diff options
Diffstat (limited to 'activesupport/lib/active_support/core_ext/string')
6 files changed, 83 insertions, 202 deletions
diff --git a/activesupport/lib/active_support/core_ext/string/access.rb b/activesupport/lib/active_support/core_ext/string/access.rb index c0d5cdf2d5..9b5266c58c 100644 --- a/activesupport/lib/active_support/core_ext/string/access.rb +++ b/activesupport/lib/active_support/core_ext/string/access.rb @@ -1,99 +1,35 @@ require "active_support/multibyte" class String - unless '1.9'.respond_to?(:force_encoding) - # Returns the character at the +position+ treating the string as an array (where 0 is the first character). - # - # Examples: - # "hello".at(0) # => "h" - # "hello".at(4) # => "o" - # "hello".at(10) # => ERROR if < 1.9, nil in 1.9 - def at(position) - mb_chars[position, 1].to_s - end - - # Returns the remaining of the string from the +position+ treating the string as an array (where 0 is the first character). - # - # Examples: - # "hello".from(0) # => "hello" - # "hello".from(2) # => "llo" - # "hello".from(10) # => "" if < 1.9, nil in 1.9 - def from(position) - mb_chars[position..-1].to_s - end - - # Returns the beginning of the string up to the +position+ treating the string as an array (where 0 is the first character). - # - # Examples: - # "hello".to(0) # => "h" - # "hello".to(2) # => "hel" - # "hello".to(10) # => "hello" - def to(position) - mb_chars[0..position].to_s - end - - # Returns the first character of the string or the first +limit+ characters. - # - # Examples: - # "hello".first # => "h" - # "hello".first(2) # => "he" - # "hello".first(10) # => "hello" - def first(limit = 1) - if limit == 0 - '' - elsif limit >= size - self - else - mb_chars[0...limit].to_s - end - end - - # Returns the last character of the string or the last +limit+ characters. - # - # Examples: - # "hello".last # => "o" - # "hello".last(2) # => "lo" - # "hello".last(10) # => "hello" - def last(limit = 1) - if limit == 0 - '' - elsif limit >= size - self - else - mb_chars[(-limit)..-1].to_s - end - end - else - def at(position) - self[position] - end + def at(position) + self[position] + end - def from(position) - self[position..-1] - end + def from(position) + self[position..-1] + end - def to(position) - self[0..position] - end + def to(position) + self[0..position] + end - def first(limit = 1) - if limit == 0 - '' - elsif limit >= size - self - else - to(limit - 1) - end + def first(limit = 1) + if limit == 0 + '' + elsif limit >= size + self + else + to(limit - 1) end + end - def last(limit = 1) - if limit == 0 - '' - elsif limit >= size - self - else - from(-limit) - end + def last(limit = 1) + if limit == 0 + '' + elsif limit >= size + self + else + from(-limit) end end end diff --git a/activesupport/lib/active_support/core_ext/string/conversions.rb b/activesupport/lib/active_support/core_ext/string/conversions.rb index 0f8933b658..541f969faa 100644 --- a/activesupport/lib/active_support/core_ext/string/conversions.rb +++ b/activesupport/lib/active_support/core_ext/string/conversions.rb @@ -1,37 +1,7 @@ -# 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..dc635ed6a5 100644 --- a/activesupport/lib/active_support/core_ext/string/encoding.rb +++ b/activesupport/lib/active_support/core_ext/string/encoding.rb @@ -1,11 +1,8 @@ +require 'active_support/deprecation' + class String - if defined?(Encoding) && "".respond_to?(:encode) - def encoding_aware? - true - end - else - def encoding_aware? - false - end + def encoding_aware? + ActiveSupport::Deprecation.warn 'String#encoding_aware? is deprecated', caller + true end -end
\ No newline at end of file +end diff --git a/activesupport/lib/active_support/core_ext/string/filters.rb b/activesupport/lib/active_support/core_ext/string/filters.rb index d478ee0ef6..1a34e88a87 100644 --- a/activesupport/lib/active_support/core_ext/string/filters.rb +++ b/activesupport/lib/active_support/core_ext/string/filters.rb @@ -36,14 +36,13 @@ class String # "And they found that many people were sleeping better.".truncate(25, :omission => "... (continued)") # # => "And they f... (continued)" def truncate(length, options = {}) - text = self.dup - options[:omission] ||= "..." + return self.dup unless self.length > length - length_with_room_for_omission = length - options[:omission].mb_chars.length - chars = text.mb_chars + options[:omission] ||= "..." + length_with_room_for_omission = length - options[:omission].length stop = options[:separator] ? - (chars.rindex(options[:separator].mb_chars, length_with_room_for_omission) || length_with_room_for_omission) : length_with_room_for_omission + (rindex(options[:separator], length_with_room_for_omission) || length_with_room_for_omission) : length_with_room_for_omission - (chars.length > length ? chars[0...stop] + options[:omission] : text).to_s + self[0...stop] + options[:omission] end end diff --git a/activesupport/lib/active_support/core_ext/string/multibyte.rb b/activesupport/lib/active_support/core_ext/string/multibyte.rb index aae1cfccf2..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? #:nodoc - 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 diff --git a/activesupport/lib/active_support/core_ext/string/output_safety.rb b/activesupport/lib/active_support/core_ext/string/output_safety.rb index 5d7f74bb65..73aa7dd89a 100644 --- a/activesupport/lib/active_support/core_ext/string/output_safety.rb +++ b/activesupport/lib/active_support/core_ext/string/output_safety.rb @@ -20,7 +20,7 @@ class ERB if s.html_safe? s else - s.gsub(/&/, "&").gsub(/\"/, """).gsub(/>/, ">").gsub(/</, "<").html_safe + s.encode(s.encoding, :xml => :attr)[1...-1].html_safe end end @@ -136,11 +136,6 @@ module ActiveSupport #:nodoc: coder.represent_scalar nil, to_str end - def to_yaml(*args) - return super() if defined?(YAML::ENGINE) && !YAML::ENGINE.syck? - to_str.to_yaml(*args) - end - UNSAFE_STRING_METHODS.each do |unsafe_method| if 'String'.respond_to?(unsafe_method) class_eval <<-EOT, __FILE__, __LINE__ + 1 |