Last active
November 22, 2016 17:11
-
-
Save niczero/0c95bacd9e85203f7de2c4f41b6c63df to your computer and use it in GitHub Desktop.
Translating utf8 byte strings
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
# Steal bits, but don't take at face value | |
# Originally stolen from https://gist.github.com/nicwolff/1484073 | |
sub _decode { | |
my ($self, $in) = @_; | |
my $log = $self->app->log; | |
my $out = ''; | |
use bytes; # Who said C was dead? | |
my ($i, $length) = (0, length $in); | |
while ($i < $length) { | |
my $b = substr $in, $i, 1; | |
if (ord $b < 0x80) { | |
# 7-bit ascii | |
$out .= $b; | |
} | |
elsif (ord($b) >> 5 == 6 and $i + 1 < $length - 1) { | |
# Possible 2-byte char | |
my $next = substr $in, $i + 1, 1; | |
if (ord($next) >> 6 == 2) { | |
$out .= $b . $next; | |
++$i; | |
} | |
else { | |
$out .= decode 'cp1252', $b; | |
} | |
} | |
elsif (ord($b) >> 4 == 14 and $i + 2 < $length - 1) { | |
# Possible 3-byte char | |
my $next = substr $in, $i + 1, 1; | |
my $nextagain = substr $in, $i + 2, 1; | |
if (ord($next) >> 6 == 2 and ord($nextagain) >> 6 == 2) { | |
$out .= $b . $next . $nextagain; | |
$i += 2; | |
} | |
else { | |
$out .= decode 'cp1252', $b; | |
} | |
} | |
else { | |
$out .= decode 'cp1252', $b; | |
} | |
++$i; | |
} | |
return $out; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment