nutch-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From lewismc <...@git.apache.org>
Subject [GitHub] nutch pull request: NUTCH-2155 - Add crawl completion utility
Date Wed, 28 Oct 2015 21:59:42 GMT
Github user lewismc commented on a diff in the pull request:

    https://github.com/apache/nutch/pull/83#discussion_r43324357
  
    --- Diff: src/java/org/apache/nutch/util/CrawlCompletionStats.java ---
    @@ -0,0 +1,189 @@
    +/**
    + * Licensed to the Apache Software Foundation (ASF) under one or more
    + * contributor license agreements.  See the NOTICE file distributed with
    + * this work for additional information regarding copyright ownership.
    + * The ASF licenses this file to You under the Apache License, Version 2.0
    + * (the "License"); you may not use this file except in compliance with
    + * the License.  You may obtain a copy of the License at
    + *
    + *     http://www.apache.org/licenses/LICENSE-2.0
    + *
    + * Unless required by applicable law or agreed to in writing, software
    + * distributed under the License is distributed on an "AS IS" BASIS,
    + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
    + * See the License for the specific language governing permissions and
    + * limitations under the License.
    + */
    +
    +package org.apache.nutch.util;
    +
    +import java.io.IOException;
    +import java.net.URL;
    +import java.text.SimpleDateFormat;
    +import org.slf4j.Logger;
    +import org.slf4j.LoggerFactory;
    +import org.apache.hadoop.conf.Configuration;
    +import org.apache.hadoop.conf.Configured;
    +import org.apache.hadoop.fs.Path;
    +import org.apache.hadoop.io.LongWritable;
    +import org.apache.hadoop.io.Text;
    +import org.apache.hadoop.mapreduce.Job;
    +import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
    +import org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat;
    +import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
    +import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
    +import org.apache.hadoop.mapreduce.Mapper;
    +import org.apache.hadoop.mapreduce.Reducer;
    +import org.apache.hadoop.util.Tool;
    +import org.apache.hadoop.util.ToolRunner;
    +import org.apache.nutch.crawl.CrawlDatum;
    +import org.apache.nutch.util.NutchConfiguration;
    +import org.apache.nutch.util.TimingUtil;
    +import org.apache.nutch.util.URLUtil;
    +
    +/**
    + * Extracts some simple crawl completion stats from the crawldb
    + *
    + * Stats will be sorted by host/domain and will be of the form:
    + * 1	www.spitzer.caltech.edu FETCHED
    + * 50	www.spitzer.caltech.edu UNFETCHED
    + *
    + */
    +public class CrawlCompletionStats extends Configured implements Tool {
    +
    +  private static final Logger LOG = LoggerFactory
    +      .getLogger(CrawlCompletionStats.class);
    +
    +  private static final int MODE_HOST = 1;
    +  private static final int MODE_DOMAIN = 2;
    +
    +  private int mode = 0;
    +
    +  public int run(String[] args) throws Exception {
    +    if (args.length < 2) {
    --- End diff --
    
    Not a absolute requirement but merely a suggestion, it would be GREAT to see commons-cli
used here to prevent incorrect CLI usage. It also prints much more user friendly output when
invoked without options or with '-h'.
    For excellent examples of where commons-cli is already used please see [here](https://github.com/apache/nutch/blob/trunk/src/java/org/apache/nutch/scoring/webgraph/WebGraph.java#L698-L760)
@MJJoyce.
    I like this job as well, it's a neat and quick way to see domain coverage.


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

Mime
View raw message