1# Protocol Buffers - Google's data interchange format
2# Copyright 2008 Google Inc.  All rights reserved.
3# http://code.google.com/p/protobuf/
4#
5# Redistribution and use in source and binary forms, with or without
6# modification, are permitted provided that the following conditions are
7# met:
8#
9#     * Redistributions of source code must retain the above copyright
10# notice, this list of conditions and the following disclaimer.
11#     * Redistributions in binary form must reproduce the above
12# copyright notice, this list of conditions and the following disclaimer
13# in the documentation and/or other materials provided with the
14# distribution.
15#     * Neither the name of Google Inc. nor the names of its
16# contributors may be used to endorse or promote products derived from
17# this software without specific prior written permission.
18#
19# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
20# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
21# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
22# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
23# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
24# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
25# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
26# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
27# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
28# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
29# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
30
31"""Provides type checking routines.
32
33This module defines type checking utilities in the forms of dictionaries:
34
35VALUE_CHECKERS: A dictionary of field types and a value validation object.
36TYPE_TO_BYTE_SIZE_FN: A dictionary with field types and a size computing
37  function.
38TYPE_TO_SERIALIZE_METHOD: A dictionary with field types and serialization
39  function.
40FIELD_TYPE_TO_WIRE_TYPE: A dictionary with field typed and their
41  coresponding wire types.
42TYPE_TO_DESERIALIZE_METHOD: A dictionary with field types and deserialization
43  function.
44"""
45
46__author__ = 'robinson@google.com (Will Robinson)'
47
48from google.protobuf.internal import decoder
49from google.protobuf.internal import encoder
50from google.protobuf.internal import wire_format
51from google.protobuf import descriptor
52
53_FieldDescriptor = descriptor.FieldDescriptor
54
55
56def GetTypeChecker(cpp_type, field_type):
57  """Returns a type checker for a message field of the specified types.
58
59  Args:
60    cpp_type: C++ type of the field (see descriptor.py).
61    field_type: Protocol message field type (see descriptor.py).
62
63  Returns:
64    An instance of TypeChecker which can be used to verify the types
65    of values assigned to a field of the specified type.
66  """
67  if (cpp_type == _FieldDescriptor.CPPTYPE_STRING and
68      field_type == _FieldDescriptor.TYPE_STRING):
69    return UnicodeValueChecker()
70  return _VALUE_CHECKERS[cpp_type]
71
72
73# None of the typecheckers below make any attempt to guard against people
74# subclassing builtin types and doing weird things.  We're not trying to
75# protect against malicious clients here, just people accidentally shooting
76# themselves in the foot in obvious ways.
77
78class TypeChecker(object):
79
80  """Type checker used to catch type errors as early as possible
81  when the client is setting scalar fields in protocol messages.
82  """
83
84  def __init__(self, *acceptable_types):
85    self._acceptable_types = acceptable_types
86
87  def CheckValue(self, proposed_value):
88    if not isinstance(proposed_value, self._acceptable_types):
89      message = ('%.1024r has type %s, but expected one of: %s' %
90                 (proposed_value, type(proposed_value), self._acceptable_types))
91      raise TypeError(message)
92
93
94# IntValueChecker and its subclasses perform integer type-checks
95# and bounds-checks.
96class IntValueChecker(object):
97
98  """Checker used for integer fields.  Performs type-check and range check."""
99
100  def CheckValue(self, proposed_value):
101    if not isinstance(proposed_value, (int, long)):
102      message = ('%.1024r has type %s, but expected one of: %s' %
103                 (proposed_value, type(proposed_value), (int, long)))
104      raise TypeError(message)
105    if not self._MIN <= proposed_value <= self._MAX:
106      raise ValueError('Value out of range: %d' % proposed_value)
107
108
109class UnicodeValueChecker(object):
110
111  """Checker used for string fields."""
112
113  def CheckValue(self, proposed_value):
114    if not isinstance(proposed_value, (str, unicode)):
115      message = ('%.1024r has type %s, but expected one of: %s' %
116                 (proposed_value, type(proposed_value), (str, unicode)))
117      raise TypeError(message)
118
119    # If the value is of type 'str' make sure that it is in 7-bit ASCII
120    # encoding.
121    if isinstance(proposed_value, str):
122      try:
123        unicode(proposed_value, 'ascii')
124      except UnicodeDecodeError:
125        raise ValueError('%.1024r has type str, but isn\'t in 7-bit ASCII '
126                         'encoding. Non-ASCII strings must be converted to '
127                         'unicode objects before being added.' %
128                         (proposed_value))
129
130
131class Int32ValueChecker(IntValueChecker):
132  # We're sure to use ints instead of longs here since comparison may be more
133  # efficient.
134  _MIN = -2147483648
135  _MAX = 2147483647
136
137
138class Uint32ValueChecker(IntValueChecker):
139  _MIN = 0
140  _MAX = (1 << 32) - 1
141
142
143class Int64ValueChecker(IntValueChecker):
144  _MIN = -(1 << 63)
145  _MAX = (1 << 63) - 1
146
147
148class Uint64ValueChecker(IntValueChecker):
149  _MIN = 0
150  _MAX = (1 << 64) - 1
151
152
153# Type-checkers for all scalar CPPTYPEs.
