Java ParseContext.get方法代碼示例

import org.apache.tika.parser.ParseContext; //導入方法依賴的package包/類
public void parse(InputStream inputStream, ContentHandler contentHandler,
  Metadata metadata, ParseContext parseContext)
  throws IOException, SAXException, TikaException {

  this.config = parseContext.get(ProfileParserConfig.class, config);
  initialize(this.config.getAgeProfilerModelUrl(),
    this.config.getGenderProfilerModelUrl());
  if (!isAvailable()) {
    return;
  }
  ProfileExtractor extractor = null;

  try {
    extractor = new ProfileExtractor(this.ageProfiler, this.genderProfiler);
  } catch (Exception e) {
    LOG.warning("Profiler setup failed: " + e);
    return;
  }

  Profile profile = extractor.getProfileFromInput(inputStream);

  metadata.add("Author_AGE", profile.getAgeRange());
  metadata.add("Author_GENDER", profile.getGender());
  metadata.add("Author_"+ TraitProfiler.TRAITS.TRAIT_AGREEABLE.name(),
    Double.toString(profile.getTraits().get(0)));
  metadata.add("Author_"+ TraitProfiler.TRAITS.TRAIT_CONSCIENTIOUS.name(),
    Double.toString(profile.getTraits().get(1)));
  metadata.add("Author_"+ TraitProfiler.TRAITS.TRAIT_EXTROVERT.name(),
    Double.toString(profile.getTraits().get(2)));
  metadata.add("Author_"+ TraitProfiler.TRAITS.TRAIT_OPEN.name(),
    Double.toString(profile.getTraits().get(3)));
  metadata.add("Author_"+ TraitProfiler.TRAITS.TRAIT_STABLE.name(),
    Double.toString(profile.getTraits().get(4)));

}
 

import org.apache.tika.parser.ParseContext; //導入方法依賴的package包/類
/**
 * Ritorna i tipi supportati
 * @param context contesto
 * @return tipi supportati
 */
@Override
public Set<MediaType> getSupportedTypes(ParseContext context) {
    // If Tesseract is installed, offer our supported image types
    TesseractOCRConfig config = context == null ? DEFAULT_CONFIG : context.get(TesseractOCRConfig.class, DEFAULT_CONFIG);
    if (hasTesseract(config)) {
        return SUPPORTED_TYPES;
    }

    // Otherwise don't advertise anything, so the other image parsers
    //  can be selected instead
    return Collections.emptySet();
}
 

import org.apache.tika.parser.ParseContext; //導入方法依賴的package包/類
protected AbstractPOIFSExtractor(ParseContext context) {
  EmbeddedDocumentExtractor ex = context.get(EmbeddedDocumentExtractor.class);

  if (ex == null) {
    this.extractor = new ParsingEmbeddedDocumentExtractor(context);
  } else {
    this.extractor = ex;
  }

  tikaConfig = context.get(TikaConfig.class);
  mimeTypes = context.get(MimeTypes.class);
  detector = context.get(Detector.class);
}
 

import org.apache.tika.parser.ParseContext; //導入方法依賴的package包/類
public AbstractOOXMLExtractor(ParseContext context, POIXMLTextExtractor extractor) {
    this.extractor = extractor;

    EmbeddedDocumentExtractor ex = context.get(EmbeddedDocumentExtractor.class);

    if (ex==null) {
        embeddedExtractor = new ParsingEmbeddedDocumentExtractor(context);
    } else {
        embeddedExtractor = ex;
    }

}
 

import org.apache.tika.parser.ParseContext; //導入方法依賴的package包/類
public void parse(InputStream stream, ContentHandler handler,
    Metadata metadata, ParseContext context) throws IOException,
    SAXException, TikaException {
  // Automatically detect the character encoding
  AutoDetectReader reader = new AutoDetectReader(new CloseShieldInputStream(
      stream), metadata, context.get(ServiceLoader.class, LOADER));
  try {
    Charset charset = reader.getCharset();
    MediaType type = new MediaType(MediaType.TEXT_PLAIN, charset);
    metadata.set(Metadata.CONTENT_TYPE, type.toString());
    // deprecated, see TIKA-431
    metadata.set(Metadata.CONTENT_ENCODING, charset.name());

    XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
    xhtml.startDocument();

    xhtml.startElement("p");
    char[] buffer = new char[4096];
    int n = reader.read(buffer);
    while (n != -1) {
      xhtml.characters(buffer, 0, n);
      n = reader.read(buffer);
    }
    xhtml.endElement("p");

    xhtml.endDocument();
  } finally {
    reader.close();
  }
}
 

import org.apache.tika.parser.ParseContext; //導入方法依賴的package包/類
public void parse(InputStream stream, ContentHandler handler,
    Metadata metadata, ParseContext context) throws IOException,
    SAXException, TikaException {
  // Automatically detect the character encoding
  AutoDetectReader reader = new AutoDetectReader(new CloseShieldInputStream(
      stream), metadata, context.get(ServiceLoader.class, LOADER));
  try {
    Charset charset = reader.getCharset();
    // charset = Charset.forName("utf-8");
    String previous = metadata.get(Metadata.CONTENT_TYPE);
    if (previous == null || previous.startsWith("text/html")) {
      MediaType type = new MediaType(MediaType.TEXT_HTML, charset);
      metadata.set(Metadata.CONTENT_TYPE, type.toString());
    }
    // deprecated, see TIKA-431
    metadata.set(Metadata.CONTENT_ENCODING, charset.name());

