Created
June 27, 2011 10:48
-
-
Save motemen/1048663 to your computer and use it in GitHub Desktop.
highlight text by mecab segmentation
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 opts; | |
use Text::MeCab; | |
use Encode; | |
use Encode::Locale; | |
use Term::ANSIColor; | |
my @COLORS = qw( | |
yellow red blue green cyan magenta | |
); | |
opts my $legend => 'Bool'; | |
Encode::Locale::decode_argv; | |
binmode(STDIN, ':encoding(console_in)'); | |
binmode(STDOUT, ':encoding(console_out)'); | |
my @patterns = @ARGV; | |
if ($legend) { | |
for (0 .. $#patterns) { | |
print color $COLORS[ $_ % @COLORS ]; | |
print $patterns[$_]; | |
print color 'reset'; | |
print ' '; | |
} | |
print "\n"; | |
} | |
my $mecab = Text::MeCab->new; | |
my $enc = Text::MeCab::ENCODING; | |
while (my $line = <STDIN>) { | |
chomp $line; | |
for (my $node = $mecab->parse(encode($enc => $line)); $node && defined $node->surface; $node = $node->next) { | |
my $feature = decode($enc => $node->feature); | |
my $color; | |
for (0 .. $#patterns) { | |
if ($feature =~ $patterns[$_]) { | |
$color = $COLORS[ $_ % @COLORS ]; | |
last; | |
} | |
} | |
print color $color if $color; | |
print decode($enc => $node->surface); | |
print color 'reset' if $color; | |
} | |
print "\n"; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment