From 477513171700dddfdb91c3541f7f43368bd4a30f Mon Sep 17 00:00:00 2001
From: Ben Kurtovic <ben.kurtovic@gmail.com>
Date: Sat, 30 Mar 2019 22:49:53 -0400
Subject: [PATCH] Fix not memoizing bad routes after failing inside a table
 (fixes #206)

---
 CHANGELOG                                      |  1 +
 docs/changelog.rst                             |  2 ++
 mwparserfromhell/parser/ctokenizer/tok_parse.c |  1 +
 mwparserfromhell/parser/tokenizer.py           |  1 +
 tests/tokenizer/tables.mwtest                  | 14 ++++++++++++++
 5 files changed, 19 insertions(+)

diff --git a/CHANGELOG b/CHANGELOG
index c27e826..14ec205 100644
--- a/CHANGELOG
+++ b/CHANGELOG
@@ -3,6 +3,7 @@ v0.6 (unreleased):
 - Fixed manual construction of Node objects, previously unsupported. (#214)
 - Fixed Wikicode transformation methods (replace(), remove(), etc.) when passed
   an empty section as an argument. (#212)
+- Fixed the parser getting stuck inside malformed tables. (#206)
 
 v0.5.2 (released November 1, 2018):
 
diff --git a/docs/changelog.rst b/docs/changelog.rst
index e12f74e..2a222e3 100644
--- a/docs/changelog.rst
+++ b/docs/changelog.rst
@@ -12,6 +12,8 @@ Unreleased
 - Fixed :class:`.Wikicode` transformation methods (:meth:`.Wikicode.replace`,
   :meth:`.Wikicode.remove`, etc.) when passed an empty section as an argument.
   (`#212 <https://github.com/earwig/mwparserfromhell/issues/212>`_)
+- Fixed the parser getting stuck inside malformed tables.
+  (`#206 <https://github.com/earwig/mwparserfromhell/issues/206>`_)
 
 v0.5.2
 ------
diff --git a/mwparserfromhell/parser/ctokenizer/tok_parse.c b/mwparserfromhell/parser/ctokenizer/tok_parse.c
index 3a2cda9..6d34cfb 100644
--- a/mwparserfromhell/parser/ctokenizer/tok_parse.c
+++ b/mwparserfromhell/parser/ctokenizer/tok_parse.c
@@ -2254,6 +2254,7 @@ static int Tokenizer_parse_table(Tokenizer* self)
         Py_DECREF(padding);
         Py_DECREF(style);
         while (!Tokenizer_IS_CURRENT_STACK(self, restore_point)) {
+            Tokenizer_memoize_bad_route(self);
             trash = Tokenizer_pop(self);
             Py_XDECREF(trash);
         }
diff --git a/mwparserfromhell/parser/tokenizer.py b/mwparserfromhell/parser/tokenizer.py
index a9a02cc..a68c132 100644
--- a/mwparserfromhell/parser/tokenizer.py
+++ b/mwparserfromhell/parser/tokenizer.py
@@ -1133,6 +1133,7 @@ class Tokenizer(object):
             table = self._parse(contexts.TABLE_OPEN)
         except BadRoute:
             while self._stack_ident != restore_point:
+                self._memoize_bad_route()
                 self._pop()
             self._head = reset
             self._emit_text("{")
diff --git a/tests/tokenizer/tables.mwtest b/tests/tokenizer/tables.mwtest
index 16012cf..b8e92cf 100644
--- a/tests/tokenizer/tables.mwtest
+++ b/tests/tokenizer/tables.mwtest
@@ -408,3 +408,17 @@ name:   junk_after_table_row
 label:  ignore junk on the first line of a table row
 input:  "{|\n|- foo="bar" | baz\n|blerp\n|}"
 output: [TagOpenOpen(wiki_markup="{|"), Text(text="table"), TagCloseOpen(padding="\n"), TagOpenOpen(wiki_markup="|-"), Text(text="tr"), TagAttrStart(pad_first=" ", pad_before_eq="", pad_after_eq=""), Text(text="foo"), TagAttrEquals(), TagAttrQuote(char='"'), Text(text="bar"), TagAttrStart(pad_first=" ", pad_before_eq=" ", pad_after_eq=""), Text(text="|"), TagAttrStart(pad_first="", pad_before_eq="", pad_after_eq=""), Text(text="baz"), TagCloseOpen(padding="\n"), TagOpenOpen(wiki_markup="|"), Text(text="td"), TagCloseOpen(padding=""), Text(text="blerp\n"), TagOpenClose(wiki_markup=""), Text(text="td"), TagCloseClose(), TagOpenClose(wiki_markup=""), Text(text="tr"), TagCloseClose(), TagOpenClose(wiki_markup="|}"), Text(text="table"), TagCloseClose()]
+
+---
+
+name:   incomplete_nested_open_only
+label:  many nested incomplete tables: table open only
+input:  "{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|"
+output: [Text(text="{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|\n{|")]
+
+---
+
+name:   incomplete_nested_open_and_row
+label:  many nested incomplete tables: table open and row separator (see issue #206)
+input:  "{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-"
+output: [Text(text="{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-\n{|\n|-")]