Sha256: 966b99b91c64f04c88891294edd6c544ea23023e9a9d662362dcd11191a2650b
Contents?: true
Size: 1.6 KB
Versions: 19
Compression:
Stored size: 1.6 KB
Contents
# encoding: UTF-8
# Copyright 2012 Twitter, Inc
# http://www.apache.org/licenses/LICENSE-2.0
module TwitterCldr
module Tokenizers
class UnicodeRegexTokenizer
extend Forwardable
def_delegator :tokenizer, :insert_before
def tokenize(pattern)
tokenizer.tokenize(pattern)
end
private
def tokenizer
@tokenizer ||= begin
recognizers = [
# The variable name can contain letters and digits, but must start with a letter.
TokenRecognizer.new(:variable, /\$\w[\w\d]*/),
TokenRecognizer.new(:character_set, /\[:\w+:\]|\\p\{[\w=]+\}/), # [:Lu:] or \p{Lu} or \p{Sentence_Break=CF}
TokenRecognizer.new(:negated_character_set, /\[:\^\w+:\]|\\P\{[\w=]+\}/), #[:^Lu:] or \P{Lu}
TokenRecognizer.new(:unicode_char, /\\u\{?[a-fA-F0-9]{1,6}\}?/),
TokenRecognizer.new(:multichar_string, /\{\w+\}/u),
TokenRecognizer.new(:escaped_character, /\\./),
TokenRecognizer.new(:negate, /\^/),
TokenRecognizer.new(:ampersand, /&/),
TokenRecognizer.new(:pipe, /\|/),
TokenRecognizer.new(:dash, /-/),
# stuff that shouldn't be converted to codepoints
TokenRecognizer.new(:special_char, /\{\d,?\d?\}|[$?:{}()*+\.,\/\\]/),
TokenRecognizer.new(:open_bracket, /\[/),
TokenRecognizer.new(:close_bracket, /\]/),
TokenRecognizer.new(:string, //) do |val|
val == " " ? val : val.strip
end
]
Tokenizer.new(recognizers)
end
end
end
end
end
Version data entries
19 entries across 19 versions & 2 rubygems