textbringer 2 → 3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a7815997c04d50a71d83ccb13cc2b2ec378679b26e74d6a2add40635d033c7ad
-  data.tar.gz: 82193a90e99ba1d56df8c1f6cfde23ae6560585273e3c25777d55f3f7fa3c78a
+  metadata.gz: 66be90097685aaa387bc495b1ec0480eeaa4f7015480c5358fd07268d3e14fdb
+  data.tar.gz: f848eefb51793d46065411ef40b5c8c96f04ebb490a1919c3497e44ed7f0c574
 SHA512:
-  metadata.gz: 6bc44799c79165fee0acf71efedd019692432da5a3b6f6c005a485587e7aecd44e2a82ba380272f42fa51a4519e1d461c9f1cdcb5f2f25f76a62029dff0358ca
-  data.tar.gz: 21ae07326bfbb38398950efcf5d0f0e9abea6195aafa26430691d2879d9e92ff3f4d50a4be5f77ed1d5082fbe776724c737ec7103d7ccd2d977638c3e160be81
+  metadata.gz: 33afdb5cdc3c255a5910e0757393a650dce8ab09b705a58725f391a70e8c46bf7a1b1c31959bf4ed0e96b435c0ba745d3f13c353f5c869f64afa764b23551f9a
+  data.tar.gz: 9b9cc0408ab6d79038d080ebfce6fe3c6c11fe600b88a267c0d2b75c35d12eec02e9a8d95aa82169919fdb49da13c973274b7a9a05edba1a570641167e09c094

data/lib/textbringer/commands/help.rb

@@ -151,9 +151,9 @@ module Textbringer
     define_command(:describe_char,
                    doc: "Describe the char after point") do
       require "unicode/name"
-      require "unicode/categories"
       require "unicode/blocks"
       require "unicode/scripts"
+      require "unicode/categories"
       require "unicode/types"
 
       show_help do |help|
@@ -166,9 +166,9 @@ module Textbringer
         char = /[\0-\x20\x7f]/.match?(c) ? Keymap.key_name(c) : c
         codepoint = "U+%04X" % c.ord
         name = Unicode::Name.readable(c)
+        script = Unicode::Scripts.script(c)
         category = Unicode::Categories.category(c)
         category_long = Unicode::Categories.category(c, format: :long)
-        script = Unicode::Scripts.script(c)
         block = Unicode::Blocks.block(c)
         type = Unicode::Types.type(c)
         help.insert(<<EOF)
@@ -176,9 +176,9 @@ module Textbringer
 character: #{char}
 codepoint: #{codepoint}
      name: #{name}
- category: #{category} (#{category_long})
-   script: #{script}
     block: #{block}
+   script: #{script}
+ category: #{category} (#{category_long})
      type: #{type}
 EOF
       end

data/lib/textbringer/version.rb

@@ -1,3 +1,3 @@
 module Textbringer
-  VERSION = "2"
+  VERSION = "3"
 end

data/lib/textbringer/window/fallback_characters.rb

@@ -1,6 +1,43 @@
 module Textbringer
   class Window
     FALLBACK_CHARACTERS = {
+      # Diacritical marks
+      ## https://www.unicode.org/charts/PDF/U0300.pdf
+      ## characters combinable with alphabet:
+      ## ("\u{0300}".."\u{036f}").filter { |c|
+      ##   ("a".."z").any? { |c2|
+      ##     "#{c2}#{c}".unicode_normalize(:nfc).size == 1
+      ##   }
+      ## }
+      "̀" => "`",
+      "́" => "´",
+      "̂" => "ˆ",
+      "̃" => "˜",
+      "̄" => "¯",
+      "̆" => "˘",
+      "̇" => "˙",
+      "̈" => "¨",
+      "̉" => "ˀ",
+      "̊" => "˚",
+      "̋" => "˝",
+      "̌" => "ˇ",
+      "̏" => '"',
+      "̑" => nil, # combining character only
+      "̛" => nil, # combining character only
+      "̣" => nil, # combining character only
+      "̤" => nil, # combining character only
+      "̥" => "˳",
+      "̦" => ",",
+      "̧" => "¸",
+      "̨" => "˛",
+      "̭" => nil, # combining character only
+      "̮" => nil, # combining character only
+      "̰" => nil, # combining character only
+      "̱" => "ˍ",
+      "̀" => nil, # combining character only
+      "́" => nil, # combining character only
+      "̈́" => nil, # combining character only
+
       # Hiragana
       "゙" => "゛",
       "゚" => "゜",

data/lib/textbringer/window.rb

@@ -705,13 +705,11 @@ module Textbringer
       pos = @buffer.point + c.bytesize
       while nextc = @buffer.char_after(pos)
         case nextc
-        when /[\u{fe00}-\u{fe0f}\u{e0100}-\u{e01ef}]/ # variation selectors
+        when /\p{Variation_Selector}/
           c += nextc
         when /[\p{Mn}\p{Me}]/ # nonspacing & enclosing marks
           # Normalize パ (U+30CF + U+309A) to パ (U+30D1) so that curses can
           # caluculate display width correctly.
-          # Display combining marks by codepoint when characters cannot be
-          # combined by NFC.
           newc = (c + nextc).unicode_normalize(:nfc)
           return c if newc.size != c.size
           c = newc
@@ -769,17 +767,12 @@ module Textbringer
         s.gsub(/
           (?<ascii_control>[\0-\b\v-\x1f\x7f])
         | (?<nonascii_control>\p{C})
-        | (?<combining_diacritical_mark>[\u{0300}-\u{036f}])
-        | (?<other_special_char>[\p{M}\u{1100}-\u{11ff}])
+        | (?<other_special_char>[\p{M}\p{In_Hangul_Jamo}])
         /x) { |c|
           if $~[:ascii_control]
             "^" + (c.ord ^ 0x40).chr
           elsif $~[:nonascii_control]
             "<%04x>" % c.ord
-          elsif $~[:combining_diacritical_mark]
-            # Use U+00A0 as the base character, following the convention
-            # described in section 2.11.4 of Unicode Standard 16.0.0
-            "\u{00a0}#{c}"
           elsif $~[:other_special_char]
             FALLBACK_CHARACTERS[c] || c
           end

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: textbringer
 version: !ruby/object:Gem::Version
-  version: '2'
+  version: '3'
 platform: ruby
 authors:
 - Shugo Maeda
 bindir: exe
 cert_chain: []
-date: 2025-04-04 00:00:00.000000000 Z
+date: 2025-04-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rdoc