Created
June 26, 2012 18:22
-
-
Save kols/2997719 to your computer and use it in GitHub Desktop.
Convert hex string to ruby string
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
#!/usr/bin/env ruby | |
def convert_hexstr(str, start=0, index=nil) | |
index ||= str.length | |
hexstr = str[start, index] | |
ar = [] | |
hexstr.scan(/\\x../).each do |s| | |
ar << s.gsub('\\', '0').to_i(16) | |
end | |
ar.empty? ? str : ar.pack('C*').force_encoding('utf-8') | |
end | |
def convert(str) | |
non_hexstr_start += 4 if | |
non_hexstr_start = str.index(/(\\x..)([^(\\x..)]+)(\\x..)/) | |
hexstr_start, hexstr_end = str.index(/\\x../), str.rindex(/\\x../) | |
if ! non_hexstr_start | |
if hexstr_start || hexstr_end | |
hexstr_length = hexstr_end + 3 - hexstr_start + 1 | |
str[hexstr_start, hexstr_length] = convert_hexstr(str) | |
end | |
str | |
else | |
hexstr_length = non_hexstr_start - hexstr_start | |
parsed_str_before_non_hexstr = convert_hexstr(str, hexstr_start, | |
hexstr_length) | |
str[hexstr_start, hexstr_length] = parsed_str_before_non_hexstr | |
convert(str) | |
end | |
end | |
def main | |
f_name = ARGV[0] | |
new_lines = Array.new | |
File.open(f_name) do |f| | |
f.each do |line| | |
new_lines << convert(line) | |
end | |
end | |
File.open(f_name, 'w') { |f| f.write new_lines.join } | |
end | |
def test | |
puts convert('\xE7\x94\xA8 Python \xE5\xBB\xBA\xE8\x8B\xB1\xE8\xAF\xAD\xE5\x8D\x95\xE8\xAF\x8D\xE8\xA1\xA8') | |
puts convert('\xE8\xAE\xA9\xE4\xBD\xA0\xE7\x9A\x84MSN\xE5\x89\x8D\xE9\x9D\xA2\xE5\xA4\x9A\xE4\xB8\xAAIAM\xE7\x9A\x84\xE6\x96\xB9\xE6\xB3\x95[\xE8\xBD\xAC]') | |
puts convert('Wordpress on dotcloud') | |
puts convert('Eng\xE7\x94\xA8lish') | |
end | |
#test | |
main |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment