Example usage for org.apache.lucene.document StringField StringField

Introduction

In this page you can find the example usage for org.apache.lucene.document StringField StringField.

Prototype

public StringField(String name, BytesRef value, Store stored) 

Source Link

Document

Creates a new binary StringField, indexing the provided binary (BytesRef) value as a single token.

Usage

From source file:MyServlet.java

private static void addDoc(IndexWriter w, String Class, String number, String time, String department)
        throws IOException {
    Document doc = new Document();
    // A text field will be tokenized
    doc.add(new TextField("Classes", Class, Field.Store.YES));
    // We use a string field for isbn because we don\'t want it tokenized
    doc.add(new StringField("Number", number, Field.Store.YES));
    doc.add(new StringField("Time", time, Field.Store.YES));
    doc.add(new StringField("Department", department, Field.Store.YES));
    w.addDocument(doc);/*from  w  ww .java  2  s  . c o m*/
}

---

From source file:FileIndexer.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);//  ww w.  j a  v a 2  s . c om

        // 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:IrqaQuery.java

License:Apache License

public static void indexDoc(String docid, String... args) throws IOException {
    //        docid, title, contents,...
    Document doc = new Document();

    Field pathField = new StringField("docid", docid, Field.Store.YES);
    doc.add(pathField);//from  w  w  w  . j  a v a  2s  . co  m

    for (int i = 0; i < args.length; i += 2) {
        String field = args[i];
        String field_text = args[i + 1];
        doc.add(new TextField(field, field_text, Field.Store.NO));
        //            System.out.println("[doc.add]" + path + ":" + field + ":" + field_text);
    }

    System.out.println("adding " + docid);
    writer.addDocument(doc);
}

---

From source file:DocIndexer.java

License:Apache License

private RAMDirectory index() throws IOException, UnsupportedEncodingException, FileNotFoundException {
    RAMDirectory directory = new RAMDirectory();
    IndexWriterConfig config = new IndexWriterConfig(new StandardAnalyzer(CharArraySet.EMPTY_SET));
    config.setOpenMode(OpenMode.CREATE);
    config.setCommitOnClose(true);/*ww w .  j ava  2 s . co  m*/
    try (IndexWriter iwriter = new IndexWriter(directory, config)) {
        for (String inputFile : inputFiles) {
            File file = new File(inputFile);
            if (file.length() == 0) {
                continue;
            }

            String title;
            try (BufferedReader titleReader = new BufferedReader(
                    new InputStreamReader(new FileInputStream(file), "UTF-8"))) {
                title = titleReader.readLine();
                if (title != null && title.startsWith("[[")) {
                    // Generally the first line of the txt is the title. In a few cases the
                    // first line is a "[[tag]]" and the second line is the title.
                    title = titleReader.readLine();
                }
            }
            Matcher matcher = SECTION_HEADER.matcher(title);
            if (matcher.matches()) {
                title = matcher.group(1);
            }

            String outputFile = AsciiDoctor.mapInFileToOutFile(inputFile, inExt, outExt);
            try (FileReader reader = new FileReader(file)) {
                Document doc = new Document();
                doc.add(new TextField(Constants.DOC_FIELD, reader));
                doc.add(new StringField(Constants.URL_FIELD, prefix + outputFile, Field.Store.YES));
                doc.add(new TextField(Constants.TITLE_FIELD, title, Field.Store.YES));
                iwriter.addDocument(doc);
            }
        }
    }
    return directory;
}

---

From source file:LuceneIndexDirectoryOrFile.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 ww w .j  a  va2s  . c  o m*/
 * 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 {

                //    File file = new File(fileToBeIndexed);
                BufferedReader br = new BufferedReader(new FileReader(file));
                String title = "";
                String docno = "";
                String text = "";
                String line = "";
                boolean docStarted = false;
                Document doc = null;
                while ((line = br.readLine()) != null) {

                    //Note that these fields are part of a TRECtext file
                    if (line.indexOf("<DOC>") > -1) {
                        docStarted = true;
                        doc = new Document();
                    } else if (line.indexOf("</DOC>") > -1) {
                        docStarted = false;

                        /*             Previous versions had fields with parameters
                                           doc.add(new Field("title", title, Field.Store.YES, Field.Index.ANALYZED));
                                           doc.add(new Field("docno", docno, Field.Store.NO, Field.Index.NOT_ANALYZED));
                                           doc.add(new Field("text", text, Field.Store.YES, Field.Index.ANALYZED));
                                                   
                                          StringField -- not analyzed, in one chunk
                                          TextFiled -- analyzed
                                                   
                         */

                        doc.add(new StringField("docno", docno, Field.Store.YES));
                        doc.add(new TextField("title", title, Field.Store.YES));
                        doc.add(new TextField("text", text, Field.Store.YES));

                        writer.addDocument(doc);
                    }
                    if (docStarted) {
                        int i = -1;
                        if (((i = line.indexOf("<TITLE>")) > -1) && (line.indexOf("</TITLE>") > -1)) {
                            title = (line.substring(i + "<TITLE>".length(), line.indexOf("</TITLE>")));
                        } else if ((i = line.indexOf("<TEXT>")) > -1) {
                            text = line.substring(i + "<TEXT>".length());
                        } else if ((i = line.indexOf("<DOCNO>")) > -1) {
                            docno = line.substring(i + "<DOCNO>".length(), line.indexOf("</DOCNO>"));
                        }

                    }
                }
                br.close();
                System.out.println("adding " + 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.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"))));
                               
                          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:IndexTaxis.java

License:Apache License

static void addOneField(Document doc, String fieldName, String rawValue) {
    // nocommit/*from  ww  w.ja  v  a 2  s.  c  o  m*/
    /*
    if (fieldName.equals("pick_up_lat")) {
      double value = Double.parseDouble(rawValue);
      doc.add(new DoublePoint(fieldName, value));
      doc.add(new SortedNumericDocValuesField(fieldName, NumericUtils.doubleToSortableLong(value)));
    }
    */
    switch (fieldName) {
    case "vendor_id":
    case "cab_color":
    case "payment_type":
    case "trip_type":
    case "rate_code":
    case "store_and_fwd_flag":
        doc.add(new StringField(fieldName, rawValue, Field.Store.NO));
        doc.add(new SortedSetDocValuesField(fieldName, new BytesRef(rawValue)));
        break;
    case "vendor_name":
        doc.add(new TextField(fieldName, rawValue, Field.Store.NO));
        break;
    case "pick_up_date_time":
    case "drop_off_date_time": {
        long value = Long.parseLong(rawValue);
        doc.add(new LongPoint(fieldName, value));
        doc.add(new SortedNumericDocValuesField(fieldName, value));
    }
        break;
    case "passenger_count": {
        int value = Integer.parseInt(rawValue);
        doc.add(new IntPoint(fieldName, value));
        doc.add(new SortedNumericDocValuesField(fieldName, value));
    }
        break;
    case "trip_distance":
    case "pick_up_lat":
    case "pick_up_lon":
    case "drop_off_lat":
    case "drop_off_lon":
    case "fare_amount":
    case "surcharge":
    case "mta_tax":
    case "extra":
    case "ehail_fee":
    case "improvement_surcharge":
    case "tip_amount":
    case "tolls_amount":
    case "total_amount": {
        double value;
        try {
            value = Double.parseDouble(rawValue);
        } catch (NumberFormatException nfe) {
            System.out.println(
                    "WARNING: failed to parse \"" + rawValue + "\" as double for field \"" + fieldName + "\"");
            return;
        }
        doc.add(new DoublePoint(fieldName, value));
        doc.add(new SortedNumericDocValuesField(fieldName, NumericUtils.doubleToSortableLong(value)));
    }
        break;
    default:
        throw new AssertionError("failed to handle field \"" + fieldName + "\"");
    }
}

---

From source file:alix.lucene.Alix.java

License:Open Source License

/**
 * Starts a new Lucene document and gives an id.
 * Called by the XSL/* w w w .  j a  v a 2s .c  o m*/
 * 
 * @param idField ID field name
 */
public static void docNew() {
    doc = new Document();
    // key to delete
    doc.add(new StringField(FILENAME, filename, Store.YES));
}

