Created
May 22, 2012 07:55
-
-
Save addywaddy/2767432 to your computer and use it in GitHub Desktop.
RegexpHash: Hash subclass for building nested regular expressions
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
| class RegexpHash < Hash | |
| def add_word(word, hsh = nil) | |
| hsh ||= self | |
| return unless (word && word.length > 0) | |
| key = word.slice(0..0) | |
| hsh[key] ||= {} | |
| add_word(word.slice(1..-1), hsh[key]) | |
| end | |
| def flatten!(hsh = nil) | |
| hsh ||= self | |
| hsh.keys.each do |key| | |
| if hsh[key] && (hsh[key].keys.length == 1) | |
| child_key = hsh[key].keys[0] | |
| child_value = hsh[key][child_key] | |
| hsh[key + child_key] = child_value | |
| hsh.delete(key) | |
| flatten!(hsh) if child_value | |
| else | |
| flatten!(hsh[key]) if hsh[key] | |
| end | |
| end | |
| end | |
| def to_regexp | |
| flatten! | |
| pattern = self.inspect. | |
| gsub("{", "("). | |
| gsub("}", ")"). | |
| gsub(',', '|'). | |
| gsub('()', ''). | |
| gsub(/(\"|=\>|\s)/,'') | |
| Regexp.new(pattern) | |
| end | |
| end | |
| store = RegexpHash.new | |
| ["doggy", "dolly", "dilbert", "dogbert"].each do |word| | |
| store.add_word(word) | |
| end | |
| puts store.to_regexp | |
| # => (?-mix:(d(o(lly|g(bert|gy))|ilbert))) | |
| p "doggy dolly bert xxxdogbertxxx".scan(store.to_regexp) | |
| # => [["doggy", "oggy", "ggy", "gy"], ["dolly", "olly", "lly", nil], ["dogbert", "ogbert", "gbert", "bert"]] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment