Examples of org.apache.tika.sax.TaggedContentHandler

org.apache.tika.sax.TaggedContentHandler
essing that may throw an SAXException either from this handler // or from some other XML parsing activity processXML(handler); } catch (SAXException e) { if (handler.isCauseOf(e)) { // The exception was caused by this handler. // Use e.getCause() to get the original exception. } else { // The exception was caused by something else. } }
Alternatively, the {@link #throwIfCauseOf(Exception)} method can beused to let higher levels of code handle the exception caused by this stream while other processing errors are being taken care of at this lower level.
```
 TaggedContentHandler handler = new TaggedContentHandler(...); try { processXML(handler); } catch (SAXException e) { stream.throwIfCauseOf(e); // ... or process the exception that was caused by something else } 
```
@see TaggedSAXException

            InputStream stream, ContentHandler handler,
            Metadata metadata, ParseContext context)
            throws IOException, SAXException, TikaException {
        Parser parser = getParser(metadata);
        TaggedInputStream taggedStream = new TaggedInputStream(stream);
        TaggedContentHandler taggedHandler = new TaggedContentHandler(handler);
        try {
            parser.parse(taggedStream, taggedHandler, metadata, context);
        } catch (RuntimeException e) {
            throw new TikaException(
                    "Unexpected RuntimeException from " + parser, e);
        } catch (IOException e) {
            taggedStream.throwIfCauseOf(e);
            throw new TikaException(
                    "TIKA-198: Illegal IOException from " + parser, e);
        } catch (SAXException e) {
            taggedHandler.throwIfCauseOf(e);
            throw new TikaException(
                    "TIKA-237: Illegal SAXException from " + parser, e);
        }
    }

View Full Code Here

            InputStream stream, ContentHandler handler,
            Metadata metadata, ParseContext context)
            throws IOException, SAXException, TikaException {
        Parser parser = getParser(metadata);
        TaggedInputStream taggedStream = new TaggedInputStream(stream);
        TaggedContentHandler taggedHandler = new TaggedContentHandler(handler);
        try {
            parser.parse(taggedStream, taggedHandler, metadata, context);
        } catch (RuntimeException e) {
            throw new TikaException(
                    "Unexpected RuntimeException from " + parser, e);
        } catch (IOException e) {
            taggedStream.throwIfCauseOf(e);
            throw new TikaException(
                    "TIKA-198: Illegal IOException from " + parser, e);
        } catch (SAXException e) {
            taggedHandler.throwIfCauseOf(e);
            throw new TikaException(
                    "TIKA-237: Illegal SAXException from " + parser, e);
        }
    }

View Full Code Here

        final XHTMLContentHandler xhtml =
            new XHTMLContentHandler(handler, metadata);
        xhtml.startDocument();
        xhtml.startElement("p");


        TaggedContentHandler tagged = new TaggedContentHandler(handler);
        try {
            context.getSAXParser().parse(
                    new CloseShieldInputStream(stream),
                    new OfflineContentHandler(new EmbeddedContentHandler(
                            getContentHandler(tagged, metadata, context))));
        } catch (SAXException e) {
            tagged.throwIfCauseOf(e);
            throw new TikaException("XML parse error", e);
        }


        xhtml.endElement("p");
        xhtml.endDocument();

View Full Code Here

            InputStream stream, ContentHandler handler,
            Metadata metadata, ParseContext context)
            throws IOException, SAXException, TikaException {
        Parser parser = getParser(metadata);
        TaggedInputStream taggedStream = new TaggedInputStream(stream);
        TaggedContentHandler taggedHandler = new TaggedContentHandler(handler);
        try {
            parser.parse(taggedStream, taggedHandler, metadata, context);
        } catch (RuntimeException e) {
            throw new TikaException(
                    "Unexpected RuntimeException from " + parser, e);
        } catch (IOException e) {
            taggedStream.throwIfCauseOf(e);
            throw new TikaException(
                    "TIKA-198: Illegal IOException from " + parser, e);
        } catch (SAXException e) {
            taggedHandler.throwIfCauseOf(e);
            throw new TikaException(
                    "TIKA-237: Illegal SAXException from " + parser, e);
        }
    }

View Full Code Here

            throws IOException, SAXException, TikaException {
        Parser parser = getParser(metadata, context);
        TemporaryResources tmp = new TemporaryResources();
        try {
            TikaInputStream taggedStream = TikaInputStream.get(stream, tmp);
            TaggedContentHandler taggedHandler = 
                handler != null ? new TaggedContentHandler(handler) : null;
      metadata.add("X-Parsed-By", parser.getClass().getName());
            try {
                parser.parse(taggedStream, taggedHandler, metadata, context);
            } catch (RuntimeException e) {
                throw new TikaException(
                        "Unexpected RuntimeException from " + parser, e);
            } catch (IOException e) {
                taggedStream.throwIfCauseOf(e);
                throw new TikaException(
                        "TIKA-198: Illegal IOException from " + parser, e);
            } catch (SAXException e) {
                if (taggedHandler != null) taggedHandler.throwIfCauseOf(e);
                throw new TikaException(
                        "TIKA-237: Illegal SAXException from " + parser, e);
            }
        } finally {
            tmp.dispose();

