Non-ascii characters work again in config regexes. Fixes #455.

4 files changed, 28 insertions, 2 deletions

diff --git a/CHANGES.rst b/CHANGES.rst
index 923e100d..72d39ad0 100644
--- a/CHANGES.rst
+++ b/CHANGES.rst
@@ -19,9 +19,12 @@ Unreleased
 - Files with two encoding declarations are properly supported, fixing
   `issue 453`_. Thanks, Max Linke.
 
+- Non-ascii characters in regexes in the configuration file worked in 3.7, but
+  stopped working in 4.0.  Now they work again, closing `issue 455`_.
 
 .. _issue 131: https://bitbucket.org/ned/coveragepy/issues/131/pragma-on-a-decorator-line-should-affect
 .. _issue 453: https://bitbucket.org/ned/coveragepy/issues/453/source-code-encoding-can-only-be-specified
+.. _issue 455: https://bitbucket.org/ned/coveragepy/issues/455/unusual-exclusions-stopped-working-in
 
 
 Version 4.0.3 --- 2015-11-24
diff --git a/coverage/parser.py b/coverage/parser.py
index 7b8a60f1..884d40cb 100644
--- a/coverage/parser.py
+++ b/coverage/parser.py
@@ -9,6 +9,7 @@ import re
 import token
 import tokenize
 
+from coverage import env
 from coverage.backward import range    # pylint: disable=redefined-builtin
 from coverage.backward import bytes_to_ints
 from coverage.bytecode import ByteCodes, CodeObjects
@@ -95,7 +96,10 @@ class PythonParser(object):
         part of it.
 
         """
-        regex_c = re.compile(join_regex(regexes))
+        combined = join_regex(regexes)
+        if env.PY2:
+            combined = combined.decode("utf8")
+        regex_c = re.compile(combined)
         matches = set()
         for i, ltext in enumerate(self.lines, start=1):
             if regex_c.search(ltext):
diff --git a/tests/test_config.py b/tests/test_config.py
index 93a7bbf6..5667e930 100644
--- a/tests/test_config.py
+++ b/tests/test_config.py
@@ -379,11 +379,18 @@ class ConfigFileTest(CoverageTest):
 
     def test_non_ascii(self):
         self.make_file(".coveragerc", """\
+            [report]
+            exclude_lines =
+                first
+                ✘${TOX_ENVNAME}
+                third
             [html]
             title = tabblo & «ταБЬℓσ» # numbers
             """)
+        self.set_environ("TOX_ENVNAME", "weirdo")
         cov = coverage.Coverage()
 
+        self.assertEqual(cov.config.exclude_list, ["first", "✘weirdo", "third"])
         self.assertEqual(cov.config.html_title, "tabblo & «ταБЬℓσ» # numbers")
 
     def test_unreadable_config(self):
diff --git a/tests/test_coverage.py b/tests/test_coverage.py
index 9e2a444c..02da2032 100644
--- a/tests/test_coverage.py
+++ b/tests/test_coverage.py
@@ -1,3 +1,4 @@
+# coding: utf-8
 # Licensed under the Apache License: http://www.apache.org/licenses/LICENSE-2.0
 # For details: https://bitbucket.org/ned/coveragepy/src/default/NOTICE.txt
 
@@ -1128,7 +1129,7 @@ class ExcludeTest(CoverageTest):
         self.check_coverage("""\
             a = 1; b = 2
 
-            if 0:
+            if len([]):
                 a = 4   # -cc
             """,
             [1,3], "", excludes=['-cc'])
@@ -1478,6 +1479,17 @@ class ExcludeTest(CoverageTest):
             """,
             [8,9], "", excludes=['#pragma: NO COVER'])
 
+    def test_excludes_non_ascii(self):
+        self.check_coverage("""\
+            # coding: utf-8
+            a = 1; b = 2
+
+            if len([]):
+                a = 5   # ✘cover
+            """,
+            [2, 4], "", excludes=['✘cover']
+        )
+
 
 class Py24Test(CoverageTest):
     """Tests of new syntax in Python 2.4."""