Last active
August 29, 2015 14:20
-
-
Save cygx/c1d06377387178097c58 to your computer and use it in GitHub Desktop.
This file contains hidden or 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
# https://raw.githubusercontent.com/kevina/wordlist/master/pos/part-of-speech.txt | |
my $input = slurp('part-of-speech.txt'); | |
my %words; | |
sub bench(&code) { | |
%words = (); | |
my $start = now; | |
code; | |
my $end = now; | |
say "{ +%words } words parsed in { ($end - $start).round(0.1) }s"; | |
} | |
bench { | |
use nqp; | |
my str $s = $input; | |
my int $pos = 0; | |
my int $chars = nqp::chars($s); | |
while $pos < $chars { | |
my int $tab = nqp::index($s, "\t", $pos); | |
my int $nl = nqp::index($s, "\n", $tab); | |
%words{nqp::p6box_s(nqp::substr($s, $pos, $tab - $pos))} = | |
nqp::p6box_s(nqp::substr($s, $tab + 1, $nl - $tab - 1)); | |
$pos = $nl + 1; | |
} | |
} | |
bench { | |
for $input.lines(:eager) { | |
my $tab = .index("\t"); | |
%words{.substr(0, $tab)} = .substr($tab + 1); | |
} | |
} | |
bench { | |
for $input.lines(:eager) { | |
my ($k, $v) = .split("\t", 2); | |
%words{$k} = $v; | |
} | |
} |
This file contains hidden or 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 Time::HiRes qw(time); | |
use File::Slurp; | |
my $input = read_file('part-of-speech.txt'); | |
my %words; | |
my $start = time; | |
for ($input =~ /\N+/g) { | |
my ($k, $v) = split(/\t/, $_, 2); | |
$words{$k} = $v; | |
} | |
my $end = time; | |
printf "%u words parsed in %.2fs\n", scalar keys(%words), $end - $start; |
This file contains hidden or 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 nqp; | |
my %words; | |
given slurp("part-of-speech.txt") { | |
my int $pos = 0; | |
my int $chars = nqp::chars($_); | |
while $pos < $chars { | |
my int $tab = nqp::index($_, "\t", $pos); | |
my int $nl = nqp::index($_, "\n", $tab); | |
%words{nqp::p6box_s(nqp::substr($_, $pos, $tab - $pos))} = | |
nqp::p6box_s(nqp::substr($_, $tab + 1, $nl - $tab - 1)); | |
$pos = $nl + 1; | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment