From 857025e216cd23ec9421452f80d5db9ad686aebf Mon Sep 17 00:00:00 2001
From: "Jamie (Bear) Murphy" <1613241+ITJamie@users.noreply.github.com>
Date: Fri, 20 May 2022 17:39:35 +0100
Subject: [PATCH] add unicode error catching
So i found this when i hit some non unicode files.
examples of some errors caught with this
this is a rough fix but at least allows tests to complete. without this catch the script would crash
```
unable to process file (path removed) due to unicode decode error
'utf-8' codec can't decode byte 0xa7 in position 195: invalid start byte
unable to process file (path removed) due to unicode decode error
'utf-8' codec can't decode byte 0xa1 in position 33: invalid start byte
```
---
zulint/custom_rules.py | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/zulint/custom_rules.py b/zulint/custom_rules.py
index c40ec16..7eab9b0 100644
--- a/zulint/custom_rules.py
+++ b/zulint/custom_rules.py
@@ -134,7 +134,12 @@ def custom_check_file(
failed = False
with open(fn, encoding="utf8") as f:
- contents = f.read()
+ try:
+ contents = f.read()
+ except UnicodeDecodeError as e:
+ print(f"unable to process file {fn} due to unicode decode error")
+ print(e)
+ return True
line_starts = [m.start() for m in re.finditer(r"^.", contents, re.M | re.S)]
rules_to_apply = self.get_rules_applying_to_fn(fn=fn, rules=self.rules)