regextest 0.1.3 → 0.1.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 4f72f4c8fc5748bfb1c3d89c9cced2ebeeae0a23
-  data.tar.gz: 6b8bb46b092396449d3bd5be85b0ffe5c839c2fe
+  metadata.gz: b51a91bb714731ac6c008e71cc768024e7125ae0
+  data.tar.gz: e6f0cf1de571dc253c9097313c067763e4b09b14
 SHA512:
-  metadata.gz: 5e3e92daabfcf4145f543c67a525f767925d5b0c49b24f4dbf7463bd224e6baa006fea4bcc49f0eeefe71629b17ae0ce6ebbc4a39cbe1abf6005f4059e8eb29a
-  data.tar.gz: 41cb1005d492f96da718d446a2e484536e2aa7c178d9d2120ddcfe1f860c08645c4f4433166fd6241d889d375dafce00eb900ab0a0247eb1643e97c62f961a79
+  metadata.gz: 7e2cafea68bc1bde41e965fd3348c4bc8e4ad4160f96acb506081faa5b0db0d440461a879e5b6400bfa0dc8e04f4df3bc1276df26b7dc00e257c5bed72e5ef6e
+  data.tar.gz: 8848c862ab67d58fc053798d71139c84e84c5be3ccb6fb8651bb22dc9cb51ce70c728a613e6168773fc523b9d240913b53706e4914068496a54a3a6cf84374bf

data/Rakefile

@@ -31,6 +31,12 @@ file 'lib/regextest/front/case-folding.rb' => 'lib/pre-case-folding.rb' do
   sh 'ruby  lib/pre-case-folding.rb'
 end
 
+# Generating regression test suite
+file 'spec/regression_spec.rb' => 'lib/pre-generate-spec.rb' do
+  puts "making spec/regression_spec.rb"
+  sh 'ruby  lib/pre-generate-spec.rb'
+end
+
 # Generating documents
 file 'doc/index.html' => ['lib/regextest.rb', 'lib/regextest/regexp.rb', 'README.md'] do
   puts "making document for Regextest"
@@ -42,6 +48,7 @@ task :make =>
          'lib/regextest/front/bracket-parser.rb',
          'lib/regextest/front/unicode.rb',
          'lib/regextest/front/case-folding.rb',
+         'spec/regression_spec.rb',
          'doc/index.html',
         ] do 
   puts "Rake it!"

data/lib/pre-generate-spec.rb

@@ -0,0 +1,129 @@
+# encoding: utf-8
+
+# Copyright (C) 2016 Mikio Ikoma
+
+require 'regextest'
+require 'kconv'
+require 'timeout'
+require 'pp'
+
+class Regextest::Test
+  def initialize
+    time_out = 1
+    results = do_test(time_out)
+    @spec_file = "spec/regression_spec.rb"
+    puts_spec(@spec_file, results)
+    
+  end
+  
+  def do_test(timeout_seconds)
+    results = []
+    get_lines(timeout_seconds).each_with_index do | line, i |
+      begin
+        warn line
+        eval(line)
+      rescue SyntaxError => ex
+        warn "EVAL ERROR: #{ex}, #{line}"
+        #results.push({
+        #  explain: "raises #{ex}, when eval (#{line})",
+        #  expect:  "eval('#{line}')",
+        #  raises:   "#{ex.class}"
+        #})
+      end
+    end
+    results
+  end
+  
+  def puts_spec(spec_file, results)
+    File.open(spec_file, "w") do |fp|
+      fp.puts "require 'spec_helper'"
+      fp.puts "describe Regextest do"
+      results.each do | result |
+        explain = result[:explain].gsub("'", "\\\\'")
+        expect = result[:expect]   # .gsub("'", "\\\\'")
+        fp.puts "  it '#{explain}' do"
+        if result[:to_be]
+          fp.puts "    expect(#{expect}).to be_a(#{result[:to_be]})"
+        elsif result[:raises]
+          fp.puts "    expect {#{expect}}.to raise_error(#{result[:raises]})"
+        else
+          raise "Invalid result: #{result}"
+        end
+        fp.puts "  end"
+      end
+      fp.puts "end"
+    end
+  end
+
+  def get_lines(timeout_seconds)
+    lines = []
+    # py_source = IO.read("./contrib/Onigmo/testpy.py")
+    File::open("./contrib/Onigmo/testpy.py") do |f|
+      f.each.with_index do |line, line_num|
+        # break if line_num > 800
+        line.force_encoding("utf-8")
+        if !line.match(/ONIG_SYNTAX_PERL/)
+          if(md = line.match(/^\s*(?:x|x2|n)\s*\(.+?$/u) rescue nil)
+            line.sub!(/,\s*\".+?$/, ", results, timeout_seconds)") rescue nil
+            lines.push line if line
+          end
+        else
+          warn "Perl syntax. \nline:#{line}"
+        end
+      end
+    end
+    lines
+  end
+
+  def check_normal_test(reg, results, timeout_seconds)
+    result = nil
+    a_test = eval("/#{reg}/")
+    timeout(timeout_seconds) do
+      10.times do | i |
+        md = a_test.match_data(seed: i)
+        if(md)
+          # print "OK md:#{md},"
+          result = {
+            explain: "can parse (#{reg}) and generate match-data",
+            expect:  "/#{reg}/.match_data",
+            to_be:   "MatchData"
+          }
+        else
+          warn "Failed. reg='#{a_test}', reason=#{obj.reason}"
+          result = {
+            explain: "cannot parse / generate (#{reg})",
+            expect:  "/#{reg}/.match_data",
+            to_be:   "Nil"
+          }
+          break
+        end
+      end
+    end
+    results.push result
+  rescue => ex
+    warn "GOO: #{ex} #{ex.class}"
+    results.push({
+      explain: "raises #{ex}, when parse / generate (#{reg})",
+      expect:  "/#{reg}/.match_data",
+      raises:   "#{ex.class}"
+    })
+  end
+
+  def x(reg, *params)
+    check_normal_test(reg, *params)
+  end
+
+  def x2(reg, *params)
+    check_normal_test(reg, *params)
+  end
+
+  def n(reg, *params)
+    check_normal_test(reg, *params)
+  end
+
+end
+
+# Test suite (execute when this file is specified in command line)
+if __FILE__ == $0
+  Regextest::Test.new
+end

data/lib/regextest/back/element.rb

@@ -8,6 +8,7 @@ require 'regextest/common'
 class Regextest::Back::Element
   include Regextest::Common
   def initialize(param)
+    # puts "Element param:#{param[:cmd]} data:#{param[:data].size}"
     @command = param[:cmd]
     @param = param
     @candidates = param[:data] if @command == :CMD_SELECT
@@ -24,7 +25,7 @@ class Regextest::Back::Element
     else
       raise "invalid command at random_fix: #{@command}"
     end
-    result
+    [result].pack("U*")   # tranforms from code point to a letter
   end
   
   # size of candidates
@@ -96,32 +97,34 @@ class Regextest::Back::Element
   
   # Includes new line or not
   def new_line?
-    @candidates.index("\n")
+    @candidates.index(0xa)
   end
   
   # Sets new line
   def set_new_line
-    @candidates = ["\n"]
+    @candidates = [0xa]
   end
   
   # Is word-elements only?
   def word_elements?
-    @candidates.join("").match(/^\p{Word}+$/)
+    letters = @candidates.map{|elem| [elem].pack("U*")}
+    letters.join("").match(/^\p{Word}+$/)
   end
   
   # is non-word-elements only?
   def non_word_elements?
-    @candidates.join("").match(/^\p{^Word}+$/)
+    letters = @candidates.map{|elem| [elem].pack("U*")}
+    letters.join("").match(/^\p{^Word}+$/)
   end
 
   # set word-elements
   def set_word_elements
-    @candidates.select!{|elem| elem.match(/^\w$/)}
+    @candidates.select!{|elem| [elem].pack("U*").match(/^\w$/)}
   end
   
   # set non_word-elements
   def set_non_word_elements
-    @candidates.select!{|elem| elem.match(/^\W$/)}
+    @candidates.select!{|elem| [elem].pack("U*").match(/^\W$/)}
   end
   
   # checks empty
@@ -132,12 +135,12 @@ class Regextest::Back::Element
   # factory method to generate any char element
   def self.any_char
     # BUG: must consider other character set!
-    Regextest::Back::Element.new({cmd: :CMD_SELECT, data:  (" ".."\x7e").to_a})
+    Regextest::Back::Element.new({cmd: :CMD_SELECT, data:  (0x20..0x7e).to_a})
   end
   
   # factory method to generate any char element
   def reverse
-    @candidates = ((" ".."\x7e").to_a) - @candidates
+    @candidates = ((0x20..0x7e).to_a) - @candidates
     self
   end
   

data/lib/regextest/back/main.rb

@@ -266,8 +266,7 @@ class Regextest::Back::Main
     target = param[:json]
     letter = []
     codepoints = (target["begin"]..target["end"]).to_a
-    letter = codepoints.map{| codepoint | [codepoint].pack("U*")}   # to be faster
-    result = Regextest::Back::Element.new({cmd: :CMD_SELECT, data: letter})
+    result = Regextest::Back::Element.new({cmd: :CMD_SELECT, data: codepoints})
   end
   
   # back_refer
@@ -305,7 +304,8 @@ class Regextest::Back::Main
     target = param[:json]
     case target["value"]
     when String
-      result = Regextest::Back::Element.new({cmd: :CMD_SELECT, data: [target["value"]]})
+      codepoint = target["value"].unpack("U*")[0]
+      result = Regextest::Back::Element.new({cmd: :CMD_SELECT, data: [codepoint]})
     else
       result = generate_candidates({json: target["value"]})
     end
@@ -314,6 +314,7 @@ class Regextest::Back::Main
   
   # narrow down candidates considering anchors
   def narrow_down_candidates(candidate_array)
+    # pp candidate_array
     results = Regextest::Back::Result.new
     candidate_array.each do | elem |
       command = elem.command

data/lib/regextest/back/result.rb

@@ -127,18 +127,18 @@ class Regextest::Back::Result
   # Merge each elements of not-look-aheads
   def merge_not_look_ahead_elems(offset, sub_results)
     if Regextest::Back::Result === sub_results
-      term_offset = offset + sub_results.end_offset - 1
+      term_offset = offset + sub_results.end_offset
     else
-      term_offset = offset + sub_results.size - 1
+      term_offset = offset + sub_results.size
     end
     try_order = TstShuffle(sub_results.size.times.to_a)
-    
     found = false
     # exclude, at least, one element
     try_order.each do | j |
       results_work = @results.dup
       cur_offset = offset + j
     
+      # puts "offset=#{offset} term_offset=#{term_offset}"
       offset.step(term_offset-1).each do | i |
         sub_elem = sub_results[i-offset]
         

data/lib/regextest/version.rb

@@ -1,5 +1,5 @@
 # Copyright (C) 2016 Mikio Ikoma
 
 class Regextest
-  VERSION = "0.1.3"
+  VERSION = "0.1.4"
 end

data/regextest.gemspec

@@ -19,8 +19,12 @@ Gem::Specification.new do |spec|
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
   spec.require_paths = ["lib"]
 
+  spec.required_ruby_version = '>= 1.9.3'
+  
+  spec.add_development_dependency "ruby"
   spec.add_development_dependency "bundler", "~> 1.8"
   spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "racc", "~> 1.4.12"
   spec.add_development_dependency "yard", "~> 0.9.5"
-  spec.add_development_dependency "rspec"
+  spec.add_development_dependency "rspec", "~> 3.5.0"
 end

metadata

@@ -1,15 +1,29 @@
 --- !ruby/object:Gem::Specification
 name: regextest
 version: !ruby/object:Gem::Version
-  version: 0.1.3
+  version: 0.1.4
 platform: ruby
 authors:
 - IKOMA, Mikio
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2016-08-21 00:00:00.000000000 Z
+date: 2016-08-31 00:00:00.000000000 Z
 dependencies:
+- !ruby/object:Gem::Dependency
+  name: ruby
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
@@ -38,6 +52,20 @@ dependencies:
     - - ~>
       - !ruby/object:Gem::Version
         version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: racc
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 1.4.12
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 1.4.12
 - !ruby/object:Gem::Dependency
   name: yard
   requirement: !ruby/object:Gem::Requirement
@@ -56,16 +84,16 @@ dependencies:
   name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ~>
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 3.5.0
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ~>
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 3.5.0
 description: 'Regextest generates sample string that matches with regular expression.
   Unlike similar tools, it recognizes anchors, charactor classes and other advanced
   notation of ruby regex. Target users are programmers or students for debugging/learning
@@ -101,6 +129,7 @@ files:
 - contrib/unicode/Scripts.txt
 - contrib/unicode/UnicodeData.txt
 - lib/pre-case-folding.rb
+- lib/pre-generate-spec.rb
 - lib/pre-posix-char-class.rb
 - lib/pre-unicode.rb
 - lib/regextest.rb
@@ -151,7 +180,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - '>='
     - !ruby/object:Gem::Version
-      version: '0'
+      version: 1.9.3
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - '>='