diff options
Diffstat (limited to 'activesupport/lib/active_support/multibyte')
| -rw-r--r-- | activesupport/lib/active_support/multibyte/chars.rb | 27 | ||||
| -rw-r--r-- | activesupport/lib/active_support/multibyte/unicode.rb | 117 |
2 files changed, 57 insertions, 87 deletions
diff --git a/activesupport/lib/active_support/multibyte/chars.rb b/activesupport/lib/active_support/multibyte/chars.rb index 707cf200b5..938e4ebb72 100644 --- a/activesupport/lib/active_support/multibyte/chars.rb +++ b/activesupport/lib/active_support/multibyte/chars.rb @@ -1,7 +1,8 @@ -require 'active_support/json' -require 'active_support/core_ext/string/access' -require 'active_support/core_ext/string/behavior' -require 'active_support/core_ext/module/delegation' +require "active_support/json" +require "active_support/core_ext/string/access" +require "active_support/core_ext/string/behavior" +require "active_support/core_ext/module/delegation" +require "active_support/core_ext/regexp" module ActiveSupport #:nodoc: module Multibyte #:nodoc: @@ -45,7 +46,7 @@ module ActiveSupport #:nodoc: alias to_s wrapped_string alias to_str wrapped_string - delegate :<=>, :=~, :acts_like_string?, :to => :wrapped_string + delegate :<=>, :=~, :acts_like_string?, to: :wrapped_string # Creates a new Chars instance by wrapping _string_. def initialize(string) @@ -56,7 +57,7 @@ module ActiveSupport #:nodoc: # Forward all undefined methods to the wrapped string. def method_missing(method, *args, &block) result = @wrapped_string.__send__(method, *args, &block) - if method.to_s =~ /!$/ + if /!$/.match?(method) self if result else result.kind_of?(String) ? chars(result) : result @@ -105,7 +106,7 @@ module ActiveSupport #:nodoc: # # 'Café'.mb_chars.reverse.to_s # => 'éfaC' def reverse - chars(Unicode.unpack_graphemes(@wrapped_string).reverse.flatten.pack('U*')) + chars(Unicode.unpack_graphemes(@wrapped_string).reverse.flatten.pack("U*")) end # Limits the byte size of the string to a number of bytes without breaking @@ -142,7 +143,7 @@ module ActiveSupport #:nodoc: # # 'über'.mb_chars.capitalize.to_s # => "Über" def capitalize - (slice(0) || chars('')).upcase + (slice(1..-1) || chars('')).downcase + (slice(0) || chars("")).upcase + (slice(1..-1) || chars("")).downcase end # Capitalizes the first letter of every word, when possible. @@ -150,7 +151,7 @@ module ActiveSupport #:nodoc: # "ÉL QUE SE ENTERÓ".mb_chars.titleize # => "Él Que Se Enteró" # "日本語".mb_chars.titleize # => "日本語" def titleize - chars(downcase.to_s.gsub(/\b('?\S)/u) { Unicode.upcase($1)}) + chars(downcase.to_s.gsub(/\b('?\S)/u) { Unicode.upcase($1) }) end alias_method :titlecase, :titleize @@ -170,7 +171,7 @@ module ActiveSupport #:nodoc: # 'é'.length # => 2 # 'é'.mb_chars.decompose.to_s.length # => 3 def decompose - chars(Unicode.decompose(:canonical, @wrapped_string.codepoints.to_a).pack('U*')) + chars(Unicode.decompose(:canonical, @wrapped_string.codepoints.to_a).pack("U*")) end # Performs composition on all the characters. @@ -178,7 +179,7 @@ module ActiveSupport #:nodoc: # 'é'.length # => 3 # 'é'.mb_chars.compose.to_s.length # => 2 def compose - chars(Unicode.compose(@wrapped_string.codepoints.to_a).pack('U*')) + chars(Unicode.compose(@wrapped_string.codepoints.to_a).pack("U*")) end # Returns the number of grapheme clusters in the string. @@ -213,10 +214,10 @@ module ActiveSupport #:nodoc: def translate_offset(byte_offset) #:nodoc: return nil if byte_offset.nil? - return 0 if @wrapped_string == '' + return 0 if @wrapped_string == "" begin - @wrapped_string.byteslice(0...byte_offset).unpack('U*').length + @wrapped_string.byteslice(0...byte_offset).unpack("U*").length rescue ArgumentError byte_offset -= 1 retry diff --git a/activesupport/lib/active_support/multibyte/unicode.rb b/activesupport/lib/active_support/multibyte/unicode.rb index 72b20fff06..217919ccb8 100644 --- a/activesupport/lib/active_support/multibyte/unicode.rb +++ b/activesupport/lib/active_support/multibyte/unicode.rb @@ -1,7 +1,6 @@ module ActiveSupport module Multibyte module Unicode - extend self # A list of all available normalization forms. @@ -10,7 +9,7 @@ module ActiveSupport NORMALIZATION_FORMS = [:c, :kc, :d, :kd] # The Unicode version that is supported by the implementation - UNICODE_VERSION = '8.0.0' + UNICODE_VERSION = "8.0.0" # The default normalization used for operations that require # normalization. It can be set to any of the normalizations @@ -31,36 +30,6 @@ module ActiveSupport HANGUL_NCOUNT = HANGUL_VCOUNT * HANGUL_TCOUNT HANGUL_SCOUNT = 11172 HANGUL_SLAST = HANGUL_SBASE + HANGUL_SCOUNT - HANGUL_JAMO_FIRST = 0x1100 - HANGUL_JAMO_LAST = 0x11FF - - # All the unicode whitespace - WHITESPACE = [ - (0x0009..0x000D).to_a, # White_Space # Cc [5] <control-0009>..<control-000D> - 0x0020, # White_Space # Zs SPACE - 0x0085, # White_Space # Cc <control-0085> - 0x00A0, # White_Space # Zs NO-BREAK SPACE - 0x1680, # White_Space # Zs OGHAM SPACE MARK - (0x2000..0x200A).to_a, # White_Space # Zs [11] EN QUAD..HAIR SPACE - 0x2028, # White_Space # Zl LINE SEPARATOR - 0x2029, # White_Space # Zp PARAGRAPH SEPARATOR - 0x202F, # White_Space # Zs NARROW NO-BREAK SPACE - 0x205F, # White_Space # Zs MEDIUM MATHEMATICAL SPACE - 0x3000, # White_Space # Zs IDEOGRAPHIC SPACE - ].flatten.freeze - - # BOM (byte order mark) can also be seen as whitespace, it's a - # non-rendering character used to distinguish between little and big - # endian. This is not an issue in utf-8, so it must be ignored. - LEADERS_AND_TRAILERS = WHITESPACE + [65279] # ZERO-WIDTH NO-BREAK SPACE aka BOM - - # Returns a regular expression pattern that matches the passed Unicode - # codepoints. - def self.codepoints_to_pattern(array_of_codepoints) #:nodoc: - array_of_codepoints.collect{ |e| [e].pack 'U*'.freeze }.join('|'.freeze) - end - TRAILERS_PAT = /(#{codepoints_to_pattern(LEADERS_AND_TRAILERS)})+\Z/u - LEADERS_PAT = /\A(#{codepoints_to_pattern(LEADERS_AND_TRAILERS)})+/u # Detect whether the codepoint is in a certain character class. Returns # +true+ when it's in the specified character class and +false+ otherwise. @@ -90,25 +59,25 @@ module ActiveSupport should_break = # GB3. CR X LF - if previous == database.boundary[:cr] and current == database.boundary[:lf] + if previous == database.boundary[:cr] && current == database.boundary[:lf] false # GB4. (Control|CR|LF) ÷ - elsif previous and in_char_class?(previous, [:control,:cr,:lf]) + elsif previous && in_char_class?(previous, [:control,:cr,:lf]) true # GB5. ÷ (Control|CR|LF) elsif in_char_class?(current, [:control,:cr,:lf]) true # GB6. L X (L|V|LV|LVT) - elsif database.boundary[:l] === previous and in_char_class?(current, [:l,:v,:lv,:lvt]) + elsif database.boundary[:l] === previous && in_char_class?(current, [:l,:v,:lv,:lvt]) false # GB7. (LV|V) X (V|T) - elsif in_char_class?(previous, [:lv,:v]) and in_char_class?(current, [:v,:t]) + elsif in_char_class?(previous, [:lv,:v]) && in_char_class?(current, [:v,:t]) false # GB8. (LVT|T) X (T) - elsif in_char_class?(previous, [:lvt,:t]) and database.boundary[:t] === current + elsif in_char_class?(previous, [:lvt,:t]) && database.boundary[:t] === current false # GB8a. Regional_Indicator X Regional_Indicator - elsif database.boundary[:regional_indicator] === previous and database.boundary[:regional_indicator] === current + elsif database.boundary[:regional_indicator] === previous && database.boundary[:regional_indicator] === current false # GB9. X Extend elsif database.boundary[:extend] === current @@ -136,7 +105,7 @@ module ActiveSupport # # Unicode.pack_graphemes(Unicode.unpack_graphemes('क्षि')) # => 'क्षि' def pack_graphemes(unpacked) - unpacked.flatten.pack('U*') + unpacked.flatten.pack("U*") end # Re-order codepoints so the string becomes canonical. @@ -159,7 +128,7 @@ module ActiveSupport def decompose(type, codepoints) codepoints.inject([]) do |decomposed, cp| # if it's a hangul syllable starter character - if HANGUL_SBASE <= cp and cp < HANGUL_SLAST + if HANGUL_SBASE <= cp && cp < HANGUL_SLAST sindex = cp - HANGUL_SBASE ncp = [] # new codepoints ncp << HANGUL_LBASE + sindex / HANGUL_NCOUNT @@ -168,7 +137,7 @@ module ActiveSupport ncp << (HANGUL_TBASE + tindex) unless tindex == 0 decomposed.concat ncp # if the codepoint is decomposable in with the current decomposition type - elsif (ncp = database.codepoints[cp].decomp_mapping) and (!database.codepoints[cp].decomp_type || type == :compatibility) + elsif (ncp = database.codepoints[cp].decomp_mapping) && (!database.codepoints[cp].decomp_type || type == :compatibility) decomposed.concat decompose(type, ncp.dup) else decomposed << cp @@ -187,11 +156,11 @@ module ActiveSupport pos += 1 lindex = starter_char - HANGUL_LBASE # -- Hangul - if 0 <= lindex and lindex < HANGUL_LCOUNT + if 0 <= lindex && lindex < HANGUL_LCOUNT vindex = codepoints[starter_pos+1] - HANGUL_VBASE rescue vindex = -1 - if 0 <= vindex and vindex < HANGUL_VCOUNT + if 0 <= vindex && vindex < HANGUL_VCOUNT tindex = codepoints[starter_pos+2] - HANGUL_TBASE rescue tindex = -1 - if 0 <= tindex and tindex < HANGUL_TCOUNT + if 0 <= tindex && tindex < HANGUL_TCOUNT j = starter_pos + 2 eoa -= 2 else @@ -259,7 +228,7 @@ module ActiveSupport reader = Encoding::Converter.new(Encoding::UTF_8, Encoding::UTF_16LE) source = string.dup - out = ''.force_encoding(Encoding::UTF_16LE) + out = "".force_encoding(Encoding::UTF_16LE) loop do reader.primitive_convert(source, out) @@ -287,17 +256,17 @@ module ActiveSupport # See http://www.unicode.org/reports/tr15, Table 1 codepoints = string.codepoints.to_a case form - when :d - reorder_characters(decompose(:canonical, codepoints)) - when :c - compose(reorder_characters(decompose(:canonical, codepoints))) - when :kd - reorder_characters(decompose(:compatibility, codepoints)) - when :kc - compose(reorder_characters(decompose(:compatibility, codepoints))) + when :d + reorder_characters(decompose(:canonical, codepoints)) + when :c + compose(reorder_characters(decompose(:canonical, codepoints))) + when :kd + reorder_characters(decompose(:compatibility, codepoints)) + when :kc + compose(reorder_characters(decompose(:compatibility, codepoints))) else - raise ArgumentError, "#{form} is not a valid normalization variant", caller - end.pack('U*'.freeze) + raise ArgumentError, "#{form} is not a valid normalization variant", caller + end.pack("U*".freeze) end def downcase(string) @@ -356,7 +325,7 @@ module ActiveSupport # UnicodeDatabase. def load begin - @codepoints, @composition_exclusion, @composition_map, @boundary, @cp1252 = File.open(self.class.filename, 'rb') { |f| Marshal.load f.read } + @codepoints, @composition_exclusion, @composition_map, @boundary, @cp1252 = File.open(self.class.filename, "rb") { |f| Marshal.load f.read } rescue => e raise IOError.new("Couldn't load the Unicode tables for UTF8Handler (#{e.message}), ActiveSupport::Multibyte is unusable") end @@ -378,7 +347,7 @@ module ActiveSupport # Returns the directory in which the data files are stored. def self.dirname - File.dirname(__FILE__) + '/../values/' + File.dirname(__FILE__) + "/../values/" end # Returns the filename for the data file for this version. @@ -389,25 +358,25 @@ module ActiveSupport private - def apply_mapping(string, mapping) #:nodoc: - database.codepoints - string.each_codepoint.map do |codepoint| - cp = database.codepoints[codepoint] - if cp and (ncp = cp.send(mapping)) and ncp > 0 - ncp - else - codepoint - end - end.pack('U*') - end + def apply_mapping(string, mapping) #:nodoc: + database.codepoints + string.each_codepoint.map do |codepoint| + cp = database.codepoints[codepoint] + if cp && (ncp = cp.send(mapping)) && ncp > 0 + ncp + else + codepoint + end + end.pack("U*") + end - def recode_windows1252_chars(string) - string.encode(Encoding::UTF_8, Encoding::Windows_1252, invalid: :replace, undef: :replace) - end + def recode_windows1252_chars(string) + string.encode(Encoding::UTF_8, Encoding::Windows_1252, invalid: :replace, undef: :replace) + end - def database - @database ||= UnicodeDatabase.new - end + def database + @database ||= UnicodeDatabase.new + end end end end |