diff options
Diffstat (limited to 'activesupport/lib/active_support/multibyte')
| -rw-r--r-- | activesupport/lib/active_support/multibyte/chars.rb | 165 | ||||
| -rw-r--r-- | activesupport/lib/active_support/multibyte/utils.rb | 55 |
2 files changed, 18 insertions, 202 deletions
diff --git a/activesupport/lib/active_support/multibyte/chars.rb b/activesupport/lib/active_support/multibyte/chars.rb index b78d92f599..dcc176e93f 100644 --- a/activesupport/lib/active_support/multibyte/chars.rb +++ b/activesupport/lib/active_support/multibyte/chars.rb @@ -38,16 +38,10 @@ module ActiveSupport #:nodoc: alias to_s wrapped_string alias to_str wrapped_string - if RUBY_VERSION >= "1.9" - # Creates a new Chars instance by wrapping _string_. - def initialize(string) - @wrapped_string = string - @wrapped_string.force_encoding(Encoding::UTF_8) unless @wrapped_string.frozen? - end - else - def initialize(string) #:nodoc: - @wrapped_string = string - end + # Creates a new Chars instance by wrapping _string_. + def initialize(string) + @wrapped_string = string + @wrapped_string.force_encoding(Encoding::UTF_8) unless @wrapped_string.frozen? end # Forward all undefined methods to the wrapped string. @@ -94,151 +88,8 @@ module ActiveSupport #:nodoc: @wrapped_string <=> other.to_s end - if RUBY_VERSION < "1.9" - # Returns +true+ if the Chars class can and should act as a proxy for the string _string_. Returns - # +false+ otherwise. - def self.wants?(string) - $KCODE == 'UTF8' && consumes?(string) - end - - # Returns a new Chars object containing the _other_ object concatenated to the string. - # - # Example: - # ('Café'.mb_chars + ' périferôl').to_s # => "Café périferôl" - def +(other) - chars(@wrapped_string + other) - end - - # Like <tt>String#=~</tt> only it returns the character offset (in codepoints) instead of the byte offset. - # - # Example: - # 'Café périferôl'.mb_chars =~ /ô/ # => 12 - def =~(other) - translate_offset(@wrapped_string =~ other) - end - - # Inserts the passed string at specified codepoint offsets. - # - # Example: - # 'Café'.mb_chars.insert(4, ' périferôl').to_s # => "Café périferôl" - def insert(offset, fragment) - unpacked = Unicode.u_unpack(@wrapped_string) - unless offset > unpacked.length - @wrapped_string.replace( - Unicode.u_unpack(@wrapped_string).insert(offset, *Unicode.u_unpack(fragment)).pack('U*') - ) - else - raise IndexError, "index #{offset} out of string" - end - self - end - - # Returns +true+ if contained string contains _other_. Returns +false+ otherwise. - # - # Example: - # 'Café'.mb_chars.include?('é') # => true - def include?(other) - # We have to redefine this method because Enumerable defines it. - @wrapped_string.include?(other) - end - - # Returns the position _needle_ in the string, counting in codepoints. Returns +nil+ if _needle_ isn't found. - # - # Example: - # 'Café périferôl'.mb_chars.index('ô') # => 12 - # 'Café périferôl'.mb_chars.index(/\w/u) # => 0 - def index(needle, offset=0) - wrapped_offset = first(offset).wrapped_string.length - index = @wrapped_string.index(needle, wrapped_offset) - index ? (Unicode.u_unpack(@wrapped_string.slice(0...index)).size) : nil - end - - # Returns the position _needle_ in the string, counting in - # codepoints, searching backward from _offset_ or the end of the - # string. Returns +nil+ if _needle_ isn't found. - # - # Example: - # 'Café périferôl'.mb_chars.rindex('é') # => 6 - # 'Café périferôl'.mb_chars.rindex(/\w/u) # => 13 - def rindex(needle, offset=nil) - offset ||= length - wrapped_offset = first(offset).wrapped_string.length - index = @wrapped_string.rindex(needle, wrapped_offset) - index ? (Unicode.u_unpack(@wrapped_string.slice(0...index)).size) : nil - end - - # Returns the number of codepoints in the string - def size - Unicode.u_unpack(@wrapped_string).size - end - alias_method :length, :size - - # Strips entire range of Unicode whitespace from the right of the string. - def rstrip - chars(@wrapped_string.gsub(Unicode::TRAILERS_PAT, '')) - end - - # Strips entire range of Unicode whitespace from the left of the string. - def