
 * This is a command-line application demonstrating simple Lucene indexing.
 * Run it with no command-line arguments for usage information.
 */
public class IndexFiles {

    private IndexFiles() {
    }

    public static boolean tfidf = false;
    public static boolean bm25 = false;

    /** Index all text files under a directory. */
    public static void main(String[] args) {
        String usage = "java org.apache.lucene.demo.IndexFiles"
                + " [-index INDEX_PATH] [-docs DOCS_PATH] [-update]\n\n"
                + "This indexes the documents in DOCS_PATH, creating a Lucene index"
                + "in INDEX_PATH that can be searched with SearchFiles";
        String indexPath = "index";
        String docsPath = null;
        boolean create = true;
        for (int i = 0; i < args.length; i++) {
            if ("-index".equals(args[i])) {
                indexPath = args[i + 1];
                i++;
            } else if ("-docs".equals(args[i])) {
                docsPath = args[i + 1];
                i++;
            } else if ("-update".equals(args[i])) {
                create = false;
            } else if ("-tfidf".equals(args[i])) {
                tfidf = true;
            } else if ("-bm25".equals(args[i])) {
                bm25 = true;
            }

        }

        if (docsPath == null) {
            System.err.println("Usage: " + usage);
            System.exit(1);
        }

        final Path docDir = Paths.get(docsPath);
        if (!Files.isReadable(docDir)) {
            System.out.println("Document directory '" + docDir.toAbsolutePath()
                    + "' does not exist or is not readable, please check the path");
            System.exit(1);
        }

        Date start = new Date();
        try {
            System.out.println("Indexing to directory '" + indexPath + "'...");

            Directory dir = FSDirectory.open(Paths.get(indexPath));
            Analyzer analyzer = new StandardAnalyzer();
            IndexWriterConfig iwc = new IndexWriterConfig(analyzer);
            if (tfidf)
                iwc.setSimilarity(new TFIDF());
            if (bm25)
                iwc.setSimilarity(new BM25());
            if (create) {
                // Create a new index in the directory, removing any
                // previously indexed documents:
                iwc.setOpenMode(OpenMode.CREATE);
            } else {
                // Add new documents to an existing index:
                iwc.setOpenMode(OpenMode.CREATE_OR_APPEND);
            }

            // Optional: for better indexing performance, if you
            // are indexing many documents, increase the RAM
            // buffer.  But if you do this, increase the max heap
            // size to the JVM (eg add -Xmx512m or -Xmx1g):
            //
            // iwc.setRAMBufferSizeMB(256.0);

            IndexWriter writer = new IndexWriter(dir, iwc);
            indexDocs(writer, docDir);

            // NOTE: if you want to maximize search performance,
            // you can optionally call forceMerge here.  This can be
            // a terribly costly operation, so generally it's only
            // worth it when your index is relatively static (ie
            // you're done adding documents to it):
            //
            // writer.forceMerge(1);

            writer.close();

            Date end = new Date();
            System.out.println(end.getTime() - start.getTime() + " total milliseconds");
            System.out.println("Total # of Docs Indexed: " + numOfDocuments);

        } catch (IOException e) {
            System.out.println(" caught a " + e.getClass() + "\n with message: " + e.getMessage());
        }
    }

    /**
     * Indexes the given file using the given writer, or if a directory is given,
     * recurses over files and directories found under the given directory.
     * 
     * NOTE: This method indexes one document per input file.  This is slow.  For good
     * throughput, put multiple documents into your input file(s).  An example of this is
     * in the benchmark module, which can create "line doc" files, one document per line,
     * using the
     * <a href="../../../../../contrib-benchmark/org/apache/lucene/benchmark/byTask/tasks/WriteLineDocTask.html"
     * >WriteLineDocTask</a>.
     *  
     * @param writer Writer to the index where the given file/dir info will be stored
     * @param path The file to index, or the directory to recurse into to find files to index
     * @throws IOException If there is a low-level I/O error
     */
    static void indexDocs(final IndexWriter writer, Path path) throws IOException {
        if (Files.isDirectory(path)) {
            Files.walkFileTree(path, new SimpleFileVisitor<Path>() {
                @Override
                public FileVisitResult visitFile(Path file, BasicFileAttributes attrs) throws IOException {
                    try {
                        indexDoc(writer, file, attrs.lastModifiedTime().toMillis());
                    } catch (IOException ignore) {
                        // don't index files that can't be read.
                    }
                    return FileVisitResult.CONTINUE;
                }
            });
        } else {
            indexDoc(writer, path, Files.getLastModifiedTime(path).toMillis());
        }
    }

    protected static boolean checkForIgnoredFile(String fileName) {
        for (String s : ignore_file) {
            if (fileName.equals(s))
                return true;
        }
        return false;
    }

    protected static boolean checkForIgnoreLine(String line) {
        for (String s : ignore_line) {
            if (line.trim().equals(s))
                return true;
        }
        return false;
    }

    protected static String removeTags(String line) {
        int beginIndex = line.indexOf('>');
        int endIndex = line.lastIndexOf('<');
        if (beginIndex == -1 || endIndex == -1 || beginIndex > endIndex) {
            System.out.println(line);
            return null;
        }
        return line.substring(beginIndex + 1, endIndex).trim();
    }

