Created
March 19, 2019 09:47
-
-
Save arton/c69654c0c702858e2aa6d78878ebf994 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
require 'origami' | |
pdf = Origami::PDF.read(ARGV[0], verbosity: Origami::Parser::VERBOSE_QUIET) | |
unless pdf.pages.first.Resources.Font.C2_0 | |
exit 1 | |
end | |
font_table = {} | |
pdf.pages.first.Resources.each_font do |name, font| | |
puts name if $DEBUG | |
utbl = font_table[name.to_s] = {} | |
font.ToUnicode.data.each_line do |line| | |
if line =~ /\A<([^>]+)>\s*<([^>]+)>(?:\s*<([^>]+)>)?/ | |
if $3 | |
puts line if $DEBUG | |
base = $3.hex | |
start = $1.hex | |
start.upto($2.hex) do |i| | |
utbl[sprintf('%04X', i)] = sprintf('%04X', base + (i - start)) | |
puts "#{sprintf('%04X', i)} => #{sprintf('%04X', base + (i - start))}" if $DEBUG | |
end | |
else | |
utbl[$1.upcase] = $2 | |
puts "#{$1} => #{$2}" if $DEBUG | |
end | |
end | |
end | |
end | |
puts font_table.keys.inspect if $DEBUG | |
utbl = font_table.values[0] | |
sentence = '' | |
line = pdf.pages.first.Contents.data | |
while /(?:\/(C2_\d+)\s[^<]+)?<([0-9A-F]+)>/m.match(line) | |
rest = $' | |
if $1 | |
puts $1 if $DEBUG | |
utbl = font_table[$1] | |
end | |
sentence << $2.split('').each_slice(4).map(&:join).map do |w| | |
x = utbl[w] | |
unless x | |
puts "#{w} not found" if $DEBUG | |
x = '0000' | |
end | |
x | |
end.map(&:hex).pack('U*') | |
line = rest | |
end | |
puts sentence.strip |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment