spdx · armintaenzertng · Sep 8, 2023 · Sep 7, 2023
diff --git a/src/spdx_tools/spdx/parser/json/json_parser.py b/src/spdx_tools/spdx/parser/json/json_parser.py
@@ -2,15 +2,16 @@
 #
 # SPDX-License-Identifier: Apache-2.0
 import json
+from typing import Optional
 
 from beartype.typing import Dict
 
 from spdx_tools.spdx.model import Document
 from spdx_tools.spdx.parser.jsonlikedict.json_like_dict_parser import JsonLikeDictParser
 
 
-def parse_from_file(file_name: str) -> Document:
-    with open(file_name) as file:
+def parse_from_file(file_name: str, encoding: Optional[str] = None) -> Document:
+    with open(file_name, encoding=encoding) as file:
         input_doc_as_dict: Dict = json.load(file)
 
     return JsonLikeDictParser().parse(input_doc_as_dict)
diff --git a/src/spdx_tools/spdx/parser/parse_anything.py b/src/spdx_tools/spdx/parser/parse_anything.py
@@ -9,6 +9,8 @@
 # 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 typing import Optional
+
 from spdx_tools.spdx.formats import FileFormat, file_name_to_format
 from spdx_tools.spdx.parser.json import json_parser
 from spdx_tools.spdx.parser.rdf import rdf_parser
@@ -17,15 +19,15 @@
 from spdx_tools.spdx.parser.yaml import yaml_parser
 
 
-def parse_file(file_name: str):
+def parse_file(file_name: str, encoding: Optional[str] = None):
     input_format = file_name_to_format(file_name)
     if input_format == FileFormat.RDF_XML:
-        return rdf_parser.parse_from_file(file_name)
+        return rdf_parser.parse_from_file(file_name, encoding)
     elif input_format == FileFormat.TAG_VALUE:
-        return tagvalue_parser.parse_from_file(file_name)
+        return tagvalue_parser.parse_from_file(file_name, encoding)
     elif input_format == FileFormat.JSON:
-        return json_parser.parse_from_file(file_name)
+        return json_parser.parse_from_file(file_name, encoding)
     elif input_format == FileFormat.XML:
-        return xml_parser.parse_from_file(file_name)
+        return xml_parser.parse_from_file(file_name, encoding)
     elif input_format == FileFormat.YAML:
-        return yaml_parser.parse_from_file(file_name)
+        return yaml_parser.parse_from_file(file_name, encoding)
diff --git a/src/spdx_tools/spdx/parser/rdf/rdf_parser.py b/src/spdx_tools/spdx/parser/rdf/rdf_parser.py
@@ -1,6 +1,8 @@
 # SPDX-FileCopyrightText: 2023 spdx contributors
 #
 # SPDX-License-Identifier: Apache-2.0
+from typing import Optional
+
 from beartype.typing import Any, Dict
 from rdflib import RDF, Graph
 
@@ -22,9 +24,9 @@
 from spdx_tools.spdx.rdfschema.namespace import SPDX_NAMESPACE
 
 
-def parse_from_file(file_name: str) -> Document:
+def parse_from_file(file_name: str, encoding: Optional[str] = None) -> Document:
     graph = Graph()
-    with open(file_name) as file:
+    with open(file_name, encoding=encoding) as file:
         graph.parse(file, format="xml")
 
     document: Document = translate_graph_to_document(graph)

diff --git a/src/spdx_tools/spdx/parser/tagvalue/tagvalue_parser.py b/src/spdx_tools/spdx/parser/tagvalue/tagvalue_parser.py
@@ -1,13 +1,15 @@
 # SPDX-FileCopyrightText: 2023 spdx contributors
 #
 # SPDX-License-Identifier: Apache-2.0
+from typing import Optional
+
 from spdx_tools.spdx.model import Document
 from spdx_tools.spdx.parser.tagvalue.parser import Parser
 
 
-def parse_from_file(file_name: str) -> Document:
+def parse_from_file(file_name: str, encoding: Optional[str] = None) -> Document:
     parser = Parser()
-    with open(file_name) as file:
+    with open(file_name, encoding=encoding) as file:
         data = file.read()
     document: Document = parser.parse(data)
     return document
diff --git a/src/spdx_tools/spdx/parser/xml/xml_parser.py b/src/spdx_tools/spdx/parser/xml/xml_parser.py
@@ -1,6 +1,8 @@
 # SPDX-FileCopyrightText: 2023 spdx contributors
 #
 # SPDX-License-Identifier: Apache-2.0
+from typing import Optional
+
 import xmltodict
 from beartype.typing import Any, Dict
 
@@ -36,8 +38,8 @@
 ]
 
 
-def parse_from_file(file_name: str) -> Document:
-    with open(file_name) as file:
+def parse_from_file(file_name: str, encoding: Optional[str] = None) -> Document:
+    with open(file_name, encoding=encoding) as file:
         parsed_xml: Dict = xmltodict.parse(file.read(), encoding="utf-8")
 
     input_doc_as_dict: Dict = _fix_list_like_fields(parsed_xml).get("Document")

diff --git a/src/spdx_tools/spdx/parser/yaml/yaml_parser.py b/src/spdx_tools/spdx/parser/yaml/yaml_parser.py
@@ -1,15 +1,17 @@
 # SPDX-FileCopyrightText: 2023 spdx contributors
 #
 # SPDX-License-Identifier: Apache-2.0
+from typing import Optional
+
 import yaml
 from beartype.typing import Dict
 
 from spdx_tools.spdx.model import Document
 from spdx_tools.spdx.parser.jsonlikedict.json_like_dict_parser import JsonLikeDictParser
 
 
-def parse_from_file(file_name: str) -> Document:
-    with open(file_name) as file:
+def parse_from_file(file_name: str, encoding: Optional[str] = None) -> Document:
+    with open(file_name, encoding=encoding) as file:
         input_doc_as_dict: Dict = yaml.safe_load(file)
 
     return JsonLikeDictParser().parse(input_doc_as_dict)
diff --git a/tests/spdx/data/SPDXJSONExample-UTF-16.spdx.json b/tests/spdx/data/SPDXJSONExample-UTF-16.spdx.json
diff --git a/tests/spdx/data/SPDXRdfExample-UTF-16.spdx.rdf.xml b/tests/spdx/data/SPDXRdfExample-UTF-16.spdx.rdf.xml
diff --git a/tests/spdx/data/SPDXTagExample-UTF-16.spdx b/tests/spdx/data/SPDXTagExample-UTF-16.spdx
diff --git a/tests/spdx/data/SPDXXMLExample-UTF-16.spdx.xml b/tests/spdx/data/SPDXXMLExample-UTF-16.spdx.xml
diff --git a/tests/spdx/data/SPDXYAMLExample-UTF-16.spdx.yaml b/tests/spdx/data/SPDXYAMLExample-UTF-16.spdx.yaml
diff --git a/tests/spdx/parser/all_formats/test_parse_from_file.py b/tests/spdx/parser/all_formats/test_parse_from_file.py
@@ -44,7 +44,7 @@ def test_parse_from_file_with_2_3_example(self, parser, format_name, extension):
         assert len(doc.relationships) == 13
         assert len(doc.extracted_licensing_info) == 5
 
-    def test_parse_json_with_2_2_example(self, parser, format_name, extension):
+    def test_parse_from_file_with_2_2_example(self, parser, format_name, extension):
         doc = parser.parse_from_file(
             os.path.join(os.path.dirname(__file__), f"../../data/SPDX{format_name}Example-v2.2.spdx{extension}")
         )
@@ -55,3 +55,16 @@ def test_parse_json_with_2_2_example(self, parser, format_name, extension):
         assert len(doc.snippets) == 1
         assert len(doc.relationships) == 11
         assert len(doc.extracted_licensing_info) == 5
+
+    def test_parse_from_file_with_encoding_example(self, parser, format_name, extension):
+        doc = parser.parse_from_file(
+            os.path.join(os.path.dirname(__file__), f"../../data/SPDX{format_name}Example-UTF-16.spdx{extension}"),
+            "utf-16",
+        )
+        assert isinstance(doc, Document)
+        assert len(doc.annotations) == 5
+        assert len(doc.files) == 4
+        assert len(doc.packages) == 4
+        assert len(doc.snippets) == 1
+        assert len(doc.relationships) == 11
+        assert len(doc.extracted_licensing_info) == 5