srl_ruby 0.2.4 → 0.2.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 3642f7f1361cb920e2a9e42dcd8969d5ec75c7fe
-  data.tar.gz: 480c7561fd6972a8872e472166d07d0905c4612d
+  metadata.gz: 13bb293008059e97968eab3b976e05f7fe9c353e
+  data.tar.gz: 933e9531ae294fe4adb46e3c7ef87c58a3243388
 SHA512:
-  metadata.gz: d60a8e33fbf0b2fafdacf03127fe1502efd60bc5fc69de9d97fa9ddd07d0505d3c6577f0fb078277980b6a024f76f88887fcd01e0798f02f6b55c41ebef65bbe
-  data.tar.gz: 838e7c67fa30ac58d2fefffd701394db75a632087c2440aaaac0d2fb3b349857c79eefd446089b6ccb6878232ed56c987dcd669847b1b4aff2cf40025e0df20e
+  metadata.gz: 1c585bfad3f6330b87f47ab7c1dae115bc953a50220bc3d87642524c523cfbe1ae19193cfc0173730d456ec6691611abd59964ea4722a42bdbb1571f6c06ce9c
+  data.tar.gz: f835d81332961e020addee4ec8b5e4c46378f29ad12a7497fb03f5545eee1c884b1da5b8a621d4f76713b348b3b324fc96c4eb9f60b98037c1c7e9b98ab5d9c6

data/CHANGELOG.md

@@ -1,10 +1,11 @@
-## Unreleased
-### Added
+## [0.2.5] - 2018-04-02
+SrlRuby passes 12 tests out of 15 standard SRL tests in total. 
 ### Changed
-### Deprecated
-### Removed
-### Fixed
-### Security
+- Class `SrlRuby#Tokenizer` added keywords CARRIAGE, RETURN, VERTICAL, WORD
+- Grammar expanded to support 'CARRIAGE RETURN', 'VERTICAL TAB', 'WORD', 'NO WORD' expressions
+- Class `SrlRuby::ASTBuilder` updates to reflect changes in the grammar.
+- File `acceptance/srl_test_suite_spec.rb`. 12 test files from official test suite are passing.
+
 
 ## [0.2.4] - 2018-04-02
 SrlRuby passes 10 tests out of 15 standard SRL tests in total. 
@@ -74,3 +75,11 @@ SrlRuby passes 3 standard out of 15 standard SRL tests in total.
 ### Added
 - Initial working Github commit
 
+## Unreleased
+### Added
+### Changed
+### Deprecated
+### Removed
+### Fixed
+### Security
+

data/lib/srl_ruby/ast_builder.rb

@@ -276,6 +276,11 @@ module SrlRuby
     def reduce_tab(_production, _range, _tokens, _children)
       Regex::Character.new('\t')
     end
+    
+    # rule('special_char' => ' VERTICAL TAB').as 'vtab'
+    def reduce_vtab(_production, _range, _tokens, _children)
+      Regex::Character.new('\v')
+    end    
 
     # rule('special_char' => 'BACKSLASH').as 'backslash'
     def reduce_backslash(_production, _range, _tokens, _children)
@@ -288,6 +293,21 @@ module SrlRuby
       # TODO: control portability
       Regex::Character.new('\n')
     end
+    
+    # rule('special_char' => %w[CARRIAGE RETURN]).as 'carriage_return'
+    def reduce_carriage_return(_production, _range, _tokens, _children)
+      Regex::Character.new('\r')
+    end
+
+    # rule('special_char' => %w[WORD]).as 'word'
+    def reduce_word(_production, _range, _tokens, _children)
+      Regex::Anchor.new('\b')
+    end
+    
+    # rule('special_char' => %w[NO WORD]).as 'no word'
+    def reduce_no_word(_production, _range, _tokens, _children)
+      Regex::Anchor.new('\B')
+    end    
 
     # rule('literal' => %w[LITERALLY STRING_LIT]).as 'literally'
     def reduce_literally(_production, _range, _tokens, theChildren)

