Libguestfs - Jan 2014 - [PATCH 3/4] hivex: python: Produce Unicode strings in get_* methods

---
 configure.ac | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/configure.ac b/configure.ac
index 6785037..203f34f 100644
--- a/configure.ac
+++ b/configure.ac
@@ -329,8 +329,8 @@ AS_IF([test "x$enable_python" != "xno"],
 
             AC_MSG_CHECKING([for Python extension suffix (PEP-3149)])
             if test -z "$PYTHON_EXT_SUFFIX"; then
-                python_ext_suffix=`$PYTHON -c "import sysconfig; \
-                                             print
(sysconfig.get_config_var('EXT_SUFFIX') or
sysconfig.get_config_var('SO'))"`
+                python_ext_suffix=`$PYTHON -c "import distutils.sysconfig;
\
+                                               print
(distutils.sysconfig.get_config_var('EXT_SUFFIX') or
distutils.sysconfig.get_config_var('SO'))"`
                 PYTHON_EXT_SUFFIX=$python_ext_suffix
             fi
             AC_MSG_RESULT([$PYTHON_EXT_SUFFIX])
-- 
1.8.5.2

Hopefully. Python's unicode history is a mess.
---
 python/t/130-special.py | 25 +++++++++++++++++++------
 1 file changed, 19 insertions(+), 6 deletions(-)

diff --git a/python/t/130-special.py b/python/t/130-special.py
index 7adb9d5..f0ac008 100755
--- a/python/t/130-special.py
+++ b/python/t/130-special.py
@@ -1,4 +1,13 @@
 # coding: utf-8
+#
http://stackoverflow.com/questions/6625782/unicode-literals-that-work-in-python-3-and-2
+import sys
+if sys.version < '3':
+    import codecs
+    def u(x):
+        return codecs.unicode_escape_decode(x)[0]
+else:
+    def u(x):
+        return x
 
 import os
 import hivex
@@ -13,16 +22,20 @@ assert h
 root = h.root ()
 assert root
 
-ns = [ n for n in h.node_children (root) if h.node_name(n) ==
u"abcd_äöüß" ]
+# "abcd_äöüß"
+ns = [ n for n in h.node_children (root) if h.node_name(n) ==
u("abcd_\u00e4\u00f6\u00fc\u00df") ]
 assert len (ns) == 1
-vs = [ v for v in h.node_values (ns[0]) if h.value_key(v) ==
u"abcd_äöüß" ]
+# "abcd_äöüß"
+vs = [ v for v in h.node_values (ns[0]) if h.value_key(v) ==
u("abcd_\u00e4\u00f6\u00fc\u00df") ]
 assert len (vs) == 1
-ns = [ n for n in h.node_children (root) if h.node_name(n) ==
u"zero\0key" ]
+ns = [ n for n in h.node_children (root) if h.node_name(n) ==
u("zero\0key") ]
 assert len (ns) == 1
-vs = [ v for v in h.node_values (ns[0]) if h.value_key(v) ==
u"zero\0val" ]
+vs = [ v for v in h.node_values (ns[0]) if h.value_key(v) ==
u("zero\0val") ]
 assert len (vs) == 1
-ns = [ n for n in h.node_children (root) if h.node_name(n) ==
u"weird™" ]
+# "weird™"
+ns = [ n for n in h.node_children (root) if h.node_name(n) ==
u("weird\u2122") ]
 assert len (ns) == 1
-vs = [ v for v in h.node_values (ns[0]) if h.value_key(v) == u"symbols
$£₤₧€" ]
+# "symbols $£₤₧€"
+vs = [ v for v in h.node_values (ns[0]) if h.value_key(v) == u("symbols
\u0024\u00a3\u20a4\u20a7\u20ac") ]
 assert len (vs) == 1
 
-- 
1.8.5.2

---
 generator/generator.ml | 23 ++++-------------------
 1 file changed, 4 insertions(+), 19 deletions(-)

diff --git a/generator/generator.ml b/generator/generator.ml
index 1f2690d..908c5f3 100755
--- a/generator/generator.ml
+++ b/generator/generator.ml
@@ -2925,11 +2925,7 @@ put_string_list (char * const * const argv)
 
   list = PyList_New (argc);
   for (i = 0; i < argc; ++i) {
-#ifdef HAVE_PYSTRING_ASSTRING
-    PyList_SetItem (list, i, PyString_FromString (argv[i]));
-#else
-    PyList_SetItem (list, i, PyUnicode_FromString (argv[i]));
-#endif
+    PyList_SetItem (list, i, PyUnicode_DecodeUTF8 (argv[i], strlen (argv[i]),
NULL));
   }
 
   return list;
@@ -2985,11 +2981,7 @@ put_val_type (char *val, size_t len, hive_type t)
 {
   PyObject *r = PyTuple_New (2);
   PyTuple_SetItem (r, 0, PyLong_FromLong ((long) t));
-#ifdef HAVE_PYSTRING_ASSTRING
-  PyTuple_SetItem (r, 1, PyString_FromStringAndSize (val, len));
-#else
-  PyTuple_SetItem (r, 1, PyBytes_FromStringAndSize (val, len));
-#endif
+  PyTuple_SetItem (r, 1, PyUnicode_DecodeUTF8 (val, len, NULL));
   return r;
 }
 
@@ -3194,17 +3186,10 @@ put_val_type (char *val, size_t len, hive_type t)
            if f_len_exists name then
              pr "  size_t sz = hivex_%s_len (%s);\n"
                name (String.concat ", " c_params);
-           pr "#ifdef HAVE_PYSTRING_ASSTRING\n";
-           if f_len_exists name then
-             pr "  py_r = PyString_FromStringAndSize (r, sz);\n"
-           else
-             pr "  py_r = PyString_FromString (r);\n";
-           pr "#else\n";
            if f_len_exists name then
-             pr "  py_r = PyUnicode_FromStringAndSize (r, sz);\n"
+             pr "  py_r = PyUnicode_DecodeUTF8 (r, sz, NULL);\n"
            else
-             pr "  py_r = PyUnicode_FromString (r);\n";
-           pr "#endif\n";
+             pr "  py_r = PyUnicode_DecodeUTF8 (r, strlen (r),
NULL);\n";
            pr "  free (r);"
        | RStringList ->
            pr "  py_r = put_string_list (r);\n";
-- 
1.8.5.2

Since values are now returned as strings in Python2 and Python3,
treating them as bytes in Python 3 would break tests.
---
 python/t/210-setvalue.py | 12 ++----------
 1 file changed, 2 insertions(+), 10 deletions(-)

diff --git a/python/t/210-setvalue.py b/python/t/210-setvalue.py
index 9d93519..2ee7ac5 100644
--- a/python/t/210-setvalue.py
+++ b/python/t/210-setvalue.py
@@ -47,20 +47,12 @@ h.node_set_value (b, value1)
 value1 = { "key": "Key1", "t": 3,
"value": "JKL" }
 h.node_set_value (b, value1)
 
-# In Python2, the data is returned as a string.  In Python3, it is
-# returned as bytes.  Provide a function to convert either to a string.
-def to_string (data):
-    if sys.version_info[0] == 2:
-        return data
-    else:
-        return str (data, "utf-8")
-
 val = h.node_get_value (b, "Key1")
 t_data = h.value_value (val)
 assert t_data[0] == 3
-assert to_string (t_data[1]) == "JKL"
+assert t_data[1] == "JKL"
 
 val = h.node_get_value (b, "Key3")
 t_data = h.value_value (val)
 assert t_data[0] == 3
-assert to_string (t_data[1]) == "GHI"
+assert t_data[1] == "GHI"
-- 
1.8.5.2

ACK to all 4 patches in this series.

Thanks,

Rich.

-- 
Richard Jones, Virtualization Group, Red Hat http://people.redhat.com/~rjones
virt-df lists disk usage of guests without needing to install any
software inside the virtual machine.  Supports Linux and Windows.
http://people.redhat.com/~rjones/virt-df/