unicode-display_width 2.4.0 → 2.4.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: e64e9230d9a0df4076a18bb935b6f1aeac16e079544aa65097b1ddb967b4960c
-  data.tar.gz: 17d5cf547c89859318bc578e3e15a63ce0ab94d8801f2928097bb29d27cb6da0
+  metadata.gz: 26234cf1d4a965966cfab38151afe61c8f0a4c2d4f31fc006a319997af7bf076
+  data.tar.gz: eb5c24564cc94da5378b1d5b9065f90a70fcbcff50f914cc858634825694a544
 SHA512:
-  metadata.gz: 1ea3ee4075d687ac1708a095ffe82e833389db1ec613ef43c9f8aa3aeeb5983d585cf6ad22e7d00d1020378344d9e9450096d6b7a04f27358d5418466b7fdf41
-  data.tar.gz: 00a75b4f46daa89186bde97d5e2da86d197e5ef8704876c16085dd9a503620dc2aaf6e6e9030b9a438417f54d48070d0df06ca2b3e1530bc6d2d1be761f21054
+  metadata.gz: 8687c39d5c62292c8d124ca9a3889c30f5f7d8e64b7e5ff79fc3b58137708bfeb844b36d32a5f73920f5e63a3cb60fc4a3f465f8505ccb8134e30d2445fc1af3
+  data.tar.gz: 37b073e36650f21bca8aa40cf9809a882fcd84642824ca8380542c80f3cb7a5f78c43eabe9abd6f09a73f6ee2cb5c49f60aa8b1ec72bcc8100cd411cdda15a5a

data/CHANGELOG.md

@@ -1,5 +1,12 @@
 # CHANGELOG
 
+## 2.4.1
+
+- Improve general performance!
+- Further improve performance for ASCII strings
+
+*You should really upgrade - it's much faster now!*
+
 ## 2.4.0
 - Improve performance for ASCII-only strings, by @fatkodima
 - Require Ruby 2.4

data/README.md

@@ -91,6 +91,9 @@ You can overwrite how to handle specific code points by passing a hash (or even
 Unicode::DisplayWidth.of("a\tb", 1, "\t".ord => 10)) # => tab counted as 10, so result is 12
 ```
 
+Please note that using overwrites disables some perfomance optimizations of this gem.
+
+
 #### Emoji Support
 
 Emoji width support is included, but in must be activated manually. It will adjust the string's size for modifier and zero-width joiner sequences. You also need to add the [unicode-emoji](https://github.com/janlelis/unicode-emoji) gem to your Gemfile:

data/lib/unicode/display_width/constants.rb

@@ -2,7 +2,7 @@
 
 module Unicode
   class DisplayWidth
-    VERSION = "2.4.0"
+    VERSION = "2.4.1"
     UNICODE_VERSION = "15.0.0"
     DATA_DIRECTORY = File.expand_path(File.dirname(__FILE__) + "/../../../data/")
     INDEX_FILENAME = DATA_DIRECTORY + "/display_width.marshal.gz"

data/lib/unicode/display_width.rb

@@ -5,27 +5,33 @@ require_relative "display_width/index"
 
 module Unicode
   class DisplayWidth
-    DEPTHS = [0x10000, 0x1000, 0x100, 0x10].freeze
+    INITIAL_DEPTH = 0x10000
     ASCII_NON_ZERO_REGEX = /[\0\x05\a\b\n\v\f\r\x0E\x0F]/
 
     def self.of(string, ambiguous = 1, overwrite = {}, options = {})
-      # Optimization for ASCII-only strings without control symbols.
-      if overwrite.empty? && string.ascii_only? && !string.match?(ASCII_NON_ZERO_REGEX)
-        return string.size
+      # 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
+        else
+          return string.size
+        end
       end
 
-      # Add width of each char
-      res = string.codepoints.inject(0){ |total_width, codepoint|
-        index_or_value = INDEX
-        codepoint_depth_offset = codepoint
-        DEPTHS.each{ |depth|
-          index_or_value         = index_or_value[codepoint_depth_offset / depth]
-          codepoint_depth_offset = codepoint_depth_offset % depth
-          break unless index_or_value.is_a? Array
-        }
-        width = index_or_value.is_a?(Array) ? index_or_value[codepoint_depth_offset] : index_or_value
+      # Sum of all chars widths
+      res = string.codepoints.sum{ |codepoint|
+        next overwrite[codepoint] if overwrite[codepoint]
+        next 1 if codepoint > 15 && codepoint < 161 # very common
+
+        width = INDEX
+        depth = INITIAL_DEPTH
+        while (width = width[codepoint / depth]).is_a? Array
+          codepoint %= depth
+          depth /= 16
+        end
         width = ambiguous if width == :A
-        total_width + (overwrite[codepoint] || width || 1)
+        width || 1
       }
 
       # Substract emoji error

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: unicode-display_width
 version: !ruby/object:Gem::Version
-  version: 2.4.0
+  version: 2.4.1
 platform: ruby
 authors:
 - Jan Lelis
@@ -81,7 +81,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.7
+rubygems_version: 3.4.1
 signing_key: 
 specification_version: 4
 summary: Determines the monospace display width of a string in Ruby.