From 2c206bc16bfc9428e725d49ccc9f07975bffefc5 Mon Sep 17 00:00:00 2001
From: Ben Kurtovic <ben.kurtovic@gmail.com>
Date: Thu, 1 Nov 2018 01:20:53 -0400
Subject: [PATCH] Fix crash due to PyList_GET_SIZE being applied to a dict
 (fixes #208)

---
 CHANGELOG                                      | 1 +
 docs/changelog.rst                             | 2 ++
 mwparserfromhell/parser/ctokenizer/tokenizer.c | 2 +-
 3 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/CHANGELOG b/CHANGELOG
index 7a4cb25..7260006 100644
--- a/CHANGELOG
+++ b/CHANGELOG
@@ -4,6 +4,7 @@ v0.6 (unreleased):
 - Fixed signals getting stuck inside the C tokenizer until parsing finishes,
   in pathological cases. (#206)
 - Fixed <wbr> not being considered a single-only tag. (#200)
+- Fixed a C tokenizer crash on Python 3.7 when compiled with assertions. (#208)
 
 v0.5.1 (released March 3, 2018):
 
diff --git a/docs/changelog.rst b/docs/changelog.rst
index 4941f32..72971a3 100644
--- a/docs/changelog.rst
+++ b/docs/changelog.rst
@@ -15,6 +15,8 @@ Unreleased
   (`#206 <https://github.com/earwig/mwparserfromhell/issues/206>`)
 - Fixed `<wbr>` not being considered a single-only tag.
   (`#200 <https://github.com/earwig/mwparserfromhell/pull/200>`)
+- Fixed a C tokenizer crash on Python 3.7 when compiled with assertions.
+  (`#208 <https://github.com/earwig/mwparserfromhell/issues/208>`)
 
 v0.5.1
 ------
diff --git a/mwparserfromhell/parser/ctokenizer/tokenizer.c b/mwparserfromhell/parser/ctokenizer/tokenizer.c
index 9017909..24d0b4a 100644
--- a/mwparserfromhell/parser/ctokenizer/tokenizer.c
+++ b/mwparserfromhell/parser/ctokenizer/tokenizer.c
@@ -207,7 +207,7 @@ static int load_entities(void)
     if (!deflist)
         return -1;
     Py_DECREF(defmap);
-    numdefs = (unsigned) PyList_GET_SIZE(defmap);
+    numdefs = (unsigned) PyList_GET_SIZE(deflist);
     entitydefs = calloc(numdefs + 1, sizeof(char*));
     if (!entitydefs)
         return -1;