Re-estructure to enable packaging of the tool + convetional test structure

.gitignore

@@ -7,3 +7,6 @@ __pycache__
 roots.txt
 sbom*.spdx.json
 sbom.used-files.txt
+dist/
+build/
+*.egg-info/

sbom/Makefile → Makefile

@@ -26,7 +26,7 @@ $(SBOM_TARGETS) &: $(SBOM_DEPS)
 		sed 's/\.o$$/.ko/' $(objtree)/modules.order >> $(SBOM_ROOTS_FILE); \
 	fi
 
-	$(Q)$(PYTHON3) $(srctree)/scripts/sbom/sbom.py \
+	$(Q)kernel-sbom \
 		--src-tree $(abspath $(srctree)) \
 		--obj-tree $(abspath $(objtree)) \
 		--roots-file $(SBOM_ROOTS_FILE) \

README.md

@@ -256,7 +256,7 @@ flowchart TD
 - `sbom/`
   - `sbom.py` - The main script responsible for generating the SBOM
   - `sbom/sbom/` - Library modules used by the main script
-  - `sbom/tests/` - Unit tests for the library modules
+- `tests/` - Unit and integration tests
 - `sbom_analysis/` - Additional scripts for analyzing the outputs produced by the main script.
   - [sbom_analysis/cmd_graph_based_kernel_build/](sbom_analysis/cmd_graph_based_kernel_build/README.md) - Validation of cmd graph completeness by rebuilding the linux kernel only with files referenced in the cmd graph.
   - [sbom_analysis/cmd_graph_visualization/](sbom_analysis/cmd_graph_visualization/README.md) - Interactive visualization of the cmd graph
@@ -271,19 +271,32 @@ Activate the venv and install build dependencies:
 ```bash
 python3 -m venv .venv
 source .venv/bin/activate
+pip install -e .
 pip install pre-commit reuse ruff
 pre-commit install
 ```
 
 When committing, `reuse lint` is run as a pre-commit hook to ensure all files have compliant license headers.
 
 ## Run tests
-Unit tests can be found in `sbom/tests`. These are designed to be contributed upstream to the `linux` kernel repository.
-Integration tests are located in `sbom_integration_tests`. These tests are not intended for inclusion in the kernel repository, as they require a larger number of additional files.
+Unit tests can be found in `tests`. These are designed to be contributed upstream to the `linux` kernel repository.
+Integration tests are located in `tests/integration`. These tests are not intended for inclusion in the kernel repository, as they require a larger number of additional files.
+
+```bash
+python3 -m tests
+```
+
+Run unit + integration tests:
+
+```bash
+SRCARCH=x86 python3 -m tests --integration
+```
+
+Or explicitly:
 
 ```bash
 # Run unit tests
-python3 -m unittest discover -v -s sbom -p "test_*.py"
+python3 -m unittest discover -v -s tests -p "test_*.py"
 # Run integration tests
-python3 -m unittest discover -v -s sbom_integration_tests -p "test_*.py"
+python3 -m unittest discover -v -s tests/integration -p "test_*.py"
 ```

sbom/sbom.rst → docs/index.rst

@@ -7,10 +7,9 @@ KernelSbom
 Introduction
 ------------
 
-KernelSbom is a Python script ``scripts/sbom/sbom.py`` that can be
-executed after a successful kernel build. When invoked, KernelSbom
-analyzes all files involved in the build and generates Software Bill of
-Materials (SBOM) documents in SPDX 3.0.1 format.
+KernelSbom is a tool ``kernel-sbom`` that can be executed after a successful
+kernel build. When invoked, KernelSbom analyzes all files involved in the build
+and generates Software Bill of Materials (SBOM) documents in SPDX 3.0.1 format.
 The generated SBOM documents capture:
 
 * **Final output artifacts**, typically the kernel image and modules
@@ -67,12 +66,12 @@ Instead, source files are included in the build SBOM.
 Standalone Usage
 ----------------
 
-KernelSbom can also be used as a standalone script to generate
+KernelSbom can also be used as a standalone tool to generate
 SPDX documents for specific build outputs. For example, after a
 successful x86 kernel build, KernelSbom can generate SPDX documents
 for the ``bzImage`` kernel image::
 
-    $ SRCARCH=x86 python3 scripts/sbom/sbom.py \
+    $ SRCARCH=x86 kernel-sbom \
         --src-tree . \
         --obj-tree ./kernel_build \
         --roots arch/x86/boot/bzImage \
@@ -89,7 +88,7 @@ architecture for which the build was performed.
 
 For a full list of command-line options, run::
 
-    $ python3 scripts/sbom/sbom.py --help
+    $ kernel-sbom --help
 
 Output Format
 -------------
@@ -134,7 +133,7 @@ from multiple sources:
   Parsing these files is considered too complex for the scope of this
   project. Instead, the remaining gaps of the graph are filled using a
   list of manually defined dependencies, see
-  ``scripts/sbom/sbom/cmd_graph/hardcoded_dependencies.py``. This list is
+  ``kernel_sbom/cmd_graph/hardcoded_dependencies.py``. This list is
   known to be incomplete. However, analysis of the cmd graph indicates a
   ~99% completeness. For more information about the completeness analysis,
   see `KernelSbom #95 <https://github.com/TNG/KernelSbom/issues/95>`_.
@@ -171,7 +170,7 @@ For example::
 
 Then use the generated roots file::
 
-    $ SRCARCH=x86 python3 scripts/sbom/sbom.py \
+    $ SRCARCH=x86 kernel-sbom \
         --src-tree . \
         --obj-tree ./kernel_build \
         --roots-file sbom-roots.txt \

kernel_sbom/__init__.py

@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only OR MIT
+# Copyright (C) 2025 TNG Technology Consulting GmbH
+
+__version__ = "0.3.0a0"

sbom/sbom.py → kernel_sbom/__main__.py

@@ -12,13 +12,13 @@
 import sys
 import time
 import uuid
-import sbom.sbom_logging as sbom_logging
-from sbom.config import get_config
-from sbom.path_utils import is_relative_to
-from sbom.spdx import JsonLdSpdxDocument, SpdxIdGenerator
-from sbom.spdx.core import CreationInfo, SpdxDocument
-from sbom.spdx_graph import SpdxIdGeneratorCollection, build_spdx_graphs
-from sbom.cmd_graph import CmdGraph
+import kernel_sbom.sbom_logging as sbom_logging
+from kernel_sbom.config import get_config
+from kernel_sbom.path_utils import is_relative_to
+from kernel_sbom.spdx import JsonLdSpdxDocument, SpdxIdGenerator
+from kernel_sbom.spdx.core import CreationInfo, SpdxDocument
+from kernel_sbom.spdx_graph import SpdxIdGeneratorCollection, build_spdx_graphs
+from kernel_sbom.cmd_graph import CmdGraph
 
 
 def main():
@@ -124,6 +124,5 @@ def main():
         sys.exit(1)
 
 
-# Call main method
 if __name__ == "__main__":
     main()

sbom/sbom/cmd_graph/cmd_file.py → kernel_sbom/cmd_graph/cmd_file.py

@@ -4,10 +4,10 @@
 import os
 import re
 from dataclasses import dataclass, field
-from sbom.cmd_graph.deps_parser import parse_cmd_file_deps
-from sbom.cmd_graph.savedcmd_parser import parse_inputs_from_commands
-import sbom.sbom_logging as sbom_logging
-from sbom.path_utils import PathStr
+from kernel_sbom.cmd_graph.deps_parser import parse_cmd_file_deps
+from kernel_sbom.cmd_graph.savedcmd_parser import parse_inputs_from_commands
+import kernel_sbom.sbom_logging as sbom_logging
+from kernel_sbom.path_utils import PathStr
 
 SAVEDCMD_PATTERN = re.compile(r"^(saved)?cmd_.*?:=\s*(?P<full_command>.+)$")
 SOURCE_PATTERN = re.compile(r"^source.*?:=\s*(?P<source_file>.+)$")

sbom/sbom/cmd_graph/cmd_graph.py → kernel_sbom/cmd_graph/cmd_graph.py

@@ -5,8 +5,8 @@
 from dataclasses import dataclass, field
 from typing import Iterator
 
-from sbom.cmd_graph.cmd_graph_node import CmdGraphNode, CmdGraphNodeConfig
-from sbom.path_utils import PathStr
+from kernel_sbom.cmd_graph.cmd_graph_node import CmdGraphNode, CmdGraphNodeConfig
+from kernel_sbom.path_utils import PathStr
 
 
 @dataclass

sbom/sbom/cmd_graph/cmd_graph_node.py → kernel_sbom/cmd_graph/cmd_graph_node.py

@@ -7,11 +7,11 @@
 import os
 from typing import Iterator, Protocol
 
-from sbom import sbom_logging
-from sbom.cmd_graph.cmd_file import CmdFile
-from sbom.cmd_graph.hardcoded_dependencies import get_hardcoded_dependencies
-from sbom.cmd_graph.incbin_parser import parse_incbin_statements
-from sbom.path_utils import PathStr, is_relative_to
+from kernel_sbom import sbom_logging
+from kernel_sbom.cmd_graph.cmd_file import CmdFile
+from kernel_sbom.cmd_graph.hardcoded_dependencies import get_hardcoded_dependencies
+from kernel_sbom.cmd_graph.incbin_parser import parse_incbin_statements
+from kernel_sbom.path_utils import PathStr, is_relative_to
 
 
 @dataclass

sbom/sbom/cmd_graph/deps_parser.py → kernel_sbom/cmd_graph/deps_parser.py

@@ -2,8 +2,8 @@
 # Copyright (C) 2025 TNG Technology Consulting GmbH
 
 import re
-import sbom.sbom_logging as sbom_logging
-from sbom.path_utils import PathStr
+import kernel_sbom.sbom_logging as sbom_logging
+from kernel_sbom.path_utils import PathStr
 
 # Match dependencies on config files
 # Example match: "$(wildcard include/config/CONFIG_SOMETHING)"

sbom/sbom/cmd_graph/hardcoded_dependencies.py → kernel_sbom/cmd_graph/hardcoded_dependencies.py

@@ -3,9 +3,9 @@
 
 import os
 from typing import Callable
-import sbom.sbom_logging as sbom_logging
-from sbom.path_utils import PathStr, is_relative_to
-from sbom.environment import Environment
+import kernel_sbom.sbom_logging as sbom_logging
+from kernel_sbom.path_utils import PathStr, is_relative_to
+from kernel_sbom.environment import Environment
 
 HARDCODED_DEPENDENCIES: dict[str, list[str]] = {
     # defined in linux/Kbuild

sbom/sbom/cmd_graph/incbin_parser.py → kernel_sbom/cmd_graph/incbin_parser.py

@@ -4,7 +4,7 @@
 from dataclasses import dataclass
 import re
 
-from sbom.path_utils import PathStr
+from kernel_sbom.path_utils import PathStr
 
 INCBIN_PATTERN = re.compile(r'\s*\.incbin\s+"(?P<path>[^"]+)"')
 """Regex pattern for matching `.incbin "<path>"` statements."""

sbom/sbom/cmd_graph/savedcmd_parser.py → kernel_sbom/cmd_graph/savedcmd_parser.py

@@ -5,8 +5,8 @@
 import shlex
 from dataclasses import dataclass
 from typing import Any, Callable, Union
-import sbom.sbom_logging as sbom_logging
-from sbom.path_utils import PathStr
+import kernel_sbom.sbom_logging as sbom_logging
+from kernel_sbom.path_utils import PathStr
 
 
 class CmdParsingError(Exception):

sbom/sbom/config.py → kernel_sbom/config.py

@@ -7,7 +7,7 @@
 from enum import Enum
 import os
 from typing import Any
-from sbom.path_utils import PathStr
+from kernel_sbom.path_utils import PathStr
 
 
 class KernelSpdxDocumentKind(Enum):

sbom/sbom/spdx/build.py → kernel_sbom/spdx/build.py

@@ -2,7 +2,7 @@
 # Copyright (C) 2025 TNG Technology Consulting GmbH
 
 from dataclasses import dataclass, field
-from sbom.spdx.core import DictionaryEntry, Element, Hash
+from kernel_sbom.spdx.core import DictionaryEntry, Element, Hash
 
 
 @dataclass(kw_only=True)

sbom/sbom/spdx/core.py → kernel_sbom/spdx/core.py

@@ -4,7 +4,7 @@
 from dataclasses import dataclass, field
 from datetime import datetime, timezone
 from typing import Any, Literal
-from sbom.spdx.spdxId import SpdxId
+from kernel_sbom.spdx.spdxId import SpdxId
 
 SPDX_SPEC_VERSION = "3.0.1"
 

sbom/sbom/spdx/serialization.py → kernel_sbom/spdx/serialization.py

@@ -3,8 +3,8 @@
 
 import json
 from typing import Any
-from sbom.path_utils import PathStr
-from sbom.spdx.core import SPDX_SPEC_VERSION, SpdxDocument, SpdxObject
+from kernel_sbom.path_utils import PathStr
+from kernel_sbom.spdx.core import SPDX_SPEC_VERSION, SpdxDocument, SpdxObject
 
 
 class JsonLdSpdxDocument:

sbom/sbom/spdx/simplelicensing.py → kernel_sbom/spdx/simplelicensing.py

@@ -2,7 +2,7 @@
 # Copyright (C) 2025 TNG Technology Consulting GmbH
 
 from dataclasses import dataclass, field
-from sbom.spdx.core import Element
+from kernel_sbom.spdx.core import Element
 
 
 @dataclass(kw_only=True)

sbom/sbom/spdx/software.py → kernel_sbom/spdx/software.py

@@ -3,7 +3,7 @@
 
 from dataclasses import dataclass, field
 from typing import Literal
-from sbom.spdx.core import Artifact, ElementCollection, IntegrityMethod
+from kernel_sbom.spdx.core import Artifact, ElementCollection, IntegrityMethod
 
 
 SbomType = Literal["source", "build"]

sbom/sbom/spdx_graph/build_spdx_graphs.py → kernel_sbom/spdx_graph/build_spdx_graphs.py

@@ -5,15 +5,15 @@
 from typing import Protocol
 
 import logging
-from sbom.config import KernelSpdxDocumentKind
-from sbom.cmd_graph import CmdGraph
-from sbom.path_utils import PathStr
-from sbom.spdx_graph.kernel_file import KernelFileCollection
-from sbom.spdx_graph.spdx_graph_model import SpdxGraph, SpdxIdGeneratorCollection
-from sbom.spdx_graph.shared_spdx_elements import SharedSpdxElements
-from sbom.spdx_graph.spdx_source_graph import SpdxSourceGraph
-from sbom.spdx_graph.spdx_build_graph import SpdxBuildGraph
-from sbom.spdx_graph.spdx_output_graph import SpdxOutputGraph
+from kernel_sbom.config import KernelSpdxDocumentKind
+from kernel_sbom.cmd_graph import CmdGraph
+from kernel_sbom.path_utils import PathStr
+from kernel_sbom.spdx_graph.kernel_file import KernelFileCollection
+from kernel_sbom.spdx_graph.spdx_graph_model import SpdxGraph, SpdxIdGeneratorCollection
+from kernel_sbom.spdx_graph.shared_spdx_elements import SharedSpdxElements
+from kernel_sbom.spdx_graph.spdx_source_graph import SpdxSourceGraph
+from kernel_sbom.spdx_graph.spdx_build_graph import SpdxBuildGraph
+from kernel_sbom.spdx_graph.spdx_output_graph import SpdxOutputGraph
 
 
 class SpdxGraphConfig(Protocol):

sbom/sbom/spdx_graph/kernel_file.py → kernel_sbom/spdx_graph/kernel_file.py

@@ -6,13 +6,13 @@
 import hashlib
 import os
 import re
-from sbom.cmd_graph import CmdGraph
-from sbom.path_utils import PathStr, is_relative_to
-from sbom.spdx import SpdxId, SpdxIdGenerator
-from sbom.spdx.core import Hash
-from sbom.spdx.software import ContentIdentifier, File, SoftwarePurpose
-import sbom.sbom_logging as sbom_logging
-from sbom.spdx_graph.spdx_graph_model import SpdxIdGeneratorCollection
+from kernel_sbom.cmd_graph import CmdGraph
+from kernel_sbom.path_utils import PathStr, is_relative_to
+from kernel_sbom.spdx import SpdxId, SpdxIdGenerator
+from kernel_sbom.spdx.core import Hash
+from kernel_sbom.spdx.software import ContentIdentifier, File, SoftwarePurpose
+import kernel_sbom.sbom_logging as sbom_logging
+from kernel_sbom.spdx_graph.spdx_graph_model import SpdxIdGeneratorCollection
 
 
 class KernelFileLocation(Enum):

sbom/sbom/spdx_graph/shared_spdx_elements.py → kernel_sbom/spdx_graph/shared_spdx_elements.py

@@ -3,8 +3,8 @@
 
 from dataclasses import dataclass
 from datetime import datetime
-from sbom.spdx.core import CreationInfo, SoftwareAgent
-from sbom.spdx.spdxId import SpdxIdGenerator
+from kernel_sbom.spdx.core import CreationInfo, SoftwareAgent
+from kernel_sbom.spdx.spdxId import SpdxIdGenerator
 
 
 @dataclass(frozen=True)

sbom/sbom/spdx_graph/spdx_build_graph.py → kernel_sbom/spdx_graph/spdx_build_graph.py

@@ -3,16 +3,16 @@
 
 from dataclasses import dataclass
 from typing import Mapping
-from sbom.cmd_graph import CmdGraph
-from sbom.path_utils import PathStr
-from sbom.spdx import SpdxIdGenerator
-from sbom.spdx.build import Build
-from sbom.spdx.core import ExternalMap, NamespaceMap, Relationship, SpdxDocument
-from sbom.spdx.software import File, Sbom
-from sbom.spdx_graph.kernel_file import KernelFileCollection
-from sbom.spdx_graph.shared_spdx_elements import SharedSpdxElements
-from sbom.spdx_graph.spdx_graph_model import SpdxGraph, SpdxIdGeneratorCollection
-from sbom.spdx_graph.spdx_source_graph import source_file_license_elements
+from kernel_sbom.cmd_graph import CmdGraph
+from kernel_sbom.path_utils import PathStr
+from kernel_sbom.spdx import SpdxIdGenerator
+from kernel_sbom.spdx.build import Build
+from kernel_sbom.spdx.core import ExternalMap, NamespaceMap, Relationship, SpdxDocument
+from kernel_sbom.spdx.software import File, Sbom
+from kernel_sbom.spdx_graph.kernel_file import KernelFileCollection
+from kernel_sbom.spdx_graph.shared_spdx_elements import SharedSpdxElements
+from kernel_sbom.spdx_graph.spdx_graph_model import SpdxGraph, SpdxIdGeneratorCollection
+from kernel_sbom.spdx_graph.spdx_source_graph import source_file_license_elements
 
 
 @dataclass

sbom/sbom/spdx_graph/spdx_graph_model.py → kernel_sbom/spdx_graph/spdx_graph_model.py

@@ -2,9 +2,9 @@
 # Copyright (C) 2025 TNG Technology Consulting GmbH
 
 from dataclasses import dataclass
-from sbom.spdx.core import CreationInfo, SoftwareAgent, SpdxDocument, SpdxObject
-from sbom.spdx.software import Sbom
-from sbom.spdx.spdxId import SpdxIdGenerator
+from kernel_sbom.spdx.core import CreationInfo, SoftwareAgent, SpdxDocument, SpdxObject
+from kernel_sbom.spdx.software import Sbom
+from kernel_sbom.spdx.spdxId import SpdxIdGenerator
 
 
 @dataclass