bits.awk

bits.awk

#!/usr/bin/gawk -f

# https://www.gnu.org/software/gawk/manual/gawk.html#Nondecimal_002dnumbers
#
# https://www.gnu.org/software/gawk/manual/gawk.html#Ordinal-Functions
#
# TODO:
#   - truncate static bytes
#   - padding

function _ord_init(    low, high, i, t)
{
  low = sprintf("%c", 7) # BEL is ascii 7
  if (low == "\a") {    # regular ascii
    low = 0
    high = 127
  } else if (sprintf("%c", 128 + 7) == "\a") {
  # ascii, mark parity
    low = 128
    high = 255
  } else {        # ebcdic(!)
    low = 0
    high = 255
  }

  for (i = low; i <= high; i++) {
    t = sprintf("%c", i)
    _ord_[t] = i
  }
} function ord(str,    c) {
  # only first character is of interest
  c = substr(str, 1, 1)
  return _ord_[c]
} function chr(c) {
  # force c to be numeric by adding 0
  return sprintf("%c", c + 0)
} function byte_to_bits(byte) {
  # this function creates an array bits[] from 1 byte
  bitpos=0
  for(n=128; n>=1; n=n/2) {
    #if(byte & n)
    bits[bitpos++] = and(byte, n) ? "1" : "0"
      #printf "%d: %d\n", n, and(byte, n) ? "1" : "0"
    #else
      #printf "%d: 0\n", n
    #total+=n
  }
  #for(bitpos=0; bitpos<=7; bitpos++)
    #printf "%d", bits[bitpos]

  #printf "\ntotal: %d\n", total

  #printf "\n"
} BEGIN {
  _ord_init()
  longest=0
  printf "processing tokens"
} {
  # start string from bit 0
  bit_count=0
  # store the length of the longest string
  if(length($0)>longest)
    longest = length($0)
  # read the tokens into an array
  tokens[NR-1]=$0
  # process every byte in the line...
  for(j=1; j<=length($0); j++) {
    char = substr($0, j, 1)
    #printf "%d: %d: %c\n", NR, j, char
    byte_to_bits(ord(char))
    for(i=0; i<=7; i++) {
      #printf "%d", bits[i]

      # i want an array of bit values, so we can truncate unused bits...
      if(bits[i]==0)
	zero_bits_by_position[bit_count + i]++
    }
    bit_count+=8
    #printf "\n"
  }
  if(NR%1000==0)
    printf "."
  #printf "total bits: %d\n\n", bit_count

  #printf "DEBUG: %d\n", length(zero_bits_by_position)
  #printf "DEBUG: NR=%d\n", NR

  # print current zero bit count
  #for(i=0; i<length(zero_bits_by_position); i++) {
  #  printf "%d", zero_bits_by_position[i]
  #  # if it matches NR... that bit was never used.
  #  if(i%8==7)
  #    printf " "
  #}
  #printf "\n"

}END{
  printf "\n"
  x = 0
  y = NR
  #printf "DEBUG: %d\n", bits_by_position[longest+1]
  # count the real x (with zero bits truncated)
  for(i=0; i<longest*8; i++){
    #printf "%d: %d\n", i, zero_bits_by_position[i]
    if(zero_bits_by_position[i]!=y)
      x++
  }

  # some info
  printf "x: %d (truncating %d bits)\n", x, longest*8-x
  printf "y: %d\n", y
  printf "creating image"

  # create PBM header
  #
  # https://en.wikipedia.org/wiki/Portable_anymap#PBM_example
  printf "P1\n"			>"bits.pbm"
  printf "%d %d\n", x, y	>"bits.pbm"

  # for every token
  for(i=0; i<y; i++){
    bit_count=0
    # for every char
    for(j=1; j<=length($0); j++) {
      # get one char (byte) from the string
      char = substr(tokens[i], j, 1)
      byte_to_bits(ord(char))
      # for every bit
      for(k=0; k<=7; k++) {
	# truncate unused bits
	if(zero_bits_by_position[bit_count + k]!=y){
	  printf "%d ", bits[k] >"bits.pbm"
	}
      }
      bit_count+=8
    }
    printf "\n" >"bits.pbm"
    if(i%1000==0)
      printf "."
  }
  printf "\n"
}