reconciling scripts before another dev push

wctotal=`cat ${splitdir}/*_linecount.txt | awk '{sum+=$1}END{print sum/4}'`

check2=`cat ${splitdir}/*norm*res* | awk '{s2+=$2;}END{print s2}'`

# the below, check4, is still buggy and needs to be corrected

check4=`cat ${splitdir}/*norm*res* | awk '{s+=$3+$4+$5+$6;}END{print s}'`

if [ -z $ARG1 ] 

then

        echo "Reads don't add up.  Check ${outputdir} for results"

        exit 100

    fi

else

   # Alternate aligner check

   unmapamb=`awk 'NR%4==1{split($1,a,"_");split(a[1],b,"@"); c[b[2]]++}END{print length(c)}' ${splitdir}/*.fq`

   calctotal=`expr $check4 + $unmapamb`

   if [ $wctotal -ne $calctotal ]

   then

        echo "***! Error! The number of reads in the fastqs (${wctotal}) is not the same as the number of alignable reads reported in the stats (${check4}) plus unmapped/ambiguous (${unmapamb}), likely due to a failure during alignment. Run relaunch_prep.sh"

        echo "Reads don't add up.  Check ${outputdir} for results"

        exit 100

   else

       echo "Total: $wctotal"

       echo "Unalignable: $unmapamb"

   fi

fi

if [ -f ${outputdir}/inter.hic ] && [ -s ${outputdir}/inter.hic ] && [ -f ${outputdir}/inter_30.hic ] && [ -s ${outputdir}/inter_30.hic ]

# Juicer version 1.5

total=`ls -l aligned/merged_sort.txt | awk '{print $5}'`

total2=`ls -l aligned/merged_nodups.txt aligned/dups.txt aligned/opt_dups.txt | awk '{sum = sum + $5}END{print sum}'`

if [ $total -eq $total2 ]; then rm aligned/merged_sort.txt; rm -r splits; else echo "Problem: The sum of merged_nodups and the dups files is not the same size as merged_sort.txt"; fi

#bzip2 fastq/*.fastq

if [ $total -eq $total2 ] 

then 

    rm aligned/merged_sort.txt 

    rm -r splits 

    for i in fastq/*.fastq

    do

        gzip $i

    done

    gzip aligned/merged_nodups.txt

    gzip aligned/dups.txt

    gzip aligned/opt_dups.txt

    gzip aligned/abnormal.sam

    gzip aligned/collisions.txt

    gzip aligned/unmapped.sam

else 

    echo "Problem: The sum of merged_nodups and the dups files is not the same size as merged_sort.txt"

    echo "Did NOT clean up";

fi

# each line, the sorted locations of the enzyme restriction sites.

#

# Usage:  fragment.pl <infile>

# Juicer 1.5

use POSIX;

##########

# Juicer postprocessing script.

# This will find contact domains with Arrowhead.

# Juicer 1.5

## Read arguments

usageHelp="Usage: ${0} [-h] -j <juicer_tools_file_path> -i <hic_file_path>"

#  OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN

#  THE SOFTWARE.

##########

# Helper script for finding what files successfully aligned and preparing the directory for

# rerunning juicer.sh

# Juicer version 1.5

ls -l splits > ls_splits

awk '($9 ~/R1/ && $9 ~/fastq$/) || ($9 ~/R1/ && $9 ~/gz$/) {split($9, a, "_R1");  print a[1]a[2], $9}($9 ~/R2/ && $9 ~/fastq$/) || ($9 ~/R2/ && $9 ~/gz$/){split($9,a,"_R2");print a[1]a[2], $9}' ls_splits > fastq.txt

awk '($9 ~/_R1/ && $9 ~/fastq$/) || ($9 ~/_R1/ && $9 ~/gz$/) {split($9, a, "_R1");  print a[1]a[2], $9}($9 ~/_R2/ && $9 ~/fastq$/) || ($9 ~/_R2/ && $9 ~/gz$/){split($9,a,"_R2");print a[1]a[2], $9}' ls_splits > fastq.txt

awk '{name="splits/"$1"_norm.txt.res.txt"; if ((getline line < name) > 0){ split(line, a); if (length(a)<6 || a[2] != a[3]+a[4]+a[5]+a[6] || a[2] == 0){print "mv splits/"$2, "not_done; rm -f splits/"$1"*; rm -f splits/"$2"*;"} close(name);}else {print "mv splits/"$2, "not_done; rm -f splits/"$1"*; rm -f splits/"$2"*;"}}' fastq.txt > mv_me.sh

mkdir not_done

chmod 755 mv_me.sh

            mv splits done_splits

        fi

        mv not_done splits

        cat lsf.out >> done_lsf.out

        rm lsf.out

else

    rmdir not_done

    echo "Fastqs are aligned, run juicer.sh with -S merge flag";