Last active
January 1, 2016 08:29
-
-
Save MattOates/8118699 to your computer and use it in GitHub Desktop.
Newick grammar in Perl6... the quoted and unquoted tokens fail if you replace unquoted with <[A..Z]>* it works for the example newick string :/
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/env perl6 | |
use v6; | |
grammar BioInfo::Parser::Tree::Newick { | |
rule TOP { | |
<tree>+ | |
} | |
rule tree { | |
<node> ";" | |
} | |
rule node { | |
<children> <label>? <distance>? | <children>? <label> <distance>? | |
} | |
rule children { | |
"(" <node> ("," <node>)* ")" | |
} | |
rule label { | |
<quoted> | <unquoted> | |
} | |
rule distance { | |
":" <number> | |
} | |
token quoted { "'" ( <-[']> | "''" )* "'" } | |
#token unquoted { <[A..Z]>* } | |
token unquoted { <-[\[\]()':\s]>* } | |
token number { <[+-]>?\d+"."?\d*<[eE]>?\d* } | |
} | |
my $quoted = "(a,('Darwin''s Bulldog (Huxley)',c):-1.92e19)'The ''Root''':5;"; | |
my $unquoted = "(A:0.1,B:0.2,(C:0.3,D:0.4):0.5);"; | |
say "Quoted Newick"; | |
say BioInfo::Parser::Tree::Newick.parse($quoted); | |
say "Unquoted Newick"; | |
say BioInfo::Parser::Tree::Newick.parse($unquoted); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment