scanoss 1.40.0__py3-none-any.whl → 1.41.0__py3-none-any.whl

scanoss/inspection/{policy_check.py → policy_check/policy_check.py}

@@ -22,12 +22,12 @@ SPDX-License-Identifier: MIT
   THE SOFTWARE.
 """
 
-from abc import abstractmethod
+from abc import ABC, abstractmethod
 from enum import Enum
-from typing import Any, Callable, Dict, Generic, List, TypeVar
+from typing import Callable, Dict, Generic, List, NamedTuple, TypeVar
 
-from ..scanossbase import ScanossBase
-from .utils.license_utils import LicenseUtil
+from ...scanossbase import ScanossBase
+from ..utils.license_utils import LicenseUtil
 
 
 class PolicyStatus(Enum):
@@ -46,9 +46,13 @@ class PolicyStatus(Enum):
 # End of PolicyStatus Class
 #
 
+class PolicyOutput(NamedTuple):
+    details: str
+    summary: str
+
 T = TypeVar('T')
 
-class PolicyCheck(ScanossBase, Generic[T]):
+class PolicyCheck(ScanossBase, Generic[T], ABC):
     """
     A base class for implementing various software policy checks.
 
@@ -80,7 +84,7 @@ class PolicyCheck(ScanossBase, Generic[T]):
         self.output = output
 
     @abstractmethod
-    def run(self):
+    def run(self)-> tuple[int,PolicyOutput]:
         """
         Execute the policy check process.
 
@@ -91,14 +95,14 @@ class PolicyCheck(ScanossBase, Generic[T]):
         3. Formatting the results
         4. Saving the output to files if required
 
-        :return: A tuple containing:
+        :return: A named tuple containing two elements:
                  - First element: PolicyStatus enum value (SUCCESS, FAIL, or ERROR)
-                 - Second element: Dictionary containing the inspection results
+                 - Second element: PolicyOutput A tuple containing the policy results.
         """
         pass
 
     @abstractmethod
-    def _json(self, data: list[T]) -> Dict[str, Any]:
+    def _json(self, data: list[T]) -> PolicyOutput:
         """
         Format the policy checks results as JSON.
         This method should be implemented by subclasses to create a Markdown representation
@@ -112,7 +116,7 @@ class PolicyCheck(ScanossBase, Generic[T]):
         pass
 
     @abstractmethod
-    def _markdown(self, data: list[T]) -> Dict[str, Any]:
+    def _markdown(self, data: list[T]) -> PolicyOutput:
         """
         Generate Markdown output for the policy check results.
 
@@ -125,7 +129,7 @@ class PolicyCheck(ScanossBase, Generic[T]):
         pass
 
     @abstractmethod
-    def _jira_markdown(self, data: list[T]) -> Dict[str, Any]:
+    def _jira_markdown(self, data: list[T]) -> PolicyOutput:
         """
         Generate Markdown output for the policy check results.
 
@@ -137,7 +141,7 @@ class PolicyCheck(ScanossBase, Generic[T]):
         """
         pass
 
-    def _get_formatter(self) -> Callable[[List[dict]], Dict[str, Any]] or None:
+    def _get_formatter(self) -> Callable[[List[dict]], PolicyOutput]:
         """
         Get the appropriate formatter function based on the specified format.
 
@@ -145,7 +149,7 @@ class PolicyCheck(ScanossBase, Generic[T]):
         """
         valid_format = self._is_valid_format()
         if not valid_format:
-            return None
+            raise ValueError('Invalid format specified')
         # a map of which format function to return
         function_map = {
             'json': self._json,
@@ -205,14 +209,14 @@ class PolicyCheck(ScanossBase, Generic[T]):
         if formatter is None:
             return PolicyStatus.ERROR.value, {}
         # Format the results
-        data = formatter(components)
+        policy_output = formatter(components)
         ## Save outputs if required
-        self.print_to_file_or_stdout(data['details'], self.output)
-        self.print_to_file_or_stderr(data['summary'], self.status)
+        self.print_to_file_or_stdout(policy_output.details, self.output)
+        self.print_to_file_or_stderr(policy_output.summary, self.status)
         # Check to see if we have policy violations
         if len(components) > 0:
-            return PolicyStatus.POLICY_FAIL.value, data
-        return PolicyStatus.POLICY_SUCCESS.value, data
+            return PolicyStatus.POLICY_FAIL.value, policy_output
+        return PolicyStatus.POLICY_SUCCESS.value, policy_output
 #
 # End of PolicyCheck Class
 #

scanoss/inspection/{raw → policy_check/scanoss}/copyleft.py

@@ -24,11 +24,13 @@ SPDX-License-Identifier: MIT
 
 import json
 from dataclasses import dataclass
-from typing import Any, Dict, List
+from typing import Dict, List
 
-from ..policy_check import PolicyStatus
-from ..utils.markdown_utils import generate_jira_table, generate_table
-from .raw_base import RawBase
+from scanoss.constants import DEFAULT_COPYLEFT_LICENSE_SOURCES
+
+from ...policy_check.policy_check import PolicyCheck, PolicyOutput, PolicyStatus
+from ...utils.markdown_utils import generate_jira_table, generate_table
+from ...utils.scan_result_processor import ScanResultProcessor
 
 
 @dataclass
@@ -45,7 +47,7 @@ class Component:
     licenses: List[License]
     status: str
 
-class Copyleft(RawBase[Component]):
+class Copyleft(PolicyCheck[Component]):
     """
     SCANOSS Copyleft class
     Inspects components for copyleft licenses
@@ -63,6 +65,7 @@ class Copyleft(RawBase[Component]):
         include: str = None,
         exclude: str = None,
         explicit: str = None,
+        license_sources: list = None,
     ):
         """
         Initialise the Copyleft class.
@@ -77,18 +80,27 @@ class Copyleft(RawBase[Component]):
         :param include: Licenses to include in the analysis
         :param exclude: Licenses to exclude from the analysis
         :param explicit: Explicitly defined licenses
+        :param license_sources: List of license sources to check
         """
-        super().__init__(debug, trace, quiet, format_type,filepath, output ,status, name='Copyleft Policy')
+        super().__init__(
+            debug, trace, quiet, format_type, status, name='Copyleft Policy', output=output
+        )
         self.license_util.init(include, exclude, explicit)
         self.filepath = filepath
-        self.format = format
         self.output = output
         self.status = status
-        self.include = include
-        self.exclude = exclude
-        self.explicit = explicit
-
-    def _json(self, components: list[Component]) -> Dict[str, Any]:
+        self.license_sources = license_sources or DEFAULT_COPYLEFT_LICENSE_SOURCES
+        self.results_processor = ScanResultProcessor(
+            self.debug,
+            self.trace,
+            self.quiet,
+            self.filepath,
+            include,
+            exclude,
+            explicit,
+            self.license_sources)
+
+    def _json(self, components: list[Component]) -> PolicyOutput:
         """
         Format the components with copyleft licenses as JSON.
 
@@ -96,16 +108,16 @@ class Copyleft(RawBase[Component]):
         :return: Dictionary with formatted JSON details and summary
         """
         # A component is considered unique by its combination of PURL (Package URL) and license
-        component_licenses = self._group_components_by_license(components)
+        component_licenses = self.results_processor.group_components_by_license(components)
         details = {}
         if len(components) > 0:
             details = {'components': components}
-        return {
-            'details': f'{json.dumps(details, indent=2)}\n',
-            'summary': f'{len(component_licenses)} component(s) with copyleft licenses were found.\n',
-        }
+        return PolicyOutput(
+            details= f'{json.dumps(details, indent=2)}\n',
+            summary= f'{len(component_licenses)} component(s) with copyleft licenses were found.\n',
+        )
 
-    def _markdown(self, components: list[Component]) -> Dict[str, Any]:
+    def _markdown(self, components: list[Component]) -> PolicyOutput:
         """
         Format the components with copyleft licenses as Markdown.
 
