setlogic

#!/bin/sh
# vim:set ft=sh et sw=4 sts=4:




function assert_file ()
{
   ONE=$1
   [[ -z "$ONE" ]] && { echo "MISSING PARAMETER"; return 1; };
   [[ -f "$ONE" ]] || { echo "$ONE: IS NOT A FILE"; return 1; };
}

function file_intersection ()
{
   ONE=$1 TWO=$2
   assert_file $ONE || return 1
   assert_file $TWO || return 1
   (
      sort -u $ONE
      sort -u $TWO
   ) | sort | uniq -d
}


function union ()
{
    FIELD=$1
    if [ -n "$FIELD" ]; then 
        ((FIELD++))
        echo "awk -v AF=$FIELD '!a[$AF]++'" >&2
        set -x
        awk -v AF=$FIELD '!a[$AF]++'
        set +x
    else
        echo "awk '!a[$0]++'" >&2
        set -x
        awk '!a[$0]++'
        set +x
    fi
}

function slow_union ()
{
    set1=$1
    set2=$2
    while read a; do while read b; do if [[ "$a" = "$b" ]]; then echo -e "IN\t$a"; fi; done < ${set1}; done < ${set2}
}

function intersection_help ()
{

    local fileA
    local fileB
    fileA=$1
    fileB=$2
    assert_file $fileA || fileA=file_A.txt
    assert_file $fileB || fileB=file_B.txt


cat <<'EOF'

INTERSECTION...
____________________

comm -12 <(sort $fileA) <(sort $fileB)
grep -xF -f $fileB $fileB
sort $fileA $fileB | uniq -d  #(Assuming each of file1 or file2 does not have repeated content)

AWK
--------------

# prints lines that are in both files; order of arguments is not important
awk 'NR==FNR{a[$0];next} $0 in a' $file1 $file2


INTERSECTION
____________________

$ comm -12 <(sort set1) <(sort set2)  # outputs insersect of set1 and set2

$ grep -xF -f set1 set2

$ sort set1 set2 | uniq -d

$ join <(sort -n A) <(sort -n B)

$ awk 'NR==FNR { a[$0]; next } $0 in a' set1 set2

COMPLIMENT
____________________

$ comm -23 <(sort set1) <(sort set2)
# outputs elements in set1 that are not in set2

$ grep -vxF -f set2 set1           # ditto

$ sort set2 set2 set1 | uniq -u    # ditto

$ awk 'NR==FNR { a[$0]; next } !($0 in a)' set2 set1

SET SYMMETRIC DIFFERENCE
____________________

$ comm -3 <(sort set1) <(sort set2) | sed 's/\t//g'
# outputs elements that are in set1 or in set2 but not both

$ comm -3 <(sort set1) <(sort set2) | tr -d '\t'

$ sort set1 set2 | uniq -u

$ cat <(grep -vxF -f set1 set2) <(grep -vxF -f set2 set1)

$ grep -vxF -f set1 set2; grep -vxF -f set2 set1


EOF

}

function remainders {
         #
         ## intersection of file1 and file2
         #comm -12 <(sort file1) <(sort file2)
         ## subtraction of file1 from file2
         #comm -13 <(sort file1) <(sort file2)
         #
         #
         #
         ## intersection of file1 and file2
         #grep -xF -f file1 file2
         ## subtraction of file1 from file2
         #grep -vxF -f file1 file2
         #
         #
         #
         ## intersection of file1 and file2
         #sort file1 file2 | uniq -d  (Assuming each of file1 or file2 does not have repeated content)
         ## file1-file2 (Subtraction)
         #sort file1 file2 file2 | uniq -u
         ## same way for file2 - file1, change last file2 to file1
         #sort file1 file2 file1 | uniq -u
         #
         #
         #
         #sort file1 file1 file2 | uniq -c |
         #awk '{ if ($1 == 2) { $1 = ""; print; } }'
         #
         #
         echo HI
}


##params: file1 file2 [file3 [file4 ... ] ]
##output: lines that are in common
#function intersection_of_files_lines(){
#    if [ "$#" -eq 1 ]; then
#        sort -u "$1"
#    elif [ "$#" -eq 2 ]; then
#        (sort -u "$1";sort -u "$b")|sort|uniq -d
#    elif [ "$#" -ge 3 ]; then
#        local a="$1"
#        local b="$2"
#        shift 2
#        # make intersection of $a and $b. Then call again for intersection with rest.
#        intersection_of_files_lines <( (sort -u "$a";sort -u "$b")|sort|uniq -d) "$@"
#    fi
#}



# vim:filetype=sh