#!/bin/bash
#
# 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.
# 
# The Crawl command script : crawl <seedDir> <crawlDir> <solrURL> <numberOfRounds>
#
# 
# UNLIKE THE NUTCH ALL-IN-ONE-CRAWL COMMAND THIS SCRIPT DOES THE LINK INVERSION AND 
# INDEXING FOR EACH SEGMENT

SEEDDIR="$1"
CRAWL_PATH="$2"
SOLRURL="$3"
LIMIT="$4"

if [ "$SEEDDIR" = "" ]; then
    echo "Missing seedDir : crawl <seedDir> <crawlDir> <solrURL> <numberOfRounds>"
    exit -1;
fi

if [ "$CRAWL_PATH" = "" ]; then
    echo "Missing crawlDir : crawl <seedDir> <crawlDir> <solrURL> <numberOfRounds>"
    exit -1;
fi

if [ "$SOLRURL" = "" ]; then
    echo "Missing SOLRURL : crawl <seedDir> <crawlDir> <solrURL> <numberOfRounds>"
    exit -1;
fi

if [ "$LIMIT" = "" ]; then
    echo "Missing numberOfRounds : crawl <seedDir> <crawlDir> <solrURL> <numberOfRounds>"
    exit -1;
fi

#############################################
# MODIFY THE PARAMETERS BELOW TO YOUR NEEDS #
#############################################

# set the number of slaves nodes
numSlaves=1

# and the total number of available tasks
# sets Hadoop parameter "mapred.reduce.tasks"
numTasks=`expr $numSlaves \* 2`

# number of urls to fetch in one iteration
# 250K per task?
# Note from Apache Solr Book Authors: This line below is the stock line.
#sizeFetchlist=`expr $numSlaves \* 50000`
# Note from Apache Solr Book Authors: This line lets us control the topN aggregate documents listed.
sizeFetchlist=10

# time limit for feching
timeLimitFetch=180

# num threads for fetching
numThreads=50

#############################################

# determines whether mode based on presence of job file

mode=local
if [ -f ../*nutch-*.job ]; then
    mode=distributed
fi

bin=`dirname "$0"`
bin=`cd "$bin"; pwd`

# note that some of the options listed here could be set in the 
# corresponding hadoop site xml param file 
commonOptions="-D mapred.reduce.tasks=$numTasks -D mapred.child.java.opts=-Xmx1000m -D mapred.reduce.tasks.speculative.execution=false -D mapred.map.tasks.speculative.execution=false -D mapred.compress.map.output=true"

 # check that hadoop can be found on the path 
if [ $mode = "distributed" ]; then
 if [ $(which hadoop | wc -l ) -eq 0 ]; then
    echo "Can't find Hadoop executable. Add HADOOP_HOME/bin to the path or run in local mode."
    exit -1;
 fi
fi

# initial injection
$bin/nutch inject $CRAWL_PATH/crawldb $SEEDDIR

if [ $? -ne 0 ] 
  then exit $? 
fi


# main loop : rounds of generate - fetch - parse - update
for ((a=1; a <= LIMIT ; a++))
do
  if [ -e ".STOP" ]
  then
   echo "STOP file found - escaping loop"
   break
  fi

  echo `date` ": Iteration $a of $LIMIT"

  echo "Generating a new segment"
  $bin/nutch generate $commonOptions $CRAWL_PATH/crawldb $CRAWL_PATH/segments -topN $sizeFetchlist -numFetchers $numSlaves -noFilter
  
  if [ $? -ne 0 ] 
  then exit $? 
  fi

  # capture the name of the segment
  # call hadoop in distributed mode
  # or use ls

  if [ $mode = "local" ]; then
   SEGMENT=`ls $CRAWL_PATH/segments/ | sort -n | tail -n 1`
  else
   SEGMENT=`hadoop fs -ls $CRAWL_PATH/segments/ | grep segments |  sed -e "s/\//\\n/g" | egrep 20[0-9]+ | sort -n | tail -n 1`
  fi
  
  echo "Operating on segment : $SEGMENT"

  # fetching the segment
  echo "Fetching : $SEGMENT"
  $bin/nutch fetch $commonOptions -D fetcher.timelimit.mins=$timeLimitFetch $CRAWL_PATH/segments/$SEGMENT -noParsing -threads $numThreads

  if [ $? -ne 0 ] 
  then exit $? 
  fi

  # parsing the segment
  echo "Parsing : $SEGMENT"
  # enable the skipping of records for the parsing so that a dodgy document 
  # so that it does not fail the full task
  skipRecordsOptions="-D mapred.skip.attempts.to.start.skipping=2 -D mapred.skip.map.max.skip.records=1"
  $bin/nutch parse $commonOptions $skipRecordsOptions $CRAWL_PATH/segments/$SEGMENT

  if [ $? -ne 0 ] 
  then exit $? 
  fi

  # updatedb with this segment
  echo "CrawlDB update"
  $bin/nutch updatedb $commonOptions $CRAWL_PATH/crawldb  $CRAWL_PATH/segments/$SEGMENT

  if [ $? -ne 0 ] 
  then exit $? 
  fi

# note that the link inversion - indexing routine can be done within the main loop 
# on a per segment basis
  echo "Link inversion"
  $bin/nutch invertlinks $CRAWL_PATH/linkdb $CRAWL_PATH/segments/$SEGMENT

  if [ $? -ne 0 ] 
  then exit $? 
  fi

  echo "Dedup on crawldb"
  $bin/nutch dedup $CRAWL_PATH/crawldb
  
  if [ $? -ne 0 ] 
   then exit $? 
  fi

  echo "Indexing $SEGMENT on SOLR index -> $SOLRURL"
  $bin/nutch index -D solr.server.url=$SOLRURL $CRAWL_PATH/crawldb -linkdb $CRAWL_PATH/linkdb $CRAWL_PATH/segments/$SEGMENT
  
  if [ $? -ne 0 ] 
   then exit $? 
  fi

  echo "Cleanup on SOLR index -> $SOLRURL"
  $bin/nutch clean -D solr.server.url=$SOLRURL $CRAWL_PATH/crawldb
  
  if [ $? -ne 0 ] 
   then exit $? 
  fi

done

exit 0

