east_asian_width_simple 1.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 9bdea9f77fd2c6429ec5e7cd8e541717c1f06ab33f1c3b270cc2bb97c6723d7a
+  data.tar.gz: 27375d92f4329323c09fa6dba5cae653757dd2e32102c7f03dbb1f691dde8be9
+SHA512:
+  metadata.gz: 1a71a14256e90f3d87cd0d9533cef3552aad0a9ac78a60a4f066f063598148a261f9b549bb76e11e5d4d28575853802a293d1b1ee1b11881a0f684ea67b166cb
+  data.tar.gz: 719022070f2f7afa493ddd58cb4cd9e8e8f662eb6ddfd3334e50335c9bc809744ad8cc92983ac7954a4024737713d2d870754e4638a6e6e9eca630fa28efebe1

data/lib/east_asian_width_simple.rb

@@ -0,0 +1,59 @@
+# frozen_string_literal: true
+
+class EastAsianWidthSimple
+  Error = Class.new(StandardError)
+  MissingCodePointError = Class.new(Error)
+
+  HEX_DIGIT_REGEXP = /\h/
+  PROPERTY_TO_WIDTH_MAP = { A: nil, F: 2, H: 1, N: nil, Na: 1, W: 2 }.freeze
+
+  def initialize(east_asian_width_txt_io)
+    @lookup_table = Array.new(2**21)
+    east_asian_width_txt_io.each_line do |line|
+      next unless line.start_with?(HEX_DIGIT_REGEXP)
+
+      code_point, property = line.split(' ').first.split(';')
+      if code_point.include?('..')
+        first, last = code_point.split('..')
+        @lookup_table.fill(property.to_sym, first.to_i(16)..last.to_i(16))
+      else
+        @lookup_table[code_point.to_i(16)] = property.to_sym
+      end
+    end
+  end
+
+  def string_width(string)
+    string = string.encode(Encoding::UTF_8) unless string.encoding == Encoding::UTF_8
+    string.codepoints.sum { |codepoint| lookup_width(codepoint) }
+  end
+
+  def lookup_width(codepoint)
+    property = lookup(codepoint)
+    width = PROPERTY_TO_WIDTH_MAP[property]
+    if width.nil?
+      warn <<~WARNING_MESSAGE
+        The code point 0x#{codepoint.to_s(16)} has the property "#{property}" \
+        whose width is unknown.
+      WARNING_MESSAGE
+      return 1
+    end
+    width
+  end
+
+  def lookup(codepoint)
+    ret = @lookup_table[codepoint]
+    if ret.nil?
+      raise(
+        MissingCodePointError,
+        "Cannot find the code point 0x#{codepoint.to_s(16)} " \
+        'in the lookup table.'
+      )
+    end
+
+    ret
+  end
+
+  def inspect
+    "#<#{self.class}:#{object_id}>"
+  end
+end

metadata

@@ -0,0 +1,78 @@
+--- !ruby/object:Gem::Specification
+name: east_asian_width_simple
+version: !ruby/object:Gem::Version
+  version: 1.0.0
+platform: ruby
+authors:
+- Weihang Jian
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2022-06-11 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '13.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '13.0'
+- !ruby/object:Gem::Dependency
+  name: minitest
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.0'
+description: 'east_asian_width_simple is a Ruby gem that calculates the visual width
+  of strings by parsing and looking up East Asian Width Property Data File, aka EastAsianWidth.txt,
+  which is defined in Unicode Standard Annex #11: East Asian Width. It aims to be
+  time-performant and easy to use.
+
+  '
+email:
+- tonytonyjan@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/east_asian_width_simple.rb
+homepage: https://github.com/tonytonyjan/east_asian_width_simple
+licenses:
+- MIT
+metadata: {}
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.3.11
+signing_key:
+specification_version: 4
+summary: 'Calculate string visual width by looking up EastAsianWidth.txt from UAX
+  #11: East Asian Width'
+test_files: []