From c1d00d6dbf2837be2ac690d1462f2577e93d617a Mon Sep 17 00:00:00 2001 From: Fumiaki MATSUSHIMA Date: Sun, 9 Oct 2016 17:40:07 +0900 Subject: Remove `AS::Multibyte`'s unicode table --- activesupport/bin/generate_tables | 141 ---------- .../lib/active_support/multibyte/unicode.rb | 287 ++------------------- .../lib/active_support/values/unicode_tables.dat | Bin 1116857 -> 0 bytes .../test/multibyte_unicode_database_test.rb | 26 -- 4 files changed, 15 insertions(+), 439 deletions(-) delete mode 100755 activesupport/bin/generate_tables delete mode 100644 activesupport/lib/active_support/values/unicode_tables.dat delete mode 100644 activesupport/test/multibyte_unicode_database_test.rb diff --git a/activesupport/bin/generate_tables b/activesupport/bin/generate_tables deleted file mode 100755 index 18199b2171..0000000000 --- a/activesupport/bin/generate_tables +++ /dev/null @@ -1,141 +0,0 @@ -#!/usr/bin/env ruby -# frozen_string_literal: true - -begin - $:.unshift(File.expand_path("../lib", __dir__)) - require "active_support" -rescue IOError -end - -require "open-uri" -require "tmpdir" -require "fileutils" - -module ActiveSupport - module Multibyte - module Unicode - class UnicodeDatabase - def load; end - end - - class DatabaseGenerator - BASE_URI = "http://www.unicode.org/Public/#{UNICODE_VERSION}/ucd/" - SOURCES = { - codepoints: BASE_URI + "UnicodeData.txt", - composition_exclusion: BASE_URI + "CompositionExclusions.txt", - grapheme_break_property: BASE_URI + "auxiliary/GraphemeBreakProperty.txt", - cp1252: "http://unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1252.TXT" - } - - def initialize - @ucd = Unicode::UnicodeDatabase.new - end - - def parse_codepoints(line) - codepoint = Codepoint.new - raise "Could not parse input." unless line =~ /^ - ([0-9A-F]+); # code - ([^;]+); # name - ([A-Z]+); # general category - ([0-9]+); # canonical combining class - ([A-Z]+); # bidi class - (<([A-Z]*)>)? # decomposition type - ((\ ?[0-9A-F]+)*); # decomposition mapping - ([0-9]*); # decimal digit - ([0-9]*); # digit - ([^;]*); # numeric - ([YN]*); # bidi mirrored - ([^;]*); # unicode 1.0 name - ([^;]*); # iso comment - ([0-9A-F]*); # simple uppercase mapping - ([0-9A-F]*); # simple lowercase mapping - ([0-9A-F]*)$/ix # simple titlecase mapping - codepoint.code = $1.hex - codepoint.combining_class = Integer($4) - codepoint.decomp_type = $7 - codepoint.decomp_mapping = ($8 == "") ? nil : $8.split.collect(&:hex) - codepoint.uppercase_mapping = ($16 == "") ? 0 : $16.hex - codepoint.lowercase_mapping = ($17 == "") ? 0 : $17.hex - @ucd.codepoints[codepoint.code] = codepoint - end - - def parse_grapheme_break_property(line) - if line =~ /^([0-9A-F.]+)\s*;\s*([\w]+)\s*#/ - type = $2.downcase.intern - @ucd.boundary[type] ||= [] - if $1.include? ".." - parts = $1.split ".." - @ucd.boundary[type] << (parts[0].hex..parts[1].hex) - else - @ucd.boundary[type] << $1.hex - end - end - end - - def parse_composition_exclusion(line) - if line =~ /^([0-9A-F]+)/i - @ucd.composition_exclusion << $1.hex - end - end - - def parse_cp1252(line) - if line =~ /^([0-9A-Fx]+)\s([0-9A-Fx]+)/i - @ucd.cp1252[$1.hex] = $2.hex - end - end - - def create_composition_map - @ucd.codepoints.each do |_, cp| - if !cp.nil? && cp.combining_class == 0 && cp.decomp_type.nil? && !cp.decomp_mapping.nil? && cp.decomp_mapping.length == 2 && @ucd.codepoints[cp.decomp_mapping[0]].combining_class == 0 && !@ucd.composition_exclusion.include?(cp.code) - @ucd.composition_map[cp.decomp_mapping[0]] ||= {} - @ucd.composition_map[cp.decomp_mapping[0]][cp.decomp_mapping[1]] = cp.code - end - end - end - - def normalize_boundary_map - @ucd.boundary.each do |k, v| - if [:lf, :cr].include? k - @ucd.boundary[k] = v[0] - end - end - end - - def parse - SOURCES.each do |type, url| - filename = File.join(Dir.tmpdir, UNICODE_VERSION, "#{url.split('/').last}") - unless File.exist?