    // Get the HTML mapper from the parse context
    HtmlMapper mapper = context.get(HtmlMapper.class, new HtmlParserMapper());

    // Parse the HTML document
    org.ccil.cowan.tagsoup.Parser parser = new org.ccil.cowan.tagsoup.Parser();

    // Use schema from context or default
    Schema schema = context.get(Schema.class, HTML_SCHEMA);

    // TIKA-528: Reuse share schema to avoid heavy instantiation
    parser.setProperty(org.ccil.cowan.tagsoup.Parser.schemaProperty, schema);
    // TIKA-599: Shared schema is thread-safe only if bogons are ignored
    parser
        .setFeature(org.ccil.cowan.tagsoup.Parser.ignoreBogonsFeature, true);

    parser.setContentHandler(new XHTMLDowngradeHandler(new HtmlHandler(
        mapper, handler, metadata)));

    parser.parse(reader.asInputSource());
  } finally {
    reader.close();
  }
}
 

import org.apache.tika.parser.ParseContext; //導入方法依賴的package包/類
/**
 * Parsa lo stream
 * @param stream stream
 * @param handler handler
 * @param metadata metadata
 * @param context contesto
 * @throws IOException eccezione
 * @throws SAXException eccezione
 * @throws TikaException  eccezione
 */
@Override
public void parse(InputStream stream, ContentHandler handler, Metadata metadata, ParseContext context)
        throws IOException, SAXException, TikaException {
    TesseractOCRConfig config = context.get(TesseractOCRConfig.class, DEFAULT_CONFIG);

    // If Tesseract is not on the path with the current config, do not try to run OCR
    // getSupportedTypes shouldn't have listed us as handling it, so this should only
    //  occur if someone directly calls this parser, not via DefaultParser or similar
    if (!hasTesseract(config)) {
        return;
    }

    XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);

    TemporaryResources tmp = new TemporaryResources();
    File output = null;
    try {
        TikaInputStream tikaStream = TikaInputStream.get(stream, tmp);
        File input = tikaStream.getFile();
        long size = tikaStream.getLength();

        if (size >= config.getMinFileSizeToOcr() && size <= config.getMaxFileSizeToOcr()) {

            output = tmp.createTemporaryFile();
            doOCR(input, output, config);

            // Tesseract appends .txt to output file name
            output = new File(output.getAbsolutePath() + ".txt");

            if (output.exists()) {
                extractOutput(new FileInputStream(output), xhtml);
            }

        }

        // Temporary workaround for TIKA-1445 - until we can specify
        //  composite parsers with strategies (eg Composite, Try In Turn),
        //  always send the image onwards to the regular parser to have
        //  the metadata for them extracted as well
        _TMP_IMAGE_METADATA_PARSER.parse(tikaStream, handler, metadata, context);
    } finally {
        tmp.dispose();
        if (output != null) {
            output.delete();
        }
    }
}
 

import org.apache.tika.parser.ParseContext; //導入方法依賴的package包/類
@Override
public void parse(InputStream stream, ContentHandler handler,
		Metadata metadata, ParseContext context) throws IOException,
		SAXException, TikaException {

	/*----------------configure this parser by ParseContext Object---------------------*/
	GeoParserConfig localconfig = context.get(GeoParserConfig.class,
			defaultconfig);
	String nerModelPath = localconfig.getNERPath();
	gazetteerPath = localconfig.getGazetterPath();

	/*----------------get locationNameEntities and best nameEntity for the input stream---------------------*/
	NameEntityExtractor extractor = new NameEntityExtractor(nerModelPath);
	extractor.getAllNameEntitiesfromInput(stream);
	extractor.getBestNameEntity();
	ArrayList<String> locationNameEntities = extractor.locationNameEntities;
	String bestner = extractor.bestNameEntity;

	/*----------------build lucene search engine for the gazetteer file, 
	 *------------------------resolve geonames for each ner, store results in a hashmap---------------------*/
	GeoNameResolver resolver = new GeoNameResolver();
	resolver.buildIndex(gazetteerPath);
	HashMap<String, ArrayList<String>> resolvedGeonames = resolver
			.searchGeoName(locationNameEntities);

	/*----------------store locationNameEntities and their geonames in a geotag, each input has one geotag---------------------*/
	GeoTag geotag = new GeoTag();
	geotag.toGeoTag(resolvedGeonames, bestner);

	/* add resolved entities in metadata */

	metadata.add("Geographic_NAME", geotag.Geographic_NAME);
	metadata.add("Geographic_LONGITUDE", geotag.Geographic_LONGTITUDE);
	metadata.add("Geographic_LATITUDE", geotag.Geographic_LATITUDE);
	for (int i = 0; i < geotag.alternatives.size(); ++i) {
		GeoTag alter = (GeoTag) geotag.alternatives.get(i);
		metadata.add("Optional_NAME" + (i + 1), alter.Geographic_NAME);
		metadata.add("Optional_LONGITUDE" + (i + 1),
				alter.Geographic_LONGTITUDE);
		metadata.add("Optional_LATITUDE" + (i + 1),
				alter.Geographic_LATITUDE);
	}
}