File: squomp.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 # squomp [filepaths...]
  27 #
  28 #
  29 # SQUeeze and stOMP, by ignoring leading spaces, trailing spaces, even runs
  30 # of multiple spaces in the middle of lines, as well as trailing carriage
  31 # returns, while also turning runs of empty lines into single empty lines,
  32 # and ignoring leading/trailing empty lines, effectively also `squeezing`
  33 # lines vertically.
  34 #
  35 # This script also ensures no lines across inputs are accidentally joined,
  36 # since all lines it outputs end with line-feeds, even when the original files
  37 # don't.
  38 
  39 
  40 FNR == 1 {
  41     gsub(/^\xef\xbb\xbf/, "")
  42 }
  43 
  44 /^\r?$/ {
  45     empty = 1
  46     next
  47 }
  48 
  49 empty {
  50     if (n > 0) print ""
  51     empty = 0
  52 }
  53 
  54 {
  55     gsub(/^ +| *\r?$/, "")
  56     gsub(/ *\t */, "\t")
  57     gsub(/  +/, " ")
  58     print; fflush()
  59     n++
  60 }