Improve VS16 matching

janlelis · Nov 19, 2024 · 5d13cb1 · 5d13cb1
1 parent b79047c
commit 5d13cb1
Show file tree

Hide file tree

Showing 4 changed files with 31 additions and 44 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,5 +1,9 @@
 # CHANGELOG
 
+## 3.1.1
+
+- Performance improvements
+
 ## 3.1.0
 
 **Improve Emoji support:**

diff --git a/lib/unicode/display_width.rb b/lib/unicode/display_width.rb
@@ -30,9 +30,17 @@ class DisplayWidth
       rgi_at: :REGEX_INCLUDE_MQE_UQE,
       possible: :REGEX_WELL_FORMED,
     }
-    REGEX_EMOJI_BASIC_OR_KEYCAP = Regexp.union(Unicode::Emoji::REGEX_BASIC, Unicode::Emoji::REGEX_EMOJI_KEYCAP)
-    REGEX_EMOJI_ALL_SEQUENCES = Regexp.union(/.[\u{1F3FB}-\u{1F3FF}\u{FE0F}]?(\u{200D}.[\u{1F3FB}-\u{1F3FF}\u{FE0F}]?)+/, Unicode::Emoji::REGEX_EMOJI_KEYCAP)
     REGEX_EMOJI_NOT_POSSIBLE = /\A[#*0-9]\z/
+    REGEX_EMOJI_VS16 = Regexp.union(
+      Regexp.compile(
+        Unicode::Emoji::REGEX_TEXT_PRESENTATION.source +
+        "(?<![#*0-9])" +
+        "\u{FE0F}"
+      ),
+      Unicode::Emoji::REGEX_EMOJI_KEYCAP
+    )
+    REGEX_EMOJI_ALL_SEQUENCES = Regexp.union(/.[\u{1F3FB}-\u{1F3FF}\u{FE0F}]?(\u{200D}.[\u{1F3FB}-\u{1F3FF}\u{FE0F}]?)+/, Unicode::Emoji::REGEX_EMOJI_KEYCAP)
+    REGEX_EMOJI_ALL_SEQUENCES_AND_VS16 = Regexp.union(REGEX_EMOJI_ALL_SEQUENCES, REGEX_EMOJI_VS16)
 
     # Returns monospace display width of string
     def self.of(string, ambiguous = nil, overwrite = nil, old_options = {}, **options)
@@ -177,45 +185,23 @@ def self.emoji_width(string, mode = :all, ambiguous = DEFAULT_AMBIGUOUS)
           mode == :rgi_at,
           ambiguous,
         )
+
       elsif mode == :all_no_vs16
-        emoji_width_all(string)
+        no_emoji_string = string.gsub(REGEX_EMOJI_ALL_SEQUENCES){ res += 2; "" }
+        [res, no_emoji_string]
+
       elsif mode == :vs16
-        emoji_width_basic(string)
+        no_emoji_string = string.gsub(REGEX_EMOJI_VS16){ res += 2; "" }
+        [res, no_emoji_string]
+
       elsif mode == :all
-        res_all, string = emoji_width_all(string)
-        res_basic, string = emoji_width_basic(string)
-        [res_all + res_basic, string]
+        no_emoji_string = string.gsub(REGEX_EMOJI_ALL_SEQUENCES_AND_VS16){ res += 2; "" }
+        [res, no_emoji_string]
+
       else
         [0, string]
-      end
-    end
-
-    # Ensure all explicit VS16 sequences have width 2
-    def self.emoji_width_basic(string)
-      res = 0
 
-      no_emoji_string = string.gsub(REGEX_EMOJI_BASIC_OR_KEYCAP){ |basic_emoji|
-        if basic_emoji.size >= 2 # VS16 present
-          res += 2
-          ""
-        else
-          basic_emoji
-        end
-      }
-
-      [res, no_emoji_string]
-    end
-
-    # Use simplistic ZWJ/modifier/kecap sequence matching
-    def self.emoji_width_all(string)
-      res = 0
-
-      no_emoji_string = string.gsub(REGEX_EMOJI_ALL_SEQUENCES){
-        res += 2
-        ""
-      }
-
-      [res, no_emoji_string]
+      end
     end
 
     # Match possible Emoji first, then refine
@@ -241,14 +227,7 @@ def self.emoji_width_via_possible(string, emoji_set_regex, strict_eaw = false, a
         else
           if !strict_eaw
             # Ensure all explicit VS16 sequences have width 2
-            emoji_candidate.gsub!(Unicode::Emoji::REGEX_BASIC){ |basic_emoji|
-              if basic_emoji.size == 2 # VS16 present
-                res += 2
-                ""
-              else
-                basic_emoji
-              end
-            }
+            emoji_candidate.gsub!(REGEX_EMOJI_VS16){ res += 2; "" }
           end
 
           emoji_candidate

diff --git a/spec/display_width_spec.rb b/spec/display_width_spec.rb
@@ -255,6 +255,10 @@
         it 'counts default-text presentation Emoji with Emoji Presentation (VS16) as 2' do
           expect( "❣️".display_width(emoji: :vs16) ).to eq 2
         end
+
+        it 'works with keycaps: width 2' do
+          expect( "1️⃣".display_width(emoji: :vs16) ).to eq 2
+        end
       end
 
       describe ':rgi' do

diff --git a/unicode-display_width.gemspec b/unicode-display_width.gemspec
@@ -13,7 +13,7 @@ Gem::Specification.new do |s|
   s.extra_rdoc_files = ["README.md", "MIT-LICENSE.txt", "CHANGELOG.md"]
   s.license = 'MIT'
   s.required_ruby_version = '>= 2.5.0'
-  s.add_dependency 'unicode-emoji', '~> 4.0'
+  s.add_dependency 'unicode-emoji', '~> 4.0', '>= 4.0.4'
   s.add_development_dependency 'rspec', '~> 3.4'
   s.add_development_dependency 'rake', '~> 13.0'