Post-merge fixed for end_symbol, + two more tests (Issue #237)

lark/load_grammar.py

@@ -91,12 +91,8 @@ TERMINALS = {
     '_IGNORE': r'%ignore',
     '_DECLARE': r'%declare',
     '_IMPORT': r'%import',
-<<<<<<< HEAD
     'NUMBER': r'[+-]?\d+',
-=======
-    'NUMBER': r'\d+',
     '_END': r'\$',
->>>>>>> end_symbol
 }
 
 RULES = {
@@ -137,12 +133,8 @@ RULES = {
     '?name': ['RULE', 'TERMINAL'],
 
     'maybe': ['_LBRA expansions _RBRA'],
-<<<<<<< HEAD
     'range': ['STRING _DOTDOT STRING'],
-=======
-    'range': ['STRING _DOT _DOT STRING'],
     'end': ['_END'],
->>>>>>> end_symbol
 
     'term': ['TERMINAL _COLON expansions _NL',
               'TERMINAL _DOT NUMBER _COLON expansions _NL'],

lark/parsers/lalr_analysis.py

@@ -178,7 +178,7 @@ class LALR_Analyzer(GrammarAnalyzer):
             assert(len(root.kernel) == 1)
             for rp in root.kernel:
                 assert(rp.index == 0)
-                self.directly_reads[(root, rp.next)] = set([ Terminal('$END') ])
+                self.directly_reads[(root, rp.next)] = set([ Terminal(END) ])
 
         for state in self.lr0_states:
             seen = set()

lark/parsers/lalr_parser.py

@@ -97,9 +97,13 @@ class _Parser:
         token = Token.new_borrow_pos(END, None, token) if token else Token(END, None, 0, 1, 1)
         while True:
             _action, arg = get_action(token)
-            assert(_action is Reduce)
-            reduce(arg)
-            if state_stack[-1] == end_state:
-                return value_stack[-1]
+            if _action is Shift:
+                state_stack.append(arg)
+                value_stack.append(token)
+            else:
+                assert(_action is Reduce)
+                reduce(arg)
+                if state_stack[-1] == end_state:
+                    return value_stack[-1]
 
 ###}

tests/test_parser.py

@@ -1660,6 +1660,30 @@ def _make_parser_test(LEXER, PARSER):
             self.assertEqual(parser.parse('a'), Tree('start', [Tree('a', [])]))
             self.assertRaises(UnexpectedInput, parser.parse, 'ab')
 
+        @unittest.skipIf(PARSER!='lalr', "Using the end symbol currently works for LALR only")
+        def test_end_symbol2(self):
+            grammar = """
+                start: (a|b)+
+                a: "a" ("x"|$)
+                b: "b"
+            """
+            parser = _Lark(grammar)
+
+            self.assertEqual(parser.parse('axa'), Tree('start', [Tree('a', []),Tree('a', [])]))
+            self.assertRaises(UnexpectedInput, parser.parse, 'ab')
+
+        @unittest.skipIf(PARSER!='lalr', "Using the end symbol currently works for LALR only")
+        def test_end_symbol3(self):
+            grammar = """
+                start: (a|b)+
+                a: "a" (e|"x")
+                b: "b"
+                e: $
+            """
+            parser = _Lark(grammar)
+
+            self.assertEqual(parser.parse('axa'), Tree('start', [Tree('a', []),Tree('a', [Tree('e', [])])]))
+            self.assertRaises(UnexpectedInput, parser.parse, 'ab')
 
         @unittest.skipIf(PARSER!='lalr' or LEXER=='custom', "Serialize currently only works for LALR parsers without custom lexers (though it should be easy to extend)")
         def test_serialize(self):