types: support working with binary for Python 3

Before this patch, both bytes and str were encoded as mp_str. It was
possible to work with utf and non-utf strings, but not with
varbinary [1] (mp_bin). This patch adds varbinary support for Python 3
by default. Python 2 connector behavior remains the same.

For encoding="utf-8" (default), the following behavior is expected now:
(Python 3 -> Tarantool          -> Python 3)
 bytes    -> mp_bin (varbinary) -> bytes
 str      -> mp_str (string)    -> str

For encoding=None, the following behavior is expected now:
(Python 3 -> Tarantool          -> Python 3)
 bytes    -> mp_str (string)    -> bytes

This patch changes current behavior for Python 3. Now bytes objects
encoded to varbinary by default. bytes objects are also supported
as keys.

This patch does not add new restrictions (like "do not permit to use
str in encoding=None mode because result may be confusing") to preserve
current behavior (for example, using space name as str in schema
get_space).

1. tarantool/tarantool#4201

Closes #105

Author: DifferentialOrange

tarantool/request.py

@@ -4,6 +4,7 @@
 Request types definitions
 '''
 
+import sys
 import collections
 import msgpack
 import hashlib
@@ -84,8 +85,13 @@ def __init__(self, conn):
         # The option controls whether to pack binary (non-unicode)
         # string values as mp_bin or as mp_str.
         #
-        # The default behaviour of the connector is to pack both
-        # bytes and Unicode strings as mp_str.
+        # The default behaviour of the Python 2 connector is to pack
+        # both bytes and Unicode strings as mp_str.
+        #
+        # The default behaviour of the Python 3 connector (since
+        # default encoding is "utf-8") is to pack bytes as mp_bin
+        # and Unicode strings as mp_str. encoding=None mode must
+        # be used to work with non-utf strings.
         #
         # msgpack-0.5.0 (and only this version) warns when the
         # option is unset:
@@ -98,7 +104,10 @@ def __init__(self, conn):
         # just always set it for all msgpack versions to get rid
         # of the warning on msgpack-0.5.0 and to keep our
         # behaviour on msgpack-1.0.0.
-        packer_kwargs['use_bin_type'] = False
+        if conn.encoding is None or sys.version_info.major == 2:
+            packer_kwargs['use_bin_type'] = False
+        else:
+            packer_kwargs['use_bin_type'] = True
 
         self.packer = msgpack.Packer(**packer_kwargs)
 

tarantool/utils.py

@@ -6,7 +6,10 @@
 if sys.version_info.major == 2:
     string_types     = (basestring, )
     integer_types    = (int, long)
+    supported_types  = integer_types + string_types + (float,)
+
     ENCODING_DEFAULT = None
+
     if sys.version_info.minor < 6:
         binary_types = (str, )
     else:
@@ -17,10 +20,13 @@ def strxor(rhs, lhs):
         return "".join(chr(ord(x) ^ ord(y)) for x, y in zip(rhs, lhs))
 
 elif sys.version_info.major == 3:
-    binary_types  = (bytes, )
-    string_types  = (str, )
-    integer_types = (int, )
+    binary_types    = (bytes, )
+    string_types    = (str, )
+    integer_types   = (int, )
+    supported_types = integer_types + string_types + binary_types + (float,)
+
     ENCODING_DEFAULT = "utf-8"
+
     from base64 import decodebytes as base64_decode
 
     def strxor(rhs, lhs):
@@ -43,7 +49,7 @@ def check_key(*args, **kwargs):
         elif args[0] is None and kwargs['select']:
             return []
     for key in args:
-        assert isinstance(key, integer_types + string_types + (float,))
+        assert isinstance(key, supported_types)
     return list(args)
 
 

test/suites/lib/skip.py

@@ -1,20 +1,15 @@
 import functools
 import pkg_resources
 import re
+import sys
 
-SQL_SUPPORT_TNT_VERSION = '2.0.0'
 
-
-def skip_or_run_sql_test(func):
-    """Decorator to skip or run SQL-related tests depending on the tarantool
+def skip_or_run_test_tarantool(func, REQUIRED_TNT_VERSION, msg):
+    """Decorator to skip or run tests depending on the tarantool
     version.
 
-    Tarantool supports SQL-related stuff only since 2.0.0 version. So this
-    decorator should wrap every SQL-related test to skip it if the tarantool
-    version < 2.0.0 is used for testing.
-
-    Also, it can be used with the 'setUp' method for skipping the whole test
-    suite.
+    Also, it can be used with the 'setUp' method for skipping
+    the whole test suite.
     """
 
     @functools.wraps(func)
@@ -28,16 +23,69 @@ def wrapper(self, *args, **kwargs):
             ).group()
 
         tnt_version = pkg_resources.parse_version(self.tnt_version)
-        sql_support_tnt_version = pkg_resources.parse_version(
-            SQL_SUPPORT_TNT_VERSION
-        )
+        support_version = pkg_resources.parse_version(REQUIRED_TNT_VERSION)
 
-        if tnt_version < sql_support_tnt_version:
-            self.skipTest(
-                'Tarantool %s does not support SQL' % self.tnt_version
-            )
+        if tnt_version < support_version:
+            self.skipTest('Tarantool %s %s' % (self.tnt_version, msg))
 
         if func.__name__ != 'setUp':
             func(self, *args, **kwargs)
 
     return wrapper
+
+
+def skip_or_run_test_python_major(func, REQUIRED_PYTHON_MAJOR, msg):
+    """Decorator to skip or run tests depending on the Python major
+    version.
+
+    Also, it can be used with the 'setUp' method for skipping
+    the whole test suite.
+    """
+
+    @functools.wraps(func)
+    def wrapper(self, *args, **kwargs):
+        if func.__name__ == 'setUp':
+            func(self, *args, **kwargs)
+
+        major = sys.version_info.major
+        if major != REQUIRED_PYTHON_MAJOR:
+            self.skipTest('Python %s connector %s' % (major, msg))
+
+        if func.__name__ != 'setUp':
+            func(self, *args, **kwargs)
+
+    return wrapper
+
+
+def skip_or_run_sql_test(func):
+    """Decorator to skip or run SQL-related tests depending on the
+    tarantool version.
+
+    Tarantool supports SQL-related stuff only since 2.0.0 version.
+    So this decorator should wrap every SQL-related test to skip it if
+    the tarantool version < 2.0.0 is used for testing.
+    """
+
+    return skip_or_run_test_tarantool(func, '2.0.0', 'does not support SQL')
+
+
+def skip_or_run_varbinary_test(func):
+    """Decorator to skip or run VARBINARY-related tests depending on
+    the tarantool version.
+
+    Tarantool supports VARBINARY type only since 2.2.1 version.
+    See https://github.com/tarantool/tarantool/issues/4201
+    """
+
+    return skip_or_run_test_tarantool(func, '2.2.1',
+                                      'does not support VARBINARY type')
+
+
+def skip_or_run_mp_bin_test(func):
+    """Decorator to skip or run mp_bin-related tests depending on
+    the Python version.
+
+    Python 2 connector do not support mp_bin.
+    """
+
+    return skip_or_run_test_python_major(func, 3, 'does not support mp_bin')

test/suites/test_dml.py

@@ -6,6 +6,7 @@
 import unittest
 import tarantool
 
+from .lib.skip import skip_or_run_mp_bin_test, skip_or_run_varbinary_test
 from .lib.tarantool_server import TarantoolServer
 
 class TestSuite_Request(unittest.TestCase):
@@ -16,7 +17,13 @@ def setUpClass(self):
         self.srv = TarantoolServer()
         self.srv.script = 'test/suites/box.lua'
         self.srv.start()
-        self.con = tarantool.Connection(self.srv.host, self.srv.args['primary'])
+
+        args = [self.srv.host, self.srv.args['primary']]
+        self.con = tarantool.Connection(*args)
+        self.con_encoding_utf8 = tarantool.Connection(*args, encoding='utf-8')
+        self.con_encoding_none = tarantool.Connection(*args, encoding=None)
+        self.conns = [self.con, self.con_encoding_utf8, self.con_encoding_none]
+
         self.adm = self.srv.admin
         self.space_created = self.adm("box.schema.create_space('space_1')")
         self.adm("""
@@ -31,17 +38,64 @@ def setUpClass(self):
             parts = {2, 'num', 3, 'str'},
             unique = false})
         """.replace('\n', ' '))
+
         self.space_created = self.adm("box.schema.create_space('space_2')")
         self.adm("""
         box.space['space_2']:create_index('primary', {
             type = 'hash',
             parts = {1, 'num'},
             unique = true})
         """.replace('\n', ' '))
+
+        self.adm("box.schema.create_space('space_str')")
+        self.adm("""
+        box.space['space_str']:create_index('primary', {
+            type = 'tree',
+            parts = {1, 'str'},
+            unique = true})
+        """.replace('\n', ' '))
+
+        self.adm("box.schema.create_space('space_varbin')")
+        self.adm("""
+        box.space['space_varbin']:create_index('primary', {
+            type = 'tree',
+            parts = {1, 'varbinary'},
+            unique = true})
+        """.replace('\n', ' '))
+        self.adm("""
+        buffer = require('buffer')
+        ffi = require('ffi')
+
+        function encode_bin(bytes)
+            local tmpbuf = buffer.ibuf()
+            local p = tmpbuf:alloc(3 + #bytes)
+            p[0] = 0x91
+            p[1] = 0xC4
+            p[2] = #bytes
+            for i, c in pairs(bytes) do
+                p[i + 3 - 1] = c
+            end
+            return tmpbuf
+        end
+
+        function bintuple_insert(space, bytes)
+            local tmpbuf = encode_bin(bytes)
+            ffi.cdef[[
+                int box_insert(uint32_t space_id, const char *tuple, const char *tuple_end, box_tuple_t **result);
+            ]]
+            ffi.C.box_insert(space.id, tmpbuf.rpos, tmpbuf.wpos, nil)
+        end
+        """)
         self.adm("json = require('json')")
         self.adm("fiber = require('fiber')")
         self.adm("uuid = require('uuid')")
 
+    def assertNotRaises(self, func, *args, **kwargs):
+        try:
+            func(*args, **kwargs)
+        except Exception as e:
+            self.fail('Function raised Exception: %s' % repr(e))
+
     def setUp(self):
         # prevent a remote tarantool from clean our session
         if self.srv.is_started():
@@ -54,7 +108,8 @@ def test_00_00_authenticate(self):
         self.assertIsNone(self.srv.admin("""
         box.schema.user.grant('test', 'execute,read,write', 'universe')
         """))
-        self.assertEqual(self.con.authenticate('test', 'test')._data, None)
+        for con in self.conns:
+            self.assertEqual(con.authenticate('test', 'test')._data, None)
 
     def test_00_01_space_created(self):
         # Check that space is created in setUpClass
@@ -302,6 +357,51 @@ def test_12_update_fields(self):
             [[2, 'help', 7]]
         )
 
+    def test_13_00_string_insert_encoding_utf8_behavior(self):
+        self.assertNotRaises(
+            self.con_encoding_utf8.insert,
+            'space_str', [ 'test_13_00' ])
+
+    def test_13_01_string_select_encoding_utf8_behavior(self):
+        self.adm(r"box.space['space_str']:insert{'test_13_01'}")
+
+        strdata = 'test_13_01'
+        resp = self.con_encoding_utf8.select('space_str', [strdata])
+        self.assertEquals(resp[0][0], strdata)
+
+    @skip_or_run_mp_bin_test
+    @skip_or_run_varbinary_test
+    def test_13_02_varbinary_insert_encoding_utf8_behavior(self):
+        self.assertNotRaises(
+            self.con_encoding_utf8.insert,
+            'space_varbin', [ b'test_13_02' ])
+
+    @skip_or_run_mp_bin_test
+    @skip_or_run_varbinary_test
+    def test_13_03_varbinary_select_encoding_utf8_behavior(self):
+        self.adm(r"""
+        bintuple_insert(
+            box.space['space_varbin'],
+            {0xDE, 0xAD, 0xBE, 0xAF, 0x13, 0x03})
+        """)
+
+        bindata = bytes(bytearray.fromhex('DEADBEAF1303'))
+        resp = self.con_encoding_utf8.select('space_varbin', [bindata])
+        self.assertEquals(resp[0][0], bindata)
+
+    def test_14_00_string_insert_encoding_none_behavior(self):
+        self.assertNotRaises(
+            self.con_encoding_none.insert,
+            'space_str',
+            [ bytes(bytearray.fromhex('DEADBEAF1400')) ])
+
+    def test_14_01_string_select_encoding_none_behavior(self):
+        self.adm(r"box.space['space_str']:insert{'\xDE\xAD\xBE\xAF\x14\x01'}")
+
+        bindata = bytes(bytearray.fromhex('DEADBEAF1401'))
+        resp = self.con_encoding_none.select('space_str', [bindata])
+        self.assertEquals(resp[0][0], bindata)
+
     @classmethod
     def tearDownClass(self):
         self.con.close()