Examples of org.apache.tika.parser.txt.TXTParser

org.apache.tika.parser.txt.TXTParser
Plain text parser. The text encoding of the document stream is automatically detected based on the byte patterns found at the beginning of the stream. The input metadata key {@link HttpHeaders#CONTENT_ENCODING} is used as an encoding hintif the automatic encoding detection fails.
This parser sets the following output metadata entries:

{@link HttpHeaders#CONTENT_TYPE}

text/plain

{@link HttpHeaders#CONTENT_ENCODING}

The detected text encoding of the document.

{@link HttpHeaders#CONTENT_LANGUAGE} and {@link DublinCore#LANGUAGE}

The default language of the detected encoding. Only set if the detected encoding is associated with some specific language (for example KOI8-R with Russian or SJIS with Japanese).

     * Gets the parser to use to verify the result of the embed operation.
     *
     * @return the parser to read embedded metadata
     */
    protected Parser getParser() {
        return new TXTParser();
    }

View Full Code Here

                parsers.put(MediaType.application("vnd.sun.xml.impress"), parser);
                parsers.put(MediaType.application("vnd.sun.xml.writer"), parser);
            } else if (name.equals("org.apache.jackrabbit.extractor.PdfTextExtractor")) {
                parsers.put(MediaType.application("pdf"), new PDFParser());
            } else if (name.equals("org.apache.jackrabbit.extractor.PlainTextExtractor")) {
                parsers.put(MediaType.TEXT_PLAIN, new TXTParser());
            } else if (name.equals("org.apache.jackrabbit.extractor.PngTextExtractor")) {
                Parser parser = new ImageParser();
                parsers.put(MediaType.image("png"), parser);
                parsers.put(MediaType.image("apng"), parser);
                parsers.put(MediaType.image("mng"), parser);

View Full Code Here

            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.PdfTextExtractor")) {
                parsers.put("application/pdf", new PDFParser());
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.PlainTextExtractor")) {
                parsers.put("text/plain", new TXTParser());
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.PngTextExtractor")) {
                Parser parser = new ImageParser();
                parsers.put("image/png", parser);
                parsers.put("image/apng", parser);

View Full Code Here

            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.PdfTextExtractor")) {
                parsers.put("application/pdf", new PDFParser());
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.PlainTextExtractor")) {
                parsers.put("text/plain", new TXTParser());
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.PngTextExtractor")) {
                Parser parser = new ImageParser();
                parsers.put("image/png", parser);
                parsers.put("image/apng", parser);

View Full Code Here

            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.PdfTextExtractor")) {
                parsers.put("application/pdf", new PDFParser());
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.PlainTextExtractor")) {
                parsers.put("text/plain", new TXTParser());
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.PngTextExtractor")) {
                Parser parser = new ImageParser();
                parsers.put("image/png", parser);
                parsers.put("image/apng", parser);

View Full Code Here

            }
            continue;
          }//TESTED
          else if (mediaType.equalsIgnoreCase("bypass")) {
            Map<MediaType, Parser> parsers = autoDetectParser.getParsers();
            parsers.put(MediaType.parse(jsonStr), new TXTParser());
            autoDetectParser.setParsers(parsers);
            continue;
          }
          // Try to get media type parser:

View Full Code Here

          }
          continue;
        }//TESTED
        else if (mediaType.matches("bypass[0-9]*")) {
          Map<MediaType, Parser> parsers = autoDetectParser.getParsers();
          parsers.put(MediaType.parse(jsonStr), new TXTParser());
          autoDetectParser.setParsers(parsers);
          continue;
        }
        // Try to get media type parser:
        mediaType = mediaType.replaceFirst("([?][0-9]*$", "");

View Full Code Here

     * Gets the parser to use to verify the result of the embed operation.
     *
     * @return the parser to read embedded metadata
     */
    protected Parser getParser() {
        return new TXTParser();
    }

View Full Code Here

     * Gets the parser to use to verify the result of the embed operation.
     *
     * @return the parser to read embedded metadata
     */
    protected Parser getParser() {
        return new TXTParser();
    }

View Full Code Here

TOP

Related Classes of org.apache.tika.parser.txt.TXTParser

com.ikanow.infinit.e.harvest.extraction.document.file.FileHarvester

com.ikanow.infinit.e.harvest.extraction.text.legacy.TextExtractorTika

org.apache.jackrabbit.core.query.lucene.JackrabbitParser

org.apache.tika.detect.AutoDetectReader

org.apache.tika.embedder.ExternalEmbedderTest

org.apache.tika.io.CloseShieldInputStream

org.apache.tika.mime.MediaType

org.apache.tika.parser.ParseContext

org.apache.tika.sax.XHTMLContentHandler

java.nio.charset.Charset

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.