X-Git-Url: https://gerrit.automotivelinux.org/gerrit/gitweb?a=blobdiff_plain;ds=sidebyside;f=generator%2Fnanopb_generator.py;h=7b3c9f80622b6bbad929625f916b02ce1cb8415c;hb=45c1a32e5046fe9323d4fd0213b474a554b2bbed;hp=e3cddb61d0f4bbf984a4ac2d1d7e56d47d8260b2;hpb=4aef194a99705805153471c371e16a3633a4cc4e;p=apps%2Fagl-service-can-low-level.git diff --git a/generator/nanopb_generator.py b/generator/nanopb_generator.py old mode 100644 new mode 100755 index e3cddb61..7b3c9f80 --- a/generator/nanopb_generator.py +++ b/generator/nanopb_generator.py @@ -1,8 +1,10 @@ +#!/usr/bin/python + '''Generate header file for nanopb from a ProtoBuf FileDescriptorSet.''' -nanopb_version = "nanopb-0.2.3-dev" +nanopb_version = "nanopb-0.2.5-dev" try: - import google.protobuf.descriptor_pb2 as descriptor + import google, distutils.util # bbfreeze seems to need these import google.protobuf.text_format as text_format except: print @@ -14,21 +16,18 @@ except: raise try: - import nanopb_pb2 + import proto.nanopb_pb2 as nanopb_pb2 + import proto.descriptor_pb2 as descriptor except: print - print "***************************************************************" - print "*** Could not import the precompiled nanopb_pb2.py. ***" - print "*** Run 'make' in the 'generator' folder to update the file.***" - print "***************************************************************" + print "********************************************************************" + print "*** Failed to import the protocol definitions for generator. ***" + print "*** You have to run 'make' in the nanopb/generator/proto folder. ***" + print "********************************************************************" print raise - - - - # --------------------------------------------------------------------------- # Generation of single fields # --------------------------------------------------------------------------- @@ -36,22 +35,22 @@ except: import time import os.path -# Values are tuple (c type, pb type) +# Values are tuple (c type, pb type, encoded size) FieldD = descriptor.FieldDescriptorProto datatypes = { - FieldD.TYPE_BOOL: ('bool', 'BOOL'), - FieldD.TYPE_DOUBLE: ('double', 'DOUBLE'), - FieldD.TYPE_FIXED32: ('uint32_t', 'FIXED32'), - FieldD.TYPE_FIXED64: ('uint64_t', 'FIXED64'), - FieldD.TYPE_FLOAT: ('float', 'FLOAT'), - FieldD.TYPE_INT32: ('int32_t', 'INT32'), - FieldD.TYPE_INT64: ('int64_t', 'INT64'), - FieldD.TYPE_SFIXED32: ('int32_t', 'SFIXED32'), - FieldD.TYPE_SFIXED64: ('int64_t', 'SFIXED64'), - FieldD.TYPE_SINT32: ('int32_t', 'SINT32'), - FieldD.TYPE_SINT64: ('int64_t', 'SINT64'), - FieldD.TYPE_UINT32: ('uint32_t', 'UINT32'), - FieldD.TYPE_UINT64: ('uint64_t', 'UINT64') + FieldD.TYPE_BOOL: ('bool', 'BOOL', 1), + FieldD.TYPE_DOUBLE: ('double', 'DOUBLE', 8), + FieldD.TYPE_FIXED32: ('uint32_t', 'FIXED32', 4), + FieldD.TYPE_FIXED64: ('uint64_t', 'FIXED64', 8), + FieldD.TYPE_FLOAT: ('float', 'FLOAT', 4), + FieldD.TYPE_INT32: ('int32_t', 'INT32', 10), + FieldD.TYPE_INT64: ('int64_t', 'INT64', 10), + FieldD.TYPE_SFIXED32: ('int32_t', 'SFIXED32', 4), + FieldD.TYPE_SFIXED64: ('int64_t', 'SFIXED64', 8), + FieldD.TYPE_SINT32: ('int32_t', 'SINT32', 5), + FieldD.TYPE_SINT64: ('int64_t', 'SINT64', 10), + FieldD.TYPE_UINT32: ('uint32_t', 'UINT32', 5), + FieldD.TYPE_UINT64: ('uint64_t', 'UINT64', 10) } class Names: @@ -81,6 +80,55 @@ def names_from_type_name(type_name): raise NotImplementedError("Lookup of non-absolute type names is not supported") return Names(type_name[1:].split('.')) +def varint_max_size(max_value): + '''Returns the maximum number of bytes a varint can take when encoded.''' + for i in range(1, 11): + if (max_value >> (i * 7)) == 0: + return i + raise ValueError("Value too large for varint: " + str(max_value)) + +assert varint_max_size(0) == 1 +assert varint_max_size(127) == 1 +assert varint_max_size(128) == 2 + +class EncodedSize: + '''Class used to represent the encoded size of a field or a message. + Consists of a combination of symbolic sizes and integer sizes.''' + def __init__(self, value = 0, symbols = []): + if isinstance(value, (str, Names)): + symbols = [str(value)] + value = 0 + self.value = value + self.symbols = symbols + + def __add__(self, other): + if isinstance(other, (int, long)): + return EncodedSize(self.value + other, self.symbols) + elif isinstance(other, (str, Names)): + return EncodedSize(self.value, self.symbols + [str(other)]) + elif isinstance(other, EncodedSize): + return EncodedSize(self.value + other.value, self.symbols + other.symbols) + else: + raise ValueError("Cannot add size: " + repr(other)) + + def __mul__(self, other): + if isinstance(other, (int, long)): + return EncodedSize(self.value * other, [str(other) + '*' + s for s in self.symbols]) + else: + raise ValueError("Cannot multiply size: " + repr(other)) + + def __str__(self): + if not self.symbols: + return str(self.value) + else: + return '(' + str(self.value) + ' + ' + ' + '.join(self.symbols) + ')' + + def upperlimit(self): + if not self.symbols: + return self.value + else: + return 2**32 - 1 + class Enum: def __init__(self, names, desc, enum_options): '''desc is EnumDescriptorProto''' @@ -111,6 +159,7 @@ class Field: self.max_size = None self.max_count = None self.array_decl = "" + self.enc_size = None # Parse field options if field_options.HasField("max_size"): @@ -137,62 +186,89 @@ class Field: else: raise NotImplementedError(desc.label) + # Check if the field can be implemented with static allocation + # i.e. whether the data size is known. + if desc.type == FieldD.TYPE_STRING and self.max_size is None: + can_be_static = False + + if desc.type == FieldD.TYPE_BYTES and self.max_size is None: + can_be_static = False + + # Decide how the field data will be allocated + 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_STATIC: + self.allocation = 'STATIC' + elif field_options.type == nanopb_pb2.FT_POINTER: + self.allocation = 'POINTER' + elif field_options.type == nanopb_pb2.FT_CALLBACK: + self.allocation = 'CALLBACK' + else: + raise NotImplementedError(field_options.type) + # Decide the C data type to use in the struct. if datatypes.has_key(desc.type): - self.ctype, self.pbtype = datatypes[desc.type] + self.ctype, self.pbtype, self.enc_size = datatypes[desc.type] elif desc.type == FieldD.TYPE_ENUM: self.pbtype = 'ENUM' self.ctype = names_from_type_name(desc.type_name) if self.default is not None: self.default = self.ctype + self.default + self.enc_size = 5 # protoc rejects enum values > 32 bits elif desc.type == FieldD.TYPE_STRING: self.pbtype = 'STRING' - if self.max_size is None: - can_be_static = False - else: + self.ctype = 'char' + if self.allocation == 'STATIC': self.ctype = 'char' self.array_decl += '[%d]' % self.max_size + self.enc_size = varint_max_size(self.max_size) + self.max_size elif desc.type == FieldD.TYPE_BYTES: self.pbtype = 'BYTES' - if self.max_size is None: - can_be_static = False - else: + if self.allocation == 'STATIC': self.ctype = self.struct_name + self.name + 't' + self.enc_size = varint_max_size(self.max_size) + self.max_size + elif self.allocation == 'POINTER': + self.ctype = 'pb_bytes_ptr_t' elif desc.type == FieldD.TYPE_MESSAGE: self.pbtype = 'MESSAGE' self.ctype = self.submsgname = names_from_type_name(desc.type_name) + self.enc_size = None # Needs to be filled in after the message type is available else: raise NotImplementedError(desc.type) - 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_STATIC: - self.allocation = 'STATIC' - elif field_options.type == nanopb_pb2.FT_CALLBACK: - self.allocation = 'CALLBACK' - self.ctype = 'pb_callback_t' - self.array_decl = '' - else: - raise NotImplementedError(field_options.type) - def __cmp__(self, other): return cmp(self.tag, other.tag) def __str__(self): - if self.rules == 'OPTIONAL' and self.allocation == 'STATIC': - result = ' bool has_' + self.name + ';\n' - elif self.rules == 'REPEATED' and self.allocation == 'STATIC': - result = ' size_t ' + self.name + '_count;\n' + result = '' + if self.allocation == 'POINTER': + if self.rules == 'REPEATED': + result += ' size_t ' + self.name + '_count;\n' + + if self.pbtype == 'MESSAGE': + # Use struct definition, so recursive submessages are possible + result += ' struct _%s *%s;' % (self.ctype, self.name) + elif self.rules == 'REPEATED' and self.pbtype == 'STRING': + # String arrays need to be defined as pointers to pointers + result += ' %s **%s;' % (self.ctype, self.name) + else: + result += ' %s *%s;' % (self.ctype, self.name) + elif self.allocation == 'CALLBACK': + result += ' pb_callback_t %s;' % self.name else: - result = '' - result += ' %s %s%s;' % (self.ctype, self.name, self.array_decl) + if self.rules == 'OPTIONAL' and self.allocation == 'STATIC': + result += ' bool has_' + self.name + ';\n' + elif self.rules == 'REPEATED' and self.allocation == 'STATIC': + result += ' size_t ' + self.name + '_count;\n' + result += ' %s %s%s;' % (self.ctype, self.name, self.array_decl) return result def types(self): @@ -244,10 +320,11 @@ class Field: '''Return the pb_field_t initializer to use in the constant array. prev_field_name is the name of the previous field or None. ''' - result = ' PB_FIELD(%3d, ' % self.tag + result = ' PB_FIELD2(%3d, ' % self.tag result += '%-8s, ' % self.pbtype result += '%s, ' % self.rules - result += '%s, ' % self.allocation + result += '%-8s, ' % self.allocation + result += '%s, ' % ("FIRST" if not prev_field_name else "OTHER") result += '%s, ' % self.struct_name result += '%s, ' % self.name result += '%s, ' % (prev_field_name or self.name) @@ -274,6 +351,51 @@ class Field: return max(self.tag, self.max_size, self.max_count) + def encoded_size(self, allmsgs): + '''Return the maximum size that this field can take when encoded, + including the field tag. If the size cannot be determined, returns + None.''' + + if self.allocation != 'STATIC': + return None + + if self.pbtype == 'MESSAGE': + for msg in allmsgs: + if msg.name == self.submsgname: + encsize = msg.encoded_size(allmsgs) + if encsize is None: + return None # Submessage size is indeterminate + + # Include submessage length prefix + encsize += varint_max_size(encsize.upperlimit()) + break + else: + # Submessage cannot be found, this currently occurs when + # the submessage type is defined in a different file. + # Instead of direct numeric value, reference the size that + # has been #defined in the other file. + encsize = EncodedSize(self.submsgname + 'size') + + # We will have to make a conservative assumption on the length + # prefix size, though. + encsize += 5 + + elif self.enc_size is None: + raise RuntimeError("Could not determine encoded size for %s.%s" + % (self.struct_name, self.name)) + else: + encsize = EncodedSize(self.enc_size) + + encsize += varint_max_size(self.tag << 3) # Tag + wire type + + if self.rules == 'REPEATED': + # Decoders must be always able to handle unpacked arrays. + # Therefore we have to reserve space for it, even though + # we emit packed arrays ourselves. + encsize *= self.max_count + + return encsize + class ExtensionRange(Field): def __init__(self, struct_name, range_start, field_options): @@ -302,6 +424,12 @@ class ExtensionRange(Field): def tags(self): return '' + + def encoded_size(self, allmsgs): + # We exclude extensions from the count, because they cannot be known + # until runtime. Other option would be to return None here, but this + # way the value remains useful if extensions are not used. + return EncodedSize(0) class ExtensionField(Field): def __init__(self, struct_name, desc, field_options): @@ -310,18 +438,31 @@ class ExtensionField(Field): Field.__init__(self, self.fullname + 'struct', desc, field_options) if self.rules != 'OPTIONAL': - raise NotImplementedError("Only 'optional' is supported for extension fields. " - + "(%s.rules == %s)" % (self.fullname, self.rules)) + self.skip = True + else: + self.skip = False + self.rules = 'OPTEXT' - self.rules = 'OPTEXT' + def tags(self): + '''Return the #define for the tag number of this field.''' + identifier = '%s_tag' % self.fullname + return '#define %-40s %d\n' % (identifier, self.tag) def extension_decl(self): '''Declaration of the extension type in the .pb.h file''' + if self.skip: + msg = '/* Extension field %s was skipped because only "optional"\n' % self.fullname + msg +=' type of extension fields is currently supported. */\n' + return msg + return 'extern const pb_extension_type_t %s;\n' % self.fullname def extension_def(self): '''Definition of the extension type in the .pb.c file''' + if self.skip: + return '' + result = 'typedef struct {\n' result += str(self) result += '\n} %s;\n\n' % self.struct_name @@ -418,6 +559,18 @@ class Message: result += ' PB_LAST_FIELD\n};' return result + def encoded_size(self, allmsgs): + '''Return the maximum size that this message can take when encoded. + If the size cannot be determined, returns None. + ''' + size = EncodedSize(0) + for field in self.fields: + fsize = field.encoded_size(allmsgs) + if fsize is None: + return None + size += fsize + + return size # --------------------------------------------------------------------------- @@ -475,7 +628,8 @@ def parse_file(fdesc, file_options): for names, extension in iterate_extensions(fdesc, base_name): field_options = get_nanopb_suboptions(extension, file_options, names) - extensions.append(ExtensionField(names, extension, field_options)) + if field_options.type != nanopb_pb2.FT_IGNORE: + extensions.append(ExtensionField(names, extension, field_options)) # Fix field default values where enum short names are used. for enum in enums: @@ -580,20 +734,31 @@ def generate_header(dependencies, headername, enums, messages, extensions, optio for msg in sort_dependencies(messages): for field in msg.fields: yield field.tags() + for extension in extensions: + yield extension.tags() yield '\n' yield '/* Struct field encoding specification for nanopb */\n' for msg in messages: yield msg.fields_declaration() + '\n' + yield '\n' + + yield '/* Maximum encoded size of messages (where known) */\n' + for msg in messages: + msize = msg.encoded_size(messages) + if msize is not None: + identifier = '%s_size' % msg.name + yield '#define %-40s %s\n' % (identifier, msize) + yield '\n' - yield '\n#ifdef __cplusplus\n' + yield '#ifdef __cplusplus\n' yield '} /* extern "C" */\n' yield '#endif\n' # End of header yield '\n#endif\n' -def generate_source(headername, enums, messages, extensions): +def generate_source(headername, enums, messages, extensions, options): '''Generate content for a source file.''' yield '/* Automatically generated nanopb constant definitions */\n' @@ -771,73 +936,133 @@ optparser.add_option("-v", "--verbose", dest="verbose", action="store_true", def optparser.add_option("-s", dest="settings", metavar="OPTION:VALUE", action="append", default=[], help="Set generator option (max_size, max_count etc.).") -def process(filenames, options): - '''Process the files given on the command line.''' +def process_file(filename, fdesc, options): + '''Process a single file. + filename: The full path to the .proto or .pb source file, as string. + fdesc: The loaded FileDescriptorSet, or None to read from the input file. + options: Command line options as they come from OptionsParser. + + Returns a dict: + {'headername': Name of header file, + 'headerdata': Data for the .h header file, + 'sourcename': Name of the source code file, + 'sourcedata': Data for the .c source code file + } + ''' + toplevel_options = nanopb_pb2.NanoPBOptions() + for s in options.settings: + text_format.Merge(s, toplevel_options) + + if not fdesc: + data = open(filename, 'rb').read() + fdesc = descriptor.FileDescriptorSet.FromString(data).file[0] + + # Check if there is a separate .options file + try: + optfilename = options.options_file % os.path.splitext(filename)[0] + except TypeError: + # No %s specified, use the filename as-is + optfilename = options.options_file + + if options.verbose: + print 'Reading options from ' + optfilename + + if os.path.isfile(optfilename): + Globals.separate_options = read_options_file(open(optfilename, "rU")) + else: + Globals.separate_options = [] + + # Parse the file + file_options = get_nanopb_suboptions(fdesc, toplevel_options, Names([filename])) + enums, messages, extensions = parse_file(fdesc, file_options) + + # Decide the file names + noext = os.path.splitext(filename)[0] + headername = noext + '.' + options.extension + '.h' + sourcename = noext + '.' + options.extension + '.c' + headerbasename = os.path.basename(headername) + + # 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.dependency if d not in excludes] + + headerdata = ''.join(generate_header(dependencies, headerbasename, enums, + messages, extensions, options)) + + sourcedata = ''.join(generate_source(headerbasename, enums, + messages, extensions, options)) + + return {'headername': headername, 'headerdata': headerdata, + 'sourcename': sourcename, 'sourcedata': sourcedata} + +def main_cli(): + '''Main function when invoked directly from the command line.''' + + options, filenames = optparser.parse_args() if not filenames: optparser.print_help() - return False + sys.exit(1) if options.quiet: options.verbose = False Globals.verbose_options = options.verbose - 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) - - # Check if any separate options are specified - try: - optfilename = options.options_file % os.path.splitext(filename)[0] - except TypeError: - # No %s specified, use the filename as-is - optfilename = options.options_file - - if options.verbose: - print 'Reading options from ' + optfilename - - if os.path.isfile(optfilename): - Globals.separate_options = read_options_file(open(optfilename, "rU")) - else: - Globals.separate_options = [] - - # Parse the file - file_options = get_nanopb_suboptions(fdesc.file[0], toplevel_options, Names([filename])) - enums, messages, extensions = parse_file(fdesc.file[0], file_options) - - noext = os.path.splitext(filename)[0] - headername = noext + '.' + options.extension + '.h' - sourcename = noext + '.' + options.extension + '.c' - headerbasename = os.path.basename(headername) + results = process_file(filename, None, options) 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, extensions, options): - header.write(part) - - source = open(sourcename, 'w') - for part in generate_source(headerbasename, enums, messages, extensions): - source.write(part) + print "Writing to " + results['headername'] + " and " + results['sourcename'] + + open(results['headername'], 'w').write(results['headerdata']) + open(results['sourcename'], 'w').write(results['sourcedata']) - return True +def main_plugin(): + '''Main function when invoked as a protoc plugin.''' -if __name__ == '__main__': - options, filenames = optparser.parse_args() - status = process(filenames, options) + import sys + if sys.platform == "win32": + import os, msvcrt + # Set stdin and stdout to binary mode + msvcrt.setmode(sys.stdin.fileno(), os.O_BINARY) + msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY) - if not status: - sys.exit(1) + import proto.plugin_pb2 as plugin_pb2 + data = sys.stdin.read() + request = plugin_pb2.CodeGeneratorRequest.FromString(data) + + import shlex + args = shlex.split(request.parameter) + options, dummy = optparser.parse_args(args) + # We can't go printing stuff to stdout + Globals.verbose_options = False + options.verbose = False + options.quiet = True + + response = plugin_pb2.CodeGeneratorResponse() + + for filename in request.file_to_generate: + for fdesc in request.proto_file: + if fdesc.name == filename: + results = process_file(filename, fdesc, options) + + f = response.file.add() + f.name = results['headername'] + f.content = results['headerdata'] + + f = response.file.add() + f.name = results['sourcename'] + f.content = results['sourcedata'] + + sys.stdout.write(response.SerializeToString()) + +if __name__ == '__main__': + # Check if we are running as a plugin under protoc + if 'protoc-gen-' in sys.argv[0] or '--protoc-plugin' in sys.argv: + main_plugin() + else: + main_cli() +