(filename) - $stderr.puts "Downloading #{url.split('/').last}" - FileUtils.mkdir_p(File.dirname(filename)) - File.open(filename, "wb") do |target| - open(url) do |source| - source.each_line { |line| target.write line } - end - end - end - File.open(filename) do |file| - file.each_line { |line| send "parse_#{type}".intern, line } - end - end - create_composition_map - normalize_boundary_map - end - - def dump_to(filename) - File.open(filename, "wb") do |f| - f.write Marshal.dump([@ucd.codepoints, @ucd.composition_exclusion, @ucd.composition_map, @ucd.boundary, @ucd.cp1252]) - end - end - end - end - end -end - -if __FILE__ == $0 - filename = ActiveSupport::Multibyte::Unicode::UnicodeDatabase.filename - generator = ActiveSupport::Multibyte::Unicode::DatabaseGenerator.new - generator.parse - print "Writing to: #{filename}" - generator.dump_to filename - puts " (#{File.size(filename)} bytes)" -end diff --git a/activesupport/lib/active_support/multibyte/unicode.rb b/activesupport/lib/active_support/multibyte/unicode.rb index f923061fae..4f0e1165ef 100644 --- a/activesupport/lib/active_support/multibyte/unicode.rb +++ b/activesupport/lib/active_support/multibyte/unicode.rb @@ -11,7 +11,7 @@ module ActiveSupport NORMALIZATION_FORMS = [:c, :kc, :d, :kd] # The Unicode version that is supported by the implementation - UNICODE_VERSION = "9.0.0" + UNICODE_VERSION = RbConfig::CONFIG["UNICODE_VERSION"] # The default normalization used for operations that require # normalization. It can be set to any of the normalizations @@ -21,96 +21,13 @@ module ActiveSupport attr_accessor :default_normalization_form @default_normalization_form = :kc - # Hangul character boundaries and properties - HANGUL_SBASE = 0xAC00 - HANGUL_LBASE = 0x1100 - HANGUL_VBASE = 0x1161 - HANGUL_TBASE = 0x11A7 - HANGUL_LCOUNT = 19 - HANGUL_VCOUNT = 21 - HANGUL_TCOUNT = 28 - HANGUL_NCOUNT = HANGUL_VCOUNT * HANGUL_TCOUNT - HANGUL_SCOUNT = 11172 - HANGUL_SLAST = HANGUL_SBASE + HANGUL_SCOUNT - - # Detect whether the codepoint is in a certain character class. Returns - # +true+ when it's in the specified character class and +false+ otherwise. - # Valid character classes are: :cr, :lf, :l, - # :v, :lv, :lvt and :t. - # - # Primarily used by the grapheme cluster support. - def in_char_class?(codepoint, classes) - classes.detect { |c| database.boundary[c] === codepoint } ? true : false - end - # Unpack the string at grapheme boundaries. Returns a list of character # lists. # # Unicode.unpack_graphemes('क्षि') # => [[2325, 2381], [2359], [2367]] # Unicode.unpack_graphemes('Café') # => [[67], [97], [102], [233]] def unpack_graphemes(string) - codepoints = string.codepoints.to_a - unpacked = [] - pos = 0 - marker = 0 - eoc = codepoints.length - while (pos < eoc) - pos += 1 - previous = codepoints[pos - 1] - current = codepoints[pos] - - # See http://unicode.org/reports/tr29/#Grapheme_Cluster_Boundary_Rules - should_break = - if pos == eoc - true - # GB3. CR X LF - elsif previous == database.boundary[:cr] && current == database.boundary[:lf] - false - # GB4. (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 && in_char_class?(current, [:l, :v, :lv, :lvt]) - false - # GB7. (LV|V) X (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]) && database.boundary[:t] === current - false - # GB9. X (Extend | ZWJ) - elsif in_char_class?(current, [:extend, :zwj]) - false - # GB9a. X SpacingMark - elsif database.boundary[:spacingmark] === current - false - # GB9b. Prepend X - elsif database.boundary[:prepend] === previous - false - # GB10. (E_Base | EBG) Extend* X E_Modifier - elsif (marker...pos).any? { |i| in_char_class?(codepoints[i], [:e_base, :e_base_gaz]) && codepoints[i + 1...pos].all? { |c| database.boundary[:extend] === c } } && database.boundary[:e_modifier] === current - false - # GB11. ZWJ X (Glue_After_Zwj | EBG) - elsif database.boundary[:zwj] === previous && in_char_class?