code in blog.sheimi.me: 2012-05-13-hadoop-source-code-01 (2)

crawl.java

linkDbTool.invert(linkDb, segments, true, true, false); // invert links

if (solrUrl != null) {
  // index, dedup & merge
  FileStatus[] fstats = fs.listStatus(segments, HadoopFSUtil.getPassDirectoriesFilter(fs));
  SolrIndexer indexer = new SolrIndexer(getConf());
  indexer.indexSolr(solrUrl, crawlDb, linkDb,
    Arrays.asList(HadoopFSUtil.getPaths(fstats)));
  SolrDeleteDuplicates dedup = new SolrDeleteDuplicates();
  dedup.setConf(getConf());
  dedup.dedup(solrUrl);
}