feat: ES-163 fix pr comments, update lint.yml workflow

Author: matiasdaloia

.github/workflows/lint.yml

@@ -32,12 +32,17 @@ jobs:
           # List all changed Python files since the merge base.
           files=$(git diff --name-only "$merge_base" HEAD | grep '\.py$' || true)
 
+          # Filter out files that match exclude patterns from pyproject.toml 
+          # this is a temporary workaround until we fix all the lint errors
+          filtered_files=$(echo "$files" | grep -v -E 'tests/|test_.*\.py|src/protoc_gen_swagger/|src/scanoss/api/' || true)
+
           # Use the multi-line syntax for outputs.
           echo "files<<EOF" >> "$GITHUB_OUTPUT"
-          echo "${files}" >> "$GITHUB_OUTPUT"
+          echo "${filtered_files}" >> "$GITHUB_OUTPUT"
           echo "EOF" >> "$GITHUB_OUTPUT"
 
-          echo "Changed files: ${files}"
+          echo "Changed files before filtering: ${files}"
+          echo "Changed files after filtering: ${filtered_files}"
 
       - name: Run Ruff on changed files
         run: |
@@ -50,3 +55,4 @@ jobs:
             # Pass the list of changed files to Ruff.
             echo "${{ steps.changed_files.outputs.files }}" | xargs ruff check
           fi
+

src/scanoss/__init__.py

@@ -22,4 +22,4 @@
   THE SOFTWARE.
 """
 
-__version__ = '1.20.0'
+__version__ = '1.21.0'

src/scanoss/api/scanning/v2/scanoss_scanning_pb2_grpc.py

@@ -1,7 +1,6 @@
 # Generated by the gRPC Python protocol compiler plugin. DO NOT EDIT!
 """Client and server classes corresponding to protobuf-defined services."""
 import grpc
-import warnings
 
 from scanoss.api.common.v2 import scanoss_common_pb2 as scanoss_dot_api_dot_common_dot_v2_dot_scanoss__common__pb2
 from scanoss.api.scanning.v2 import scanoss_scanning_pb2 as scanoss_dot_api_dot_scanning_dot_v2_dot_scanoss__scanning__pb2

src/scanoss/file_filters.py

@@ -29,7 +29,6 @@
 
 from pathspec import GitIgnoreSpec
 
-from .scanoss_settings import ScanossSettings
 from .scanossbase import ScanossBase
 
 # Files to skip
@@ -240,48 +239,35 @@ class FileFilters(ScanossBase):
     Handles both inclusion and exclusion rules based on file paths, extensions, and sizes.
     """
 
-    def __init__(
-        self,
-        debug: bool = False,
-        trace: bool = False,
-        quiet: bool = False,
-        scanoss_settings: 'ScanossSettings | None' = None,
-        all_extensions: bool = False,
-        all_folders: bool = False,
-        hidden_files_folders: bool = False,
-        operation_type: str = 'scanning',
-        skip_size: int = 0,
-        skip_extensions=None,
-        skip_folders=None,
-    ):
+    def __init__(self, debug: bool = False, trace: bool = False, quiet: bool = False, **kwargs):
         """
         Initialize scan filters based on default settings. Optionally append custom settings.
 
         Args:
             debug (bool): Enable debug output
             trace (bool): Enable trace output
             quiet (bool): Suppress output
-            scanoss_settings (ScanossSettings): Custom settings to override defaults
-            all_extensions (bool): Include all file extensions
-            all_folders (bool): Include all folders
-            hidden_files_folders (bool): Include hidden files and folders
-            operation_type: operation type. can be either 'scanning' or 'fingerprinting'
+            **kwargs: Additional arguments including:
+                scanoss_settings (ScanossSettings): Custom settings to override defaults
+                all_extensions (bool): Include all file extensions
+                all_folders (bool): Include all folders
+                hidden_files_folders (bool): Include hidden files and folders
+                operation_type (str): Operation type ('scanning' or 'fingerprinting')
+                skip_size (int): Size to skip
+                skip_extensions (list): Extensions to skip
+                skip_folders (list): Folders to skip
         """
         super().__init__(debug, trace, quiet)
 
-        if skip_folders is None:
-            skip_folders = []
-        if skip_extensions is None:
-            skip_extensions = []
-        self.hidden_files_folders = hidden_files_folders
-        self.scanoss_settings = scanoss_settings
-        self.all_extensions = all_extensions
-        self.all_folders = all_folders
-        self.skip_folders = skip_folders
-        self.skip_size = skip_size
-        self.skip_extensions = skip_extensions
-        self.file_folder_pat_spec = self._get_file_folder_pattern_spec(operation_type)
-        self.size_pat_rules = self._get_size_limit_pattern_rules(operation_type)
+        self.hidden_files_folders = kwargs.get('hidden_files_folders', False)
+        self.scanoss_settings = kwargs.get('scanoss_settings')
+        self.all_extensions = kwargs.get('all_extensions', False)
+        self.all_folders = kwargs.get('all_folders', False)
+        self.skip_folders = kwargs.get('skip_folders', [])
+        self.skip_size = kwargs.get('skip_size', 0)
+        self.skip_extensions = kwargs.get('skip_extensions', [])
+        self.file_folder_pat_spec = self._get_file_folder_pattern_spec(kwargs.get('operation_type', 'scanning'))
+        self.size_pat_rules = self._get_size_limit_pattern_rules(kwargs.get('operation_type', 'scanning'))
 
     def get_filtered_files_from_folder(self, root: str) -> List[str]:
         """
@@ -311,16 +297,16 @@ def get_filtered_files_from_folder(self, root: str) -> List[str]:
             return all_files
         # Walk the tree looking for files to process. While taking into account files/folders to skip
         for dirpath, dirnames, filenames in os.walk(root_path):
-            dirpath = Path(dirpath)
-            rel_path = dirpath.relative_to(root_path)
-            if dirpath.is_symlink():  # TODO should we skip symlink folders?
-                self.print_msg(f'WARNING: Found symbolic link folder: {dirpath}')
+            dir_path = Path(dirpath)
+            rel_path = dir_path.relative_to(root_path)
+            if dir_path.is_symlink():  # TODO should we skip symlink folders?
+                self.print_msg(f'WARNING: Found symbolic link folder: {dir_path}')
 
             if self.should_skip_dir(str(rel_path)):  # Current directory should be skipped
                 dirnames.clear()
                 continue
             for filename in filenames:
-                file_path = dirpath / filename
+                file_path = dir_path / filename
                 all_files.append(str(file_path))
         # End os.walk loop
         # Now filter the files and return the reduced list
@@ -452,7 +438,7 @@ def _get_operation_size_limits(self, file_path: str = None) -> tuple:
         # End rules loop
         return min_size, max_size
 
-    def should_skip_dir(self, dir_rel_path: str) -> bool:
+    def should_skip_dir(self, dir_rel_path: str) -> bool:  # noqa: PLR0911
         """
         Check if a directory should be skipped based on operation type and default rules.
 
@@ -490,7 +476,7 @@ def should_skip_dir(self, dir_rel_path: str) -> bool:
             return True
         return False
 
-    def _should_skip_file(self, file_rel_path: str) -> bool:
+    def _should_skip_file(self, file_rel_path: str) -> bool:  # noqa: PLR0911
         """
         Check if a file should be skipped based on operation type and default rules.
 

src/scanoss/results.py

@@ -208,8 +208,15 @@ def _format_json_output(self) -> str:
         return json.dumps({'results': formatted_data, 'total': len(formatted_data)}, indent=2)
 
     def _format_plain_output(self) -> str:
+        """Format the output data into a plain text string
+
+        Returns:
+            str: The formatted output data
+        """
         if not self.data:
-            return self.print_stderr('No results to present')
+            msg = 'No results to present'
+            self.print_stderr(msg)
+            return msg
 
         formatted = ''
         for item in self.data:

src/scanoss/scanners/scanner_config.py

@@ -59,8 +59,8 @@ def create_scanner_config_from_args(args) -> ScannerConfig:
         debug=args.debug,
         trace=args.trace,
         quiet=args.quiet,
-        api_key=getattr(args, 'api_key', None),
-        url=getattr(args, 'url', None),
+        api_key=getattr(args, 'key', None),
+        url=getattr(args, 'api_url', None),
         grpc_url=getattr(args, 'grpc_url', None),
         post_size=getattr(args, 'post_size', DEFAULT_POST_SIZE),
         timeout=getattr(args, 'timeout', DEFAULT_TIMEOUT),

src/scanoss/scanners/scanner_hfh.py

@@ -292,4 +292,6 @@ def _format_plain_output(self) -> str:
         """
         Format the scan output data into a plain text string
         """
-        return self.scan_results
+        return (
+            json.dumps(self.scan_results, indent=2) if isinstance(self.scan_results, dict) else str(self.scan_results)
+        )

src/scanoss/scanossgrpc.py

@@ -26,6 +26,7 @@
 import os
 import uuid
 from dataclasses import dataclass
+from enum import IntEnum
 from typing import Dict, Optional
 from urllib.parse import urlparse
 
@@ -82,12 +83,21 @@ class ScanossGrpcError(Exception):
     pass
 
 
+class ScanossGrpcStatusCode(IntEnum):
+    """Status codes for SCANOSS gRPC responses"""
+
+    SUCCESS = 1
+    SUCCESS_WITH_WARNINGS = 2
+    FAILED_WITH_WARNINGS = 3
+    FAILED = 4
+
+
 class ScanossGrpc(ScanossBase):
     """
     Client for gRPC functionality
     """
 
-    def __init__(  # noqa: PLR0913
+    def __init__(  # noqa: PLR0913, PLR0915
         self,
         url: str = None,
         debug: bool = False,
@@ -489,13 +499,13 @@ def _check_status_response(self, status_response: StatusResponse, request_id: st
             return True
         self.print_debug(f'Checking response status (rqId: {request_id}): {status_response}')
         status_code: StatusCode = status_response.status
-        if status_code > 1:
+        if status_code > ScanossGrpcStatusCode.SUCCESS:
             ret_val = False  # default to failed
             msg = 'Unsuccessful'
-            if status_code == 2:
+            if status_code == ScanossGrpcStatusCode.SUCCESS_WITH_WARNINGS:
                 msg = 'Succeeded with warnings'
                 ret_val = True  # No need to fail as it succeeded with warnings
-            elif status_code == 3:
+            elif status_code == ScanossGrpcStatusCode.FAILED_WITH_WARNINGS:
                 msg = 'Failed with warnings'
             self.print_stderr(f'{msg} (rqId: {request_id} - status: {status_code}): {status_response.message}')
             return ret_val

src/scanoss/utils/abstract_presenter.py

@@ -34,7 +34,7 @@ def present(self, output_format: str = None, output_file: str = None):
         fmt = output_format or self.output_format
 
         if fmt and fmt not in AVAILABLE_OUTPUT_FORMATS:
-            raise Exception(
+            raise ValueError(
                 f"ERROR: Invalid output format '{fmt}'. Valid values are: {', '.join(AVAILABLE_OUTPUT_FORMATS)}"
             )
 

src/scanoss/utils/crc64.py

@@ -71,6 +71,7 @@ def hexdigest(self):
         """Get the current CRC value as a hexadecimal string."""
         return format(self.digest(), '016x')
 
+    @classmethod
     def checksum(cls, data: bytes) -> int:
         """Calculate CRC64 checksum for the given data."""
         crc = cls()
@@ -93,6 +94,3 @@ def get_hash_buff(cls, buff: bytes) -> List[bytes]:
         hash_val = crc.digest()
 
         return list(struct.pack('>Q', hash_val))
-
-
-print(CRC64.get_hash_buff('Hello, World!'))