Examples with ParseData org.apache.nutch.parse.ParseData used on opensource projects

Example 16 with ParseData

use of org.apache.nutch.parse.ParseData in project nutch by apache.

the class ExtParser method getParse.

public ParseResult getParse(Content content) {
    String contentType = content.getContentType();
    String[] params = (String[]) TYPE_PARAMS_MAP.get(contentType);
    if (params == null)
        return new ParseStatus(ParseStatus.FAILED, "No external command defined for contentType: " + contentType).getEmptyParseResult(content.getUrl(), getConf());
    String command = params[0];
    int timeout = Integer.parseInt(params[1]);
    String encoding = params[2];
    if (LOG.isTraceEnabled()) {
        LOG.trace("Use " + command + " with timeout=" + timeout + "secs");
    }
    String text = null;
    String title = null;
    try {
        byte[] raw = content.getContent();
        String contentLength = content.getMetadata().get(Response.CONTENT_LENGTH);
        if (contentLength != null && raw.length != Integer.parseInt(contentLength)) {
            return new ParseStatus(ParseStatus.FAILED, ParseStatus.FAILED_TRUNCATED, "Content truncated at " + raw.length + " bytes. Parser can't handle incomplete " + contentType + " file.").getEmptyParseResult(content.getUrl(), getConf());
        }
        ByteArrayOutputStream os = new ByteArrayOutputStream(BUFFER_SIZE);
        ByteArrayOutputStream es = new ByteArrayOutputStream(BUFFER_SIZE / 4);
        CommandRunner cr = new CommandRunner();
        cr.setCommand(command + " " + contentType);
        cr.setInputStream(new ByteArrayInputStream(raw));
        cr.setStdOutputStream(os);
        cr.setStdErrorStream(es);
        cr.setTimeout(timeout);
        cr.evaluate();
        if (cr.getExitValue() != 0)
            return new ParseStatus(ParseStatus.FAILED, "External command " + command + " failed with error: " + es.toString()).getEmptyParseResult(content.getUrl(), getConf());
        text = os.toString(encoding);
    } catch (Exception e) {
        // run time exception
        return new ParseStatus(e).getEmptyParseResult(content.getUrl(), getConf());
    }
    if (text == null)
        text = "";
    if (title == null)
        title = "";
    // collect outlink
    Outlink[] outlinks = OutlinkExtractor.getOutlinks(text, getConf());
    ParseData parseData = new ParseData(ParseStatus.STATUS_SUCCESS, title, outlinks, content.getMetadata());
    return ParseResult.createParseResult(content.getUrl(), new ParseImpl(text, parseData));
}

Example 17 with ParseData

use of org.apache.nutch.parse.ParseData in project nutch by apache.

the class HtmlParser method getParse.

public ParseResult getParse(Content content) {
    HTMLMetaTags metaTags = new HTMLMetaTags();
    URL base;
    try {
        base = new URL(content.getBaseUrl());
    } catch (MalformedURLException e) {
        return new ParseStatus(e).getEmptyParseResult(content.getUrl(), getConf());
    }
    String text = "";
    String title = "";
    Outlink[] outlinks = new Outlink[0];
    Metadata metadata = new Metadata();
    // parse the content
    DocumentFragment root;
    try {
        byte[] contentInOctets = content.getContent();
        InputSource input = new InputSource(new ByteArrayInputStream(contentInOctets));
        EncodingDetector detector = new EncodingDetector(conf);
        detector.autoDetectClues(content, true);
        detector.addClue(sniffCharacterEncoding(contentInOctets), "sniffed");
        String encoding = detector.guessEncoding(content, defaultCharEncoding);
        metadata.set(Metadata.ORIGINAL_CHAR_ENCODING, encoding);
        metadata.set(Metadata.CHAR_ENCODING_FOR_CONVERSION, encoding);
        input.setEncoding(encoding);
        if (LOG.isTraceEnabled()) {
            LOG.trace("Parsing...");
        }
        root = parse(input);
    } catch (IOException e) {
        return new ParseStatus(e).getEmptyParseResult(content.getUrl(), getConf());
    } catch (DOMException e) {
        return new ParseStatus(e).getEmptyParseResult(content.getUrl(), getConf());
    } catch (SAXException e) {
        return new ParseStatus(e).getEmptyParseResult(content.getUrl(), getConf());
    } catch (Exception e) {
        LOG.error("Error: ", e);
        return new ParseStatus(e).getEmptyParseResult(content.getUrl(), getConf());
    }
    // get meta directives
    HTMLMetaProcessor.getMetaTags(metaTags, root, base);
    // populate Nutch metadata with HTML meta directives
    metadata.addAll(metaTags.getGeneralTags());
    if (LOG.isTraceEnabled()) {
        LOG.trace("Meta tags for " + base + ": " + metaTags.toString());
    }
    // check meta directives
    if (!metaTags.getNoIndex()) {
        // okay to index
        StringBuffer sb = new StringBuffer();
        if (LOG.isTraceEnabled()) {
            LOG.trace("Getting text...");
        }
        // extract text
        utils.getText(sb, root);
        text = sb.toString();
        sb.setLength(0);
        if (LOG.isTraceEnabled()) {
            LOG.trace("Getting title...");
        }
        // extract title
        utils.getTitle(sb, root);
        title = sb.toString().trim();
    }
    if (!metaTags.getNoFollow()) {
        // okay to follow links
        // extract outlinks
        ArrayList<Outlink> l = new ArrayList<Outlink>();
        URL baseTag = base;
        String baseTagHref = utils.getBase(root);
        if (baseTagHref != null) {
            try {
                baseTag = new URL(base, baseTagHref);
            } catch (MalformedURLException e) {
                baseTag = base;
            }
        }
        if (LOG.isTraceEnabled()) {
            LOG.trace("Getting links...");
        }
        utils.getOutlinks(baseTag, l, root);
        outlinks = l.toArray(new Outlink[l.size()]);
        if (LOG.isTraceEnabled()) {
            LOG.trace("found " + outlinks.length + " outlinks in " + content.getUrl());
        }
    }
    ParseStatus status = new ParseStatus(ParseStatus.SUCCESS);
    if (metaTags.getRefresh()) {
        status.setMinorCode(ParseStatus.SUCCESS_REDIRECT);
        status.setArgs(new String[] { metaTags.getRefreshHref().toString(), Integer.toString(metaTags.getRefreshTime()) });
    }
    ParseData parseData = new ParseData(status, title, outlinks, content.getMetadata(), metadata);
    ParseResult parseResult = ParseResult.createParseResult(content.getUrl(), new ParseImpl(text, parseData));
    // run filters on parse
    ParseResult filteredParse = this.htmlParseFilters.filter(content, parseResult, metaTags, root);
    if (metaTags.getNoCache()) {
        // not okay to cache
        for (Map.Entry<org.apache.hadoop.io.Text, Parse> entry : filteredParse) entry.getValue().getData().getParseMeta().set(Nutch.CACHING_FORBIDDEN_KEY, cachingPolicy);
    }
    return filteredParse;
}

Example 18 with ParseData

use of org.apache.nutch.parse.ParseData in project nutch by apache.

the class JSParseFilter method getParse.

public ParseResult getParse(Content c) {
    String type = c.getContentType();
    if (type != null && !type.trim().equals("") && !type.toLowerCase().startsWith("application/x-javascript"))
        return new ParseStatus(ParseStatus.FAILED_INVALID_FORMAT, "Content not JavaScript: '" + type + "'").getEmptyParseResult(c.getUrl(), getConf());
    String script = new String(c.getContent());
    Outlink[] outlinks = getJSLinks(script, "", c.getUrl());
    if (outlinks == null)
        outlinks = new Outlink[0];
    // Title? use the first line of the script...
    String title;
    int idx = script.indexOf('\n');
    if (idx != -1) {
        if (idx > MAX_TITLE_LEN)
            idx = MAX_TITLE_LEN;
        title = script.substring(0, idx);
    } else {
        idx = Math.min(MAX_TITLE_LEN, script.length());
        title = script.substring(0, idx);
    }
    ParseData pd = new ParseData(ParseStatus.STATUS_SUCCESS, title, outlinks, c.getMetadata());
    return ParseResult.createParseResult(c.getUrl(), new ParseImpl(script, pd));
}

Example 19 with ParseData

use of org.apache.nutch.parse.ParseData in project nutch by apache.

the class JSParseFilter method filter.

public ParseResult filter(Content content, ParseResult parseResult, HTMLMetaTags metaTags, DocumentFragment doc) {
    Parse parse = parseResult.get(content.getUrl());
    String url = content.getBaseUrl();
    ArrayList<Outlink> outlinks = new ArrayList<Outlink>();
    walk(doc, parse, metaTags, url, outlinks);
    if (outlinks.size() > 0) {
        Outlink[] old = parse.getData().getOutlinks();
        String title = parse.getData().getTitle();
        List<Outlink> list = Arrays.asList(old);
        outlinks.addAll(list);
        ParseStatus status = parse.getData().getStatus();
        String text = parse.getText();
        Outlink[] newlinks = (Outlink[]) outlinks.toArray(new Outlink[outlinks.size()]);
        ParseData parseData = new ParseData(status, title, newlinks, parse.getData().getContentMeta(), parse.getData().getParseMeta());
        // replace original parse obj with new one
        parseResult.put(content.getUrl(), new ParseText(text), parseData);
    }
    return parseResult;
}

Example 20 with ParseData

use of org.apache.nutch.parse.ParseData in project nutch by apache.

the class ZipTextExtractor method extractText.

public String extractText(InputStream input, String url, List<Outlink> outLinksList) throws IOException {
    String resultText = "";
    ZipInputStream zin = new ZipInputStream(input);
    ZipEntry entry;
    while ((entry = zin.getNextEntry()) != null) {
        if (!entry.isDirectory()) {
            int size = (int) entry.getSize();
            byte[] b = new byte[size];
            for (int x = 0; x < size; x++) {
                int err = zin.read();
                if (err != -1) {
                    b[x] = (byte) err;
                }
            }
            String newurl = url + "/";
            String fname = entry.getName();
            newurl += fname;
            URL aURL = new URL(newurl);
            String base = aURL.toString();
            int i = fname.lastIndexOf('.');
            if (i != -1) {
                // Trying to resolve the Mime-Type
                Tika tika = new Tika();
                String contentType = tika.detect(fname);
                try {
                    Metadata metadata = new Metadata();
                    metadata.set(Response.CONTENT_LENGTH, Long.toString(entry.getSize()));
                    metadata.set(Response.CONTENT_TYPE, contentType);
                    Content content = new Content(newurl, base, b, contentType, metadata, this.conf);
                    Parse parse = new ParseUtil(this.conf).parse(content).get(content.getUrl());
                    ParseData theParseData = parse.getData();
                    Outlink[] theOutlinks = theParseData.getOutlinks();
                    for (int count = 0; count < theOutlinks.length; count++) {
                        outLinksList.add(new Outlink(theOutlinks[count].getToUrl(), theOutlinks[count].getAnchor()));
                    }
                    resultText += entry.getName() + " " + parse.getText() + " ";
                } catch (ParseException e) {
                    if (LOG.isInfoEnabled()) {
                        LOG.info("fetch okay, but can't parse " + fname + ", reason: " + e.getMessage());
                    }
                }
            }
        }
    }
    return resultText;
}