js_regex 3.4.0 → 3.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 76344824ca1ba10360b72c42fce4fe6b667dd01761665a9b36c4ab071bbaecba
-  data.tar.gz: 37ceeda59137c6871be4d3782110d06c93e0f6be85c0332bad9a8afad0831d71
+  metadata.gz: 81bb3bc59a709d6bf1eb70daf3a80361352c8478c4cfc0d158c28edad617f0ab
+  data.tar.gz: 95518db3ac6952c03874d8d5e9025fa1adb5953412e27b27add6d14ceb6ad163
 SHA512:
-  metadata.gz: 2199e2674f5187352a9e7a428266e4d35290630e4111c24c4f2f2514d2e64f46fc98512c62d5c97831c3719ca3dd90cccb7dabacb9285faa8c2d8087af94d2ea
-  data.tar.gz: 235c68de51d6dc365f49354a5e79aa73f616ebd6e7386a7a596a3c09817a7a1b242a31024af3eae7206cf89395a8eadfce9c0819a14a62b56104a2c851850082
+  metadata.gz: d85e5fddd9c7ee0ba3abf241ccc6675edfd632b6258312f2c7f0202896f8e0fdcc45baacef18973023ba4fdbff31763a511e8308e0fb8eb4934c88a45db270a9
+  data.tar.gz: 4103cec0a7465483c61938692e898f5d3d0e738c3c61ecafc8fe06e97f9166738edccf3ebd78ba3dde769c172428df2988c699cb024df2072ecb16e0d98c5ffc

data/lib/js_regex/converter/anchor_converter.rb

@@ -23,9 +23,8 @@ class JsRegex
       end
 
       def pass_boundary_with_warning(boundary)
-        warn("The boundary '#{boundary}' at index #{expression.ts} "\
-             'is not unicode-aware in JavaScript, '\
-             'so it might act differently than in Ruby.')
+        warn_of("The anchor '#{boundary}' at index #{expression.ts} "\
+                'only works at ASCII word boundaries in JavaScript.')
         boundary
       end
     end

data/lib/js_regex/converter/base.rb

@@ -54,11 +54,11 @@ class JsRegex
       def warn_of_unsupported_feature(description = nil)
         description ||= "#{subtype} #{expression.type}".tr('_', ' ')
         full_desc = "#{description} '#{expression}'"
-        warn("Dropped unsupported #{full_desc} at index #{expression.ts}")
+        warn_of("Dropped unsupported #{full_desc} at index #{expression.ts}")
         drop
       end
 
-      def warn(text)
+      def warn_of(text)
         context.warnings << text
       end
 

data/lib/js_regex/converter/escape_converter.rb

@@ -44,7 +44,7 @@ class JsRegex
         when :control, :meta_sequence
           unicode_escape_codepoint
         when :literal
-          LiteralConverter.convert_data(data)
+          LiteralConverter.convert_data(expression.char)
         when *ESCAPES_SHARED_BY_RUBY_AND_JS
           pass_through
         when :bell, :escape

data/lib/js_regex/converter/literal_converter.rb

@@ -15,42 +15,28 @@ class JsRegex
           if data =~ ASTRAL_PLANE_CODEPOINT_PATTERN
             convert_astral_data(data)
           else
-            convert_bmp_data(data)
+            escape_incompatible_bmp_literals(data)
           end
         end
 
         def convert_astral_data(data)
-          data.each_char.each_with_object(Node.new) do |chr, node|
-            if chr =~ ASTRAL_PLANE_CODEPOINT_PATTERN
-              node << surrogate_pair_for(chr)
+          data.each_char.each_with_object(Node.new) do |char, node|
+            if char =~ ASTRAL_PLANE_CODEPOINT_PATTERN
+              node << surrogate_substitution_for(char)
             else
-              node << convert_bmp_data(chr)
+              node << escape_incompatible_bmp_literals(char)
             end
           end
         end
 
-        def convert_bmp_data(data)
-          ensure_json_compatibility(
-            ensure_forward_slashes_are_escaped(data)
-          )
+        def escape_incompatible_bmp_literals(data)
+          data.gsub('/', '\\/').gsub(/[\f\n\r\t]/) { |lit| Regexp.escape(lit) }
         end
 
         private
 
-        def surrogate_pair_for(astral_char)
-          base = astral_char.codepoints.first - 65_536
-          high = ((base / 1024).floor + 55_296).to_s(16)
-          low  = (base % 1024 + 56_320).to_s(16)
-          "(?:\\u#{high}\\u#{low})"
-        end
-
-        def ensure_forward_slashes_are_escaped(data)
-          # literal slashes would signify the pattern end in JsRegex#to_s
-          data.gsub(%r{\\?/}, '\\/')
-        end
-
-        def ensure_json_compatibility(data)
-          data.gsub(%r{\\?([\f\n\r\t])}) { Regexp.escape($1) }
+        def surrogate_substitution_for(char)
+          CharacterSet::Writer.write_surrogate_ranges([], [char.codepoints])
         end
       end
 

data/lib/js_regex/converter/meta_converter.rb

@@ -8,6 +8,9 @@ class JsRegex
     # Template class implementation.
     #
     class MetaConverter < JsRegex::Converter::Base
+      DOT_EXPANSION    = '(?:[\uD800-\uDBFF][\uDC00-\uDFFF]|[^\n\uD800-\uDFFF])'
+      ML_DOT_EXPANSION = '(?:[\uD800-\uDBFF][\uDC00-\uDFFF]|[^\uD800-\uDFFF])'
+
       private
 
       def convert_data
@@ -15,7 +18,7 @@ class JsRegex
         when :alternation
           convert_alternatives
         when :dot
-          expression.multiline? ? '(?:.|\n)' : '.'
+          expression.multiline? ? ML_DOT_EXPANSION : DOT_EXPANSION
         else
           warn_of_unsupported_feature
         end

data/lib/js_regex/converter/set_converter.rb

@@ -62,9 +62,8 @@ class JsRegex
       end
 
       def pass_through_with_escaping
-        expression.to_s(:base).gsub(%r{([\f\n\r\t])|(/)}) do
-          $1 ? Regexp.escape($1) : "\\#{$2}"
-        end
+        string = expression.to_s(:base)
+        LiteralConverter.escape_incompatible_bmp_literals(string)
       end
     end
   end

data/lib/js_regex/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 class JsRegex
-  VERSION = '3.4.0'
+  VERSION = '3.5.0'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: js_regex
 version: !ruby/object:Gem::Version
-  version: 3.4.0
+  version: 3.5.0
 platform: ruby
 authors:
 - Janosch Müller
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-06-07 00:00:00.000000000 Z
+date: 2019-07-16 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: character_set
@@ -30,28 +30,28 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.5'
+        version: '1.6'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.5'
+        version: '1.6'
 - !ruby/object:Gem::Dependency
   name: regexp_property_values
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.3'
+        version: '1.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.3'
+        version: '1.0'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement