regexp-examples 1.1.3 → 1.1.4

data/lib/regexp-examples/repeaters.rb

@@ -1,4 +1,8 @@
 module RegexpExamples
+  # An abstract base class for all other repeater groups.
+  # Since all repeaters (quantifiers) are really just shorthand syntaxes for the generic:
+  # `/.{a,b}/`, the methods for generating "between `a` and `b` results" are fully
+  # generalised here.
   class BaseRepeater
     attr_reader :group, :min_repeats, :max_repeats
     def initialize(group)
@@ -6,7 +10,7 @@ module RegexpExamples
     end
 
     def result
-      group_results = group.result.first(RegexpExamples.MaxGroupResults)
+      group_results = group.result.first(RegexpExamples.max_group_results)
       results = []
       min_repeats.upto(max_repeats) do |repeats|
         if repeats.zero?
@@ -28,6 +32,9 @@ module RegexpExamples
     end
   end
 
+  # When there is "no repeater", we interpret this as a "one time repeater".
+  # For example, `/a/` is a "OneTimeRepeater" of "a"
+  # Equivalent to `/a{1}/`
   class OneTimeRepeater < BaseRepeater
     def initialize(group)
       super
@@ -36,22 +43,28 @@ module RegexpExamples
     end
   end
 
+  # When a klein star is used, e.g. `/a*/`
+  # Equivalent to `/a{0,}/`
   class StarRepeater < BaseRepeater
     def initialize(group)
       super
       @min_repeats = 0
-      @max_repeats = RegexpExamples.MaxRepeaterVariance
+      @max_repeats = RegexpExamples.max_repeater_variance
     end
   end
 
+  # When a plus is used, e.g. `/a+/`
+  # Equivalent to `/a{1,}/`
   class PlusRepeater < BaseRepeater
     def initialize(group)
       super
       @min_repeats = 1
-      @max_repeats = RegexpExamples.MaxRepeaterVariance + 1
+      @max_repeats = RegexpExamples.max_repeater_variance + 1
     end
   end
 
+  # When a question mark is used, e.g. `/a?/`
+  # Equivalent to `/a{0,1}/`
   class QuestionMarkRepeater < BaseRepeater
     def initialize(group)
       super
@@ -60,14 +73,15 @@ module RegexpExamples
     end
   end
 
+  # When a range is used, e.g. `/a{1}/`, `/a{1,}/`, `/a{1,3}/`, `/a{,3}/`
   class RangeRepeater < BaseRepeater
     def initialize(group, min, has_comma, max)
       super(group)
       @min_repeats = min || 0
-      if max # e.g. {1,100} --> Treat as {1,3} or similar, to prevent a huge number of results
-        @max_repeats = smallest(max, @min_repeats + RegexpExamples.MaxRepeaterVariance)
-      elsif has_comma # e.g. {2,} --> Treat as {2,4} or similar
-        @max_repeats = @min_repeats + RegexpExamples.MaxRepeaterVariance
+      if max # e.g. {1,100} --> Treat as {1,3} (by default max_repeater_variance)
+        @max_repeats = smallest(max, @min_repeats + RegexpExamples.max_repeater_variance)
+      elsif has_comma # e.g. {2,} --> Treat as {2,4} (by default max_repeater_variance)
+        @max_repeats = @min_repeats + RegexpExamples.max_repeater_variance
       else # e.g. {3} --> Treat as {3,3}
         @max_repeats = @min_repeats
       end

data/lib/regexp-examples/unicode_char_ranges.rb

@@ -1,6 +1,10 @@
 require 'pstore'
 
 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
     # These values were generated by: scripts/unicode_lister.rb
     # Note: Only the first 128 results are listed, for performance.

data/lib/regexp-examples/version.rb

@@ -1,3 +1,4 @@
+# Gem version
 module RegexpExamples
-  VERSION = '1.1.3'
+  VERSION = '1.1.4'
 end

data/lib/regexp-examples.rb

@@ -1,8 +1,8 @@
 require_relative 'regexp-examples/unicode_char_ranges'
-require_relative 'regexp-examples/backreferences'
 require_relative 'regexp-examples/chargroup_parser'
 require_relative 'regexp-examples/constants'
 require_relative 'regexp-examples/groups'
+require_relative 'regexp-examples/backreferences'
 require_relative 'regexp-examples/helpers'
 require_relative 'regexp-examples/parser'
 require_relative 'regexp-examples/repeaters'

data/regexp-examples.gemspec

@@ -3,14 +3,15 @@ require File.expand_path('../lib/regexp-examples/version', __FILE__)
 Gem::Specification.new do |s|
   s.name             = 'regexp-examples'
   s.version          = RegexpExamples::VERSION
-  s.summary          = "Extends the Regexp class with '#examples'"
+  s.summary          = "Extends the Regexp class with '#examples' and '#random_example'"
   s.description      =
-    'Regexp#examples returns a list of strings that are matched by the regex'
+    'Regexp#examples returns a list of "all" strings that are matched by the regex. '\
+      + 'Regexp#random_example returns one, random string that matches.'
   s.authors          = ['Tom Lord']
   s.email            = 'lord.thom@gmail.com'
   s.files            = `git ls-files -z`.split("\x0")
-  s.executables      = s.files.grep(%r{^bin/}) { |f| File.basename(f) }
-  s.test_files       = s.files.grep(%r{^(test|spec|features)/})
+  s.executables      = s.files.grep(/^bin\//) { |f| File.basename(f) }
+  s.test_files       = s.files.grep(/^(test|spec|features)\//)
   s.require_paths    = ['lib']
   s.homepage         =
     'http://rubygems.org/gems/regexp-examples'

data/scripts/unicode_lister.rb

@@ -9,17 +9,21 @@ require_relative '../lib/regexp-examples/unicode_char_ranges'
 
 # Taken from ruby documentation:
 # http://ruby-doc.org//core-2.2.0/Regexp.html#class-Regexp-label-Character+Properties
-NamedGroups = %w(
-  Alnum Alpha Blank Cntrl Digit Graph Lower Print Punct Space Upper XDigit Word ASCII Any Assigned
+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
+  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
+  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
@@ -48,7 +52,7 @@ count = 0
 filename = "./db/#{RegexpExamples::UnicodeCharRanges::STORE_FILENAME}"
 store = PStore.new(filename)
 store.transaction do
-  NamedGroups.each do |name|
+  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
@@ -57,7 +61,7 @@ store.transaction do
                      .select { |x| /\p{#{name}}/ =~ eval("?\\u{#{x.to_s(16)}}") }
                      .first(128)
     store[name.downcase] = calculate_ranges(matching_codes)
-    puts "(#{count}/#{NamedGroups.length}) Finished property: #{name}"
+    puts "(#{count}/#{NAMED_GROUPS.length}) Finished property: #{name}"
   end
   puts '*' * 50
   puts "Finished! Result stored in: #{filename}"

data/spec/helpers.rb

@@ -0,0 +1,18 @@
+# Common helper methods, for lots of tests
+# Included into the RSpec config, so accessible inside test blocks.
+module Helpers
+  def examples_exist(regexp, regexp_examples)
+    expect(regexp_examples)
+      .not_to be_empty, "No examples were generated for regexp: /#{regexp.source}/"
+  end
+
+  def examples_match(regexp, regexp_examples)
+    # Note: /\A...\z/ is used to prevent misleading examples from passing the test.
+    # For example, we don't want things like:
+    # /a*/.examples to include "xyz"
+    # /a|b/.examples to include "bad"
+    regexp_examples.each do |example|
+      expect(example).to match(/\A(?:#{regexp.source})\z/)
+    end
+  end
+end

data/spec/regexp-examples_spec.rb

@@ -3,17 +3,8 @@ RSpec.describe Regexp, '#examples' do
     regexps.each do |regexp|
       it "examples for /#{regexp.source}/" do
         regexp_examples = regexp.examples(max_group_results: 99_999)
-
-        expect(regexp_examples)
-          .not_to be_empty,
-            "No examples were generated for regexp: /#{regexp.source}/"
-        regexp_examples.each do |example|
-          expect(example).to match(/\A(?:#{regexp.source})\z/)
-        end
-        # Note: /\A...\z/ is used to prevent misleading examples from passing the test.
-        # For example, we don't want things like:
-        # /a*/.examples to include "xyz"
-        # /a|b/.examples to include "bad"
+        examples_exist(regexp, regexp_examples)
+        examples_match(regexp, regexp_examples)
       end
     end
   end
@@ -137,6 +128,7 @@ RSpec.describe Regexp, '#examples' do
     context 'for escaped octal characters' do
       examples_exist_and_match(
         /\10\20\30\40\50/,
+        /\00\07\100\177/,
         /\177123/ # Should work for numbers up to 177
       )
     end
@@ -144,7 +136,7 @@ RSpec.describe Regexp, '#examples' do
     context 'for complex patterns' do
       # Longer combinations of the above
       examples_exist_and_match(
-        /https?:\/\/(www\.)github\.com/,
+        %r{https?://(www\.)github\.com},
         /(I(N(C(E(P(T(I(O(N)))))))))*/,
         /[\w]{1}/,
         /((a?b*c+)) \1/,
@@ -208,7 +200,7 @@ RSpec.describe Regexp, '#examples' 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}}/"
+                    "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/)
@@ -304,8 +296,8 @@ RSpec.describe Regexp, '#examples' do
         it { expect(/a+|b?/.examples).to match_array ['a', 'aa', 'aaa', '', 'b'] }
 
         # Only display unique examples:
-        it { expect(/a|a|b|b/.examples).to match_array ['a', 'b'] }
-        it { expect(/[ccdd]/.examples).to match_array ['c', 'd'] }
+        it { expect(/a|a|b|b/.examples).to match_array %w(a b) }
+        it { expect(/[ccdd]/.examples).to match_array %w(c d) }
 
         # a{1}? should be equivalent to (?:a{1})?, i.e. NOT a "non-greedy quantifier"
         it { expect(/a{1}?/.examples).to match_array ['', 'a'] }

data/spec/regexp-random_example_spec.rb

@@ -5,14 +5,16 @@ RSpec.describe Regexp, '#random_example' do
         random_example = regexp.random_example
 
         expect(random_example).to be_a String # Not an Array!
-        expect(random_example).to match(Regexp.new("\\A(?:#{regexp.source})\\z", regexp.options))
+        expect(random_example)
+          .to match(Regexp.new("\\A(?:#{regexp.source})\\z", regexp.options))
       end
     end
   end
 
   context 'smoke tests' do
     # Just a few "smoke tests", to ensure the basic method isn't broken.
-    # Testing of the RegexpExamples::Parser class is all covered by Regexp#examples test already.
+    # Testing of the RegexpExamples::Parser class is all
+    # covered by Regexp#examples test already.
     random_example_matches(
       /\w{10}/,
       /(we(need(to(go(deeper)?)?)?)?) \1/,

data/spec/spec_helper.rb

@@ -2,9 +2,19 @@ require 'coveralls'
 Coveralls.wear!
 
 require './lib/regexp-examples.rb'
+require 'helpers'
 require 'pry'
 
+# Several of these tests (intentionally) use "weird" regex patterns,
+# that spam annoying warnings when running.
+# E.g. warning: invalid back reference: /\k/
+# and  warning: character class has ']' without escape: /[]]/ 
+# This config disables those warnings.
+$VERBOSE = nil
+
 RSpec.configure do |config|
+  config.include Helpers
+
   config.expect_with :rspec do |expectations|
     # This option will default to `true` in RSpec 4. It makes the `description`
     # and `failure_message` of custom matchers include text for helper methods

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: regexp-examples
 version: !ruby/object:Gem::Version
-  version: 1.1.3
+  version: 1.1.4
 platform: ruby
 authors:
 - Tom Lord
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-07-17 00:00:00.000000000 Z
+date: 2015-12-31 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -38,7 +38,8 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '10.0'
-description: Regexp#examples returns a list of strings that are matched by the regex
+description: Regexp#examples returns a list of "all" strings that are matched by the
+  regex. Regexp#random_example returns one, random string that matches.
 email: lord.thom@gmail.com
 executables: []
 extensions: []
@@ -56,6 +57,7 @@ files:
 - db/unicode_ranges_2.1.pstore
 - db/unicode_ranges_2.2.pstore
 - db/unicode_ranges_2.3.pstore
+- db/unicode_ranges_2.4.pstore
 - lib/core_extensions/regexp/examples.rb
 - lib/regexp-examples.rb
 - lib/regexp-examples/backreferences.rb
@@ -64,11 +66,17 @@ files:
 - lib/regexp-examples/groups.rb
 - lib/regexp-examples/helpers.rb
 - lib/regexp-examples/parser.rb
+- lib/regexp-examples/parser_helpers/charset_negation_helper.rb
+- lib/regexp-examples/parser_helpers/parse_after_backslash_group_helper.rb
+- lib/regexp-examples/parser_helpers/parse_group_helper.rb
+- 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/helpers.rb
 - spec/regexp-examples_spec.rb
 - spec/regexp-random_example_spec.rb
 - spec/spec_helper.rb
@@ -92,11 +100,12 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.4.6
+rubygems_version: 2.5.1
 signing_key: 
 specification_version: 4
-summary: Extends the Regexp class with '#examples'
+summary: Extends the Regexp class with '#examples' and '#random_example'
 test_files:
+- spec/helpers.rb
 - spec/regexp-examples_spec.rb
 - spec/regexp-random_example_spec.rb
 - spec/spec_helper.rb