scanoss 1.26.3__tar.gz → 1.27.1__tar.gz

{scanoss-1.26.3/src/scanoss.egg-info → scanoss-1.27.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: scanoss
-Version: 1.26.3
+Version: 1.27.1
 Summary: Simple Python library to leverage the SCANOSS APIs
 Home-page: https://scanoss.com
 Author: SCANOSS

{scanoss-1.26.3 → scanoss-1.27.1}/src/scanoss/__init__.py

@@ -22,4 +22,4 @@ SPDX-License-Identifier: MIT
   THE SOFTWARE.
 """
 
-__version__ = '1.26.3'
+__version__ = '1.27.1'

scanoss-1.27.1/src/scanoss/api/scanning/v2/scanoss_scanning_pb2.py

@@ -0,0 +1,49 @@
+# -*- coding: utf-8 -*-
+# Generated by the protocol buffer compiler.  DO NOT EDIT!
+# source: scanoss/api/scanning/v2/scanoss-scanning.proto
+"""Generated protocol buffer code."""
+from google.protobuf.internal import builder as _builder
+from google.protobuf import descriptor as _descriptor
+from google.protobuf import descriptor_pool as _descriptor_pool
+from google.protobuf import symbol_database as _symbol_database
+# @@protoc_insertion_point(imports)
+
+_sym_db = _symbol_database.Default()
+
+
+from scanoss.api.common.v2 import scanoss_common_pb2 as scanoss_dot_api_dot_common_dot_v2_dot_scanoss__common__pb2
+from google.api import annotations_pb2 as google_dot_api_dot_annotations__pb2
+from protoc_gen_swagger.options import annotations_pb2 as protoc__gen__swagger_dot_options_dot_annotations__pb2
+
+
+DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n.scanoss/api/scanning/v2/scanoss-scanning.proto\x12\x17scanoss.api.scanning.v2\x1a*scanoss/api/common/v2/scanoss-common.proto\x1a\x1cgoogle/api/annotations.proto\x1a,protoc-gen-swagger/options/annotations.proto\"\xc5\x03\n\nHFHRequest\x12:\n\x04root\x18\x01 \x01(\x0b\x32,.scanoss.api.scanning.v2.HFHRequest.Children\x12\x16\n\x0erank_threshold\x18\x02 \x01(\x05\x12\x10\n\x08\x63\x61tegory\x18\x03 \x01(\t\x12\x13\n\x0bquery_limit\x18\x04 \x01(\x05\x1a\xbb\x02\n\x08\x43hildren\x12\x0f\n\x07path_id\x18\x01 \x01(\t\x12\x16\n\x0esim_hash_names\x18\x02 \x01(\t\x12\x18\n\x10sim_hash_content\x18\x03 \x01(\t\x12>\n\x08\x63hildren\x18\x04 \x03(\x0b\x32,.scanoss.api.scanning.v2.HFHRequest.Children\x12\x1a\n\x12sim_hash_dir_names\x18\x05 \x01(\t\x12Y\n\x0flang_extensions\x18\x06 \x03(\x0b\x32@.scanoss.api.scanning.v2.HFHRequest.Children.LangExtensionsEntry\x1a\x35\n\x13LangExtensionsEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\x05:\x02\x38\x01\"\xa3\x03\n\x0bHFHResponse\x12<\n\x07results\x18\x01 \x03(\x0b\x32+.scanoss.api.scanning.v2.HFHResponse.Result\x12\x35\n\x06status\x18\x02 \x01(\x0b\x32%.scanoss.api.common.v2.StatusResponse\x1a)\n\x07Version\x12\x0f\n\x07version\x18\x01 \x01(\t\x12\r\n\x05score\x18\x02 \x01(\x02\x1a\x94\x01\n\tComponent\x12\x0c\n\x04purl\x18\x01 \x01(\t\x12\x0c\n\x04name\x18\x02 \x01(\t\x12\x0e\n\x06vendor\x18\x03 \x01(\t\x12>\n\x08versions\x18\x04 \x03(\x0b\x32,.scanoss.api.scanning.v2.HFHResponse.Version\x12\x0c\n\x04rank\x18\x05 \x01(\x05\x12\r\n\x05order\x18\x06 \x01(\x05\x1a]\n\x06Result\x12\x0f\n\x07path_id\x18\x01 \x01(\t\x12\x42\n\ncomponents\x18\x02 \x03(\x0b\x32..scanoss.api.scanning.v2.HFHResponse.Component2\x81\x02\n\x08Scanning\x12q\n\x04\x45\x63ho\x12\".scanoss.api.common.v2.EchoRequest\x1a#.scanoss.api.common.v2.EchoResponse\" \x82\xd3\xe4\x93\x02\x1a\"\x15/api/v2/scanning/echo:\x01*\x12\x81\x01\n\x0e\x46olderHashScan\x12#.scanoss.api.scanning.v2.HFHRequest\x1a$.scanoss.api.scanning.v2.HFHResponse\"$\x82\xd3\xe4\x93\x02\x1e\"\x19/api/v2/scanning/hfh/scan:\x01*B\x8a\x02Z1github.com/scanoss/papi/api/scanningv2;scanningv2\x92\x41\xd3\x01\x12m\n\x18SCANOSS Scanning Service\"L\n\x10scanoss-scanning\x12#https://github.com/scanoss/scanning\x1a\x13support@scanoss.com2\x03\x32.0*\x01\x01\x32\x10\x61pplication/json:\x10\x61pplication/jsonR;\n\x03\x34\x30\x34\x12\x34\n*Returned when the resource does not exist.\x12\x06\n\x04\x9a\x02\x01\x07\x62\x06proto3')
+
+_globals = globals()
+_builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, _globals)
+_builder.BuildTopDescriptorsAndMessages(DESCRIPTOR, 'scanoss.api.scanning.v2.scanoss_scanning_pb2', _globals)
+if not _descriptor._USE_C_DESCRIPTORS:
+  _globals['DESCRIPTOR']._loaded_options = None
+  _globals['DESCRIPTOR']._serialized_options = b'Z1github.com/scanoss/papi/api/scanningv2;scanningv2\222A\323\001\022m\n\030SCANOSS Scanning Service\"L\n\020scanoss-scanning\022#https://github.com/scanoss/scanning\032\023support@scanoss.com2\0032.0*\001\0012\020application/json:\020application/jsonR;\n\003404\0224\n*Returned when the resource does not exist.\022\006\n\004\232\002\001\007'
+  _globals['_HFHREQUEST_CHILDREN_LANGEXTENSIONSENTRY']._loaded_options = None
+  _globals['_HFHREQUEST_CHILDREN_LANGEXTENSIONSENTRY']._serialized_options = b'8\001'
+  _globals['_SCANNING'].methods_by_name['Echo']._loaded_options = None
+  _globals['_SCANNING'].methods_by_name['Echo']._serialized_options = b'\202\323\344\223\002\032\"\025/api/v2/scanning/echo:\001*'
+  _globals['_SCANNING'].methods_by_name['FolderHashScan']._loaded_options = None
+  _globals['_SCANNING'].methods_by_name['FolderHashScan']._serialized_options = b'\202\323\344\223\002\036\"\031/api/v2/scanning/hfh/scan:\001*'
+  _globals['_HFHREQUEST']._serialized_start=196
+  _globals['_HFHREQUEST']._serialized_end=649
+  _globals['_HFHREQUEST_CHILDREN']._serialized_start=334
+  _globals['_HFHREQUEST_CHILDREN']._serialized_end=649
+  _globals['_HFHREQUEST_CHILDREN_LANGEXTENSIONSENTRY']._serialized_start=596
+  _globals['_HFHREQUEST_CHILDREN_LANGEXTENSIONSENTRY']._serialized_end=649
+  _globals['_HFHRESPONSE']._serialized_start=652
+  _globals['_HFHRESPONSE']._serialized_end=1071
+  _globals['_HFHRESPONSE_VERSION']._serialized_start=784
+  _globals['_HFHRESPONSE_VERSION']._serialized_end=825
+  _globals['_HFHRESPONSE_COMPONENT']._serialized_start=828
+  _globals['_HFHRESPONSE_COMPONENT']._serialized_end=976
+  _globals['_HFHRESPONSE_RESULT']._serialized_start=978
+  _globals['_HFHRESPONSE_RESULT']._serialized_end=1071
+  _globals['_SCANNING']._serialized_start=1074
+  _globals['_SCANNING']._serialized_end=1331
+# @@protoc_insertion_point(module_scope)

