regexp_parser 0.4.9 → 0.4.10

data/lib/regexp_parser/syntax/ruby/2.3.0.rb

@@ -6,6 +6,9 @@ module Regexp::Syntax
     class V230 < Regexp::Syntax::Ruby::V22
       def initialize
         super
+
+        implements :property,    UnicodeProperty::V230
+        implements :nonproperty, UnicodeProperty::V230
       end
     end
 

data/lib/regexp_parser/syntax/ruby/2.4.0.rb

@@ -6,6 +6,9 @@ module Regexp::Syntax
     class V240 < Regexp::Syntax::Ruby::V23
       def initialize
         super
+
+        implements :property,    UnicodeProperty::V240
+        implements :nonproperty, UnicodeProperty::V240
       end
     end
 

data/lib/regexp_parser/syntax/ruby/2.5.0.rb

@@ -6,6 +6,9 @@ module Regexp::Syntax
     class V250 < Regexp::Syntax::Ruby::V24
       def initialize
         super
+
+        implements :property,    UnicodeProperty::V250
+        implements :nonproperty, UnicodeProperty::V250
       end
     end
 

data/lib/regexp_parser/syntax/ruby/2.6.0.rb

@@ -0,0 +1,13 @@
+require File.expand_path('../2.5', __FILE__)
+
+module Regexp::Syntax
+  module Ruby
+
+    class V260 < Regexp::Syntax::Ruby::V25
+      def initialize
+        super
+      end
+    end
+
+  end
+end

data/lib/regexp_parser/syntax/ruby/2.6.rb

@@ -0,0 +1,8 @@
+require File.expand_path('../2.6.0', __FILE__)
+
+module Regexp::Syntax
+  module Ruby
+    # uses the latest 2.6 release
+    class V26 < Regexp::Syntax::Ruby::V260; end
+  end
+end

data/lib/regexp_parser/syntax/tokens/unicode_property.rb

@@ -2,8 +2,10 @@ module Regexp::Syntax
   module Token
 
     module UnicodeProperty
-      CharType = [:alnum, :alpha, :ascii, :blank, :cntrl, :digit, :graph, :lower,
-                  :print, :punct, :space, :upper, :word, :xdigit]
+      CharType_V190 = [:alnum, :alpha, :ascii, :blank, :cntrl, :digit, :graph,
+                       :lower, :print, :punct, :space, :upper, :word, :xdigit]
+
+      CharType_V250 = [:xposixpunct]
 
       POSIX  = [:any, :assigned, :newline]
 
@@ -44,9 +46,15 @@ module Regexp::Syntax
       # These were merged (from Onigmo) in the branch for 2.2.0
       Age_V220 = [:age_6_2, :age_6_3, :age_7_0]
 
-      Age = Age_V193 + Age_V200 + Age_V220
+      Age_V230 = [:age_8_0]
+
+      Age_V240 = [:age_9_0]
+
+      Age_V250 = [:age_10_0]
+
+      Age = Age_V193 + Age_V200 + Age_V220 + Age_V230 + Age_V240 + Age_V250
 
-      Derived = [
+      Derived_V190 = [
         :ascii_hex,
         :alphabetic,
         :cased,
@@ -100,7 +108,13 @@ module Regexp::Syntax
         :xid_continue,
       ]
 
-      Script =[
+      Derived_V250 = [
+        :regional_indicator
+      ]
+
+      Derived = Derived_V190 + Derived_V250
+
+      Script_V190 = [
         :script_arabic,
         :script_imperial_aramaic,
         :script_armenian,
@@ -197,9 +211,9 @@ module Regexp::Syntax
         :script_unknown
       ]
 
-      Script_6_0 = [:script_brahmi, :script_batak, :script_mandaic]
+      Script_V193 = [:script_brahmi, :script_batak, :script_mandaic]
 
-      Script_7_0 = [
+      Script_V220 = [
         :script_caucasian_albanian,
         :script_bassa_vah,
         :script_duployan,
@@ -225,6 +239,8 @@ module Regexp::Syntax
         :script_warang_citi
       ]
 
