Created
July 22, 2013 14:37
-
-
Save caugner/6054317 to your computer and use it in GitHub Desktop.
Ruby regular expression for German texts
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
#!/bin/ruby | |
# uppercase characters | |
uchar = 'A-ZÄÖÜÁÀÉÈ' | |
# lowercase characters | |
lchar = 'a-zäöüßáàéè' | |
# all characters | |
char = uchar + lchar | |
# whitespace characters | |
space_char = ' ' | |
# whitespace | |
space = '(?:[' + space_char + ']+)' | |
# hyphens | |
hyphen = '(?:' + space + '(?:--|-|–|—)' + space + ')' | |
# end of word | |
eow = '(?:' + space + '|,' + space + '|;' + space + '|\.' + space + '(?![A-Z]))' | |
# end of sentence | |
eos_char = '\\.\\?\\!…' | |
eos = '(?:[' + eos_char + ']+)' | |
# uppercase word | |
uword = '[' + uchar + '+]' | |
# lowercase word | |
lword = '[' + lchar + '+]' | |
# capital word | |
cword = '[' + uchar + '][' + char + ']*' | |
# any word | |
word = '[' + char + ']+' | |
# before word | |
before_word = '(?:' + eow + '|' + hyphen + ')' | |
# bracket text | |
in_bracket = '(?:' + word + '(?:' + before_word + word + ')*)' | |
bracket_round = '\\(' + in_bracket + '\\)' | |
bracket_square = '\\[' + in_bracket + '\\]' | |
bracket_curly = '\\{' + in_bracket + '\\}' | |
brackets = '(?:' + [bracket_round, bracket_square, bracket_curly].join('|') + ')' | |
# quoted text | |
in_quote = in_bracket + ",?" | |
quote_german = '„' + in_quote + '“' | |
quote_double = '"' + in_quote + '"' | |
quote_single = "'" + in_quote + "'" | |
quotes = '(?:' + [quote_german, quote_double,quote_single].join('|') + ')' | |
# sentence | |
sentence = cword + '(?:' + before_word + '(?:' + [word,brackets,quotes].join('|') + '))+' + eos |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment