data-contract-validator 1.0.3__tar.gz → 1.0.4a0__tar.gz

{data_contract_validator-1.0.3/data_contract_validator.egg-info → data_contract_validator-1.0.4a0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data-contract-validator
-Version: 1.0.3
+Version: 1.0.4a0
 Summary: Adding pre-commit-fixes
 Author-email: Ogunniran Siji <ogunniransiji@gmail.com>
 Maintainer-email: Ogunniran Siji <ogunniransiji@gmail.com>

{data_contract_validator-1.0.3 → data_contract_validator-1.0.4a0}/data_contract_validator/cli.py

@@ -71,7 +71,7 @@ def init(interactive: bool, framework: str, dbt_path: str, output_dir: str):
 
 
 def _interactive_setup() -> Dict[str, Any]:
-    """Interactive setup wizard - 3 simple questions."""
+    """Interactive setup wizard with directory support."""
     click.echo("📋 Quick Setup (3 questions):")
     click.echo()
 
@@ -100,63 +100,100 @@ def _interactive_setup() -> Dict[str, Any]:
         show_default=True,
     )
 
-    # Question 3: API models location
+    # Question 3: API models location with directory support
     click.echo()
     if framework == "fastapi":
-        default_path = "app/models.py"
-        prompt_text = "3️⃣  Where are your Pydantic models?"
+        default_path = "app/models"  # Default to directory
+        prompt_text = "3️⃣  Where are your Pydantic models? (file or directory)"
+        help_text = (
+            "   💡 Examples: 'app/models.py' (single file) or 'app/models' (directory)"
+        )
     elif framework == "django":
         default_path = "models.py"
         prompt_text = "3️⃣  Where are your Django models?"
+        help_text = "   💡 Examples: 'myapp/models.py' or 'models'"
     else:
-        default_path = "models.py"
+        default_path = "models"
         prompt_text = "3️⃣  Where are your API models?"
+        help_text = "   💡 Can be a file (models.py) or directory (models/)"
 
+    click.echo(help_text)
     api_location = click.prompt(prompt_text, default=default_path, show_default=True)
 
-    # Auto-detect if it's local file or GitHub repo
+    # Auto-detect if it's local file/directory or GitHub repo
     is_github_repo = "/" in api_location and not api_location.startswith((".", "/"))
 
     if is_github_repo:
-        # Format: "org/repo" or "org/repo/path/to/file.py"
+        # Format: "org/repo" or "org/repo/path/to/models"
         parts = api_location.split("/")
         if len(parts) >= 2:
             repo = "/".join(parts[:2])
-            path = "/".join(parts[2:]) if len(parts) > 2 else "models.py"
+            path = "/".join(parts[2:]) if len(parts) > 2 else "app/models"
         else:
             repo = api_location
-            path = "models.py"
+            path = "app/models"
 
         api_config = {"type": "github", "repo": repo, "path": path}
         click.echo(f"   🐙 GitHub repo detected: {repo}/{path}")
     else:
         api_config = {"type": "local", "path": api_location}
 
-        # Check if local file exists
-        if Path(api_location).exists():
-            click.echo("   ✅ Local file found")
+        # Check if local file/directory exists and provide feedback
+        local_path = Path(api_location)
+        if local_path.exists():
+            if local_path.is_file():
+                click.echo(f"   ✅ Local file found: {api_location}")
+            elif local_path.is_dir():
+                # Count Python files in directory
+                py_files = list(local_path.rglob("*.py"))
+                py_files = [
+                    f
+                    for f in py_files
+                    if not f.name.startswith("test_") and f.name != "__init__.py"
+                ]
+                click.echo(
+                    f"   ✅ Local directory found: {api_location} ({len(py_files)} Python files)"
+                )
+            else:
+                click.echo(
+                    f"   ⚠️  Path exists but is neither file nor directory: {api_location}"
+                )
         else:
-            click.echo(f"   ⚠️  File not found: {api_location}")
+            click.echo(f"   ⚠️  Path not found: {api_location}")
             if not click.confirm("   Continue anyway?"):
                 sys.exit(1)
 
+            # New question about manifest parsing
+    click.echo()
+    disable_manifest = click.confirm(
+        "4️⃣  Disable manifest.json parsing? (recommended if you have CTE-based models)",
+        default=True
+    )
+    
+    if disable_manifest:
+        click.echo("   📄 Will use SQL file parsing (better for complex models)")
+    else:
+        click.echo("   📋 Will try manifest.json first, fallback to SQL parsing")
+
     return {
         "version": "1.0",
         "name": f"contracts-{Path.cwd().name}",
-        "description": "Auto-generated data contract validation",
         "source": {
-            "dbt": {"project_path": dbt_path, "auto_compile": True, "timeout": 120}
+            "dbt": {
+                "project_path": dbt_path, 
+                "auto_compile": True, 
+                "disable_manifest": disable_manifest  # NEW
+            }
         },
         "target": {framework: api_config},
         "validation": {
             "fail_on": ["missing_tables", "missing_required_columns"],
-            "warn_on": ["type_mismatches", "missing_optional_columns"],
-            "mode": "strict",
+            "warn_on": ["type_mismatches"]
         },
-        "output": {"format": "terminal", "show_suggestions": True, "max_issues": 20},
     }
 
 
+
 def _quick_setup(framework: str, dbt_path: str) -> Dict[str, Any]:
     """Quick non-interactive setup with smart defaults."""
 
@@ -454,17 +491,27 @@ def _test_setup(config_file: Path) -> bool:
     "--output", type=click.Choice(["terminal", "json", "github"]), default="terminal"
 )
 @click.option("--dbt-project", help="Override DBT project path")
-@click.option("--fastapi-local", help="Override FastAPI models path")
+@click.option(
+    "--fastapi-local", help="Override FastAPI models path (file or directory)"
+)
+@click.option("--fastapi-directory", help="Override FastAPI models directory path")
 @click.option("--fastapi-repo", help="Override FastAPI repo (org/repo)")
-@click.option("--fastapi-path", default="app/models.py", help="Path in FastAPI repo")
+@click.option(
+    "--fastapi-path",
+    default="app/models",
+    help="Path in FastAPI repo (file or directory)",
+)
+@click.option("--disable-manifest", is_flag=True, help="Force SQL parsing, ignore manifest.json")
 def validate(
     config: str,
     dry_run: bool,
     output: str,
     dbt_project: str,
     fastapi_local: str,
+    fastapi_directory: str,
     fastapi_repo: str,
     fastapi_path: str,
+    disable_manifest: bool, 
 ):
     """🔍 Validate data contracts (prevents production breaks)."""
 
@@ -486,12 +533,20 @@ def validate(
 
     if dry_run:
         click.echo("🧪 Dry run - testing configuration only")
-        _test_configuration(config_data, dbt_project, fastapi_local, fastapi_repo)
+        _test_configuration(
+            config_data, dbt_project, fastapi_local, fastapi_directory, fastapi_repo, disable_manifest 
+        )
         return
 
     # Run actual validation
     _run_validation(
-        config_data, output, dbt_project, fastapi_local, fastapi_repo, fastapi_path
+        config_data,
+        output,
+        dbt_project,
+        fastapi_local,
+        fastapi_directory,
+        fastapi_repo,
+        fastapi_path,
     )
 
 
@@ -530,27 +585,64 @@ def _run_validation(
     fastapi_local: str,
     fastapi_repo: str,
     fastapi_path: str,
+    disable_manifest: bool = False,
 ):
-    """Run the actual validation."""
+    """Run the actual validation with manifest disable option."""
 
     # Get DBT project path
     dbt_path = dbt_project or config_data.get("source", {}).get("dbt", {}).get(
         "project_path", "."
     )
 
-    # Initialize DBT extractor
+    # Get disable_manifest from config file OR command line flag
+    config_disable_manifest = config_data.get("source", {}).get("dbt", {}).get("disable_manifest", False)
+    use_disable_manifest = disable_manifest or config_disable_manifest  # CLI flag takes precedence
+
+    if use_disable_manifest:
+        click.echo("📄 Manifest parsing disabled")
+        if disable_manifest:
+            click.echo("   (via --disable-manifest flag)")
+        else:
+            click.echo("   (via .retl-validator.yml config)")
+
+    # Initialize DBT extractor with disable_manifest option
     try:
-        dbt_extractor = DBTExtractor(dbt_path)
+        dbt_extractor = DBTExtractor(dbt_path, disable_manifest=use_disable_manifest)
     except Exception as e:
         click.echo(f"❌ Error initializing DBT extractor: {e}")
         sys.exit(1)
 
