scanoss 1.24.0__tar.gz → 1.25.1__tar.gz

{scanoss-1.24.0/src/scanoss.egg-info → scanoss-1.25.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: scanoss
-Version: 1.24.0
+Version: 1.25.1
 Summary: Simple Python library to leverage the SCANOSS APIs
 Home-page: https://scanoss.com
 Author: SCANOSS

{scanoss-1.24.0 → scanoss-1.25.1}/src/scanoss/__init__.py

@@ -22,4 +22,4 @@ SPDX-License-Identifier: MIT
   THE SOFTWARE.
 """
 
-__version__ = '1.24.0'
+__version__ = '1.25.1'

scanoss-1.25.1/src/scanoss/data/build_date.txt

@@ -0,0 +1 @@
+date: 20250612124028, utime: 1749732028

{scanoss-1.24.0 → scanoss-1.25.1}/src/scanoss/inspection/copyleft.py

@@ -23,7 +23,8 @@ SPDX-License-Identifier: MIT
 """
 
 import json
-from typing import Dict, Any
+from typing import Any, Dict
+
 from .policy_check import PolicyCheck, PolicyStatus
 
 
@@ -33,7 +34,7 @@ class Copyleft(PolicyCheck):
     Inspects components for copyleft licenses
     """
 
-    def __init__(
+    def __init__( # noqa: PLR0913
         self,
         debug: bool = False,
         trace: bool = True,
@@ -158,6 +159,30 @@ class Copyleft(PolicyCheck):
         self.print_debug(f'Copyleft components: {filtered_components}')
         return filtered_components
 
+    def _get_components(self):
+        """
+        Extract and process components from results and their dependencies.
+
+        This method performs the following steps:
+        1. Validates that `self.results` is loaded. Returns `None` if not.
+        2. Extracts file, snippet, and dependency components into a dictionary.
+        3. Converts components to a list and processes their licenses.
+
+        :return: A list of processed components with license data, or `None` if `self.results` is not set.
+        """
+        if self.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)
+        # Convert to list and process licenses
+        results_list = list(components.values())
+        for component in results_list:
+            component['licenses'] = list(component['licenses'].values())
+        return results_list
+
     def run(self):
         """
         Run the copyleft license inspection process.

{scanoss-1.24.0 → scanoss-1.25.1}/src/scanoss/inspection/policy_check.py

@@ -26,9 +26,10 @@ import json
 import os.path
 from abc import abstractmethod
 from enum import Enum
-from typing import Callable, List, Dict, Any
-from .utils.license_utils import LicenseUtil
+from typing import Any, Callable, Dict, List
+
 from ..scanossbase import ScanossBase
+from .utils.license_utils import LicenseUtil
 
 
 class PolicyStatus(Enum):
@@ -87,7 +88,7 @@ class PolicyCheck(ScanossBase):
 
     VALID_FORMATS = {'md', 'json', 'jira_md'}
 
-    def __init__(
+    def __init__( # noqa: PLR0913
         self,
         debug: bool = False,
         trace: bool = True,
@@ -165,6 +166,30 @@ class PolicyCheck(ScanossBase):
         """
         pass
 
+    @abstractmethod
+    def _get_components(self):
+        """
+        Retrieve and process components from the preloaded results.
+
+        This method performs the following steps:
+        1. Checks if the results have been previously loaded (self.results).
+        2. Extracts and processes components from the loaded results.
+
+        :return: A list of processed components, or None if an error occurred during any step.
+
+        Possible reasons for returning None include:
+        - Results not loaded (self.results is None)
+        - Failure to extract components from the results
+
+        Note:
+        - This method assumes that the results have been previously loaded and stored in self.results.
+        - Implementations must extract components (e.g. via `_get_components_data`,
+          `_get_dependencies_data`, or other helpers).
+        - If `self.results` is `None`, simply return `None`.
+        """
+    pass
+
+
     def _append_component(
         self, components: Dict[str, Any], new_component: Dict[str, Any], id: str, status: str
     ) -> Dict[str, Any]:
@@ -181,10 +206,9 @@ class PolicyCheck(ScanossBase):
         :param status: The new component status
         :return: The updated components dictionary
         """
-
         # Determine the component key and purl based on component type
         if id in [ComponentID.FILE.value, ComponentID.SNIPPET.value]:
-            purl = new_component['purl'][0]  # Take first purl for these component types
+            purl = new_component['purl'][0]  # Take the first purl for these component types
         else:
             purl = new_component['purl']
 
@@ -195,14 +219,13 @@ class PolicyCheck(ScanossBase):
             'licenses': {},
             'status': status,
         }
-
         if not new_component.get('licenses'):
-            self.print_stderr(f'WARNING: Results missing licenses. Skipping.')
+            self.print_debug(f'WARNING: Results missing licenses. Skipping: {new_component}')
             return components
         # Process licenses for this component
-        for l in new_component['licenses']:
-            if l.get('name'):
-                spdxid = l['name']
+        for license_item in new_component['licenses']:
+            if license_item.get('name'):
+                spdxid = license_item['name']
                 components[component_key]['licenses'][spdxid] = {
                     'spdxid': spdxid,
                     'copyleft': self.license_util.is_copyleft(spdxid),
@@ -210,71 +233,79 @@ class PolicyCheck(ScanossBase):
                 }
         return components
 
-    def _get_components_from_results(self, results: Dict[str, Any]) -> list or None:
+    def _get_components_data(self, results: Dict[str, Any], components: Dict[str, Any]) -> Dict[str, Any]:
         """
-        Process the results dictionary to extract and format component information.
-
-        This function iterates through the results dictionary, identifying components from
-        different sources (files, snippets, and dependencies). It consolidates this information
-        into a list of unique components, each with its associated licenses and other details.
+        Extract and process file and snippet components from results.
 
         :param results: A dictionary containing the raw results of a component scan
-        :return: A list of dictionaries, each representing a unique component with its details
+        :param components: Existing components dictionary to update
+        :return: Updated components dictionary with file and snippet data
         """
-        if results is None:
-            self.print_stderr(f'ERROR: Results cannot be empty')
-            return None
-        components = {}
         for component in results.values():
             for c in component:
                 component_id = c.get('id')
                 if not component_id:
-                    self.print_stderr(f'WARNING: Result missing id. Skipping.')
+                    self.print_debug(f'WARNING: Result missing id. Skipping: {c}')
+                    continue
+                ## Skip dependency
+                if component_id == ComponentID.DEPENDENCY.value:
                     continue
                 status = c.get('status')
-                if not component_id:
-                    self.print_stderr(f'WARNING: Result missing status. Skipping.')
+                if not status:
+                    self.print_debug(f'WARNING: Result missing status. Skipping: {c}')
                     continue
                 if component_id in [ComponentID.FILE.value, ComponentID.SNIPPET.value]:
                     if not c.get('purl'):
-                        self.print_stderr(f'WARNING: Result missing purl. Skipping.')
+                        self.print_debug(f'WARNING: Result missing purl. Skipping: {c}')
                         continue
                     if len(c.get('purl')) <= 0:
-                        self.print_stderr(f'WARNING: Result missing purls. Skipping.')
+                        self.print_debug(f'WARNING: Result missing purls. Skipping: {c}')
                         continue
                     if not c.get('version'):
-                        self.print_stderr(f'WARNING: Result missing version. Skipping.')
+                        self.print_msg(f'WARNING: Result missing version. Skipping: {c}')
                         continue
                     component_key = f'{c["purl"][0]}@{c["version"]}'
-                    # Initialize or update the component entry
                     if component_key not in components:
                         components = self._append_component(components, c, component_id, status)
+            # End component loop
+        # End components loop
+        return components
+
+    def _get_dependencies_data(self, results: Dict[str, Any], components: Dict[str, Any]) -> Dict[str, Any]:
+        """
+        Extract and process dependency components from results.
 
-                if c['id'] == ComponentID.DEPENDENCY.value:
+        :param results: A dictionary containing the raw results of a component scan
+        :param components: Existing components dictionary to update
+        :return: Updated components dictionary with dependency data
+        """
+        for component in results.values():
+            for c in component:
+                component_id = c.get('id')
+                if not component_id:
+                    self.print_debug(f'WARNING: Result missing id. Skipping: {c}')
+                    continue
+                status = c.get('status')
+                if not status:
+                    self.print_debug(f'WARNING: Result missing status. Skipping: {c}')
+                    continue
+                if component_id == ComponentID.DEPENDENCY.value:
                     if c.get('dependencies') is None:
                         continue
-                    for d in c['dependencies']:
-                        if not d.get('purl'):
-                            self.print_stderr(f'WARNING: Result missing purl. Skipping.')
-                            continue
-                        if len(d.get('purl')) <= 0:
-                            self.print_stderr(f'WARNING: Result missing purls. Skipping.')
+                    for dependency in c['dependencies']:
+                        if not dependency.get('purl'):
+                            self.print_debug(f'WARNING: Dependency result missing purl. Skipping: {dependency}')
                             continue
-                        if not d.get('version'):
-                            self.print_stderr(f'WARNING: Result missing version. Skipping.')
+                        if not dependency.get('version'):
+                            self.print_msg(f'WARNING: Dependency result missing version. Skipping: {dependency}')
                             continue
-                        component_key = f'{d["purl"]}@{d["version"]}'
+                        component_key = f'{dependency["purl"]}@{dependency["version"]}'
                         if component_key not in components:
-                            components = self._append_component(components, d, component_id, status)
-                    # End of dependencies loop
-                # End if
-            # End of component loop
-        # End of results loop
-        results = list(components.values())
-        for component in results:
-            component['licenses'] = list(component['licenses'].values())
-
-        return results
+                            components = self._append_component(components, dependency, component_id, status)
+                    # End dependency loop
+            # End component loop
+        # End of result loop
+        return components
 
     def generate_table(self, headers, rows, centered_columns=None):
         """
@@ -380,30 +411,6 @@ class PolicyCheck(ScanossBase):
                 self.print_stderr(f'ERROR: Problem parsing input JSON: {e}')
         return None
 
-    def _get_components(self):
-        """
-        Retrieve and process components from the preloaded results.
-
-        This method performs the following steps:
-        1. Checks if the results have been previously loaded (self.results).
-        2. Extracts and processes components from the loaded results.
-
-        :return: A list of processed components, or None if an error occurred during any step.
-                 Possible reasons for returning None include:
-                 - Results not loaded (self.results is None)
-                 - Failure to extract components from the results
-
-        Note:
-        - This method assumes that the results have been previously loaded and stored in self.results.
-        - If results is None, the method returns None without performing any further operations.
-        - The actual processing of components is delegated to the _get_components_from_results method.
-        """
-        if self.results is None:
-            return None
-        components = self._get_components_from_results(self.results)
-        return components
-
-
 #
 # End of PolicyCheck Class
 #

{scanoss-1.24.0 → scanoss-1.25.1}/src/scanoss/inspection/undeclared_component.py

@@ -23,7 +23,8 @@ SPDX-License-Identifier: MIT
 """
 
 import json
-from typing import Dict, Any
+from typing import Any, Dict
+
 from .policy_check import PolicyCheck, PolicyStatus
 
 
@@ -33,7 +34,7 @@ class UndeclaredComponent(PolicyCheck):
     Inspects for undeclared components
     """
 
-    def __init__(
+    def __init__( # noqa: PLR0913
         self,
         debug: bool = False,
         trace: bool = True,
@@ -73,7 +74,7 @@ class UndeclaredComponent(PolicyCheck):
         :return: List of undeclared components
         """
         if components is None:
-            self.print_debug(f'WARNING: No components provided!')
+            self.print_debug('WARNING: No components provided!')
             return None
         undeclared_components = []
         for component in components:
@@ -87,25 +88,35 @@ class UndeclaredComponent(PolicyCheck):
         """
         Get a summary of the undeclared components.
 
