Add messages implementation for python (#165)

* [python] Add messages implementation for python

* [python] Review fixes

* Fixup property type definitions
* Fixup property descriptions
  * Descriptions inlined where possible
  * Property descriptions are placed after properties per se
* Remove redundant double-quotes at type definitions
* Split enums and model templates
* Simplify gh-action test matrix
* Fixup empty project.toml settings

* Update python/pyproject.toml

Co-authored-by: Luke Hill <20105237+luke-hill@users.noreply.github.com>

* Update CHANGELOG.md

---------

Co-authored-by: Luke Hill <20105237+luke-hill@users.noreply.github.com>
Co-authored-by: David Goss <david@davidgoss.co>

.github/workflows/release-pypi.yaml

@@ -0,0 +1,23 @@
+name: Release Python
+
+on:
+  push:
+    branches: [release/*]
+
+jobs:
+  release:
+    name: Release
+    runs-on: ubuntu-latest
+    environment: Release
+    permissions:
+      id-token: write
+    defaults:
+      run:
+        working-directory: python
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - uses: cucumber/action-publish-pypi@v3.0.0
+        with:
+          working-directory: "python"

.github/workflows/test-python.yml

@@ -0,0 +1,45 @@
+---
+name: test-python
+
+on:
+  push:
+    branches:
+      - main
+      - renovate/**
+  pull_request:
+    branches:
+      - main
+  workflow_dispatch:
+
+jobs:
+  build:
+
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        include:
+          # Test latest python on Windows / macOS
+          - { os: 'windows-latest', python-version: '3.13' }
+          - { os: 'macos-latest', python-version: '3.13' }
+        os: ['ubuntu-latest']
+        python-version: ['3.9', '3.10', '3.11', '3.12', '3.13', 'pypy3.9', 'pypy3.10']
+
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -U setuptools
+          pip install tox tox-gh-actions codecov
+      - name: Test with tox
+        working-directory: ./python
+        run: |
+          tox
+      - name: Gather codecov report
+        working-directory: ./python
+        run: |
+          codecov

.pre-commit-config.yaml

@@ -0,0 +1,38 @@
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+---
+files: ^python/
+exclude: .*python/src/cucumber_messages/_messages\.py
+repos:
+  - repo: https://github.com/psf/black
+    rev: 24.10.0
+    hooks:
+      - id: black
+        args:
+          - "python/src"
+          - "python/tests"
+  - repo: https://github.com/pycqa/isort
+    rev: 5.13.2
+    hooks:
+      - id: isort
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-added-large-files
+  - repo: https://github.com/macisamuele/language-formatters-pre-commit-hooks
+    rev: v2.14.0
+    hooks:
+      - id: pretty-format-toml
+        args: [--autofix]
+  - repo: https://github.com/asottile/pyupgrade
+    rev: v3.19.1
+    hooks:
+      - id: pyupgrade
+        args: ["--py39-plus"]
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.13.0
+    hooks:
+      - id: mypy
+        additional_dependencies: [types-setuptools, types-certifi]

CHANGELOG.md

@@ -6,6 +6,8 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/)
 and this project adheres to [Semantic Versioning](http://semver.org/).
 
 ## [Unreleased]
+### Added
+- [python] Added Python implementation ([#165](https://github.com/cucumber/messages/pull/165))
 
 ## [27.1.0] - 2025-01-28
 ### Added

Makefile

@@ -27,7 +27,7 @@ schemas = \
 	./jsonschema/UndefinedParameterType.json \
 	./jsonschema/Envelope.json
 
-languages = cpp go java javascript perl php ruby dotnet
+languages = cpp dotnet go java javascript perl php python ruby
 
 .DEFAULT_GOAL = help
 

codegen/codegen.rb

@@ -11,6 +11,7 @@
 require_relative 'generators/markdown'
 require_relative 'generators/perl'
 require_relative 'generators/php'
+require_relative 'generators/python'
 require_relative 'generators/ruby'
 require_relative 'generators/typescript'
 

codegen/generators/python.rb

@@ -0,0 +1,153 @@
+# frozen_string_literal: true
+
+module Generator
+  class Python < Base
+    def format_enum_value(value)
+      value.downcase.gsub(/[.\/+\s-]/, '_')
+    end
+
+    def get_sorted_properties(definition)
+      required_fields = definition['required'] || []
+      definition['properties'].sort_by do |name, *|
+        [required_fields.include?(name) ? 0 : 1, name]
+      end
+    end
+
+    def format_property(parent_type_name, property_name, property, required_fields)
+      snake_name = property_name.gsub(/([A-Z]+)([A-Z][a-z])/, '\1_\2')
+                               .gsub(/([a-z\d])([A-Z])/, '\1_\2')
+                               .downcase
+
+      property_type = get_property_type(parent_type_name, property_name, property)
+      is_required = required_fields.include?(property_name)
+
+      property_description = if property['description'] && !property['description'].include?("\n")
+        "  # #{property['description']}"
+      else
+        ''
+      end
+      if is_required
+        "#{snake_name}: #{property_type}#{property_description}"
+      else
+        "#{snake_name}: Optional[#{property_type}] = None#{property_description}"
+      end
+    end
+
+    def get_property_type(parent_type_name, property_name, property)
+      type = type_for(parent_type_name, property_name, property)
+      type.match?(/\A[A-Z]/) ? class_name(type) : type
+    end
+
+    def array_type_for(type_name)
+      inner_type = if language_translations_for_data_types.values.include?(type_name)
+        type_name  # Keep primitive types as is
+      else
+        class_name(type_name)  # CamelCase for complex types
+      end
+      inner_type
+    end
+
+    def format_description(raw_description, indent_string: '    ')
+      return '""" """' if raw_description.nil?
+
+      lines = raw_description.split("\n").map { |line|
+        if line.strip.empty?
+          ""
+        else
+          "#{indent_string}#{line.rstrip}"
+        end
+      }
+
+      %("""\n#{lines.join("\n")}\n#{indent_string}""")
+    end
+
+    def language_translations_for_data_types
+      {
+        'integer' => 'int',
+        'string' => 'str',
+        'boolean' => 'bool',
+        'array' => 'list'
+      }
+    end
+
+    private
+
+    def default_value(parent_type_name, property_name, property)
+      if property['type'] == 'string'
+        default_value_for_string(parent_type_name, property_name, property)
+      elsif property['type'] == 'integer'
+        '0'
+      elsif property['type'] == 'boolean'
+        'False'
+      elsif property['type'] == 'array'
+        '[]'
+      elsif property['$ref']
+        "#{class_name(type_for(parent_type_name, nil, property))}()"
+      else
+        'None'
+      end
+    end
+
+    def default_value_for_string(parent_type_name, property_name, property)
+      if property['enum']
+        enum_type_name = type_for(parent_type_name, property_name, property)
+        "#{class_name(enum_type_name)}.#{enum_constant(property['enum'][0])}"
+      else
+        '""'
+      end
+    end
+
+    def type_for(parent_type_name, property_name, property)
+      if property['$ref']
+        property_type_from_ref(property['$ref'])
+      elsif property['type']
+        property_type_from_type(parent_type_name, property_name, property, type: property['type'])
+      else
+        raise "Property #{property_name} did not define 'type' or '$ref'"
+      end
+    end
+
+    def property_type_from_type(parent_type_name, property_name, property, type:)
+      if type == 'array'
+        type = type_for(parent_type_name, nil, property['items'])
+        inner_type = array_type_for(type)
+        "list[#{inner_type}]"
+      elsif property['enum']
+        enum_name(parent_type_name, property_name, property['enum'])
+      else
+        language_translations_for_data_types.fetch(type)
+      end
+    end
+
+    def enum_constant(value)
+      value.gsub(/[.\/+]/, '_').downcase
+    end
+
+    def enum_name(parent_type_name, property_name, enum)
+      "#{class_name(parent_type_name)}#{capitalize(property_name)}".tap do |name|
+        @enum_set.add({ name: name, values: enum })
+      end
+    end
+
+    def property_type_from_ref(ref)
+      class_name(ref)
+    end
+
+    def class_name(ref)
+      return ref if language_translations_for_data_types.values.include?(ref)
+
+      # Remove .json extension if present
+      name = ref.sub(/\.json$/, '')
+      # Get the basename without path
+      name = File.basename(name)
+      # Convert each word to proper case, handling camelCase and snake_case
+      parts = name.gsub(/[._-]/, '_').split('_').map do |part|
+        # Split by any existing camelCase
+        subparts = part.scan(/[A-Z][a-z]*|[a-z]+/)
+        subparts.map(&:capitalize).join
+      end
+      # Join all parts to create final CamelCase name
+      parts.join
+    end
+  end
+end

codegen/templates/python.enum.py.erb

@@ -0,0 +1,17 @@
+# This code was generated using the code generator from cucumber-messages.
+# Manual changes will be lost if the code is regenerated.
+# Generator: cucumber-messages-python
+
+from enum import Enum
+
+
+<%- @enums.each_with_index do |enum, index| -%>
+class <%= enum[:name] %>(Enum):
+    <%- enum[:values].each do |value| -%>
+    <%= format_enum_value(value) %> = "<%= value %>"
+    <%- end -%>
+<%- if index < @enums.length - 1 -%>
+
+
+<%- end -%>
+<%- end -%>

codegen/templates/python.py.erb

@@ -0,0 +1,34 @@
+# This code was generated using the code generator from cucumber-messages.
+# Manual changes will be lost if the code is regenerated.
+# Generator: cucumber-messages-python
+
+from __future__ import annotations
+from dataclasses import dataclass
+from typing import Optional
+
+from ._message_enums import *
+
+<%- @schemas.each_with_index do |schema_pair, index| -%>
+<%- key, definition = schema_pair -%>
+@dataclass
+class <%= class_name(key) %>:
+    <%- if definition['description'] -%>
+    <%= format_description(definition['description']) %>
+    <%- end -%>
+    <%- if definition['properties'].any? -%>
+    <%- required_fields = definition['required'] || [] -%>
+    <%- get_sorted_properties(definition).each do |property_name, property| -%>
+    <%= format_property(key, property_name, property, required_fields) %>
+    <%- if property['description'] && property['description'].include?("\n") -%>
+    <%= format_description(property['description']) %>
+
+    <%- end -%>
+    <%- end -%>
+    <%- else -%>
+    pass
+    <%- end -%>
+<%- if index < @schemas.length - 1 -%>
+
+
+<%- end -%>
+<%- end -%>

python/.gitignore

@@ -0,0 +1,55 @@
+*.rej
+*.py[cod]
+/.env
+*.orig
+**/__pycache__
+
+# C extensions
+*.so
+
+# Packages
+*.egg
+*.egg-info
+dist
+build
+_build
+eggs
+parts
+bin
+var
+sdist
+develop-eggs
+.installed.cfg
+lib
+lib64
+
+# Installer logs
+pip-log.txt
+
+# Unit test / coverage reports
+.coverage
+.tox
+nosetests.xml
+
+# Translations
+*.mo
+
+# Mr Developer
+.mr.developer.cfg
+.project
+.pydevproject
+.pytest_cache
+.ropeproject
+
+# Sublime
+/*.sublime-*
+
+#PyCharm
+/.idea
+
+# virtualenv
+/.Python
+/lib
+/include
+/share
+/local