@@ -114,7 +126,7 @@ class Copyleft(RawBase[Component]):
         """
         return self._md_summary_generator(components, generate_table)
 
-    def _jira_markdown(self, components: list[Component]) -> Dict[str, Any]:
+    def _jira_markdown(self, components: list[Component]) -> PolicyOutput:
         """
         Format the components with copyleft licenses as Markdown.
 
@@ -123,7 +135,7 @@ class Copyleft(RawBase[Component]):
         """
         return self._md_summary_generator(components, generate_jira_table)
 
-    def _md_summary_generator(self, components: list[Component], table_generator):
+    def _md_summary_generator(self, components: list[Component], table_generator) -> PolicyOutput:
         """
         Generates a Markdown summary for components with a focus on copyleft licenses.
 
@@ -138,15 +150,10 @@ class Copyleft(RawBase[Component]):
             A callable function to generate tabular data for components.
 
         Returns:
-        dict
-            A dictionary containing two keys:
-            - 'details': A detailed Markdown representation including a table of components
-              and associated copyleft license data.
-            - 'summary': A textual summary highlighting the total number of components
-              with copyleft licenses.
+            PolicyOutput
         """
         # A component is considered unique by its combination of PURL (Package URL) and license
-        component_licenses = self._group_components_by_license(components)
+        component_licenses = self.results_processor.group_components_by_license(components)
         headers = ['Component', 'License', 'URL', 'Copyleft']
         centered_columns = [1, 4]
         rows = []
@@ -160,10 +167,10 @@ class Copyleft(RawBase[Component]):
             rows.append(row)
         # End license loop
         # End component loop
-        return {
-            'details': f'### Copyleft Licenses\n{table_generator(headers, rows, centered_columns)}',
-            'summary': f'{len(component_licenses)} component(s) with copyleft licenses were found.\n',
-        }
+        return PolicyOutput(
+            details= f'### Copyleft Licenses\n{table_generator(headers, rows, centered_columns)}',
+            summary= f'{len(component_licenses)} component(s) with copyleft licenses were found.\n',
+        )
 
     def _get_components_with_copyleft_licenses(self, components: list) -> list[Dict]:
         """
@@ -202,14 +209,13 @@ class Copyleft(RawBase[Component]):
 
         :return: A list of processed components with license data, or `None` if `self.results` is not set.
         """
-        if self.results is None:
+        if self.results_processor.get_results() is None:
             return None
-
         components: dict = {}
         # Extract component and license data from file and dependency results. Both helpers mutate `components`
-        self._get_components_data(self.results, components)
-        self._get_dependencies_data(self.results, components)
-        return self._convert_components_to_list(components)
+        self.results_processor.get_components_data(components)
+        self.results_processor.get_dependencies_data(components)
+        return self.results_processor.convert_components_to_list(components)
 
     def run(self):
         """

scanoss/inspection/{raw → policy_check/scanoss}/undeclared_component.py

@@ -24,11 +24,11 @@ SPDX-License-Identifier: MIT
 
 import json
 from dataclasses import dataclass
-from typing import Any, Dict, List
+from typing import List
 
-from ..policy_check import PolicyStatus
-from ..utils.markdown_utils import generate_jira_table, generate_table
-from .raw_base import RawBase
+from ...policy_check.policy_check import PolicyCheck, PolicyOutput, PolicyStatus
+from ...utils.markdown_utils import generate_jira_table, generate_table
+from ...utils.scan_result_processor import ScanResultProcessor
 
 
 @dataclass
@@ -44,7 +44,7 @@ class Component:
     licenses: List[License]
     status: str
 
