File: rtsv.sh
   1 #!/bin/sh
   2 
   3 # The MIT License (MIT)
   4 #
   5 # Copyright © 2024 pacman64
   6 #
   7 # Permission is hereby granted, free of charge, to any person obtaining a copy
   8 # of this software and associated documentation files (the “Software”), to deal
   9 # in the Software without restriction, including without limitation the rights
  10 # to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
  11 # copies of the Software, and to permit persons to whom the Software is
  12 # furnished to do so, subject to the following conditions:
  13 #
  14 # The above copyright notice and this permission notice shall be included in
  15 # all copies or substantial portions of the Software.
  16 #
  17 # THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
  18 # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
  19 # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
  20 # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
  21 # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
  22 # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  23 # SOFTWARE.
  24 
  25 
  26 # rtsv [options...] [filenames...]
  27 #
  28 # Realign Tab Separated-Values, by padding with spaces to match each column's
  29 # widest value, right-aligning all numbers.
  30 
  31 
  32 # handle leading options
  33 case "$1" in
  34     -h|--h|-help|--help)
  35         awk '/^# +rtsv/, /^$/ { gsub(/^# ?/, ""); print }' "$0"
  36         exit 0
  37     ;;
  38 esac
  39 
  40 
  41 awk -F "\t" '
  42 function match_number(v) {
  43     return match(v, /^[+-]?[0-9]+(\.[0-9]+)?$/)
  44 }
  45 
  46 function match_dot_digits(v) {
  47     return match(v, /\.[0-9]+$/)
  48 }
  49 
  50 {
  51     gsub(/\r$/, "")
  52 
  53     for (i = 1; i <= NF; i++) {
  54         data[NR][i] = $i
  55 
  56         if (match_number($i)) {
  57             if (match_dot_digits($i)) {
  58                 dd = RLENGTH
  59                 if (dot_decs[i] < dd) dot_decs[i] = dd
  60                 iw = RSTART - 1
  61                 if (int_widths[i] < iw) int_widths[i] = iw
  62             } else {
  63                 w = length($i)
  64                 if (int_widths[i] < w) int_widths[i] = w
  65             }
  66 
  67             continue
  68         }
  69 
  70         w = length($i)
  71         if (widths[i] < w) widths[i] = w
  72     }
  73 }
  74 
  75 END {
  76     # fix column-widths using the number-padding info
  77     for (i = 1; i <= NF; i++) {
  78         w = int_widths[i] + dot_decs[i]
  79         if (widths[i] < w) widths[i] = w
  80     }
  81 
  82     for (i = 1; i <= NR; i++) {
  83         last = length(data[i])
  84 
  85         for (j = 1; j <= last; j++) {
  86             if (j > 1) printf "  " # put 2-space gaps between columns
  87 
  88             v = data[i][j]
  89 
  90             if (!match_number(v)) {
  91                 # avoid adding trailing spaces at the end of lines
  92                 printf "%*s", (j == last) ? 0 : -widths[j], v
  93                 continue
  94             }
  95 
  96             w = length(v)
  97             if (match_dot_digits(v)) {
  98                 dd = RLENGTH
  99                 iw = RSTART - 1
 100             } else {
 101                 dd = 0
 102                 iw = w
 103             }
 104 
 105             dpad = dot_decs[j] - dd
 106             ipad = int_widths[j] - iw
 107             if (ipad < 0) ipad = 0
 108             lpad = widths[j] - (ipad + w + dpad)
 109             if (lpad < 0) lpad = 0
 110 
 111             # avoid adding trailing spaces at the end of lines
 112             if (j == last) dpad = 0
 113 
 114             printf "%*s%*s%s%*s", lpad, "", ipad, "", v, dpad, ""
 115         }
 116 
 117         printf "\n"
 118     }
 119 }' "$@"