Merge pull request #1435 from lark-parser/issue1434

Bugfix for issue #1434

Author: erezsh

lark/parsers/grammar_analysis.py

@@ -3,7 +3,7 @@
 from collections import Counter, defaultdict
 from typing import List, Dict, Iterator, FrozenSet, Set
 
-from ..utils import bfs, fzset, classify
+from ..utils import bfs, fzset, classify, OrderedSet
 from ..exceptions import GrammarError
 from ..grammar import Rule, Terminal, NonTerminal, Symbol
 from ..common import ParserConf
@@ -177,13 +177,13 @@ def __init__(self, parser_conf: ParserConf, debug: bool=False, strict: bool=Fals
 
         self.FIRST, self.FOLLOW, self.NULLABLE = calculate_sets(rules)
 
-    def expand_rule(self, source_rule: NonTerminal, rules_by_origin=None) -> State:
+    def expand_rule(self, source_rule: NonTerminal, rules_by_origin=None) -> OrderedSet[RulePtr]:
         "Returns all init_ptrs accessible by rule (recursive)"
 
         if rules_by_origin is None:
             rules_by_origin = self.rules_by_origin
 
-        init_ptrs = set()
+        init_ptrs = OrderedSet[RulePtr]()
         def _expand_rule(rule: NonTerminal) -> Iterator[NonTerminal]:
             assert not rule.is_term, rule
 
@@ -200,4 +200,4 @@ def _expand_rule(rule: NonTerminal) -> Iterator[NonTerminal]:
         for _ in bfs([source_rule], _expand_rule):
             pass
 
-        return fzset(init_ptrs)
+        return init_ptrs

lark/utils.py

@@ -341,3 +341,6 @@ def __bool__(self):
 
     def __len__(self) -> int:
         return len(self.d)
+
+    def __repr__(self):
+        return f"{type(self).__name__}({', '.join(map(repr,self))})"

tests/test_parser.py

@@ -975,6 +975,19 @@ def test_resolve_ambiguity_with_shared_node2(self):
             tree = l.parse("")
             self.assertEqual(tree, Tree('start', [Tree('x', [])]))
 
+
+        def test_consistent_derivation_order1(self):
+            # Should return the same result for any hash-seed
+            parser = Lark('''
+                start: a a
+                a: "." | b
+                b: "."
+            ''', lexer=LEXER)
+
+            tree = parser.parse('..')
+            n = Tree('a', [Tree('b', [])])
+            assert tree == Tree('start', [n, n])
+
     _NAME = "TestFullEarley" + LEXER.capitalize()
     _TestFullEarley.__name__ = _NAME
     globals()[_NAME] = _TestFullEarley