Refactoring the code checker functionality

code_utils/README.md

@@ -23,8 +23,8 @@ uv sync --extra dev
 # Run the code extractor
 uv run code-util extract
 
-# Run compiler checks on extracted code
-uv run code-util check
+# Run compiler checks on extracted code, (can only be done on lang at a time)
+uv run code-util check -l programming-language
 
 # Get help in the cli
 uv run code-util --help
@@ -34,14 +34,21 @@ uv run code-util --help
 ## Structure
 
 - `main.py` - Entrypoint for the CLI. 
-- `code_finder.py` - CodeFinder class
-- `code_checker.py` - CodeChecker class.
-- `docker/` - docker files are different scripts and config the container uses.
+- `code_finder/` - module for code relating to the CodeFinder class a.k.a the functionality to scan through markdown documents.
+- `code_checker/` - module for code relating to the CodeChecker class a.k.a the functionality to build containers and run commands in them.
+- `code_checker/docker/` - docker files, scripts and config that the containers use.
 - `temp/` - Generated code snippets (gitignored).
 - `files_with_code.txt` - List of files containing code (gitignored).
 
 ## Dependancies
 
-- [Click](https://click.palletsprojects.com/en/stable/) - Framework for building CLIs
+- [Click](https://click.palletsprojects.com/en/stable/) - Framework for building CLIs.
 - [Docker SDK For Python](https://docker-py.readthedocs.io/en/stable/) - Library for interacting with the Docker API. 
+- [Pytest](https://docs.pytest.org/en/stable/index.html) - Python Unit testing Framework.
+- [Pyfakefs](https://pytest-pyfakefs.readthedocs.io/en/latest/) - Python utility for faking a filesystem during testing.
+
+## Notes
+
+ - Hard coded to only deal with python, javascript(typescript) and C#
+ - Javascript container uses a private npm package. Please set PAT_TOKEN and CODAT_EMAIL env vars in order to build.
 

code_utils/code_checker/__init__.py

@@ -0,0 +1,7 @@
+"""Code checker package for validating code snippets from Codat documentation."""
+
+from .code_checker import CodeChecker
+from .docker_operator import DockerOperator
+from .codat_code_checker_config_models import CodeCheckerConfig, LanguageDockerConfig, DEFAULT_CONFIG
+
+__all__ = ['CodeChecker', 'DockerOperator', 'CodeCheckerConfig', 'LanguageDockerConfig', 'DEFAULT_CONFIG']

code_utils/code_checker/codat_code_checker_config_models.py

@@ -0,0 +1,58 @@
+from dataclasses import dataclass
+from typing import Dict
+from pathlib import Path
+
+
+@dataclass
+class LanguageDockerConfig:
+    """Configuration for a specific programming language's Docker setup."""
+    docker_directory: str
+    validation_command: str
+    working_directory: str = ""
+
+    def get_docker_path(self, base_dir: Path) -> Path:
+        """Get the full path to the Docker directory for this language."""
+        return base_dir / self.docker_directory
+
+
+@dataclass 
+class CodeCheckerConfig:
+    """Complete configuration for the CodeChecker Docker utility."""
+    python: LanguageDockerConfig
+    javascript: LanguageDockerConfig
+    csharp: LanguageDockerConfig
+    container_name: str = "code-snippets:latest"
+
+    def get_language_config(self, language: str) -> LanguageDockerConfig:
+        """Get Docker configuration for a specific language."""
+        language_map = {
+            'python': self.python,
+            'javascript': self.javascript, 
+            'csharp': self.csharp
+        }
+        return language_map.get(language.lower())
+
+    def get_all_languages(self) -> list[str]:
+        """Get list of all supported language names."""
+        return ['python', 'javascript', 'csharp']
+
+
+# Default configuration instance based on current CodeChecker implementation
+DEFAULT_CONFIG = CodeCheckerConfig(
+    python=LanguageDockerConfig(
+        docker_directory="docker/python",
+        validation_command="bash -c 'cd snippets && pyright .'",
+        working_directory="python/snippets"
+    ),
+    javascript=LanguageDockerConfig(
+        docker_directory="docker/javascript", 
+        validation_command="tsc --noEmit",
+        working_directory="javascript"
+    ),
+    csharp=LanguageDockerConfig(
+        docker_directory="docker/csharp",
+        validation_command="bash -c 'cd /workspace/code-snippets/csharp && ./validate-csharp-snippets.sh'",
+        working_directory="/workspace/code-snippets/csharp"
+    ),
+    container_name="code-snippets"
+)

code_utils/code_checker/code_checker.py

@@ -0,0 +1,128 @@
+"""
+Code Checker for validating code snippets for a specified programming language.
+This module builds and runs a Docker container to validate complete code snippets.
+"""
+
+import sys
+from pathlib import Path
+from typing import Dict, Optional
+
+from .codat_code_checker_config_models import CodeCheckerConfig, DEFAULT_CONFIG
+from .docker_operator import DockerOperator
+
+
+class CodeChecker:
+    """
+    A class for validating code snippets by building and running validation commands
+    in a Docker container for a specified programming language environment.
+    """
+
+    def __init__(self, target_language: str, config: Optional[CodeCheckerConfig] = None, base_dir: Optional[Path] = None, docker_operator: Optional[DockerOperator] = None):
+        """
+        Initialize the CodeChecker with dependency injection.
+
+        Args:
+            target_language: Specific language to check (required).
+            config: Configuration object for Docker settings. Defaults to DEFAULT_CONFIG.
+            base_dir: Base directory path. Defaults to the directory containing this file.
+            docker_operator: DockerOperator instance. If None, creates DockerOperator(config, base_dir).
+        """
+        self.config = config or DEFAULT_CONFIG
+        self.base_dir = base_dir or Path(__file__).parent
+        self.docker_wrapper = docker_operator or DockerOperator(self.config, self.base_dir)
+        self.target_language = target_language.lower()
+
+    def _build_docker_images(self) -> Dict[str, Dict[str, any]]:
+        """
+        Build Docker image for the target language.
+
+        Returns:
+            Dictionary with build results for the target language
+        """
+        build_results = {}
+
+        print(f"🔨 Building Docker images for: {self.target_language}...")
+        print("=" * 60)
+
+        success, message = self.docker_wrapper.build_language_image(self.target_language)
+        build_results[self.target_language] = {
+            'success': success,
+            'message': message
+        }
+
+        if not success:
+            print(f"❌ Failed to build {self.target_language} image: {message}")
+
+        print("=" * 60)
+
+        return build_results
+
+    def _validate_language_snippets(self, language: str) -> Dict[str, any]:
+        """
+        Validate code snippets for a specific language using the DockerOperator.
+
+        Args:
+            language: The programming language to validate
+
+        Returns:
+            Dictionary with validation results
+        """
+        success, output = self.docker_wrapper.validate_language_snippets(language)
+        return {
+            'success': success,
+            'output': output
+        }
+
+    def check_complete_snippets(self) -> Dict[str, Dict[str, any]]:
+        """
+        Build Docker image and validate complete code snippets for the target language.
+
+        Returns:
+            Dictionary with validation results for the target language:
+            {
+                'build': {language: {'success': bool, 'message': str}},
+                'validation': {language: {'success': bool, 'output': str}}
+            }
+        """
+        print(f"🚀 Starting code snippet validation for: {self.target_language}...")
+        print("=" * 60)
+
+        # Step 1: Build Docker images for target languages
+        build_results = self._build_docker_images()
+
+        # Check if all builds succeeded
+        all_builds_successful = all(result['success'] for result in build_results.values())
+
+        if not all_builds_successful:
+            failed_builds = [lang for lang, result in build_results.items() if not result['success']]
+            print(f"❌ Docker build failed for: {', '.join(failed_builds)}")
+            return {
+                'build': build_results,
+                'validation': {}
+            }
+
+        print("=" * 60)
+
+        # Step 2: Validate snippets for target languages
+        validation_results = {}
+
+        validation_results[self.target_language] = self._validate_language_snippets(self.target_language)
+
+        # Summary
+        print("=" * 60)
+        print("📊 Validation Summary:")
+
+        validation_result = validation_results[self.target_language]
+
+        if validation_result['success']:
+            print(f"🎉 {self.target_language.title()} validation passed!")
+        else:
+            print(f"❌ {self.target_language.title()} validation failed!")
+
+        return {
+            'build': build_results,
+            'validation': validation_results
+        }
+
+
+

code_utils/code_checker/docker/.dockerignore

@@ -0,0 +1,64 @@
+# Exclude unnecessary files from Docker build context
+**/__pycache__/
+**/*.pyc
+**/*.pyo
+**/*.pyd
+**/.Python
+**/env/
+**/venv/
+**/.venv/
+**/pip-log.txt
+**/pip-delete-this-directory.txt
+
+# Node modules and TypeScript compilation outputs
+**/node_modules/
+**/npm-debug.log*
+**/yarn-debug.log*
+**/yarn-error.log*
+**/.npm
+**/.yarn-integrity
+**/dist/
+**/build/
+
+# .NET build outputs
+**/bin/
+**/obj/
+**/*.user
+**/*.suo
+**/*.cache
+**/packages/
+
+# Version control
+**/.git/
+**/.gitignore
+**/.gitattributes
+
+# IDE and editor files
+**/.vscode/
+**/.idea/
+**/*.swp
+**/*.swo
+*~
+
+# OS generated files
+**/.DS_Store
+**/.DS_Store?
+**/._*
+**/.Spotlight-V100
+**/.Trashes
+**/ehthumbs.db
+**/Thumbs.db
+
+# Documentation and temp files
+**/temp/incomplete/
+**/*.md
+**/*.txt
+**/output.txt
+**/link-results.json
+
+# Only include the complete code snippets and dependency files
+!temp/*/complete/
+!docker/requirements.txt
+!docker/package.json
+!docker/tsconfig.json
+!docker/CodatSnippets.csproj

code_utils/code_checker/docker/csharp/CodatSnippets.csproj

@@ -0,0 +1,21 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <TargetFramework>net8.0</TargetFramework>
+    <OutputType>Exe</OutputType>
+    <ImplicitUsings>enable</ImplicitUsings>
+    <Nullable>enable</Nullable>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <PackageReference Include="Codat.Platform" Version="*" />
+    <PackageReference Include="Codat.BankFeeds" Version="*" />
+    <PackageReference Include="Codat.Lending" Version="*" />
+    <PackageReference Include="Codat.Sync.Commerce" Version="*" />
+    <PackageReference Include="Codat.Sync.Expenses" Version="*" />
+    <PackageReference Include="Codat.Sync.Payables" Version="*" />
+    <PackageReference Include="Codat.Sync.Payroll" Version="*" />
+    <PackageReference Include="Newtonsoft.Json" Version="13.0.3" />
+  </ItemGroup>
+
+</Project>

code_utils/code_checker/docker/csharp/Dockerfile

@@ -0,0 +1,59 @@
+# C#/.NET-specific Dockerfile for Codat code snippets validation
+FROM ubuntu:22.04
+
+# Set environment variables
+ENV DEBIAN_FRONTEND=noninteractive
+ENV DOTNET_CLI_TELEMETRY_OPTOUT=1
+ENV DOTNET_SKIP_FIRST_TIME_EXPERIENCE=1
+
+# Update package list and install common dependencies
+RUN apt-get update && apt-get install -y \
+    curl \
+    wget \
+    apt-transport-https \
+    software-properties-common \
+    gnupg \
+    lsb-release \
+    ca-certificates \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install .NET 8.0 SDK
+RUN wget https://packages.microsoft.com/config/ubuntu/22.04/packages-microsoft-prod.deb -O packages-microsoft-prod.deb \
+    && dpkg -i packages-microsoft-prod.deb \
+    && rm packages-microsoft-prod.deb \
+    && apt-get update \
+    && apt-get install -y dotnet-sdk-8.0 \
+    && rm -rf /var/lib/apt/lists/*
+
+# Create workspace directory
+WORKDIR /workspace/code-snippets/csharp
+
+# Copy C# project file and restore packages
+COPY code_checker/docker/csharp/CodatSnippets.csproj ./CodatSnippets.csproj
+RUN dotnet restore
+
+# Create directory for code snippets and copy them from temp directory
+RUN mkdir -p ./snippets/
+
+# Copy C# code snippets from temp directory (similar to other languages)
+COPY temp/csharp/complete/ ./snippets/
+
+# Copy C# validation script and fix line endings
+COPY code_checker/docker/csharp/validate-csharp-snippets.sh ./validate-csharp-snippets.sh
+RUN sed -i 's/\r$//' validate-csharp-snippets.sh && chmod +x validate-csharp-snippets.sh
+
+# Verify .NET installation and show packages
+RUN echo "=== C#/.NET Environment Information ===" && \
+    echo ".NET version:" && dotnet --version && \
+    echo "" && \
+    echo "=== C# Codat Packages ===" && \
+    dotnet list package | grep -i codat || echo "Codat packages will be available after restore" && \
+    echo "" && \
+    echo "=== C# Snippets Count ===" && \
+    find ./snippets -name "*.cs" 2>/dev/null | wc -l | xargs echo "C# snippets found:" || echo "No snippets directory found yet"
+
+# Set working directory
+WORKDIR /workspace/code-snippets/csharp
+
+# Default command
+CMD ["/bin/bash"]