Add new flag --skip-hash-collection

davidkopp · davidkopp · commit 091e64268f5a · 2025-09-19T00:01:24.000+02:00
diff --git a/CLAUDE.md b/CLAUDE.md
@@ -15,7 +15,7 @@ pip install -r requirements.txt
 
 # Run specific detectors for testing
 python3 -m dependency_resolver docker <container_name>
-python3 -m dependency_resolver host --skip-system-scope
+python3 -m dependency_resolver host --skip-system-scope --skip-hash-generation
 
 # Execute linting and formatting
 pre-commit run --files $(git diff --name-only --diff-filter=ACMR HEAD)
diff --git a/dependency_resolver/__main__.py b/dependency_resolver/__main__.py
@@ -36,6 +36,7 @@ def parse_arguments() -> argparse.Namespace:
   %(prog)s --venv-path ~/.virtualenvs/myproject   # Use specific virtual environment for pip
   %(prog)s --debug                                # Enable debug output
   %(prog)s --skip-system-scope                    # Skip system scope package managers
+  %(prog)s --skip-hash-collection                 # Skip hash collection for improved performance
         """,
     )
 
@@ -78,6 +79,12 @@ def parse_arguments() -> argparse.Namespace:
         help="Format JSON output with indentation",
     )
 
+    parser.add_argument(
+        "--skip-hash-collection",
+        action="store_true",
+        help="Skip hash collection for packages and project locations to improve performance",
+    )
+
     return parser.parse_args()
 
 
@@ -122,7 +129,10 @@ def main() -> None:
     try:
         executor = create_executor(args.environment_type, args.environment_identifier, debug=args.debug)
         orchestrator = Orchestrator(
-            debug=args.debug, skip_system_scope=args.skip_system_scope, venv_path=args.venv_path
+            debug=args.debug,
+            skip_system_scope=args.skip_system_scope,
+            venv_path=args.venv_path,
+            skip_hash_collection=args.skip_hash_collection,
         )
         dependencies = orchestrator.resolve_dependencies(executor, args.working_dir, args.only_container_info)
         formatter = OutputFormatter(debug=args.debug)
diff --git a/dependency_resolver/core/interfaces.py b/dependency_resolver/core/interfaces.py
@@ -32,10 +32,15 @@ def is_usable(self, executor: EnvironmentExecutor, working_dir: Optional[str] =
 
     @abstractmethod
     def get_dependencies(
-        self, executor: EnvironmentExecutor, working_dir: Optional[str] = None
+        self, executor: EnvironmentExecutor, working_dir: Optional[str] = None, skip_hash_collection: bool = False
     ) -> tuple[list[dict[str, Any]], dict[str, Any]]:
         """Extract dependencies with versions and hashes.
 
+        Args:
+            executor: Environment executor for running commands
+            working_dir: Working directory to use
+            skip_hash_collection: Skip hash collection for improved performance
+
         Returns:
             tuple: (packages, metadata)
             - packages: List of package dicts with name, version, type, and optional hash
diff --git a/dependency_resolver/core/orchestrator.py b/dependency_resolver/core/orchestrator.py
@@ -16,9 +16,11 @@ def __init__(
         debug: bool = False,
         skip_system_scope: bool = False,
         venv_path: str | None = None,
+        skip_hash_collection: bool = False,
     ):
         self.debug = debug
         self.skip_system_scope = skip_system_scope
+        self.skip_hash_collection = skip_hash_collection
 
         # Create detector instances
         self.detectors: list[PackageManagerDetector] = [
@@ -69,15 +71,19 @@ def resolve_dependencies(
 