{scanoss-1.26.3 → scanoss-1.27.1}/src/scanoss/cli.py

@@ -54,6 +54,7 @@ from . import __version__
 from .components import Components
 from .constants import (
     DEFAULT_API_TIMEOUT,
+    DEFAULT_HFH_RANK_THRESHOLD,
     DEFAULT_POST_SIZE,
     DEFAULT_RETRY,
     DEFAULT_TIMEOUT,
@@ -623,24 +624,16 @@ def setup_args() -> None:  # noqa: PLR0912, PLR0915
         '--format',
         '-f',
         type=str,
-        choices=['json'],
+        choices=['json', 'cyclonedx'],
         default='json',
         help='Result output format (optional - default: json)',
     )
     p_folder_scan.add_argument(
-        '--best-match',
-        '-bm',
-        action='store_true',
-        default=False,
-        help='Enable best match mode (optional - default: False)',
-    )
-    p_folder_scan.add_argument(
-        '--threshold',
+        '--rank-threshold',
         type=int,
-        choices=range(1, 101),
-        metavar='1-100',
-        default=100,
-        help='Threshold for result matching (optional - default: 100)',
+        default=DEFAULT_HFH_RANK_THRESHOLD,
+        help='Filter results to only show those with rank value at or below this threshold (e.g., --rank-threshold 3 '
+        'returns results with rank 1, 2, or 3). Lower rank values indicate higher quality matches.',
     )
     p_folder_scan.set_defaults(func=folder_hashing_scan)
 
@@ -1455,7 +1448,7 @@ def utils_certloc(*_):
     Run the "utils certloc" sub-command
     :param _: ignored/unused
     """
-    import certifi # noqa: PLC0415,I001
+    import certifi  # noqa: PLC0415,I001
 
     print(f'CA Cert File: {certifi.where()}')
 
