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

Example 6 with CrawlDatum

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

the class TestJexlIndexingFilter method testBlockNotMatchingDocuments.

@Test
public void testBlockNotMatchingDocuments() throws Exception {
    Configuration conf = NutchConfiguration.create();
    conf.set("index.jexl.filter", "doc.lang[0]=='en'");
    JexlIndexingFilter filter = new JexlIndexingFilter();
    filter.setConf(conf);
    Assert.assertNotNull(filter);
    NutchDocument doc = new NutchDocument();
    String title = "The Foo Page";
    Outlink[] outlinks = new Outlink[] { new Outlink("http://foo.com/", "Foo") };
    Metadata metaData = new Metadata();
    metaData.add("Language", "en/us");
    ParseData parseData = new ParseData(ParseStatus.STATUS_SUCCESS, title, outlinks, metaData);
    ParseImpl parse = new ParseImpl("this is a sample foo bar page. hope you enjoy it.", parseData);
    CrawlDatum crawlDatum = new CrawlDatum();
    crawlDatum.setFetchTime(100L);
    Inlinks inlinks = new Inlinks();
    doc.add("lang", "ru");
    NutchDocument result = filter.filter(doc, parse, new Text("http://nutch.apache.org/index.html"), crawlDatum, inlinks);
    Assert.assertNull(result);
}

Example 7 with CrawlDatum

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

the class TestLinksIndexingFilter method testIndexHostsOnlyAndFilterInlinks.

@Test
public void testIndexHostsOnlyAndFilterInlinks() throws Exception {
    conf = NutchConfiguration.create();
    conf.set(LinksIndexingFilter.LINKS_ONLY_HOSTS, "true");
    conf.set(LinksIndexingFilter.LINKS_INLINKS_HOST, "true");
    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(1, doc.getField("inlinks").getValues().size());
    Assert.assertEquals("Index only the host portion of the inlinks after filtering", new URL("http://www.test.com").getHost(), doc.getFieldValue("inlinks"));
}

Example 8 with CrawlDatum

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

the class TestLinksIndexingFilter method testIndexHostsOnlyAndFilterOutlinks.

@Test
public void testIndexHostsOnlyAndFilterOutlinks() throws Exception {
    conf = NutchConfiguration.create();
    conf.set(LinksIndexingFilter.LINKS_ONLY_HOSTS, "true");
    conf.set(LinksIndexingFilter.LINKS_OUTLINKS_HOST, "true");
    Outlink[] outlinks = generateOutlinks(true);
    filter.setConf(conf);
    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("Index only the host portion of the outlinks after filtering", new URL("http://www.test.com").getHost(), doc.getFieldValue("outlinks"));
}

Example 9 with CrawlDatum

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

the class TestLinksIndexingFilter method testFilterInlinks.

@Test
public void testFilterInlinks() throws Exception {
    conf.set(LinksIndexingFilter.LINKS_INLINKS_HOST, "true");
    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(1, doc.getField("inlinks").getValues().size());
    Assert.assertEquals("Filter inlinks, allow only those from a different host", "http://www.test.com", doc.getFieldValue("inlinks"));
}

Example 10 with CrawlDatum

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

the class TestMoreIndexingFilter method assertContentType.

private void assertContentType(Configuration conf, String source, String expected) throws IndexingException {
    Metadata metadata = new Metadata();
    metadata.add(Response.CONTENT_TYPE, source);
    MoreIndexingFilter filter = new MoreIndexingFilter();
    filter.setConf(conf);
    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(), new Inlinks());
    Assert.assertEquals("mime type not detected", expected, doc.getFieldValue("type"));
}