use of org.apache.nutch.indexer.basic.BasicIndexingFilter in project nutch by apache.
the class TestBasicIndexingFilter method testBasicIndexingFilter.
@Test
public void testBasicIndexingFilter() throws Exception {
Configuration conf = NutchConfiguration.create();
conf.setInt("indexer.max.title.length", 10);
conf.setBoolean("indexer.add.domain", true);
conf.setInt("indexer.max.content.length", 20);
BasicIndexingFilter filter = new BasicIndexingFilter();
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();
try {
filter.filter(doc, parse, new Text("http://nutch.apache.org/index.html"), crawlDatum, inlinks);
} catch (Exception e) {
e.printStackTrace();
Assert.fail(e.getMessage());
}
Assert.assertNotNull(doc);
Assert.assertEquals("test title, expect \"The Foo Pa\"", "The Foo Pa", doc.getField("title").getValues().get(0));
Assert.assertEquals("test domain, expect \"apache.org\"", "apache.org", doc.getField("domain").getValues().get(0));
Assert.assertEquals("test host, expect \"nutch.apache.org\"", "nutch.apache.org", doc.getField("host").getValues().get(0));
Assert.assertEquals("test url, expect \"http://nutch.apache.org/index.html\"", "http://nutch.apache.org/index.html", doc.getField("url").getValues().get(0));
Assert.assertEquals("test content", "this is a sample foo", doc.getField("content").getValues().get(0));
Assert.assertEquals("test fetch time", new Date(100L), (Date) doc.getField("tstamp").getValues().get(0));
}
use of org.apache.nutch.indexer.basic.BasicIndexingFilter 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;
}
Aggregations