data/lib/srl_ruby/grammar.rb

@@ -12,8 +12,8 @@ module SrlRuby
     add_terminals('UPPERCASE', 'LETTER', 'FROM', 'TO')
     add_terminals('DIGIT', 'NUMBER', 'ANY', 'NO')
     add_terminals('CHARACTER', 'WHITESPACE', 'ANYTHING')
-    add_terminals('TAB', 'BACKSLASH', 'NEW', 'LINE')
-    add_terminals('OF', 'ONE')
+    add_terminals('TAB', 'BACKSLASH', 'NEW', 'LINE', 'WORD')
+    add_terminals('CARRIAGE', 'RETURN', 'VERTICAL', 'OF', 'ONE')
     add_terminals('EXACTLY', 'TIMES', 'ONCE', 'TWICE')
     add_terminals('BETWEEN', 'AND', 'OPTIONAL', 'OR')
     add_terminals('MORE', 'NEVER', 'AT', 'LEAST')
@@ -74,8 +74,12 @@ module SrlRuby
     rule('character_class' => 'ANYTHING').as 'anything'
     rule('character_class' => %w[ONE OF STRING_LIT]).as 'one_of'
     rule('special_char' => 'TAB').as 'tab'
+    rule('special_char' => 'VERTICAL TAB').as 'vtab'
     rule('special_char' => 'BACKSLASH').as 'backslash'
     rule('special_char' => %w[NEW LINE]).as 'new_line'
+    rule('special_char' => %w[CARRIAGE RETURN]).as 'carriage_return'
+    rule('special_char' => %w[WORD]).as 'word'
+    rule('special_char' => %w[NO WORD]).as 'no_word'
     rule('literal' => %w[LITERALLY STRING_LIT]).as 'literally'
     rule('alternation' => %w[ANY OF LPAREN alternatives RPAREN]).as 'any_of'
     rule('alternatives' => %w[alternatives separator quantifiable]).as 'alternative_list'

data/lib/srl_ruby/tokenizer.rb

@@ -38,6 +38,7 @@ module SrlRuby
       BETWEEN
       BY
       CAPTURE
+      CARRIAGE
       CASE
       CHARACTER
       DIGIT
@@ -66,6 +67,7 @@ module SrlRuby
       ONE
       OPTIONAL
       OR
+      RETURN
       STARTS
       TAB
       TIMES
@@ -73,8 +75,10 @@ module SrlRuby
       TWICE
       UNTIL
       UPPERCASE
+      VERTICAL
       WHITESPACE
       WITH
+      WORD
     ].map { |x| [x, x] } .to_h
 
     class ScanError < StandardError; end

data/lib/srl_ruby/version.rb

@@ -1,3 +1,3 @@
 module SrlRuby
-  VERSION = '0.2.4'.freeze
+  VERSION = '0.2.5'.freeze
 end

data/spec/acceptance/srl_test_suite_spec.rb

@@ -61,6 +61,11 @@ RSpec.describe Acceptance do
     rule_file_repr = load_file('literally_spaces.rule')
     test_rule_file(rule_file_repr)
   end
+  
+  it 'should support non word boundary' do
+    rule_file_repr = load_file('no_word.rule')
+    test_rule_file(rule_file_repr)
+  end
 
   it 'should match non digit pattern' do
     rule_file_repr = load_file('nondigit.rule')
@@ -87,8 +92,13 @@ RSpec.describe Acceptance do
     test_rule_file(rule_file_repr)
   end
 
-  it 'should' do
+  it 'should process an URL' do
     rule_file_repr = load_file('website_example_url.rule')
     test_rule_file(rule_file_repr)
   end
+  
+  it 'should match a word boundary' do
+    rule_file_repr = load_file('word.rule')
+    test_rule_file(rule_file_repr)
+  end  
 end

data/spec/srl_ruby_spec.rb

@@ -100,6 +100,11 @@ describe SrlRuby do
       regexp = SrlRuby.parse('tab')
       expect(regexp.source).to eq('\t')
     end
+    
+    it "should parse 'vertical tab' syntax" do
+      regexp = SrlRuby.parse('vertical tab')
+      expect(regexp.source).to eq('\v')
+    end
 
     it "should parse 'backslash' syntax" do
       regexp = SrlRuby.parse('backslash')
@@ -110,6 +115,21 @@ describe SrlRuby do
       regexp = SrlRuby.parse('new line')
       expect(regexp.source).to eq('\n')
     end
+    
+    it "should parse 'carriage return' syntax" do
+      regexp = SrlRuby.parse('carriage return')
+      expect(regexp.source).to eq('\r')
+    end 
+
+    it "should parse 'word' syntax" do
+      regexp = SrlRuby.parse('word, literally "is"')
+      expect(regexp.source).to eq('\bis')
+    end 
+
+    it "should parse 'no word' syntax" do
+      regexp = SrlRuby.parse('no word, literally "is"')
+      expect(regexp.source).to eq('\Bis')
+    end    
   end # context
 
   context 'Parsing alternations:' do

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: srl_ruby
 version: !ruby/object:Gem::Version
-  version: 0.2.4
+  version: 0.2.5
 platform: ruby
 authors:
 - Dimitri Geshef