+      Script = Script_V190 + Script_V193 + Script_V220
+
       UnicodeBlock = [
         :block_inalphabetic_presentation_forms,
         :block_inarabic_presentation_forms_a,
@@ -253,7 +269,7 @@ module Regexp::Syntax
         :block_incombining_half_marks,
         :block_incontrol_pictures,
         :block_incurrency_symbols,
-        :block_incyrillic_supplementary,
+        :block_incyrillic_supplement,
         :block_incyrillic,
         :block_indevanagari,
         :block_indingbats,
@@ -333,14 +349,28 @@ module Regexp::Syntax
         :block_inyijing_hexagram_symbols,
       ]
 
-      V190 = CharType + POSIX + Category::All + Derived + Script + UnicodeBlock
-      V193 = Age_V193 + Script_6_0
+      Emoji = [
+        :emoji_any,
+        :emoji_component,
+        :emoji_modifier,
+        :emoji_modifier_base,
+        :emoji_presentation,
+      ]
+
+      V190 = CharType_V190 + POSIX + Category::All + Derived_V190 + Script_V190 + UnicodeBlock
+      V193 = Age_V193 + Script_V193
 
       V200 = Age_V200
 
-      V220 = Age_V220 + Script_7_0
+      V220 = Age_V220 + Script_V220
+
+      V230 = Age_V230
+
+      V240 = Age_V240
+
+      V250 = Age_V250 + CharType_V250 + Derived_V250 + Emoji
 
-      All  = V190 + V193 + V200 + V220
+      All  = V190 + V193 + V200 + V220 + V230 + V240 + V250
 
       Type = :property
       NonType = :nonproperty

data/lib/regexp_parser/syntax/versions.rb

@@ -1,88 +1,10 @@
+# Ruby 1.8.x is no longer a supported runtime,
+# but its regex features are still recognized.
+#
+# Aliases for the latest patch version are provided as 'ruby/n.n',
+# e.g. 'ruby/1.9' refers to Ruby v1.9.3.
 module Regexp::Syntax
-
-  VERSIONS = [
-    # Ruby 1.8.x (NOTE: 1.8.6 is no longer a supported runtime,
-    # but its regex features are still recognized.)
-    'ruby/1.8.6',
-    'ruby/1.8.7',
-
-    # alias for the latest 1.8 implementation
-    'ruby/1.8',
-
-    # Ruby 1.9.x
-    'ruby/1.9.1',
-    'ruby/1.9.2',
-    'ruby/1.9.3',
-
-    # alias for the latest 1.9 implementation
-    'ruby/1.9',
-
-    # Ruby 2.0.x
-    'ruby/2.0.0',
-
-    # alias for the latest 2.0 implementations
-    'ruby/2.0',
-
-    # Ruby 2.1.x
-    'ruby/2.1.0',
-    'ruby/2.1.2',
-    'ruby/2.1.3',
-    'ruby/2.1.4',
-    'ruby/2.1.5',
-    'ruby/2.1.6',
-    'ruby/2.1.7',
-    'ruby/2.1.8',
-    'ruby/2.1.9',
-    'ruby/2.1.10',
-
-    # alias for the latest 2.1 implementations
-    'ruby/2.1',
-
-    # Ruby 2.2.x
-    'ruby/2.2.0',
-    'ruby/2.2.1',
-    'ruby/2.2.2',
-    'ruby/2.2.3',
-    'ruby/2.2.4',
-    'ruby/2.2.5',
-    'ruby/2.2.6',
-    'ruby/2.2.7',
-    'ruby/2.2.8',
-    'ruby/2.2.9',
-
-    # alias for the latest 2.2 implementations
-    'ruby/2.2',
-
-    # Ruby 2.3.x
-    'ruby/2.3.0',
-    'ruby/2.3.1',
-    'ruby/2.3.2',
-    'ruby/2.3.3',
-    'ruby/2.3.4',
-    'ruby/2.3.5',
-    'ruby/2.3.6',
-
-    # alias for the latest 2.3 implementation
-    'ruby/2.3',
-
-    # Ruby 2.4.x
-    'ruby/2.4.0',
-    'ruby/2.4.1',
-    'ruby/2.4.2',
-    'ruby/2.4.3',
-
-    # alias for the latest 2.4 implementation
-    'ruby/2.4',
-
-    # Ruby 2.5.x
-    'ruby/2.5.0',
-
-    # alias for the latest 2.5 implementation
-    'ruby/2.5',
-  ]
-
-end
-
-Regexp::Syntax::VERSIONS.each do |version|
-  require File.expand_path("../#{version}", __FILE__)
+  version_file_paths = Dir[File.expand_path('../ruby/*.rb', __FILE__)]
+  version_file_paths.each { |path| require path }
+  VERSIONS = version_file_paths.map { |path| path[%r{(ruby/.*)\.rb}, 1] }
 end

data/lib/regexp_parser/syntax.rb

@@ -16,7 +16,7 @@ module Regexp::Syntax
 
   class UnknownSyntaxNameError < SyntaxError
     def initialize(name)
-      super "Unknown syntax name '#{name}'. Forgot to add it to Regexp::Syntax::VERSIONS?"
+      super "Unknown syntax name '#{name}'."
     end
   end
 

data/lib/regexp_parser/version.rb

@@ -1,5 +1,5 @@
 class Regexp
   class Parser
-    VERSION = '0.4.9'
+    VERSION = '0.4.10'
   end
 end

data/test/parser/test_properties.rb

@@ -6,20 +6,24 @@ class ParserProperties < Test::Unit::TestCase
   props = [
     'Alnum',
     'Alpha',
-    'Any',
     'Ascii',
     'Blank',
     'Cntrl',
     'Digit',
     'Graph',
     'Lower',
-    'Newline',
     'Print',
     'Punct',
     'Space',
     'Upper',
     'Word',
     'Xdigit',
+    'XPosixPunct',
+
+    'Newline',
+
+    'Any',
+    'Assigned',
 
     'L',
     'Letter',
@@ -144,6 +148,10 @@ class ParserProperties < Test::Unit::TestCase
     'Age=5.1',
     'Age=5.2',
     'Age=6.0',
+    'Age=7.0',
+    'Age=8.0',
+    'Age=9.0',
+    'Age=10.0',
 
     'ahex',
     'ASCII_Hex_Digit',
@@ -264,6 +272,9 @@ class ParserProperties < Test::Unit::TestCase
 
     'radical',
 
+    'ri',
+    'Regional_Indicator',
+
     'sd',
     'Soft_Dotted',
 
@@ -288,6 +299,12 @@ class ParserProperties < Test::Unit::TestCase
 
     'xidc',
     'XID_Continue',
+
+    'Emoji',
+    'Emoji_Component',
+    'Emoji_Modifier',
+    'Emoji_Modifier_Base',
+    'Emoji_Presentation',
   ]
 
   modes.each do |mode|
@@ -295,7 +312,7 @@ class ParserProperties < Test::Unit::TestCase
 
     props.each do |property|
       define_method "test_parse_#{token_type}_#{property}" do
-        t = RP.parse "ab\\#{mode}{#{property}}", 'ruby/1.9'
+        t = RP.parse "ab\\#{mode}{#{property}}", 'ruby/2.5'
 
         assert t.expressions.last.is_a?(UnicodeProperty::Base),
                "Expected property, but got #{t.expressions.last.class.name}"
@@ -351,6 +368,20 @@ class ParserProperties < Test::Unit::TestCase
            "Expected Script property, but got #{t.expressions[1].class.name}"
   end
 
+  def test_parse_property_script_v193
+    t = RP.parse 'ab\p{Brahmi}cd', 'ruby/1.9.3'
+
+    assert t.expressions[1].is_a?(UnicodeProperty::Script),
+           "Expected Script property, but got #{t.expressions[1].class.name}"
+  end
+
+  def test_parse_property_script_v220
+    t = RP.parse 'ab\p{Caucasian_Albanian}cd', 'ruby/2.2'
+
+    assert t.expressions[1].is_a?(UnicodeProperty::Script),
+           "Expected Script property, but got #{t.expressions[1].class.name}"
+  end
+
   def test_parse_property_block
     t = RP.parse 'ab\p{InArmenian}cd', 'ruby/1.9'
 

data/test/scanner/test_all.rb

@@ -13,6 +13,12 @@ if RUBY_VERSION >= '2.0.0'
   end
 end
 
+if RUBY_VERSION >= '2.5.0'
+  %w{emojis}.each do|tc|
+    require File.expand_path("../test_#{tc}", __FILE__)
+  end
+end
+
 class TestRegexpScanner < Test::Unit::TestCase
 
   def test_scanner_returns_an_array

data/test/scanner/test_emojis.rb

@@ -0,0 +1,31 @@
+require File.expand_path("../../helpers", __FILE__)
+
+class ScannerUnicodeEmojis < Test::Unit::TestCase
+
+  tests = {
+    'Emoji'               => :emoji_any,
+    'Emoji_Component'     => :emoji_component,
+    'Emoji_Modifier'      => :emoji_modifier,
+    'Emoji_Modifier_Base' => :emoji_modifier_base,
+    'Emoji_Presentation'  => :emoji_presentation,
+  }
+
+  tests.each_with_index do |(property, token), count|
+    define_method "test_scanner_property_#{token}_#{count}" do
+      tokens = RS.scan("a\\p{#{property}}c")
+      result = tokens.at(1)
+
+      assert_equal :property, result[0]
+      assert_equal token,     result[1]
+    end
+
+    define_method "test_scanner_nonproperty_#{token}_#{count}" do
+      tokens = RS.scan("a\\P{#{property}}c")
+      result = tokens.at(1)
+
+      assert_equal :nonproperty, result[0]
+      assert_equal token,        result[1]
+    end
+  end
+
+end

data/test/scanner/test_properties.rb

@@ -5,20 +5,24 @@ class ScannerProperties < Test::Unit::TestCase
   tests = {
     'Alnum'                               => :alnum,
     'Alpha'                               => :alpha,
-    'Any'                                 => :any,
     'Ascii'                               => :ascii,
     'Blank'                               => :blank,
     'Cntrl'                               => :cntrl,
     'Digit'                               => :digit,
     'Graph'                               => :graph,
     'Lower'                               => :lower,
-    'Newline'                             => :newline,
     'Print'                               => :print,
     'Punct'                               => :punct,
     'Space'                               => :space,
     'Upper'                               => :upper,
     'Word'                                => :word,
     'Xdigit'                              => :xdigit,
+    'XPosixPunct'                         => :xposixpunct,
+
+    'Newline'                             => :newline,
+
+    'Any'                                 => :any,
+    'Assigned'                            => :assigned,
 
     'L'                                   => :letter_any,
     'Letter'                              => :letter_any,
@@ -147,6 +151,9 @@ class ScannerProperties < Test::Unit::TestCase
     'Age=6.2'                             => :age_6_2,
     'Age=6.3'                             => :age_6_3,
     'Age=7.0'                             => :age_7_0,
+    'Age=8.0'                             => :age_8_0,
+    'Age=9.0'                             => :age_9_0,
+    'Age=10.0'                            => :age_10_0,
 
     'ahex'                                => :ascii_hex,
     'ASCII_Hex_Digit'                     => :ascii_hex,
@@ -267,6 +274,9 @@ class ScannerProperties < Test::Unit::TestCase
 
     'radical'                             => :radical,
 
+    'ri'                                  => :regional_indicator,
+    'Regional_Indicator'                  => :regional_indicator,
+
     'sd'                                  => :soft_dotted,
     'Soft_Dotted'                         => :soft_dotted,