(current, [:glue_after_zwj, :e_base_gaz]) - false - # GB12. ^ (RI RI)* RI X RI - # GB13. [^RI] (RI RI)* RI X RI - elsif codepoints[marker..pos].all? { |c| database.boundary[:regional_indicator] === c } && codepoints[marker..pos].count { |c| database.boundary[:regional_indicator] === c }.even? - false - # GB999. Any ÷ Any - else - true - end - - if should_break - unpacked << codepoints[marker..pos - 1] - marker = pos - end - end - unpacked + string.scan(/\X/).map(&:codepoints) end # Reverse operation of unpack_graphemes. @@ -120,100 +37,18 @@ module ActiveSupport unpacked.flatten.pack("U*") end - # Re-order codepoints so the string becomes canonical. - def reorder_characters(codepoints) - length = codepoints.length - 1 - pos = 0 - while pos < length do - cp1, cp2 = database.codepoints[codepoints[pos]], database.codepoints[codepoints[pos + 1]] - if (cp1.combining_class > cp2.combining_class) && (cp2.combining_class > 0) - codepoints[pos..pos + 1] = cp2.code, cp1.code - pos += (pos > 0 ? -1 : 1) - else - pos += 1 - end - end - codepoints - end - # Decompose composed characters to the decomposed form. def decompose(type, codepoints) - codepoints.inject([]) do |decomposed, cp| - # if it's a hangul syllable starter character - if HANGUL_SBASE <= cp && cp < HANGUL_SLAST - sindex = cp - HANGUL_SBASE - ncp = [] # new codepoints - ncp << HANGUL_LBASE + sindex / HANGUL_NCOUNT - ncp << HANGUL_VBASE + (sindex % HANGUL_NCOUNT) / HANGUL_TCOUNT - tindex = sindex % HANGUL_TCOUNT - 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) && (!database.codepoints[cp].decomp_type || type == :compatibility) - decomposed.concat decompose(type, ncp.dup) - else - decomposed << cp - end + if type == :compatibility + codepoints.pack("U*").unicode_normalize(:nfkd).codepoints + else + codepoints.pack("U*").unicode_normalize(:nfd).codepoints end end # Compose decomposed characters to the composed form. def compose(codepoints) - pos = 0 - eoa = codepoints.length - 1 - starter_pos = 0 - starter_char = codepoints[0] - previous_combining_class = -1 - while pos < eoa - pos += 1 - lindex = starter_char - HANGUL_LBASE - # -- Hangul - if 0 <= lindex && lindex < HANGUL_LCOUNT - vindex = codepoints[starter_pos + 1] - HANGUL_VBASE rescue vindex = -1 - if 0 <= vindex && vindex < HANGUL_VCOUNT - tindex = codepoints[starter_pos + 2] - HANGUL_TBASE rescue tindex = -1 - if 0 <= tindex && tindex < HANGUL_TCOUNT - j = starter_pos + 2 - eoa -= 2 - else - tindex = 0 - j = starter_pos + 1 - eoa -= 1 - end - codepoints[starter_pos..j] = (lindex * HANGUL_VCOUNT + vindex) * HANGUL_TCOUNT + tindex + HANGUL_SBASE - end - starter_pos += 1 - starter_char = codepoints[starter_pos] - # -- Other characters - else - current_char = codepoints[pos] - current = database.codepoints[current_char] - if current.combining_class > previous_combining_class - if ref = database.composition_map[starter_char] - composition = ref[current_char] - else - composition = nil - end - unless composition.nil? - codepoints[starter_pos] = composition - starter_char = composition - codepoints.delete_at pos - eoa -= 1 - pos -= 1 - previous_combining_class = -1 - else - previous_combining_class = current.combining_class - end - else - previous_combining_class = current.combining_class - end - if current.combining_class == 0 - starter_pos = pos - starter_char = codepoints[pos] - end - end - end - codepoints + codepoints.pack("U*").unicode_normalize(:nfc).codepoints end # Rubinius' String#scrub, however, doesn't support ASCII-incompatible chars. @@ -266,129 +101,37 @@ module ActiveSupport def normalize(string, form = nil) form ||= @default_normalization_form # See http://www.unicode.org/reports/tr15, Table 1 - codepoints = string.codepoints.to_a case form when :d - reorder_characters(decompose(:canonical, codepoints)) + string.unicode_normalize(:nfd) when :c - compose(reorder_characters(decompose(:canonical, codepoints))) + string.unicode_normalize(:nfc) when :kd - reorder_characters(decompose(:compatibility, codepoints)) + string.unicode_normalize(:nfkd) when :kc - compose(reorder_characters(decompose(:compatibility, codepoints))) + string.unicode_normalize(:nfkc) else raise ArgumentError, "#{form} is not a valid normalization variant", caller - end.pack("U*".freeze) + end end def downcase(string) - apply_mapping string, :lowercase_mapping + string.downcase end def upcase(string) - apply_mapping string, :uppercase_mapping + string.upcase end def swapcase(string) - apply_mapping string, :swapcase_mapping - end - - # Holds data about a codepoint in the Unicode database. - class Codepoint - attr_accessor :code, :combining_class, :decomp_type, :decomp_mapping, :uppercase_mapping, :lowercase_mapping - - # Initializing Codepoint object with default values - def initialize - @combining_class = 0 - @uppercase_mapping = 0 - @lowercase_mapping = 0 - end - - def swapcase_mapping - uppercase_mapping > 0 ? uppercase_mapping : lowercase_mapping - end - end - - # Holds static data from the Unicode database. - class UnicodeDatabase - ATTRIBUTES = :codepoints, :composition_exclusion, :composition_map, :boundary, :cp1252 - - attr_writer(*ATTRIBUTES) - - def initialize - @codepoints = Hash.new(Codepoint.new) - @composition_exclusion = [] - @composition_map = {} - @boundary = {} - @cp1252 = {} - end - - # Lazy load the Unicode database so it's only loaded when it's actually used - ATTRIBUTES.each do |attr_name| - class_eval(<<-EOS, __FILE__, __LINE__ + 1) - def #{attr_name} # def codepoints - load # load - @#{attr_name} # @codepoints - end # end - EOS - end - - # Loads the Unicode database and returns all the internal objects of - # UnicodeDatabase. - def load - begin - @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 - - # Redefine the === method so we can write shorter rules for grapheme cluster breaks - @boundary.each_key do |k| - @boundary[k].instance_eval do - def ===(other) - detect { |i| i === other } ? true : false - end - end if @boundary[k].kind_of?(Array) - end - - # define attr_reader methods for the instance variables - class << self - attr_reader(*ATTRIBUTES) - end - end - - # Returns the directory in which the data files are stored. - def self.dirname - File.expand_path("../values", __dir__) - end - - # Returns the filename for the data file for this version. - def self.filename - File.expand_path File.join(dirname, "unicode_tables.dat") - end + string.swapcase end private - def apply_mapping(string, mapping) - 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 database - @database ||= UnicodeDatabase.new - end end end end diff --git a/activesupport/lib/active_support/values/unicode_tables.dat b/activesupport/lib/active_support/values/unicode_tables.dat deleted file mode 100644 index f7d9c48bbe..0000000000 Binary files a/activesupport/lib/active_support/values/unicode_tables.dat and /dev/null differ diff --git a/activesupport/test/multibyte_unicode_database_test.rb b/activesupport/test/multibyte_unicode_database_test.rb deleted file mode 100644 index 540a34493d..0000000000 --- a/activesupport/test/multibyte_unicode_database_test.rb +++ /dev/null @@ -1,26 +0,0 @@ -# frozen_string_literal: true - -require "abstract_unit" - -class MultibyteUnicodeDatabaseTest < ActiveSupport::TestCase - include ActiveSupport::Multibyte::Unicode - - def setup - @ucd = UnicodeDatabase.new - end - - UnicodeDatabase::ATTRIBUTES.each do |attribute| - define_method "test_lazy_loading_on_attribute_access_of_#{attribute}" do - assert_called(@ucd, :load) do - @ucd.send(attribute) - end - end - end - - def test_load - @ucd.load - UnicodeDatabase::ATTRIBUTES.each do |attribute| - assert @ucd.send(attribute).length > 1 - end - end -end -- cgit v1.2.3