From 99b6987477879211b48c1e1ba3988a571f3a5e23 Mon Sep 17 00:00:00 2001
From: Jan Lelis <hi@ruby.consulting>
Date: Wed, 4 Jan 2023 12:13:03 +0100
Subject: [PATCH] Avoid overwrite lookup if no overwrites are set

---
 CHANGELOG.md                 |  3 +++
 lib/unicode/display_width.rb | 48 +++++++++++++++++++++++++++++++-----
 2 files changed, 45 insertions(+), 6 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index b7e2f7d..2b01f9d 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -2,7 +2,10 @@
 
 ## 2.4.2 (unreleased)
 
+More performance improvements:
+
 - Optimize lookup of first 4096 codepoints
+- Avoid overwrite lookup if no overwrites are set
 
 ## 2.4.1
 
diff --git a/lib/unicode/display_width.rb b/lib/unicode/display_width.rb
index 77816e6..bbd7026 100644
--- a/lib/unicode/display_width.rb
+++ b/lib/unicode/display_width.rb
@@ -10,16 +10,51 @@ class DisplayWidth
     FIRST_4096 = decompress_index(INDEX[0][0], 1)
 
     def self.of(string, ambiguous = 1, overwrite = {}, options = {})
-      # Optimization for ASCII-only strings without certain control symbols
-      if overwrite.empty? && string.ascii_only?
-        if string.match?(ASCII_NON_ZERO_REGEX)
-          res = string.gsub(ASCII_NON_ZERO_REGEX, "").size - string.count("\b")
-          return res < 0 ? 0 : res
+      if overwrite.empty?
+        # Optimization for ASCII-only strings without certain control symbols
+        if string.ascii_only?
+          if string.match?(ASCII_NON_ZERO_REGEX)
+            res = string.gsub(ASCII_NON_ZERO_REGEX, "").size - string.count("\b")
+            res < 0 ? 0 : res
+          else
+            string.size
+          end
         else
-          return string.size
+          width_no_overwrite(string, ambiguous, options)
         end
+      else
+        width_all_features(string, ambiguous, overwrite, options)
       end
+    end
 
+    def self.width_no_overwrite(string, ambiguous, options = {})
+      # Sum of all chars widths
+      res = string.codepoints.sum{ |codepoint|
+        if codepoint > 15 && codepoint < 161 # very common
+          next 1
+        elsif codepoint < 0x1001
+          width = FIRST_4096[codepoint]
+        else
+          width = INDEX
+          depth = INITIAL_DEPTH
+          while (width = width[codepoint / depth]).instance_of? Array
+            codepoint %= depth
+            depth /= 16
+          end
+        end
+
+        width == :A ? ambiguous : (width || 1)
+      }
+
+      # Substract emoji error
+      res -= emoji_extra_width_of(string, ambiguous) if options[:emoji]
+
+      # Return result + prevent negative lengths
+      res < 0 ? 0 : res
+    end
+
+    # Same as .width_no_overwrite - but with applying overwrites for each char
+    def self.width_all_features(string, ambiguous, overwrite, options)
       # Sum of all chars widths
       res = string.codepoints.sum{ |codepoint|
         next overwrite[codepoint] if overwrite[codepoint]
@@ -47,6 +82,7 @@ def self.of(string, ambiguous = 1, overwrite = {}, options = {})
       res < 0 ? 0 : res
     end
 
+
     def self.emoji_extra_width_of(string, ambiguous = 1, overwrite = {}, _ = {})
       require "unicode/emoji"