Update comment in data-files to mention rake command

CHANGELOG.md

@@ -5,6 +5,12 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog],
 and this project adheres to [Semantic Versioning].
 
+## [Unreleased]
+
+### Fixed
+
+- Update comment in data-files to mention rake command. ([@skryukov])
+
 ## [0.2.2] - 2023-11-25
 
 ### Changed

README.md

@@ -260,6 +260,8 @@ To set directory for generated files, use `DEST_DIR` environment variable, e.g.
 
 Unicode data cached in the `tmp` directory by default, to change it, use `CACHE_DIR` environment variable, e.g. `CACHE_DIR=~/.cache/unicode_data bundle exec rake idna:generate`.
 
+_Note: `rake idna:generate` might generate different results on different versions of Ruby due to usage of built-in Unicode normalization methods._
+
 ### Inspect Unicode data
 
 To inspect Unicode data, run `bundle exec rake 'idna:inspect[<HEX_CODE>]'`.

lib/uri/idna/data/bidi_classes.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-# This file is automatically generated by bin/generate
+# This file is automatically generated by rake idna:generate
 # Unicode version 15.1.0
 
 module URI

lib/uri/idna/data/codepoint_classes.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-# This file is automatically generated by bin/generate
+# This file is automatically generated by rake idna:generate
 # Unicode version 15.1.0
 
 module URI

lib/uri/idna/data/joining_types.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-# This file is automatically generated by bin/generate
+# This file is automatically generated by rake idna:generate
 # Unicode version 15.1.0
 
 module URI

lib/uri/idna/data/leading_combiners.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-# This file is automatically generated by bin/generate
+# This file is automatically generated by rake idna:generate
 # Unicode version 15.1.0
 
 module URI

lib/uri/idna/data/scripts.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-# This file is automatically generated by bin/generate
+# This file is automatically generated by rake idna:generate
 # Unicode version 15.1.0
 
 module URI

lib/uri/idna/data/unicode_version.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-# This file is automatically generated by bin/generate
+# This file is automatically generated by rake idna:generate
 # Unicode version 15.1.0
 
 module URI

lib/uri/idna/data/uts46.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-# This file is automatically generated by bin/generate
+# This file is automatically generated by rake idna:generate
 # Unicode version 15.1.0
 
 module URI

lib/uri/idna/data/virama_combining_classes.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-# This file is automatically generated by bin/generate
+# This file is automatically generated by rake idna:generate
 # Unicode version 15.1.0
 
 module URI

tasks/idna_generator.rb

@@ -20,7 +20,8 @@ class IDNAGenerator < BaseGenerator
   def data
     @data ||= { bidi_classes: {}, codepoint_classes: {}, combiners: [], virama_combining_classes: [] }.tap do |hash|
       ucdata.codepoints do |cp|
-        next unless [cp.value].pack("U").valid_encoding?
+        # skip UTF-16 surrogates
+        next if cp.value >= 0xd800 && cp.value <= 0xdfff
 
         bidi_class = BIDI_MAPPING[cp.bidi_class] || "UNUSED"
         hash[:bidi_classes][bidi_class] ||= []

tasks/templates/bidi_classes.erb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-# This file is automatically generated by bin/generate
+# This file is automatically generated by rake idna:generate
 # Unicode version <%= ucdata.version %>
 
 module URI

tasks/templates/codepoint_classes.erb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-# This file is automatically generated by bin/generate
+# This file is automatically generated by rake idna:generate
 # Unicode version <%= ucdata.version %>
 
 module URI

tasks/templates/joining_types.erb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-# This file is automatically generated by bin/generate
+# This file is automatically generated by rake idna:generate
 # Unicode version <%= ucdata.version %>
 
 module URI

tasks/templates/leading_combiners.erb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-# This file is automatically generated by bin/generate
+# This file is automatically generated by rake idna:generate
 # Unicode version <%= ucdata.version %>
 
 module URI

tasks/templates/scripts.erb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-# This file is automatically generated by bin/generate
+# This file is automatically generated by rake idna:generate
 # Unicode version <%= ucdata.version %>
 
 module URI

tasks/templates/unicode_version.erb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-# This file is automatically generated by bin/generate
+# This file is automatically generated by rake idna:generate
 # Unicode version <%= ucdata.version %>
 
 module URI

tasks/templates/uts46.erb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-# This file is automatically generated by bin/generate
+# This file is automatically generated by rake idna:generate
 # Unicode version <%= ucdata.version %>
 
 module URI

tasks/templates/virama_combining_classes.erb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-# This file is automatically generated by bin/generate
+# This file is automatically generated by rake idna:generate
 # Unicode version <%= ucdata.version %>
 
 module URI