[issue_508] add methods to remove duplicated items from list properties

Signed-off-by: Meret Behrens <[email protected]>

Author: meretp

src/spdx/document_utils.py

@@ -1,7 +1,8 @@
 # SPDX-FileCopyrightText: 2022 spdx contributors
 #
 # SPDX-License-Identifier: Apache-2.0
-from typing import Dict, List, Union
+from copy import deepcopy
+from typing import Any, Dict, List, Union
 
 from spdx.model.document import Document
 from spdx.model.file import File
@@ -29,3 +30,30 @@ def get_contained_spdx_elements(document: Document) -> Dict[str, Union[Package,
     contained_spdx_elements.update({snippet.spdx_id: snippet for snippet in document.snippets})
 
     return contained_spdx_elements
+
+
+def create_document_without_duplicates(document: Document) -> Document:
+    document_without_duplicates = deepcopy(document)
+    for elements in [
+        [document_without_duplicates.creation_info],
+        document_without_duplicates.files,
+        document_without_duplicates.packages,
+        document_without_duplicates.snippets,
+        document_without_duplicates.extracted_licensing_info,
+    ]:
+        for element in elements:
+            for key, value in element.__dict__.items():
+                if isinstance(value, list):
+                    value_without_duplicates = create_list_without_duplicates(value)
+                    setattr(element, key, value_without_duplicates)
+
+    return document_without_duplicates
+
+
+def create_list_without_duplicates(list_with_potential_duplicates: List[Any]) -> List[Any]:
+    list_without_duplicates = []
+    for element in list_with_potential_duplicates:
+        if element not in list_without_duplicates:
+            list_without_duplicates.append(deepcopy(element))
+
+    return list_without_duplicates

src/spdx/writer/json/json_writer.py

@@ -4,14 +4,19 @@
 import json
 from typing import List
 
+from spdx.document_utils import create_document_without_duplicates
 from spdx.jsonschema.document_converter import DocumentConverter
 from spdx.model.document import Document
 from spdx.validation.document_validator import validate_full_spdx_document
 from spdx.validation.validation_message import ValidationMessage
 
 
 def write_document_to_file(
-    document: Document, file_name: str, validate: bool = True, converter: DocumentConverter = None
+    document: Document,
+    file_name: str,
+    validate: bool = True,
+    converter: DocumentConverter = None,
+    drop_duplicates: bool = True,
 ):
     """
     Serializes the provided document to json and writes it to a file with the provided name. Unless validate is set
@@ -22,6 +27,8 @@ def write_document_to_file(
         validation_messages: List[ValidationMessage] = validate_full_spdx_document(document)
         if validation_messages:
             raise ValueError(f"Document is not valid. The following errors were detected: {validation_messages}")
+    if drop_duplicates:
+        document = create_document_without_duplicates(document)
     if converter is None:
         converter = DocumentConverter()
     document_dict = converter.convert(document)

src/spdx/writer/rdf/rdf_writer.py

@@ -6,6 +6,7 @@
 from rdflib import DOAP, Graph
 from rdflib.compare import to_isomorphic
 
+from spdx.document_utils import create_document_without_duplicates
 from spdx.model.document import Document
 from spdx.rdfschema.namespace import POINTER_NAMESPACE, SPDX_NAMESPACE
 from spdx.validation.document_validator import validate_full_spdx_document
@@ -19,12 +20,13 @@
 from spdx.writer.rdf.snippet_writer import add_snippet_to_graph
 
 
-def write_document_to_file(document: Document, file_name: str, validate: bool):
+def write_document_to_file(document: Document, file_name: str, validate: bool, drop_duplicates: bool = True):
     if validate:
         validation_messages: List[ValidationMessage] = validate_full_spdx_document(document)
         if validation_messages:
             raise ValueError(f"Document is not valid. The following errors were detected: {validation_messages}")
-
+    if drop_duplicates:
+        document = create_document_without_duplicates(document)
     graph = Graph()
     doc_namespace = document.creation_info.document_namespace
     external_doc_ref_to_namespace: Dict[str, str] = {

src/spdx/writer/tagvalue/tagvalue_writer.py

@@ -10,6 +10,7 @@
 #  limitations under the License.
 from typing import List, TextIO
 