---

From source file:alix.lucene.Alix.java

License:Open Source License

private static void addField(String name, String value, String options, float boost) {
    // do not add field for null ?
    if (value == null)
        return;/*www.j  a  v a  2s .com*/
    if (doc == null) {
        System.err.println("Please call docNew() before field()!");
        return;
    }
    if (name == Alix.FILENAME) {
        System.err.println(name + " is a reserved field name for Alix.");
        return;
    }
    Field field;
    if (options == null || "".equals(options)) {
        field = new StringField(name, value, Store.YES);
    } else if (options.contains("#")) {
        field = new IntField(name, Integer.parseInt(value), Field.Store.YES);
    } else if (options.contains(".")) {
        field = new FloatField(name, Float.parseFloat(value), Field.Store.YES);
    } else {
        field = new Field(name, value, fieldType(options));
    }
    if (boost > 0)
        field.setBoost(boost);
    doc.add(field);
}

---

From source file:antnlp.opie.indexsearch.IndexFiles.java

License:Apache License

/** Indexes a single document */
static void indexDoc(IndexWriter writer, Path file, long lastModified) throws IOException {

    InputStreamReader iReader = new InputStreamReader(Files.newInputStream(file), StandardCharsets.UTF_8);
    BufferedReader bufReader = new BufferedReader(iReader);

    String docLine = null;//from ww  w .j  a  v  a 2s . c  o m
    while ((docLine = bufReader.readLine()) != null) {
        docLine = docLine.trim();
        if (docLine.length() == 0)
            continue;
        String[] column = docLine.split("\\t");
        System.out.println(column[0]);
        System.out.println(column[1]);

        // make a new, empty document
        Document doc = new Document();

        // Add the id of the file as a field named "id".  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 docidField = new StringField("docid", column[0], Field.Store.YES);
        doc.add(docidField);

        // 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", column[1], 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 " + column[0]);
            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 " + column[0]);
            writer.updateDocument(new Term("docid", column[0]), doc);
        }
    }
    iReader.close();
    bufReader.close();
}

---

From source file:api.startup.PDFIndexer.java

License:Open Source License

/**
 * Indexes a single document and writes it to the given index writer
 * @param writer - the index writer to writer
 * @param metadata - the document//from w w  w. j a  v  a 2s . c om
 * @throws IOException
 */
static void indexDoc(IndexWriter writer, DocumentMetadata metadata) throws IOException {
    Path file = Paths.get(metadata.getFilename());
    try {
        Document doc = new Document();

        Field pathField = new StringField(Constants.FIELD_PATH, file.toString(), Field.Store.YES);
        doc.add(pathField);

        // Add Document metadata //
        doc.add(new StringField(Constants.FIELD_AUTHOR, metadata.getAuthor(), Field.Store.YES));
        doc.add(new StringField(Constants.FIELD_TITLE, metadata.getTitle(), Field.Store.YES));
        doc.add(new StringField(Constants.FIELD_CONFERENCE, metadata.getConference(), Field.Store.YES));
        // End of Document Metadata //

        Field modified = new LongField(Constants.FIELD_MODIFIED, Files.getLastModifiedTime(file).toMillis(),
                Field.Store.YES);
        doc.add(modified);

        PDFTextExtractor extractor = new PDFTextExtractor();
        // Get the string contents
        String textContents = extractor.extractText(file.toString());

        // Store the string contents
        FieldType contentsType = new FieldType();
        contentsType.setStored(true);
        contentsType.setTokenized(true);
        contentsType.setStoreTermVectors(true);
        contentsType.setStoreTermVectorPositions(true);
        contentsType.setStoreTermVectorPayloads(true);
        contentsType.setStoreTermVectorOffsets(true);
        contentsType.setIndexOptions(IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS);
        Field contents = new Field(Constants.FIELD_CONTENTS, textContents, contentsType);
        doc.add(contents);

        if (writer.getConfig().getOpenMode() == IndexWriterConfig.OpenMode.CREATE) {
            // New index, so we just add the document (no old document can be there):
            log.info("adding " + file + " to index");
            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.info("updating " + file + " in index");
            writer.updateDocument(new Term(Constants.FIELD_PATH, file.toString()), doc);
        }
    } catch (IOException e) {
        log.error("Failed to read file " + metadata.getFilename());
    }

}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• 18
• 19
• 20
• 21
• 22
• 23
• 24
• 25
• 26
• 27
• 28
• 29
• 30
• 31
• 32
• 33
• 34
• 35
• 36
• 37
• 38
• 39
• 40
• 41
• 42
• 43
• 44
• 45
• 46
• 47
• 48
• 49
• 50
• »