Examples with LanguageHandler org.apache.tika.language.detect.LanguageHandler used on opensource projects

Example 1 with LanguageHandler

use of org.apache.tika.language.detect.LanguageHandler in project tika by apache.

the class Language method languageDetectionWithHandler.

public static void languageDetectionWithHandler() throws Exception {
    LanguageHandler handler = new LanguageHandler();
    new AutoDetectParser().parse(System.in, handler, new Metadata(), new ParseContext());
    LanguageResult result = handler.getLanguage();
    System.out.println(result.getLanguage());
}

Example 2 with LanguageHandler

use of org.apache.tika.language.detect.LanguageHandler in project tika by apache.

the class MetadataResource method parseMetadata.

private Metadata parseMetadata(InputStream is, MultivaluedMap<String, String> httpHeaders, UriInfo info) throws IOException {
    final Metadata metadata = new Metadata();
    final ParseContext context = new ParseContext();
    Parser parser = TikaResource.createParser();
    TikaResource.fillMetadata(parser, metadata, context, httpHeaders);
    //no need to pass parser for embedded document parsing
    TikaResource.fillParseContext(context, httpHeaders, null);
    TikaResource.logRequest(LOG, info, metadata);
    TikaResource.parse(parser, LOG, info.getPath(), is, new LanguageHandler() {

        public void endDocument() {
            metadata.set("language", getLanguage().getLanguage());
        }
    }, metadata, context);
    return metadata;
}

Example 3 with LanguageHandler

use of org.apache.tika.language.detect.LanguageHandler in project tika by apache.

the class LanguageDetectingParser method parse.

public void parse(InputStream stream, ContentHandler handler, final Metadata metadata, ParseContext context) throws SAXException, IOException, TikaException {
    LanguageHandler langHandler = new LanguageHandler();
    ContentHandler tee = new TeeContentHandler(handler, langHandler);
    super.parse(stream, tee, metadata, context);
    LanguageResult result = langHandler.getLanguage();
    if (result.isReasonablyCertain()) {
        metadata.set(TikaCoreProperties.LANGUAGE, result.getLanguage());
    }
}

Example 4 with LanguageHandler

use of org.apache.tika.language.detect.LanguageHandler in project tika by apache.

the class RecursiveMetadataResource method parseMetadata.

private MetadataList parseMetadata(InputStream is, MultivaluedMap<String, String> httpHeaders, UriInfo info, String handlerTypeName) throws Exception {
    final Metadata metadata = new Metadata();
    final ParseContext context = new ParseContext();
    Parser parser = TikaResource.createParser();
    // TODO: parameterize choice of max chars/max embedded attachments
    BasicContentHandlerFactory.HANDLER_TYPE type = BasicContentHandlerFactory.parseHandlerType(handlerTypeName, DEFAULT_HANDLER_TYPE);
    RecursiveParserWrapper wrapper = new RecursiveParserWrapper(parser, new BasicContentHandlerFactory(type, -1));
    TikaResource.fillMetadata(parser, metadata, context, httpHeaders);
    // no need to add parser to parse recursively
    TikaResource.fillParseContext(context, httpHeaders, null);
    TikaResource.logRequest(LOG, info, metadata);
    TikaResource.parse(wrapper, LOG, info.getPath(), is, new LanguageHandler() {

        public void endDocument() {
            metadata.set("language", getLanguage().getLanguage());
        }
    }, metadata, context);
    return new MetadataList(wrapper.getMetadata());
}