unicode-display_width 3.1.0 → 3.1.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 01657362aaf60cf79bb03c63bb96e01914139c7bb965dc9bed18e7988b8c6709
-  data.tar.gz: 297cc1ab03e72a02e9f33eb4eec2dea2006f23987818083c4bc12aa168e437c3
+  metadata.gz: 1886b39340f01645fd4e64d032ab1611e471e60c4dbd46e3d8867125ef45232d
+  data.tar.gz: dc452df48efa0f7f9cd862b0390f611df83e4dcd82c640f4faa151b05022596f
 SHA512:
-  metadata.gz: a3878d504a273e44268762fca4857bf26a9322e0e54c0afc437d953dca675822262c9aec54cb5de3d23390b4b778403b36ce0f73ba5b0f1d2c8554a1f796d210
-  data.tar.gz: 00de0d22f3b245f16de15b3b4864ff754da04ea94eafdeaf06c0e38fec8cfb2559fbeaafc17f165534e70a386e154f70d7b071f5a226c9f64d7088bbb408cabb
+  metadata.gz: 85dfef303836ba1c13271144ad24f89dbc40591d9056ee187c9ee5b7b6ff1f19d8d9ebd4e21108f78a61d2e3d3c6ce44f560005e3216cf3f8fa595466c50dfc7
+  data.tar.gz: eae08ff81ed83a3965820aaf09ce10fd028428adf6653807d3fb87b0c96b9ae7be757d38ffa90a8a27b39a8454e4b2694109a8aaddcc75d21d0e449ce8f7f628

data/CHANGELOG.md

@@ -1,5 +1,9 @@
 # CHANGELOG
 
+## 3.1.1
+
+- Performance improvements
+
 ## 3.1.0
 
 **Improve Emoji support:**

data/README.md

@@ -114,10 +114,11 @@ The `emoji:` option can be used to configure which type of Emoji should be consi
 `:all_no_vs16` | EAW (1 or 2) | 2 for all ZWJ/modifier/keycap sequences, even if they are not well-formed Emoji sequences | WezTerm
 `:possible`| 2                | 2 for all possible/well-formed Emoji sequences | ?
 `:rgi`     | 2                | 2 for all [RGI Emoji](https://www.unicode.org/reports/tr51/#def_rgi_set) sequences | ?
-`:rgi_at`  | EAW (1 or 2)     | 1 or 2: Like `:rgi`, but Emoji sequences starting with a default-text Emoji have width 1 | Apple Terminal
+`:rgi_at`  | EAW (1 or 2)     | 1 or 2: Like `:rgi`, but Emoji sequences starting with a default-text Emoji have EAW | Apple Terminal
 `:vs16`    | 2                | 2 * number of partial Emoji (sequences never considered to represent a combined Emoji) | kitty?
 `false` or  `:none` | EAW (1 or 2) | No Emoji adjustments | gnome-terminal, many older terminals
 
+- *EAW:* East Asian Width
 - *RGI Emoji:* Emoji Recommended for General Interchange
 - *ZWJ:* Zero-width Joiner: Codepoint `U+200D`,used in many Emoji sequences
 

data/lib/unicode/display_width/constants.rb

@@ -2,7 +2,7 @@
 
 module Unicode
   class DisplayWidth
-    VERSION = "3.1.0"
+    VERSION = "3.1.1"
     UNICODE_VERSION = "16.0.0"
     DATA_DIRECTORY = File.expand_path(File.dirname(__FILE__) + "/../../../data/")
     INDEX_FILENAME = DATA_DIRECTORY + "/display_width.marshal.gz"

data/lib/unicode/display_width.rb

@@ -30,9 +30,17 @@ module Unicode
       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 @@ module Unicode
           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 @@ module Unicode
         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

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: unicode-display_width
 version: !ruby/object:Gem::Version
-  version: 3.1.0
+  version: 3.1.1
 platform: ruby
 authors:
 - Jan Lelis
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-11-18 00:00:00.000000000 Z
+date: 2024-11-19 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: unicode-emoji
@@ -17,6 +17,9 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '4.0'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 4.0.4
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
@@ -24,6 +27,9 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '4.0'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 4.0.4
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement