Examples with XHTMLContentHandler org.apache.tika.sax.XHTMLContentHandler used on opensource projects

Example 1 with XHTMLContentHandler

use of org.apache.tika.sax.XHTMLContentHandler in project jackrabbit-oak by apache.

the class HtmlRepresentation method render.

public void render(PropertyState property, HttpServletResponse response) throws IOException {
    try {
        XHTMLContentHandler xhtml = startResponse(response, property.getName());
        xhtml.startDocument();
        if (property.isArray()) {
            xhtml.startElement("ol");
            for (String value : property.getValue(STRINGS)) {
                xhtml.element("li", value);
            }
            xhtml.endElement("ol");
        } else {
            xhtml.element("p", property.getValue(STRING));
        }
        xhtml.endDocument();
    } catch (SAXException e) {
        throw new IOException(e);
    }
}

Example 2 with XHTMLContentHandler

use of org.apache.tika.sax.XHTMLContentHandler in project tika by apache.

the class ExternalParser method parse.

/**
     * Executes the configured external command and passes the given document
     * stream as a simple XHTML document to the given SAX content handler.
     * Metadata is only extracted if {@link #setMetadataExtractionPatterns(Map)}
     * has been called to set patterns.
     */
public void parse(InputStream stream, ContentHandler handler, Metadata metadata, ParseContext context) throws IOException, SAXException, TikaException {
    XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
    TemporaryResources tmp = new TemporaryResources();
    try {
        parse(TikaInputStream.get(stream, tmp), xhtml, metadata, tmp);
    } finally {
        tmp.dispose();
    }
}

Example 3 with XHTMLContentHandler

use of org.apache.tika.sax.XHTMLContentHandler in project tika by apache.

the class EmptyParser method parse.

public void parse(InputStream stream, ContentHandler handler, Metadata metadata, ParseContext context) throws SAXException {
    XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
    xhtml.startDocument();
    xhtml.endDocument();
}

Example 4 with XHTMLContentHandler

use of org.apache.tika.sax.XHTMLContentHandler in project tika by apache.

the class RTFParser method parse.

public void parse(InputStream stream, ContentHandler handler, Metadata metadata, ParseContext context) throws IOException, SAXException, TikaException {
    metadata.set(Metadata.CONTENT_TYPE, "application/rtf");
    TaggedInputStream tagged = new TaggedInputStream(stream);
    try {
        XHTMLContentHandler xhtmlHandler = new XHTMLContentHandler(handler, metadata);
        RTFEmbObjHandler embObjHandler = new RTFEmbObjHandler(xhtmlHandler, metadata, context, getMemoryLimitInKb());
        final TextExtractor ert = new TextExtractor(xhtmlHandler, metadata, embObjHandler);
        ert.extract(stream);
    } catch (IOException e) {
        tagged.throwIfCauseOf(e);
        throw new TikaException("Error parsing an RTF document", e);
    }
}

Example 5 with XHTMLContentHandler

use of org.apache.tika.sax.XHTMLContentHandler in project tika by apache.

the class Latin1StringsParser method doParse.

/**
     * Does a best effort to extract Latin1 strings encoded with ISO-8859-1,
     * UTF-8 or UTF-16. Valid chars are saved into the output buffer and the
     * temporary buffer position is incremented. When an invalid char is read,
     * the difference of the temporary and current buffer position is checked.
     * If it is greater than the minimum string size, the current buffer
     * position is updated to the temp position. If it is not, the temp position
     * is reseted to the current position.
     * 
     * @param stream
     *            the input stream.
     * @param handler
     *            the output content handler
     * @param metadata
     *            the metadata of the file
     * @param context
     *            the parsing context
     * @throws IOException
     *             if an io error occurs
     * @throws SAXException
     *             if a sax error occurs
     */
private void doParse(InputStream stream, ContentHandler handler, Metadata metadata, ParseContext context) throws IOException, SAXException {
    tmpPos = 0;
    outPos = 0;
    xhtml = new XHTMLContentHandler(handler, metadata);
    xhtml.startDocument();
    int i = 0;
    do {
        inSize = 0;
        while ((i = stream.read(input, inSize, BUF_SIZE - inSize)) > 0) {
            inSize += i;
        }
        inPos = 0;
        while (inPos < inSize) {
            byte c = input[inPos++];
            boolean utf8 = false;
            /*
                 * Test for a possible UTF8 encoded char
                 */
            if (c == (byte) 0xC3) {
                byte c_ = inPos < inSize ? input[inPos++] : (byte) stream.read();
                /*
                     * Test if the next byte is in the valid UTF8 range
                     */
                if (c_ >= (byte) 0x80 && c_ <= (byte) 0xBF) {
                    utf8 = true;
                    output[tmpPos++] = (byte) (c_ + 0x40);
                } else {
                    output[tmpPos++] = c;
                    c = c_;
                }
                if (tmpPos == BUF_SIZE)
                    flushBuffer();
            /*
                     * Test for a possible UTF8 encoded char
                     */
            } else if (c == (byte) 0xC2) {
                byte c_ = inPos < inSize ? input[inPos++] : (byte) stream.read();
                /*
                     * Test if the next byte is in the valid UTF8 range
                     */
                if (c_ >= (byte) 0xA0 && c_ <= (byte) 0xBF) {
                    utf8 = true;
                    output[tmpPos++] = c_;
                } else {
                    output[tmpPos++] = c;
                    c = c_;
                }
                if (tmpPos == BUF_SIZE)
                    flushBuffer();
            }
            if (!utf8)
                /*
                     * Test if the byte is a valid char.
                     */
                if (isChar(c)) {
                    output[tmpPos++] = c;
                    if (tmpPos == BUF_SIZE)
                        flushBuffer();
                } else {
                    /*
                         * Test if the byte is an invalid char, marking a string
                         * end. If it is a zero, test 2 positions before or
                         * ahead for a valid char, meaning it marks the
                         * transition between ISO-8859-1 and UTF16 sequences.
                         */
                    if (c != 0 || (inPos >= 3 && isChar(input[inPos - 3])) || (inPos + 1 < inSize && isChar(input[inPos + 1]))) {
                        if (tmpPos - outPos >= minSize) {
                            output[tmpPos++] = 0x0A;
                            outPos = tmpPos;
                            if (tmpPos == BUF_SIZE)
                                flushBuffer();
                        } else
                            tmpPos = outPos;
                    }
                }
        }
    } while (i != -1 && !Thread.currentThread().isInterrupted());
    if (tmpPos - outPos >= minSize) {
        output[tmpPos++] = 0x0A;
        outPos = tmpPos;
    }
    xhtml.characters(new String(output, 0, outPos, "windows-1252"));
    xhtml.endDocument();
}