View Full Code Here

            throws IOException, SAXException, TikaException {
        Parser parser = getParser(metadata);
        TemporaryResources tmp = new TemporaryResources();
        try {
            TikaInputStream taggedStream = TikaInputStream.get(stream, tmp);
            TaggedContentHandler taggedHandler = new TaggedContentHandler(handler);
            try {
                parser.parse(taggedStream, taggedHandler, metadata, context);
            } catch (RuntimeException e) {
                throw new TikaException(
                        "Unexpected RuntimeException from " + parser, e);
            } catch (IOException e) {
                taggedStream.throwIfCauseOf(e);
                throw new TikaException(
                        "TIKA-198: Illegal IOException from " + parser, e);
            } catch (SAXException e) {
                taggedHandler.throwIfCauseOf(e);
                throw new TikaException(
                        "TIKA-237: Illegal SAXException from " + parser, e);
            }
        } finally {
            tmp.dispose();

View Full Code Here

                Metadata metadata, ParseContext context)
                throws IOException, SAXException, TikaException {
            Thread thread = new Thread(this, "Tika network parser");
            thread.start();


            TaggedContentHandler tagged = new TaggedContentHandler(handler);
            try {
                context.getSAXParser().parse(
                        stream, new TeeContentHandler(
                                tagged, new MetaHandler(metadata)));
            } catch (SAXException e) {
                tagged.throwIfCauseOf(e);
                throw new TikaException(
                        "Invalid network parser output", e);
            } catch (IOException e) {
                throw new TikaException(
                        "Unable to read network parser output", e);

View Full Code Here

        final XHTMLContentHandler xhtml =
            new XHTMLContentHandler(handler, metadata);
        xhtml.startDocument();
        xhtml.startElement("p");


        TaggedContentHandler tagged = new TaggedContentHandler(handler);
        try {
            context.getSAXParser().parse(
                    new CloseShieldInputStream(stream),
                    new OfflineContentHandler(new EmbeddedContentHandler(
                            getContentHandler(tagged, metadata, context))));
        } catch (SAXException e) {
            tagged.throwIfCauseOf(e);
            throw new TikaException("XML parse error", e);
        }


        xhtml.endElement("p");
        xhtml.endDocument();

View Full Code Here

            throws IOException, SAXException, TikaException {
        Parser parser = getParser(metadata, context);
        TemporaryResources tmp = new TemporaryResources();
        try {
            TikaInputStream taggedStream = TikaInputStream.get(stream, tmp);
            TaggedContentHandler taggedHandler = 
                handler != null ? new TaggedContentHandler(handler) : null;
            if (parser instanceof ParserDecorator){
                metadata.add("X-Parsed-By", ((ParserDecorator) parser).getWrappedParser().getClass().getName());
            } else {
                metadata.add("X-Parsed-By", parser.getClass().getName());
            }
            try {
                parser.parse(taggedStream, taggedHandler, metadata, context);
            } catch (RuntimeException e) {
                throw new TikaException(
                        "Unexpected RuntimeException from " + parser, e);
            } catch (IOException e) {
                taggedStream.throwIfCauseOf(e);
                throw new TikaException(
                        "TIKA-198: Illegal IOException from " + parser, e);
            } catch (SAXException e) {
                if (taggedHandler != null) taggedHandler.throwIfCauseOf(e);
                throw new TikaException(
                        "TIKA-237: Illegal SAXException from " + parser, e);
            }
        } finally {
            tmp.dispose();

View Full Code Here

        final XHTMLContentHandler xhtml =
            new XHTMLContentHandler(handler, metadata);
        xhtml.startDocument();
        xhtml.startElement("p");


        TaggedContentHandler tagged = new TaggedContentHandler(handler);
        try {
            context.getSAXParser().parse(
                    new CloseShieldInputStream(stream),
                    new OfflineContentHandler(new EmbeddedContentHandler(
                            getContentHandler(tagged, metadata, context))));
        } catch (SAXException e) {
            tagged.throwIfCauseOf(e);
            throw new TikaException("XML parse error", e);
        } finally {
            xhtml.endElement("p");
            xhtml.endDocument();
        }

View Full Code Here

TOP

Related Classes of org.apache.tika.sax.TaggedContentHandler

org.apache.tika.parser.CompositeParser

org.apache.tika.parser.NetworkParser$ParsingTask

org.apache.tika.parser.xml.XMLParser

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.