Shell Programming and Scripting

perl -lane'
  $c = 1;
  ($w = $F[$c]) =~ s/\d/z/g;
  ($d = $F[$c]) =~ s/\D/0/g;
  push @data, [$_, $w, $d];
  END {
    print join $/, map $_->[0], sort {
      $a->[1] cmp $b->[1] ||
        $a->[2] <=> $b->[2]
      } @data
    }' infile

NSU3051 NSU305011 5 6 G 6  
NSU3051 NSU305009 1 7 9 J
NSU3050 NSU3050120 4 I 8 9 
NSU3050 NSU30501210 9 J K L

NSU3050 NSU3050120 4 I 8 9 
NSU3050 NSU30501210 9 J K L
NSU3051 NSU305009 1 7 9 J
NSU3051 NSU305011 5 6 G 6

perl -lane'
  @w = @d = ();
  for (0..1) {
    ($w = $F[$_]) =~ s/\d/z/g;
    ($d = $F[$_]) =~ s/\D/0/g;
    push @w, $w;
    push @d, $d;
    }
  push @data, [$_, [@w], [@d]];
  END {
    print join $/, map $_->[0], sort {
      $a->[1][0] cmp $b->[1][0] ||
        $a->[2][0] <=> $b->[2][0] ||
          $a->[1][1] cmp $b->[1][1] ||
            $a->[2][1] <=> $b->[2][1]          
      } @data
    }' infile

sort -k 1 -k 2 File

NSU305B NSU305011 5 6 G 6  
NSU3051 NSU305009 1 7 9 J
NSU305C NSU3050120 4 I 8 9 
NSU3050 NSU30501210 9 J K L

NSU3050 NSU30501210 9 J K L
NSU3051 NSU305009 1 7 9 J
NSU305B NSU305011 5 6 G 6  
NSU305C NSU3050120 4 I 8 9

NSU305B NSU305011 5 6 G 6  
NSU305C NSU3050120 4 I 8 9 
NSU3050 NSU30501210 9 J K L
NSU3051 NSU305009 1 7 9 J

#!/usr/bin/env bash

# @(#) s1	Demonstrate hybrid sort, msort.
# http://freecode.com/projects/msort

# Section 1, setup, pre-solution, $Revision: 1.25 $".
# Infrastructure details, environment, debug commands for forum posts. 
# Uncomment export command to run script as external user.
# export PATH="/usr/local/bin:/usr/bin:/bin" HOME=""
set +o nounset
pe() { for _i;do printf "%s" "$_i";done; printf "\n"; }
pl() { pe;pe "-----" ;pe "$*"; }
edges() { local _f _n _l;: ${1?"edges: need file"}; _f=$1;_l=$(wc -l $_f);
  head -${_n:=3} $_f ; pe "--- ( $_l: lines total )" ; tail -$_n $_f ; }
db() { : ; }
db() { ( printf " db, ";for _i;do printf "%s" "$_i";done;printf "\n" ) >&2 ; }
C=$HOME/bin/context && [ -f $C ] && $C msort
set -o nounset
pe

FILE=${1-data1}
shift
E=${1-expected-output.txt}

# Display sample of data file, with head & tail as a last resort.
# NB, input, expected-output trimmed trailing blanks.
db " Section 1: display of input data."
pe " || start sample [ specimen first:middle:last ] $FILE"
specimen $FILE $E 2>/dev/null \
|| { pe "(head/tail)"; head -n 5 $FILE; pe " ||"; tail -n 5 $FILE; }
pe " || end"

# Section 2, solution.
pl " Results:"
db " Section 2: solution."
msort -q -j -l -n 1 -c h $FILE |
tee f1

# Section 3, post-solution, check results, clean-up, etc.
v1=$(wc -l <$E)
v2=$(wc -l < f1)
pl " Comparison of $v2 created lines with $v1 lines of desired results:"
db " Section 3: validate generated calculations with desired results."

pl " Comparison with desired results:"
if [ ! -f $E -o ! -s $E ]
then
  pe " Comparison file \"$E\" zero-length or missing."
  exit
fi
if cmp $E f1
then
  pe " Succeeded -- files have same content."
else
  pe " Failed -- files not identical -- detailed comparison follows."
  if diff -b $E f1
  then
    pe " Succeeded by ignoring whitespace differences."
  fi
fi

exit 0

% ./s1

Environment: LC_ALL = C, LANG = C
(Versions displayed with local utility "version")
OS, ker|rel, machine: Linux, 2.6.26-2-amd64, x86_64
Distribution        : Debian GNU/Linux 5.0.8 (lenny) 
bash GNU bash 3.2.39
msort 8.44

 db,  Section 1: display of input data.
 || start sample [ specimen first:middle:last ] data1
Whole: 5:0:5 of 4 lines in file "data1"
NSU30504 5 6 G 6
NSU3050B T 7 9 J
NSU30506 T I 8 9
NSU3050C H J K L

Whole: 5:0:5 of 4 lines in file "expected-output.txt"
NSU3050B T 7 9 J
NSU3050C H J K L
NSU30504 5 6 G 6
NSU30506 T I 8 9
 || end

-----
 Results:
 db,  Section 2: solution.
NSU3050B T 7 9 J
NSU3050C H J K L
NSU30504 5 6 G 6
NSU30506 T I 8 9

-----
 Comparison of 4 created lines with 4 lines of desired results:
 db,  Section 3: validate generated calculations with desired results.

-----
 Comparison with desired results:
 Succeeded -- files have same content.

% ./s2

Environment: LC_ALL = C, LANG = C
(Versions displayed with local utility "version")
OS, ker|rel, machine: Linux, 2.6.26-2-amd64, x86_64
Distribution        : Debian GNU/Linux 5.0.8 (lenny) 
bash GNU bash 3.2.39
msort 8.44

 db,  Section 1: display of input data.
 || start sample [ specimen first:middle:last ] data2
Whole: 5:0:5 of 4 lines in file "data2"
NSU3051 NSU305011 5 6 G 6
NSU3051 NSU305009 1 7 9 J
NSU3050 NSU3050120 4 I 8 9
NSU3050 NSU30501210 9 J K L

Whole: 5:0:5 of 4 lines in file "expected-2"
NSU3050 NSU3050120 4 I 8 9
NSU3050 NSU30501210 9 J K L
NSU3051 NSU305009 1 7 9 J
NSU3051 NSU305011 5 6 G 6
 || end

-----
 Results:
 db,  Section 2: solution.
NSU3050 NSU3050120 4 I 8 9
NSU3050 NSU30501210 9 J K L
NSU3051 NSU305009 1 7 9 J
NSU3051 NSU305011 5 6 G 6

-----
 Comparison of 4 created lines with 4 lines of desired results:
 db,  Section 3: validate generated calculations with desired results.

-----
 Comparison with desired results:
 Succeeded -- files have same content.

pandeeswaran@ubuntu:~$ sort -n file_a
NSU30504 5 6 G 6  
NSU30506 T I 8 9 
NSU3050B T 7 9 J
NSU3050C H J K L