Extract common validation, deduplication and conversion code for the writers

Signed-off-by: Holger Frydrych <holger.frydrych@tngtech.com>

Author: fholger

src/spdx_tools/spdx/writer/json/json_writer.py

@@ -3,13 +3,11 @@
 # SPDX-License-Identifier: Apache-2.0
 import json
 
-from beartype.typing import List, IO
+from beartype.typing import IO
 
-from spdx_tools.spdx.document_utils import create_document_without_duplicates
 from spdx_tools.spdx.jsonschema.document_converter import DocumentConverter
 from spdx_tools.spdx.model import Document
-from spdx_tools.spdx.validation.document_validator import validate_full_spdx_document
-from spdx_tools.spdx.validation.validation_message import ValidationMessage
+from spdx_tools.spdx.writer.write_utils import convert, validate_and_deduplicate
 
 
 def write_document_to_stream(
@@ -24,15 +22,8 @@ def write_document_to_stream(
     to False, validates the document before serialization. Unless a DocumentConverter instance is provided,
     a new one is created.
     """
-    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)
-    if converter is None:
-        converter = DocumentConverter()
-    document_dict = converter.convert(document)
+    document = validate_and_deduplicate(document, validate, drop_duplicates)
+    document_dict = convert(document, converter)
     json.dump(document_dict, stream, indent=4)
 
 

src/spdx_tools/spdx/writer/rdf/rdf_writer.py

@@ -1,31 +1,24 @@
 # SPDX-FileCopyrightText: 2023 spdx contributors
 #
 # SPDX-License-Identifier: Apache-2.0
-from beartype.typing import Dict, List, IO
+from beartype.typing import IO, Dict
 from rdflib import DOAP, Graph
 from rdflib.compare import to_isomorphic
 
-from spdx_tools.spdx.document_utils import create_document_without_duplicates
 from spdx_tools.spdx.model import Document
 from spdx_tools.spdx.rdfschema.namespace import POINTER_NAMESPACE, SPDX_NAMESPACE
-from spdx_tools.spdx.validation.document_validator import validate_full_spdx_document
-from spdx_tools.spdx.validation.validation_message import ValidationMessage
 from spdx_tools.spdx.writer.rdf.annotation_writer import add_annotation_to_graph
 from spdx_tools.spdx.writer.rdf.creation_info_writer import add_creation_info_to_graph
 from spdx_tools.spdx.writer.rdf.extracted_licensing_info_writer import add_extracted_licensing_info_to_graph
 from spdx_tools.spdx.writer.rdf.file_writer import add_file_to_graph
 from spdx_tools.spdx.writer.rdf.package_writer import add_package_to_graph
 from spdx_tools.spdx.writer.rdf.relationship_writer import add_relationship_to_graph
 from spdx_tools.spdx.writer.rdf.snippet_writer import add_snippet_to_graph
+from spdx_tools.spdx.writer.write_utils import validate_and_deduplicate
 
 
 def write_document_to_stream(document: Document, stream: IO[bytes], 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)
+    document = validate_and_deduplicate(document, validate, drop_duplicates)
     graph = Graph()
     doc_namespace = document.creation_info.document_namespace
     external_doc_ref_to_namespace: Dict[str, str] = {

src/spdx_tools/spdx/writer/tagvalue/tagvalue_writer.py

@@ -8,12 +8,9 @@
 #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
-from beartype.typing import List, TextIO
+from beartype.typing import TextIO
 
-from spdx_tools.spdx.document_utils import create_document_without_duplicates
 from spdx_tools.spdx.model import Document, Relationship, RelationshipType
-from spdx_tools.spdx.validation.document_validator import validate_full_spdx_document
-from spdx_tools.spdx.validation.validation_message import ValidationMessage
 from spdx_tools.spdx.writer.tagvalue.annotation_writer import write_annotation
 from spdx_tools.spdx.writer.tagvalue.creation_info_writer import write_creation_info
 from spdx_tools.spdx.writer.tagvalue.extracted_licensing_info_writer import write_extracted_licensing_info
@@ -28,16 +25,11 @@
     write_optional_heading,
     write_separator,
 )
+from spdx_tools.spdx.writer.write_utils import validate_and_deduplicate
 
 
 def write_document_to_stream(document: Document, stream: TextIO, 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)
-
+    document = validate_and_deduplicate(document, validate, drop_duplicates)
     write_document(document, stream)
 
 

src/spdx_tools/spdx/writer/write_utils.py

@@ -0,0 +1,26 @@
+# SPDX-FileCopyrightText: 2023 spdx contributors
+#
+# SPDX-License-Identifier: Apache-2.0
+from beartype.typing import List
+
+from spdx_tools.spdx.document_utils import create_document_without_duplicates
+from spdx_tools.spdx.jsonschema.document_converter import DocumentConverter
+from spdx_tools.spdx.model import Document
+from spdx_tools.spdx.validation.document_validator import validate_full_spdx_document
+from spdx_tools.spdx.validation.validation_message import ValidationMessage
+
+
+def validate_and_deduplicate(document: Document, validate: bool = True, drop_duplicates: bool = True) -> Document:
+    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)
+    return document
+
+
+def convert(document: Document, converter: DocumentConverter) -> dict:
+    if converter is None:
+        converter = DocumentConverter()
+    return converter.convert(document)

src/spdx_tools/spdx/writer/xml/xml_writer.py

@@ -2,13 +2,11 @@
 #
 # SPDX-License-Identifier: Apache-2.0
 import xmltodict
-from beartype.typing import List, IO
+from beartype.typing import IO
 
-from spdx_tools.spdx.document_utils import create_document_without_duplicates
 from spdx_tools.spdx.jsonschema.document_converter import DocumentConverter
 from spdx_tools.spdx.model import Document
-from spdx_tools.spdx.validation.document_validator import validate_full_spdx_document
-from spdx_tools.spdx.validation.validation_message import ValidationMessage
+from spdx_tools.spdx.writer.write_utils import convert, validate_and_deduplicate
 
 
 def write_document_to_stream(
@@ -23,16 +21,8 @@ def write_document_to_stream(
     to False, validates the document before serialization. Unless a DocumentConverter instance is provided,
     a new one is created.
     """
-    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)
-
-    if converter is None:
-        converter = DocumentConverter()
-    document_dict = {"Document": converter.convert(document)}
+    document = validate_and_deduplicate(document, validate, drop_duplicates)
+    document_dict = {"Document": convert(document, converter)}
     xmltodict.unparse(document_dict, stream, encoding="utf-8", pretty=True)
 
 

src/spdx_tools/spdx/writer/yaml/yaml_writer.py

@@ -2,13 +2,11 @@
 #
 # SPDX-License-Identifier: Apache-2.0
 import yaml
-from beartype.typing import List, IO
+from beartype.typing import IO
 
-from spdx_tools.spdx.document_utils import create_document_without_duplicates
 from spdx_tools.spdx.jsonschema.document_converter import DocumentConverter
 from spdx_tools.spdx.model import Document
-from spdx_tools.spdx.validation.document_validator import validate_full_spdx_document
-from spdx_tools.spdx.validation.validation_message import ValidationMessage
+from spdx_tools.spdx.writer.write_utils import convert, validate_and_deduplicate
 
 
 def write_document_to_stream(
@@ -23,15 +21,8 @@ def write_document_to_stream(
     to False, validates the document before serialization. Unless a DocumentConverter instance is provided,
     a new one is created.
     """
-    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)
-    if converter is None:
-        converter = DocumentConverter()
-    document_dict = converter.convert(document)
+    document = validate_and_deduplicate(document, validate, drop_duplicates)
+    document_dict = convert(document, converter)
     yaml.safe_dump(document_dict, stream, indent=2)