@@ -1466,11 +1459,11 @@ def utils_cert_download(_, args):  # pylint: disable=PLR0912 # noqa: PLR0912
     :param _: ignore/unused
     :param args: Parsed arguments
     """
-    import socket # noqa: PLC0415,I001
-    import traceback # noqa: PLC0415,I001
-    from urllib.parse import urlparse # noqa: PLC0415,I001
+    import socket  # noqa: PLC0415,I001
+    import traceback  # noqa: PLC0415,I001
+    from urllib.parse import urlparse  # noqa: PLC0415,I001
 
-    from OpenSSL import SSL, crypto # noqa: PLC0415,I001
+    from OpenSSL import SSL, crypto  # noqa: PLC0415,I001
 
     file = sys.stdout
     if args.output:
@@ -1518,7 +1511,7 @@ def utils_pac_proxy(_, args):
     :param _: ignore/unused
     :param args: Parsed arguments
     """
-    from pypac.resolver import ProxyResolver # noqa: PLC0415,I001
+    from pypac.resolver import ProxyResolver  # noqa: PLC0415,I001
 
     if not args.pac:
         print_stderr('Error: No pac file option specified.')
@@ -1592,7 +1585,7 @@ def crypto_algorithms(parser, args):
         sys.exit(1)
     except Exception as e:
         if args.debug:
-            import traceback # noqa: PLC0415,I001
+            import traceback  # noqa: PLC0415,I001
 
             traceback.print_exc()
         print_stderr(f'ERROR: {e}')
@@ -1634,7 +1627,7 @@ def crypto_hints(parser, args):
         sys.exit(1)
     except Exception as e:
         if args.debug:
-            import traceback # noqa: PLC0415,I001
+            import traceback  # noqa: PLC0415,I001
 
             traceback.print_exc()
         print_stderr(f'ERROR: {e}')
@@ -1676,7 +1669,7 @@ def crypto_versions_in_range(parser, args):
         sys.exit(1)
     except Exception as e:
         if args.debug:
-            import traceback # noqa: PLC0415,I001
+            import traceback  # noqa: PLC0415,I001
 
             traceback.print_exc()
         print_stderr(f'ERROR: {e}')
@@ -1965,11 +1958,9 @@ def folder_hashing_scan(parser, args):
             config=scanner_config,
             client=client,
             scanoss_settings=scanoss_settings,
+            rank_threshold=args.rank_threshold,
         )
 
-        scanner.best_match = args.best_match
-        scanner.threshold = args.threshold
-
         if scanner.scan():
             scanner.present(output_file=args.output, output_format=args.format)
     except ScanossGrpcError as e:

{scanoss-1.26.3 → scanoss-1.27.1}/src/scanoss/constants.py

@@ -12,3 +12,5 @@ DEFAULT_URL = 'https://api.osskb.org'  # default free service URL
 DEFAULT_URL2 = 'https://api.scanoss.com'  # default premium service URL
 
 DEFAULT_API_TIMEOUT = 600
+
+DEFAULT_HFH_RANK_THRESHOLD = 5

{scanoss-1.26.3 → scanoss-1.27.1}/src/scanoss/cyclonedx.py

@@ -22,14 +22,13 @@ SPDX-License-Identifier: MIT
   THE SOFTWARE.
 """
 
+import datetime
 import json
 import os.path
 import sys
 import uuid
-import datetime
 
 from . import __version__
-
 from .scanossbase import ScanossBase
 from .spdxlite import SpdxLite
 
@@ -49,7 +48,7 @@ class CycloneDx(ScanossBase):
         self.debug = debug
         self._spdx = SpdxLite(debug=debug)
 
-    def parse(self, data: json):
+    def parse(self, data: json):  # noqa: PLR0912, PLR0915
         """
         Parse the given input (raw/plain) JSON string and return CycloneDX summary
         :param data: json - JSON object
@@ -58,7 +57,7 @@ class CycloneDx(ScanossBase):
         if not data:
             self.print_stderr('ERROR: No JSON data provided to parse.')
             return None, None
-        self.print_debug(f'Processing raw results into CycloneDX format...')
+        self.print_debug('Processing raw results into CycloneDX format...')
         cdx = {}
         vdx = {}
         for f in data:
@@ -171,17 +170,22 @@ class CycloneDx(ScanossBase):
             success = self.produce_from_str(f.read(), output_file)
         return success
 
-    def produce_from_json(self, data: json, output_file: str = None) -> bool:
+    def produce_from_json(self, data: json, output_file: str = None) -> tuple[bool, json]:  # noqa: PLR0912
         """
-        Produce the CycloneDX output from the input data
-        :param data: JSON object
-        :param output_file: Output file (optional)
-        :return: True if successful, False otherwise
+        Produce the CycloneDX output from the raw scan results input data
+
+        Args:
+            data (json): JSON object
+            output_file (str, optional): Output file (optional). Defaults to None.
+
+        Returns:
+            bool: True if successful, False otherwise
+            json: The CycloneDX output
         """
         cdx, vdx = self.parse(data)
         if not cdx:
             self.print_stderr('ERROR: No CycloneDX data returned for the JSON string provided.')
-            return False
+            return False, None
         self._spdx.load_license_data()  # Load SPDX license name data for later reference
         #
         # Using CDX version 1.4: https://cyclonedx.org/docs/1.4/json/
@@ -264,7 +268,7 @@ class CycloneDx(ScanossBase):
         if output_file:
             file.close()
 
-        return True
+        return True, data
 
     def produce_from_str(self, json_str: str, output_file: str = None) -> bool:
         """

scanoss-1.27.1/src/scanoss/data/build_date.txt

@@ -0,0 +1 @@
+date: 20250709092546, utime: 1752053146

{scanoss-1.26.3 → scanoss-1.27.1}/src/scanoss/file_filters.py

@@ -25,7 +25,7 @@ SPDX-License-Identifier: MIT
 import os
 import sys
 from pathlib import Path
-from typing import List
+from typing import List, Optional
 
 from pathspec import GitIgnoreSpec
 
@@ -511,7 +511,7 @@ class FileFilters(ScanossBase):
         # Now filter the files and return the reduced list
         return self.get_filtered_files_from_files(all_files, str(root_path))
 
-    def get_filtered_files_from_files(self, files: List[str], scan_root: str = None) -> List[str]:
+    def get_filtered_files_from_files(self, files: List[str], scan_root: Optional[str] = None) -> List[str]:
         """
         Retrieve a list of files to scan or fingerprint from a given list of files based on filter settings.
 
@@ -615,8 +615,13 @@ class FileFilters(ScanossBase):
         # Default patterns for skipping directories
         if not self.all_folders:
             DEFAULT_SKIPPED_DIR_LIST = DEFAULT_SKIPPED_DIRS_HFH if self.is_folder_hashing_scan else DEFAULT_SKIPPED_DIRS
+            DEFAULT_SKIPPED_DIR_EXT_LIST = (
+                DEFAULT_SKIPPED_DIR_EXT_HFH if self.is_folder_hashing_scan else DEFAULT_SKIPPED_DIR_EXT
+            )
             for dir_name in DEFAULT_SKIPPED_DIR_LIST:
                 patterns.append(f'{dir_name}/')
+            for dir_extension in DEFAULT_SKIPPED_DIR_EXT_LIST:
+                patterns.append(f'*{dir_extension}/')
 
         # Custom patterns added in SCANOSS settings file
         if self.scanoss_settings:

{scanoss-1.26.3 → scanoss-1.27.1}/src/scanoss/scanner.py

@@ -22,40 +22,40 @@ SPDX-License-Identifier: MIT
   THE SOFTWARE.
 """
 
+import datetime
 import json
 import os
-from pathlib import Path
 import sys
-import datetime
+from pathlib import Path
 from typing import Any, Dict, List, Optional
-import importlib_resources
 
+import importlib_resources
 from progress.bar import Bar
 from progress.spinner import Spinner
 from pypac.parser import PACFile
 
 from scanoss.file_filters import FileFilters
 
-from .scanossapi import ScanossApi
-from .cyclonedx import CycloneDx
-from .spdxlite import SpdxLite
+from . import __version__
 from .csvoutput import CsvOutput
-from .threadedscanning import ThreadedScanning
+from .cyclonedx import CycloneDx
 from .scancodedeps import ScancodeDeps
-from .threadeddependencies import ThreadedDependencies, SCOPE
-from .scanossgrpc import ScanossGrpc
-from .scantype import ScanType
-from .scanossbase import ScanossBase
 from .scanoss_settings import ScanossSettings
+from .scanossapi import ScanossApi
+from .scanossbase import ScanossBase
+from .scanossgrpc import ScanossGrpc
 from .scanpostprocessor import ScanPostProcessor
-from . import __version__
+from .scantype import ScanType
+from .spdxlite import SpdxLite
+from .threadeddependencies import SCOPE, ThreadedDependencies
+from .threadedscanning import ThreadedScanning
 
 FAST_WINNOWING = False
 try:
     from scanoss_winnowing.winnowing import Winnowing
 
     FAST_WINNOWING = True
-except ModuleNotFoundError or ImportError:
+except (ModuleNotFoundError, ImportError):
     FAST_WINNOWING = False
     from .winnowing import Winnowing
 
@@ -284,7 +284,7 @@ class Scanner(ScanossBase):
             return True
         return False
 
-    def scan_folder_with_options(
+    def scan_folder_with_options(  # noqa: PLR0913
         self,
         scan_dir: str,
         deps_file: str = None,
@@ -332,7 +332,7 @@ class Scanner(ScanossBase):
                 success = False
         return success
 
-    def scan_folder(self, scan_dir: str) -> bool:
+    def scan_folder(self, scan_dir: str) -> bool:  # noqa: PLR0912, PLR0915
         """
         Scan the specified folder producing fingerprints, send to the SCANOSS API and return results
 
@@ -400,7 +400,7 @@ class Scanner(ScanossBase):
                 scan_block += wfp
                 scan_size = len(scan_block.encode('utf-8'))
                 wfp_file_count += 1
-                # If the scan request block (group of WFPs) or larger than the POST size or we have reached the file limit, add it to the queue
+                # If the scan request block (group of WFPs) or larger than the POST size or we have reached the file limit, add it to the queue  # noqa: E501
                 if wfp_file_count > self.post_file_count or scan_size >= self.max_post_size:
                     self.threaded_scan.queue_add(scan_block)
                     queue_size += 1
@@ -484,7 +484,7 @@ class Scanner(ScanossBase):
             self.__log_result(json.dumps(results, indent=2, sort_keys=True))
         elif self.output_format == 'cyclonedx':
             cdx = CycloneDx(self.debug, self.scan_output)
-            success = cdx.produce_from_json(results)
+            success, _ = cdx.produce_from_json(results)
         elif self.output_format == 'spdxlite':
             spdxlite = SpdxLite(self.debug, self.scan_output)
             success = spdxlite.produce_from_json(results)
@@ -509,7 +509,7 @@ class Scanner(ScanossBase):
             for response in scan_responses:
                 if response is not None:
                     if file_map:
-                        response = self._deobfuscate_filenames(response, file_map)
+                        response = self._deobfuscate_filenames(response, file_map)  # noqa: PLW2901
                     results.update(response)
 
         dep_files = dep_responses.get('files', None) if dep_responses else None
@@ -532,7 +532,7 @@ class Scanner(ScanossBase):
                 deobfuscated[key] = value
         return deobfuscated
 
