Prevent pyexpat.c from being recorded as source code. #419

3 files changed, 20 insertions, 2 deletions

diff --git a/CHANGES.rst b/CHANGES.rst
index 349247ff..610ea4bf 100644
--- a/CHANGES.rst
+++ b/CHANGES.rst
@@ -15,7 +15,11 @@ Version 4.1
   are seeing corrupt data files, but this lets them continue combining anyway.
   Prompted by `issue 418`_.
 
+- Pyexpat C code will no longer be recorded as a source file, fixing
+  `issue 419`_.
+
 .. _issue 418: https://bitbucket.org/ned/coveragepy/issues/418/json-parse-error
+.. _issue 419: https://bitbucket.org/ned/coveragepy/issues/419/nosource-no-source-for-code-path-to-c
 
 
 Version 4.0 --- 20 September 2015
diff --git a/coverage/control.py b/coverage/control.py
index 77737181..a5741a47 100644
--- a/coverage/control.py
+++ b/coverage/control.py
@@ -7,6 +7,7 @@ import atexit
 import inspect
 import os
 import platform
+import re
 import sys
 import traceback
 
@@ -289,7 +290,7 @@ class Coverage(object):
             # environments (virtualenv, for example), these modules may be
             # spread across a few locations. Look at all the candidate modules
             # we've imported, and take all the different ones.
-            for m in (atexit, inspect, os, platform, _structseq, traceback):
+            for m in (atexit, inspect, os, platform, re, _structseq, traceback):
                 if m is not None and hasattr(m, "__file__"):
                     self.pylib_dirs.add(self._canonical_dir(m))
             if _structseq and not hasattr(_structseq, '__file__'):
@@ -475,6 +476,11 @@ class Coverage(object):
             # can't do anything with the data later anyway.
             return nope(disp, "not a real file name")
 
+        # pyexpat does a dumb thing, calling the trace function explicitly from
+        # C code with a C file name.
+        if re.search(r"[/\\]Modules[/\\]pyexpat.c", filename):
+            return nope(disp, "pyexpat lies about itself")
+
         # Jython reports the .class file to the tracer, use the source file.
         if filename.endswith("$py.class"):
             filename = filename[:-9] + ".py"
@@ -805,7 +811,7 @@ class Coverage(object):
         """
         self._init()
         if not self._measured:
-            return
+            return self.data
 
         self.collector.save_data(self.data)
 
diff --git a/tests/test_oddball.py b/tests/test_oddball.py
index 2ca1aa75..bca7f127 100644
--- a/tests/test_oddball.py
+++ b/tests/test_oddball.py
@@ -226,6 +226,14 @@ class PyexpatTest(CoverageTest):
         self.assertEqual(statements, [101, 102])
         self.assertEqual(missing, [])
 
+        # Make sure pyexpat isn't recorded as a source file.
+        # https://bitbucket.org/ned/coveragepy/issues/419/nosource-no-source-for-code-path-to-c
+        files = cov.get_data().measured_files()
+        self.assertFalse(
+            any(f.endswith("pyexpat.c") for f in files),
+            "Pyexpat.c is in the measured files!: %r:" % (files,)
+        )
+
 
 class ExceptionTest(CoverageTest):
     """I suspect different versions of Python deal with exceptions differently