File: wctabs.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 # wctabs [options...] [filepaths...]
  27 #
  28 # Run `wc` (word-count) with the arguments given, turning its output into
  29 # lines of tab-separated values: this removes output-parsing ambiguities,
  30 # in case of filepaths with spaces in them.
  31 #
  32 # You can run `wc --help` to see all its options, which you can also use
  33 # with this script.
  34 
  35 
  36 # handle help option(s)
  37 case "$1" in
  38     -h|--h|-help|--help)
  39         # show help message, extracting the info-comment at the start
  40         # of this file, and quit
  41         awk '/^# +wctabs/, /^$/ { gsub(/^# ?/, ""); print }' "$0"
  42         exit 0
  43     ;;
  44 esac
  45 
  46 # avoid testing all permutations of up to 5 single-char options
  47 stats=$(awk 'BEGIN {
  48     bytes = 0
  49     chars = 0
  50     words = 0
  51     lines = 0
  52     maxll = 0
  53 
  54     for (i = 1; i < ARGC; i++) {
  55         s = ARGV[i]
  56         delete ARGV[i]
  57 
  58         if (s !~ /^-/) {
  59             continue
  60         }
  61 
  62         switch (s) {
  63         case "--bytes":
  64             bytes = 1
  65             break
  66         case "--chars":
  67             chars = 1
  68             break
  69         case "--lines":
  70             lines = 1
  71             break
  72         case "--words":
  73             words = 1
  74             break
  75         case "--max-line-length":
  76             maxll = 1
  77             break
  78         default:
  79             if (s ~ /c/) { bytes = 1 }
  80             if (s ~ /m/) { chars = 1 }
  81             if (s ~ /w/) { words = 1 }
  82             if (s ~ /l/) { lines = 1 }
  83             if (s ~ /L/) { maxll = 1 }
  84             break
  85         }
  86     }
  87 
  88     stats = bytes + chars + words + lines + maxll
  89     # `wc` defaults to 3 stats when not explicitly given any option
  90     print (stats == 0) ? 3 : stats
  91 }' "$@")
  92 
  93 # ensure errors propagate correctly thru pipes
  94 # set -o pipefail
  95 
  96 case "${stats}" in
  97     1)
  98         wc "$@" | sed -E 's-^ +--; s- +-\t-1'
  99     ;;
 100     2)
 101         wc "$@" | sed -E 's-^ +--; s- +-\t-1; s- +-\t-1'
 102     ;;
 103     3)
 104         wc "$@" | sed -E 's-^ +--; s- +-\t-1; s- +-\t-1; s- +-\t-1'
 105     ;;
 106     4)
 107         wc "$@" | sed -E 's-^ +--; s- +-\t-1; s- +-\t-1; s- +-\t-1; s- +-\t-1'
 108     ;;
 109     5)
 110         wc "$@" | \
 111         sed -E 's-^ +--; s- +-\t-1; s- +-\t-1; s- +-\t-1; s- +-\t-1; s- +-\t-1'
 112     ;;
 113     *)
 114         printf "%s: only up to 5 options were expected" "$0" > /dev/stderr
 115         exit 1
 116     ;;
 117 esac