    //  private static boolean checkForIgnoreStartsWith(String line) {
    //     for(String s : ignore_startsWith){
    //        if(line.startsWith(s)) return true;
    //     }
    //      return false;
    //   }

    public final static String docStart = "<DOC>";
    public final static String docEnd = "</DOC>";
    public final static String textStart = "<TEXT>";
    public final static String textEnd = "</TEXT>";
    public final static Set<String> ignore_line = new HashSet<>(
            Arrays.asList("<p>", "</p>", "<ABS>", "<AU>", "<DATE1>", "<H1>", "<HEADER>", "<HT>", "<TEXT>", "<TR>",
                    "<BYLINE>", "<CORRECTION>", "<CORRECTION-DATE>", "<DATE>", "<DATELINE>", "<GRAPHIC>",
                    "<LENGTH>", "<SECTION>", "<SUBJECT>", "<TYPE>"));
    public final static Set<String> ignore_startsWith = new HashSet<>(Arrays.asList("Language: ", "Article Type:"));
    public final static Set<String> ignore_file = new HashSet<>(
            Arrays.asList("readchg.txt", "readmefb.txt", "readfrcg", "readmeft", "readmela.txt"));
    public final static String docNO_start = "<DOCNO>";
    public final static String docID_start = "<DOCID>";
    public static int numOfDocuments = 0;

    /** Indexes a single document */
    static void indexDoc(IndexWriter writer, Path file, long lastModified) throws IOException {
        if (checkForIgnoredFile(file.getFileName().toString()))
            return;
        try (InputStream stream = Files.newInputStream(file)) {
            // make a new, empty document

            // Add the path of the file as a field named "path".  Use a
            // field that is indexed (i.e. searchable), but don't tokenize 
            // the field into separate words and don't index term frequency
            // or positional information:

            // Add the last modified date of the file a field named "modified".
            // Use a LongField that is indexed (i.e. efficiently filterable with
            // NumericRangeFilter).  This indexes to milli-second resolution, which
            // is often too fine.  You could instead create a number based on
            // year/month/day/hour/minutes/seconds, down the resolution you require.
            // For example the long value 2011021714 would mean
            // February 17, 2011, 2-3 PM.

            // Add the contents of the file to a field named "contents".  Specify a Reader,
            // so that the text of the file is tokenized and indexed, but not stored.
            // Note that FileReader expects the file to be in UTF-8 encoding.
            // If that's not the case searching for special characters will fail.

            //doc.add(new TextField("contents", new BufferedReader(new InputStreamReader(stream, StandardCharsets.UTF_8))));

            BufferedReader br = new BufferedReader(new InputStreamReader(stream, StandardCharsets.UTF_8));
            String line, docNO = null, docID = null, s;
            StringBuilder sb = new StringBuilder();
            Field docIDField = null;
            Document doc = new Document();

            boolean docFound = false;
            //      boolean testOut = false;
            //      PrintWriter pw = new PrintWriter("out.txt");
            while ((line = br.readLine()) != null) {
                line = line.trim();
                //To-do detect document boundaries
                if (line.startsWith(docNO_start)) {
                    docNO = removeTags(line);
                    continue;
                }
                if (line.startsWith(docID_start)) {
                    docID = removeTags(line);
                    continue;
                }

                //         if(checkForIgnoreStartsWith(line)){continue;}
                //         if(checkForIgnoreLine(line)){continue;}

                if (line.equals(docStart)) {
                    docFound = true;
                    //testOut = true;
                    continue;
                }

                if (line.equals(docEnd)) {
                    docFound = false;

                    if (docNO != null) {
                        docIDField = new StringField("docID", docNO, Field.Store.YES);
                        doc.add(docIDField);
                    } else if (docID != null) {
                        docIDField = new StringField("docID", docID, Field.Store.YES);
                        doc.add(docIDField);
                    } else {
                        continue;
                    }

                    //doc.add(new TermVector("contents",sb.toString(),Field.Store.NO));
                    if (tfidf || bm25) {
                        FieldType tv = new FieldType();
                        tv.setTokenized(true);
                        tv.setStoreTermVectors(true);
                        tv.setIndexOptions(IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS);
                        s = sb.toString();
                        byte[] bytes = s.getBytes();
                        ByteArrayInputStream bstream = new ByteArrayInputStream(bytes);
                        InputStreamReader isr = new InputStreamReader(bstream);
                        doc.add(new Field("contents", isr, tv));
                    } else {
                        doc.add(new TextField("contents", sb.toString(), Field.Store.NO));
                    }

                    Field pathField = new StringField("path", file.toString(), Field.Store.YES);
                    doc.add(pathField);
                    doc.add(new LongField("modified", lastModified, Field.Store.NO));
                    numOfDocuments++;
                    sb.setLength(0);
                    //             testOut = false;
                    //             pw.close();
                    if (writer.getConfig().getOpenMode() == OpenMode.CREATE) {
                        // New index, so we just add the document (no old document can be there):
                        System.out.println("adding " + file);
                        writer.addDocument(doc);
                    } else {
                        // Existing index (an old copy of this document may have been indexed) so 
                        // we use updateDocument instead to replace the old one matching the exact 
                        // path, if present:
                        System.out.println("updating " + file);
                        writer.updateDocument(new Term("path", file.toString()), doc);
                    }
                    doc = new Document();
                    continue;
                }

                if (docFound) {
                    sb.append(line).append("\n");
                    //            if(testOut) pw.println(line);
                }

            }

        }
    }

}