对generate.max.count参数的处理在org.apache.nutch.crawl.Generator内部类Selector中java
org.apache.nutch.crawl.Generator中相关变量声明状况apache
private HashMap<String, int[]> hostCounts = new HashMap<String, int[]>(); private int maxCount;
内部类Selector的config方法中数组
maxCount = job.getInt(GENERATOR_MAX_COUNT, -1);
reduce方法中的处理dom
/*** 一、获取 某一主机下的int[] ,若是为null,声明一个数组,放入map中,int数组第2个值+1; */ //1 int[] hostCount = hostCounts.get(hostordomain); if (hostCount == null) { hostCount = new int[] { 1, 0 }; hostCounts.put(hostordomain, hostCount); } hostCount[1]++;// increment hostCount //二、检查是否到了topN的数量,若是hostCount的第一个值大于limit // check if topN reached, select next segment if it is while (segCounts[hostCount[0] - 1] >= limit//segCounts : && hostCount[0] < maxNumSegments) { hostCount[0]++; hostCount[1] = 0; } // reached the limit of allowed URLs per host / domain // see if we can put it in the next segment? if (hostCount[1] >= maxCount) { if (hostCount[0] < maxNumSegments) { hostCount[0]++; hostCount[1] = 0; } else { if (hostCount[1] == maxCount + 1 && LOG.isInfoEnabled()) { LOG.info("Host or domain " + hostordomain + " has more than " + maxCount + " URLs for all " + maxNumSegments + " segments. Additional URLs won't be included in the fetchlist."); } // skip this entry continue; } } entry.segnum = new IntWritable(hostCount[0]); segCounts[hostCount[0] - 1]++;