Example usage for org.apache.lucene.index IndexWriter updateDocument

List of usage examples for org.apache.lucene.index IndexWriter updateDocument

Introduction

In this page you can find the example usage for org.apache.lucene.index IndexWriter updateDocument.

Prototype

private long updateDocument(final DocumentsWriterDeleteQueue.Node<?> delNode,
            Iterable<? extends IndexableField> doc) throws IOException 

Source Link

Usage

From source file:sisTradicional.IndexFiles.java

License:Apache License

/**
 * Indexes the given file using the given writer, or if a directory is given,
 * recurses over files and directories found under the given directory.
 * /*from w  w  w  .j a  va2s . c om*/
 * 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 file 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(IndexWriter writer, File file, boolean temporal) 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]), temporal);
                }
            }
        } else {

            FileInputStream fis;
            try {
                fis = new FileInputStream(file);
            } catch (FileNotFoundException fnfe) {
                // 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
                return;
            }

            try {

                // 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.getName(), Field.Store.YES);
                doc.add(pathField);

                //TODO: add url

                // 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.
                doc.add(new LongField("modified", file.lastModified(), Field.Store.YES));

                // 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(fis, "UTF-8"))));
                try {
                    DocumentBuilderFactory DBF = DocumentBuilderFactory.newInstance();
                    DocumentBuilder DB = DBF.newDocumentBuilder();
                    org.w3c.dom.Document xmlDoc = DB.parse(file);
                    if (xmlDoc.getElementsByTagName("dc:title").item(0) != null) {
                        doc.add(new TextField("title",
                                xmlDoc.getElementsByTagName("dc:title").item(0).getTextContent(),
                                Field.Store.YES));
                    }
                    NodeList creatorList = xmlDoc.getElementsByTagName("dc:creator");
                    if (creatorList.item(0) != null) {
                        String creators = creatorList.item(0).getTextContent();
                        for (int i = 1; i < creatorList.getLength(); i++) {
                            creators = creators + " " + creatorList.item(i).getTextContent();
                        }
                        doc.add(new TextField("creator", creators, Field.Store.YES));
                    }
                    if (xmlDoc.getElementsByTagName("dc:date").item(0) != null) {
                        doc.add(new TextField("date",
                                xmlDoc.getElementsByTagName("dc:date").item(0).getTextContent(),
                                Field.Store.YES));
                    }
                    if (xmlDoc.getElementsByTagName("dc:publisher").item(0) != null) {
                        doc.add(new TextField("publisher",
                                xmlDoc.getElementsByTagName("dc:publisher").item(0).getTextContent(),
                                Field.Store.YES));
                    }

                } catch (ParserConfigurationException e) {

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

                    e.printStackTrace();
                }
                doc.add(new TextField("contents", new BufferedReader(new InputStreamReader(fis, "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.getName());
                    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.getPath()), doc);
                }

            } finally {
                fis.close();
                if (temporal) {
                    file.delete();
                }
            }
        }
    }
}

From source file:stemEvalLucene.evalLucene.java

License:Apache License

/** 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);// w ww.  j a  v a 2 s.c  om

        String f = file.getFileName().toString();
        f = f.replaceFirst("\\.txt", "");
        doc.add(new StringField("filename", f, Field.Store.YES));

        // 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.
        doc.add(new LongField("modified", lastModified, Field.Store.NO));

        // 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):
            //log("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:
            //log("updating " + file);
            writer.updateDocument(new Term("path", file.toString()), doc);
        }
    }
}

From source file:test.IndexFiles.java

License:Apache License

/** 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();
        //Document doc = LucenePDFDocument

        // 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);/*w  w w  .  ja va  2  s. co  m*/

        // 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);
        }
    }
}

From source file:tmp.IndexFiles.java

License:Apache License

/** Indexes a single document */
public 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);/*from  w w w.  j a va  2s .co  m*/

        // 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.
        doc.add(new LongField("modified", lastModified, Field.Store.NO));

        // 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);
        }
    }
}

From source file:trabajo.IndexFiles.java

License:Apache License

/**
 * Indexes the given file using the given writer, or if a directory is
 * given, recurses over files and directories found under the given
 * directory.//from   www .  j  av a  2 s.com
 * 
 * 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 file
 *            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(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 {

            FileInputStream fis;
            try {
                fis = new FileInputStream(file);
            } catch (FileNotFoundException fnfe) {
                // 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
                return;
            }

            try {

                // 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.getPath(), Field.Store.YES);
                doc.add(pathField);

                // 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.
                doc.add(new LongField("modified", file.lastModified(), Field.Store.NO));

                // 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(fis, "UTF-8"))));

                insertIndexTag("title", file, doc, true);
                insertIndexTag("identifier", file, doc, false);
                insertIndexTag("language", file, doc, true);
                insertIndexTag("description", file, doc, true);
                insertIndexTag("creator", file, doc, true);
                insertIndexTag("publisher", file, doc, true);
                insertIndexTag("date", file, doc, false);

                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.getPath()), doc);
                }

            } finally {
                fis.close();
            }
        }
    }
}

From source file:uk.ac.glasgow.scclippy.plugin.lucene.IndexFiles.java

License:Apache License

/**
 * Indexes a single document//from ww w .  java2s  .  c  om
 */
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 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.
        doc.add(new LongField("modified", lastModified, Field.Store.NO));

        // 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):
            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:
            writer.updateDocument(new Term("path", file.toString()), doc);
        }
        filesIndexed++;
    }
}