#!/bin/bash

# This script should be put into cc-index-table (github project) toplevel folder
# It works with the get_maori_WET_records_for_crawl.sh script, which has to be
# placed in cc-index-table/src/script

# crawl_ids are from http://index.commoncrawl.org/
# We only want the crawl_ids from Sep 2018 and onwards as that's when
# the content_languages field was included in CommonCrawl's columnar index

# https://www.cyberciti.biz/faq/bash-for-loop-array/
# (else chain commands as at https://superuser.com/questions/237072/wrapping-long-bash-commands-in-script-files)
crawl_ids=( "CC-MAIN-2019-35" "CC-MAIN-2019-30" "CC-MAIN-2019-26" \
      "CC-MAIN-2019-22" "CC-MAIN-2019-18" "CC-MAIN-2019-13" \
      "CC-MAIN-2019-09" "CC-MAIN-2019-04" "CC-MAIN-2018-51" \
      "CC-MAIN-2018-47" "CC-MAIN-2018-43" "CC-MAIN-2018-39" )

for crawl_id in "${crawl_ids[@]}"
do
    echo "About to start off index and WARC download process for CRAWL ID: $crawl_id"
    ./src/script/get_maori_WET_records_for_crawl.sh $crawl_id
    result=$?
    if [ $result != 0 ]; then
	echo "Processing common-crawl $crawl_id failed with exit value: $result"
	echo "Will cease to process remaining cc crawls. Exitting..."
	exit $result
    fi
done

# Important note from
# https://www.tldp.org/LDP/abs/html/exit-status.html
# "When a script ends with an exit that has no parameter, the exit
# status of the script is the exit status of the last command executed
# in the script (previous to the exit)."