blob: eab1c1d24630c1326e503a9e73a092ee363b94d1 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
|
module ActiveSupport #:nodoc:
module CoreExtensions #:nodoc:
module String #:nodoc:
if RUBY_VERSION < '1.9'
# Define methods for handling unicode data.
module Unicode
# +chars+ is a Unicode safe proxy for string methods. It creates and returns an instance of the
# ActiveSupport::Multibyte::Chars class which encapsulates the original string. A Unicode safe version of all
# the String methods are defined on this proxy class. Undefined methods are forwarded to String, so all of the
# string overrides can also be called through the +chars+ proxy.
#
# name = 'Claus Müller'
# name.reverse #=> "rell??M sualC"
# name.length #=> 13
#
# name.chars.reverse.to_s #=> "rellüM sualC"
# name.chars.length #=> 12
#
#
# All the methods on the chars proxy which normally return a string will return a Chars object. This allows
# method chaining on the result of any of these methods.
#
# name.chars.reverse.length #=> 12
#
# The Char object tries to be as interchangeable with String objects as possible: sorting and comparing between
# String and Char work like expected. The bang! methods change the internal string representation in the Chars
# object. Interoperability problems can be resolved easily with a +to_s+ call.
#
# For more information about the methods defined on the Chars proxy see ActiveSupport::Multibyte::Chars and
# ActiveSupport::Multibyte::Handlers::UTF8Handler
def chars
ActiveSupport::Multibyte::Chars.new(self)
end
# Returns true if the string has UTF-8 semantics (a String used for purely byte resources is unlikely to have
# them), returns false otherwise.
def is_utf8?
ActiveSupport::Multibyte::Handlers::UTF8Handler.consumes?(self)
end
end
else
module Unicode #:nodoc:
def chars
self
end
def is_utf8?
case encoding
when Encoding::UTF_8
valid_encoding?
when Encoding::ASCII_8BIT
dup.force_encoding('UTF-8').valid_encoding?
else
false
end
end
end
end
end
end
end
|