lstrip - chars(@wrapped_string.gsub(Unicode::LEADERS_PAT, '')) - end - - # Strips entire range of Unicode whitespace from the right and left of the string. - def strip - rstrip.lstrip - end - - # Returns the codepoint of the first character in the string. - # - # Example: - # 'こんにちは'.mb_chars.ord # => 12371 - def ord - Unicode.u_unpack(@wrapped_string)[0] - end - - # Works just like <tt>String#rjust</tt>, only integer specifies characters instead of bytes. - # - # Example: - # - # "¾ cup".mb_chars.rjust(8).to_s - # # => " ¾ cup" - # - # "¾ cup".mb_chars.rjust(8, " ").to_s # Use non-breaking whitespace - # # => " ¾ cup" - def rjust(integer, padstr=' ') - justify(integer, :right, padstr) - end - - # Works just like <tt>String#ljust</tt>, only integer specifies characters instead of bytes. - # - # Example: - # - # "¾ cup".mb_chars.rjust(8).to_s - # # => "¾ cup " - # - # "¾ cup".mb_chars.rjust(8, " ").to_s # Use non-breaking whitespace - # # => "¾ cup " - def ljust(integer, padstr=' ') - justify(integer, :left, padstr) - end - - # Works just like <tt>String#center</tt>, only integer specifies characters instead of bytes. - # - # Example: - # - # "¾ cup".mb_chars.center(8).to_s - # # => " ¾ cup " - # - # "¾ cup".mb_chars.center(8, " ").to_s # Use non-breaking whitespace - # # => " ¾ cup " - def center(integer, padstr=' ') - justify(integer, :center, padstr) - end - - else - def =~(other) - @wrapped_string =~ other - end + def =~(other) + @wrapped_string =~ other end # Works just like <tt>String#split</tt>, with the exception that the items in the resulting list are Chars @@ -431,9 +282,7 @@ module ActiveSupport #:nodoc: return nil if byte_offset.nil? return 0 if @wrapped_string == '' - if @wrapped_string.respond_to?(:force_encoding) - @wrapped_string = @wrapped_string.dup.force_encoding(Encoding::ASCII_8BIT) - end + @wrapped_string = @wrapped_string.dup.force_encoding(Encoding::ASCII_8BIT) begin @wrapped_string[0...byte_offset].unpack('U*').length diff --git a/activesupport/lib/active_support/multibyte/utils.rb b/activesupport/lib/active_support/multibyte/utils.rb index 94b393cee2..bd6d4bad41 100644 --- a/activesupport/lib/active_support/multibyte/utils.rb +++ b/activesupport/lib/active_support/multibyte/utils.rb @@ -2,36 +2,14 @@ module ActiveSupport #:nodoc: module Multibyte #:nodoc: - if Kernel.const_defined?(:Encoding) - # Returns a regular expression that matches valid characters in the current encoding - def self.valid_character - VALID_CHARACTER[Encoding.default_external.to_s] - end - else - def self.valid_character - case $KCODE - when 'UTF8' - VALID_CHARACTER['UTF-8'] - when 'SJIS' - VALID_CHARACTER['Shift_JIS'] - end - end + # Returns a regular expression that matches valid characters in the current encoding + def self.valid_character + VALID_CHARACTER[Encoding.default_external.to_s] end - if 'string'.respond_to?(:valid_encoding?) - # Verifies the encoding of a string - def self.verify(string) - string.valid_encoding? - end - else - def self.verify(string) - if expression = valid_character - # Splits the string on character boundaries, which are determined based on $KCODE. - string.split(//).all? { |c| expression =~ c } - else - true - end - end + # Verifies the encoding of a string + def self.verify(string) + string.valid_encoding? end # Verifies the encoding of the string and raises an exception when it's not valid @@ -39,22 +17,11 @@ module ActiveSupport #:nodoc: raise EncodingError.new("Found characters with invalid encoding") unless verify(string) end - if 'string'.respond_to?(:force_encoding) - # Removes all invalid characters from the string. - # - # Note: this method is a no-op in Ruby 1.9 - def self.clean(string) - string - end - else - def self.clean(string) - if expression = valid_character - # Splits the string on character boundaries, which are determined based on $KCODE. - string.split(//).grep(expression).join - else - string - end - end + # Removes all invalid characters from the string. + # + # Note: this method is a no-op in Ruby 1.9 + def self.clean(string) + string end end end |