Java Code Examples for org.apache.tika.sax.WriteOutContentHandler#isWriteLimitReached()

The following examples show how to use org.apache.tika.sax.WriteOutContentHandler#isWriteLimitReached() . You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example 1
Source File: ContentExtractor.java    From jate with GNU Lesser General Public License v3.0 6 votes vote down vote up 
private String parseTXTToString(InputStream stream, Metadata metadata) throws IOException, TikaException {
	WriteOutContentHandler handler = new WriteOutContentHandler(maxStringLength);
	try {
		ParseContext context = new ParseContext();
		context.set(Parser.class, txtParser);
		txtParser.parse(stream, new BodyContentHandler(handler), metadata, context);
	} catch (SAXException e) {
		if (!handler.isWriteLimitReached(e)) {
			// This should never happen with BodyContentHandler...
			throw new TikaException("Unexpected SAX processing failure", e);
		}
	} finally {
		stream.close();
	}
	return handler.toString();
}
Example 2
Source File: NodeTika.java    From node-tika with MIT License 4 votes vote down vote up 
public static String extractText(String uri, Map<String, Object> options) throws Exception {
	final AutoDetectParser parser = createParser();
	final Metadata metadata = new Metadata();
	final ParseContext context = new ParseContext();

	String outputEncoding = null;
	String contentType = null;
	int maxLength = -1;

	if (options != null) {
		Object option;

		option = options.get("outputEncoding");
		if (option != null) {
			outputEncoding = option.toString();
		}

		option = options.get("contentType");
		if (option != null) {
			contentType = option.toString();
		}

		option = options.get("maxLength");
		if (option != null) {
			maxLength = (int)Float.parseFloat(option.toString());
		}
	}

	if (outputEncoding == null) {
		outputEncoding = "UTF-8";
	}

	fillMetadata(parser, metadata, contentType, uri);
	fillParseContext(context, options);

	final ByteArrayOutputStream outputStream = new ByteArrayOutputStream();
	final OutputStreamWriter writer = new OutputStreamWriter(outputStream, outputEncoding);
	final WriteOutContentHandler contentHandler = new WriteOutContentHandler(writer, maxLength);

	final TikaInputStream inputStream = createInputStream(uri, metadata);

	// Set up recursive parsing of archives.
	// See: http://wiki.apache.org/tika/RecursiveMetadata
	context.set(Parser.class, parser);
	context.set(EmbeddedDocumentExtractor.class, new ParsingEmbeddedDocumentExtractor(context));

	try {
		parser.parse(inputStream, new BodyContentHandler(contentHandler), metadata, context);
	} catch (Throwable e) {
		if (!contentHandler.isWriteLimitReached(e)) {
			throw e;
		} else {
			writer.close();
		}
	} finally {
		inputStream.close();
	}

	return outputStream.toString(outputEncoding);
}