python3 str handling

In python3 ctypes, a str is passed to ctypes as wchar*.  This means
the layout of the string magic looks like [ascii, null, ascii, null,
etc].  For some reason, magic handles this just fine most of the time,
but it's clearly wrong and I'm amazed it worked at all.

3 files changed, 15 insertions, 1 deletions

diff --git a/magic.py b/magic.py
index a97e929..8637c95 100644
--- a/magic.py
+++ b/magic.py
@@ -72,6 +72,11 @@ class Magic:
         """
         with self.lock:
             try:
+                # if we're on python3, convert buf to bytes
+                # otherwise this string is passed as wchar*
+                # which is not what libmagic expects
+                if type(buf) == str and str != bytes:
+                   buf = buf.encode('utf-8', errors='replace')
                 return maybe_decode(magic_buffer(self.cookie, buf))
             except MagicException as e:
                 return self._handle509Bug(e)
diff --git a/test/run.sh b/test/run.sh
index 3768497..2764e15 100755
--- a/test/run.sh
+++ b/test/run.sh
@@ -1,12 +1,14 @@
 #!/bin/sh
 
-set -e
 
 # ensure we can use unicode filenames in the test
 export LC_ALL=en_US.UTF-8
 THISDIR=`dirname $0`
 export PYTHONPATH=${THISDIR}/..
 
+echo "python2.6"
 python2.6 ${THISDIR}/test.py
+echo "python2.7"
 python2.7 ${THISDIR}/test.py
+echo "python3.0"
 python3 ${THISDIR}/test.py
diff --git a/test/test.py b/test/test.py
index 6ae5c07..78ddb2b 100755
--- a/test/test.py
+++ b/test/test.py
@@ -30,6 +30,13 @@ class MagicTest(unittest.TestCase):
                     break
             else:
                 self.assertTrue(False, "no match for " + repr(expected_value))
+
+    def test_from_buffer_str_and_bytes(self):
+        m = magic.Magic(mime=True)
+        s = '#!/usr/bin/env python\nprint("foo")'
+        self.assertEqual("text/x-python", m.from_buffer(s))
+        b = b'#!/usr/bin/env python\nprint("foo")'
+        self.assertEqual("text/x-python", m.from_buffer(b))
                 
     def test_mime_types(self):
         dest = os.path.join(MagicTest.TESTDATA_DIR, b'\xce\xbb'.decode('utf-8'))