-class UndeclaredComponent(RawBase[Component]):
+class UndeclaredComponent(PolicyCheck[Component]):
     """
     SCANOSS UndeclaredComponent class
     Inspects for undeclared components
@@ -59,7 +59,7 @@ class UndeclaredComponent(RawBase[Component]):
         format_type: str = 'json',
         status: str = None,
         output: str = None,
-        sbom_format: str = 'settings',
+        sbom_format: str = 'settings'
     ):
         """
         Initialize the UndeclaredComponent class.
@@ -74,13 +74,14 @@ class UndeclaredComponent(RawBase[Component]):
         :param sbom_format: Sbom format for status output (default 'settings')
         """
         super().__init__(
-            debug, trace, quiet,format_type, filepath, output, status, name='Undeclared Components Policy'
+            debug, trace, quiet, format_type, status, name='Undeclared Components Policy', output=output
         )
         self.filepath = filepath
-        self.format = format
         self.output = output
         self.status = status
         self.sbom_format = sbom_format
+        self.results_processor = ScanResultProcessor(self.debug, self.trace, self.quiet, self.filepath)
+
 
     def _get_undeclared_components(self, components: list[Component]) -> list or None:
         """
@@ -163,7 +164,7 @@ class UndeclaredComponent(RawBase[Component]):
 
         return summary
 
-    def _json(self, components: list[Component]) -> Dict[str, Any]:
+    def _json(self, components: list[Component]) -> PolicyOutput:
         """
         Format the undeclared components as JSON.
 
@@ -171,16 +172,16 @@ class UndeclaredComponent(RawBase[Component]):
         :return: Dictionary with formatted JSON details and summary
         """
         # Use component grouped by licenses to generate the summary
-        component_licenses = self._group_components_by_license(components)
+        component_licenses = self.results_processor.group_components_by_license(components)
         details = {}
         if len(components) > 0:
             details = {'components': components}
-        return {
-            'details': f'{json.dumps(details, indent=2)}\n',
-            'summary': self._get_summary(component_licenses),
-        }
+        return PolicyOutput(
+            details=f'{json.dumps(details, indent=2)}\n',
+            summary=self._get_summary(component_licenses)
+        )
 
-    def _markdown(self, components: list[Component]) -> Dict[str, Any]:
+    def _markdown(self, components: list[Component]) -> PolicyOutput:
         """
         Format the undeclared components as Markdown.
 
@@ -190,15 +191,15 @@ class UndeclaredComponent(RawBase[Component]):
         headers = ['Component', 'License']
         rows = []
         # TODO look at using SpdxLite license name lookup method
-        component_licenses = self._group_components_by_license(components)
+        component_licenses = self.results_processor.group_components_by_license(components)
         for component in component_licenses:
             rows.append([component.get('purl'), component.get('spdxid')])
-        return {
-            'details': f'### Undeclared components\n{generate_table(headers, rows)}\n',
-            'summary': self._get_summary(component_licenses),
-        }
+        return PolicyOutput(
+            details= f'### Undeclared components\n{generate_table(headers, rows)}\n',
+            summary= self._get_summary(component_licenses),
+        )
 
-    def _jira_markdown(self, components: list) -> Dict[str, Any]:
+    def _jira_markdown(self, components: list) -> PolicyOutput:
         """
         Format the undeclared components as Markdown.
 
@@ -208,13 +209,13 @@ class UndeclaredComponent(RawBase[Component]):
         headers = ['Component', 'License']
         rows = []
         # TODO look at using SpdxLite license name lookup method
-        component_licenses = self._group_components_by_license(components)
+        component_licenses = self.results_processor.group_components_by_license(components)
         for component in component_licenses:
             rows.append([component.get('purl'), component.get('spdxid')])
-        return {
-            'details': f'{generate_jira_table(headers, rows)}',
-            'summary': self._get_jira_summary(component_licenses),
-        }
+        return PolicyOutput(
+            details= f'{generate_jira_table(headers, rows)}',
+            summary= self._get_jira_summary(component_licenses),
+        )
 
     def _get_unique_components(self, components: list) -> list:
         """
@@ -272,13 +273,13 @@ class UndeclaredComponent(RawBase[Component]):
 
         :return: A list of processed components with their licenses, or `None` if `self.results` is not set.
         """
-        if self.results is None:
+        if self.results_processor.get_results() is None:
             return None
         components: dict = {}
         # Extract file and snippet components
-        components = self._get_components_data(self.results, components)
+        components = self.results_processor.get_components_data(components)
         # Convert to list and process licenses
-        return self._convert_components_to_list(components)
+        return self.results_processor.convert_components_to_list(components)
 
     def run(self):
         """

scanoss/inspection/{raw → summary}/component_summary.py

@@ -24,11 +24,36 @@ SPDX-License-Identifier: MIT
 import json
 from typing import Any
 
-from ..policy_check import T
-from .raw_base import RawBase
+from ...scanossbase import ScanossBase
+from ..policy_check.policy_check import T
+from ..utils.scan_result_processor import ScanResultProcessor
+
+
+class ComponentSummary(ScanossBase):
+
+    def __init__( # noqa: PLR0913
+        self,
+        debug: bool = False,
+        trace: bool = False,
+        quiet: bool = False,
+        filepath: str = None,
+        format_type: str = 'json',
+        output: str = None,
+    ):
+        """
+        Initialize the ComponentSummary class.
 
+        :param debug: Enable debug mode
+        :param trace: Enable trace mode
+        :param quiet: Enable quiet mode
+        :param filepath: Path to the file containing component data
+        :param format_type: Output format ('json' or 'md')
+        """
+        super().__init__(debug, trace, quiet)
+        self.filepath = filepath
+        self.output = output
+        self.results_processor = ScanResultProcessor(debug, trace, quiet, filepath)
 
-class ComponentSummary(RawBase):
 
     def _json(self, data: dict[str,Any]) -> dict[str,Any]:
         """
@@ -77,11 +102,11 @@ class ComponentSummary(RawBase):
         """
         Get a component summary from detected components.
 
-        :param components: List of all components
+        :param scan_components: List of all components
         :return: Dict with license summary information
         """
         # A component is considered unique by its combination of PURL (Package URL) and license
-        component_licenses = self._group_components_by_license(scan_components)
+        component_licenses = self.results_processor.group_components_by_license(scan_components)
         total_components = len(component_licenses)
         # Get undeclared components
         undeclared_components = len([c for c in component_licenses if c['status'] == 'pending'])
@@ -121,13 +146,13 @@ class ComponentSummary(RawBase):
 
         :return: A list of processed components with license data, or `None` if `self.results` is not set.
         """
-        if self.results is None:
-            raise ValueError(f'Error: No results found in ${self.filepath}')
+        if self.results_processor.get_results() is None:
+            raise ValueError(f'Error: No results found in {self.filepath}')
 
         components: dict = {}
         # Extract component and license data from file and dependency results. Both helpers mutate `components`
-        self._get_components_data(self.results, components)
-        return self._convert_components_to_list(components)
+        self.results_processor.get_components_data(components)
+        return self.results_processor.convert_components_to_list(components)
 
     def _format(self, component_summary) -> str:
         # TODO: Implement formatter to support dynamic outputs

scanoss/inspection/{raw → summary}/license_summary.py

@@ -25,11 +25,12 @@ SPDX-License-Identifier: MIT
 import json
 from typing import Any
 
-from ..policy_check import T
-from .raw_base import RawBase
+from ...scanossbase import ScanossBase
+from ..policy_check.policy_check import T
+from ..utils.scan_result_processor import ScanResultProcessor
 
 
-class LicenseSummary(RawBase):
+class LicenseSummary(ScanossBase):
     """
        SCANOSS LicenseSummary class
        Inspects results and generates comprehensive license summaries from detected components.
@@ -38,6 +39,42 @@ class LicenseSummary(RawBase):
        information, providing detailed summaries including copyleft analysis and license statistics.
        """
 
+    # Define required license fields as class constants
+    REQUIRED_LICENSE_FIELDS = ['spdxid', 'url', 'copyleft', 'source']
+
+    def __init__( # noqa: PLR0913
+        self,
+        debug: bool = False,
+        trace: bool = False,
+        quiet: bool = False,
+        filepath: str = None,
+        status: str = None,
+        output: str = None,
+        include: str = None,
+        exclude: str = None,
+        explicit: str = None,
+    ):
+        """
+        Initialize the LicenseSummary class.
+
+        :param debug: Enable debug mode
+        :param trace: Enable trace mode
+        :param quiet: Enable quiet mode
+        :param filepath: Path to the file containing component data
+        :param output: Path to save detailed output
+        :param include: Licenses to include in the analysis
+        :param exclude: Licenses to exclude from the analysis
+        :param explicit: Explicitly defined licenses
+        """
+        super().__init__(debug=debug, trace=trace, quiet=quiet)
+        self.results_processor = ScanResultProcessor(debug, trace, quiet, filepath, include, exclude, explicit)
+        self.filepath = filepath
+        self.output = output
+        self.status = status
+        self.include = include
+        self.exclude = exclude
+        self.explicit = explicit
+
     def _json(self, data: dict[str,Any]) -> dict[str, Any]:
         """
         Format license summary data as JSON.
@@ -78,41 +115,6 @@ class LicenseSummary(RawBase):
         """
         pass
 
-    # Define required license fields as class constants
-    REQUIRED_LICENSE_FIELDS = ['spdxid', 'url', 'copyleft', 'source']
-
-    def __init__( # noqa: PLR0913
-        self,
-        debug: bool = False,
-        trace: bool = False,
-        quiet: bool = False,
-        filepath: str = None,
-        status: str = None,
-        output: str = None,
-        include: str = None,
-        exclude: str = None,
-        explicit: str = None,
-    ):
-        """
-        Initialize the LicenseSummary class.
-
-        :param debug: Enable debug mode
-        :param trace: Enable trace mode (default True)
-        :param quiet: Enable quiet mode
-        :param filepath: Path to the file containing component data
-        :param output: Path to save detailed output
-        :param include: Licenses to include in the analysis
-        :param exclude: Licenses to exclude from the analysis
-        :param explicit: Explicitly defined licenses
-        """
-        super().__init__(debug, trace, quiet, filepath = filepath, output=output)
-        self.license_util.init(include, exclude, explicit)
-        self.filepath = filepath
-        self.output = output
-        self.status = status
-        self.include = include
-        self.exclude = exclude
-        self.explicit = explicit
 
     def _get_licenses_summary_from_components(self, components: list)-> dict:
         """
@@ -122,7 +124,7 @@ class LicenseSummary(RawBase):
         :return: Dict with license summary information
         """
         # A component is considered unique by its combination of PURL (Package URL) and license
-        component_licenses = self._group_components_by_license(components)
+        component_licenses = self.results_processor.group_components_by_license(components)
         license_component_count = {}
         # Count license per component
         for lic in component_licenses:
@@ -164,14 +166,14 @@ class LicenseSummary(RawBase):
 
         :return: A list of processed components with license data, or `None` if `self.results` is not set.
         """
-        if self.results is None:
-            raise ValueError(f'Error: No results found in ${self.filepath}')
+        if self.results_processor.get_results() is None:
+            raise ValueError(f'Error: No results found in {self.filepath}')
 
         components: dict = {}
         # Extract component and license data from file and dependency results. Both helpers mutate `components`
-        self._get_components_data(self.results, components)
-        self._get_dependencies_data(self.results, components)
-        return self._convert_components_to_list(components)
+        self.results_processor.get_components_data(components)
+        self.results_processor.get_dependencies_data(components)
+        return self.results_processor.convert_components_to_list(components)
 
     def _format(self, license_summary) -> str:
         # TODO: Implement formatter to support dynamic outputs