Add support for running the nanopb generator as protoc plugin.

Will be used to implement issue 47.

For now, symlink nanopb_generator.py as protoc-gen-nanopb and
use protoc --nanopb_out=. to call it.

4 files changed, 419 insertions, 55 deletions

diff --git a/generator/Makefile b/generator/Makefile
index 161ef387..f2b02a95 100644
--- a/generator/Makefile
+++ b/generator/Makefile
@@ -1,2 +1,5 @@
 nanopb_pb2.py: nanopb.proto
 	protoc --python_out=. -I /usr/include -I . nanopb.proto
+
+plugin_pb2.py: plugin.proto
+	protoc --python_out=. -I /usr/include -I . plugin.proto
diff --git a/generator/nanopb_generator.py b/generator/nanopb_generator.py
index 55e5ab65..d70938a1 100644..100755
--- a/generator/nanopb_generator.py
+++ b/generator/nanopb_generator.py
@@ -1,3 +1,5 @@
+#!/usr/bin/python
+
 '''Generate header file for nanopb from a ProtoBuf FileDescriptorSet.'''
 nanopb_version = "nanopb-0.2.3-dev"
 
@@ -602,7 +604,7 @@ def generate_header(dependencies, headername, enums, messages, extensions, optio
     # 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'
@@ -780,73 +782,126 @@ 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 plugin_pb2
+    data = sys.stdin.read()
+    request = plugin_pb2.CodeGeneratorRequest.FromString(data)
     
-    if not status:
-        sys.exit(1)
+    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]:
+        main_plugin()
+    else:
+        main_cli()
+
diff --git a/generator/plugin.proto b/generator/plugin.proto
new file mode 100644
index 00000000..651ed10c
--- /dev/null
+++ b/generator/plugin.proto
@@ -0,0 +1,145 @@
+// Protocol Buffers - Google's data interchange format
+// Copyright 2008 Google Inc.  All rights reserved.
+// http://code.google.com/p/protobuf/
+//
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions are
+// met:
+//
+//     * Redistributions of source code must retain the above copyright
+// notice, this list of conditions and the following disclaimer.
+//     * Redistributions in binary form must reproduce the above
+// copyright notice, this list of conditions and the following disclaimer
+// in the documentation and/or other materials provided with the
+// distribution.
+//     * Neither the name of Google Inc. nor the names of its
+// contributors may be used to endorse or promote products derived from
+// this software without specific prior written permission.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+// Author: kenton@google.com (Kenton Varda)
+//
+// WARNING:  The plugin interface is currently EXPERIMENTAL and is subject to
+//   change.
+//
+// protoc (aka the Protocol Compiler) can be extended via plugins.  A plugin is
+// just a program that reads a CodeGeneratorRequest from stdin and writes a
+// CodeGeneratorResponse to stdout.
+//
+// Plugins written using C++ can use google/protobuf/compiler/plugin.h instead
+// of dealing with the raw protocol defined here.
+//
+// A plugin executable needs only to be placed somewhere in the path.  The
+// plugin should be named "protoc-gen-$NAME", and will then be used when the
+// flag "--${NAME}_out" is passed to protoc.
+
+package google.protobuf.compiler;
+
+import "google/protobuf/descriptor.proto";
+
+// An encoded CodeGeneratorRequest is written to the plugin's stdin.
+message CodeGeneratorRequest {
+  // The .proto files that were explicitly listed on the command-line.  The
+  // code generator should generate code only for these files.  Each file's
+  // descriptor will be included in proto_file, below.
+  repeated string file_to_generate = 1;
+
+  // The generator parameter passed on the command-line.
+  optional string parameter = 2;
+
+  // FileDescriptorProtos for all files in files_to_generate and everything
+  // they import.  The files will appear in topological order, so each file
+  // appears before any file that imports it.
+  //
+  // protoc guarantees that all proto_files will be written after
+  // the fields above, even though this is not technically guaranteed by the
+  // protobuf wire format.  This theoretically could allow a plugin to stream
+  // in the FileDescriptorProtos and handle them one by one rather than read
+  // the entire set into memory at once.  However, as of this writing, this
+  // is not similarly optimized on protoc's end -- it will store all fields in
+  // memory at once before sending them to the plugin.
+  repeated FileDescriptorProto proto_file = 15;
+}
+
+// The plugin writes an encoded CodeGeneratorResponse to stdout.
+message CodeGeneratorResponse {
+  // Error message.  If non-empty, code generation failed.  The plugin process
+  // should exit with status code zero even if it reports an error in this way.
+  //
+  // This should be used to indicate errors in .proto files which prevent the
+  // code generator from generating correct code.  Errors which indicate a
+  // problem in protoc itself -- such as the input CodeGeneratorRequest being
+  // unparseable -- should be reported by writing a message to stderr and
+  // exiting with a non-zero status code.
+  optional string error = 1;
+
+  // Represents a single generated file.
+  message File {
+    // The file name, relative to the output directory.  The name must not
+    // contain "." or ".." components and must be relative, not be absolute (so,
+    // the file cannot lie outside the output directory).  "/" must be used as
+    // the path separator, not "\".
+    //
+    // If the name is omitted, the content will be appended to the previous
+    // file.  This allows the generator to break large files into small chunks,
+    // and allows the generated text to be streamed back to protoc so that large
+    // files need not reside completely in memory at one time.  Note that as of
+    // this writing protoc does not optimize for this -- it will read the entire
+    // CodeGeneratorResponse before writing files to disk.
+    optional string name = 1;
+
+    // If non-empty, indicates that the named file should already exist, and the
+    // content here is to be inserted into that file at a defined insertion
+    // point.  This feature allows a code generator to extend the output
+    // produced by another code generator.  The original generator may provide
+    // insertion points by placing special annotations in the file that look
+    // like:
+    //   @@protoc_insertion_point(NAME)
+    // The annotation can have arbitrary text before and after it on the line,
+    // which allows it to be placed in a comment.  NAME should be replaced with
+    // an identifier naming the point -- this is what other generators will use
+    // as the insertion_point.  Code inserted at this point will be placed
+    // immediately above the line containing the insertion point (thus multiple
+    // insertions to the same point will come out in the order they were added).
+    // The double-@ is intended to make it unlikely that the generated code
+    // could contain things that look like insertion points by accident.
+    //
+    // For example, the C++ code generator places the following line in the
+    // .pb.h files that it generates:
+    //   // @@protoc_insertion_point(namespace_scope)
+    // This line appears within the scope of the file's package namespace, but
+    // outside of any particular class.  Another plugin can then specify the
+    // insertion_point "namespace_scope" to generate additional classes or
+    // other declarations that should be placed in this scope.
+    //
+    // Note that if the line containing the insertion point begins with
+    // whitespace, the same whitespace will be added to every line of the
+    // inserted text.  This is useful for languages like Python, where
+    // indentation matters.  In these languages, the insertion point comment
+    // should be indented the same amount as any inserted code will need to be
+    // in order to work correctly in that context.
+    //
+    // The code generator that generates the initial file and the one which
+    // inserts into it must both run as part of a single invocation of protoc.
+    // Code generators are executed in the order in which they appear on the
+    // command line.
+    //
+    // If |insertion_point| is present, |name| must also be present.
+    optional string insertion_point = 2;
+
+    // The file contents.
+    optional string content = 15;
+  }
+  repeated File file = 15;
+}
diff --git a/generator/plugin_pb2.py b/generator/plugin_pb2.py
new file mode 100644
index 00000000..2d8c09d4
--- /dev/null
+++ b/generator/plugin_pb2.py
@@ -0,0 +1,161 @@
+# Generated by the protocol buffer compiler.  DO NOT EDIT!
+
+from google.protobuf import descriptor
+from google.protobuf import message
+from google.protobuf import reflection
+from google.protobuf import descriptor_pb2
+# @@protoc_insertion_point(imports)
+
+
+import google.protobuf.descriptor_pb2
+
+DESCRIPTOR = descriptor.FileDescriptor(
+  name='plugin.proto',
+  package='google.protobuf.compiler',
+  serialized_pb='\n\x0cplugin.proto\x12\x18google.protobuf.compiler\x1a google/protobuf/descriptor.proto\"}\n\x14\x43odeGeneratorRequest\x12\x18\n\x10\x66ile_to_generate\x18\x01 \x03(\t\x12\x11\n\tparameter\x18\x02 \x01(\t\x12\x38\n\nproto_file\x18\x0f \x03(\x0b\x32$.google.protobuf.FileDescriptorProto\"\xaa\x01\n\x15\x43odeGeneratorResponse\x12\r\n\x05\x65rror\x18\x01 \x01(\t\x12\x42\n\x04\x66ile\x18\x0f \x03(\x0b\x32\x34.google.protobuf.compiler.CodeGeneratorResponse.File\x1a>\n\x04\x46ile\x12\x0c\n\x04name\x18\x01 \x01(\t\x12\x17\n\x0finsertion_point\x18\x02 \x01(\t\x12\x0f\n\x07\x63ontent\x18\x0f \x01(\t')
+
+
+
+
+_CODEGENERATORREQUEST = descriptor.Descriptor(
+  name='CodeGeneratorRequest',
+  full_name='google.protobuf.compiler.CodeGeneratorRequest',
+  filename=None,
+  file=DESCRIPTOR,
+  containing_type=None,
+  fields=[
+    descriptor.FieldDescriptor(
+      name='file_to_generate', full_name='google.protobuf.compiler.CodeGeneratorRequest.file_to_generate', index=0,
+      number=1, type=9, cpp_type=9, label=3,
+      has_default_value=False, default_value=[],
+      message_type=None, enum_type=None, containing_type=None,
+      is_extension=False, extension_scope=None,
+      options=None),
+    descriptor.FieldDescriptor(
+      name='parameter', full_name='google.protobuf.compiler.CodeGeneratorRequest.parameter', index=1,
+      number=2, type=9, cpp_type=9, label=1,
+      has_default_value=False, default_value=unicode("", "utf-8"),
+      message_type=None, enum_type=None, containing_type=None,
+      is_extension=False, extension_scope=None,
+      options=None),
+    descriptor.FieldDescriptor(
+      name='proto_file', full_name='google.protobuf.compiler.CodeGeneratorRequest.proto_file', index=2,
+      number=15, type=11, cpp_type=10, label=3,
+      has_default_value=False, default_value=[],
+      message_type=None, enum_type=None, containing_type=None,
+      is_extension=False, extension_scope=None,
+      options=None),
+  ],
+  extensions=[
+  ],
+  nested_types=[],
+  enum_types=[
+  ],
+  options=None,
+  is_extendable=False,
+  extension_ranges=[],
+  serialized_start=76,
+  serialized_end=201,
+)
+
+
+_CODEGENERATORRESPONSE_FILE = descriptor.Descriptor(
+  name='File',
+  full_name='google.protobuf.compiler.CodeGeneratorResponse.File',
+  filename=None,
+  file=DESCRIPTOR,
+  containing_type=None,
+  fields=[
+    descriptor.FieldDescriptor(
+      name='name', full_name='google.protobuf.compiler.CodeGeneratorResponse.File.name', index=0,
+      number=1, type=9, cpp_type=9, label=1,
+      has_default_value=False, default_value=unicode("", "utf-8"),
+      message_type=None, enum_type=None, containing_type=None,
+      is_extension=False, extension_scope=None,
+      options=None),
+    descriptor.FieldDescriptor(
+      name='insertion_point', full_name='google.protobuf.compiler.CodeGeneratorResponse.File.insertion_point', index=1,
+      number=2, type=9, cpp_type=9, label=1,
+      has_default_value=False, default_value=unicode("", "utf-8"),
+      message_type=None, enum_type=None, containing_type=None,
+      is_extension=False, extension_scope=None,
+      options=None),
+    descriptor.FieldDescriptor(
+      name='content', full_name='google.protobuf.compiler.CodeGeneratorResponse.File.content', index=2,
+      number=15, type=9, cpp_type=9, label=1,
+      has_default_value=False, default_value=unicode("", "utf-8"),
+      message_type=None, enum_type=None, containing_type=None,
+      is_extension=False, extension_scope=None,
+      options=None),
+  ],
+  extensions=[
+  ],
+  nested_types=[],
+  enum_types=[
+  ],
+  options=None,
+  is_extendable=False,
+  extension_ranges=[],
+  serialized_start=312,
+  serialized_end=374,
+)
+
+_CODEGENERATORRESPONSE = descriptor.Descriptor(
+  name='CodeGeneratorResponse',
+  full_name='google.protobuf.compiler.CodeGeneratorResponse',
+  filename=None,
+  file=DESCRIPTOR,
+  containing_type=None,
+  fields=[
+    descriptor.FieldDescriptor(
+      name='error', full_name='google.protobuf.compiler.CodeGeneratorResponse.error', index=0,
+      number=1, type=9, cpp_type=9, label=1,
+      has_default_value=False, default_value=unicode("", "utf-8"),
+      message_type=None, enum_type=None, containing_type=None,
+      is_extension=False, extension_scope=None,
+      options=None),
+    descriptor.FieldDescriptor(
+      name='file', full_name='google.protobuf.compiler.CodeGeneratorResponse.file', index=1,
+      number=15, type=11, cpp_type=10, label=3,
+      has_default_value=False, default_value=[],
+      message_type=None, enum_type=None, containing_type=None,
+      is_extension=False, extension_scope=None,
+      options=None),
+  ],
+  extensions=[
+  ],
+  nested_types=[_CODEGENERATORRESPONSE_FILE, ],
+  enum_types=[
+  ],
+  options=None,
+  is_extendable=False,
+  extension_ranges=[],
+  serialized_start=204,
+  serialized_end=374,
+)
+
+_CODEGENERATORREQUEST.fields_by_name['proto_file'].message_type = google.protobuf.descriptor_pb2._FILEDESCRIPTORPROTO
+_CODEGENERATORRESPONSE_FILE.containing_type = _CODEGENERATORRESPONSE;
+_CODEGENERATORRESPONSE.fields_by_name['file'].message_type = _CODEGENERATORRESPONSE_FILE
+DESCRIPTOR.message_types_by_name['CodeGeneratorRequest'] = _CODEGENERATORREQUEST
+DESCRIPTOR.message_types_by_name['CodeGeneratorResponse'] = _CODEGENERATORRESPONSE
+
+class CodeGeneratorRequest(message.Message):
+  __metaclass__ = reflection.GeneratedProtocolMessageType
+  DESCRIPTOR = _CODEGENERATORREQUEST
+  
+  # @@protoc_insertion_point(class_scope:google.protobuf.compiler.CodeGeneratorRequest)
+
+class CodeGeneratorResponse(message.Message):
+  __metaclass__ = reflection.GeneratedProtocolMessageType
+  
+  class File(message.Message):
+    __metaclass__ = reflection.GeneratedProtocolMessageType
+    DESCRIPTOR = _CODEGENERATORRESPONSE_FILE
+    
+    # @@protoc_insertion_point(class_scope:google.protobuf.compiler.CodeGeneratorResponse.File)
+  DESCRIPTOR = _CODEGENERATORRESPONSE
+  
+  # @@protoc_insertion_point(class_scope:google.protobuf.compiler.CodeGeneratorResponse)
+
+# @@protoc_insertion_point(module_scope)