Examples with CrawlDatum org.apache.nutch.crawl.CrawlDatum used on opensource projects

Example 36 with CrawlDatum

use of org.apache.nutch.crawl.CrawlDatum 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 37 with CrawlDatum

use of org.apache.nutch.crawl.CrawlDatum 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 38 with CrawlDatum

use of org.apache.nutch.crawl.CrawlDatum 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 39 with CrawlDatum

use of org.apache.nutch.crawl.CrawlDatum 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 40 with CrawlDatum

use of org.apache.nutch.crawl.CrawlDatum in project nutch by apache.

the class TestIndexReplace method parseAndFilterFile.

/**
 * Run a test file through the Nutch parser and index filters.
 *
 * @param fileName
 * @param conf
 * @return the Nutch document with the replace indexer applied
 */
public NutchDocument parseAndFilterFile(String fileName, Configuration conf) {
    NutchDocument doc = new NutchDocument();
    BasicIndexingFilter basicIndexer = new BasicIndexingFilter();
    basicIndexer.setConf(conf);
    Assert.assertNotNull(basicIndexer);
    MetadataIndexer metaIndexer = new MetadataIndexer();
    metaIndexer.setConf(conf);
    Assert.assertNotNull(basicIndexer);
    ReplaceIndexer replaceIndexer = new ReplaceIndexer();
    replaceIndexer.setConf(conf);
    Assert.assertNotNull(replaceIndexer);
    try {
        String urlString = "file:" + sampleDir + fileSeparator + fileName;
        Text text = new Text(urlString);
        CrawlDatum crawlDatum = new CrawlDatum();
        Protocol protocol = new ProtocolFactory(conf).getProtocol(urlString);
        Content content = protocol.getProtocolOutput(text, crawlDatum).getContent();
        Parse parse = new ParseUtil(conf).parse(content).get(content.getUrl());
        crawlDatum.setFetchTime(100L);
        Inlinks inlinks = new Inlinks();
        doc = basicIndexer.filter(doc, parse, text, crawlDatum, inlinks);
        doc = metaIndexer.filter(doc, parse, text, crawlDatum, inlinks);
        doc = replaceIndexer.filter(doc, parse, text, crawlDatum, inlinks);
    } catch (Exception e) {
        e.printStackTrace();
        Assert.fail(e.toString());
    }
    return doc;
}