File: squeeze.awk
   1 #!/usr/bin/awk -f
   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 # squeeze [filepaths...]
  27 #
  28 #
  29 # Aggressively trim unneeded whitespace out of lines, also ignoring leading
  30 # UTF-8 BOMs, and trailing carriage-returns on all lines.
  31 #
  32 # This script also ensures no lines across inputs are accidentally joined,
  33 # since all lines it outputs end with line-feeds, even when the original files
  34 # don't.
  35 
  36 
  37 # ignore leading UTF-8 BOMs on the first line of each input, when present
  38 FNR == 1 { gsub(/^\xef\xbb\xbf/, "") }
  39 
  40 {
  41     # ignore leading spaces, trailing spaces, and trailing carriage-returns
  42     gsub(/^ +| *\r?$/, "")
  43     # ignore spaces around tabs
  44     gsub(/ *\t */, "\t")
  45     # turn all runs of multiple spaces into single spaces
  46     gsub(/  +/, " ")
  47 
  48     # flush all output lines immediately, in case input lines come in stutters
  49     print; fflush()
  50 }