Last active
February 18, 2017 08:05
-
-
Save Logioniz/f2b059ff0cf0274af058fb5082f75518 to your computer and use it in GitHub Desktop.
Web server wrapper for mystem
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/perl | |
use Mojo::Base -strict; | |
use Mojo::JSON::MaybeXS; | |
use Mojo::JSON 'decode_json'; | |
use Mojolicious::Lite; | |
use IPC::Open3; | |
use Mojo::IOLoop; | |
my $mystem_path = '/usr/local/bin/mystem'; | |
my $write = new IO::Handle; | |
my $read = new IO::Handle; | |
my $pid = open3($write, $read, undef, $mystem_path, '-gi', '-d', '-c', '--format', 'json'); | |
sub analyze { | |
my $text = shift; | |
utf8::decode($text); | |
my $result = []; | |
for my $line (split /\r?\n/, $text) { | |
my $message = "$line\n"; | |
utf8::encode($message); | |
syswrite $write, $message, length($message); | |
my ($ans, $res) = ('', undef); | |
while (1) { | |
my $len = sysread $read, my $data, 65535; | |
$ans .= $data; | |
$res = eval { decode_json $ans }; | |
last unless $@; | |
} | |
push @$result, @$res; | |
} | |
return $result; | |
} | |
sub get_lemma { | |
my $o = shift; | |
return $o->{analysis}[0]{lex} if $o->{analysis}; | |
return $o->{text} if $o->{text}; | |
return undef; | |
} | |
sub lemmatize { | |
my $text = shift; | |
my $infos = analyze($text); | |
my @lemmas = grep { $_ } map { get_lemma($_) } @$infos; | |
return @lemmas; | |
} | |
sub lemmatize_to_string { | |
return join '', lemmatize(shift); | |
} | |
any '/' => sub { | |
my $c = shift; | |
my $text = $c->param('text'); | |
$c->render(json => analyze($text)); | |
}; | |
any '/lemmatize' => sub { | |
my $c = shift; | |
my $text = $c->param('text'); | |
$c->render(text => lemmatize_to_string($text)); | |
}; | |
Mojo::IOLoop->singleton->on(finish => sub { | |
my $loop = shift; | |
$write->close; | |
waitpid $pid, 0; | |
}); | |
app->start; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment