Method reduce

src/java/org/apache/nutch/crawl/DbUpdateReducer.java:81–237

(UrlWithScore key, Iterable<NutchWritable> values,
      Context context)

  }

  @Override
  protected void reduce(UrlWithScore key, Iterable<NutchWritable> values,
      Context context) throws IOException, InterruptedException {
    String keyUrl = key.getUrl().toString();

    WebPage page = null;
    //initialize old_page for checking if the outlink is already in the datastore
    WebPage old_page = null;
    inlinkedScoreData.clear();

    for (NutchWritable nutchWritable : values) {
      Writable val = nutchWritable.get();
      if (val instanceof WebPageWritable) {
        page = ((WebPageWritable) val).getWebPage();
      } else {
        inlinkedScoreData.add((ScoreDatum) val);
        if (inlinkedScoreData.size() >= maxLinks) {
          LOG.info("Limit reached, skipping further inlinks for " + keyUrl);
          break;
        }
      }
    }
    String url;
    try {
      url = TableUtil.unreverseUrl(keyUrl);
    } catch (Exception e) {
      // this can happen because a newly discovered malformed link
      // may slip by url filters
      // TODO: Find a better solution
      return;
    }

    //check if page is already in the db
    if(page == null && (old_page = datastore.get(keyUrl)) != null) { 
      //if we return here inlinks will not be updated
      page=old_page;
    } 
    else if (page == null) { //new row 
      if (!additionsAllowed) {
        return;
      }
      page = WebPage.newBuilder().build();
      schedule.initializeSchedule(url, page);
      page.setStatus((int) CrawlStatus.STATUS_UNFETCHED);
      try {
        scoringFilters.initialScore(url, page);
      } catch (ScoringFilterException e) {
        page.setScore(0.0f);
      }
    } else {
      byte status = page.getStatus().byteValue();
      switch (status) {
      case CrawlStatus.STATUS_FETCHED: // succesful fetch
      case CrawlStatus.STATUS_REDIR_TEMP: // successful fetch, redirected
      case CrawlStatus.STATUS_REDIR_PERM:
      case CrawlStatus.STATUS_NOTMODIFIED: // successful fetch, notmodified
        int modified = FetchSchedule.STATUS_UNKNOWN;
        if (status == CrawlStatus.STATUS_NOTMODIFIED) {