Shell Programming and Scripting

#!/usr/bin/env bash

# @(#) s1	Demonstrate adjust count of fields according to digit count.

# Uncomment to run script as external user.
# export PATH="/usr/local/bin:/usr/bin:/bin"
# Infrastructure details, environment, commands for forum posts. 
set +o nounset
pe() { for i;do printf "%s" "$i";done; printf "\n"; }
pl() { pe;pe "-----" ;pe "$*"; }
LC_ALL=C ; LANG=C ; export LC_ALL LANG
pe ; pe "Environment: LC_ALL = $LC_ALL, LANG = $LANG"
pe "(Versions displayed with local utility \"version\")"
c=$( ps | grep $$ | awk '{print $NF}' )
version >/dev/null 2>&1 && s=$(_eat $0 $1) || s=""
[ "$c" = "$s" ] && p="$s" || p="$c"
version >/dev/null 2>&1 && version "=o" $p specimen awk cmp diff
set -o nounset

FILE1=${1-data1}
shift
FILE2=${1-data2}

# Sample data files with head / tail if specimen fails.
pe
specimen $FILE1 $FILE2 \
|| { pe "(head/tail)"; head -n 5 $FILE1 $FILE2; pe " ||" ;\
     tail -n 5 $FILE1 $FILE2; }

pl " Results:"
awk -v f2="$FILE2" '
# first lines of pairs: print, skip
NR % 2 != 0 { print ; getline unused < f2 ; next }
            { digits = split($0,junk,"") - 1
              # print " Found", digits, " fields in line", NR
              getline < f2
              for (i = 1 ; i <= digits-1 ; i++) {
                printf("%s%s",$i,FS)
              }
              printf("%s",$digits)
              printf("\n")
            }
' $FILE1 |
tee t1

# Check results.

pl " Comparison with desired results:"
if cmp expected-output.txt t1
then
  pe " Passed -- files have same content."
else
  pe " Failed -- files differ -- details:"
  diff expected-output.txt t1
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 
GNU bash 3.2.39
specimen (local) 1.17
GNU Awk 3.1.5
cmp (GNU diffutils) 2.8.1
diff (GNU diffutils) 2.8.1

Whole: 5:0:5 of 6 lines in file "data1"
>1_19_130_F3
T01220131330230213311013000000110000
>1_23_69_F3
T01200211300200200010000001000000
>1_24_124_F3
T010203113002002111111200002010

Whole: 5:0:5 of 6 lines in file "data2"
>1_19_130_F3
24 18 9 18 23 4 11 4 5 9 5 8 15 20 4 4 7 4 7 4 4 4 4 4 4 4 4 7 4 4 4 4 8 4 9 
>1_23_69_F3
26 4 7 4 4 17 5 23 4 4 5 6 5 5 4 4 4 5 4 4 4 4 4 4 4 4 4 8 4 4 4 4 7 4 4 
>1_24_124_F3
32 27 24 18 29 22 23 17 18 19 24 19 15 29 12 9 16 6 26 4 4 4 4 4 4 4 4 7 4 4 4 12 10 4 5

-----
 Results:
>1_19_130_F3
24 18 9 18 23 4 11 4 5 9 5 8 15 20 4 4 7 4 7 4 4 4 4 4 4 4 4 7 4 4 4 4 8 4 9
>1_23_69_F3
26 4 7 4 4 17 5 23 4 4 5 6 5 5 4 4 4 5 4 4 4 4 4 4 4 4 4 8 4 4 4 4
>1_24_124_F3
32 27 24 18 29 22 23 17 18 19 24 19 15 29 12 9 16 6 26 4 4 4 4 4 4 4 4 7 4 4

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

  awk 'NR==FNR{T[NR]=length($1);next} 
      {if (FNR%2) {print $0} 
      else {{for (i=1;i<T[FNR];i++) printf "%s ",$i}; printf "\n"}
      }' file1 file2

awk '{
  getline line < "file1"
  gsub("[A-Za-z]","",line)
  n=length(line)
  $(n+1)="_"
  sub(" _.*","")
}1' file2

n=length(line)

$(n+1)="_"