-    def scan_file_with_options(
+    def scan_file_with_options(  # noqa: PLR0913
         self,
         file: str,
         deps_file: str = None,
@@ -603,7 +603,7 @@ class Scanner(ScanossBase):
             success = False
         return success
 
-    def scan_files(self, files: []) -> bool:
+    def scan_files(self, files: []) -> bool:  # noqa: PLR0912, PLR0915
         """
         Scan the specified list of files, producing fingerprints, send to the SCANOSS API and return results
         Please note that by providing an explicit list you bypass any exclusions that may be defined on the scanner
@@ -657,7 +657,7 @@ class Scanner(ScanossBase):
             file_count += 1
             if self.threaded_scan:
                 wfp_size = len(wfp.encode('utf-8'))
-                # If the WFP is bigger than the max post size and we already have something stored in the scan block, add it to the queue
+                # If the WFP is bigger than the max post size and we already have something stored in the scan block, add it to the queue  # noqa: E501
                 if scan_block != '' and (wfp_size + scan_size) >= self.max_post_size:
                     self.threaded_scan.queue_add(scan_block)
                     queue_size += 1
@@ -666,7 +666,7 @@ class Scanner(ScanossBase):
                 scan_block += wfp
                 scan_size = len(scan_block.encode('utf-8'))
                 wfp_file_count += 1
-                # If the scan request block (group of WFPs) or larger than the POST size or we have reached the file limit, add it to the queue
+                # If the scan request block (group of WFPs) or larger than the POST size or we have reached the file limit, add it to the queue  # noqa: E501
                 if wfp_file_count > self.post_file_count or scan_size >= self.max_post_size:
                     self.threaded_scan.queue_add(scan_block)
                     queue_size += 1
@@ -755,7 +755,7 @@ class Scanner(ScanossBase):
                 success = False
         return success
 
-    def scan_wfp_file(self, file: str = None) -> bool:
+    def scan_wfp_file(self, file: str = None) -> bool:  # noqa: PLR0912, PLR0915
         """
         Scan the contents of the specified WFP file (in the current process)
         :param file: Scan the contents of the specified WFP file (in the current process)

{scanoss-1.26.3 → scanoss-1.27.1}/src/scanoss/scanners/container_scanner.py

@@ -436,10 +436,12 @@ class ContainerScannerPresenter(AbstractPresenter):
         scan_results = {}
         for f in self.scanner.decorated_scan_results['files']:
             scan_results[f['file']] = [f]
-        if not cdx.produce_from_json(scan_results, self.output_file):
+        success, cdx_output = cdx.produce_from_json(scan_results)
+        if not success:
             error_msg = 'Failed to produce CycloneDX output'
             self.base.print_stderr(error_msg)
-            raise ValueError(error_msg)
+            return None
+        return json.dumps(cdx_output, indent=2)
 
     def _format_spdxlite_output(self) -> str:
         """

{scanoss-1.26.3 → scanoss-1.27.1}/src/scanoss/scanners/folder_hasher.py

@@ -15,7 +15,7 @@ from scanoss.utils.simhash import WordFeatureSet, fingerprint, simhash, vectoriz
 
 MINIMUM_FILE_COUNT = 8
 MINIMUM_CONCATENATED_NAME_LENGTH = 32
-MINIMUM_FILE_NAME_LENGTH = 32
+MAXIMUM_FILE_NAME_LENGTH = 32
 
 
 class DirectoryNode:
@@ -35,7 +35,7 @@ class DirectoryFile:
     Represents a file in the directory tree for folder hashing.
     """
 
-    def __init__(self, path: str, key: bytes, key_str: str):
+    def __init__(self, path: str, key: List[bytes], key_str: str):
         self.path = path
         self.key = key
         self.key_str = key_str
@@ -77,7 +77,7 @@ class FolderHasher:
     def __init__(
         self,
         scan_dir: str,
-        config: Optional[FolderHasherConfig] = None,
+        config: FolderHasherConfig,
         scanoss_settings: Optional[ScanossSettings] = None,
     ):
         self.base = ScanossBase(
@@ -140,7 +140,7 @@ class FolderHasher:
         root_node = DirectoryNode(str(root))
 
         all_files = [
-            f for f in root.rglob('*') if f.is_file() and len(f.name.encode('utf-8')) <= MINIMUM_FILE_NAME_LENGTH
+            f for f in root.rglob('*') if f.is_file() and len(f.name.encode('utf-8')) <= MAXIMUM_FILE_NAME_LENGTH
         ]
         filtered_files = self.file_filters.get_filtered_files_from_files(all_files, str(root))
 
@@ -185,7 +185,7 @@ class FolderHasher:
         Recursively compute folder hash data for a directory node.
 
         The hash data includes the path identifier, simhash for file names,
-        simhash for file content, and children node hash information.
+        simhash for file content, directory hash, language extensions, and children node hash information.
 
         Args:
             node (DirectoryNode): The directory node to compute the hash for.
@@ -194,11 +194,22 @@ class FolderHasher:
             dict: The computed hash data for the node.
         """
         hash_data = self._hash_calc(node)
+        
+        # Safely calculate relative path
+        try:
+            node_path = Path(node.path).resolve()
+            scan_dir_path = Path(self.scan_dir).resolve()
+            rel_path = node_path.relative_to(scan_dir_path)
+        except ValueError:
+            # If relative_to fails, use the node path as is or a fallback
+            rel_path = Path(node.path).name if node.path else Path('.')
 
         return {
-            'path_id': node.path,
+            'path_id': str(rel_path),
             'sim_hash_names': f'{hash_data["name_hash"]:02x}' if hash_data['name_hash'] is not None else None,
             'sim_hash_content': f'{hash_data["content_hash"]:02x}' if hash_data['content_hash'] is not None else None,
+            'sim_hash_dir_names': f'{hash_data["dir_hash"]:02x}' if hash_data['dir_hash'] is not None else None,
+            'lang_extensions': hash_data['lang_extensions'],
             'children': [self._hash_calc_from_node(child) for child in node.children.values()],
         }
 
@@ -215,9 +226,12 @@ class FolderHasher:
             node (DirectoryNode): The directory node containing file items.
 
         Returns:
-            dict: A dictionary with 'name_hash' and 'content_hash' keys.
+            dict: A dictionary with 'name_hash', 'content_hash', 'dir_hash', and 'lang_extensions' keys.
         """
         processed_hashes = set()
+        unique_file_names = set()
+        unique_directories = set()
+        extension_map = {}
         file_hashes = []
         selected_names = []
 
@@ -225,37 +239,64 @@ class FolderHasher:
             key_str = file.key_str
             if key_str in processed_hashes:
                 continue
-            processed_hashes.add(key_str)
 
-            selected_names.append(os.path.basename(file.path))
+            file_name = os.path.basename(file.path)
+
+            file_name_without_extension, extension = os.path.splitext(file_name)
+            current_directory = os.path.dirname(file.path)
+
+            if extension and len(extension) > 1:
+                ext_without_dot = extension[1:]
+                extension_map[ext_without_dot] = extension_map.get(ext_without_dot, 0) + 1
+
+            current_directory.replace(self.scan_dir, '', 1).lstrip(os.path.sep)
+            parts = current_directory.split(os.path.sep)
+            for d in parts:
+                if d in {'', '.', '..'}:
+                    continue
+                unique_directories.add(d)
 
-            file_key = bytes(file.key)
-            file_hashes.append(file_key)
+            processed_hashes.add(key_str)
+            unique_file_names.add(file_name_without_extension)
+            selected_names.append(file_name)
+            file_hashes.append(file.key)
 
         if len(selected_names) < MINIMUM_FILE_COUNT:
-            return {
-                'name_hash': None,
-                'content_hash': None,
-            }
+            return {'name_hash': None, 'content_hash': None, 'dir_hash': None, 'lang_extensions': None}
 
         selected_names.sort()
         concatenated_names = ''.join(selected_names)
 
         if len(concatenated_names.encode('utf-8')) < MINIMUM_CONCATENATED_NAME_LENGTH:
-            return {
-                'name_hash': None,
-                'content_hash': None,
-            }
+            return {'name_hash': None, 'content_hash': None, 'dir_hash': None, 'lang_extensions': None}
+
+        # Concatenate the unique file names without the extensions, adding a space and sorting them alphabetically
+        unique_file_names_list = list(unique_file_names)
+        unique_file_names_list.sort()
+        concatenated_names = ' '.join(unique_file_names_list)
+
+        # We do the same for the directory names, adding a space and sorting them alphabetically
+        unique_directories_list = list(unique_directories)
+        unique_directories_list.sort()
+        concatenated_directories = ' '.join(unique_directories_list)
 
         names_simhash = simhash(WordFeatureSet(concatenated_names.encode('utf-8')))
+        dir_simhash = simhash(WordFeatureSet(concatenated_directories.encode('utf-8')))
         content_simhash = fingerprint(vectorize_bytes(file_hashes))
 
+        # Debug logging similar to Go implementation
+        self.base.print_debug(f'Unique file names: {unique_file_names_list}')
+        self.base.print_debug(f'Unique directories: {unique_directories_list}')
+        self.base.print_debug(f'{dir_simhash:x}/{names_simhash:x} - {content_simhash:x} - {extension_map}')
+
         return {
             'name_hash': names_simhash,
             'content_hash': content_simhash,
+            'dir_hash': dir_simhash,
+            'lang_extensions': extension_map,
         }
 
-    def present(self, output_format: str = None, output_file: str = None):
+    def present(self, output_format: Optional[str] = None, output_file: Optional[str] = None):
         """Present the hashed tree in the selected format"""
         self.presenter.present(output_format=output_format, output_file=output_file)
 

{scanoss-1.26.3 → scanoss-1.27.1}/src/scanoss/scanners/scanner_hfh.py

@@ -29,6 +29,8 @@ from typing import Dict, Optional
 
 from progress.spinner import Spinner
 
+from scanoss.constants import DEFAULT_HFH_RANK_THRESHOLD
+from scanoss.cyclonedx import CycloneDx
 from scanoss.file_filters import FileFilters
 from scanoss.scanners.folder_hasher import FolderHasher
 from scanoss.scanners.scanner_config import ScannerConfig
@@ -52,6 +54,7 @@ class ScannerHFH:
         config: ScannerConfig,
         client: Optional[ScanossGrpc] = None,
         scanoss_settings: Optional[ScanossSettings] = None,
+        rank_threshold: int = DEFAULT_HFH_RANK_THRESHOLD,
     ):
         """
         Initialize the ScannerHFH.
@@ -61,6 +64,7 @@ class ScannerHFH:
             config (ScannerConfig): Configuration parameters for the scanner.
             client (ScanossGrpc): gRPC client for communicating with the scanning service.
             scanoss_settings (Optional[ScanossSettings]): Optional settings for Scanoss.
+            rank_threshold (int): Get results with rank below this threshold (default: 5).
         """
         self.base = ScanossBase(
             debug=config.debug,
@@ -88,8 +92,7 @@ class ScannerHFH:
         self.scan_dir = scan_dir
         self.client = client
         self.scan_results = None
-        self.best_match = False
-        self.threshold = 100
+        self.rank_threshold = rank_threshold
 
     def scan(self) -> Optional[Dict]:
         """
@@ -100,8 +103,7 @@ class ScannerHFH:
         """
         hfh_request = {
             'root': self.folder_hasher.hash_directory(self.scan_dir),
-            'threshold': self.threshold,
-            'best_match': self.best_match,
+            'rank_threshold': self.rank_threshold,
         }
 
         spinner = Spinner('Scanning folder...')
@@ -160,8 +162,53 @@ class ScannerHFHPresenter(AbstractPresenter):
             else str(self.scanner.scan_results)
         )
 
-    def _format_cyclonedx_output(self) -> str:
-        raise NotImplementedError('CycloneDX output is not implemented')
+    def _format_cyclonedx_output(self) -> str:  # noqa: PLR0911
+        if not self.scanner.scan_results:
+            return ''
+        try:
+            if 'results' not in self.scanner.scan_results or not self.scanner.scan_results['results']:
+                self.base.print_stderr('ERROR: No scan results found')
+                return ''
+
+            first_result = self.scanner.scan_results['results'][0]
+
+            best_match_components = [c for c in first_result.get('components', []) if c.get('order') == 1]
+            if not best_match_components:
+                self.base.print_stderr('ERROR: No best match component found')
+                return ''
+
+            best_match_component = best_match_components[0]
+            if not best_match_component.get('versions'):
+                self.base.print_stderr('ERROR: No versions found for best match component')
+                return ''
+
+            best_match_version = best_match_component['versions'][0]
+            purl = best_match_component['purl']
+
+            get_dependencies_json_request = {
+                'files': [
+                    {
+                        'file': f'{best_match_component["name"]}:{best_match_version["version"]}',
+                        'purls': [{'purl': purl, 'requirement': best_match_version['version']}],
+                    }
+                ]
+            }
+
+            decorated_scan_results = self.scanner.client.get_dependencies(get_dependencies_json_request)
+
+            cdx = CycloneDx(self.base.debug)
+            scan_results = {}
+            for f in decorated_scan_results['files']:
+                scan_results[f['file']] = [f]
+            success, cdx_output = cdx.produce_from_json(scan_results)
+            if not success:
+                error_msg = 'ERROR: Failed to produce CycloneDX output'
+                self.base.print_stderr(error_msg)
+                return None
+            return json.dumps(cdx_output, indent=2)
+        except Exception as e:
+            self.base.print_stderr(f'ERROR: Failed to get license information: {e}')
+            return None
 
     def _format_spdxlite_output(self) -> str:
         raise NotImplementedError('SPDXlite output is not implemented')

{scanoss-1.26.3 → scanoss-1.27.1/src/scanoss.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: scanoss
-Version: 1.26.3
+Version: 1.27.1
 Summary: Simple Python library to leverage the SCANOSS APIs
 Home-page: https://scanoss.com
 Author: SCANOSS

