srl_ruby 0.2.0 → 0.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 6aad01259ac0746c8e49a856822c5e8c53aaed52
-  data.tar.gz: b814be25539c6304eab9471843c2eaa92abbbfc7
+  metadata.gz: 26a19da14fe9e1f84e095aa9eb4ac135915407ae
+  data.tar.gz: 2edefb6e8473d2e03df633fc35e2f1c5863df09a
 SHA512:
-  metadata.gz: 3f93e5d7277bafd3c4ca6449855d6a423eae6b6912d4e5543f7f2042026d6f1b56a970c3241a5152ae184b3e78a72e68ab437cdeb1e37cfc694f96c68941d4ad
-  data.tar.gz: f83cc31f5c5ccaeae1c14a0997d75da1eb4eed6ec3f306f822477de72c074383636d060530eb08f8176276a37870a4767a0635edf22035ed281987c88a9ff085
+  metadata.gz: 004a7a30442c6b5e49cf91a0eaa5689c1dd2f770a82593bb7bcc26450e91c009f743701e5d89a4afeb30c102fc8e2994e311ab70402600c7990b6c864e6b085f
+  data.tar.gz: b681c6cf73d7669cfd93b12c995b9844e0ad8b4933a7b0a98a130385a8f5f46608c39fcc114f1c625c469596a1cdc25e9b484b7023e2f968e293ede44d0a3da1

data/CHANGELOG.md

@@ -6,7 +6,20 @@
 ### Fixed
 ### Security
 
+## [0.2.1] - 2018-03-15
+SrlRuby passes 7 tests out of 15 standard SRL tests in total.  
+### Changed
+- File `acceptance/srl_test_suite_spec.rb`. More examples in spec file.
+- File `ast_builder.rb` updates to reflect grammar changes.
+
+### Fixed
+- SRL grammar now accepts a comma before 'must end' anchor
+- SRL grammar now accepts a comma before an option
+- Class `Tokenizer#_next_token` now recognizes correctly escaped quotes within string literal
+- File `ast_builder.rb` fixed anchor implementation.
+
 ## [0.2.0] - 2018-03-14
+SrlRuby passes 3 standard out of 15 standard SRL tests in total.
 ### Added
 - Added `spec/acceptance/support` directory. It contains test harness to use the .rule files from standard SRL test suite. 
 - Added `acceptance/srl_test_suite_spec.rb`file. Spec file designed to standard SRL test suite. At this date, SrlRuby passes 3 tests out of 15 tests in total.

data/lib/srl_ruby/ast_builder.rb

@@ -15,7 +15,7 @@ module SrlRuby
     attr_reader :options
 
     protected
-    
+
     def terminal2node()
       Terminal2NodeClass
     end
@@ -80,14 +80,14 @@ module SrlRuby
     def repetition(expressionToRepeat, aMultiplicity)
       return Regex::Repetition.new(expressionToRepeat, aMultiplicity)
     end
-    
+
     def begin_anchor
       return Regex::Anchor.new('^')
     end
-    
-    # rule('expression' => %w[pattern separator flags]).as 'flagged_expr'
+
+    # rule('expression' => %w[pattern flags]).as 'flagged_expr'
     def reduce_flagged_expr(_production, aRange, theTokens, theChildren)
-      @options = theChildren[2] if theChildren[2]
+      @options = theChildren[1] if theChildren[1]
       return_first_child(aRange, theTokens, theChildren)
     end
 
@@ -100,6 +100,11 @@ module SrlRuby
     def reduce_flag_sequence(_production, _range, _tokens, theChildren)
       theChildren[0] << theChildren[2]
     end
+    
+    # rule('flags' => %w[separator single_flag]).as 'flag_simple'
+    def reduce_flag_simple(_production, _range, _tokens, theChildren)
+      [theChildren.last]
+    end
 
     # rule('single_flag' => %w[CASE INSENSITIVE]).as 'case_insensitive'
     def reduce_case_insensitive(_production, _range, _tokens, _children)
@@ -118,21 +123,17 @@ module SrlRuby
 
     # rule 'quantifiable' => %w[begin_anchor anchorable end_anchor]
     def reduce_pinned_quantifiable(_production, _range, _tokens, theChildren)
-      theChildren[1].begin_anchor = theChildren[0]
-      theChildren[1].end_anchor = theChildren[2]
-      return theChildren[1]
+      return Regex::Concatenation.new(*theChildren)
     end
 
     # rule 'quantifiable' => %w[begin_anchor anchorable]
     def reduce_begin_anchor_quantifiable(_production, _range, _tokens, theChildren)
-      theChildren[1].begin_anchor = theChildren[0]
-      return theChildren[1]
+      return Regex::Concatenation.new(*theChildren)
     end
 
     # rule 'quantifiable' => %w[anchorable end_anchor]
     def reduce_end_anchor_quantifiable(_production, _range, _tokens, theChildren)
-      theChildren[0].end_anchor = theChildren[1]
-      return theChildren[0]
+      return Regex::Concatenation.new(*theChildren)
     end
 
     # rule 'begin_anchor' => %w[STARTS WITH]
@@ -140,12 +141,12 @@ module SrlRuby
       begin_anchor
     end
 
-    # rule 'begin_anchor' => %w[BEGIN WITH]  
+    # rule 'begin_anchor' => %w[BEGIN WITH]
     def reduce_begin_with(_production, _range, _tokens, _children)
       begin_anchor
-    end  
+    end
 
-    # rule 'end_anchor' => %w[MUST END].as 'end_anchor'
+    # rule('end_anchor' => %w[separator MUST END]).as 'end_anchor'
     def reduce_end_anchor(_production, _range, _tokens, _children)
       return Regex::Anchor.new('$')
     end
@@ -312,30 +313,30 @@ module SrlRuby
       return Regex::Concatenation.new(group, theChildren[3])
     end
 
-    # rule('capturing_group' => %w[CAPTURE assertable AS var_name]).as 
+    # rule('capturing_group' => %w[CAPTURE assertable AS var_name]).as
     #   'named_capture'
     def reduce_named_capture(_production, _range, _tokens, theChildren)
       name = theChildren[3].token.lexeme.dup
       return Regex::CapturingGroup.new(theChildren[1], name)
     end
 
-    # rule('capturing_group' => %w[CAPTURE assertable AS var_name 
+    # rule('capturing_group' => %w[CAPTURE assertable AS var_name
     #   UNTIL assertable]).as 'named_capture_until'
     def reduce_named_capture_until(_production, _range, _tokens, theChildren)
       name = theChildren[3].token.lexeme.dup
       group = Regex::CapturingGroup.new(theChildren[1], name)
       return Regex::Concatenation.new(group, theChildren[5])
     end
-    
+
     # rule('quantifier' => 'ONCE').as 'once'
     def reduce_once(_production, _range, _tokens, _children)
       multiplicity(1, 1)
     end
-    
+
     # rule('quantifier' => 'TWICE').as 'twice'
     def reduce_twice(_production, _range, _tokens, _children)
       multiplicity(2, 2)
-    end  
+    end
 
     # rule('quantifier' => %w[EXACTLY count TIMES]).as 'exactly'
     def reduce_exactly(_production, _range, _tokens, theChildren)
@@ -350,7 +351,7 @@ module SrlRuby
       upper = theChildren[3].token.lexeme.to_i
       multiplicity(lower, upper)
     end
-    
+
     # rule('quantifier' => 'OPTIONAL').as 'optional'
     def reduce_optional(_production, _range, _tokens, _children)
       multiplicity(0, 1)
@@ -360,27 +361,27 @@ module SrlRuby
     def reduce_once_or_more(_production, _range, _tokens, _children)
       multiplicity(1, :more)
     end
-    
+
     # rule('quantifier' => %w[NEVER OR MORE]).as 'never_or_more'
     def reduce_never_or_more(_production, _range, _tokens, _children)
       multiplicity(0, :more)
     end
-    
-    # rule('quantifier' => %w[AT LEAST count TIMES]).as 'at_least' 
+
+    # rule('quantifier' => %w[AT LEAST count TIMES]).as 'at_least'
     def reduce_at_least(_production, _range, _tokens, theChildren)
       count = theChildren[2].token.lexeme.to_i
       multiplicity(count, :more)
-    end 
-    
+    end
+
     # rule('times_suffix' => 'TIMES').as 'times_keyword'
     def reduce_times_keyword(_production, _range, _tokens, _children)
       return nil
     end
-    
+
     # rule('times_suffix' => []).as 'times_dropped'
     def reduce_times_dropped(_production, _range, _tokens, _children)
       return nil
-    end  
+    end
   end # class
 end # module
 # End of file

data/lib/srl_ruby/grammar.rb

@@ -24,13 +24,14 @@ module SrlRuby
     add_terminals('LAZY')
 
     rule('srl' => 'expression').as 'start_rule'
-    rule('expression' => %w[pattern separator flags]).as 'flagged_expr'
+    rule('expression' => %w[pattern flags]).as 'flagged_expr'
     rule('expression' => 'pattern').as 'simple_expr'
     rule('pattern' => %w[pattern separator quantifiable]).as 'pattern_sequence'
     rule('pattern' => 'quantifiable').as 'basic_pattern'
     rule('separator' => 'COMMA').as 'comma_separator'
     rule('separator' => []).as 'void_separator'
     rule('flags' => %w[flags separator single_flag]).as 'flag_sequence'
+    rule('flags' => %w[separator single_flag]).as 'flag_simple'
     rule('single_flag' => %w[CASE INSENSITIVE]).as 'case_insensitive'
     rule('single_flag' => %w[MULTI LINE]).as 'multi_line'
     rule('single_flag' => %w[ALL LAZY]).as 'all_lazy'
@@ -40,7 +41,7 @@ module SrlRuby
     rule('quantifiable' => 'anchorable').as 'simple_quantifiable'
     rule('begin_anchor' => %w[STARTS WITH]).as 'starts_with'
     rule('begin_anchor' => %w[BEGIN WITH]).as 'begin_with'
-    rule('end_anchor' => %w[MUST END]).as 'end_anchor'
+    rule('end_anchor' => %w[separator MUST END]).as 'end_anchor'
     rule('anchorable' => 'assertable').as 'simple_anchorable'
     rule('anchorable' => %w[assertable assertion]).as 'asserted_anchorable'
     rule('assertion' => %w[IF FOLLOWED BY assertable]).as 'if_followed'

data/lib/srl_ruby/regex_repr.rb

@@ -11,3 +11,4 @@ require_relative '../regex/non_capturing_group'
 require_relative '../regex/anchor'
 require_relative '../regex/lookaround'
 require_relative '../regex/capturing_group'
+require_relative '../regex/match_option'

data/lib/srl_ruby/tokenizer.rb

@@ -116,10 +116,10 @@ module SrlRuby
         # TODO: handle case unknown identifier
       elsif (lexeme = scanner.scan(/[a-zA-Z]((?=\s)|$)/))
         token = build_token('LETTER_LIT', lexeme)
-      elsif (lexeme = scanner.scan(/"([^"]|\\")*"/)) # Double quotes literal?
+      elsif (lexeme = scanner.scan(/"(?:\\"|[^"])*"/)) # Double quotes literal?
         unquoted = lexeme.gsub(/(^")|("$)/, '')
         token = build_token('STRING_LIT', unquoted)
-      elsif (lexeme = scanner.scan(/'([^']|\\')*'/)) # Single quotes literal?
+      elsif (lexeme = scanner.scan(/'(?:\\'|[^'])*'/)) # Single quotes literal?
         unquoted = lexeme.gsub(/(^')|('$)/, '')
         token = build_token('STRING_LIT', unquoted)
       else # Unknown token
@@ -137,9 +137,9 @@ module SrlRuby
         col = scanner.pos - aLexeme.size - @line_start + 1
         pos = Position.new(@lineno, col)
         token = SrlToken.new(aLexeme, aSymbolName, pos)
-      rescue StandardError
+      rescue StandardError => exc
         puts "Failing with '#{aSymbolName}' and '#{aLexeme}'"
-        raise ex
+        raise exc
       end
 
       return token

data/lib/srl_ruby/version.rb

@@ -1,3 +1,3 @@
 module SrlRuby
-  VERSION = '0.2.0'.freeze
+  VERSION = '0.2.1'.freeze
 end

data/lib/srl_ruby.rb

@@ -42,6 +42,8 @@ module SrlRuby # This module is used as a namespace
 
     # Now output the regexp literal
     root = ast_ptree.root
+    # puts root.to_str # TODO remove this line
+    # pp root
     return Regexp.new(root.to_str)
   end
 end # module

data/spec/acceptance/srl_test_suite_spec.rb

@@ -39,19 +39,37 @@ RSpec.describe Acceptance do
   end
 
   it 'should match a backslash' do
-    puts __FILE__
     rule_file_repr = load_file('backslash.rule')
     test_rule_file(rule_file_repr)
   end
   
+  it 'should support named capture group' do
+    rule_file_repr = load_file('basename_capture_group.rule')
+    test_rule_file(rule_file_repr)
+  end
+  
+  it 'should match uppercase letter(s)' do
+    rule_file_repr = load_file('issue_17_uppercase_letter.rule')
+    test_rule_file(rule_file_repr)
+  end 
+  
   it 'should not trim literal strings' do
     rule_file_repr = load_file('literally_spaces.rule')
     test_rule_file(rule_file_repr)
-  end  
+  end 
+
+  it 'should match a tab' do
+    rule_file_repr = load_file('tab.rule')
+    test_rule_file(rule_file_repr)
+  end
+
+  it 'should match mail address' do
+    rule_file_repr = load_file('website_example_email.rule')
+    test_rule_file(rule_file_repr)
+  end
 
   it 'should support lookahead' do
     rule_file_repr = load_file('website_example_lookahead.rule')
     test_rule_file(rule_file_repr)
   end
-    
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: srl_ruby
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.2.1
 platform: ruby
 authors:
 - Dimitri Geshef
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-03-14 00:00:00.000000000 Z
+date: 2018-03-15 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rley