unicode-display_width 2.3.0 → 2.4.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 1fce5b196a16187b338dee6aaba7f4bf499bfc12eee213085c29296851671bc4
-  data.tar.gz: 4554e159dbc6242ab9e8e285282a6bb4361d715997df21ef81b1d9c90665b4cd
+  metadata.gz: 26234cf1d4a965966cfab38151afe61c8f0a4c2d4f31fc006a319997af7bf076
+  data.tar.gz: eb5c24564cc94da5378b1d5b9065f90a70fcbcff50f914cc858634825694a544
 SHA512:
-  metadata.gz: 57824a99da0e7db191264802c8cd01e47319b1387643f4d2ea269a5ab86cfdd2c3d188bcdddc71d56c3cecfd1538940bc68b7d870f424e39cf1d9849cf8123d1
-  data.tar.gz: 655e5048a23f2576e076511d267cf5df7e382c7531e9f1e954c05e3aea5fbbf3975c1af6b4b7fadc4c433283a96afeb02e5621ca925af4bda605d9a6e3ffafeb
+  metadata.gz: 8687c39d5c62292c8d124ca9a3889c30f5f7d8e64b7e5ff79fc3b58137708bfeb844b36d32a5f73920f5e63a3cb60fc4a3f465f8505ccb8134e30d2445fc1af3
+  data.tar.gz: 37b073e36650f21bca8aa40cf9809a882fcd84642824ca8380542c80f3cb7a5f78c43eabe9abd6f09a73f6ee2cb5c49f60aa8b1ec72bcc8100cd411cdda15a5a

data/CHANGELOG.md

@@ -1,5 +1,16 @@
 # 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
+
 ## 2.3.0
 
 - Unicode 15.0

data/README.md

@@ -1,12 +1,14 @@
 ## Unicode::DisplayWidth [![[version]](https://badge.fury.io/rb/unicode-display_width.svg)](https://badge.fury.io/rb/unicode-display_width) [<img src="https://github.com/janlelis/unicode-display_width/workflows/Test/badge.svg" />](https://github.com/janlelis/unicode-display_width/actions?query=workflow%3ATest)
 
-Determines the monospace display width of a string in Ruby. Implementation based on [EastAsianWidth.txt](https://www.unicode.org/Public/UNIDATA/EastAsianWidth.txt) and other data, 100% in Ruby. It does not rely on the OS vendor (like [wcwidth()](https://github.com/janlelis/wcswidth-ruby)) to provide an up-to-date method for measuring string width.
+Determines the monospace display width of a string in Ruby. Useful for all kinds of terminal-based applications. Implementation based on [EastAsianWidth.txt](https://www.unicode.org/Public/UNIDATA/EastAsianWidth.txt) and other data, 100% in Ruby. It does not rely on the OS vendor (like [wcwidth()](https://github.com/janlelis/wcswidth-ruby)) to provide an up-to-date method for measuring string width.
 
 Unicode version: **15.0.0** (September 2022)
 
 Supported Rubies: **3.1**, **3.0**, **2.7**
 
-Old Rubies which might still work: **2.6**, **2.5**, **2.4**, **2.3**, **2.2**, **2.1**, **2.0**, **1.9**
+Old Rubies which might still work: **2.6**, **2.5**, **2.4**
+
+For even older Rubies, use version 2.3.0 of this gem: **2.3**, **2.2**, **2.1**, **2.0**, **1.9**
 
 ## Version 2.0 — Breaking Changes
 
@@ -39,7 +41,7 @@ Width  | Characters                   | Comment
 -------|------------------------------|--------------------------------------------------
 X      | (user defined)               | Overwrites any other values
 -1     | `"\b"`                       | Backspace (total width never below 0)
-0      | `"\0"`, `"\x05"`, `"\a"`, `"\n"`, `"\v"`, `"\f"`, `"\r"`, `"\x0E"`, `"\x0F"` | [C0 control codes](https://en.wikipedia.org/wiki/C0_and_C1_control_codes#C0_.28ASCII_and_derivatives.29) that do not change horizontal width
+0      | `"\0"`, `"\x05"`, `"\a"`, `"\n"`, `"\v"`, `"\f"`, `"\r"`, `"\x0E"`, `"\x0F"` | [C0 control codes](https://en.wikipedia.org/wiki/C0_and_C1_control_codes#C0_.28ASCII_and_derivatives.29) which do not change horizontal width
 1      | `"\u{00AD}"`                 | SOFT HYPHEN
 2      | `"\u{2E3A}"`                 | TWO-EM DASH
 3      | `"\u{2E3B}"`                 | THREE-EM DASH
@@ -89,6 +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 = "2.3.0"
+    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

@@ -5,23 +5,39 @@ 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 = {})
-      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
+      # 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
+
+      # 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
       res -= emoji_extra_width_of(string, ambiguous, overwrite) if options[:emoji]
+
+      # Return result + prevent negative lengths
       res < 0 ? 0 : res
     end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: unicode-display_width
 version: !ruby/object:Gem::Version
-  version: 2.3.0
+  version: 2.4.1
 platform: ruby
 authors:
 - Jan Lelis
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2022-09-14 00:00:00.000000000 Z
+date: 2023-01-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
@@ -62,7 +62,7 @@ homepage: https://github.com/janlelis/unicode-display_width
 licenses:
 - MIT
 metadata:
-  changelog_uri: https://github.com/janlelis/unicode-display_width/blob/master/CHANGELOG.md
+  changelog_uri: https://github.com/janlelis/unicode-display_width/blob/main/CHANGELOG.md
   source_code_uri: https://github.com/janlelis/unicode-display_width
   bug_tracker_uri: https://github.com/janlelis/unicode-display_width/issues
   rubygems_mfa_required: 'true'
@@ -74,14 +74,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 1.9.3
+      version: 2.4.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !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.