Detect when a 4.x data file is being read. #886

3 files changed, 32 insertions, 6 deletions

diff --git a/CHANGES.rst b/CHANGES.rst
index 37f36080..bd36d953 100644
--- a/CHANGES.rst
+++ b/CHANGES.rst
@@ -24,6 +24,11 @@ want to know what's different in 5.0 since 4.5.x, see :ref:`whatsnew5x`.
 Unreleased
 ----------
 
+- If a 4.x data file is the cause of a "file is not a database" error, then use
+  a more specific error message, "Looks like a coverage 4.x data file, are you
+  mixing versions of coverage?"  Helps diagnose the problems described in
+  `issue 886`_.
+
 - Measurement contexts and relative file names didn't work together, as
   reported in `issue_899`_ and `issue_900`_.  This is now fixed, thanks to
   David Szotten.
@@ -37,6 +42,7 @@ Unreleased
   different drive (`issue 895`_).  Thanks, Olivier Grisel.
 
 .. _issue 880: https://github.com/nedbat/coveragepy/issues/880
+.. _issue 886: https://github.com/nedbat/coveragepy/issues/886
 .. _issue 895: https://github.com/nedbat/coveragepy/issues/895
 .. _issue 899: https://github.com/nedbat/coveragepy/issues/899
 .. _issue 900: https://github.com/nedbat/coveragepy/issues/900
diff --git a/coverage/sqldata.py b/coverage/sqldata.py
index 01f5ce01..613a280c 100644
--- a/coverage/sqldata.py
+++ b/coverage/sqldata.py
@@ -1031,7 +1031,20 @@ class SqliteDb(SimpleReprMixin):
         try:
             return self.con.execute(sql, parameters)
         except sqlite3.Error as exc:
-            raise CoverageException("Couldn't use data file {!r}: {}".format(self.filename, exc))
+            msg = str(exc)
+            try:
+                # `execute` is the first thing we do with the database, so try
+                # hard to provide useful hints if something goes wrong now.
+                with open(self.filename, "rb") as bad_file:
+                    cov4_sig = b"!coverage.py: This is a private format"
+                    if bad_file.read(len(cov4_sig)) == cov4_sig:
+                        msg = (
+                            "Looks like a coverage 4.x data file. "
+                            "Are you mixing versions of coverage?"
+                        )
+            except Exception:
+                pass
+            raise CoverageException("Couldn't use data file {!r}: {}".format(self.filename, msg))
 
     def executemany(self, sql, data):
         """Same as :meth:`python:sqlite3.Connection.executemany`."""
diff --git a/tests/test_api.py b/tests/test_api.py
index 8fa81d07..30a90c3c 100644
--- a/tests/test_api.py
+++ b/tests/test_api.py
@@ -295,6 +295,17 @@ class ApiTest(CoverageTest):
         with self.assertRaisesRegex(CoverageException, "No data to report."):
             cov.report()
 
+    def test_cov4_data_file(self):
+        cov4_data = (
+            "!coverage.py: This is a private format, don't read it directly!"
+            '{"lines":{"/private/tmp/foo.py":[1,5,2,3]}}'
+        )
+        self.make_file(".coverage", cov4_data)
+        cov = coverage.Coverage()
+        with self.assertRaisesRegex(CoverageException, "Looks like a coverage 4.x data file"):
+            cov.load()
+        cov.erase()
+
     def make_code1_code2(self):
         """Create the code1.py and code2.py files."""
         self.make_file("code1.py", """\
@@ -384,15 +395,11 @@ class ApiTest(CoverageTest):
         cov.save()
         self.assert_file_count(".coverage.*", 2)
 
-    def make_bad_data_file(self):
-        """Make one bad data file."""
-        self.make_file(".coverage.foo", """La la la, this isn't coverage data!""")
-
     def test_combining_corrupt_data(self):
         # If you combine a corrupt data file, then you will get a warning,
         # and the file will remain.
         self.make_good_data_files()
-        self.make_bad_data_file()
+        self.make_file(".coverage.foo", """La la la, this isn't coverage data!""")
         cov = coverage.Coverage()
         warning_regex = (
             r"Couldn't use data file '.*\.coverage\.foo': file (is encrypted or )?is not a database"