Lucene

readme.md

build

mvn install

index

java -cp target/java_searcher-1.0-SNAPSHOT.jar com.github.horitaku1124.java_searcher.IndexFiles  -index ./index -docs ~/git/Excel-Extraction/data

search

java -cp target/java_searcher-1.0-SNAPSHOT.jar com.github.horitaku1124.java_searcher.SearchFiles -query 東京

IndexFiles.java

package com.github.horitaku1124.java_searcher;

import java.io.BufferedReader;
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.Date;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.LongPoint;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
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 org.apache.poi.openxml4j.exceptions.InvalidFormatException;


public class IndexFiles {
    private IndexFiles() {}

    /** 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;
            }
        }

        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 (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");

        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    /**
     * 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 {
                        String fileName = file.toAbsolutePath().toString();
                        if (fileName.endsWith(".xls") || fileName.endsWith(".xlsx")) {
                            indexDoc_xls(writer, file, attrs.lastModifiedTime().toMillis());
                        }
                    } catch (Exception e) {
                        e.printStackTrace();
                        // don't index files that can't be read.
                    }
                    return FileVisitResult.CONTINUE;
                }
            });
        } else {
            indexDoc(writer, path, Files.getLastModifiedTime(path).toMillis());
        }
    }

    static void indexDoc_xls(IndexWriter writer, Path file, long lastModified) throws IOException, InvalidFormatException {
        String content = DumpExcel.readFile(file.toString());

        // make a new, empty document
        Document doc = new 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:
        Field pathField = new StringField("path", file.toString(), Field.Store.YES);
        doc.add(pathField);

        // Add the last modified date of the file a field named "modified".
        // Use a LongPoint that is indexed (i.e. efficiently filterable with
        // PointRangeQuery).  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.
        doc.add(new LongPoint("modified", lastModified));

        // 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", content, Field.Store.YES));

        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);
        }
    }
    /** Indexes a single document */
    static void indexDoc(IndexWriter writer, Path file, long lastModified) throws IOException {
        try (InputStream stream = Files.newInputStream(file)) {
            // make a new, empty document
            Document doc = new 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:
            Field pathField = new StringField("path", file.toString(), Field.Store.YES);
            doc.add(pathField);

            // Add the last modified date of the file a field named "modified".
            // Use a LongPoint that is indexed (i.e. efficiently filterable with
            // PointRangeQuery).  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.
            doc.add(new LongPoint("modified", lastModified));

            // 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))));

            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);
            }
        }
    }
}

SearchFiles.java

package com.github.horitaku1124.java_searcher;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.nio.charset.StandardCharsets;
import java.nio.file.Files;
import java.nio.file.Paths;
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.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;

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

    private SearchFiles() {}

    /** Simple command-line based search demo. */
    public static void main(String[] args) throws Exception {
        String usage =
                "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.";
        if (args.length > 0 && ("-h".equals(args[0]) || "-help".equals(args[0]))) {
            System.out.println(usage);
            System.exit(0);
        }

        String index = "index";
        String field = "contents";
        String queries = null;
        int repeat = 0;
        boolean raw = false;
        String queryString = null;
        int hitsPerPage = 10;

        for(int i = 0;i < args.length;i++) {
            if ("-index".equals(args[i])) {
                index = args[i+1];
                i++;
            } else if ("-field".equals(args[i])) {
                field = args[i+1];
                i++;
            } else if ("-queries".equals(args[i])) {
                queries = args[i+1];
                i++;
            } else if ("-query".equals(args[i])) {
                queryString = args[i+1];
                i++;
            } else if ("-repeat".equals(args[i])) {
                repeat = Integer.parseInt(args[i+1]);
                i++;
            } else if ("-raw".equals(args[i])) {
                raw = true;
            } else if ("-paging".equals(args[i])) {
                hitsPerPage = Integer.parseInt(args[i+1]);
                if (hitsPerPage <= 0) {
                    System.err.println("There must be at least 1 hit per page.");
                    System.exit(1);
                }
                i++;
            }
        }

        IndexReader reader = DirectoryReader.open(FSDirectory.open(Paths.get(index)));
        IndexSearcher searcher = new IndexSearcher(reader);
        Analyzer analyzer = new StandardAnalyzer();

        BufferedReader in = null;
        if (queries != null) {
            in = Files.newBufferedReader(Paths.get(queries), StandardCharsets.UTF_8);
        } else {
            in = new BufferedReader(new InputStreamReader(System.in, StandardCharsets.UTF_8));
        }
        QueryParser parser = new QueryParser(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) {
                break;
            }

            line = line.trim();
            if (line.length() == 0) {
                break;
            }

            Query query = parser.parse(line);
            System.out.println("Searching for: " + query.toString(field));

            if (repeat > 0) {                           // repeat & time as benchmark
                Date start = new Date();
                for (int i = 0; i < repeat; i++) {
                    searcher.search(query, 100);
                }
                Date end = new Date();
                System.out.println("Time: "+(end.getTime()-start.getTime())+"ms");
            }

            doPagingSearch(in, searcher, query, hitsPerPage, raw, queries == null && queryString == null);

            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) throws IOException {

        // Collect enough docs to show 5 pages
        TopDocs results = searcher.search(query, 5 * hitsPerPage);
        ScoreDoc[] hits = results.scoreDocs;

        int numTotalHits = Math.toIntExact(results.totalHits);
        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);

            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.println((i+1) + ". " + path);
                    String title = doc.get("title");
                    if (title != null) {
                        System.out.println("   Title: " + doc.get("title"));
                    }
                } else {
                    System.out.println((i+1) + ". " + "No path for this document");
                }

            }

            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);
            }
        }
    }
}