+from spdx.document_utils import create_document_without_duplicates
 from spdx.model.document import Document
 from spdx.validation.document_validator import validate_full_spdx_document
 from spdx.validation.validation_message import ValidationMessage
@@ -29,11 +30,13 @@
 )
 
 
-def write_document_to_file(document: Document, file_name: str, validate: bool = True):
+def write_document_to_file(document: Document, file_name: str, validate: bool = True, drop_duplicates: bool = True):
     if validate:
         validation_messages: List[ValidationMessage] = validate_full_spdx_document(document)
         if validation_messages:
             raise ValueError(f"Document is not valid. The following errors were detected: {validation_messages}")
+    if drop_duplicates:
+        document = create_document_without_duplicates(document)
 
     with open(file_name, "w") as out:
         write_document(document, out)

src/spdx/writer/xml/xml_writer.py

@@ -5,14 +5,19 @@
 
 import xmltodict
 
+from spdx.document_utils import create_document_without_duplicates
 from spdx.jsonschema.document_converter import DocumentConverter
 from spdx.model.document import Document
 from spdx.validation.document_validator import validate_full_spdx_document
 from spdx.validation.validation_message import ValidationMessage
 
 
 def write_document_to_file(
-    document: Document, file_name: str, validate: bool = True, converter: DocumentConverter = None
+    document: Document,
+    file_name: str,
+    validate: bool = True,
+    converter: DocumentConverter = None,
+    drop_duplicates: bool = True,
 ):
     """
     Serializes the provided document to XML and writes it to a file with the provided name. Unless validate is set
@@ -23,6 +28,9 @@ def write_document_to_file(
         validation_messages: List[ValidationMessage] = validate_full_spdx_document(document)
         if validation_messages:
             raise ValueError(f"Document is not valid. The following errors were detected: {validation_messages}")
+    if drop_duplicates:
+        document = create_document_without_duplicates(document)
+
     if converter is None:
         converter = DocumentConverter()
     document_dict = {"Document": converter.convert(document)}

src/spdx/writer/yaml/yaml_writer.py

@@ -5,14 +5,19 @@
 
 import yaml
 
+from spdx.document_utils import create_document_without_duplicates
 from spdx.jsonschema.document_converter import DocumentConverter
 from spdx.model.document import Document
 from spdx.validation.document_validator import validate_full_spdx_document
 from spdx.validation.validation_message import ValidationMessage
 
 
 def write_document_to_file(
-    document: Document, file_name: str, validate: bool = True, converter: DocumentConverter = None
+    document: Document,
+    file_name: str,
+    validate: bool = True,
+    converter: DocumentConverter = None,
+    drop_duplicates: bool = True,
 ):
     """
     Serializes the provided document to yaml and writes it to a file with the provided name. Unless validate is set
@@ -23,6 +28,8 @@ def write_document_to_file(
         validation_messages: List[ValidationMessage] = validate_full_spdx_document(document)
         if validation_messages:
             raise ValueError(f"Document is not valid. The following errors were detected: {validation_messages}")
+    if drop_duplicates:
+        document = create_document_without_duplicates(document)
     if converter is None:
         converter = DocumentConverter()
     document_dict = converter.convert(document)

