From 8842928963d265e35b9da2c1e2a2acadbee4151a Mon Sep 17 00:00:00 2001
From: Erez Sh <erezshin@gmail.com>
Date: Fri, 13 Dec 2019 09:30:41 +0200
Subject: [PATCH] Fixed multithreading bug in ContextualLexer (Issue #493)

---
 lark/lexer.py            | 19 +++++++------------
 lark/parser_frontends.py | 16 ++++++++++++----
 2 files changed, 19 insertions(+), 16 deletions(-)

diff --git a/lark/lexer.py b/lark/lexer.py
index 871b25e..9d26318 100644
--- a/lark/lexer.py
+++ b/lark/lexer.py
@@ -288,10 +288,7 @@ class Lexer(object):
 
     Method Signatures:
         lex(self, stream) -> Iterator[Token]
-
-        set_parser_state(self, state)   # Optional
     """
-    set_parser_state = NotImplemented
     lex = NotImplemented
 
 
@@ -349,6 +346,7 @@ class TraditionalLexer(Lexer):
 
 
 class ContextualLexer(Lexer):
+
     def __init__(self, terminals, states, ignore=(), always_accept=(), user_callbacks={}):
         tokens_by_name = {}
         for t in terminals:
@@ -371,18 +369,15 @@ class ContextualLexer(Lexer):
 
         self.root_lexer = TraditionalLexer(terminals, ignore=ignore, user_callbacks=user_callbacks)
 
-        self.set_parser_state(None) # Needs to be set on the outside
-
-    def set_parser_state(self, state):
-        self.parser_state = state
-
-    def lex(self, stream):
-        l = _Lex(self.lexers[self.parser_state], self.parser_state)
+    def lex(self, stream, get_parser_state):
+        parser_state = get_parser_state()
+        l = _Lex(self.lexers[parser_state], parser_state)
         try:
             for x in l.lex(stream, self.root_lexer.newline_types, self.root_lexer.ignore_types):
                 yield x
-                l.lexer = self.lexers[self.parser_state]
-                l.state = self.parser_state
+                parser_state = get_parser_state()
+                l.lexer = self.lexers[parser_state]
+                l.state = parser_state # For debug only, no need to worry about multithreading
         except UnexpectedCharacters as e:
             # In the contextual lexer, UnexpectedCharacters can mean that the terminal is defined,
             # but not in the current context.
diff --git a/lark/parser_frontends.py b/lark/parser_frontends.py
index ec82299..8b42772 100644
--- a/lark/parser_frontends.py
+++ b/lark/parser_frontends.py
@@ -79,14 +79,13 @@ class WithLexer(_ParserFrontend):
     def _serialize(self, data, memo):
         data['parser'] = data['parser'].serialize(memo)
 
-    def lex(self, text):
-        stream = self.lexer.lex(text)
+    def lex(self, *args):
+        stream = self.lexer.lex(*args)
         return self.postlex.process(stream) if self.postlex else stream
 
     def parse(self, text, start=None):
         token_stream = self.lex(text)
-        sps = self.lexer.set_parser_state
-        return self._parse(token_stream, start, *[sps] if sps is not NotImplemented else [])
+        return self._parse(token_stream, start)
 
     def init_traditional_lexer(self):
         self.lexer = TraditionalLexer(self.lexer_conf.tokens, ignore=self.lexer_conf.ignore, user_callbacks=self.lexer_conf.callbacks)
@@ -114,6 +113,15 @@ class LALR_ContextualLexer(LALR_WithLexer):
                                      ignore=self.lexer_conf.ignore,
                                      always_accept=always_accept,
                                      user_callbacks=self.lexer_conf.callbacks)
+
+
+    def parse(self, text, start=None):
+        parser_state = [None]
+        def set_parser_state(s):
+            parser_state[0] = s
+
+        token_stream = self.lex(text, lambda: parser_state[0])
+        return self._parse(token_stream, start, set_parser_state)
 ###}
 
 class LALR_CustomLexer(LALR_WithLexer):