Add debug flag to Early and XEarley to allow dumping the SPPF

lark/parser_frontends.py

@@ -139,7 +139,8 @@ class Earley(WithLexer):
         self.init_traditional_lexer()
 
         resolve_ambiguity = options.ambiguity == 'resolve'
-        self.parser = earley.Parser(parser_conf, self.match, resolve_ambiguity=resolve_ambiguity)
+        debug = options.debug if options else False
+        self.parser = earley.Parser(parser_conf, self.match, resolve_ambiguity=resolve_ambiguity, debug=debug)
 
     def match(self, term, token):
         return term.name == token.type
@@ -152,10 +153,12 @@ class XEarley(_ParserFrontend):
 
         self._prepare_match(lexer_conf)
         resolve_ambiguity = options.ambiguity == 'resolve'
+        debug = options.debug if options else False
         self.parser = xearley.Parser(parser_conf,
                                     self.match,
                                     ignore=lexer_conf.ignore,
                                     resolve_ambiguity=resolve_ambiguity,
+                                    debug=debug,
                                     **kw
                                     )
 

lark/parsers/earley.py

@@ -20,10 +20,11 @@ from .earley_common import Item, TransitiveItem
 from .earley_forest import ForestToTreeVisitor, ForestSumVisitor, SymbolNode, ForestToAmbiguousTreeVisitor
 
 class Parser:
-    def __init__(self, parser_conf, term_matcher, resolve_ambiguity=True):
+    def __init__(self, parser_conf, term_matcher, resolve_ambiguity=True, debug=False):
         analysis = GrammarAnalyzer(parser_conf)
         self.parser_conf = parser_conf
         self.resolve_ambiguity = resolve_ambiguity
+        self.debug = debug
 
         self.FIRST = analysis.FIRST
         self.NULLABLE = analysis.NULLABLE
@@ -296,6 +297,10 @@ class Parser:
         # symbol should have been completed in the last step of the Earley cycle, and will be in
         # this column. Find the item for the start_symbol, which is the root of the SPPF tree.
         solutions = [n.node for n in columns[-1] if n.is_complete and n.node is not None and n.s == start_symbol and n.start == 0]
+        if self.debug:
+            from .earley_forest import ForestToPyDotVisitor
+            debug_walker = ForestToPyDotVisitor()
+            debug_walker.visit(solutions[0], "sppf.png")
 
         if not solutions:
             expected_tokens = [t.expect for t in to_scan]

lark/parsers/xearley.py

@@ -24,8 +24,8 @@ from .earley_forest import SymbolNode
 
 
 class Parser(BaseParser):
-    def __init__(self,  parser_conf, term_matcher, resolve_ambiguity=True, ignore = (), complete_lex = False):
-        BaseParser.__init__(self, parser_conf, term_matcher, resolve_ambiguity)
+    def __init__(self,  parser_conf, term_matcher, resolve_ambiguity=True, ignore = (), complete_lex = False, debug=False):
+        BaseParser.__init__(self, parser_conf, term_matcher, resolve_ambiguity, debug)
         self.ignore = [Terminal(t) for t in ignore]
         self.complete_lex = complete_lex