tests/spdx/test_document_utils.py

@@ -5,8 +5,28 @@
 
 import pytest
 
-from spdx.document_utils import get_contained_spdx_element_ids, get_contained_spdx_elements, get_element_from_spdx_id
-from tests.spdx.fixtures import document_fixture, file_fixture, package_fixture, snippet_fixture
+from spdx.document_utils import (
+    create_document_without_duplicates,
+    create_list_without_duplicates,
+    get_contained_spdx_element_ids,
+    get_contained_spdx_elements,
+    get_element_from_spdx_id,
+)
+from spdx.model.file import FileType
+from spdx.model.spdx_no_assertion import SpdxNoAssertion
+from spdx.model.spdx_none import SpdxNone
+from tests.spdx.fixtures import (
+    actor_fixture,
+    checksum_fixture,
+    creation_info_fixture,
+    document_fixture,
+    external_document_ref_fixture,
+    external_package_ref_fixture,
+    extracted_licensing_info_fixture,
+    file_fixture,
+    package_fixture,
+    snippet_fixture,
+)
 
 
 @pytest.fixture
@@ -34,3 +54,74 @@ def test_get_contained_spdx_elements(variables):
     assert contained_elements[package.spdx_id] == package
     assert contained_elements[file.spdx_id] == file
     assert contained_elements[snippet.spdx_id] == snippet
+
+
+def test_create_list_without_duplicates():
+    list_with_duplicates = [1, 2, 3, 5, 1, 67, 9, 67]
+
+    list_without_duplicates = create_list_without_duplicates(list_with_duplicates)
+
+    assert list_without_duplicates == [1, 2, 3, 5, 67, 9]
+
+
+def test_create_document_without_duplicates():
+    document = document_fixture(
+        creation_info=creation_info_fixture(
+            creators=[actor_fixture(name="creatorName"), actor_fixture(name="creatorName")],
+            external_document_refs=[external_document_ref_fixture(), external_document_ref_fixture()],
+        ),
+        packages=[
+            package_fixture(
+                checksums=[checksum_fixture(), checksum_fixture()],
+                license_info_from_files=[SpdxNoAssertion(), SpdxNoAssertion()],
+                external_references=[external_package_ref_fixture(), external_package_ref_fixture()],
+                attribution_texts=["duplicated text", "duplicated text"],
+            )
+        ],
+        files=[
+            file_fixture(
+                checksums=[checksum_fixture(), checksum_fixture()],
+                file_types=[FileType.TEXT, FileType.TEXT],
+                license_info_in_file=[SpdxNoAssertion(), SpdxNoAssertion()],
+                contributors=["duplicated contributor", "duplicated contributor"],
+                attribution_texts=["duplicated text", "duplicated text"],
+            )
+        ],
+        snippets=[
+            snippet_fixture(
+                license_info_in_snippet=[SpdxNone(), SpdxNone()],
+                attribution_texts=["duplicated text", "duplicated text"],
+            )
+        ],
+        extracted_licensing_info=[
+            extracted_licensing_info_fixture(cross_references=["duplicated reference", "duplicated reference"])
+        ],
+    )
+    expected_document = document_fixture(
+        creation_info=creation_info_fixture(
+            creators=[actor_fixture(name="creatorName")], external_document_refs=[external_document_ref_fixture()]
+        ),
+        packages=[
+            package_fixture(
+                checksums=[checksum_fixture()],
+                license_info_from_files=[SpdxNoAssertion()],
+                external_references=[external_package_ref_fixture()],
+                attribution_texts=["duplicated text"],
+            )
+        ],
+        files=[
+            file_fixture(
+                checksums=[checksum_fixture()],
+                file_types=[FileType.TEXT],
+                license_info_in_file=[SpdxNoAssertion()],
+                contributors=["duplicated contributor"],
+                attribution_texts=["duplicated text"],
+            )
+        ],
+        snippets=[snippet_fixture(license_info_in_snippet=[SpdxNone()], attribution_texts=["duplicated text"])],
+        extracted_licensing_info=[extracted_licensing_info_fixture(cross_references=["duplicated reference"])],
+    )
+
+    document_without_duplicates = create_document_without_duplicates(document)
+
+    assert document_without_duplicates == expected_document