regexp_parser 0.1.5 → 0.1.6

data/test/syntax/ruby/test_all.rb

@@ -1,6 +1,6 @@
 require File.expand_path("../../../helpers", __FILE__)
 
-%w{1.8 1.9.1 1.9.3}.each do|tc|
+%w{1.8 1.9.1 1.9.3 2.x}.each do|tc|
   require File.expand_path("../test_#{tc}", __FILE__)
 end
 

metadata

@@ -1,23 +1,21 @@
 --- !ruby/object:Gem::Specification
 name: regexp_parser
 version: !ruby/object:Gem::Version
-  version: 0.1.5
+  version: 0.1.6
 platform: ruby
 authors:
 - Ammar Ali
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-01-14 00:00:00.000000000 Z
+date: 2014-10-06 00:00:00.000000000 Z
 dependencies: []
 description: A library for tokenizing, lexing, and parsing Ruby regular expressions.
-email: ammarabuali@gmail.com
+email:
+- ammarabuali@gmail.com
 executables: []
 extensions: []
-extra_rdoc_files:
-- ChangeLog
-- LICENSE
-- README.rdoc
+extra_rdoc_files: []
 files:
 - lib/regexp_parser/ctype.rb
 - lib/regexp_parser/expression/classes/alternation.rb
@@ -44,7 +42,11 @@ files:
 - lib/regexp_parser/syntax/ruby/1.9.3.rb
 - lib/regexp_parser/syntax/ruby/1.9.rb
 - lib/regexp_parser/syntax/ruby/2.0.0.rb
+- lib/regexp_parser/syntax/ruby/2.0.rb
 - lib/regexp_parser/syntax/ruby/2.1.0.rb
+- lib/regexp_parser/syntax/ruby/2.1.2.rb
+- lib/regexp_parser/syntax/ruby/2.1.3.rb
+- lib/regexp_parser/syntax/ruby/2.1.rb
 - lib/regexp_parser/syntax/tokens/anchor.rb
 - lib/regexp_parser/syntax/tokens/assertion.rb
 - lib/regexp_parser/syntax/tokens/backref.rb
@@ -80,7 +82,6 @@ files:
 - test/parser/test_sets.rb
 - test/scanner/test_all.rb
 - test/scanner/test_anchors.rb
-- test/scanner/test_conditionals.rb
 - test/scanner/test_errors.rb
 - test/scanner/test_escapes.rb
 - test/scanner/test_groups.rb
@@ -88,7 +89,6 @@ files:
 - test/scanner/test_meta.rb
 - test/scanner/test_properties.rb
 - test/scanner/test_quantifiers.rb
-- test/scanner/test_quoting.rb
 - test/scanner/test_refcalls.rb
 - test/scanner/test_scripts.rb
 - test/scanner/test_sets.rb
@@ -96,6 +96,7 @@ files:
 - test/syntax/ruby/test_1.8.rb
 - test/syntax/ruby/test_1.9.1.rb
 - test/syntax/ruby/test_1.9.3.rb
+- test/syntax/ruby/test_2.x.rb
 - test/syntax/ruby/test_all.rb
 - test/syntax/test_all.rb
 - test/test_all.rb
@@ -104,12 +105,13 @@ files:
 - VERSION.yml
 - Rakefile
 - LICENSE
-- README.rdoc
+- README.md
 - ChangeLog
 homepage: http://github.com/ammar/regexp_parser
 licenses:
 - MIT
-metadata: {}
+metadata:
+  issue_tracker: https://github.com/ammar/regexp_parser/issues
 post_install_message: 
 rdoc_options:
 - --inline-source
@@ -120,7 +122,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - '>='
     - !ruby/object:Gem::Version
-      version: '0'
+      version: 1.8.7
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - '>='
@@ -154,7 +156,6 @@ test_files:
 - test/parser/test_sets.rb
 - test/scanner/test_all.rb
 - test/scanner/test_anchors.rb
-- test/scanner/test_conditionals.rb
 - test/scanner/test_errors.rb
 - test/scanner/test_escapes.rb
 - test/scanner/test_groups.rb
@@ -162,7 +163,6 @@ test_files:
 - test/scanner/test_meta.rb
 - test/scanner/test_properties.rb
 - test/scanner/test_quantifiers.rb
-- test/scanner/test_quoting.rb
 - test/scanner/test_refcalls.rb
 - test/scanner/test_scripts.rb
 - test/scanner/test_sets.rb
@@ -170,6 +170,7 @@ test_files:
 - test/syntax/ruby/test_1.8.rb
 - test/syntax/ruby/test_1.9.1.rb
 - test/syntax/ruby/test_1.9.3.rb
+- test/syntax/ruby/test_2.x.rb
 - test/syntax/ruby/test_all.rb
 - test/syntax/test_all.rb
 - test/test_all.rb

data/README.rdoc

@@ -1,307 +0,0 @@
-= Regexp::Parser
-
-== What?
-A ruby library to help with lexing, parsing, and transforming regular expressions.
-
-* Multilayered
-
-  * A scanner based on ragel[http://www.complang.org/ragel/]
-  * A lexer that produces a "stream" of tokens
-  * A parser that produces a "tree" of Regexp::Expression objects (OO API)
-
-* Lexes and parses both 1.8 and 1.9 regular expression flavors
-* Supports ruby 1.8 and 1.9 runtime
-
-For an example of regexp_parser in use, see the meta_re project[https://github.com/ammar/meta_re]
-
----
-== Requirements
-
-* ruby '1.8.6'..'1.9.2'
-* ragel, but only if you want to hack on the scanner
-
-
----
-== Install
-
-  gem install regexp_parser
-
----
-== Components
-=== Scanner
-A ragel generated scanner that recognizes the cumulative syntax of both
-supported flavors. Breaks the expression's text into tokens, including
-their type, token, text, and start/end offsets within the original
-pattern.
-
-==== Example
-The following scans the given pattern and prints out the type, token, text and
-start/end offsets for each token found.
-
-  require 'regexp_parser'
-
-  Regexp::Scanner.scan /(ab?(cd)*[e-h]+)/  do |type, token, text, ts, te|
-    puts "type: #{type}, token: #{token}, text: '#{text}' [#{ts}..#{te}]"
-  end
-
-A one-liner that returns an array of the textual parts of the given pattern:
-
-  Regexp::Scanner.scan( /(cat?([b]at)){3,5}/ ).map {|token| token[2]}
-  #=> ["(", "cat", "?", "(", "[", "b", "]", "at", ")", ")", "{3,5}"]
-
-
-==== Notes
-  * The scanner performs basic syntax error checking, like detecting missing
-    balancing punctuation and premature end of pattern. Flavor validity checks
-    are performed in the lexer.
-
-  * To keep the scanner simple(r) and fairly reusable for other uses, it
-    does not perform lexical analysis on the tokens, sticking to the task
-    of tokenizing and leaving lexical analysis upto to the lexer.
-
-  * If the input is a ruby Regexp object, the scanner calls #source on it to
-    get its string representation. #source does not include the options of
-    expression (m, i, and x) To include the options the scan, #to_s should
-    be called on the Regexp before passing it to the scanner, or any of the
-    higher layers.
-
-
----
-=== Syntax
-Defines the supported tokens for a specific engine implementation (aka a
-flavor). Syntax classes act as lookup tables, and are layered to create
-flavor variations. Syntax only comes into play in the lexer.
-
-==== Example
-The following instantiates the syntax for Ruby 1.9 and checks a couple of its
-implementations features, and then does the same for Ruby 1.8:
-
-  require 'regexp_parser'
-
-  ruby_19 = Regexp::Syntax.new 'ruby/1.9'
-  ruby_19.implements? :quantifier, :zero_or_one             # => true
-  ruby_19.implements? :quantifier, :zero_or_one_reluctant   # => true
-  ruby_19.implements? :quantifier, :zero_or_one_possessive  # => true
-
-  ruby_18 = Regexp::Syntax.new 'ruby/1.8'
-  ruby_18.implements? :quantifier, :zero_or_one             # => true
-  ruby_18.implements? :quantifier, :zero_or_one_reluctant   # => true
-  ruby_18.implements? :quantifier, :zero_or_one_possessive  # => false
-
-
-==== Notes
-  * Variatiions on a token, for example a named group with < and > vs one with a
-    pair of single quotes, are specified with an underscore followed by two
-    characters appended to the base token. In the previous named group example,
-    the tokens would be :named_ab (angle brackets) and :named_sq (single quotes).
-    These variations are normalized by the syntax to :named.
-
-==== TODO
-  * Add flavor limits: like Ruby 1.8's maximum allowed number of grouped 
-    expressions (253).
-
-
----
-=== Lexer
-Sits on top of the scanner and performs lexical analysis on the tokens that
-it emits. Among its tasks are breaking quantified literal runs, collecting the
-emitted token structures into an array of Token objects, calculating their
-nesting depth, normalizing tokens for the parser, and checkng if the tokens
-are implemented by the given syntax flavor.
-
-Tokens objects are Structs, basically data objects, with a few helper methods,
-like #next, #previous, #offsets and #length.
-
-==== Example
-The following example scans the given pattern, checks it against the ruby 1.8
-syntax, and prints the token objects' text.
-
-  require 'regexp_parser'
-
-  Regexp::Lexer.scan(/a?(b)*[c]+/, 'ruby/1.8') do |token|
-    puts "#{'  ' * token.depth}#{token.text}"
-  end
-
-A one-liner that returns an array of the textual parts of the given pattern.
-Compare the output with that of the one-liner example of the Scanner.
-
-  Regexp::Lexer.scan( /(cat?([b]at)){3,5}/ ).map {|token| token.text}
-  #=> ["(", "ca", "t", "?", "(", "[", "b", "]", "at", ")", ")", "{3,5}"]
-
-==== Notes
-  * The default syntax is that of the latest released version of ruby.
-
-  * The lexer performs some basic parsing to determine the depth of a the
-    emitted tokens. This responsibility might be relegated to the scanner.
-
-
----
-=== Parser
-Sits on top of the lexer and transforms the "stream" of Token objects emitted
-by it into a tree of Expression objects represented by an instance of the
-Expression::Root class. See Expression below for more information.
-
-==== Example
-
-  require 'regexp_parser'
-
-  regex = /a?(b)*[c]+/m
-
-  # using #to_s on the Regexp object to include options
-  root = Regexp::Parser.parse( regex.to_s, 'ruby/1.8')
-
-  root.multiline?         # => true (aliased as m?)
-  root.case_insensitive?  # => false (aliased as i?)
-
-  # simple tree walking method
-  def walk(e, depth = 0)
-    puts "#{'  ' * depth}> #{e.class}"
-    unless e.expressions.empty?
-      e.each {|s| walk(s, depth+1) }
-    end
-  end
-
-  walk(root)
-
-  # output
-  > Regexp::Expression::Root
-    > Regexp::Expression::Literal
-    > Regexp::Expression::Group::Capture
-      > Regexp::Expression::Literal
-    > Regexp::Expression::CharacterSet
-
-Note: quantifiers do not appear in the output because they are members of the
-Expression class. See the next section for more details.
-
----
-=== Expression
-The base class of all objects returned by the parser, implements most of the
-functions that are common to all expression classes.
-
-Each Expression object contains the following members:
-
-  * quantifier: an instance of Expression::Quantifier that holds the details
-    of repetition for the Expression. Has a nil value if the expressions is not
-    quantified.
-
-  * expressions: an array, holds the sub-expressions for the expression if it
-    is a group or alternation expression. Empty if the expression doesn't have
-    sub-expressions.
-
-  * options: a hash, holds the keys :i, :m, and :x with a boolean value that
-    indicates if the expression has a given option.
-
-Expressions also contain the following "lower level" members
-(from the scanner/lexer)
-
-  * type: a symbol, denoting the expression type, such as :group, :quantifier
-  * token: a symbol, for the object's token, or opening token (in the case of
-    groups and sets)
-  * text: a string, the text of the expression (same as token for nesting expressions)
-
-Every expressions also has the following methods:
-
-  * to_s: returns the string representation of the expression.
-  * <<: adds sub-expresions to the expression.
-  * each: iterates over the expressions sub-expressions, if any.
-  * []: access sub-expressions by index.
-  * quantified?: return true if the expressions was followed by a quantifier.
-  * quantity: returns an array of the expression's min and max repetitions.
-  * greedy?: returns true if the expression's quantifier is greedy.
-  * reluctant? or lazy?: returns true if the expression's quantifier is
-    reluctant.
-  * possessive?: returns true if the expression's quantifier is possessive.
-  * multiline? or m?: returns true if the expression has the m option
-  * case_insensitive? or ignore_case? or i?: returns true if the expression
-    has the i option
-  * free_spacing? or extended? or x?: returns true if the expression has the x
-    option
-
-A special expression class Expression::Sequence is used to hold the array of
-possible alternatives within an Expression::Alternation expression.
-
-
-== Scanner Syntax
-The following syntax elements are supported by the scanner. 
-
-  - Alternation: a|b|c, etc.
-  - Anchors: ^, $, \b, etc.
-  - Character Classes (aka Sets): [abc], [^\]]
-  - Character Types: \d, \H, \s, etc.
-  - Escape Sequences: \t, \+, \?, etc.
-  - Grouped Expressions
-    - Assertions
-      - Lookahead: (?=abc)
-      - Negative Lookahead: (?!abc)
-      - Lookabehind: (?<=abc)
-      - Negative Lookbehind: (?<\!abc)
-    - Atomic: (?>abc)
-    - Back-references:
-      - Named: \k<name>
-      - Nest Level: \k<n-1>
-      - Numbered: \k<1>
-      - Relative: \k<-2>
-    - Capturing: (abc)
-    - Comment: (?# comment)
-    - Named: (?<name>abc)
-    - Options: (?mi-x:abc)
-    - Passive: (?:abc)
-    - Sub-expression Calls: \g<name>, \g<1>
-  - Literals: abc, def?, etc.
-  - POSIX classes: [:alpha:], [:print:], etc.
-  - Quantifiers
-    - Greedy: ?, *, +, {m,M}
-    - Reluctant: ??, *?, +?, {m,M}?
-    - Possessive: ?+, *+, ++, {m,M}+
-  - String Escapes
-    - Control: \C-C, \cD, etc.
-    - Hex: \x20, \x{701230}, etc.
-    - Meta: \M-c, \M-\C-C etc.
-    - Octal: \0, \01, \012
-    - Unicode: \uHHHH, \u{H+ H+}
-  - Traditional Back-references: \1 thru \9
-  - Unicode Properties: 
-    - Age: \p{Age=2.1}, \P{age=5.2}, etc.
-    - Classes: \p{Alpha}, \P{Space}, etc.
-    - Derived Properties: \p{Math}, \P{Lowercase}, etc.
-    - General Categories: \p{Lu}, \P{Cs}, etc.
-    - Scripts: \p{Arabic}, \P{Hiragana}, etc.
-    - Simple Properties: \p{Dash}, \p{Extender}, etc.
-
-See something missing? Please submit an issue[https://github.com/ammar/regexp_parser/issues]
-
-== References
-Documentation and information being read while working on this project.
-
-==== Ruby Flavors
-* Oniguruma Regular Expressions link[http://www.geocities.jp/kosako3/oniguruma/doc/RE.txt]
-* Read Ruby > Regexps link[http://ruby.runpaint.org/regexps]
-
-
-==== General
-* Enumerating the strings of regular languages link[http://www.cs.dartmouth.edu/~doug/nfa.ps.gz]
-* Mastering Regular Expressions, By Jeffrey E.F. Friedl (2nd Edition) book[http://oreilly.com/catalog/9781565922570/]
-* Regular Expression Flavor Comparison link[http://www.regular-expressions.info/refflavors.html]
-
-
-==== Unicode
-* Unicode Derived Properties link[http://www.unicode.org/Public/UNIDATA/DerivedCoreProperties.txt]
-* Unicode Explained, By Jukka K. Korpela. book[http://oreilly.com/catalog/9780596101213]
-* Unicode Property Aliases link[http://www.unicode.org/Public/UNIDATA/PropertyAliases.txt]
-* Unicode Regular Expressions link[http://www.unicode.org/reports/tr18/]
-* Unicode Standard Annex #44 link[http://www.unicode.org/reports/tr44/]
-
-== Thanks
-This work is based on and inspired by the hard work and ideas of many people,
-directly or indirectly. The following are only a few of those that should be 
-thanked.
-
-* Adrian Thurston, for developing ragel[http://www.complang.org/ragel/].
-* Caleb Clausen, for feedback, which inspired this,  valuable insights on structuring the parser,
-  and lots of cool code[http://github.com/coatl].
-* Jan Goyvaerts, for his excellent resource[http://www.regular-expressions.info] on regular expressions. I owe him a "steak dinner", at least.
-* Run Paint Run Run, for his work on Read[http://ruby.runpaint.org/] Ruby
-* Yukihiro Matsumoto, of course! For "The Ruby", of course!
-
-== Copyright
-Copyright (c) 2010 Ammar Ali. See LICENSE file for details.

data/test/scanner/test_conditionals.rb

@@ -1,31 +0,0 @@
-require File.expand_path("../../helpers", __FILE__)
-
-class ScannerConditionals < Test::Unit::TestCase
-
-  tests = {
-    /(?(1)Y|N)/         => [0, :conditional,  :open,        '(?(',  0,  3],
-    /(?(2)Y|N)/         => [1, :conditional,  :condition,   '2',    3,  4],
-    /(?(3)Y|N)/         => [2, :conditional,  :yes,         'Y',    5,  6],
-
-    #"(?(<name>)Y|N)"    => [0, :conditional,  :condition, '(?(<name>)Y|N)',  0, 14],
-    #"(?('name')Y|N)"    => [0, :conditional,  :yes,       "(?('name')Y|N)",  0, 14],
-  }
-
-  count = 0
-  tests.each do |pattern, test|
-    define_method "test_scan_#{test[1]}_#{test[2]}_#{count+=1}" do
-
-      tokens = RS.scan(pattern)
-      token = tokens[test[0]]
-      assert_equal( test[1,5], token )
-
-    end
-  end
-
- #def test_scanner_quote
- #  tokens = RS.scan('a\QX\Eb\QX\Ec')
- #  puts tokens.inspect
- #  #assert_equal( tokens[0] )
- #end
-
-end