iam-policy-validator 1.0.4__py3-none-any.whl → 1.1.1__py3-none-any.whl

iam_validator/commands/cache.py

@@ -0,0 +1,402 @@
+"""Cache management command for IAM Policy Validator."""
+
+import argparse
+import logging
+from pathlib import Path
+
+from rich.console import Console
+from rich.table import Table
+
+from iam_validator.commands.base import Command
+from iam_validator.core.aws_fetcher import AWSServiceFetcher
+from iam_validator.core.config_loader import ConfigLoader
+
+logger = logging.getLogger(__name__)
+console = Console()
+
+
+class CacheCommand(Command):
+    """Manage AWS service definition cache."""
+
+    @property
+    def name(self) -> str:
+        return "cache"
+
+    @property
+    def help(self) -> str:
+        return "Manage AWS service definition cache"
+
+    @property
+    def epilog(self) -> str:
+        return """
+Examples:
+  # Show cache information
+  iam-validator cache info
+
+  # List all cached services
+  iam-validator cache list
+
+  # Clear all cached AWS service definitions
+  iam-validator cache clear
+
+  # Refresh cache (clear and pre-fetch common services)
+  iam-validator cache refresh
+
+  # Pre-fetch common AWS services
+  iam-validator cache prefetch
+
+  # Show cache location
+  iam-validator cache location
+"""
+
+    def add_arguments(self, parser: argparse.ArgumentParser) -> None:
+        """Add cache command arguments."""
+        subparsers = parser.add_subparsers(dest="cache_action", help="Cache action to perform")
+
+        # Info subcommand
+        info_parser = subparsers.add_parser("info", help="Show cache information and statistics")
+        info_parser.add_argument(
+            "--config",
+            type=str,
+            help="Path to configuration file",
+        )
+
+        # List subcommand
+        list_parser = subparsers.add_parser("list", help="List all cached AWS services")
+        list_parser.add_argument(
+            "--config",
+            type=str,
+            help="Path to configuration file",
+        )
+        list_parser.add_argument(
+            "--format",
+            choices=["table", "columns", "simple"],
+            default="table",
+            help="Output format (default: table)",
+        )
+
+        # Clear subcommand
+        clear_parser = subparsers.add_parser(
+            "clear", help="Clear all cached AWS service definitions"
+        )
+        clear_parser.add_argument(
+            "--config",
+            type=str,
+            help="Path to configuration file",
+        )
+
+        # Refresh subcommand
+        refresh_parser = subparsers.add_parser(
+            "refresh", help="Clear cache and pre-fetch common AWS services"
+        )
+        refresh_parser.add_argument(
+            "--config",
+            type=str,
+            help="Path to configuration file",
+        )
+
+        # Prefetch subcommand
+        prefetch_parser = subparsers.add_parser(
+            "prefetch", help="Pre-fetch common AWS services (without clearing)"
+        )
+        prefetch_parser.add_argument(
+            "--config",
+            type=str,
+            help="Path to configuration file",
+        )
+
+        # Location subcommand
+        location_parser = subparsers.add_parser("location", help="Show cache directory location")
+        location_parser.add_argument(
+            "--config",
+            type=str,
+            help="Path to configuration file",
+        )
+
+    async def execute(self, args: argparse.Namespace) -> int:
+        """Execute cache command."""
+        if not hasattr(args, "cache_action") or not args.cache_action:
+            console.print("[red]Error:[/red] No cache action specified")
+            console.print("Use 'iam-validator cache --help' for available actions")
+            return 1
+
+        # Load config to get cache settings
+        config_path = getattr(args, "config", None)
+        config = ConfigLoader.load_config(explicit_path=config_path, allow_missing=True)
+
+        cache_enabled = config.get_setting("cache_enabled", True)
+        cache_ttl_hours = config.get_setting("cache_ttl_hours", 168)
+        cache_directory = config.get_setting("cache_directory", None)
+        cache_ttl_seconds = cache_ttl_hours * 3600
+
+        # Get cache directory (even if caching is disabled, for info purposes)
+        cache_dir = AWSServiceFetcher._get_cache_directory(cache_directory)
+
+        action = args.cache_action
+
+        if action == "info":
+            return await self._show_info(cache_dir, cache_enabled, cache_ttl_hours)
+        elif action == "list":
+            output_format = getattr(args, "format", "table")
+            return self._list_cached_services(cache_dir, output_format)
+        elif action == "clear":
+            return await self._clear_cache(cache_dir, cache_enabled)
+        elif action == "refresh":
+            return await self._refresh_cache(cache_enabled, cache_ttl_seconds, cache_directory)
