feat: remove generated protobuf code from substrait-python (#145)

Generation of protobuf bindings has been extracted to the
substrait-protobuf package.

BREAKING CHANGE: code under `substrait.gen.proto` is now found under
`substrait`
BREAKING CHANGE: simple extension files have been moved from
`extensions` to `extension_files`
BREAKING CHANGE: version information has been moved to
`substrait.version` module

Author: vbarua

CONTRIBUTING.md

@@ -37,12 +37,12 @@ You can run the full code generation using the following command or use the indi
 pixi run codegen
 ```
 
-## Protobuf stubs
+## Extension Copying
 
-Run the proto codegen only:
+Copy the core function extensions into substrait-python
 
 ```
-pixi run codegen-proto
+pixi run copy-extensions
 ```
 
 ## Antlr grammar

buf.gen.yaml

@@ -0,0 +1,16 @@
+#!/usr/bin/env bash
+
+set -eou pipefail
+
+submodule_dir=./third_party/substrait
+extension_dir=./src/substrait/extension_files
+
+# Remove the old extension files
+rm -rf "$extension_dir"
+
+# Copy over new yaml files
+cp -fr "$submodule_dir"/extensions "$extension_dir"
+find "$extension_dir" -type f -exec chmod u+rw {} +
+
+# Ensure there's an __init__.py file in the extension directory
+touch $extension_dir/__init__.py

buf.yaml

@@ -1,4 +1,5 @@
-import substrait.gen.proto.algebra_pb2 as stalg
+import substrait.algebra_pb2 as stalg
+
 from substrait.builders.extended_expression import (
     column,
     literal,

copy_extension_yamls.sh

@@ -5,7 +5,10 @@ authors = [{name = "Substrait contributors", email = "substrait@googlegroups.com
 license = {text = "Apache-2.0"}
 readme = "README.md"
 requires-python = ">=3.10,<3.14"
-dependencies = ["protobuf >=5,<7"]
+dependencies = [
+    "protobuf >=5,<7",
+    "substrait-protobuf==0.79.0",
+]
 dynamic = ["version"]
 
 [tool.setuptools_scm]
@@ -53,11 +56,11 @@ update-substrait = [ { task = "update-submodule" }, { task = "codegen" }]
 
 update-submodule = "./update_submodule.sh"
 
-codegen = [{ task = "antlr" }, { task = "codegen-proto" }, { task = "codegen-extensions" }]
+codegen = [{ task = "antlr" }, { task = "copy-extensions" }, { task = "codegen-extensions" }]
 
 check-codegen = "./check_codegen.sh"
 
-codegen-proto = "./gen_proto.sh"
+copy-extensions = "./copy_extension_yamls.sh"
 
 antlr = """
 	cd third_party/substrait/grammar \

examples/builder_example.py

@@ -2,10 +2,11 @@
 from datetime import date
 from typing import Any, Callable, Iterable, Union
 
-import substrait.gen.proto.algebra_pb2 as stalg
-import substrait.gen.proto.extended_expression_pb2 as stee
-import substrait.gen.proto.extensions.extensions_pb2 as ste
-import substrait.gen.proto.type_pb2 as stp
+import substrait.algebra_pb2 as stalg
+import substrait.extended_expression_pb2 as stee
+import substrait.extensions.extensions_pb2 as ste
+import substrait.type_pb2 as stp
+
 from substrait.extension_registry import ExtensionRegistry
 from substrait.type_inference import infer_extended_expression_schema
 from substrait.utils import (