Publishing nanopb-0.1.7

tools/set_version.sh is used to update the values.

Update issue 36
Status: FixedInGit

CHANGELOG

@@ -1,3 +1,13 @@
+nanopb-0.1.7 (not yet released)
+ Remove "skip" mode from pb_istream_t callbacks. Example implementation had a bug. (issue 37)
+ Add option to use shorter names for enum values (issue 38)
+ Improve options support in generator (issues 12, 30)
+ Add nanopb version number to generated files (issue 36)
+ Add extern "C" to generated headers (issue 35)
+ Add names for structs to allow forward declaration (issue 39)
+ Add buffer size check in example (issue 34)
+ Fix build warnings on MS compilers (issue 33)
+
 nanopb-0.1.6
  Reorganize the field decoder interface (issue 2)
  Improve performance in submessage decoding (issue 28)

docs/concepts.rst

@@ -38,6 +38,20 @@ This file, in turn, requires the file *google/protobuf/descriptor.proto*. This i
 
     protoc -I/usr/include -Inanopb/generator -I. -omessage.pb message.proto
 
+The options can be defined in file, message and field scopes::
+
+    option (nanopb_fileopt).max_size = 20; // File scope
+    message Message
+    {
+        option (nanopb_msgopt).max_size = 30; // Message scope
+        required string fieldsize = 1 [(nanopb).max_size = 40]; // Field scope
+    }
+
+It is also possible to give the options on command line, but then they will affect the whole file. For example::
+
+    user@host:~$ python ../generator/nanopb_generator.py -s 'max_size: 20' message.pb
+
+
 Streams
 =======
 
@@ -92,9 +106,8 @@ Writing to stdout::
 
 Input streams
 -------------
-For input streams, there are a few extra rules:
+For input streams, there is one extra rule:
 
-#) If buf is NULL, read from stream but don't store the data. This is used to skip unknown input.
 #) You don't need to know the length of the message in advance. After getting EOF error when reading, set bytes_left to 0 and return false. Pb_decode will detect this and if the EOF was in a proper position, it will return true.
 
 Here is the structure::

example/common.c

@@ -19,15 +19,6 @@ static bool read_callback(pb_istream_t *stream, uint8_t *buf, size_t count)
     int fd = (intptr_t)stream->state;
     int result;
     
-    if (buf == NULL)
-    {
-        /* Well, this is a really inefficient way to skip input. */
-        /* It is only used when there are unknown fields. */
-        char dummy;
-        while (count-- && recv(fd, &dummy, 1, 0) == 1);
-        return count == 0;
-    }
-    
     result = recv(fd, buf, count, MSG_WAITALL);
     
     if (result == 0)

generator/nanopb.proto

@@ -7,9 +7,24 @@
 
 import "google/protobuf/descriptor.proto";
 
+enum FieldType {
+    FT_DEFAULT = 0; // Automatically decide field type, generate static field if possible.
+    FT_CALLBACK = 1; // Always generate a callback field.
+    FT_STATIC = 2; // Generate a static field or raise an exception if not possible.
+}
+
 message NanoPBOptions {
+  // Allocated size for 'bytes' and 'string' fields.
   optional int32 max_size = 1;
+  
+  // Allocated number of entries in arrays ('repeated' fields)
   optional int32 max_count = 2;
+  
+  // Force type of field (callback or static allocation)
+  optional FieldType type = 3 [default = FT_DEFAULT];
+  
+  // Use long names for enums, i.e. EnumName_EnumValue.
+  optional bool long_names = 4 [default = true];
 }
 
 // Protocol Buffers extension number registry
@@ -20,7 +35,20 @@ message NanoPBOptions {
 // Extensions: 1010 (all types)                                                                                                                
 // --------------------------------   
 
+extend google.protobuf.FileOptions {
+    optional NanoPBOptions nanopb_fileopt = 1010;
+}
+
+extend google.protobuf.MessageOptions {
+    optional NanoPBOptions nanopb_msgopt = 1010;
+}
+
+extend google.protobuf.EnumOptions {
+    optional NanoPBOptions nanopb_enumopt = 1010;
+}
+
 extend google.protobuf.FieldOptions {
     optional NanoPBOptions nanopb = 1010;
 }
 
+

generator/nanopb_generator.py

@@ -1,4 +1,5 @@
 '''Generate header file for nanopb from a ProtoBuf FileDescriptorSet.'''
+nanopb_version = "nanopb-0.1.7"
 
 try:
     import google.protobuf.descriptor_pb2 as descriptor
@@ -22,6 +23,16 @@ except:
     print
     raise
 
+
+
+
+
+
+# ---------------------------------------------------------------------------
+#                     Generation of single fields
+# ---------------------------------------------------------------------------
+
+import time
 import os.path
 
 # Values are tuple (c type, pb ltype)
@@ -69,19 +80,24 @@ def names_from_type_name(type_name):
     return Names(type_name[1:].split('.'))
 
 class Enum:
-    def __init__(self, names, desc):
+    def __init__(self, names, desc, enum_options):
         '''desc is EnumDescriptorProto'''
-        self.names = names + desc.name
+        
+        if enum_options.long_names:
+            self.names = names + desc.name
+        else:
+            self.names = names
+        
         self.values = [(self.names + x.name, x.number) for x in desc.value]
     
     def __str__(self):
-        result = 'typedef enum {\n'
+        result = 'typedef enum _%s {\n' % self.names
         result += ',\n'.join(["    %s = %d" % x for x in self.values])
         result += '\n} %s;' % self.names
         return result
 
 class Field:
-    def __init__(self, struct_name, desc):
+    def __init__(self, struct_name, desc, field_options):
         '''desc is FieldDescriptorProto'''
         self.tag = desc.number
         self.struct_name = struct_name
@@ -91,28 +107,27 @@ class Field:
         self.max_count = None
         self.array_decl = ""
         
-        # Parse nanopb-specific field options
-        if desc.options.HasExtension(nanopb_pb2.nanopb):
-            ext = desc.options.Extensions[nanopb_pb2.nanopb]
-            if ext.HasField("max_size"):
-                self.max_size = ext.max_size
-            if ext.HasField("max_count"):
-                self.max_count = ext.max_count
+        # Parse field options
+        if field_options.HasField("max_size"):
+            self.max_size = field_options.max_size
+        
+        if field_options.HasField("max_count"):
+            self.max_count = field_options.max_count
         
         if desc.HasField('default_value'):
             self.default = desc.default_value
-        
+           
         # Decide HTYPE
         # HTYPE is the high-order nibble of nanopb field description,
         # defining whether value is required/optional/repeated.
-        is_callback = False
+        can_be_static = True
         if desc.label == FieldD.LABEL_REQUIRED:
             self.htype = 'PB_HTYPE_REQUIRED'
         elif desc.label == FieldD.LABEL_OPTIONAL:
             self.htype = 'PB_HTYPE_OPTIONAL'
         elif desc.label == FieldD.LABEL_REPEATED:
             if self.max_count is None:
-                is_callback = True
+                can_be_static = False
             else:
                 self.htype = 'PB_HTYPE_ARRAY'
                 self.array_decl = '[%d]' % self.max_count
@@ -133,14 +148,14 @@ class Field:
         elif desc.type == FieldD.TYPE_STRING:
             self.ltype = 'PB_LTYPE_STRING'
             if self.max_size is None:
-                is_callback = True
+                can_be_static = False
             else:
                 self.ctype = 'char'
                 self.array_decl += '[%d]' % self.max_size
         elif desc.type == FieldD.TYPE_BYTES:
             self.ltype = 'PB_LTYPE_BYTES'
             if self.max_size is None:
-                is_callback = True
+                can_be_static = False
             else:
                 self.ctype = self.struct_name + self.name + 't'
         elif desc.type == FieldD.TYPE_MESSAGE:
@@ -149,7 +164,16 @@ class Field:
         else:
             raise NotImplementedError(desc.type)
         
-        if is_callback:
+        if field_options.type == nanopb_pb2.FT_DEFAULT:
+            if can_be_static:
+                field_options.type = nanopb_pb2.FT_STATIC
+            else:
+                field_options.type = nanopb_pb2.FT_CALLBACK
+        
+        if field_options.type == nanopb_pb2.FT_STATIC and not can_be_static:
+            raise Exception("Field %s is defined as static, but max_size or max_count is not given." % self.name)
+        
+        if field_options.type == nanopb_pb2.FT_CALLBACK:
             self.htype = 'PB_HTYPE_CALLBACK'
             self.ctype = 'pb_callback_t'
             self.array_decl = ''
@@ -264,10 +288,19 @@ class Field:
         return max(self.tag, self.max_size, self.max_count)        
 
 
+
+
+
+
+# ---------------------------------------------------------------------------
+#                   Generation of messages (structures)
+# ---------------------------------------------------------------------------
+
+
 class Message:
-    def __init__(self, names, desc):
+    def __init__(self, names, desc, message_options):
         self.name = names
-        self.fields = [Field(self.name, f) for f in desc.field]
+        self.fields = [Field(self.name, f, get_nanopb_suboptions(f, message_options)) for f in desc.field]
         self.ordered_fields = self.fields[:]
         self.ordered_fields.sort()
 
@@ -276,7 +309,7 @@ class Message:
         return [str(field.ctype) for field in self.fields]
     
     def __str__(self):
-        result = 'typedef struct {\n'
+        result = 'typedef struct _%s {\n' % self.name
         result += '\n'.join([str(f) for f in self.ordered_fields])
         result += '\n} %s;' % self.name
         return result
@@ -313,6 +346,16 @@ class Message:
         result += '    PB_LAST_FIELD\n};'
         return result
 
+
+
+
+
+
+# ---------------------------------------------------------------------------
+#                    Processing of entire .proto files
+# ---------------------------------------------------------------------------
+
+
 def iterate_messages(desc, names = Names()):
     '''Recursively find all messages. For each, yield name, DescriptorProto.'''
     if hasattr(desc, 'message_type'):
@@ -327,7 +370,7 @@ def iterate_messages(desc, names = Names()):
         for x in iterate_messages(submsg, sub_names):
             yield x
 
-def parse_file(fdesc):
+def parse_file(fdesc, file_options):
     '''Takes a FileDescriptorProto and returns tuple (enum, messages).'''
     
     enums = []
@@ -339,12 +382,14 @@ def parse_file(fdesc):
         base_name = Names()
     
     for enum in fdesc.enum_type:
-        enums.append(Enum(base_name, enum))
+        enum_options = get_nanopb_suboptions(enum, file_options)
+        enums.append(Enum(base_name, enum, enum_options))
     
     for names, message in iterate_messages(fdesc, base_name):
-        messages.append(Message(names, message))
+        message_options = get_nanopb_suboptions(message, file_options)
+        messages.append(Message(names, message, message_options))
         for enum in message.enum_type:
-            enums.append(Enum(names, enum))
+            enums.append(Enum(names, enum, message_options))
     
     return enums, messages
 
@@ -385,6 +430,7 @@ def generate_header(dependencies, headername, enums, messages):
     '''
     
     yield '/* Automatically generated nanopb header */\n'
+    yield '/* Generated by %s at %s. */\n\n' % (nanopb_version, time.asctime())
     
     symbol = headername.replace('.', '_').upper()
     yield '#ifndef _PB_%s_\n' % symbol
@@ -394,7 +440,10 @@ def generate_header(dependencies, headername, enums, messages):
     for dependency in dependencies:
         noext = os.path.splitext(dependency)[0]
         yield '#include "%s.pb.h"\n' % noext
-    yield '\n'
+    
+    yield '#ifdef __cplusplus\n'
+    yield 'extern "C" {\n'
+    yield '#endif\n\n'
     
     yield '/* Enum definitions */\n'
     for enum in enums:
@@ -458,6 +507,10 @@ def generate_header(dependencies, headername, enums, messages):
                 yield 'STATIC_ASSERT((%s), YOU_MUST_DEFINE_PB_FIELD_32BIT)\n' % assertion
             yield '#endif\n'
     
+    yield '\n#ifdef __cplusplus\n'
+    yield '} /* extern "C" */\n'
+    yield '#endif\n'
+    
     # End of header
     yield '\n#endif\n'
 
@@ -465,6 +518,7 @@ def generate_source(headername, enums, messages):
     '''Generate content for a source file.'''
     
     yield '/* Automatically generated nanopb constant definitions */\n'
+    yield '/* Generated by %s at %s. */\n\n' % (nanopb_version, time.asctime())
     yield '#include "%s"\n\n' % headername
     
     for msg in messages:
@@ -475,39 +529,105 @@ def generate_source(headername, enums, messages):
     for msg in messages:
         yield msg.fields_definition() + '\n\n'
 
-if __name__ == '__main__':
-    import sys
-    import os.path
+
+
+# ---------------------------------------------------------------------------
+#                         Command line interface
+# ---------------------------------------------------------------------------
+
+import sys
+import os.path    
+from optparse import OptionParser
+import google.protobuf.text_format as text_format
+
+optparser = OptionParser(
+    usage = "Usage: nanopb_generator.py [options] file.pb ...",
+    epilog = "Compile file.pb from file.proto by: 'protoc -ofile.pb file.proto'. " +
+             "Output will be written to file.pb.h and file.pb.c.")
+optparser.add_option("-x", dest="exclude", metavar="FILE", action="append", default=[],
+    help="Exclude file from generated #include list.")
+optparser.add_option("-q", "--quiet", dest="quiet", action="store_true", default=False,
+    help="Don't print anything except errors.")
+optparser.add_option("-v", "--verbose", dest="verbose", action="store_true", default=False,
+    help="Print more information.")
+optparser.add_option("-s", dest="settings", metavar="OPTION:VALUE", action="append", default=[],
+    help="Set generator option (max_size, max_count etc.).")
+
+def get_nanopb_suboptions(subdesc, options):
+    '''Get copy of options, and merge information from subdesc.'''
+    new_options = nanopb_pb2.NanoPBOptions()
+    new_options.CopyFrom(options)
     
-    if len(sys.argv) != 2:
-        print "Usage: " + sys.argv[0] + " file.pb"
-        print "where file.pb has been compiled from .proto by:"
-        print "protoc -ofile.pb file.proto"
-        print "Output fill be written to file.pb.h and file.pb.c"
+    if isinstance(subdesc.options, descriptor.FieldOptions):
+        ext_type = nanopb_pb2.nanopb
+    elif isinstance(subdesc.options, descriptor.FileOptions):
+        ext_type = nanopb_pb2.nanopb_fileopt
+    elif isinstance(subdesc.options, descriptor.MessageOptions):
+        ext_type = nanopb_pb2.nanopb_msgopt
+    elif isinstance(subdesc.options, descriptor.EnumOptions):
+        ext_type = nanopb_pb2.nanopb_enumopt
+    else:
+        raise Exception("Unknown options type")
+    
+    if subdesc.options.HasExtension(ext_type):
+        ext = subdesc.options.Extensions[ext_type]
+        new_options.MergeFrom(ext)
+    
+    return new_options
+
+def process(filenames, options):
+    '''Process the files given on the command line.'''
+    
+    if not filenames:
+        optparser.print_help()
+        return False
+    
+    if options.quiet:
+        options.verbose = False
+    
+    toplevel_options = nanopb_pb2.NanoPBOptions()
+    for s in options.settings:
+        text_format.Merge(s, toplevel_options)
+    
+    for filename in filenames:
+        data = open(filename, 'rb').read()
+        fdesc = descriptor.FileDescriptorSet.FromString(data)
+        
+        file_options = get_nanopb_suboptions(fdesc.file[0], toplevel_options)
+        
+        if options.verbose:
+            print "Options for " + filename + ":"
+            print text_format.MessageToString(file_options)
+        
+        enums, messages = parse_file(fdesc.file[0], file_options)
+        
+        noext = os.path.splitext(filename)[0]
+        headername = noext + '.pb.h'
+        sourcename = noext + '.pb.c'
+        headerbasename = os.path.basename(headername)
+        
+        if not options.quiet:
+            print "Writing to " + headername + " and " + sourcename
+        
+        # List of .proto files that should not be included in the C header file
+        # even if they are mentioned in the source .proto.
+        excludes = ['nanopb.proto', 'google/protobuf/descriptor.proto'] + options.exclude
+        dependencies = [d for d in fdesc.file[0].dependency if d not in excludes]
+        
+        header = open(headername, 'w')
+        for part in generate_header(dependencies, headerbasename, enums, messages):
+            header.write(part)
+
+        source = open(sourcename, 'w')
+        for part in generate_source(headerbasename, enums, messages):
+            source.write(part)
+
+    return True
+
+if __name__ == '__main__':
+    options, filenames = optparser.parse_args()
+    status = process(filenames, options)
+    
+    if not status:
         sys.exit(1)
     
-    data = open(sys.argv[1], 'rb').read()
-    fdesc = descriptor.FileDescriptorSet.FromString(data)
-    enums, messages = parse_file(fdesc.file[0])
-    
-    noext = os.path.splitext(sys.argv[1])[0]
-    headername = noext + '.pb.h'
-    sourcename = noext + '.pb.c'
-    headerbasename = os.path.basename(headername)
-    
-    print "Writing to " + headername + " and " + sourcename
-    
-    # List of .proto files that should not be included in the C header file
-    # even if they are mentioned in the source .proto.
-    excludes = ['nanopb.proto', 'google/protobuf/descriptor.proto']
-    dependencies = [d for d in fdesc.file[0].dependency if d not in excludes]
-    
-    header = open(headername, 'w')
-    for part in generate_header(dependencies, headerbasename, enums, messages):
-        header.write(part)
-
-    source = open(sourcename, 'w')
-    for part in generate_source(headerbasename, enums, messages):
-        source.write(part)
-
-    

generator/nanopb_pb2.py

@@ -7,15 +7,70 @@ from google.protobuf import descriptor_pb2
 # @@protoc_insertion_point(imports)
 