+        elif action == "prefetch":
+            return await self._prefetch_services(cache_enabled, cache_ttl_seconds, cache_directory)
+        elif action == "location":
+            return self._show_location(cache_dir)
+        else:
+            console.print(f"[red]Error:[/red] Unknown cache action: {action}")
+            return 1
+
+    async def _show_info(self, cache_dir: Path, cache_enabled: bool, cache_ttl_hours: int) -> int:
+        """Show cache information and statistics."""
+        table = Table(title="Cache Information")
+        table.add_column("Setting", style="cyan", no_wrap=True)
+        table.add_column("Value", style="white")
+
+        # Cache status
+        table.add_row(
+            "Status", "[green]Enabled[/green]" if cache_enabled else "[red]Disabled[/red]"
+        )
+
+        # Cache location
+        table.add_row("Location", str(cache_dir))
+
+        # Cache exists?
+        exists = cache_dir.exists()
+        table.add_row("Exists", "[green]Yes[/green]" if exists else "[yellow]No[/yellow]")
+
+        # Cache TTL
+        ttl_days = cache_ttl_hours / 24
+        table.add_row("TTL", f"{cache_ttl_hours} hours ({ttl_days:.1f} days)")
+
+        if exists:
+            # Count cached files
+            cache_files = list(cache_dir.glob("*.json"))
+            table.add_row("Cached Services", str(len(cache_files)))
+
+            # Calculate cache size
+            total_size = sum(f.stat().st_size for f in cache_files)
+            size_mb = total_size / (1024 * 1024)
+            table.add_row("Cache Size", f"{size_mb:.2f} MB")
+
+            # Show some cached services
+            if cache_files:
+                service_names = []
+                for f in cache_files[:5]:
+                    name = f.stem.split("_")[0] if "_" in f.stem else f.stem
+                    service_names.append(name)
+                sample = ", ".join(service_names)
+                if len(cache_files) > 5:
+                    sample += f", ... ({len(cache_files) - 5} more)"
+                table.add_row("Sample Services", sample)
+
+        console.print(table)
+        return 0
+
+    def _list_cached_services(self, cache_dir: Path, output_format: str) -> int:
+        """List all cached AWS services."""
+        if not cache_dir.exists():
+            console.print("[yellow]Cache directory does not exist[/yellow]")
+            return 0
+
+        cache_files = list(cache_dir.glob("*.json"))
+
+        if not cache_files:
+            console.print("[yellow]No services cached yet[/yellow]")
+            return 0
+
+        # Extract service names from filenames
+        services = []
+        for f in cache_files:
+            # Handle both formats: "service_hash.json" and "services_list.json"
+            if f.stem == "services_list":
+                continue  # Skip the services list file
+
+            # Extract service name (before underscore or full name)
+            name = f.stem.split("_")[0] if "_" in f.stem else f.stem
+
+            # Get file stats
+            size = f.stat().st_size
+            mtime = f.stat().st_mtime
+
+            services.append({
+                "name": name,
+                "size": size,
+                "file": f.name,
+                "mtime": mtime
+            })
+
+        # Sort by service name
+        services.sort(key=lambda x: x["name"])
+
+        if output_format == "table":
+            self._print_services_table(services)
+        elif output_format == "columns":
+            self._print_services_columns(services)
+        else:  # simple
+            self._print_services_simple(services)
+
+        return 0
+
+    def _print_services_table(self, services: list[dict]) -> None:
+        """Print services in a nice table format."""
+        from datetime import datetime
+
+        table = Table(title=f"Cached AWS Services ({len(services)} total)")
+        table.add_column("Service", style="cyan", no_wrap=True)
+        table.add_column("Cache File", style="white")
+        table.add_column("Size", style="yellow", justify="right")
+        table.add_column("Cached", style="green")
+
+        for svc in services:
+            size_kb = svc["size"] / 1024
+            cached_time = datetime.fromtimestamp(svc["mtime"]).strftime("%Y-%m-%d %H:%M")
+
+            table.add_row(
+                svc["name"],
+                svc["file"],
+                f"{size_kb:.1f} KB",
+                cached_time
+            )
+
+        console.print(table)
+
+    def _print_services_columns(self, services: list[dict]) -> None:
+        """Print services in columns format (like ls)."""
+        from rich.columns import Columns
+
+        console.print(f"[cyan]Cached AWS Services ({len(services)} total):[/cyan]\n")
+
+        service_names = [f"[green]{svc['name']}[/green]" for svc in services]
+        console.print(Columns(service_names, equal=True, expand=False))
+
+    def _print_services_simple(self, services: list[dict]) -> None:
+        """Print services in simple list format."""
+        console.print(f"[cyan]Cached AWS Services ({len(services)} total):[/cyan]\n")
+
+        for svc in services:
+            console.print(svc["name"])
+
+    async def _clear_cache(self, cache_dir: Path, cache_enabled: bool) -> int:
+        """Clear all cached AWS service definitions."""
+        if not cache_enabled:
+            console.print("[yellow]Warning:[/yellow] Cache is disabled in config")
+            return 0
+
+        if not cache_dir.exists():
+            console.print("[yellow]Cache directory does not exist, nothing to clear[/yellow]")
+            return 0
+
+        # Count files before deletion
+        cache_files = list(cache_dir.glob("*.json"))
+        file_count = len(cache_files)
+
+        if file_count == 0:
+            console.print("[yellow]Cache is already empty[/yellow]")
+            return 0
+
+        # Delete cache files
+        deleted = 0
+        failed = 0
+        for cache_file in cache_files:
+            try:
+                cache_file.unlink()
+                deleted += 1
+            except Exception as e:
+                logger.error(f"Failed to delete {cache_file}: {e}")
+                failed += 1
+
+        if failed == 0:
+            console.print(f"[green]✓[/green] Cleared {deleted} cached service definitions")
+        else:
+            console.print(
+                f"[yellow]![/yellow] Cleared {deleted} files, failed to delete {failed} files"
+            )
+            return 1
+
+        return 0
+
+    async def _refresh_cache(
+        self, cache_enabled: bool, cache_ttl_seconds: int, cache_directory: str | None
+    ) -> int:
+        """Clear cache and pre-fetch common services."""
+        if not cache_enabled:
+            console.print("[red]Error:[/red] Cache is disabled in config")
+            console.print("Enable cache by setting 'cache_enabled: true' in your config")
+            return 1
+
+        console.print("[cyan]Refreshing cache...[/cyan]")
+
+        # Create fetcher and clear cache
+        async with AWSServiceFetcher(
+            enable_cache=cache_enabled,
+            cache_ttl=cache_ttl_seconds,
+            cache_dir=cache_directory,
+            prefetch_common=False,  # Don't prefetch yet, we'll do it after clearing
+        ) as fetcher:
+            # Clear existing cache
+            console.print("Clearing old cache...")
+            await fetcher.clear_caches()
+
+            # Prefetch common services
+            console.print("Fetching fresh AWS service definitions...")
+            services = await fetcher.fetch_services()
+            console.print(f"[green]✓[/green] Fetched list of {len(services)} AWS services")
+
+            # Prefetch common services
+            console.print("Pre-fetching common services...")
+            prefetched = 0
+            for service_name in fetcher.COMMON_SERVICES:
+                try:
+                    await fetcher.fetch_service_by_name(service_name)
+                    prefetched += 1
+                except Exception as e:
+                    logger.warning(f"Failed to prefetch {service_name}: {e}")
+
+            console.print(f"[green]✓[/green] Pre-fetched {prefetched} common services")
+
+        console.print("[green]✓[/green] Cache refreshed successfully")
+        return 0
+
+    async def _prefetch_services(
+        self, cache_enabled: bool, cache_ttl_seconds: int, cache_directory: str | None
+    ) -> int:
+        """Pre-fetch common AWS services without clearing cache."""
+        if not cache_enabled:
+            console.print("[red]Error:[/red] Cache is disabled in config")
+            console.print("Enable cache by setting 'cache_enabled: true' in your config")
+            return 1
+
+        console.print("[cyan]Pre-fetching common AWS services...[/cyan]")
+
+        async with AWSServiceFetcher(
+            enable_cache=cache_enabled,
+            cache_ttl=cache_ttl_seconds,
+            cache_dir=cache_directory,
+            prefetch_common=True,  # Enable prefetching
+        ) as fetcher:
+            # Prefetching happens in __aenter__, just wait for it
+            prefetched = len(fetcher._prefetched_services)
+            total = len(fetcher.COMMON_SERVICES)
+
+            console.print(
+                f"[green]✓[/green] Pre-fetched {prefetched}/{total} common services successfully"
+            )
+
+        return 0
+
+    def _show_location(self, cache_dir: Path) -> int:
+        """Show cache directory location."""
+        console.print(f"[cyan]Cache directory:[/cyan] {cache_dir}")
+
+        if cache_dir.exists():
+            console.print("[green]✓[/green] Directory exists")
+        else:
+            console.print("[yellow]![/yellow] Directory does not exist yet")
+            console.print("It will be created automatically when caching is used")
+
+        return 0

iam_validator/commands/validate.py

@@ -59,9 +59,9 @@ Examples:
         parser.add_argument(
             "--format",
             "-f",
-            choices=["console", "json", "markdown", "html", "csv", "sarif"],
+            choices=["console", "enhanced", "json", "markdown", "html", "csv", "sarif"],
             default="console",
-            help="Output format (default: console)",
+            help="Output format (default: console). Use 'enhanced' for modern visual output with Rich library",
         )
 
         parser.add_argument(
@@ -177,7 +177,8 @@ Examples:
         report = generator.generate_report(results)
 
         # Output results
-        if args.format == "console":
+        if args.format is None:
+            # Default: use classic console output (direct Rich printing)
             generator.print_console_report(report)
         elif args.format == "json":
             if args.output:
@@ -190,7 +191,7 @@ Examples:
             else:
                 print(generator.generate_github_comment(report))
         else:
-            # Use formatter registry for other formats (html, csv, sarif)
+            # Use formatter registry for other formats (enhanced, html, csv, sarif)
             output_content = generator.format_report(report, args.format)
             if args.output:
                 with open(args.output, "w", encoding="utf-8") as f:
@@ -285,6 +286,7 @@ Examples:
 
         # Output final results
         if args.format == "console":
+            # Classic console output (direct Rich printing from report.py)
             generator.print_console_report(report)
         elif args.format == "json":
             if args.output:
@@ -297,7 +299,7 @@ Examples:
             else:
                 print(generator.generate_github_comment(report))
         else:
-            # Use formatter registry for other formats (html, csv, sarif)
+            # Use formatter registry for other formats (enhanced, html, csv, sarif)
             output_content = generator.format_report(report, args.format)
             if args.output:
                 with open(args.output, "w", encoding="utf-8") as f:

iam_validator/core/access_analyzer_report.py

@@ -8,6 +8,7 @@ from rich.panel import Panel
 from rich.table import Table
 from rich.text import Text
 
+from iam_validator.__version__ import __version__
 from iam_validator.core.access_analyzer import (
     AccessAnalyzerFinding,
     AccessAnalyzerReport,
@@ -70,7 +71,7 @@ class AccessAnalyzerReportFormatter:
 
         panel = Panel(
             summary_text,
-            title="[bold]Access Analyzer Validation Summary[/bold]",
+            title=f"[bold]Access Analyzer Validation Summary (iam-validator v{__version__})[/bold]",
             border_style="blue",
         )
         self.console.print(panel)

iam_validator/core/aws_fetcher.py

@@ -23,7 +23,9 @@ import asyncio
 import hashlib
 import json
 import logging
+import os
 import re
+import sys
 import time
 from collections import OrderedDict
 from pathlib import Path
@@ -122,28 +124,51 @@ class AWSServiceFetcher:
     BASE_URL = "https://servicereference.us-east-1.amazonaws.com/"
 
     # Common AWS services to pre-fetch
+    # All other services will be fetched on-demand (lazy loading if found in policies)
     COMMON_SERVICES = [
-        "iam",
-        "sts",
-        "s3",
+        "acm",
+        "apigateway",
+        "autoscaling",
+        "backup",
+        "batch",
+        "bedrock",
+        "cloudformation",
+        "cloudfront",
+        "cloudtrail",
+        "cloudwatch",
+        "config",
+        "dynamodb",
+        "ec2-instance-connect",
         "ec2",
+        "ecr",
+        "ecs",
+        "eks",
+        "elasticache",
+        "elasticloadbalancing",
+        "events",
+        "firehose",
+        "glacier",
+        "glue",
+        "guardduty",
+        "iam",
+        "imagebuilder",
+        "inspector2",
+        "kinesis",
+        "kms",
         "lambda",
-        "dynamodb",
+        "logs",
         "rds",
-        "cloudwatch",
+        "route53",
+        "s3",
+        "scheduler",
+        "secretsmanager",
+        "securityhub",
         "sns",
         "sqs",
-        "kms",
-        "cloudformation",
-        "elasticloadbalancing",
-        "autoscaling",
-        "route53",
-        "apigateway",
-        "ecs",
-        "eks",
-        "cloudfront",
-        "logs",
-        "events",
+        "sts",
+        "support",
+        "waf",
+        "wafv2",
     ]
 
     def __init__(
@@ -151,11 +176,12 @@ class AWSServiceFetcher:
         timeout: float = 30.0,
         retries: int = 3,
         enable_cache: bool = True,
-        cache_ttl: int = 3600,
+        cache_ttl: int = 604800,
         memory_cache_size: int = 256,
         connection_pool_size: int = 50,
         keepalive_connections: int = 20,
         prefetch_common: bool = True,
+        cache_dir: Path | str | None = None,
     ):
         """Initialize aws service fetcher.
 
@@ -163,11 +189,12 @@ class AWSServiceFetcher:
             timeout: Request timeout in seconds
             retries: Number of retry attempts
             enable_cache: Enable disk caching
-            cache_ttl: Cache time to live in seconds (default: 1 hour)
+            cache_ttl: Cache time to live in seconds (default: 7 days)
             memory_cache_size: Max items in memory cache
             connection_pool_size: Max connections in pool
             keepalive_connections: Number of keepalive connections
             prefetch_common: Pre-fetch common services on init
+            cache_dir: Custom cache directory (defaults to platform-specific user cache dir)
         """
         self.timeout = timeout
         self.retries = retries
@@ -177,7 +204,7 @@ class AWSServiceFetcher:
 
         self._client: httpx.AsyncClient | None = None
         self._memory_cache = LRUCache(maxsize=memory_cache_size, ttl=cache_ttl)
-        self._cache_dir = Path.cwd() / ".cache" / "aws_services"
+        self._cache_dir = self._get_cache_directory(cache_dir)
         self._patterns = CompiledPatterns()
 
         # Batch request queue
@@ -195,6 +222,39 @@ class AWSServiceFetcher:
         if self.enable_cache:
             self._cache_dir.mkdir(parents=True, exist_ok=True)
 
+    @staticmethod
+    def _get_cache_directory(cache_dir: Path | str | None = None) -> Path:
+        """Get the cache directory path, using platform-appropriate defaults.
+
+        Priority:
+        1. Provided cache_dir parameter
+        2. Platform-specific user cache directory
+           - Linux/Unix: ~/.cache/iam-validator/aws_services
+           - macOS: ~/Library/Caches/iam-validator/aws_services
+           - Windows: %LOCALAPPDATA%/iam-validator/cache/aws_services
+
+        Args:
+            cache_dir: Optional custom cache directory path
+
+        Returns:
+            Path object for the cache directory
+        """
+        if cache_dir is not None:
+            return Path(cache_dir)
+
+        # Determine platform-specific cache directory
+        if sys.platform == "darwin":
+            # macOS
+            base_cache = Path.home() / "Library" / "Caches"
+        elif sys.platform == "win32":
+            # Windows
+            base_cache = Path(os.environ.get("LOCALAPPDATA", Path.home() / "AppData" / "Local"))
+        else:
+            # Linux and other Unix-like systems
+            base_cache = Path(os.environ.get("XDG_CACHE_HOME", Path.home() / ".cache"))
+
+        return base_cache / "iam-validator" / "aws_services"
+
     async def __aenter__(self) -> "AWSServiceFetcher":
         """Async context manager entry with optimized settings."""
         self._client = httpx.AsyncClient(

iam_validator/core/check_registry.py

@@ -30,6 +30,7 @@ class CheckConfig:
     severity: str | None = None  # Override default severity
     config: dict[str, Any] = field(default_factory=dict)  # Check-specific config
     description: str = ""
+    root_config: dict[str, Any] = field(default_factory=dict)  # Full config for cross-check access
 
 
 class PolicyCheck(ABC):
@@ -433,6 +434,7 @@ def create_default_registry(
         # Import and register built-in checks
         from iam_validator.checks import (
             ActionConditionEnforcementCheck,
+            ActionResourceConstraintCheck,
             ActionValidationCheck,
             ConditionKeyValidationCheck,
             PolicySizeCheck,
@@ -446,6 +448,7 @@ def create_default_registry(
         registry.register(ResourceValidationCheck())
         registry.register(SecurityBestPracticesCheck())
         registry.register(ActionConditionEnforcementCheck())
+        registry.register(ActionResourceConstraintCheck())
         registry.register(SidUniquenessCheck())
         registry.register(PolicySizeCheck())
 

iam_validator/core/cli.py

@@ -6,7 +6,7 @@ import logging
 import os
 import sys
 
-from iam_validator import __version__
+from iam_validator.__version__ import __version__
 from iam_validator.commands import ALL_COMMANDS