regexp-examples 1.5.1 → 1.6.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 38fbbe3d506284921194e15fded3d672d114212223e46cc380bba3f0f669b432
-  data.tar.gz: d0c47861293efcf61aa4f0d7ce3eee05aac8e57c43affe9a0e58af61e8cbc50b
+  metadata.gz: d1bdebf385885ec8033d7f7b34d5d473837c7ae983b4fbda4facb45f8bbc96a0
+  data.tar.gz: 79b2c7a8c76ebe3e3d6d2e0d6ee12ffaefc5a86acdbe69d8d5476afab1c25f96
 SHA512:
-  metadata.gz: 989d3c74e5120a0612d340b3919e511b8aad3eabc06a5c939bab2deb724f0168644af75f4e47c5b5c577689df768c8414ac1c93a1e1d4cf0885f75a8a983d1ca
-  data.tar.gz: 8125cb96126af56ce2fc283e47da4963706e86f11f9fa287c8fdd4b495514852c6ab64aad061ce60a19160694eea39382621cfda56ad92808d2f4fc855f0448d
+  metadata.gz: 5858e4813711b88549a2237857f23db0c941b5d3f9fd88275ab83b7b0e2002b854bbfa774d0d8c05e99df9098b2935f03346823df2f57819159f30c9d36e9767
+  data.tar.gz: 126a04b363ed23ef0e4ea4ee5f36f40b20280e44e8892985f87f0eef391ddcb20c2299a87324b15693aa02c5ab2eb484c8d2622889f057a5b1b29f82fed73c7b

data/.ruby-version

@@ -1 +1 @@
-2.6.3
+3.1.2

data/.travis.yml

@@ -1,10 +1,12 @@
 language: ruby
+cache: bundler
 rvm:
   - 2.4.5
   - 2.5.5
   - 2.6.2 # Uses unicode 12.0.0
   - 2.6.3 # Uses unicode 12.1.0
-  - 2.7.0
+  - 2.7.2
+  - 3.0.0
   - ruby-head
 matrix:
   allow_failures:

data/Gemfile

@@ -3,7 +3,6 @@ source 'https://rubygems.org'
 group :test do
   gem 'rspec'
   gem 'coveralls', require: false
-  gem 'pry'
 end
 
 # Specify your gem's dependencies in regexp-examples.gemspec

data/README.md

@@ -52,7 +52,7 @@ Obviously, you will get different (random) results if you try these yourself!
 ```
 
 ## Supported ruby versions
-MRI 2.4.0 (oldest non-[EOL](https://www.ruby-lang.org/en/news/2019/03/31/support-of-ruby-2-3-has-ended/) version) --> 2.6.3 (latest stable version)
+MRI 2.4.0 (oldest non-[EOL](https://www.ruby-lang.org/en/news/2019/03/31/support-of-ruby-2-3-has-ended/) version) --> 3.0.0 (latest stable version)
 
 MRI 2.0.0 --> 2.3.x were supported until version `1.5.0` of this library. Support was dropped primarily
 because of the need to use `RbConfig::CONFIG['UNICODE_VERSION']`, which was added to ruby version `2.4.0`.

data/lib/regexp-examples/char_sets.rb

@@ -53,7 +53,5 @@ module RegexpExamples
       'word'   => Word,
       'ascii'  => Any
     }.freeze
-
-    NamedPropertyCharMap = UnicodeCharRanges.instance
   end.freeze
 end

data/lib/regexp-examples/parser_helpers/charset_negation_helper.rb

@@ -2,7 +2,7 @@
 module RegexpExamples
   module CharsetNegationHelper
     def negate_if(charset, is_negative)
-      is_negative ? (CharSets::Any.dup - charset) : charset
+      is_negative ? (CharSets::Any.dup - charset.to_a) : charset
     end
   end
 end

data/lib/regexp-examples/parser_helpers/parse_after_backslash_group_helper.rb

@@ -1,3 +1,5 @@
+require 'regexp_property_values'
+
 module RegexpExamples
   # A collection of related helper methods, utilised by the `Parser` class
   module ParseAfterBackslashGroupHelper
@@ -91,13 +93,19 @@ module RegexpExamples
     end
 
     def parse_backslash_named_property(p_negation, caret_negation, property_name)
-      @current_position += (caret_negation.length + # 0 or 1, of '^' is present
+      @current_position += (caret_negation.length + # 0 or 1, if '^' is present
                             property_name.length +
                             2) # Length of opening and closing brackets (always 2)
       # Beware of double negatives! E.g. /\P{^Space}/
       is_negative = (p_negation == 'P') ^ (caret_negation == '^')
       CharGroup.new(
-        negate_if(CharSets::NamedPropertyCharMap[property_name.downcase], is_negative),
+        negate_if(
+          RegexpPropertyValues[property_name]
+            .matched_codepoints
+            .lazy
+            .filter_map { |cp| cp.chr('utf-8') unless cp.between?(0xD800, 0xDFFF) },
+          is_negative
+        ),
         @ignorecase
       )
     end

data/lib/regexp-examples/version.rb

@@ -1,4 +1,4 @@
 # Gem version
 module RegexpExamples
-  VERSION = '1.5.1'.freeze
+  VERSION = '1.6.0'.freeze
 end

data/lib/regexp-examples.rb

@@ -1,4 +1,3 @@
-require_relative 'regexp-examples/unicode_char_ranges'
 require_relative 'regexp-examples/chargroup_parser'
 require_relative 'regexp-examples/config'
 require_relative 'regexp-examples/char_sets'
@@ -8,6 +7,5 @@ require_relative 'regexp-examples/max_results_limiter'
 require_relative 'regexp-examples/helpers'
 require_relative 'regexp-examples/parser'
 require_relative 'regexp-examples/repeaters'
-require_relative 'regexp-examples/unicode_char_ranges'
 require_relative 'regexp-examples/version'
 require_relative 'core_extensions/regexp/examples'

data/regexp-examples.gemspec

@@ -14,9 +14,10 @@ Gem::Specification.new do |s|
   s.test_files       = s.files.grep(/^(test|spec|features)\//)
   s.require_paths    = ['lib']
   s.homepage         = 'http://rubygems.org/gems/regexp-examples'
-  s.add_development_dependency 'bundler', '> 1.7'
-  s.add_development_dependency 'rake', '~> 12.0'
-  s.add_development_dependency 'pry', '~> 0.12.0'
+  s.add_dependency 'regexp_property_values', '~> 1.5'
+  s.add_development_dependency 'bundler', '~> 2.4'
+  s.add_development_dependency 'rake', '~> 13.0'
+  s.add_development_dependency 'pry'
   s.add_development_dependency 'warning', '~> 0.10.0'
   s.license          = 'MIT'
   s.required_ruby_version = '>= 2.4.0'

data/spec/regexp-examples_spec.rb

@@ -190,37 +190,24 @@ RSpec.describe Regexp, '#examples' do
         /\P{Ll}/, # Negation syntax type 2
         /\P{^Ll}/ # Double negation!! (Should cancel out)
       )
-      # An exhaustive set of tests for all named properties!!! This is useful
-      # for verifying the PStore contains correct values for all ruby versions
-      %w[
-        Alnum Alpha Blank Cntrl Digit Graph Lower Print Punct Space Upper XDigit
-        Word ASCII Any Assigned L Ll Lm Lo Lt Lu M Mn Mc Me N Nd Nl No P Pc Pd
-        Ps Pe Pi Pf Po S Sm Sc Sk So Z Zs Zl Zp C Cc Cf Cn Co Arabic Armenian
-        Balinese Bengali Bopomofo Braille Buginese Buhid Canadian_Aboriginal
-        Cham Cherokee Common Coptic Cyrillic Devanagari Ethiopic Georgian
-        Glagolitic Greek Gujarati Gurmukhi Han Hangul Hanunoo Hebrew Hiragana
-        Inherited Kannada Katakana Kayah_Li Khmer Lao Latin Lepcha Limbu Malayalam
-        Mongolian Myanmar New_Tai_Lue Nko Ogham Ol_Chiki Oriya Phags_Pa Rejang
-        Runic Saurashtra Sinhala Sundanese Syloti_Nagri Syriac Tagalog Tagbanwa
-        Tai_Le Tamil Telugu Thaana Thai Tibetan Tifinagh Vai Yi
-      ].each do |property|
-        it "examples for /\p{#{property}}/" do
-          regexp_examples = /\p{#{property}}/.examples(max_group_results: 99_999)
-          expect(regexp_examples)
-            .not_to be_empty,
-                    "No examples were generated for regexp: /\p{#{property}}/"
-          # Just do one big check, for test system performance (~30% faster)
-          # (Otherwise, we're doing up to 128 checks on 123 properties!!!)
-          expect(regexp_examples.join('')).to match(/\A\p{#{property}}+\z/)
-        end
-      end
 
-      # The following seem to genuinely have no matching examples (!!??!!?!)
-      %w[
-        Cs Carian Cuneiform Cypriot Deseret Gothic Kharoshthi Linear_B Lycian
-        Lydian Old_Italic Old_Persian Osmanya Phoenician Shavian Ugaritic
-      ].each do |property|
-        examples_are_empty(/\p{#{property}}/)
+      expected_empty_properties = %w[surrogate inlowsurrogates inhighsurrogates inhighprivateusesurrogates]
+
+      RegexpPropertyValues.all_for_current_ruby.map(&:identifier).each do |property|
+        if(expected_empty_properties).include?(property)
+          examples_are_empty(/\p{#{property}}/)
+        else
+          it "examples for /\p{#{property}}/" do
+            regexp_examples = /\p{#{property}}/.examples(max_group_results: 99_999)
+
+            expect(regexp_examples)
+              .not_to be_empty,
+            "No examples were generated for regexp: /\p{#{property}}/"
+              # Just do one big check, for test system performance (~30% faster)
+              # (Otherwise, we're potentially doing 99999 checks on 123 properties!!!)
+              expect(regexp_examples.join('')).to match(/\A\p{#{property}}+\z/)
+          end
+        end
       end
     end
 

metadata

@@ -1,57 +1,71 @@
 --- !ruby/object:Gem::Specification
 name: regexp-examples
 version: !ruby/object:Gem::Version
-  version: 1.5.1
+  version: 1.6.0
 platform: ruby
 authors:
 - Tom Lord
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-01-09 00:00:00.000000000 Z
+date: 2024-05-20 00:00:00.000000000 Z
 dependencies:
+- !ruby/object:Gem::Dependency
+  name: regexp_property_values
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.5'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.5'
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">"
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.7'
+        version: '2.4'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">"
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.7'
+        version: '2.4'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '12.0'
+        version: '13.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '12.0'
+        version: '13.0'
 - !ruby/object:Gem::Dependency
   name: pry
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 0.12.0
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 0.12.0
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: warning
   requirement: !ruby/object:Gem::Requirement
@@ -103,10 +117,8 @@ files:
 - lib/regexp-examples/parser_helpers/parse_multi_group_helper.rb
 - lib/regexp-examples/parser_helpers/parse_repeater_helper.rb
 - lib/regexp-examples/repeaters.rb
-- lib/regexp-examples/unicode_char_ranges.rb
 - lib/regexp-examples/version.rb
 - regexp-examples.gemspec
-- scripts/unicode_lister.rb
 - spec/config_spec.rb
 - spec/gem_helper.rb
 - spec/helpers.rb
@@ -118,7 +130,7 @@ homepage: http://rubygems.org/gems/regexp-examples
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -133,8 +145,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.3
-signing_key: 
+rubygems_version: 3.3.7
+signing_key:
 specification_version: 4
 summary: Extends the Regexp class with '#examples' and '#random_example'
 test_files:

data/lib/regexp-examples/unicode_char_ranges.rb

@@ -1,59 +0,0 @@
-require 'pstore'
-require 'singleton'
-
-module RegexpExamples
-  # Interface to the retrieve the character sets that match a regex named property.
-  # E.g. `/\p{Alpha}/`
-  # These matching values are stored, compressed, in a PStore. They are specific to
-  # the ruby minor version.
-  class UnicodeCharRanges
-    include Singleton
-    # These values were generated by: scripts/unicode_lister.rb
-    # Note: Only the first 128 results are listed, for performance.
-    # Also, some groups seem to have no matches (weird!)
-    STORE_FILENAME = "unicode_ranges_#{RbConfig::CONFIG['UNICODE_VERSION']}.pstore".freeze
-
-    attr_reader :range_store
-
-    def initialize
-      @range_store = PStore.new(unicode_ranges_file)
-    end
-
-    def get(key)
-      range_store.transaction(true) do
-        ranges_to_unicode(range_store[key])
-      end
-    end
-
-    alias [] get
-
-    private
-
-    # The method is written like this to future-proof it a little,
-    # i.e. the gem won't completely break for a new ruby version release
-    def unicode_ranges_file
-      db_path = File.join(__dir__, '../../db')
-      Dir["#{db_path}/*.pstore"].sort.select do |file|
-        file <= "#{db_path}/#{STORE_FILENAME}"
-      end.last
-    end
-
-    # TODO: Document example input/output of this method
-    # It's pretty simple, but this code is a little confusing!!
-    def ranges_to_unicode(ranges)
-      result = []
-      ranges.each do |range|
-        if range.is_a? Integer # Small hack to increase data compression
-          result << hex_to_unicode(range.to_s(16))
-        else
-          range.each { |num| result << hex_to_unicode(num.to_s(16)) }
-        end
-      end
-      result
-    end
-
-    def hex_to_unicode(hex)
-      [hex.to_i(16)].pack('U')
-    end
-  end
-end

data/scripts/unicode_lister.rb

@@ -1,68 +0,0 @@
-require 'pstore'
-require_relative '../lib/regexp-examples/unicode_char_ranges'
-# A script to generate lists of all unicode characters
-# that match all named group/character properties regexps.
-# For use in e.g. /\p{Arabic}/.examples
-
-# To (re-)generate this list, simply run this file!
-# > ruby scripts/unicode_lister.rb
-
-# Taken from ruby documentation:
-# http://ruby-doc.org//core-2.2.0/Regexp.html#class-Regexp-label-Character+Properties
-NAMED_GROUPS = %w(
-  Alnum Alpha Blank Cntrl Digit Graph Lower Print Punct Space Upper XDigit Word ASCII
-  Any Assigned
-
-  L Ll Lm Lo Lt Lu M Mn Mc Me N Nd Nl No P Pc Pd Ps Pe Pi Pf Po S Sm Sc Sk So Z Zs Zl
-  Zp C Cc Cf Cn Co Cs
-
-  Arabic Armenian Balinese Bengali Bopomofo Braille Buginese Buhid Canadian_Aboriginal
-  Carian Cham Cherokee Common Coptic Cuneiform Cypriot Cyrillic Deseret Devanagari
-  Ethiopic Georgian Glagolitic Gothic Greek Gujarati Gurmukhi Han Hangul Hanunoo Hebrew
-  Hiragana Inherited Kannada Katakana Kayah_Li Kharoshthi Khmer Lao Latin Lepcha Limbu
-  Linear_B Lycian Lydian Malayalam Mongolian Myanmar New_Tai_Lue Nko Ogham Ol_Chiki
-  Old_Italic Old_Persian Oriya Osmanya Phags_Pa Phoenician Rejang Runic Saurashtra
-  Shavian Sinhala Sundanese Syloti_Nagri Syriac Tagalog Tagbanwa Tai_Le Tamil Telugu
-  Thaana Thai Tibetan Tifinagh Ugaritic Vai Yi
-)
-
-# Note: For the range 55296..57343, these are reserved values that are not legal
-# unicode characters.
-# I.e. a character encoding-related exception gets raised when you do:
-# `/regex/ =~ eval("?\\u{#{x.to_s(16)}}")`
-# TODO: Add a link to somewhere that explains this better.
-
-# "Compresses" the values in an array by using ranges.
-# Example input: [1, 2, 3, 4, 6, 7, 12, 14]
-# Example output: [1..4, 6..7, 12, 14]
-def calculate_ranges(matching_codes)
-  return [] if matching_codes.empty?
-  first = matching_codes.shift
-  matching_codes.inject([first..first]) do |r, x|
-    if r.last.last.succ != x
-      r << (x..x) # Start new range
-    else
-      r[0..-2] << (r.last.first..x) # Update last range
-    end
-  end
-    .map { |range| range.size == 1 ? range.first : range } # Replace `int..int` with `int`
-end
-
-count = 0
-filename = "./db/#{RegexpExamples::UnicodeCharRanges::STORE_FILENAME}"
-store = PStore.new(filename)
-store.transaction do
-  NAMED_GROUPS.each do |name|
-    count += 1
-    # Only generating first 128 matches, for performance...
-    # (I have tried this with generating ALL examples, and it makes the ruby gem
-    # painfully slow and bloated... Especially the test suite.)
-    matching_codes = [(0..55_295), (57_344..65_535)].map(&:to_a).flatten.lazy
-                     .select { |x| /\p{#{name}}/ =~ eval("?\\u{#{x.to_s(16)}}") }
-                     .first(128)
-    store[name.downcase] = calculate_ranges(matching_codes)
-    puts "(#{count}/#{NAMED_GROUPS.length}) Finished property: #{name}"
-  end
-  puts '*' * 50
-  puts "Finished! Result stored in: #{filename}"
-end