 
+import google.protobuf.descriptor_pb2
+
 DESCRIPTOR = descriptor.FileDescriptor(
   name='nanopb.proto',
   package='',
-  serialized_pb='\n\x0cnanopb.proto\x1a google/protobuf/descriptor.proto\"4\n\rNanoPBOptions\x12\x10\n\x08max_size\x18\x01 \x01(\x05\x12\x11\n\tmax_count\x18\x02 \x01(\x05:>\n\x06nanopb\x12\x1d.google.protobuf.FieldOptions\x18\xf2\x07 \x01(\x0b\x32\x0e.NanoPBOptions')
+  serialized_pb='\n\x0cnanopb.proto\x1a google/protobuf/descriptor.proto\"t\n\rNanoPBOptions\x12\x10\n\x08max_size\x18\x01 \x01(\x05\x12\x11\n\tmax_count\x18\x02 \x01(\x05\x12$\n\x04type\x18\x03 \x01(\x0e\x32\n.FieldType:\nFT_DEFAULT\x12\x18\n\nlong_names\x18\x04 \x01(\x08:\x04true*;\n\tFieldType\x12\x0e\n\nFT_DEFAULT\x10\x00\x12\x0f\n\x0b\x46T_CALLBACK\x10\x01\x12\r\n\tFT_STATIC\x10\x02:E\n\x0enanopb_fileopt\x12\x1c.google.protobuf.FileOptions\x18\xf2\x07 \x01(\x0b\x32\x0e.NanoPBOptions:G\n\rnanopb_msgopt\x12\x1f.google.protobuf.MessageOptions\x18\xf2\x07 \x01(\x0b\x32\x0e.NanoPBOptions:E\n\x0enanopb_enumopt\x12\x1c.google.protobuf.EnumOptions\x18\xf2\x07 \x01(\x0b\x32\x0e.NanoPBOptions:>\n\x06nanopb\x12\x1d.google.protobuf.FieldOptions\x18\xf2\x07 \x01(\x0b\x32\x0e.NanoPBOptions')
+
+_FIELDTYPE = descriptor.EnumDescriptor(
+  name='FieldType',
+  full_name='FieldType',
+  filename=None,
+  file=DESCRIPTOR,
+  values=[
+    descriptor.EnumValueDescriptor(
+      name='FT_DEFAULT', index=0, number=0,
+      options=None,
+      type=None),
+    descriptor.EnumValueDescriptor(
+      name='FT_CALLBACK', index=1, number=1,
+      options=None,
+      type=None),
+    descriptor.EnumValueDescriptor(
+      name='FT_STATIC', index=2, number=2,
+      options=None,
+      type=None),
+  ],
+  containing_type=None,
+  options=None,
+  serialized_start=168,
+  serialized_end=227,
+)
 
 
+FT_DEFAULT = 0
+FT_CALLBACK = 1
+FT_STATIC = 2
+
+NANOPB_FILEOPT_FIELD_NUMBER = 1010
+nanopb_fileopt = descriptor.FieldDescriptor(
+  name='nanopb_fileopt', full_name='nanopb_fileopt', index=0,
+  number=1010, type=11, cpp_type=10, label=1,
+  has_default_value=False, default_value=None,
+  message_type=None, enum_type=None, containing_type=None,
+  is_extension=True, extension_scope=None,
+  options=None)
+NANOPB_MSGOPT_FIELD_NUMBER = 1010
+nanopb_msgopt = descriptor.FieldDescriptor(
+  name='nanopb_msgopt', full_name='nanopb_msgopt', index=1,
+  number=1010, type=11, cpp_type=10, label=1,
+  has_default_value=False, default_value=None,
+  message_type=None, enum_type=None, containing_type=None,
+  is_extension=True, extension_scope=None,
+  options=None)
+NANOPB_ENUMOPT_FIELD_NUMBER = 1010
+nanopb_enumopt = descriptor.FieldDescriptor(
+  name='nanopb_enumopt', full_name='nanopb_enumopt', index=2,
+  number=1010, type=11, cpp_type=10, label=1,
+  has_default_value=False, default_value=None,
+  message_type=None, enum_type=None, containing_type=None,
+  is_extension=True, extension_scope=None,
+  options=None)
 NANOPB_FIELD_NUMBER = 1010
 nanopb = descriptor.FieldDescriptor(
-  name='nanopb', full_name='nanopb', index=0,
+  name='nanopb', full_name='nanopb', index=3,
   number=1010, type=11, cpp_type=10, label=1,
   has_default_value=False, default_value=None,
   message_type=None, enum_type=None, containing_type=None,
@@ -44,6 +99,20 @@ _NANOPBOPTIONS = descriptor.Descriptor(
       message_type=None, enum_type=None, containing_type=None,
       is_extension=False, extension_scope=None,
       options=None),
+    descriptor.FieldDescriptor(
+      name='type', full_name='NanoPBOptions.type', index=2,
+      number=3, type=14, cpp_type=8, label=1,
+      has_default_value=True, default_value=0,
+      message_type=None, enum_type=None, containing_type=None,
+      is_extension=False, extension_scope=None,
+      options=None),
+    descriptor.FieldDescriptor(
+      name='long_names', full_name='NanoPBOptions.long_names', index=3,
+      number=4, type=8, cpp_type=7, label=1,
+      has_default_value=True, default_value=True,
+      message_type=None, enum_type=None, containing_type=None,
+      is_extension=False, extension_scope=None,
+      options=None),
   ],
   extensions=[
   ],
@@ -54,11 +123,11 @@ _NANOPBOPTIONS = descriptor.Descriptor(
   is_extendable=False,
   extension_ranges=[],
   serialized_start=50,
-  serialized_end=102,
+  serialized_end=166,
 )
 
-import google.protobuf.descriptor_pb2
-
+_NANOPBOPTIONS.fields_by_name['type'].enum_type = _FIELDTYPE
+DESCRIPTOR.message_types_by_name['NanoPBOptions'] = _NANOPBOPTIONS
 
 class NanoPBOptions(message.Message):
   __metaclass__ = reflection.GeneratedProtocolMessageType
@@ -66,6 +135,12 @@ class NanoPBOptions(message.Message):
   
   # @@protoc_insertion_point(class_scope:NanoPBOptions)
 
+nanopb_fileopt.message_type = _NANOPBOPTIONS
+google.protobuf.descriptor_pb2.FileOptions.RegisterExtension(nanopb_fileopt)
+nanopb_msgopt.message_type = _NANOPBOPTIONS
+google.protobuf.descriptor_pb2.MessageOptions.RegisterExtension(nanopb_msgopt)
+nanopb_enumopt.message_type = _NANOPBOPTIONS
+google.protobuf.descriptor_pb2.EnumOptions.RegisterExtension(nanopb_enumopt)
 nanopb.message_type = _NANOPBOPTIONS
 google.protobuf.descriptor_pb2.FieldOptions.RegisterExtension(nanopb)
 # @@protoc_insertion_point(module_scope)

pb.h

@@ -6,6 +6,8 @@
  * see pb_encode.h or pb_decode.h
  */
 
+#define NANOPB_VERSION nanopb-0.1.7
+
 #include <stdint.h>
 #include <stddef.h>
 #include <stdbool.h>
@@ -75,6 +77,7 @@ typedef enum {
     
     /* Number of declared LTYPES */
     PB_LTYPES_COUNT = 7,
+    PB_LTYPE_MASK = 0x0F,
     
     /******************
      * Modifier flags *
@@ -95,11 +98,13 @@ typedef enum {
      * data_offset points to pb_callback_t structure.
      * LTYPE should be 0 (it is ignored, but sometimes
      * used to speculatively index an array). */
-    PB_HTYPE_CALLBACK = 0x30
+    PB_HTYPE_CALLBACK = 0x30,
+    
+    PB_HTYPE_MASK = 0xF0
 } pb_packed pb_type_t;
 
-#define PB_HTYPE(x) ((x) & 0xF0)
-#define PB_LTYPE(x) ((x) & 0x0F)
+#define PB_HTYPE(x) ((x) & PB_HTYPE_MASK)
+#define PB_LTYPE(x) ((x) & PB_LTYPE_MASK)
 
 /* This structure is used in auto-generated constants
  * to specify struct fields.
@@ -145,10 +150,12 @@ struct _pb_field_t {
  * It has the number of bytes in the beginning, and after that an array.
  * Note that actual structs used will have a different length of bytes array.
  */
-typedef struct {
+struct _pb_bytes_array_t {
     size_t size;
     uint8_t bytes[1];
-} pb_bytes_array_t;
+};
+
+typedef struct _pb_bytes_array_t pb_bytes_array_t;
 
 /* This structure is used for giving the callback function.
  * It is stored in the message structure and filled in by the method that

pb_decode.c

@@ -36,18 +36,6 @@ static const pb_decoder_t PB_DECODERS[PB_LTYPES_COUNT] = {
  * pb_istream *
  **************/
 
-bool checkreturn pb_read(pb_istream_t *stream, uint8_t *buf, size_t count)
-{
-    if (stream->bytes_left < count)
-        PB_RETURN_ERROR(stream, "end-of-stream");
-    
-    if (!stream->callback(stream, buf, count))
-        PB_RETURN_ERROR(stream, "io error");
-    
-    stream->bytes_left -= count;
-    return true;
-}
-
 static bool checkreturn buf_read(pb_istream_t *stream, uint8_t *buf, size_t count)
 {
     uint8_t *source = (uint8_t*)stream->state;
@@ -59,6 +47,33 @@ static bool checkreturn buf_read(pb_istream_t *stream, uint8_t *buf, size_t coun
     return true;
 }
 
+bool checkreturn pb_read(pb_istream_t *stream, uint8_t *buf, size_t count)
+{
+	if (buf == NULL && stream->callback != buf_read)
+	{
+		/* Skip input bytes */
+		uint8_t tmp[16];
+		while (count > 16)
+		{
+			if (!pb_read(stream, tmp, 16))
+				return false;
+			
+			count -= 16;
+		}
+		
+		return pb_read(stream, tmp, count);
+	}
+
+    if (stream->bytes_left < count)
+        PB_RETURN_ERROR(stream, "end-of-stream");
+    
+    if (!stream->callback(stream, buf, count))
+        PB_RETURN_ERROR(stream, "io error");
+    
+    stream->bytes_left -= count;
+    return true;
+}
+
 pb_istream_t pb_istream_from_buffer(uint8_t *buf, size_t bufsize)
 {
     pb_istream_t stream;
@@ -83,7 +98,7 @@ static bool checkreturn pb_decode_varint32(pb_istream_t *stream, uint32_t *dest)
 bool checkreturn pb_decode_varint(pb_istream_t *stream, uint64_t *dest)
 {
     uint8_t byte;
-    uint8_t bitpos = 0;
+    int bitpos = 0;
     *dest = 0;
     
     while (bitpos < 64 && pb_read(stream, &byte, 1))
@@ -447,7 +462,7 @@ bool checkreturn pb_decode_noinit(pb_istream_t *stream, const pb_field_t fields[
         if (PB_HTYPE(iter.current->type) == PB_HTYPE_REQUIRED
             && iter.required_field_index < PB_MAX_REQUIRED_FIELDS)
         {
-            fields_seen[iter.required_field_index >> 3] |= 1 << (iter.required_field_index & 7);
+            fields_seen[iter.required_field_index >> 3] |= (uint8_t)(1 << (iter.required_field_index & 7));
         }
             
         if (!decode_field(stream, wire_type, &iter))
@@ -483,9 +498,9 @@ bool pb_decode_svarint(pb_istream_t *stream, int64_t *dest)
         return false;
     
     if (value & 1)
-        *dest = ~(value >> 1);
+        *dest = (int64_t)(~(value >> 1));
     else
-        *dest = value >> 1;
+        *dest = (int64_t)(value >> 1);
     
     return true;
 }
@@ -539,9 +554,9 @@ bool checkreturn pb_dec_varint(pb_istream_t *stream, const pb_field_t *field, vo
     
     switch (field->data_size)
     {
-        case 1: *(uint8_t*)dest = value; break;
-        case 2: *(uint16_t*)dest = value; break;
-        case 4: *(uint32_t*)dest = value; break;
+        case 1: *(uint8_t*)dest = (uint8_t)value; break;
+        case 2: *(uint16_t*)dest = (uint16_t)value; break;
+        case 4: *(uint32_t*)dest = (uint32_t)value; break;
         case 8: *(uint64_t*)dest = value; break;
         default: PB_RETURN_ERROR(stream, "invalid data_size");
     }
@@ -556,7 +571,7 @@ bool checkreturn pb_dec_svarint(pb_istream_t *stream, const pb_field_t *field, v
     
     switch (field->data_size)
     {
-        case 4: *(int32_t*)dest = value; break;
+        case 4: *(int32_t*)dest = (int32_t)value; break;
         case 8: *(int64_t*)dest = value; break;
         default: PB_RETURN_ERROR(stream, "invalid data_size");
     }

pb_decode.h

@@ -12,6 +12,10 @@
 #include <stdbool.h>
 #include "pb.h"
 
+#ifdef __cplusplus
+extern "C" {
+#endif
+
 /* Lightweight input stream.
  * You can provide a callback function for reading or use
  * pb_istream_from_buffer.
@@ -19,12 +23,10 @@
  * Rules for callback:
  * 1) Return false on IO errors. This will cause decoding to abort.
  * 
- * 2) If buf is NULL, read but don't store bytes ("skip input").
- * 
- * 3) You can use state to store your own data (e.g. buffer pointer),
+ * 2) You can use state to store your own data (e.g. buffer pointer),
  * and rely on pb_read to verify that no-body reads past bytes_left.
  * 
- * 4) Your callback may be used with substreams, in which case bytes_left
+ * 3) Your callback may be used with substreams, in which case bytes_left
  * is different than from the main stream. Don't use bytes_left to compute
  * any pointers.
  */
@@ -104,4 +106,8 @@ bool pb_skip_varint(pb_istream_t *stream);
 bool pb_skip_string(pb_istream_t *stream);
 #endif
 
+#ifdef __cplusplus
+} /* extern "C" */
+#endif
+
 #endif

pb_encode.c

@@ -205,7 +205,7 @@ bool checkreturn pb_encode(pb_ostream_t *stream, const pb_field_t fields[], cons
 bool checkreturn pb_encode_varint(pb_ostream_t *stream, uint64_t value)
 {
     uint8_t buffer[10];
-    int i = 0;
+    size_t i = 0;
     
     if (value == 0)
         return pb_write(stream, (uint8_t*)&value, 1);
@@ -225,9 +225,9 @@ bool checkreturn pb_encode_svarint(pb_ostream_t *stream, int64_t value)
 {
     uint64_t zigzagged;
     if (value < 0)
-        zigzagged = ~(value << 1);
+        zigzagged = (uint64_t)(~(value << 1));
     else
-        zigzagged = value << 1;
+        zigzagged = (uint64_t)(value << 1);
     
     return pb_encode_varint(stream, zigzagged);
 }
@@ -266,7 +266,7 @@ bool checkreturn pb_encode_fixed64(pb_ostream_t *stream, const void *value)
     #endif
 }
 
-bool checkreturn pb_encode_tag(pb_ostream_t *stream, pb_wire_type_t wiretype, int field_number)
+bool checkreturn pb_encode_tag(pb_ostream_t *stream, pb_wire_type_t wiretype, uint32_t field_number)
 {
     uint64_t tag = wiretype | (field_number << 3);
     return pb_encode_varint(stream, tag);
@@ -370,7 +370,7 @@ bool checkreturn pb_enc_varint(pb_ostream_t *stream, const pb_field_t *field, co
 
 bool checkreturn pb_enc_svarint(pb_ostream_t *stream, const pb_field_t *field, const void *src)
 {
-    uint64_t value = 0;
+    int64_t value = 0;
     
     switch (field->data_size)
     {

pb_encode.h

@@ -9,6 +9,10 @@
 #include <stdbool.h>
 #include "pb.h"
 
+#ifdef __cplusplus
+extern "C" {
+#endif
+
 /* Lightweight output stream.
  * You can provide callback for writing or use pb_ostream_from_buffer.
  * 
@@ -54,7 +58,7 @@ bool pb_encode_tag_for_field(pb_ostream_t *stream, const pb_field_t *field);
 
 /* Encode field header by manually specifing wire type. You need to use this if
  * you want to write out packed arrays from a callback field. */
-bool pb_encode_tag(pb_ostream_t *stream, pb_wire_type_t wiretype, int field_number);
+bool pb_encode_tag(pb_ostream_t *stream, pb_wire_type_t wiretype, uint32_t field_number);
 
 /* Encode an integer in the varint format.
  * This works for bool, enum, int32, int64, uint32 and uint64 field types. */
@@ -99,5 +103,8 @@ bool pb_enc_string(pb_ostream_t *stream, const pb_field_t *field, const void *sr
  * instead, it has the same functionality with a less confusing interface. */
 bool pb_enc_submessage(pb_ostream_t *stream, const pb_field_t *field, const void *src);
 
+#ifdef __cplusplus
+} /* extern "C" */
+#endif
 
 #endif

tests/Makefile

@@ -4,7 +4,7 @@ DEPS=../pb_decode.h ../pb_encode.h ../pb.h person.pb.h callbacks.pb.h unittests.
 TESTS=test_decode1 test_encode1 decode_unittests encode_unittests test_no_messages
 
 # More strict checks for the core part of nanopb
-CFLAGS_CORE=-pedantic -Wextra -Wcast-qual -Wlogical-op
+CFLAGS_CORE=-pedantic -Wextra -Wcast-qual -Wlogical-op -Wconversion
 
 all: breakpoints $(TESTS) run_unittests
 
@@ -55,7 +55,7 @@ coverage: run_unittests
 	gcov pb_encode.gcda
 	gcov pb_decode.gcda
 
-run_unittests: decode_unittests encode_unittests test_cxxcompile test_encode1 test_encode2 test_encode3 test_decode1 test_decode2 test_decode3 test_encode_callbacks test_decode_callbacks test_missing_fields
+run_unittests: decode_unittests encode_unittests test_cxxcompile test_encode1 test_encode2 test_encode3 test_decode1 test_decode2 test_decode3 test_encode_callbacks test_decode_callbacks test_missing_fields test_options
 	rm -f *.gcda
 	
 	./decode_unittests > /dev/null
@@ -70,6 +70,9 @@ run_unittests: decode_unittests encode_unittests test_cxxcompile test_encode1 te
 	[ "`./test_encode2 | ./test_decode2`" = \
 	"`./test_encode2 | protoc --decode=Person -I. -I../generator -I/usr/include person.proto`" ]
 	
+	[ "`./test_decode2 < person_with_extra_field.pb`" = \
+	"`./test_encode2 | ./test_decode2`" ]
+	
 	[ "`./test_encode_callbacks | ./test_decode_callbacks`" = \
 	"`./test_encode_callbacks | protoc --decode=TestMessage callbacks.proto`" ]
 
@@ -79,5 +82,13 @@ run_unittests: decode_unittests encode_unittests test_cxxcompile test_encode1 te
 	
 	./test_missing_fields
 
+test_options: options.pb.h options.expected
+	cat options.expected | while read -r p; do \
+	    if ! grep -q "$$p" $<; then \
+	        echo Expected: "$$p"; \
+	        exit 1; \
+	    fi \
+	done
+
 run_fuzztest: test_decode2
 	bash -c 'I=1; while true; do cat /dev/urandom | ./test_decode2 > /dev/null; I=$$(($$I+1)); echo -en "\r$$I"; done'

tests/options.expected

@@ -0,0 +1,5 @@
+char filesize\[20\];
+char msgsize\[30\];
+char fieldsize\[40\];
+pb_callback_t int32_callback;
+[^_]EnumValue1 = 1

tests/options.proto

@@ -0,0 +1,39 @@
+/* Test nanopb option parsing.
+ * options.expected lists the patterns that are searched for in the output.
+ */
+
+import "nanopb.proto";
+
+// File level options
+option (nanopb_fileopt).max_size = 20;
+
+message Message1
+{
+    required string filesize = 1;
+}
+
+// Message level options
+message Message2
+{
+    option (nanopb_msgopt).max_size = 30;
+    required string msgsize = 1;
+}
+
+// Field level options
+message Message3
+{
+    required string fieldsize = 1 [(nanopb).max_size = 40];
+}
+
+// Forced callback field
+message Message4
+{
+    required int32 int32_callback = 1 [(nanopb).type = FT_CALLBACK];
+}
+
+// Short enum names
+enum Enum1
+{
+    option (nanopb_enumopt).long_names = false;
+    EnumValue1 = 1;
+}

tests/test_decode1.c

@@ -63,6 +63,12 @@ int main()
     uint8_t buffer[512];
     size_t count = fread(buffer, 1, sizeof(buffer), stdin);
     
+    if (!feof(stdin))
+    {
+    	printf("Message does not fit in buffer\n");
+    	return 1;
+    }
+    
     /* Construct a pb_istream_t for reading from the buffer */
     pb_istream_t stream = pb_istream_from_buffer(buffer, count);
     

tests/test_decode2.c

@@ -59,13 +59,6 @@ bool callback(pb_istream_t *stream, uint8_t *buf, size_t count)
     FILE *file = (FILE*)stream->state;
     bool status;
     
-    if (buf == NULL)
-    {
-       /* Skipping data */
-        while (count-- && fgetc(file) != EOF);
-        return count == 0;
-    }
-    
     status = (fread(buf, 1, count, file) == count);
     
     if (feof(file))

tests/test_decode3.c

@@ -26,20 +26,20 @@ bool check_alltypes(pb_istream_t *stream, int mode)
     if (!pb_decode(stream, AllTypes_fields, &alltypes))
         return false;
     
-    TEST(alltypes.req_int32         == 1001);
-    TEST(alltypes.req_int64         == 1002);
+    TEST(alltypes.req_int32         == -1001);
+    TEST(alltypes.req_int64         == -1002);
     TEST(alltypes.req_uint32        == 1003);
     TEST(alltypes.req_uint64        == 1004);
-    TEST(alltypes.req_sint32        == 1005);
-    TEST(alltypes.req_sint64        == 1006);
+    TEST(alltypes.req_sint32        == -1005);
+    TEST(alltypes.req_sint64        == -1006);
     TEST(alltypes.req_bool          == true);
     
     TEST(alltypes.req_fixed32       == 1008);
-    TEST(alltypes.req_sfixed32      == 1009);
+    TEST(alltypes.req_sfixed32      == -1009);
     TEST(alltypes.req_float         == 1010.0f);
     
     TEST(alltypes.req_fixed64       == 1011);
-    TEST(alltypes.req_sfixed64      == 1012);
+    TEST(alltypes.req_sfixed64      == -1012);
     TEST(alltypes.req_double        == 1013.0f);
     
     TEST(strcmp(alltypes.req_string, "1014") == 0);
@@ -50,20 +50,20 @@ bool check_alltypes(pb_istream_t *stream, int mode)
     TEST(alltypes.req_submsg.substuff3 == 3);
     TEST(alltypes.req_enum == MyEnum_Truth);
     
-    TEST(alltypes.rep_int32_count == 5 && alltypes.rep_int32[4] == 2001 && alltypes.rep_int32[0] == 0);
-    TEST(alltypes.rep_int64_count == 5 && alltypes.rep_int64[4] == 2002 && alltypes.rep_int64[0] == 0);
+    TEST(alltypes.rep_int32_count == 5 && alltypes.rep_int32[4] == -2001 && alltypes.rep_int32[0] == 0);
+    TEST(alltypes.rep_int64_count == 5 && alltypes.rep_int64[4] == -2002 && alltypes.rep_int64[0] == 0);
     TEST(alltypes.rep_uint32_count == 5 && alltypes.rep_uint32[4] == 2003 && alltypes.rep_uint32[0] == 0);
     TEST(alltypes.rep_uint64_count == 5 && alltypes.rep_uint64[4] == 2004 && alltypes.rep_uint64[0] == 0);
-    TEST(alltypes.rep_sint32_count == 5 && alltypes.rep_sint32[4] == 2005 && alltypes.rep_sint32[0] == 0);
-    TEST(alltypes.rep_sint64_count == 5 && alltypes.rep_sint64[4] == 2006 && alltypes.rep_sint64[0] == 0);
+    TEST(alltypes.rep_sint32_count == 5 && alltypes.rep_sint32[4] == -2005 && alltypes.rep_sint32[0] == 0);
+    TEST(alltypes.rep_sint64_count == 5 && alltypes.rep_sint64[4] == -2006 && alltypes.rep_sint64[0] == 0);
     TEST(alltypes.rep_bool_count == 5 && alltypes.rep_bool[4] == true && alltypes.rep_bool[0] == false);
     
     TEST(alltypes.rep_fixed32_count == 5 && alltypes.rep_fixed32[4] == 2008 && alltypes.rep_fixed32[0] == 0);
-    TEST(alltypes.rep_sfixed32_count == 5 && alltypes.rep_sfixed32[4] == 2009 && alltypes.rep_sfixed32[0] == 0);
+    TEST(alltypes.rep_sfixed32_count == 5 && alltypes.rep_sfixed32[4] == -2009 && alltypes.rep_sfixed32[0] == 0);
     TEST(alltypes.rep_float_count == 5 && alltypes.rep_float[4] == 2010.0f && alltypes.rep_float[0] == 0.0f);
     
     TEST(alltypes.rep_fixed64_count == 5 && alltypes.rep_fixed64[4] == 2011 && alltypes.rep_fixed64[0] == 0);
-    TEST(alltypes.rep_sfixed64_count == 5 && alltypes.rep_sfixed64[4] == 2012 && alltypes.rep_sfixed64[0] == 0);
+    TEST(alltypes.rep_sfixed64_count == 5 && alltypes.rep_sfixed64[4] == -2012 && alltypes.rep_sfixed64[0] == 0);
     TEST(alltypes.rep_double_count == 5 && alltypes.rep_double[4] == 2013.0 && alltypes.rep_double[0] == 0.0);
     
     TEST(alltypes.rep_string_count == 5 && strcmp(alltypes.rep_string[4], "2014") == 0 && alltypes.rep_string[0][0] == '\0');

tests/test_encode3.c

@@ -14,20 +14,20 @@ int main(int argc, char **argv)
     /* Initialize the structure with constants */
     AllTypes alltypes = {0};
     
-    alltypes.req_int32         = 1001;
-    alltypes.req_int64         = 1002;
+    alltypes.req_int32         = -1001;
+    alltypes.req_int64         = -1002;
     alltypes.req_uint32        = 1003;
     alltypes.req_uint64        = 1004;
-    alltypes.req_sint32        = 1005;
-    alltypes.req_sint64        = 1006;
+    alltypes.req_sint32        = -1005;
+    alltypes.req_sint64        = -1006;
     alltypes.req_bool          = true;
     
     alltypes.req_fixed32       = 1008;
-    alltypes.req_sfixed32      = 1009;
+    alltypes.req_sfixed32      = -1009;
     alltypes.req_float         = 1010.0f;
     
     alltypes.req_fixed64       = 1011;
-    alltypes.req_sfixed64      = 1012;
+    alltypes.req_sfixed64      = -1012;
     alltypes.req_double        = 1013.0;
     
     strcpy(alltypes.req_string, "1014");
@@ -37,20 +37,20 @@ int main(int argc, char **argv)
     alltypes.req_submsg.substuff2 = 1016;
     alltypes.req_enum = MyEnum_Truth;
     
-    alltypes.rep_int32_count = 5; alltypes.rep_int32[4] = 2001;
-    alltypes.rep_int64_count = 5; alltypes.rep_int64[4] = 2002;
+    alltypes.rep_int32_count = 5; alltypes.rep_int32[4] = -2001;
+    alltypes.rep_int64_count = 5; alltypes.rep_int64[4] = -2002;
     alltypes.rep_uint32_count = 5; alltypes.rep_uint32[4] = 2003;
     alltypes.rep_uint64_count = 5; alltypes.rep_uint64[4] = 2004;
-    alltypes.rep_sint32_count = 5; alltypes.rep_sint32[4] = 2005;
-    alltypes.rep_sint64_count = 5; alltypes.rep_sint64[4] = 2006;
+    alltypes.rep_sint32_count = 5; alltypes.rep_sint32[4] = -2005;
+    alltypes.rep_sint64_count = 5; alltypes.rep_sint64[4] = -2006;
     alltypes.rep_bool_count = 5; alltypes.rep_bool[4] = true;
     
     alltypes.rep_fixed32_count = 5; alltypes.rep_fixed32[4] = 2008;
-    alltypes.rep_sfixed32_count = 5; alltypes.rep_sfixed32[4] = 2009;
+    alltypes.rep_sfixed32_count = 5; alltypes.rep_sfixed32[4] = -2009;
     alltypes.rep_float_count = 5; alltypes.rep_float[4] = 2010.0f;
     
     alltypes.rep_fixed64_count = 5; alltypes.rep_fixed64[4] = 2011;
-    alltypes.rep_sfixed64_count = 5; alltypes.rep_sfixed64[4] = 2012;
+    alltypes.rep_sfixed64_count = 5; alltypes.rep_sfixed64[4] = -2012;
     alltypes.rep_double_count = 5; alltypes.rep_double[4] = 2013.0;
     
     alltypes.rep_string_count = 5; strcpy(alltypes.rep_string[4], "2014");

tools/set_version.sh

@@ -0,0 +1,10 @@
+#!/bin/bash
+
+# Run this from the top directory of nanopb tree.
+# e.g. user@localhost:~/nanopb$ tools/set_version.sh nanopb-0.1.9-dev
+# It sets the version number in pb.h and generator/nanopb_generator.py.
+
+sed -i -e 's/nanopb_version\s*=\s*"[^"]*"/nanopb_version = "'$1'"/' generator/nanopb_generator.py
+sed -i -e 's/#define\s*NANOPB_VERSION\s*.*/#define NANOPB_VERSION '$1'/' pb.h
+
+