Search in sources :

Example 6 with ParseImpl

use of org.apache.nutch.parse.ParseImpl 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"));
}
Also used : ParseStatus(org.apache.nutch.parse.ParseStatus) NutchDocument(org.apache.nutch.indexer.NutchDocument) ParseData(org.apache.nutch.parse.ParseData) ParseImpl(org.apache.nutch.parse.ParseImpl) CrawlDatum(org.apache.nutch.crawl.CrawlDatum) Text(org.apache.hadoop.io.Text) Inlinks(org.apache.nutch.crawl.Inlinks) Inlink(org.apache.nutch.crawl.Inlink) URL(java.net.URL) Test(org.junit.Test)

Example 7 with ParseImpl

use of org.apache.nutch.parse.ParseImpl 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"));
}
Also used : Outlink(org.apache.nutch.parse.Outlink) ParseStatus(org.apache.nutch.parse.ParseStatus) NutchDocument(org.apache.nutch.indexer.NutchDocument) ParseData(org.apache.nutch.parse.ParseData) ParseImpl(org.apache.nutch.parse.ParseImpl) CrawlDatum(org.apache.nutch.crawl.CrawlDatum) Text(org.apache.hadoop.io.Text) Inlinks(org.apache.nutch.crawl.Inlinks) URL(java.net.URL) Test(org.junit.Test)

Example 8 with ParseImpl

use of org.apache.nutch.parse.ParseImpl 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"));
}
Also used : ParseStatus(org.apache.nutch.parse.ParseStatus) NutchDocument(org.apache.nutch.indexer.NutchDocument) ParseData(org.apache.nutch.parse.ParseData) ParseImpl(org.apache.nutch.parse.ParseImpl) CrawlDatum(org.apache.nutch.crawl.CrawlDatum) Text(org.apache.hadoop.io.Text) Inlinks(org.apache.nutch.crawl.Inlinks) Inlink(org.apache.nutch.crawl.Inlink) Test(org.junit.Test)

Example 9 with ParseImpl

use of org.apache.nutch.parse.ParseImpl 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"));
}
Also used : ParseStatus(org.apache.nutch.parse.ParseStatus) NutchDocument(org.apache.nutch.indexer.NutchDocument) ParseData(org.apache.nutch.parse.ParseData) Metadata(org.apache.nutch.metadata.Metadata) ParseImpl(org.apache.nutch.parse.ParseImpl) CrawlDatum(org.apache.nutch.crawl.CrawlDatum) Text(org.apache.hadoop.io.Text) Inlinks(org.apache.nutch.crawl.Inlinks)

Example 10 with ParseImpl

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

the class TestMoreIndexingFilter method testContentDispositionTitle.

@Test
public void testContentDispositionTitle() throws IndexingException {
    Configuration conf = NutchConfiguration.create();
    Metadata metadata = new Metadata();
    metadata.add(Response.CONTENT_DISPOSITION, "filename=filename.ext");
    MoreIndexingFilter filter = new MoreIndexingFilter();
    filter.setConf(conf);
    Text url = new Text("http://www.example.com/");
    ParseImpl parseImpl = new ParseImpl("text", new ParseData(new ParseStatus(), "title", new Outlink[0], metadata));
    NutchDocument doc = new NutchDocument();
    doc = filter.filter(doc, parseImpl, url, new CrawlDatum(), new Inlinks());
    Assert.assertEquals("content-disposition not detected", "filename.ext", doc.getFieldValue("title"));
    /* NUTCH-1140: do not add second title to avoid a multi-valued title field */
    doc = new NutchDocument();
    doc.add("title", "title");
    doc = filter.filter(doc, parseImpl, url, new CrawlDatum(), new Inlinks());
    Assert.assertEquals("do not add second title by content-disposition", "title", doc.getFieldValue("title"));
}
Also used : Outlink(org.apache.nutch.parse.Outlink) ParseStatus(org.apache.nutch.parse.ParseStatus) NutchConfiguration(org.apache.nutch.util.NutchConfiguration) Configuration(org.apache.hadoop.conf.Configuration) ParseData(org.apache.nutch.parse.ParseData) NutchDocument(org.apache.nutch.indexer.NutchDocument) Metadata(org.apache.nutch.metadata.Metadata) ParseImpl(org.apache.nutch.parse.ParseImpl) CrawlDatum(org.apache.nutch.crawl.CrawlDatum) Text(org.apache.hadoop.io.Text) Inlinks(org.apache.nutch.crawl.Inlinks) Test(org.junit.Test)

Aggregations

ParseImpl (org.apache.nutch.parse.ParseImpl)31 ParseData (org.apache.nutch.parse.ParseData)29 Text (org.apache.hadoop.io.Text)21 CrawlDatum (org.apache.nutch.crawl.CrawlDatum)21 ParseStatus (org.apache.nutch.parse.ParseStatus)21 Inlinks (org.apache.nutch.crawl.Inlinks)20 Outlink (org.apache.nutch.parse.Outlink)17 Test (org.junit.Test)17 NutchDocument (org.apache.nutch.indexer.NutchDocument)16 Metadata (org.apache.nutch.metadata.Metadata)15 Configuration (org.apache.hadoop.conf.Configuration)13 NutchConfiguration (org.apache.nutch.util.NutchConfiguration)13 URL (java.net.URL)6 IOException (java.io.IOException)5 Inlink (org.apache.nutch.crawl.Inlink)5 Parse (org.apache.nutch.parse.Parse)5 ByteArrayInputStream (java.io.ByteArrayInputStream)4 ArrayList (java.util.ArrayList)4 ParseResult (org.apache.nutch.parse.ParseResult)4 MalformedURLException (java.net.MalformedURLException)3