diff options
Diffstat (limited to 'activesupport/lib/active_support/core_ext/string')
3 files changed, 49 insertions, 100 deletions
diff --git a/activesupport/lib/active_support/core_ext/string/conversions.rb b/activesupport/lib/active_support/core_ext/string/conversions.rb index 0f8933b658..73eedf5982 100644 --- a/activesupport/lib/active_support/core_ext/string/conversions.rb +++ b/activesupport/lib/active_support/core_ext/string/conversions.rb @@ -1,37 +1,8 @@ -# encoding: utf-8 require 'date' require 'active_support/core_ext/time/publicize_conversion_methods' require 'active_support/core_ext/time/calculations' class String - # Returns the codepoint of the first character of the string, assuming a - # single-byte character encoding: - # - # "a".ord # => 97 - # "à".ord # => 224, in ISO-8859-1 - # - # This method is defined in Ruby 1.8 for Ruby 1.9 forward compatibility on - # these character encodings. - # - # <tt>ActiveSupport::Multibyte::Chars#ord</tt> is forward compatible with - # Ruby 1.9 on UTF8 strings: - # - # "a".mb_chars.ord # => 97 - # "à".mb_chars.ord # => 224, in UTF8 - # - # Note that the 224 is different in both examples. In ISO-8859-1 "à" is - # represented as a single byte, 224. In UTF8 it is represented with two - # bytes, namely 195 and 160, but its Unicode codepoint is 224. If we - # call +ord+ on the UTF8 string "à" the return value will be 195. That is - # not an error, because UTF8 is unsupported, the call itself would be - # bogus. - def ord - self[0] - end unless method_defined?(:ord) - - # +getbyte+ backport from Ruby 1.9 - alias_method :getbyte, :[] unless method_defined?(:getbyte) - # Form can be either :utc (default) or :local. def to_time(form = :utc) return nil if self.blank? diff --git a/activesupport/lib/active_support/core_ext/string/encoding.rb b/activesupport/lib/active_support/core_ext/string/encoding.rb index d4781bfe0c..236f72e933 100644 --- a/activesupport/lib/active_support/core_ext/string/encoding.rb +++ b/activesupport/lib/active_support/core_ext/string/encoding.rb @@ -1,11 +1,5 @@ class String - if defined?(Encoding) && "".respond_to?(:encode) - def encoding_aware? - true - end - else - def encoding_aware? - false - end + def encoding_aware? + true end end
\ No newline at end of file diff --git a/activesupport/lib/active_support/core_ext/string/multibyte.rb b/activesupport/lib/active_support/core_ext/string/multibyte.rb index 400db2ce39..4e7824ad74 100644 --- a/activesupport/lib/active_support/core_ext/string/multibyte.rb +++ b/activesupport/lib/active_support/core_ext/string/multibyte.rb @@ -2,71 +2,55 @@ require 'active_support/multibyte' class String - if RUBY_VERSION >= "1.9" - # == Multibyte proxy - # - # +mb_chars+ is a multibyte safe proxy for string methods. - # - # In Ruby 1.8 and older 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. If the proxy class doesn't respond to a certain method, it's forwarded to the encapsulated string. - # - # name = 'Claus Müller' - # name.reverse # => "rell??M sualC" - # name.length # => 13 - # - # name.mb_chars.reverse.to_s # => "rellüM sualC" - # name.mb_chars.length # => 12 - # - # In Ruby 1.9 and newer +mb_chars+ returns +self+ because String is (mostly) encoding aware. This means that - # it becomes easy to run one version of your code on multiple Ruby versions. - # - # == Method chaining - # - # 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.mb_chars.reverse.length # => 12 - # - # == Interoperability and configuration - # - # The Chars 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. For - # information about how to change the default Multibyte behavior see ActiveSupport::Multibyte. - def mb_chars - if ActiveSupport::Multibyte.proxy_class.consumes?(self) - ActiveSupport::Multibyte.proxy_class.new(self) - else - self - end - end - - def is_utf8? - case encoding - when Encoding::UTF_8 - valid_encoding? - when Encoding::ASCII_8BIT, Encoding::US_ASCII - dup.force_encoding(Encoding::UTF_8).valid_encoding? - else - false - end - end - else - def mb_chars - if ActiveSupport::Multibyte.proxy_class.wants?(self) - ActiveSupport::Multibyte.proxy_class.new(self) - else - self - end + # == Multibyte proxy + # + # +mb_chars+ is a multibyte safe proxy for string methods. + # + # In Ruby 1.8 and older 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. If the proxy class doesn't respond to a certain method, it's forwarded to the encapsulated string. + # + # name = 'Claus Müller' + # name.reverse # => "rell??M sualC" + # name.length # => 13 + # + # name.mb_chars.reverse.to_s # => "rellüM sualC" + # name.mb_chars.length # => 12 + # + # In Ruby 1.9 and newer +mb_chars+ returns +self+ because String is (mostly) encoding aware. This means that + # it becomes easy to run one version of your code on multiple Ruby versions. + # + # == Method chaining + # + # 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.mb_chars.reverse.length # => 12 + # + # == Interoperability and configuration + # + # The Chars 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. For + # information about how to change the default Multibyte behavior see ActiveSupport::Multibyte. + def mb_chars + if ActiveSupport::Multibyte.proxy_class.consumes?(self) + ActiveSupport::Multibyte.proxy_class.new(self) + else + self end + 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::Chars.consumes?(self) + def is_utf8? + case encoding + when Encoding::UTF_8 + valid_encoding? + when Encoding::ASCII_8BIT, Encoding::US_ASCII + dup.force_encoding(Encoding::UTF_8).valid_encoding? + else + false end end end |