Sha256: 8f7699250ef757e2c2b88b63994d5bfacdf0f61e638e623b8121c9da5a307697
Contents?: true
Size: 1.18 KB
Versions: 11
Compression:
Stored size: 1.18 KB
Contents
# encoding: UTF-8
# Copyright 2012 Twitter, Inc
# http://www.apache.org/licenses/LICENSE-2.0
module TwitterCldr
module Parsers
class UnicodeRegexParser
# unicode_char, escaped_char, string, multichar_string
# Can exist inside and outside of character classes
class UnicodeString < Component
attr_reader :codepoints
def initialize(codepoints)
@codepoints = codepoints
end
def to_set
# If the number of codepoints is greater than 1, treat them as a
# group (eg. multichar string). This is definitely a hack in that
# it means there has to be special logic in RangeSet that deals
# with data types that aren't true integer ranges. I can't think
# of any other way to support multichar strings :(
if codepoints.size > 1
TwitterCldr::Utils::RangeSet.new([codepoints..codepoints])
else
TwitterCldr::Utils::RangeSet.new([codepoints.first..codepoints.first])
end
end
def to_regexp_str
cps = codepoints.is_a?(Array) ? codepoints : [codepoints]
array_to_regex(cps)
end
end
end
end
end
Version data entries
11 entries across 11 versions & 2 rubygems