-    # Initialize FastAPI extractor
+    # Initialize FastAPI extractor with directory support
     try:
         if fastapi_local:
-            fastapi_extractor = FastAPIExtractor.from_local_file(fastapi_local)
+            # Use local path (file or directory)
+            local_path = fastapi_local
+
+            # Auto-detect if it's a file or directory
+            path = Path(local_path)
+            if path.is_file():
+                click.echo(f"📄 Using FastAPI models file: {local_path}")
+                fastapi_extractor = FastAPIExtractor.from_local_file(local_path)
+            elif path.is_dir():
+                click.echo(f"📁 Using FastAPI models directory: {local_path}")
+                fastapi_extractor = FastAPIExtractor.from_local_directory(local_path)
+            else:
+                raise ValueError(f"Path does not exist: {local_path}")
+
         elif fastapi_repo:
+            # Use GitHub repository
             github_token = os.environ.get("GITHUB_TOKEN")
+
+            # Check if fastapi_path ends with .py (file) or not (directory)
+            if fastapi_path.endswith(".py"):
+                click.echo(
+                    f"📄 Using FastAPI models file: {fastapi_repo}/{fastapi_path}"
+                )
+            else:
+                click.echo(
+                    f"📁 Using FastAPI models directory: {fastapi_repo}/{fastapi_path}"
+                )
+
             fastapi_extractor = FastAPIExtractor.from_github_repo(
                 repo=fastapi_repo, path=fastapi_path, token=github_token
             )
@@ -558,14 +650,23 @@ def _run_validation(
             # Get from config
             target_config = list(config_data.get("target", {}).values())[0]
             if target_config.get("type") == "local":
-                fastapi_extractor = FastAPIExtractor.from_local_file(
-                    target_config.get("path")
-                )
+                local_path = target_config.get("path")
+                path = Path(local_path)
+
+                if path.is_file():
+                    fastapi_extractor = FastAPIExtractor.from_local_file(local_path)
+                elif path.is_dir():
+                    fastapi_extractor = FastAPIExtractor.from_local_directory(
+                        local_path
+                    )
+                else:
+                    raise ValueError(f"Path does not exist: {local_path}")
+
             elif target_config.get("type") == "github":
                 github_token = os.environ.get("GITHUB_TOKEN")
                 fastapi_extractor = FastAPIExtractor.from_github_repo(
                     repo=target_config.get("repo"),
-                    path=target_config.get("path", "app/models.py"),
+                    path=target_config.get("path", "app/models"),
                     token=github_token,
                 )
             else:

{data_contract_validator-1.0.3 → data_contract_validator-1.0.4a0}/data_contract_validator/extractors/dbt.py

@@ -1,6 +1,6 @@
 # data_contract_validator/extractors/dbt.py
 """
-DBT schema extractor - simplified version of your working code.
+DBT schema extractor
 """
 
 import json
@@ -16,11 +16,12 @@ from ..core.models import Schema
 class DBTExtractor(BaseExtractor):
     """Extract schemas from DBT projects."""
 
-    def __init__(self, project_path: str = "."):
+    def __init__(self, project_path: str = ".", disable_manifest: bool = False):
         self.project_path = Path(project_path)
         self.target_dir = self.project_path / "target"
         self.manifest_path = self.target_dir / "manifest.json"
         self.models_path = self.project_path / "models"
+        self.disable_manifest = disable_manifest
 
     def extract_schemas(self) -> Dict[str, Schema]:
         """Extract schemas from DBT project."""

data_contract_validator-1.0.4a0/data_contract_validator/extractors/fastapi.py

@@ -0,0 +1,439 @@
+# data_contract_validator/extractors/fastapi.py
+"""
+Enhanced FastAPI/Pydantic schema extractor with directory support
+"""
+
+import ast
+import re
+import requests
+import os
+from pathlib import Path
+from typing import Dict, List, Any, Optional, Union, get_type_hints
+
+from .base import BaseExtractor
+from ..core.models import Schema
+
+
+class FastAPIExtractor(BaseExtractor):
+    """Extract schemas from FastAPI/Pydantic models - supports files and directories."""
+
+    def __init__(
+        self, content: str = None, source: str = "unknown", file_path: str = None
+    ):
+        self.content = content
+        self.source = source
+        self.file_path = file_path
+        self.all_files_content = {}  # For directory mode
+
+    @classmethod
+    def from_local_file(cls, file_path: str) -> "FastAPIExtractor":
+        """Create extractor from local file."""
+        file_path = Path(file_path)
+
+        if not file_path.exists():
+            raise ValueError(f"Path does not exist: {file_path}")
+
+        if file_path.is_file():
+            # Single file mode (existing behavior)
+            with open(file_path, "r", encoding="utf-8") as f:
+                content = f.read()
+            return cls(
+                content=content, source=f"local:{file_path}", file_path=str(file_path)
+            )
+
+        elif file_path.is_dir():
+            # Directory mode (new functionality)
+            return cls._from_local_directory(file_path)
+
+        else:
+            raise ValueError(f"Path is neither file nor directory: {file_path}")
+
+    @classmethod
+    def from_local_directory(cls, directory_path: str) -> "FastAPIExtractor":
+        """Create extractor from local directory containing model files."""
+        return cls._from_local_directory(Path(directory_path))
+
+    @classmethod
+    def _from_local_directory(cls, dir_path: Path) -> "FastAPIExtractor":
+        """Internal method to handle directory extraction."""
+        if not dir_path.is_dir():
+            raise ValueError(f"Not a directory: {dir_path}")
+
+        # Find all Python files in the directory and subdirectories
+        python_files = list(dir_path.rglob("*.py"))
+
+        if not python_files:
+            raise ValueError(f"No Python files found in directory: {dir_path}")
+
+        print(f"🔍 Found {len(python_files)} Python files in {dir_path}")
+
+        # Read all files
+        all_files_content = {}
+        for py_file in python_files:
+            # Skip common non-model files
+            if py_file.name in [
+                "__init__.py",
+                "test_",
+                "tests.py",
+            ] or py_file.name.startswith("test_"):
+                continue
+
+            try:
+                with open(py_file, "r", encoding="utf-8") as f:
+                    content = f.read()
+                    relative_path = py_file.relative_to(dir_path)
+                    all_files_content[str(relative_path)] = content
+                    print(f"   📄 Loaded: {relative_path}")
+            except Exception as e:
+                print(f"   ⚠️  Could not read {py_file}: {e}")
+
+        if not all_files_content:
+            raise ValueError(f"Could not read any Python files from: {dir_path}")
+
+        # Create extractor instance for directory mode
+        extractor = cls(source=f"local_directory:{dir_path}")
+        extractor.all_files_content = all_files_content
+        return extractor
+
+    @classmethod
+    def from_github_repo(
+        cls, repo: str, path: str, token: str = None
+    ) -> "FastAPIExtractor":
+        """Create extractor from GitHub repository - supports files and directories."""
+
+        # First, check if it's a file or directory
+        if path.endswith(".py"):
+            # Single file
+            content = cls._fetch_github_file(repo, path, token)
+            if not content:
+                raise ValueError(f"Could not fetch {repo}/{path} from GitHub")
+            return cls(content, source=f"github:{repo}/{path}")
+        else:
+            # Assume it's a directory
+            return cls._from_github_directory(repo, path, token)
+
+    @classmethod
+    def _from_github_directory(
+        cls, repo: str, dir_path: str, token: str = None
+    ) -> "FastAPIExtractor":
+        """Fetch all Python files from a GitHub directory."""
+
+        # Get directory contents from GitHub API
+        url = f"https://api.github.com/repos/{repo}/contents/{dir_path}"
+        headers = {}
+
+        if token:
+            headers["Authorization"] = f"token {token}"
+
+        try:
+            response = requests.get(url, headers=headers)
+            if response.status_code != 200:
+                raise ValueError(
+                    f"Could not fetch directory {repo}/{dir_path}: {response.status_code}"
+                )
+
+            contents = response.json()
+            if not isinstance(contents, list):
+                raise ValueError(f"Path {dir_path} is not a directory")
+
+            all_files_content = {}
+
+            for item in contents:
+                if item["type"] == "file" and item["name"].endswith(".py"):
+                    # Skip common non-model files
+                    if item["name"] in ["__init__.py"] or item["name"].startswith(
+                        "test_"
+                    ):
+                        continue
+
+                    file_content = cls._fetch_github_file(repo, item["path"], token)
+                    if file_content:
+                        all_files_content[item["name"]] = file_content
+                        print(f"   📄 Downloaded: {item['name']}")
+
+                elif item["type"] == "dir":
+                    # Recursively fetch subdirectories
+                    try:
+                        subdir_files = cls._fetch_github_directory_recursive(
+                            repo, item["path"], token
+                        )
+                        for sub_path, sub_content in subdir_files.items():
+                            all_files_content[f"{item['name']}/{sub_path}"] = (
+                                sub_content
+                            )
+                    except Exception as e:
+                        print(f"   ⚠️  Could not fetch subdirectory {item['name']}: {e}")
+
+            if not all_files_content:
+                raise ValueError(f"No Python model files found in {repo}/{dir_path}")
+
+            print(
+                f"   ✅ Downloaded {len(all_files_content)} files from {repo}/{dir_path}"
+            )
+
+            extractor = cls(source=f"github_directory:{repo}/{dir_path}")
+            extractor.all_files_content = all_files_content
+            return extractor
+
+        except Exception as e:
+            raise ValueError(f"Error fetching GitHub directory {repo}/{dir_path}: {e}")
+
+    @classmethod
+    def _fetch_github_directory_recursive(
+        cls, repo: str, dir_path: str, token: str = None
+    ) -> Dict[str, str]:
+        """Recursively fetch Python files from GitHub directory."""
+        url = f"https://api.github.com/repos/{repo}/contents/{dir_path}"
+        headers = {}
+
+        if token:
+            headers["Authorization"] = f"token {token}"
+
+        files_content = {}
+
+        try:
+            response = requests.get(url, headers=headers)
+            if response.status_code == 200:
+                contents = response.json()
+
+                for item in contents:
+                    if item["type"] == "file" and item["name"].endswith(".py"):
+                        if (
+                            not item["name"].startswith("test_")
+                            and item["name"] != "__init__.py"
+                        ):
+                            file_content = cls._fetch_github_file(
+                                repo, item["path"], token
+                            )
+                            if file_content:
+                                files_content[item["name"]] = file_content
+
+                    elif item["type"] == "dir":
+                        # Recursive call for subdirectories
+                        subdir_files = cls._fetch_github_directory_recursive(
+                            repo, item["path"], token
+                        )
+                        for sub_path, sub_content in subdir_files.items():
+                            files_content[f"{item['name']}/{sub_path}"] = sub_content
+
+        except Exception as e:
+            print(f"   ⚠️  Error fetching subdirectory {dir_path}: {e}")
+
+        return files_content
+
+    @staticmethod
+    def _fetch_github_file(repo: str, path: str, token: str = None) -> Optional[str]:
+        """Fetch file content from GitHub API."""
+        url = f"https://api.github.com/repos/{repo}/contents/{path}"
+        headers = {}
+
+        if token:
+            headers["Authorization"] = f"token {token}"
+
+        try:
+            response = requests.get(url, headers=headers)
+            if response.status_code == 200:
+                import base64
+
+                content = base64.b64decode(response.json()["content"]).decode("utf-8")
+                return content
+            else:
+                print(f"   ❌ GitHub API error for {path}: {response.status_code}")
+                return None
+        except Exception as e:
+            print(f"   ❌ Error fetching {path} from GitHub: {e}")
+            return None
+
+    def extract_schemas(self) -> Dict[str, Schema]:
+        """Extract schemas from FastAPI/Pydantic models."""
+
+        if self.all_files_content:
+            # Directory mode - extract from multiple files
+            return self._extract_schemas_from_directory()
+        else:
+            # Single file mode - existing behavior
+            return self._extract_schemas_from_single_file()
+
+    def _extract_schemas_from_single_file(self) -> Dict[str, Schema]:
+        """Extract schemas from a single file (existing behavior)."""
+        print(f"🔍 Extracting FastAPI schemas from {self.source}")
+
+        try:
+            schemas = self._parse_pydantic_models(self.content)
+            print(f"   ✅ Found {len(schemas)} models")
+            return schemas
+        except Exception as e:
+            print(f"   ❌ Error parsing models: {e}")
+            return {}
+
+    def _extract_schemas_from_directory(self) -> Dict[str, Schema]:
+        """Extract schemas from multiple files in a directory."""
+        print(f"🔍 Extracting FastAPI schemas from directory {self.source}")
+
+        all_schemas = {}
+        total_models = 0
+
+        for file_path, file_content in self.all_files_content.items():
+            try:
+                print(f"   📄 Processing: {file_path}")
+                file_schemas = self._parse_pydantic_models(
+                    file_content, file_source=file_path
+                )
+
+                # Check for duplicate model names across files
+                for schema_name, schema in file_schemas.items():
+                    if schema_name in all_schemas:
+                        print(
+                            f"   ⚠️  Duplicate model name '{schema_name}' found in {file_path}"
+                        )
+                        print(f"       Previous: {all_schemas[schema_name].source}")
+                        print(f"       Current:  {schema.source}")
+                        # Use a unique name by including file path
+                        unique_name = f"{schema_name}_{file_path.replace('/', '_').replace('.py', '')}"