+        :param components: List of all components
+        :return: Component summary markdown
+        """
+
+        """
+        Get a summary of the undeclared components.
+
         :param components: List of all components
         :return: Component summary markdown
         """
         if len(components) > 0:
+            json_content = json.dumps(self._generate_scanoss_file(components), indent=2)
+
             if self.sbom_format == 'settings':
-                json_str = (
-                    json.dumps(self._generate_scanoss_file(components), indent=2)
-                    .replace('\n', '\\n')
-                    .replace('"', '\\"')
+                return (
+                    f'{len(components)} undeclared component(s) were found.\n'
+                    f'Add the following snippet into your `scanoss.json` file\n'
+                    f'{{code:json}}\n'
+                    f'{json_content}\n'
+                    f'{{code}}\n'
                 )
-                return f'{len(components)} undeclared component(s) were found.\nAdd the following snippet into your `scanoss.json` file\n{{code:json}}\n{json.dumps(self._generate_scanoss_file(components), indent=2)}\n{{code}}\n'
             else:
-                json_str = (
-                    json.dumps(self._generate_scanoss_file(components), indent=2)
-                    .replace('\n', '\\n')
-                    .replace('"', '\\"')
+                return (
+                    f'{len(components)} undeclared component(s) were found.\n'
+                    f'Add the following snippet into your `sbom.json` file\n'
+                    f'{{code:json}}\n'
+                    f'{json_content}\n'
+                    f'{{code}}\n'
                 )
-                return f'{len(components)} undeclared component(s) were found.\nAdd the following snippet into your `sbom.json` file\n{{code:json}}\n{json.dumps(self._generate_scanoss_file(components), indent=2)}\n{{code}}\n'
-
         return f'{len(components)} undeclared component(s) were found.\\n'
 
     def _get_summary(self, components: list) -> str:
@@ -190,7 +201,7 @@ class UndeclaredComponent(PolicyCheck):
         """
         unique_components = {}
         if components is None:
-            self.print_stderr(f'WARNING: No components provided!')
+            self.print_stderr('WARNING: No components provided!')
             return []
 
         for component in components:
@@ -225,6 +236,29 @@ class UndeclaredComponent(PolicyCheck):
 
         return sbom
 
+    def _get_components(self):
+        """
+        Extract and process components from file results only.
+
+        This method performs the following steps:
+        1. Validates if `self.results` is loaded. Returns `None` if not loaded.
+        2. Extracts file and snippet components into a dictionary.
+        3. Converts the components dictionary into a list of components.
+        4. Processes the licenses for each component by converting them into a list.
+
+        :return: A list of processed components with their licenses, or `None` if `self.results` is not set.
+        """
+        if self.results is None:
+            return None
+        components: dict = {}
+        # Extract file and snippet components
+        components = self._get_components_data(self.results, components)
+        # Convert to list and process licenses
+        results_list = list(components.values())
+        for component in results_list:
+            component['licenses'] = list(component['licenses'].values())
+        return results_list
+
     def run(self):
         """
         Run the undeclared component inspection process.

{scanoss-1.24.0 → scanoss-1.25.1}/src/scanoss/winnowing.py

@@ -32,9 +32,10 @@ import hashlib
 import pathlib
 import platform
 import re
+from typing import Tuple
 
-from crc32c import crc32c
 from binaryornot.check import is_binary
+from crc32c import crc32c
 
 from .scanossbase import ScanossBase
 
@@ -157,7 +158,7 @@ class Winnowing(ScanossBase):
     a list of WFP fingerprints with their corresponding line numbers.
     """
 
-    def __init__(
+    def __init__(  # noqa: PLR0913
         self,
         size_limit: bool = False,
         debug: bool = False,
@@ -197,6 +198,7 @@ class Winnowing(ScanossBase):
         self.strip_hpsm_ids = strip_hpsm_ids
         self.strip_snippet_ids = strip_snippet_ids
         self.hpsm = hpsm
+        self.is_windows = platform.system() == 'Windows'
         if hpsm:
             self.crc8_maxim_dow_table = []
             self.crc8_generate_table()
@@ -218,11 +220,11 @@ class Winnowing(ScanossBase):
             return byte
         if byte >= ASCII_a:
             return byte
-        if (byte >= 65) and (byte <= 90):
+        if (byte >= ASCII_A) and (byte <= ASCII_Z):
             return byte + 32
         return 0
 
-    def __skip_snippets(self, file: str, src: str) -> bool:
+    def __skip_snippets(self, file: str, src: str) -> bool:  # noqa: PLR0911
         """
         Determine files that are not of interest based on their content or file extension
         Parameters
@@ -351,7 +353,55 @@ class Winnowing(ScanossBase):
             self.print_debug(f'Stripped snippet ids from {file}')
         return wfp
 
-    def wfp_for_contents(self, file: str, bin_file: bool, contents: bytes) -> str:
+    def __detect_line_endings(self, contents: bytes) -> Tuple[bool, bool, bool]:
+        """Detect the types of line endings present in file contents.
+
+        Args:
+            contents: File contents as bytes.
+
+        Returns:
+            Tuple of (has_crlf, has_lf_only, has_cr_only, has_mixed) indicating which line ending types are present.
+        """
+        has_crlf = b'\r\n' in contents
+        # For LF detection, we need to find LF that's not part of CRLF
+        content_without_crlf = contents.replace(b'\r\n', b'')
+        has_standalone_lf = b'\n' in content_without_crlf
+        # For CR detection, we need to find CR that's not part of CRLF
+        has_standalone_cr = b'\r' in content_without_crlf
+
+        return has_crlf, has_standalone_lf, has_standalone_cr
+
+    def __calculate_opposite_line_ending_hash(self, contents: bytes):
+        """Calculate hash for contents with opposite line endings.
+
+        If the file is primarily Unix (LF), calculates Windows (CRLF) hash.
+        If the file is primarily Windows (CRLF), calculates Unix (LF) hash.
+
+        Args:
+            contents: File contents as bytes.
+
+        Returns:
+            Hash with opposite line endings as hex string, or None if no line endings detected.
+        """
+        has_crlf, has_standalone_lf, has_standalone_cr = self.__detect_line_endings(contents)
+
+        if not has_crlf and not has_standalone_lf and not has_standalone_cr:
+            return None
+
+        # Normalize all line endings to LF first
+        normalized = contents.replace(b'\r\n', b'\n').replace(b'\r', b'\n')
+
+        # Determine the dominant line ending type
+        if has_crlf and not has_standalone_lf and not has_standalone_cr:
+            # File is Windows (CRLF) - produce Unix (LF) hash
+            opposite_contents = normalized
+        else:
+            # File is Unix (LF/CR) or mixed - produce Windows (CRLF) hash
+            opposite_contents = normalized.replace(b'\n', b'\r\n')
+
+        return hashlib.md5(opposite_contents).hexdigest()
+
+    def wfp_for_contents(self, file: str, bin_file: bool, contents: bytes) -> str:  # noqa: PLR0912, PLR0915
         """
         Generate a Winnowing fingerprint (WFP) for the given file contents
         Parameters
@@ -371,7 +421,7 @@ class Winnowing(ScanossBase):
         content_length = len(contents)
         original_filename = file
 
-        if platform.system() == 'Windows':
+        if self.is_windows:
             original_filename = file.replace('\\', '/')
         wfp_filename = repr(original_filename).strip("'")  # return a utf-8 compatible version of the filename
         if self.obfuscate:  # hide the real size of the file and its name, but keep the suffix
@@ -380,6 +430,13 @@ class Winnowing(ScanossBase):
             self.file_map[wfp_filename] = original_filename  # Save the file name map for later (reverse lookup)
 
         wfp = 'file={0},{1},{2}\n'.format(file_md5, content_length, wfp_filename)
+
+        # Add opposite line ending hash based on line ending analysis
+        if not bin_file:
+            opposite_hash = self.__calculate_opposite_line_ending_hash(contents)
+            if opposite_hash is not None:
+                wfp += f'fh2={opposite_hash}\n'
+
         # We don't process snippets for binaries, or other uninteresting files, or if we're requested to skip
         if bin_file or self.skip_snippets or self.__skip_snippets(file, contents.decode('utf-8', 'ignore')):
             return wfp
@@ -467,7 +524,7 @@ class Winnowing(ScanossBase):
         for i, byte in enumerate(content):
             c = byte
             if c == ASCII_LF:  # When there is a new line
-                if len(list_normalized):
+                if list_normalized:
                     crc_lines.append(self.crc8_buffer(list_normalized))
                     list_normalized = []
                 elif last_line + 1 == i:

{scanoss-1.24.0 → scanoss-1.25.1/src/scanoss.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: scanoss
-Version: 1.24.0
+Version: 1.25.1
 Summary: Simple Python library to leverage the SCANOSS APIs
 Home-page: https://scanoss.com
 Author: SCANOSS