Created
December 28, 2010 18:38
-
-
Save njh/757525 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
| def extract_pronunciation(string) | |
| result = string.dup | |
| regexes = { | |
| %r[\(IPA: ["\[/].*?["\]/]\) ] => '', | |
| %r[\(pronounced ["\[/].*?["\]/]\) ] => '', | |
| # for when pronounciation is mixed in with birthdate, e.g. (pronounced /bəˈɹɛlɪs/; born December 7, 1979) | |
| %r[pronounced ["\[/].*?["\]/]\; ] => '', | |
| } | |
| for regex in regexes.keys | |
| if result =~ regex | |
| result.sub!(regex, regexes[regex]) | |
| break | |
| end | |
| end | |
| return result | |
| end | |
| def test_extract_pronunciation | |
| examples = { | |
| 'U2 (IPA: /ˌjuːˈtuː/) are a rock band from Dublin,' => 'U2 are a rock band from Dublin,', | |
| 'Albert Camus (IPA: [albɛʁ kamy]) is ' => 'Albert Camus is ', | |
| 'Anton Corbijn (pronounced [kɔrˈbɛin]) (born May 20, 1955) ' => 'Anton Corbijn (born May 20, 1955) ', | |
| 'Breed 77 (pronounced "Breed Seven-Seven") is a band whose' => 'Breed 77 is a band whose', | |
| 'Sara Beth Bareilles (pronounced /bəˈɹɛlɪs/; born December 7, 1979) is an American' => 'Sara Beth Bareilles (born December 7, 1979) is an American' | |
| } | |
| examples.keys.each do |string| | |
| assert_equal examples[string], @tapp.send(:extract_pronunciation, string) | |
| end | |
| end | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment