Examples with TripleHandlerException org.apache.any23.writer.TripleHandlerException used on opensource projects

Example 1 with TripleHandlerException

use of org.apache.any23.writer.TripleHandlerException in project nutch by apache.

the class Any23ParseFilter method filter.

/**
 * @see org.apache.nutch.parse.HtmlParseFilter#filter(Content, ParseResult, HTMLMetaTags, DocumentFragment)
 */
@Override
public ParseResult filter(Content content, ParseResult parseResult, HTMLMetaTags metaTags, DocumentFragment doc) {
    String[] extractorNames = conf.getStrings(ANY_23_EXTRACTORS_CONF, "html-head-meta");
    String[] supportedContentTypes = conf.getStrings(ANY_23_CONTENT_TYPES_CONF, "text/html", "application/xhtml+xml");
    String contentType = content.getContentType();
    if (supportedContentTypes != null && !Arrays.asList(supportedContentTypes).contains(contentType)) {
        LOG.debug("Ignoring document at {} because it has an unsupported Content-Type {}", content.getUrl(), contentType);
        return parseResult;
    }
    Any23Parser parser;
    try {
        String htmlContent = new String(content.getContent(), Charset.forName("UTF-8"));
        parser = new Any23Parser(content.getUrl(), htmlContent, contentType, extractorNames);
    } catch (TripleHandlerException e) {
        throw new RuntimeException("Error running Any23 parser: " + e.getMessage());
    }
    Set<String> triples = parser.getTriples();
    Parse parse = parseResult.get(content.getUrl());
    Metadata metadata = parse.getData().getParseMeta();
    for (String triple : triples) {
        metadata.add(ANY23_TRIPLES, triple);
    }
    return parseResult;
}