scanoss-1.26.3/src/scanoss/api/scanning/v2/scanoss_scanning_pb2.py

@@ -1,43 +0,0 @@
-# -*- coding: utf-8 -*-
-# Generated by the protocol buffer compiler.  DO NOT EDIT!
-# source: scanoss/api/scanning/v2/scanoss-scanning.proto
-"""Generated protocol buffer code."""
-from google.protobuf.internal import builder as _builder
-from google.protobuf import descriptor as _descriptor
-from google.protobuf import descriptor_pool as _descriptor_pool
-from google.protobuf import symbol_database as _symbol_database
-# @@protoc_insertion_point(imports)
-
-_sym_db = _symbol_database.Default()
-
-
-from scanoss.api.common.v2 import scanoss_common_pb2 as scanoss_dot_api_dot_common_dot_v2_dot_scanoss__common__pb2
-from google.api import annotations_pb2 as google_dot_api_dot_annotations__pb2
-from protoc_gen_swagger.options import annotations_pb2 as protoc__gen__swagger_dot_options_dot_annotations__pb2
-
-
-DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n.scanoss/api/scanning/v2/scanoss-scanning.proto\x12\x17scanoss.api.scanning.v2\x1a*scanoss/api/common/v2/scanoss-common.proto\x1a\x1cgoogle/api/annotations.proto\x1a,protoc-gen-swagger/options/annotations.proto\"\xff\x01\n\nHFHRequest\x12\x12\n\nbest_match\x18\x01 \x01(\x08\x12\x11\n\tthreshold\x18\x02 \x01(\x05\x12:\n\x04root\x18\x03 \x01(\x0b\x32,.scanoss.api.scanning.v2.HFHRequest.Children\x1a\x8d\x01\n\x08\x43hildren\x12\x0f\n\x07path_id\x18\x01 \x01(\t\x12\x16\n\x0esim_hash_names\x18\x02 \x01(\t\x12\x18\n\x10sim_hash_content\x18\x03 \x01(\t\x12>\n\x08\x63hildren\x18\x04 \x03(\x0b\x32,.scanoss.api.scanning.v2.HFHRequest.Children\"\xc1\x02\n\x0bHFHResponse\x12<\n\x07results\x18\x01 \x03(\x0b\x32+.scanoss.api.scanning.v2.HFHResponse.Result\x12\x35\n\x06status\x18\x02 \x01(\x0b\x32%.scanoss.api.common.v2.StatusResponse\x1a\x39\n\tComponent\x12\x0c\n\x04purl\x18\x01 \x01(\t\x12\x10\n\x08versions\x18\x02 \x03(\t\x12\x0c\n\x04rank\x18\x03 \x01(\x05\x1a\x81\x01\n\x06Result\x12\x0f\n\x07path_id\x18\x01 \x01(\t\x12\x42\n\ncomponents\x18\x02 \x03(\x0b\x32..scanoss.api.scanning.v2.HFHResponse.Component\x12\x13\n\x0bprobability\x18\x03 \x01(\x02\x12\r\n\x05stage\x18\x04 \x01(\x05\x32\x81\x02\n\x08Scanning\x12q\n\x04\x45\x63ho\x12\".scanoss.api.common.v2.EchoRequest\x1a#.scanoss.api.common.v2.EchoResponse\" \x82\xd3\xe4\x93\x02\x1a\"\x15/api/v2/scanning/echo:\x01*\x12\x81\x01\n\x0e\x46olderHashScan\x12#.scanoss.api.scanning.v2.HFHRequest\x1a$.scanoss.api.scanning.v2.HFHResponse\"$\x82\xd3\xe4\x93\x02\x1e\"\x19/api/v2/scanning/hfh/scan:\x01*B\x8a\x02Z1github.com/scanoss/papi/api/scanningv2;scanningv2\x92\x41\xd3\x01\x12m\n\x18SCANOSS Scanning Service\"L\n\x10scanoss-scanning\x12#https://github.com/scanoss/scanning\x1a\x13support@scanoss.com2\x03\x32.0*\x01\x01\x32\x10\x61pplication/json:\x10\x61pplication/jsonR;\n\x03\x34\x30\x34\x12\x34\n*Returned when the resource does not exist.\x12\x06\n\x04\x9a\x02\x01\x07\x62\x06proto3')
-
-_builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, globals())
-_builder.BuildTopDescriptorsAndMessages(DESCRIPTOR, 'scanoss.api.scanning.v2.scanoss_scanning_pb2', globals())
-if _descriptor._USE_C_DESCRIPTORS == False:
-
-  DESCRIPTOR._options = None
-  DESCRIPTOR._serialized_options = b'Z1github.com/scanoss/papi/api/scanningv2;scanningv2\222A\323\001\022m\n\030SCANOSS Scanning Service\"L\n\020scanoss-scanning\022#https://github.com/scanoss/scanning\032\023support@scanoss.com2\0032.0*\001\0012\020application/json:\020application/jsonR;\n\003404\0224\n*Returned when the resource does not exist.\022\006\n\004\232\002\001\007'
-  _SCANNING.methods_by_name['Echo']._options = None
-  _SCANNING.methods_by_name['Echo']._serialized_options = b'\202\323\344\223\002\032\"\025/api/v2/scanning/echo:\001*'
-  _SCANNING.methods_by_name['FolderHashScan']._options = None
-  _SCANNING.methods_by_name['FolderHashScan']._serialized_options = b'\202\323\344\223\002\036\"\031/api/v2/scanning/hfh/scan:\001*'
-  _HFHREQUEST._serialized_start=196
-  _HFHREQUEST._serialized_end=451
-  _HFHREQUEST_CHILDREN._serialized_start=310
-  _HFHREQUEST_CHILDREN._serialized_end=451
-  _HFHRESPONSE._serialized_start=454
-  _HFHRESPONSE._serialized_end=775
-  _HFHRESPONSE_COMPONENT._serialized_start=586
-  _HFHRESPONSE_COMPONENT._serialized_end=643
-  _HFHRESPONSE_RESULT._serialized_start=646
-  _HFHRESPONSE_RESULT._serialized_end=775
-  _SCANNING._serialized_start=778
-  _SCANNING._serialized_end=1035
-# @@protoc_insertion_point(module_scope)

scanoss-1.26.3/src/scanoss/data/build_date.txt

@@ -1 +0,0 @@
-date: 20250626171827, utime: 1750958307