Created
June 8, 2011 10:44
-
-
Save shiba-yu36/1014187 to your computer and use it in GitHub Desktop.
Encode::Guessで判定失敗したときに、全ての文字コードを試してみる例
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
use strict; | |
use warnings; | |
use utf8; | |
use Encode; | |
use Encode::Guess qw/ascii utf8 euc-jp shiftjis 7bit-jis/; | |
my $presence_list = [qw( | |
出席 出 しゅっせき | |
)]; | |
my $absence_list = [qw( | |
欠席 欠 けっせき | |
)]; | |
my $presence_re = join '|', map {quotemeta $_} @$presence_list; | |
my $absence_re = join '|', map {quotemeta $_} @$absence_list; | |
my $str = encode('shiftjis', '出席します'); | |
# guess decoder | |
my $decoders = []; | |
my $decoder = Encode::Guess->guess($str); | |
unless (ref($decoder)) { | |
my @names = split(' or ', $decoder); | |
for my $name (@names) { | |
my $d = find_encoding($name); | |
push @$decoders, $d if $d; | |
} | |
} | |
else { | |
push @$decoders, $decoder; | |
} | |
return if @$decoders == 0; | |
my $rollcall_type = 0; | |
for my $d (@$decoders) { | |
my $decoded_str = $d->decode($str); | |
$rollcall_type = 1 if $decoded_str =~ qr{$presence_re}; | |
$rollcall_type = 2 if $decoded_str =~ qr{$absence_re}; | |
} | |
warn $rollcall_type; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment