Examples with HtmlParser org.apache.tika.parser.html.HtmlParser used on opensource projects

Example 1 with HtmlParser

use of org.apache.tika.parser.html.HtmlParser in project tika by apache.

the class TikaResource method createParser.

@SuppressWarnings("serial")
public static Parser createParser() {
    final Parser parser = new AutoDetectParser(tikaConfig);
    Map<MediaType, Parser> parsers = ((AutoDetectParser) parser).getParsers();
    parsers.put(MediaType.APPLICATION_XML, new HtmlParser());
    ((AutoDetectParser) parser).setParsers(parsers);
    ((AutoDetectParser) parser).setFallback(new Parser() {

        public Set<MediaType> getSupportedTypes(ParseContext parseContext) {
            return parser.getSupportedTypes(parseContext);
        }

        public void parse(InputStream inputStream, ContentHandler contentHandler, Metadata metadata, ParseContext parseContext) {
            throw new WebApplicationException(Response.Status.UNSUPPORTED_MEDIA_TYPE);
        }
    });
    if (digester != null) {
        return new DigestingParser(parser, digester);
    }
    return parser;
}

Example 2 with HtmlParser

use of org.apache.tika.parser.html.HtmlParser in project tika by apache.

the class OutlookExtractor method parse.

public void parse(XHTMLContentHandler xhtml, Metadata metadata) throws TikaException, SAXException, IOException {
    try {
        msg.setReturnNullOnMissingChunk(true);
        try {
            metadata.set(Office.MAPI_MESSAGE_CLASS, getMessageClass(msg.getMessageClass()));
        } catch (ChunkNotFoundException e) {
        }
        //  as Unicode, try to sort out an encoding for them
        if (msg.has7BitEncodingStrings()) {
            guess7BitEncoding(msg);
        }
        // Start with the metadata
        String subject = msg.getSubject();
        Map<String, String[]> headers = normalizeHeaders(msg.getHeaders());
        String from = msg.getDisplayFrom();
        handleFromTo(headers, metadata);
        metadata.set(TikaCoreProperties.TITLE, subject);
        // TODO: Move to description in Tika 2.0
        metadata.set(TikaCoreProperties.TRANSITION_SUBJECT_TO_DC_DESCRIPTION, msg.getConversationTopic());
        try {
            for (String recipientAddress : msg.getRecipientEmailAddressList()) {
                if (recipientAddress != null)
                    metadata.add(Metadata.MESSAGE_RECIPIENT_ADDRESS, recipientAddress);
            }
        } catch (ChunkNotFoundException he) {
        }
        for (Map.Entry<String, String[]> e : headers.entrySet()) {
            String headerKey = e.getKey();
            for (String headerValue : e.getValue()) {
                metadata.add(Metadata.MESSAGE_RAW_HEADER_PREFIX + headerKey, headerValue);
            }
        }
        // First try via the proper chunk
        if (msg.getMessageDate() != null) {
            metadata.set(TikaCoreProperties.CREATED, msg.getMessageDate().getTime());
            metadata.set(TikaCoreProperties.MODIFIED, msg.getMessageDate().getTime());
        } else {
            if (headers != null && headers.size() > 0) {
                for (Map.Entry<String, String[]> header : headers.entrySet()) {
                    String headerKey = header.getKey();
                    if (headerKey.toLowerCase(Locale.ROOT).startsWith("date:")) {
                        String date = headerKey.substring(headerKey.indexOf(':') + 1).trim();
                        // See if we can parse it as a normal mail date
                        try {
                            Date d = MboxParser.parseDate(date);
                            metadata.set(TikaCoreProperties.CREATED, d);
                            metadata.set(TikaCoreProperties.MODIFIED, d);
                        } catch (ParseException e) {
                            // Store it as-is, and hope for the best...
                            metadata.set(TikaCoreProperties.CREATED, date);
                            metadata.set(TikaCoreProperties.MODIFIED, date);
                        }
                        break;
                    }
                }
            }
        }
        xhtml.element("h1", subject);
        // Output the from and to details in text, as you
        //  often want them in text form for searching
        xhtml.startElement("dl");
        if (from != null) {
            header(xhtml, "From", from);
        }
        header(xhtml, "To", msg.getDisplayTo());
        header(xhtml, "Cc", msg.getDisplayCC());
        header(xhtml, "Bcc", msg.getDisplayBCC());
        try {
            header(xhtml, "Recipients", msg.getRecipientEmailAddress());
        } catch (ChunkNotFoundException e) {
        }
        xhtml.endElement("dl");
        // Get the message body. Preference order is: html, rtf, text
        Chunk htmlChunk = null;
        Chunk rtfChunk = null;
        Chunk textChunk = null;
        for (Chunk chunk : msg.getMainChunks().getChunks()) {
            if (chunk.getChunkId() == MAPIProperty.BODY_HTML.id) {
                htmlChunk = chunk;
            }
            if (chunk.getChunkId() == MAPIProperty.RTF_COMPRESSED.id) {
                rtfChunk = chunk;
            }
            if (chunk.getChunkId() == MAPIProperty.BODY.id) {
                textChunk = chunk;
            }
        }
        boolean doneBody = false;
        xhtml.startElement("div", "class", "message-body");
        if (htmlChunk != null) {
            byte[] data = null;
            if (htmlChunk instanceof ByteChunk) {
                data = ((ByteChunk) htmlChunk).getValue();
            } else if (htmlChunk instanceof StringChunk) {
                data = ((StringChunk) htmlChunk).getRawValue();
            }
            if (data != null) {
                Parser htmlParser = EmbeddedDocumentUtil.tryToFindExistingLeafParser(HtmlParser.class, parseContext);
                if (htmlParser == null) {
                    htmlParser = new HtmlParser();
                }
                htmlParser.parse(new ByteArrayInputStream(data), new EmbeddedContentHandler(new BodyContentHandler(xhtml)), new Metadata(), parseContext);
                doneBody = true;
            }
        }
        if (rtfChunk != null && !doneBody) {
            ByteChunk chunk = (ByteChunk) rtfChunk;
            MAPIRtfAttribute rtf = new MAPIRtfAttribute(MAPIProperty.RTF_COMPRESSED, Types.BINARY.getId(), chunk.getValue());
            Parser rtfParser = EmbeddedDocumentUtil.tryToFindExistingLeafParser(RTFParser.class, parseContext);
            if (rtfParser == null) {
                rtfParser = new RTFParser();
            }
            rtfParser.parse(new ByteArrayInputStream(rtf.getData()), new EmbeddedContentHandler(new BodyContentHandler(xhtml)), new Metadata(), parseContext);
            doneBody = true;
        }
        if (textChunk != null && !doneBody) {
            xhtml.element("p", ((StringChunk) textChunk).getValue());
        }
        xhtml.endElement("div");
        // Process the attachments
        for (AttachmentChunks attachment : msg.getAttachmentFiles()) {
            xhtml.startElement("div", "class", "attachment-entry");
            String filename = null;
            if (attachment.getAttachLongFileName() != null) {
                filename = attachment.getAttachLongFileName().getValue();
            } else if (attachment.getAttachFileName() != null) {
                filename = attachment.getAttachFileName().getValue();
            }
            if (filename != null && filename.length() > 0) {
                xhtml.element("h1", filename);
            }
            if (attachment.getAttachData() != null) {
                handleEmbeddedResource(TikaInputStream.get(attachment.getAttachData().getValue()), filename, null, null, xhtml, true);
            }
            if (attachment.getAttachmentDirectory() != null) {
                handleEmbeddedOfficeDoc(attachment.getAttachmentDirectory().getDirectory(), xhtml);
            }
            xhtml.endElement("div");
        }
    } catch (ChunkNotFoundException e) {
        throw new TikaException("POI MAPIMessage broken - didn't return null on missing chunk", e);
    } finally {
    //You'd think you'd want to call msg.close().
    //Don't do that.  That closes down the file system.
    //If an msg has multiple msg attachments, some of them
    //can reside in the same file system.  After the first
    //child is read, the fs is closed, and the other children
    //get a java.nio.channels.ClosedChannelException
    }
}

Example 3 with HtmlParser

use of org.apache.tika.parser.html.HtmlParser in project tika by apache.

the class TIAParsingExample method useHtmlParser.

public static void useHtmlParser() throws Exception {
    InputStream stream = new ByteArrayInputStream(new byte[0]);
    ContentHandler handler = new DefaultHandler();
    Metadata metadata = new Metadata();
    ParseContext context = new ParseContext();
    Parser parser = new HtmlParser();
    parser.parse(stream, handler, metadata, context);
}

Example 4 with HtmlParser

use of org.apache.tika.parser.html.HtmlParser in project tika by apache.

the class ChmParser method parse.

@Override
public void parse(InputStream stream, ContentHandler handler, Metadata metadata, ParseContext context) throws IOException, SAXException, TikaException {
    ChmExtractor chmExtractor = new ChmExtractor(stream);
    // metadata
    metadata.set(Metadata.CONTENT_TYPE, "application/vnd.ms-htmlhelp");
    // content
    XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
    xhtml.startDocument();
    Parser htmlParser = EmbeddedDocumentUtil.tryToFindExistingLeafParser(HtmlParser.class, context);
    if (htmlParser == null) {
        htmlParser = new HtmlParser();
    }
    for (DirectoryListingEntry entry : chmExtractor.getChmDirList().getDirectoryListingEntryList()) {
        final String entryName = entry.getName();
        if (entryName.endsWith(".html") || entryName.endsWith(".htm")) {
            //                AttributesImpl attrs = new AttributesImpl();
            //                attrs.addAttribute("", "name", "name", "String", entryName);
            //                xhtml.startElement("", "document", "document", attrs);
            byte[] data = chmExtractor.extractChmEntry(entry);
            parsePage(data, htmlParser, xhtml, context);
        //                xhtml.endElement("", "", "document");
        }
    }
    xhtml.endDocument();
}

Example 5 with HtmlParser

use of org.apache.tika.parser.html.HtmlParser in project tika by apache.

the class TIAParsingExample method useCompositeParser.

public static void useCompositeParser() throws Exception {
    InputStream stream = new ByteArrayInputStream(new byte[0]);
    ContentHandler handler = new DefaultHandler();
    ParseContext context = new ParseContext();
    Map<MediaType, Parser> parsersByType = new HashMap<MediaType, Parser>();
    parsersByType.put(MediaType.parse("text/html"), new HtmlParser());
    parsersByType.put(MediaType.parse("application/xml"), new XMLParser());
    CompositeParser parser = new CompositeParser();
    parser.setParsers(parsersByType);
    parser.setFallback(new TXTParser());
    Metadata metadata = new Metadata();
    metadata.set(Metadata.CONTENT_TYPE, "text/html");
    parser.parse(stream, handler, metadata, context);
}