154_VALUE_CHECKERS = {
155    _FieldDescriptor.CPPTYPE_INT32: Int32ValueChecker(),
156    _FieldDescriptor.CPPTYPE_INT64: Int64ValueChecker(),
157    _FieldDescriptor.CPPTYPE_UINT32: Uint32ValueChecker(),
158    _FieldDescriptor.CPPTYPE_UINT64: Uint64ValueChecker(),
159    _FieldDescriptor.CPPTYPE_DOUBLE: TypeChecker(
160        float, int, long),
161    _FieldDescriptor.CPPTYPE_FLOAT: TypeChecker(
162        float, int, long),
163    _FieldDescriptor.CPPTYPE_BOOL: TypeChecker(bool, int),
164    _FieldDescriptor.CPPTYPE_ENUM: Int32ValueChecker(),
165    _FieldDescriptor.CPPTYPE_STRING: TypeChecker(str),
166    }
167
168
169# Map from field type to a function F, such that F(field_num, value)
170# gives the total byte size for a value of the given type.  This
171# byte size includes tag information and any other additional space
172# associated with serializing "value".
173TYPE_TO_BYTE_SIZE_FN = {
174    _FieldDescriptor.TYPE_DOUBLE: wire_format.DoubleByteSize,
175    _FieldDescriptor.TYPE_FLOAT: wire_format.FloatByteSize,
176    _FieldDescriptor.TYPE_INT64: wire_format.Int64ByteSize,
177    _FieldDescriptor.TYPE_UINT64: wire_format.UInt64ByteSize,
178    _FieldDescriptor.TYPE_INT32: wire_format.Int32ByteSize,
179    _FieldDescriptor.TYPE_FIXED64: wire_format.Fixed64ByteSize,
180    _FieldDescriptor.TYPE_FIXED32: wire_format.Fixed32ByteSize,
181    _FieldDescriptor.TYPE_BOOL: wire_format.BoolByteSize,
182    _FieldDescriptor.TYPE_STRING: wire_format.StringByteSize,
183    _FieldDescriptor.TYPE_GROUP: wire_format.GroupByteSize,
184    _FieldDescriptor.TYPE_MESSAGE: wire_format.MessageByteSize,
185    _FieldDescriptor.TYPE_BYTES: wire_format.BytesByteSize,
186    _FieldDescriptor.TYPE_UINT32: wire_format.UInt32ByteSize,
187    _FieldDescriptor.TYPE_ENUM: wire_format.EnumByteSize,
188    _FieldDescriptor.TYPE_SFIXED32: wire_format.SFixed32ByteSize,
189    _FieldDescriptor.TYPE_SFIXED64: wire_format.SFixed64ByteSize,
190    _FieldDescriptor.TYPE_SINT32: wire_format.SInt32ByteSize,
191    _FieldDescriptor.TYPE_SINT64: wire_format.SInt64ByteSize
192    }
193
194
195# Maps from field types to encoder constructors.
196TYPE_TO_ENCODER = {
197    _FieldDescriptor.TYPE_DOUBLE: encoder.DoubleEncoder,
198    _FieldDescriptor.TYPE_FLOAT: encoder.FloatEncoder,
199    _FieldDescriptor.TYPE_INT64: encoder.Int64Encoder,
200    _FieldDescriptor.TYPE_UINT64: encoder.UInt64Encoder,
201    _FieldDescriptor.TYPE_INT32: encoder.Int32Encoder,
202    _FieldDescriptor.TYPE_FIXED64: encoder.Fixed64Encoder,
203    _FieldDescriptor.TYPE_FIXED32: encoder.Fixed32Encoder,
204    _FieldDescriptor.TYPE_BOOL: encoder.BoolEncoder,
205    _FieldDescriptor.TYPE_STRING: encoder.StringEncoder,
206    _FieldDescriptor.TYPE_GROUP: encoder.GroupEncoder,
207    _FieldDescriptor.TYPE_MESSAGE: encoder.MessageEncoder,
208    _FieldDescriptor.TYPE_BYTES: encoder.BytesEncoder,
209    _FieldDescriptor.TYPE_UINT32: encoder.UInt32Encoder,
210    _FieldDescriptor.TYPE_ENUM: encoder.EnumEncoder,
211    _FieldDescriptor.TYPE_SFIXED32: encoder.SFixed32Encoder,
212    _FieldDescriptor.TYPE_SFIXED64: encoder.SFixed64Encoder,
213    _FieldDescriptor.TYPE_SINT32: encoder.SInt32Encoder,
214    _FieldDescriptor.TYPE_SINT64: encoder.SInt64Encoder,
215    }
216
217
218# Maps from field types to sizer constructors.
219TYPE_TO_SIZER = {
220    _FieldDescriptor.TYPE_DOUBLE: encoder.DoubleSizer,
221    _FieldDescriptor.TYPE_FLOAT: encoder.FloatSizer,
222    _FieldDescriptor.TYPE_INT64: encoder.Int64Sizer,
223    _FieldDescriptor.TYPE_UINT64: encoder.UInt64Sizer,
224    _FieldDescriptor.TYPE_INT32: encoder.Int32Sizer,
225    _FieldDescriptor.TYPE_FIXED64: encoder.Fixed64Sizer,
226    _FieldDescriptor.TYPE_FIXED32: encoder.Fixed32Sizer,
227    _FieldDescriptor.TYPE_BOOL: encoder.BoolSizer,
228    _FieldDescriptor.TYPE_STRING: encoder.StringSizer,
229    _FieldDescriptor.TYPE_GROUP: encoder.GroupSizer,
230    _FieldDescriptor.TYPE_MESSAGE: encoder.MessageSizer,
231    _FieldDescriptor.TYPE_BYTES: encoder.BytesSizer,
232    _FieldDescriptor.TYPE_UINT32: encoder.UInt32Sizer,
233    _FieldDescriptor.TYPE_ENUM: encoder.EnumSizer,
234    _FieldDescriptor.TYPE_SFIXED32: encoder.SFixed32Sizer,
235    _FieldDescriptor.TYPE_SFIXED64: encoder.SFixed64Sizer,
236    _FieldDescriptor.TYPE_SINT32: encoder.SInt32Sizer,
237    _FieldDescriptor.TYPE_SINT64: encoder.SInt64Sizer,
238    }
239
240
241# Maps from field type to a decoder constructor.
242TYPE_TO_DECODER = {
243    _FieldDescriptor.TYPE_DOUBLE: decoder.DoubleDecoder,
244    _FieldDescriptor.TYPE_FLOAT: decoder.FloatDecoder,
245    _FieldDescriptor.TYPE_INT64: decoder.Int64Decoder,
246    _FieldDescriptor.TYPE_UINT64: decoder.UInt64Decoder,
247    _FieldDescriptor.TYPE_INT32: decoder.Int32Decoder,
248    _FieldDescriptor.TYPE_FIXED64: decoder.Fixed64Decoder,
249    _FieldDescriptor.TYPE_FIXED32: decoder.Fixed32Decoder,
250    _FieldDescriptor.TYPE_BOOL: decoder.BoolDecoder,
251    _FieldDescriptor.TYPE_STRING: decoder.StringDecoder,
252    _FieldDescriptor.TYPE_GROUP: decoder.GroupDecoder,
253    _FieldDescriptor.TYPE_MESSAGE: decoder.MessageDecoder,
254    _FieldDescriptor.TYPE_BYTES: decoder.BytesDecoder,
255    _FieldDescriptor.TYPE_UINT32: decoder.UInt32Decoder,
256    _FieldDescriptor.TYPE_ENUM: decoder.EnumDecoder,
257    _FieldDescriptor.TYPE_SFIXED32: decoder.SFixed32Decoder,
258    _FieldDescriptor.TYPE_SFIXED64: decoder.SFixed64Decoder,
259    _FieldDescriptor.TYPE_SINT32: decoder.SInt32Decoder,
260    _FieldDescriptor.TYPE_SINT64: decoder.SInt64Decoder,
261    }
262
263# Maps from field type to expected wiretype.
264FIELD_TYPE_TO_WIRE_TYPE = {
265    _FieldDescriptor.TYPE_DOUBLE: wire_format.WIRETYPE_FIXED64,
266    _FieldDescriptor.TYPE_FLOAT: wire_format.WIRETYPE_FIXED32,
267    _FieldDescriptor.TYPE_INT64: wire_format.WIRETYPE_VARINT,
268    _FieldDescriptor.TYPE_UINT64: wire_format.WIRETYPE_VARINT,
269    _FieldDescriptor.TYPE_INT32: wire_format.WIRETYPE_VARINT,
270    _FieldDescriptor.TYPE_FIXED64: wire_format.WIRETYPE_FIXED64,
271    _FieldDescriptor.TYPE_FIXED32: wire_format.WIRETYPE_FIXED32,
272    _FieldDescriptor.TYPE_BOOL: wire_format.WIRETYPE_VARINT,
273    _FieldDescriptor.TYPE_STRING:
274      wire_format.WIRETYPE_LENGTH_DELIMITED,
275    _FieldDescriptor.TYPE_GROUP: wire_format.WIRETYPE_START_GROUP,
276    _FieldDescriptor.TYPE_MESSAGE:
277      wire_format.WIRETYPE_LENGTH_DELIMITED,
278    _FieldDescriptor.TYPE_BYTES:
279      wire_format.WIRETYPE_LENGTH_DELIMITED,
280    _FieldDescriptor.TYPE_UINT32: wire_format.WIRETYPE_VARINT,
281    _FieldDescriptor.TYPE_ENUM: wire_format.WIRETYPE_VARINT,
282    _FieldDescriptor.TYPE_SFIXED32: wire_format.WIRETYPE_FIXED32,
283    _FieldDescriptor.TYPE_SFIXED64: wire_format.WIRETYPE_FIXED64,
284    _FieldDescriptor.TYPE_SINT32: wire_format.WIRETYPE_VARINT,
285    _FieldDescriptor.TYPE_SINT64: wire_format.WIRETYPE_VARINT,
286    }
287