fix: safe_repr for cyrillic (getsentry#79)

untitaker · web-flow · commit 1d548224b17b · 2018-09-25T15:07:10.000+02:00
* fix: safe_repr for cyrillic

* fix: Coding hint for Py2

* fix: Fix another py2 issue

* fix: remove unused import
diff --git a/sentry_sdk/utils.py b/sentry_sdk/utils.py
@@ -260,11 +260,25 @@ def safe_repr(value):
         rv = repr(value)
         if isinstance(rv, bytes):
             rv = rv.decode("utf-8", "replace")
+
+        # At this point `rv` contains a bunch of literal escape codes, like
+        # this (exaggerated example):
+        #
+        # u"\\x2f"
+        #
+        # But we want to show this string as:
+        #
+        # u"/"
         try:
-            return rv.encode("utf-8").decode("unicode-escape")
+            # unicode-escape does this job, but can only decode latin1. So we
+            # attempt to encode in latin1.
+            return rv.encode("latin1").decode("unicode-escape")
         except Exception:
+            # Since usually strings aren't latin1 this can break. In those
+            # cases we just give up.
             return rv
     except Exception:
+        # If e.g. the call to `repr` already fails
         return u"<broken repr>"
 
 
diff --git a/tests/test_utils.py b/tests/test_utils.py
@@ -1,7 +1,8 @@
+# coding: utf-8
 import sys
 import os
 
-from hypothesis import given, assume
+from hypothesis import given
 import hypothesis.strategies as st
 
 from sentry_sdk.utils import safe_repr, exceptions_from_error_tuple
@@ -17,15 +18,8 @@ def test_safe_repr_never_broken_for_strings(x):
     assert u"broken repr" not in r
 
 
-@given(x=any_string)
-def test_safe_repr_never_leaves_escapes_in(x):
-    if isinstance(x, bytes):
-        assume(b"\\u" not in x and b"\\x" not in x)
-    else:
-        assume(u"\\u" not in x and u"\\x" not in x)
-    r = safe_repr(x)
-    assert isinstance(r, text_type)
-    assert u"\\u" not in r and u"\\x" not in r
+def test_safe_repr_regressions():
+    assert u"лошадь" in safe_repr(u"лошадь")
 
 
 def test_abs_path():