                     # Special handling for docker-info detector
                     if detector_name == "docker-info":
-                        packages, metadata = detector.get_dependencies(executor, working_dir)
+                        packages, metadata = detector.get_dependencies(
+                            executor, working_dir, skip_hash_collection=self.skip_hash_collection
+                        )
                         if metadata:  # Only include if we got container info
                             metadata["type"] = "container"
                             result["source"] = metadata
                         if self.debug:
                             print(f"Found container info for {detector_name}")
                     else:
                         # Standard handling for package detectors
-                        packages, metadata = detector.get_dependencies(executor, working_dir)
+                        packages, metadata = detector.get_dependencies(
+                            executor, working_dir, skip_hash_collection=self.skip_hash_collection
+                        )
 
                         if detector.has_system_scope(executor, working_dir):
                             # System scope packages
diff --git a/dependency_resolver/detectors/apk_detector.py b/dependency_resolver/detectors/apk_detector.py
@@ -25,18 +25,22 @@ def is_usable(self, executor: EnvironmentExecutor, working_dir: Optional[str] =
         return apk_exit_code == 0
 
     def get_dependencies(
-        self, executor: EnvironmentExecutor, working_dir: Optional[str] = None
+        self, executor: EnvironmentExecutor, working_dir: Optional[str] = None, skip_hash_collection: bool = False
     ) -> tuple[list[dict[str, Any]], dict[str, Any]]:
         """Extract system packages with versions and architecture using apk list.
 
         Uses 'apk list --installed' for comprehensive package information including architecture.
         See docs/technical/detectors/apk_detector.md
 
+        Args:
+            skip_hash_collection: Not applicable for apk (no hash collection implemented)
+
         Returns:
             tuple: (packages, metadata)
             - packages: List of package dicts with name, version, type
             - metadata: Empty dict (system scope has no metadata)
         """
+        _ = skip_hash_collection  # Not applicable for apk detector
         command = "apk list --installed"
         stdout, _, exit_code = executor.execute_command(command, working_dir)
 
diff --git a/dependency_resolver/detectors/docker_info_detector.py b/dependency_resolver/detectors/docker_info_detector.py
@@ -14,14 +14,15 @@ def is_usable(self, executor: EnvironmentExecutor, working_dir: Optional[str] =
         return isinstance(executor, DockerExecutor)
 
     def get_dependencies(
-        self, executor: EnvironmentExecutor, working_dir: Optional[str] = None
+        self, executor: EnvironmentExecutor, working_dir: Optional[str] = None, skip_hash_collection: bool = False
     ) -> tuple[list[dict[str, Any]], dict[str, Any]]:
         """Extract Docker container metadata.
 
         Note: This detector returns metadata rather than packages, but conforms to the interface.
         The orchestrator handles this specially.
         """
         _ = working_dir  # Unused parameter, required by interface
+        _ = skip_hash_collection  # Not applicable for docker metadata
         if not isinstance(executor, DockerExecutor):
             return [], {}
 
diff --git a/dependency_resolver/detectors/dpkg_detector.py b/dependency_resolver/detectors/dpkg_detector.py
@@ -31,7 +31,7 @@ def is_usable(self, executor: EnvironmentExecutor, working_dir: Optional[str] =
         return dpkg_exit_code == 0
 
     def get_dependencies(
-        self, executor: EnvironmentExecutor, working_dir: Optional[str] = None
+        self, executor: EnvironmentExecutor, working_dir: Optional[str] = None, skip_hash_collection: bool = False
     ) -> tuple[list[dict[str, Any]], dict[str, Any]]:
         """Extract system packages with versions using dpkg-query.
 
@@ -49,8 +49,8 @@ def get_dependencies(
         if exit_code != 0:
             return [], {}
 
-        # Collect all package hashes in a single batch operation
-        batch_hashes = self._collect_all_package_hashes(executor)
+        # Collect all package hashes in a single batch operation (unless skipped)
+        batch_hashes = {} if skip_hash_collection else self._collect_all_package_hashes(executor)
 
         packages = []
         for line in stdout.strip().split("\n"):
@@ -65,13 +65,15 @@ def get_dependencies(
 
                     package_data = {"name": package_name, "version": full_version, "type": PACKAGE_TYPE_DPKG}
 
-                    # Use batch-collected hash or fallback to individual lookup
-                    package_hash = batch_hashes.get(package_name)
-                    if not package_hash:
-                        package_hash = self._get_package_hash(executor, package_name, architecture)
+                    # Skip hash collection if requested
+                    if not skip_hash_collection:
+                        # Use batch-collected hash or fallback to individual lookup
+                        package_hash = batch_hashes.get(package_name)
+                        if not package_hash:
+                            package_hash = self._get_package_hash(executor, package_name, architecture)
 
-                    if package_hash:
-                        package_data["hash"] = package_hash
+                        if package_hash:
+                            package_data["hash"] = package_hash
 
                     packages.append(package_data)
 
diff --git a/dependency_resolver/detectors/maven_detector.py b/dependency_resolver/detectors/maven_detector.py
@@ -25,7 +25,7 @@ def is_usable(self, executor: EnvironmentExecutor, working_dir: Optional[str] =
         return executor.path_exists(f"{search_dir}/pom.xml")
 
     def get_dependencies(
-        self, executor: EnvironmentExecutor, working_dir: Optional[str] = None
+        self, executor: EnvironmentExecutor, working_dir: Optional[str] = None, skip_hash_collection: bool = False
     ) -> tuple[list[dict[str, Any]], dict[str, Any]]:
         """Extract Maven dependencies with versions.
 
@@ -51,8 +51,8 @@ def get_dependencies(
 
         # Build metadata for project scope
         metadata = {"location": location}
-        # Generate location-based hash if we have packages
-        if packages:
+        # Generate location-based hash if we have packages (unless skipped)
+        if packages and not skip_hash_collection:
             metadata["hash"] = self._generate_location_hash(executor, location)
 
         return packages, metadata
diff --git a/dependency_resolver/detectors/npm_detector.py b/dependency_resolver/detectors/npm_detector.py
@@ -38,7 +38,7 @@ def is_usable(self, executor: EnvironmentExecutor, working_dir: Optional[str] =
         return executor.path_exists(f"{search_dir}/package-lock.json")
 
     def get_dependencies(
-        self, executor: EnvironmentExecutor, working_dir: Optional[str] = None
+        self, executor: EnvironmentExecutor, working_dir: Optional[str] = None, skip_hash_collection: bool = False
     ) -> tuple[list[dict[str, Any]], dict[str, Any]]:
         """Extract npm dependencies with versions.
 
@@ -77,8 +77,8 @@ def get_dependencies(
         else:
             # Build metadata for project scope
             metadata = {"location": location}
-            # Generate location-based hash if we have packages
-            if packages:
+            # Generate location-based hash if we have packages (unless skipped)
+            if packages and not skip_hash_collection:
                 metadata["hash"] = self._generate_location_hash(executor, location)
             return packages, metadata
 
diff --git a/dependency_resolver/detectors/pip_detector.py b/dependency_resolver/detectors/pip_detector.py
@@ -27,7 +27,7 @@ def is_usable(self, executor: EnvironmentExecutor, working_dir: Optional[str] =
         return exit_code == 0
 
     def get_dependencies(
-        self, executor: EnvironmentExecutor, working_dir: Optional[str] = None
+        self, executor: EnvironmentExecutor, working_dir: Optional[str] = None, skip_hash_collection: bool = False
     ) -> tuple[list[dict[str, Any]], dict[str, Any]]:
         """Extract pip dependencies with versions.
 
@@ -72,8 +72,8 @@ def get_dependencies(
         else:
             # Build metadata for project scope
             metadata = {"location": location}
-            # Generate location-based hash if we have packages
-            if packages:
+            # Generate location-based hash if we have packages (unless skipped)
+            if packages and not skip_hash_collection:
                 metadata["hash"] = self._generate_location_hash(executor, location)
             return packages, metadata
 
diff --git a/docs/guides/troubleshooting.md b/docs/guides/troubleshooting.md
@@ -170,9 +170,10 @@ npm --version
 **Solutions**:
 
 1. Use `--skip-system-scope` to skip system package managers
-2. Use `--only-container-info` for Docker metadata only
-3. Specify working directory to limit scope
-4. Check if system has many installed packages
+2. Use `--skip-hash-collection` to skip hash generation for packages and locations
+3. Use `--only-container-info` for Docker metadata only
+4. Specify working directory to limit scope
+5. Check if system has many installed packages
 
 ## Getting Help
 
diff --git a/docs/usage/cli-guide.md b/docs/usage/cli-guide.md
@@ -43,6 +43,9 @@ python3 -m dependency_resolver --working-dir /path/to/project
 
 # Skip system scope package managers (focus on project dependencies)
 python3 -m dependency_resolver --skip-system-scope
+
+# Skip hash collection for improved performance
+python3 -m dependency_resolver --skip-hash-collection
 ```
 
 ## Common Usage Patterns
@@ -79,6 +82,9 @@ python3 -m dependency_resolver --debug
 
 # Focus on project dependencies only
 python3 -m dependency_resolver --skip-system-scope --debug
+
+# Fast analysis without hash collection
+python3 -m dependency_resolver --skip-hash-collection --debug
 ```
 
 ## Supported Environments
diff --git a/docs/usage/programmatic-api.md b/docs/usage/programmatic-api.md
@@ -27,7 +27,8 @@ deps_json = dependency_resolver.resolve_host_dependencies()
 # Get Python dictionary for further processing
 deps_dict = dependency_resolver.resolve_dependencies_as_dict(
     environment_type="host",
-    skip_system_scope=True
+    skip_system_scope=True,
+    skip_hash_collection=True  # Skip hash collection for improved performance
 )
 ```
 
@@ -46,7 +47,8 @@ docker_deps = dependency_resolver.resolve_docker_dependencies(
 docker_dict = dependency_resolver.resolve_docker_dependencies_as_dict(
     container_identifier="nginx",
     working_dir="/app",
-    skip_system_scope=False
+    skip_system_scope=False,
+    skip_hash_collection=False  # Include hashes in output
 )
 ```
 
@@ -66,7 +68,7 @@ from dependency_resolver import Orchestrator, HostExecutor, DockerExecutor, Outp
 
 # Host system analysis with custom settings
 executor = HostExecutor()
-orchestrator = Orchestrator(debug=True, skip_system_scope=True)
+orchestrator = Orchestrator(debug=True, skip_system_scope=True, skip_hash_collection=True)
 dependencies = orchestrator.resolve_dependencies(executor)
 
 # Format output
@@ -82,7 +84,7 @@ from dependency_resolver import Orchestrator, DockerExecutor, OutputFormatter
 # Docker container analysis
 container_id = "nginx"
 executor = DockerExecutor(container_id)
-orchestrator = Orchestrator(debug=False, skip_system_scope=False)
+orchestrator = Orchestrator(debug=False, skip_system_scope=False, skip_hash_collection=False)
 
 dependencies = orchestrator.resolve_dependencies(executor, working_dir="/app")
 
@@ -116,7 +118,8 @@ for scope, result in dependencies.items():
 orchestrator = Orchestrator(
     debug=True,                    # Enable debug output
     skip_system_scope=False,       # Skip system-wide package managers
-    venv_path="/path/to/venv"      # Specify Python virtual environment path
+    venv_path="/path/to/venv",     # Specify Python virtual environment path
+    skip_hash_collection=False     # Skip hash collection for improved performance
 )
 ```
 
@@ -179,7 +182,8 @@ class DependencyTracker:
             deps = dependency_resolver.resolve_dependencies_as_dict(
                 environment_type="host",
                 working_dir=working_dir,
-                skip_system_scope=True  # Focus on project dependencies
+                skip_system_scope=True,      # Focus on project dependencies
+                skip_hash_collection=True    # Skip hashes for faster fingerprinting
             )
 
             # Create stable fingerprint from dependency versions
