Sha256: 09cc4662253188a32d72b4a8b91f129891fb5f434f01fbc1d2c8efbe40daa00d
Contents?: true
Size: 1.73 KB
Versions: 6
Compression:
Stored size: 1.73 KB
Contents
# encoding: UTF-8
# Copyright 2012 Twitter, Inc
# http://www.apache.org/licenses/LICENSE-2.0
module TwitterCldr
module Shared
class UnicodeRegex
class << self
def compile(str, modifiers = "", symbol_table = nil)
new(
parser.parse(tokenizer.tokenize(str), {
:symbol_table => symbol_table
}), modifiers
)
end
# All unicode characters
def all_unicode
@all_unicode ||= TwitterCldr::Utils::RangeSet.new(
[0..0x10FFFF]
)
end
# A few <control> characters (i.e. 2..7) and public/private surrogates (i.e. 55296..57343).
# These don't play nicely with Ruby's regular expression engine, and I think we
# can safely disregard them.
def invalid_regexp_chars
@invalid_regexp_chars ||= TwitterCldr::Utils::RangeSet.new(
[2..7, 55296..57343]
)
end
def valid_regexp_chars
@valid_regexp_chars ||= all_unicode.subtract(invalid_regexp_chars)
end
private
def tokenizer
@tokenizer ||= TwitterCldr::Tokenizers::UnicodeRegexTokenizer.new
end
def parser
@parser ||= TwitterCldr::Parsers::UnicodeRegexParser.new
end
end
extend Forwardable
def_delegator :to_regexp, :match
def_delegator :to_regexp, :=~
attr_reader :elements, :modifiers
def initialize(elements, modifiers = nil)
@elements = elements
@modifiers = nil
end
def to_regexp
@regexp ||= Regexp.new(to_regexp_str, modifiers)
end
def to_regexp_str
@regexp_str ||= elements.map(&:to_regexp_str).join
end
end
end
end
Version data entries
6 entries across 6 versions & 2 rubygems