Created
November 18, 2011 05:26
-
-
Save billdueber/1375681 to your computer and use it in GitHub Desktop.
Simple term parser
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
require 'parslet' | |
require 'pp' | |
class AdvParser < Parslet::Parser | |
rule(:space) { match['\\s\\t'].repeat(1) } # at least one space/tab | |
rule(:space?) { space.maybe } # zero or 1 things that match the 'space' rule | |
rule(:startexpr) { str('(') >> space? } # '(' followed by optional space | |
rule(:endexpr) { space? >> str(')') } | |
# A phrase is anything (but a double-quote) between double-quotes | |
rule(:phrase) { str('"') >> match['^"'].repeat(1).as(:phrase) >> str('"') } | |
rule(:opand) { str('AND') } | |
rule(:opor) { str('OR') } | |
rule(:opnot) { str('NOT') } | |
rule(:op) { opand | opor | opnot } | |
rule(:fname) { str('TI') | str('AU') | str('KY') } | |
rule(:field) { fname.as(:field) >> str(':') } | |
rule(:word) { match['^\\s\\t"()'].repeat(1) } | |
rule(:searchword) { field.absent? >> op.absent? >> word } | |
rule(:searchwords) { (space? >> searchword).repeat(1) } | |
rule(:term) { phrase | searchwords.as(:words) } | |
rule(:terms) { (space? >> term).repeat(1) } | |
rule(:fsearch) { field >> space? >> terms.as(:search) } | |
root(:fsearch) | |
end | |
pp AdvParser.new.parse('TI: hello there "Bill Dueber" how are you?') | |
# puts AdvParser.new.parse('TI: bill AND dueber') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment