Don't collapse in an ascii-only file-world. #533

4 files changed, 30 insertions, 12 deletions

diff --git a/CHANGES.rst b/CHANGES.rst
index 865d105..1ff0dbb 100644
--- a/CHANGES.rst
+++ b/CHANGES.rst
@@ -43,6 +43,8 @@ Unreleased
 - Fixed an unusual bug involving multiple coding declarations affecting code
   containing code in multi-line strings: `issue 529`_.
 
+- Deal properly with non-ASCII file names in an ASCII-only world, `issue 533`_.
+
 - Prevented deprecation warnings from configparser that happened in some
   circumstances, closing `issue 530`_.
 
@@ -59,6 +61,7 @@ Unreleased
 .. _issue 525: https://bitbucket.org/ned/coveragepy/issues/525/coverage-combine-when-not-in-parallel-mode
 .. _issue 529: https://bitbucket.org/ned/coveragepy/issues/529/encoding-marker-may-only-appear-on-the
 .. _issue 530: https://bitbucket.org/ned/coveragepy/issues/530/deprecationwarning-you-passed-a-bytestring
+.. _issue 533: https://bitbucket.org/ned/coveragepy/issues/533/exception-on-unencodable-file-name
 
 
 Version 4.2 --- 2016-07-26
diff --git a/coverage/files.py b/coverage/files.py
index 9de4849..af2fe52 100644
--- a/coverage/files.py
+++ b/coverage/files.py
@@ -63,7 +63,11 @@ def canonical_filename(filename):
                 if path is None:
                     continue
                 f = os.path.join(path, filename)
-                if os.path.exists(f):
+                try:
+                    exists = os.path.exists(f)
+                except UnicodeError:
+                    exists = False
+                if exists:
                     filename = f
                     break
         cf = abs_file(filename)
@@ -147,7 +151,11 @@ else:
 def abs_file(filename):
     """Return the absolute normalized form of `filename`."""
     path = os.path.expandvars(os.path.expanduser(filename))
-    path = os.path.abspath(os.path.realpath(path))
+    try:
+        path = os.path.realpath(path)
+    except UnicodeError:
+        pass
+    path = os.path.abspath(path)
     path = actual_path(path)
     path = unicode_filename(path)
     return path
diff --git a/tests/test_api.py b/tests/test_api.py
index 1018ff0..6f14210 100644
--- a/tests/test_api.py
+++ b/tests/test_api.py
@@ -100,16 +100,6 @@ class ApiTest(CoverageTest):
         filename, _, _, _ = cov.analysis(sys.modules["mymod"])
         self.assertEqual(os.path.basename(filename), "mymod.py")
 
-    def test_unencodable_filename(self):
-        code = """a = 1\nb = 2\n"""
-        cov = coverage.Coverage()
-        cov.start()
-        globs = {}
-        exec(compile(code, "wut\xe9\xea\xeb\xec\x01\x02.py", 'exec'), globs)
-        cov.stop()
-        self.assertEqual(globs['a'], 1)
-        self.assertEqual(globs['b'], 2)
-
     def test_ignore_stdlib(self):
         self.make_file("mymain.py", """\
             import colorsys
diff --git a/tests/test_process.py b/tests/test_process.py
index aa2045f..62b6dc8 100644
--- a/tests/test_process.py
+++ b/tests/test_process.py
@@ -721,6 +721,23 @@ class ProcessTest(CoverageTest):
         # about 5.
         self.assertGreater(data.line_counts()['os.py'], 50)
 
+    def test_lang_c(self):
+        # LANG=C forces getfilesystemencoding on Linux to 'ascii', which causes
+        # failures with non-ascii file names. We don't want to make a real file
+        # with strange characters, though, because that gets the test runners
+        # tangled up.  This will isolate the concerns to the coverage.py code.
+        # https://bitbucket.org/ned/coveragepy/issues/533/exception-on-unencodable-file-name
+        self.make_file("weird_file.py", r"""
+            globs = {}
+            code = "a = 1\nb = 2\n"
+            exec(compile(code, "wut\xe9\xea\xeb\xec\x01\x02.py", 'exec'), globs)
+            print(globs['a'])
+            print(globs['b'])
+            """)
+        self.set_environ("LANG", "C")
+        out = self.run_command("python -m coverage run weird_file.py")
+        self.assertEqual(out, "1\n2\n")
+
     def test_deprecation_warnings(self):
         # Test that coverage doesn't trigger deprecation warnings.
         # https://bitbucket.org/ned/coveragepy/issue/305/pendingdeprecationwarning-the-imp-module