[issue-456] add annotation parser

Signed-off-by: Meret Behrens <meret.behrens@tngtech.com>
spdx · meretp · Feb 22, 2023 · Feb 1, 2023 · Feb 1, 2023 · Feb 9, 2023
commit 1eb803bf57e982a2d27c203bf2143a68f4e0cadf
diff --git a/src/spdx/parser/rdf/annotation_parser.py b/src/spdx/parser/rdf/annotation_parser.py
@@ -0,0 +1,43 @@
+# Copyright (c) 2023 spdx contributors
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#     http://www.apache.org/licenses/LICENSE-2.0
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# 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 rdflib import URIRef, Graph, RDFS
+
+from spdx.datetime_conversions import datetime_from_str
+from spdx.model.annotation import Annotation, AnnotationType
+from spdx.parser.jsonlikedict.actor_parser import ActorParser
+from spdx.parser.logger import Logger
+from spdx.parser.parsing_functions import raise_parsing_error_if_logger_has_messages, construct_or_raise_parsing_error
+from spdx.parser.rdf.graph_parsing_functions import parse_literal, parse_spdx_id
+from spdx.rdfschema.namespace import SPDX_NAMESPACE
+
+
+def parse_annotation(annotation_node: URIRef, graph: Graph, parent_ref: URIRef, doc_namespace) -> Annotation:
+    logger = Logger()
+    spdx_id = parse_spdx_id(parent_ref, doc_namespace)
+    annotator = parse_literal(logger, graph, annotation_node, SPDX_NAMESPACE.annotator,
+                              method_to_apply=ActorParser.parse_actor)
+    annotation_type = graph.value(annotation_node, SPDX_NAMESPACE.annotationType)
+    if annotation_type:
+        annotation_type = annotation_type.removeprefix(SPDX_NAMESPACE).replace("annotationType_", "").upper()
+    try:
+        annotation_type = AnnotationType[annotation_type]
+    except KeyError:
+        logger.append(f"Invalid AnnotationType: {annotation_type}")
+    annotation_date = parse_literal(logger, graph, annotation_node, SPDX_NAMESPACE.annotationDate,
+                                    method_to_apply=datetime_from_str)
+    annotation_comment = parse_literal(logger, graph, annotation_node, RDFS.comment)
+
+    raise_parsing_error_if_logger_has_messages(logger, "Annotation")
+    annotation = construct_or_raise_parsing_error(Annotation, dict(spdx_id=spdx_id, annotation_type=annotation_type,
+                                                                   annotator=annotator, annotation_date=annotation_date,
+                                                                   annotation_comment=annotation_comment))
+
+    return annotation
diff --git a/src/spdx/parser/rdf/rdf_parser.py b/src/spdx/parser/rdf/rdf_parser.py
@@ -14,6 +14,7 @@
 from spdx.parser.error import SPDXParsingError
 from spdx.parser.logger import Logger
 from spdx.parser.parsing_functions import construct_or_raise_parsing_error, raise_parsing_error_if_logger_has_messages
+from spdx.parser.rdf.annotation_parser import parse_annotation
 from spdx.parser.rdf.creation_info_parser import parse_creation_info
 from spdx.parser.rdf.file_parser import parse_file
 from spdx.parser.rdf.snippet_parser import parse_snippet
@@ -51,7 +52,12 @@ def translate_graph_to_document(graph: Graph) -> Document:
         except SPDXParsingError as err:
             logger.extend(err.get_messages())
 
+    annotations = []
+    for (parent_node, _, annotation_node) in graph.triples((None, SPDX_NAMESPACE.annotation, None)):
+        annotations.append(parse_annotation(annotation_node, graph, parent_node, creation_info.document_namespace))
+
     raise_parsing_error_if_logger_has_messages(logger)
     document = construct_or_raise_parsing_error(Document,
-                                                dict(creation_info=creation_info, snippets=snippets, files=files))
+                                                dict(creation_info=creation_info, snippets=snippets, files=files,
+                                                     annotations=annotations))
     return document
diff --git a/tests/spdx/parser/rdf/test_annotation_parser.py b/tests/spdx/parser/rdf/test_annotation_parser.py
@@ -0,0 +1,34 @@
+# Copyright (c) 2023 spdx contributors
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#     http://www.apache.org/licenses/LICENSE-2.0
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# 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.
+import os
+from datetime import datetime
+
+from rdflib import Graph, URIRef
+
+from spdx.model.actor import Actor, ActorType
+from spdx.model.annotation import AnnotationType
+from spdx.parser.rdf.annotation_parser import parse_annotation
+from spdx.rdfschema.namespace import SPDX_NAMESPACE
+
+
+def test_parse_annotation():
+    graph = Graph().parse(os.path.join(os.path.dirname(__file__), "data/file_to_test_rdf_parser.rdf.xml"))
+    doc_namespace = "https://some.namespace"
+    file_node = URIRef(f"{doc_namespace}#SPDXRef-File")
+    annotation_node = graph.value(subject=file_node, predicate=SPDX_NAMESPACE.annotation)
+
+    annotation = parse_annotation(annotation_node, graph, file_node, doc_namespace)
+
+    assert annotation.spdx_id == "SPDXRef-File"
+    assert annotation.annotation_type == AnnotationType.REVIEW
+    assert annotation.annotator == Actor(ActorType.PERSON, "annotatorName", "some@mail.com")
+    assert annotation.annotation_date == datetime(2022, 12, 1, 0, 0)
+    assert annotation.annotation_comment == "annotationComment"
diff --git a/tests/spdx/parser/rdf/test_rdf_parser.py b/tests/spdx/parser/rdf/test_rdf_parser.py
@@ -29,3 +29,4 @@ def test_rdf_parser_with_2_3_example():
     assert type(doc) == Document
     assert len(doc.snippets) ==  1
     assert len(doc.files) == 5
+    assert len(doc.annotations) == 5