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

Example 26 with ParseData

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

the class TestLinksIndexingFilter method testFilterOutlinks.

@Test
public void testFilterOutlinks() throws Exception {
    conf.set(LinksIndexingFilter.LINKS_OUTLINKS_HOST, "true");
    filter.setConf(conf);
    Outlink[] outlinks = generateOutlinks();
    NutchDocument doc = filter.filter(new NutchDocument(), new ParseImpl("text", new ParseData(new ParseStatus(), "title", outlinks, metadata)), new Text("http://www.example.com/"), new CrawlDatum(), new Inlinks());
    Assert.assertEquals(1, doc.getField("outlinks").getValues().size());
    Assert.assertEquals("Filter outlinks, allow only those from a different host", outlinks[0].getToUrl(), doc.getFieldValue("outlinks"));
}

Example 27 with ParseData

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

the class TestLinksIndexingFilter method testNoFilterInlinks.

@Test
public void testNoFilterInlinks() throws Exception {
    conf.set(LinksIndexingFilter.LINKS_INLINKS_HOST, "false");
    filter.setConf(conf);
    Inlinks inlinks = new Inlinks();
    inlinks.add(new Inlink("http://www.test.com", "test"));
    inlinks.add(new Inlink("http://www.example.com", "example"));
    NutchDocument doc = filter.filter(new NutchDocument(), new ParseImpl("text", new ParseData(new ParseStatus(), "title", new Outlink[0], metadata)), new Text("http://www.example.com/"), new CrawlDatum(), inlinks);
    Assert.assertEquals("All inlinks must be indexed even those from the same host", inlinks.size(), doc.getField("inlinks").getValues().size());
}

Example 28 with ParseData

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

the class TestLinksIndexingFilter method testNoFilterOutlinks.

@Test
public void testNoFilterOutlinks() throws Exception {
    filter.setConf(conf);
    Outlink[] outlinks = generateOutlinks();
    NutchDocument doc = filter.filter(new NutchDocument(), new ParseImpl("text", new ParseData(new ParseStatus(), "title", outlinks, metadata)), new Text("http://www.example.com/"), new CrawlDatum(), new Inlinks());
    Assert.assertEquals("All outlinks must be indexed even those from the same host", outlinks.length, doc.getField("outlinks").getValues().size());
}

Example 29 with ParseData

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

the class TestLinksIndexingFilter method testIndexOnlyHostPart.

@Test
public void testIndexOnlyHostPart() throws Exception {
    conf.set(LinksIndexingFilter.LINKS_INLINKS_HOST, "true");
    conf.set(LinksIndexingFilter.LINKS_OUTLINKS_HOST, "true");
    conf.set(LinksIndexingFilter.LINKS_ONLY_HOSTS, "true");
    filter.setConf(conf);
    Outlink[] outlinks = generateOutlinks(true);
    Inlinks inlinks = new Inlinks();
    inlinks.add(new Inlink("http://www.test.com/one-awesome-page", "test"));
    inlinks.add(new Inlink("http://www.test.com/other-awesome-page", "test"));
    inlinks.add(new Inlink("http://www.example.com/my-first-awesome-example", "example"));
    NutchDocument doc = filter.filter(new NutchDocument(), new ParseImpl("text", new ParseData(new ParseStatus(), "title", outlinks, metadata)), new Text("http://www.example.com/"), new CrawlDatum(), inlinks);
    NutchField docOutlinks = doc.getField("outlinks");
    Assert.assertEquals("Only the host portion of the outlink URL must be indexed", new URL("http://www.test.com").getHost(), docOutlinks.getValues().get(0));
    Assert.assertEquals("The inlinks coming from the same host must count only once", 1, doc.getField("inlinks").getValues().size());
    Assert.assertEquals("Only the host portion of the inlinks URL must be indexed", new URL("http://www.test.com").getHost(), doc.getFieldValue("inlinks"));
}

Example 30 with ParseData

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

the class MimeTypeIndexingFilter method main.

/**
 * Main method for invoking this tool
 *
 * @throws IOException
 * @throws IndexingException
 */
public static void main(String[] args) throws IOException, IndexingException {
    Option helpOpt = new Option("h", "help", false, "show this help message");
    Option rulesOpt = OptionBuilder.withArgName("file").hasArg().withDescription("Rules file to be used in the tests relative to the conf directory").isRequired().create("rules");
    Options options = new Options();
    options.addOption(helpOpt).addOption(rulesOpt);
    CommandLineParser parser = new GnuParser();
    HelpFormatter formatter = new HelpFormatter();
    String rulesFile;
    try {
        CommandLine line = parser.parse(options, args);
        if (line.hasOption("help") || !line.hasOption("rules")) {
            formatter.printHelp("org.apache.nutch.indexer.filter.MimeTypeIndexingFilter", options, true);
            return;
        }
        rulesFile = line.getOptionValue("rules");
    } catch (UnrecognizedOptionException e) {
        formatter.printHelp("org.apache.nutch.indexer.filter.MimeTypeIndexingFilter", options, true);
        return;
    } catch (Exception e) {
        LOG.error(StringUtils.stringifyException(e));
        e.printStackTrace();
        return;
    }
    MimeTypeIndexingFilter filter = new MimeTypeIndexingFilter();
    Configuration conf = NutchConfiguration.create();
    conf.set(MimeTypeIndexingFilter.MIMEFILTER_REGEX_FILE, rulesFile);
    filter.setConf(conf);
    BufferedReader in = new BufferedReader(new InputStreamReader(System.in));
    String line;
    while ((line = in.readLine()) != null && !line.isEmpty()) {
        Metadata metadata = new Metadata();
        metadata.set(Response.CONTENT_TYPE, line);
        ParseImpl parse = new ParseImpl("text", new ParseData(new ParseStatus(), "title", new Outlink[0], metadata));
        NutchDocument doc = filter.filter(new NutchDocument(), parse, new Text("http://www.example.com/"), new CrawlDatum(), new Inlinks());
        if (doc != null) {
            System.out.print("+ ");
            System.out.println(line);
        } else {
            System.out.print("- ");
            System.out.println(line);
        }
    }
}