+                        all_schemas[unique_name] = schema
+                        print(f"       Renamed to: {unique_name}")
+                    else:
+                        all_schemas[schema_name] = schema
+
+                if file_schemas:
+                    print(f"       ✅ Found {len(file_schemas)} models")
+                    total_models += len(file_schemas)
+                else:
+                    print(f"       ⚪ No Pydantic models found")
+
+            except Exception as e:
+                print(f"   ❌ Error parsing {file_path}: {e}")
+
+        print(
+            f"   ✅ Total: {total_models} models from {len(self.all_files_content)} files"
+        )
+        return all_schemas
+
+    def _parse_pydantic_models(
+        self, content: str, file_source: str = None
+    ) -> Dict[str, Schema]:
+        """Parse Pydantic models from Python code."""
+        try:
+            tree = ast.parse(content)
+            schemas = {}
+
+            for node in ast.walk(tree):
+                if isinstance(node, ast.ClassDef):
+                    # Check if it's a Pydantic model
+                    if self._is_pydantic_model(node):
+                        schema = self._analyze_pydantic_class(node, file_source)
+                        if schema:
+                            table_name = schema.name
+                            schemas[table_name] = schema
+
+            return schemas
+
+        except Exception as e:
+            print(f"   ❌ Error parsing Python code: {e}")
+            return {}
+
+    def _is_pydantic_model(self, node: ast.ClassDef) -> bool:
+        """Check if class inherits from BaseModel or SQLModel."""
+        for base in node.bases:
+            if isinstance(base, ast.Name) and base.id in ["BaseModel", "SQLModel"]:
+                return True
+            elif isinstance(base, ast.Attribute) and base.attr in [
+                "BaseModel",
+                "SQLModel",
+            ]:
+                return True
+        return False
+
+    def _analyze_pydantic_class(
+        self, node: ast.ClassDef, file_source: str = None
+    ) -> Optional[Schema]:
+        """Analyze a Pydantic class to extract schema."""
+        # Convert class name to table name
+        table_name = self._class_to_table_name(node.name)
+
+        # Skip SQLModel tables (database models, not API models)
+        if self._is_sqlmodel_table(node):
+            return None
+
+        columns = []
+
+        # Parse type annotations
+        for item in node.body:
+            if isinstance(item, ast.AnnAssign) and isinstance(item.target, ast.Name):
+                field_name = item.target.id
+                field_type = self._parse_type_annotation(item.annotation)
+                is_required = not self._is_optional_type(item.annotation)
+
+                columns.append(
+                    {
+                        "name": field_name,
+                        "type": self._python_to_sql_type(field_type),
+                        "required": is_required,
+                        "nullable": not is_required,
+                    }
+                )
+
+        if not columns:
+            return None
+
+        # Create source identifier
+        if file_source:
+            source = f"pydantic:{node.name}@{file_source}"
+        else:
+            source = f"pydantic:{node.name}"
+
+        return Schema(name=table_name, columns=columns, source=source)
+
+    def _is_sqlmodel_table(self, node: ast.ClassDef) -> bool:
+        """Check if this is a SQLModel table (database model, not API model)."""
+        # Look for table=True in the class definition
+        for base in node.bases:
+            if isinstance(base, ast.Call):
+                for keyword in base.keywords:
+                    if (
+                        keyword.arg == "table"
+                        and isinstance(keyword.value, ast.Constant)
+                        and keyword.value.value is True
+                    ):
+                        return True
+        return False
+
+    def _class_to_table_name(self, class_name: str) -> str:
+        """Convert CamelCase class name to snake_case table name."""
+        # Insert underscore before capital letters
+        table_name = re.sub("(.)([A-Z][a-z]+)", r"\1_\2", class_name)
+        table_name = re.sub("([a-z0-9])([A-Z])", r"\1_\2", table_name).lower()
+
+        # Remove common suffixes
+        for suffix in ["_model", "_schema", "_response", "_request"]:
+            if table_name.endswith(suffix):
+                table_name = table_name[: -len(suffix)]
+                break
+
+        return table_name
+
+    def _parse_type_annotation(self, annotation) -> str:
+        """Parse type annotation to string."""
+        if isinstance(annotation, ast.Name):
+            return annotation.id
+        elif isinstance(annotation, ast.Subscript):
+            if isinstance(annotation.value, ast.Name):
+                # Handle Optional[Type], List[Type], etc.
+                inner_type = self._parse_type_annotation(annotation.slice)
+                return f"{annotation.value.id}[{inner_type}]"
+        elif isinstance(annotation, ast.Attribute):
+            # Handle datetime.datetime, etc.
+            if hasattr(annotation.value, "id"):
+                return f"{annotation.value.id}.{annotation.attr}"
+            return annotation.attr
+
+        return "unknown"
+
+    def _is_optional_type(self, annotation) -> bool:
+        """Check if type annotation is Optional."""
+        if isinstance(annotation, ast.Subscript):
+            if isinstance(annotation.value, ast.Name):
+                # Check for Optional[Type] or Union[Type, None]
+                if annotation.value.id in ["Optional", "Union"]:
+                    return True
+        return False

{data_contract_validator-1.0.3 → data_contract_validator-1.0.4a0/data_contract_validator.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data-contract-validator
-Version: 1.0.3
+Version: 1.0.4a0
 Summary: Adding pre-commit-fixes
 Author-email: Ogunniran Siji <ogunniransiji@gmail.com>
 Maintainer-email: Ogunniran Siji <ogunniransiji@gmail.com>

{data_contract_validator-1.0.3 → data_contract_validator-1.0.4a0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "data-contract-validator"
-version = "1.0.3"
+version = "1.0.4a"
 description = "Adding pre-commit-fixes"
 readme = "README.md"
 license = {text = "MIT"}

data_contract_validator-1.0.3/data_contract_validator/extractors/fastapi.py

@@ -1,200 +0,0 @@
-# data_contract_validator/extractors/fastapi.py
-"""
-FastAPI/Pydantic schema extractor - simplified version of your working code.
-"""
-
-import ast
-import re
-import requests
-import os
-from pathlib import Path
-from typing import Dict, List, Any, Optional, Union, get_type_hints
-
-from .base import BaseExtractor
-from ..core.models import Schema
-
-
-class FastAPIExtractor(BaseExtractor):
-    """Extract schemas from FastAPI/Pydantic models."""
-
-    def __init__(self, content: str, source: str = "unknown"):
-        self.content = content
-        self.source = source
-
-    @classmethod
-    def from_local_file(cls, file_path: str) -> "FastAPIExtractor":
-        """Create extractor from local file."""
-        file_path = Path(file_path)
-        with open(file_path, "r", encoding="utf-8") as f:
-            content = f.read()
-        return cls(content, source=f"local:{file_path}")
-
-    @classmethod
-    def from_github_repo(
-        cls, repo: str, path: str, token: str = None
-    ) -> "FastAPIExtractor":
-        """Create extractor from GitHub repository."""
-        content = cls._fetch_github_file(repo, path, token)
-        if not content:
-            raise ValueError(f"Could not fetch {repo}/{path} from GitHub")
-        return cls(content, source=f"github:{repo}/{path}")
-
-    @staticmethod
-    def _fetch_github_file(repo: str, path: str, token: str = None) -> Optional[str]:
-        """Fetch file content from GitHub API."""
-        url = f"https://api.github.com/repos/{repo}/contents/{path}"
-        headers = {}
-
-        if token:
-            headers["Authorization"] = f"token {token}"
-
-        try:
-            response = requests.get(url, headers=headers)
-            if response.status_code == 200:
-                import base64
-
-                content = base64.b64decode(response.json()["content"]).decode("utf-8")
-                print(f"   ✅ Downloaded {path} from {repo}")
-                return content
-            else:
-                print(f"   ❌ GitHub API error: {response.status_code}")
-                return None
-        except Exception as e:
-            print(f"   ❌ Error fetching from GitHub: {e}")
-            return None
-
-    def extract_schemas(self) -> Dict[str, Schema]:
-        """Extract schemas from FastAPI/Pydantic models."""
-        print(f"🔍 Extracting FastAPI schemas from {self.source}")
-
-        try:
-            schemas = self._parse_pydantic_models(self.content)
-            print(f"   ✅ Found {len(schemas)} models")
-            return schemas
-        except Exception as e:
-            print(f"   ❌ Error parsing models: {e}")
-            return {}
-
-    def _parse_pydantic_models(self, content: str) -> Dict[str, Schema]:
-        """Parse Pydantic models from Python code."""
-        try:
-            tree = ast.parse(content)
-            schemas = {}
-
-            for node in ast.walk(tree):
-                if isinstance(node, ast.ClassDef):
-                    # Check if it's a Pydantic model
-                    if self._is_pydantic_model(node):
-                        schema = self._analyze_pydantic_class(node)
-                        if schema:
-                            table_name = schema.name
-                            schemas[table_name] = schema
-                            print(f"   ✅ Found model: {node.name} -> {table_name}")
-
-            return schemas
-
-        except Exception as e:
-            print(f"   ❌ Error parsing Python code: {e}")
-            return {}
-
-    def _is_pydantic_model(self, node: ast.ClassDef) -> bool:
-        """Check if class inherits from BaseModel or SQLModel."""
-        for base in node.bases:
-            if isinstance(base, ast.Name) and base.id in ["BaseModel", "SQLModel"]:
-                return True
-            elif isinstance(base, ast.Attribute) and base.attr in [
-                "BaseModel",
-                "SQLModel",
-            ]:
-                return True
-        return False
-
-    def _analyze_pydantic_class(self, node: ast.ClassDef) -> Optional[Schema]:
-        """Analyze a Pydantic class to extract schema."""
-        # Convert class name to table name
-        table_name = self._class_to_table_name(node.name)
-
-        # Skip SQLModel tables (database models, not API models)
-        if self._is_sqlmodel_table(node):
-            return None
-
-        columns = []
-
-        # Parse type annotations
-        for item in node.body:
-            if isinstance(item, ast.AnnAssign) and isinstance(item.target, ast.Name):
-                field_name = item.target.id
-                field_type = self._parse_type_annotation(item.annotation)
-                is_required = not self._is_optional_type(item.annotation)
-
-                columns.append(
-                    {
-                        "name": field_name,
-                        "type": self._python_to_sql_type(field_type),
-                        "required": is_required,
-                        "nullable": not is_required,
-                    }
-                )
-
-        if not columns:
-            return None
-
-        return Schema(name=table_name, columns=columns, source=f"pydantic:{node.name}")
-
-    def _is_sqlmodel_table(self, node: ast.ClassDef) -> bool:
-        """Check if this is a SQLModel table (database model, not API model)."""
-        # Look for table=True in the class definition
-        for base in node.bases:
-            if isinstance(base, ast.Call):
-                for keyword in base.keywords:
-                    if (
-                        keyword.arg == "table"
-                        and isinstance(keyword.value, ast.Constant)
-                        and keyword.value.value is True
-                    ):
-                        return True
-        return False
-
-    def _class_to_table_name(self, class_name: str) -> str:
-        """Convert CamelCase class name to snake_case table name."""
-        # Insert underscore before capital letters
-        table_name = re.sub("(.)([A-Z][a-z]+)", r"\1_\2", class_name)
-        table_name = re.sub("([a-z0-9])([A-Z])", r"\1_\2", table_name).lower()
-
-        # Remove common suffixes
-        for suffix in ["_model", "_schema", "_response", "_request"]:
-            if table_name.endswith(suffix):
-                table_name = table_name[: -len(suffix)]
-                break
-
-        # Pluralize if it doesn't end with 's'
-        # if not table_name.endswith('s') and not table_name.endswith('_data'):
-        #     table_name += 's'
-
-        return table_name
-
-    def _parse_type_annotation(self, annotation) -> str:
-        """Parse type annotation to string."""
-        if isinstance(annotation, ast.Name):
-            return annotation.id
-        elif isinstance(annotation, ast.Subscript):
-            if isinstance(annotation.value, ast.Name):
-                # Handle Optional[Type], List[Type], etc.
-                inner_type = self._parse_type_annotation(annotation.slice)
-                return f"{annotation.value.id}[{inner_type}]"
-        elif isinstance(annotation, ast.Attribute):
-            # Handle datetime.datetime, etc.
-            if hasattr(annotation.value, "id"):
-                return f"{annotation.value.id}.{annotation.attr}"
-            return annotation.attr
-
-        return "unknown"
-
-    def _is_optional_type(self, annotation) -> bool:
-        """Check if type annotation is Optional."""
-        if isinstance(annotation, ast.Subscript):
-            if isinstance(annotation.value, ast.Name):
-                # Check for Optional[Type] or Union[Type, None]
-                if annotation.value.id in ["Optional", "Union"]:
-                    return True
-        return False