Last active
December 27, 2019 21:28
-
-
Save dakkar/e34d213e43fa7d2fa1b252784dfb36a1 to your computer and use it in GitHub Desktop.
be faster by doing more work?
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
| feeding a 18kb email message, I get: | |
| $ perl6 /tmp/p.p6 medium-sized-email-message.txt | |
| slurping 0.00634555 | |
| matching 1.1612016 | |
| parsing 0.02143336 |
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 v6.d; | |
| sub time(&block,:$name = 'took') { | |
| my $start = now; | |
| LEAVE { say "$name { now - $start }" } | |
| return block(); | |
| } | |
| my @separators = ( | |
| "\x0a\x0d\x0a\x0d", | |
| "\x0d\x0a\x0d\x0a", | |
| "\x0a\x0a", | |
| "\x0d\x0d", | |
| ); | |
| my grammar Message { | |
| regex TOP { | |
| <headers> | |
| <separator> | |
| <body> | |
| } | |
| token newline { [\x0d\x0a] | [\x0a\x0d] | \x0a | \x0d } | |
| token separator { @separators } | |
| token body { .* } | |
| regex headers { | |
| <header>+ % <newline> | |
| } | |
| regex header { | |
| <name> \: \h* <value> | |
| || <junk> | |
| } | |
| token name { | |
| <-[:\s]>+ | |
| } | |
| regex value { | |
| <line>+ % [<newline> \h+] | |
| } | |
| token line { \N* } | |
| token junk { \N+ } | |
| } | |
| my Str $string = time :name('slurping'), { slurp(@*ARGS[0].IO,:enc<utf8-c8>) }; | |
| my $done = time :name('matching'), { $string ~~ /@separators/ }; | |
| my $match = time :name('parsing'), { Message.parse($string) }; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment