regexp_parser 1.7.1 → 2.1.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: dd872b22bf04a288790ef0f73df9041f14fb88a08c2a03852d9dbbc238b452d6
-  data.tar.gz: 4641097a24b5fa0f7b0c8e5aacc152587fe8b15d30f3f78bbec8157887b8b897
+  metadata.gz: 077b8a0c90d90cf46e44671ec1335a5373eef72c61a0bcf4de43ba5217a188c3
+  data.tar.gz: b9aed868af73adcdf40c09720c5d10091b25a53b25a792717ceb5591039a2931
 SHA512:
-  metadata.gz: 858570df4a7047a2d8b09555b56de28a66ca4f8022e596c249900f5312f8e7fb9376384ca816bc3c08f3e324930702ad410a28b5be680adea6867e1f8075441e
-  data.tar.gz: 0d70e7b4f18739826bb334fb305e335e44a354ae302214ca3c1884f66ace8680e48a9e4c64b890b220b82056da761084413c8b9b8c5e363382f5cf165b3d3448
+  metadata.gz: 9c04d9a6434c6e3f322e97e8e2a1c86b3ddda88bd8821368a37b92f5836e4c3df1dc27a79165303420c3e8d5eea31bda1483824da01a40ce30961b645ba65ddd
+  data.tar.gz: 01e5c261e9dca0c4df7c696128dbc0520ca40aa6b9393cc8d6c3bdb8386470aeb773566000b811f98c1407038216c8d2c0b444c7955ea5a881ac759796f8a440

data/CHANGELOG.md

@@ -1,5 +1,143 @@
 ## [Unreleased]
 
+## [2.1.1] - 2021-02-23 - [Janosch Müller](mailto:janosch84@gmail.com)
+
+### Fixed
+
+- fixed `NameError` when requiring only `'regexp_parser/scanner'` in v2.1.0
+  * thanks to [Jared White and Sam Ruby](https://github.com/ruby2js/ruby2js) for the report
+
+## [2.1.0] - 2021-02-22 - [Janosch Müller](mailto:janosch84@gmail.com)
+
+### Added
+
+- common ancestor for all scanning/parsing/lexing errors
+  * `Regexp::Parser::Error` can now be rescued as a catch-all
+  * the following errors (and their many descendants) now inherit from it:
+    - `Regexp::Expression::Conditional::TooManyBranches`
+    - `Regexp::Parser::ParserError`
+    - `Regexp::Scanner::ScannerError`
+    - `Regexp::Scanner::ValidationError`
+    - `Regexp::Syntax::SyntaxError`
+  * it replaces `ArgumentError` in some rare cases (`Regexp::Parser.parse('?')`)
+  * thanks to [sandstrom](https://github.com/sandstrom) for the cue
+
+### Fixed
+
+- fixed scanning of whole-pattern recursion calls `\g<0>` and `\g'0'`
+  * a regression in v2.0.1 had caused them to be scanned as literals
+- fixed scanning of some backreference and subexpression call edge cases
+  * e.g. `\k<+1>`, `\g<x-1>`
+- fixed tokenization of some escapes in character sets
+  * `.`, `|`, `{`, `}`, `(`, `)`, `^`, `$`, `?`, `+`, `*`
+  * all of these correctly emitted `#type` `:literal` and `#token` `:literal` if *not* escaped
+  * if escaped, they emitted e.g. `#type` `:escape` and `#token` `:group_open` for `[\(]`
+  * the escaped versions now correctly emit `#type` `:escape` and `#token` `:literal`
+- fixed handling of control/metacontrol escapes in character sets
+  * e.g. `[\cX]`, `[\M-\C-X]`
+  * they were misread as bunch of individual literals, escapes, and ranges
+- fixed some cases where calling `#dup`/`#clone` on expressions led to shared state
+
+## [2.0.3] - 2020-12-28 - [Janosch Müller](mailto:janosch84@gmail.com)
+
+### Fixed
+
+- fixed error when scanning some unlikely and redundant but valid charset patterns
+  * e.g. `/[[.a-b.]]/`, `/[[=e=]]/`,
+- fixed ancestry of some error classes related to syntax version lookup
+  * `NotImplementedError`, `InvalidVersionNameError`, `UnknownSyntaxNameError`
+  * they now correctly inherit from `Regexp::Syntax::SyntaxError` instead of Rubys `::SyntaxError`
+
+## [2.0.2] - 2020-12-25 - [Janosch Müller](mailto:janosch84@gmail.com)
+
+### Fixed
+
+- fixed `FrozenError` when calling `#to_s` on a frozen `Group::Passive`
+  * thanks to [Daniel Gollahon](https://github.com/dgollahon)
+
+## [2.0.1] - 2020-12-20 - [Janosch Müller](mailto:janosch84@gmail.com)
+
+### Fixed
+
+- fixed error when scanning some group names
+  * this affected names containing hyphens, digits or multibyte chars, e.g. `/(?<a1>a)/`
+  * thanks to [Daniel Gollahon](https://github.com/dgollahon) for the report
+- fixed error when scanning hex escapes with just one hex digit
+  * e.g. `/\x0A/` was scanned correctly, but the equivalent `/\xA/` was not
+  * thanks to [Daniel Gollahon](https://github.com/dgollahon) for the report
+
+## [2.0.0] - 2020-11-25 - [Janosch Müller](mailto:janosch84@gmail.com)
+
+### Changed
+
+- some methods that used to return byte-based indices now return char-based indices
+  * the returned values have only changed for Regexps that contain multibyte chars
+  * this is only a breaking change if you used such methods directly AND relied on them pointing to bytes
+  * affected methods:
+  * `Regexp::Token` `#length`, `#offset`, `#te`, `#ts`
+  * `Regexp::Expression::Base` `#full_length`, `#offset`, `#starts_at`, `#te`, `#ts`
+  * thanks to [Akinori MUSHA](https://github.com/knu) for the report
+- removed some deprecated methods/signatures
+  * these are rarely used and have been showing deprecation warnings for a long time
+  * `Regexp::Expression::Subexpression.new` with 3 arguments
+  * `Regexp::Expression::Root.new` without a token argument
+  * `Regexp::Expression.parsed`
+
+### Added
+
+- `Regexp::Expression::Base#base_length`
+  * returns the character count of an expression body, ignoring any quantifier
+- pragmatic, experimental support for chained quantifiers
+  * e.g.: `/^a{10}{4,6}$/` matches exactly 40, 50 or 60 `a`s
+  * successive quantifiers used to be silently dropped by the parser
+  * they are now wrapped with passive groups as if they were written `(?:a{10}){4,6}`
+  * thanks to [calfeld](https://github.com/calfeld) for reporting this a while back
+
+### Fixed
+
+- incorrect encoding output for non-ascii comments
+  * this led to a crash when calling `#to_s` on parse results containing such comments
+  * thanks to [Michael Glass](https://github.com/michaelglass) for the report
+- some crashes when scanning contrived patterns such as `'\😋'`
+
+### [1.8.2] - 2020-10-11 - [Janosch Müller](mailto:janosch84@gmail.com)
+
+### Fixed
+
+- fix `FrozenError` in `Expression::Base#repetitions` on Ruby 3.0
+  * thanks to [Thomas Walpole](https://github.com/twalpole)
+- removed "unknown future version" warning on Ruby 3.0
+
+### [1.8.1] - 2020-09-28 - [Janosch Müller](mailto:janosch84@gmail.com)
+
+### Fixed
+
+- fixed scanning of comment-like text in normal mode
+  * this was an old bug, but had become more prevalent in v1.8.0
+  * thanks to [Tietew](https://github.com/Tietew) for the report
+- specified correct minimum Ruby version in gemspec
+  * it said 1.9 but really required 2.0 as of v1.8.0
+
+### [1.8.0] - 2020-09-20 - [Janosch Müller](mailto:janosch84@gmail.com)
+
+### Changed
+
+- dropped support for running on Ruby 1.9.x
+
+### Added
+
+- regexp flags can now be passed when parsing a `String` as regexp body
+  * see the [README](/README.md#usage) for details
+  * thanks to [Owen Stephens](https://github.com/owst)
+- bare occurrences of `\g` and `\k` are now allowed and scanned as literal escapes
+  * matches Onigmo behavior
+  * thanks for the report to [Marc-André Lafortune](https://github.com/marcandre)
+
+### Fixed
+
+- fixed parsing comments without preceding space or trailing newline in x-mode
+  * thanks to [Owen Stephens](https://github.com/owst)
+
 ### [1.7.1] - 2020-06-07 - [Ammar Ali](mailto:ammarabuali@gmail.com)
 
 ### Fixed

data/Gemfile

@@ -3,7 +3,12 @@ source 'https://rubygems.org'
 gemspec
 
 group :development, :test do
+  gem 'ice_nine', '~> 0.11.2'
   gem 'rake', '~> 13.0'
   gem 'regexp_property_values', '~> 1.0'
-  gem 'rspec', '~> 3.8'
+  gem 'rspec', '~> 3.10'
+  if RUBY_VERSION.to_f >= 2.7
+    gem 'gouteur'
+    gem 'rubocop', '~> 1.7'
+  end
 end

data/README.md

@@ -1,6 +1,6 @@
 # Regexp::Parser
 
-[![Gem Version](https://badge.fury.io/rb/regexp_parser.svg)](http://badge.fury.io/rb/regexp_parser) [![Build Status](https://secure.travis-ci.org/ammar/regexp_parser.svg?branch=master)](http://travis-ci.org/ammar/regexp_parser) [![Code Climate](https://codeclimate.com/github/ammar/regexp_parser.svg)](https://codeclimate.com/github/ammar/regexp_parser/badges)
+[![Gem Version](https://badge.fury.io/rb/regexp_parser.svg)](http://badge.fury.io/rb/regexp_parser) [![Build Status](https://github.com/ammar/regexp_parser/workflows/tests/badge.svg)](https://github.com/ammar/regexp_parser/actions) [![Build Status](https://github.com/ammar/regexp_parser/workflows/gouteur/badge.svg)](https://github.com/ammar/regexp_parser/actions) [![Code Climate](https://codeclimate.com/github/ammar/regexp_parser.svg)](https://codeclimate.com/github/ammar/regexp_parser/badges)
 
 A Ruby gem for tokenizing, parsing, and transforming regular expressions.
 
@@ -8,8 +8,8 @@ A Ruby gem for tokenizing, parsing, and transforming regular expressions.
   * A scanner/tokenizer based on [Ragel](http://www.colm.net/open-source/ragel/)
   * A lexer that produces a "stream" of token objects.
   * A parser that produces a "tree" of Expression objects (OO API)
-* Runs on Ruby 1.9, 2.x, and JRuby (1.9 mode) runtimes.
-* Recognizes Ruby 1.8, 1.9, and 2.x regular expressions [See Supported Syntax](#supported-syntax)
+* Runs on Ruby 2.x, 3.x and JRuby runtimes
+* Recognizes Ruby 1.8, 1.9, 2.x and 3.x regular expressions [See Supported Syntax](#supported-syntax)
 
 
 _For examples of regexp_parser in use, see [Example Projects](#example-projects)._
@@ -18,13 +18,10 @@ _For examples of regexp_parser in use, see [Example Projects](#example-projects)
 ---
 ## Requirements
 
-* Ruby >= 1.9
+* Ruby >= 2.0
 * Ragel >= 6.0, but only if you want to build the gem or work on the scanner.
 
 
-_Note: See the .travis.yml file for covered versions._
-
-
 ---
 ## Install
 
@@ -72,6 +69,17 @@ called with the results as follows:
 * **Parser**: after completion, the block gets passed the root expression.
   _The result of the block is returned._
 
+All three methods accept either a `Regexp` or `String` (containing the pattern)
+- if a String is passed, `options` can be supplied:
+
+```ruby
+require 'regexp_parser'
+
+Regexp::Parser.parse(
+  "a+ # Recognises a and A...",
+  options: ::Regexp::EXTENDED | ::Regexp::IGNORECASE
+)
+```
 
 ---
 ## Components
@@ -306,7 +314,7 @@ Expression class. See the next section for details._
 
 ## Supported Syntax
 The three modules support all the regular expression syntax features of Ruby 1.8,
-1.9, and 2.x:
+1.9, 2.x and 3.x:
 
 _Note that not all of these are available in all versions of Ruby_
 
@@ -429,13 +437,17 @@ rake install
 ## Example Projects
 Projects using regexp_parser.
 
+- [capybara](https://github.com/teamcapybara/capybara) is an integration testing tool that uses regexp_parser to convert Regexps to css/xpath selectors.
+
+- [js_regex](https://github.com/janosch-x/js_regex) converts Ruby regular expressions to JavaScript-compatible regular expressions.
+
 - [meta_re](https://github.com/ammar/meta_re) is a regular expression preprocessor with alias support.
 
 - [mutant](https://github.com/mbj/mutant) (before v0.9.0) manipulates your regular expressions (amongst others) to see if your tests cover their behavior.
 
-- [twitter-cldr-rb](https://github.com/twitter/twitter-cldr-rb) uses regexp_parser to generate examples of postal codes.
+- [rubocop](https://github.com/rubocop-hq/rubocop) is a linter for Ruby that uses regexp_parser to lint Regexps.
 
-- [js_regex](https://github.com/janosch-x/js_regex) converts Ruby regular expressions to JavaScript-compatible regular expressions.
+- [twitter-cldr-rb](https://github.com/twitter/twitter-cldr-rb) is a localization helper that uses regexp_parser to generate examples of postal codes.
 
 
 ## References
@@ -464,4 +476,4 @@ Documentation and books used while working on this project.
 
 ---
 ##### Copyright
-_Copyright (c) 2010-2019 Ammar Ali. See LICENSE file for details._
+_Copyright (c) 2010-2020 Ammar Ali. See LICENSE file for details._

data/Rakefile

@@ -7,8 +7,8 @@ require 'bundler'
 require 'rubygems/package_task'
 
 
-RAGEL_SOURCE_DIR = File.expand_path '../lib/regexp_parser/scanner', __FILE__
-RAGEL_OUTPUT_DIR = File.expand_path '../lib/regexp_parser', __FILE__
+RAGEL_SOURCE_DIR = File.join(__dir__, 'lib/regexp_parser/scanner')
+RAGEL_OUTPUT_DIR = File.join(__dir__, 'lib/regexp_parser')
 RAGEL_SOURCE_FILES = %w{scanner} # scanner.rl includes property.rl
 
 
@@ -25,11 +25,11 @@ end
 
 namespace :ragel do
   desc "Process the ragel source files and output ruby code"
-  task :rb do |t|
-    RAGEL_SOURCE_FILES.each do |file|
-      output_file = "#{RAGEL_OUTPUT_DIR}/#{file}.rb"
+  task :rb do
+    RAGEL_SOURCE_FILES.each do |source_file|
+      output_file = "#{RAGEL_OUTPUT_DIR}/#{source_file}.rb"
       # using faster flat table driven FSM, about 25% larger code, but about 30% faster
-      sh "ragel -F1 -R #{RAGEL_SOURCE_DIR}/#{file}.rl -o #{output_file}"
+      sh "ragel -F1 -R #{RAGEL_SOURCE_DIR}/#{source_file}.rl -o #{output_file}"
 
       contents = File.read(output_file)
 
@@ -42,7 +42,7 @@ namespace :ragel do
   end
 
   desc "Delete the ragel generated source file(s)"
-  task :clean do |t|
+  task :clean do
     RAGEL_SOURCE_FILES.each do |file|
       sh "rm -f #{RAGEL_OUTPUT_DIR}/#{file}.rb"
     end
@@ -61,7 +61,7 @@ namespace :props do
   task :update do
     require 'regexp_property_values'
     RegexpPropertyValues.update
-    dir = File.expand_path('../lib/regexp_parser/scanner/properties', __FILE__)
+    dir = File.join(__dir__, 'lib/regexp_parser/scanner/properties')
 
     require 'psych'
     write_hash_to_file = ->(hash, path) do

data/lib/regexp_parser/error.rb

@@ -0,0 +1,4 @@
+class Regexp::Parser
+  # base class for all gem-specific errors (inherited but never raised itself)
+  class Error < StandardError; end
+end

data/lib/regexp_parser/expression.rb

@@ -1,5 +1,6 @@
-module Regexp::Expression
+require 'regexp_parser/error'
 
+module Regexp::Expression
   class Base
     attr_accessor :type, :token
     attr_accessor :text, :ts
@@ -21,7 +22,7 @@ module Regexp::Expression
       self.options           = options
     end
 
-    def initialize_clone(orig)
+    def initialize_copy(orig)
       self.text       = (orig.text       ? orig.text.dup         : nil)
       self.options    = (orig.options    ? orig.options.dup      : nil)
       self.quantifier = (orig.quantifier ? orig.quantifier.clone : nil)
@@ -34,6 +35,10 @@ module Regexp::Expression
 
     alias :starts_at :ts
 
+    def base_length
+      to_s(:base).length
+    end
+
     def full_length
       to_s.length
     end
@@ -80,8 +85,12 @@ module Regexp::Expression
       return 1..1 unless quantified?
       min = quantifier.min
       max = quantifier.max < 0 ? Float::INFINITY : quantifier.max
-      # fix Range#minmax - https://bugs.ruby-lang.org/issues/15807
-      (min..max).tap { |r| r.define_singleton_method(:minmax) { [min, max] } }
+      range = min..max
+      # fix Range#minmax on old Rubies - https://bugs.ruby-lang.org/issues/15807
+      if RUBY_VERSION.to_f < 2.7
+        range.define_singleton_method(:minmax) { [min, max] }
+      end
+      range
     end
 
     def greedy?
@@ -114,23 +123,6 @@ module Regexp::Expression
     alias :to_h :attributes
   end
 
-  def self.parsed(exp)
-    warn('WARNING: Regexp::Expression::Base.parsed is buggy and '\
-         'will be removed in 2.0.0. Use Regexp::Parser.parse instead.')
-    case exp
-    when String
-      Regexp::Parser.parse(exp)
-    when Regexp
-      Regexp::Parser.parse(exp.source) # <- causes loss of root options
-    when Regexp::Expression            # <- never triggers
-      exp
-    else
-      raise ArgumentError, 'Expression.parsed accepts a String, Regexp, or '\
-                           'a Regexp::Expression as a value for exp, but it '\
-                           "was given #{exp.class.name}."
-    end
-  end
-
 end # module Regexp::Expression
 
 require 'regexp_parser/expression/quantifier'

data/lib/regexp_parser/expression/classes/backref.rb

@@ -2,6 +2,11 @@ module Regexp::Expression
   module Backreference
     class Base < Regexp::Expression::Base
       attr_accessor :referenced_expression
+
+      def initialize_copy(orig)
+        self.referenced_expression = orig.referenced_expression.dup
+        super
+      end
     end
 
     class Number < Backreference::Base

data/lib/regexp_parser/expression/classes/conditional.rb

@@ -1,6 +1,6 @@
 module Regexp::Expression
   module Conditional
-    class TooManyBranches < StandardError
+    class TooManyBranches < Regexp::Parser::Error
       def initialize
         super('The conditional expression has more than 2 branches')
       end
@@ -15,6 +15,11 @@ module Regexp::Expression
         ref = text.tr("'<>()", "")
         ref =~ /\D/ ? ref : Integer(ref)
       end
+
+      def initialize_copy(orig)
+        self.referenced_expression = orig.referenced_expression.dup
+        super
+      end
     end
 
     class Branch < Regexp::Expression::Sequence; end
@@ -53,6 +58,11 @@ module Regexp::Expression
       def to_s(format = :full)
         "#{text}#{condition}#{branches.join('|')})#{quantifier_affix(format)}"
       end
+
+      def initialize_copy(orig)
+        self.referenced_expression = orig.referenced_expression.dup
+        super
+      end
     end
   end
 end

data/lib/regexp_parser/expression/classes/free_space.rb

@@ -1,8 +1,8 @@
 module Regexp::Expression
 
   class FreeSpace < Regexp::Expression::Base
-    def quantify(token, text, min = nil, max = nil, mode = :greedy)
-      raise "Can not quantify a free space object"
+    def quantify(_token, _text, _min = nil, _max = nil, _mode = :greedy)
+      raise Regexp::Parser::Error, 'Can not quantify a free space object'
     end
   end
 

data/lib/regexp_parser/expression/classes/group.rb

@@ -10,11 +10,36 @@ module Regexp::Expression
       def comment?; false end
     end
 
-    class Atomic  < Group::Base; end
-    class Passive < Group::Base; end
+    class Passive < Group::Base
+      attr_writer :implicit
+
+      def initialize(*)
+        @implicit = false
+        super
+      end
+
+      def to_s(format = :full)
+        if implicit?
+          "#{expressions.join}#{quantifier_affix(format)}"
+        else
+          super
+        end
+      end
+
+      def implicit?
+        @implicit
+      end
+    end
+
     class Absence < Group::Base; end
+    class Atomic  < Group::Base; end
     class Options < Group::Base
       attr_accessor :option_changes
+
+      def initialize_copy(orig)
+        self.option_changes = orig.option_changes.dup
+        super
+      end
     end
 
     class Capture < Group::Base
@@ -33,7 +58,7 @@ module Regexp::Expression
         super
       end
 
-      def initialize_clone(orig)
+      def initialize_copy(orig)
         @name = orig.name.dup
         super
       end