File: rtsv.sh
   1 #!/bin/sh
   2 
   3 # The MIT License (MIT)
   4 #
   5 # Copyright © 2020-2025 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 case "$1" in
  33     -h|--h|-help|--help)
  34         awk '/^# +rtsv /, /^$/ { gsub(/^# ?/, ""); print }' "$0"
  35         exit 0
  36     ;;
  37 esac
  38 
  39 
  40 awk -F "\t" '
  41 function match_number(v) {
  42     return match(v, /^[+-]?[0-9]+(\.[0-9]+)?$/)
  43 }
  44 
  45 function match_dot_digits(v) {
  46     return match(v, /\.[0-9]+$/)
  47 }
  48 
  49 {
  50     gsub(/\r$/, "")
  51 
  52     for (i = 1; i <= NF; i++) {
  53         data[NR][i] = $i
  54 
  55         if (match_number($i)) {
  56             if (match_dot_digits($i)) {
  57                 dd = RLENGTH
  58                 if (dot_decs[i] < dd) dot_decs[i] = dd
  59                 iw = RSTART - 1
  60                 if (int_widths[i] < iw) int_widths[i] = iw
  61             } else {
  62                 w = length($i)
  63                 if (int_widths[i] < w) int_widths[i] = w
  64             }
  65 
  66             continue
  67         }
  68 
  69         w = length($i)
  70         if (widths[i] < w) widths[i] = w
  71     }
  72 }
  73 
  74 END {
  75     # fix column-widths using the number-padding info
  76     for (i = 1; i <= NF; i++) {
  77         w = int_widths[i] + dot_decs[i]
  78         if (widths[i] < w) widths[i] = w
  79     }
  80 
  81     for (i = 1; i <= NR; i++) {
  82         last = length(data[i])
  83 
  84         for (j = 1; j <= last; j++) {
  85             if (j > 1) printf "  " # put 2-space gaps between columns
  86 
  87             v = data[i][j]
  88 
  89             if (!match_number(v)) {
  90                 # avoid adding trailing spaces at the end of lines
  91                 printf "%*s", (j == last) ? 0 : -widths[j], v
  92                 continue
  93             }
  94 
  95             w = length(v)
  96             if (match_dot_digits(v)) {
  97                 dd = RLENGTH
  98                 iw = RSTART - 1
  99             } else {
 100                 dd = 0
 101                 iw = w
 102             }
 103 
 104             dpad = dot_decs[j] - dd
 105             ipad = int_widths[j] - iw
 106             if (ipad < 0) ipad = 0
 107             lpad = widths[j] - (ipad + w + dpad)
 108             if (lpad < 0) lpad = 0
 109 
 110             # avoid adding trailing spaces at the end of lines
 111             if (j == last) dpad = 0
 112 
 113             printf "%*s%*s%s%*s", lpad, "", ipad, "", v, dpad, ""
 114         }
 115 
 116         printf "\n"
 117     }
 118 }
 119 ' "$@"