[issue-573] unify parse_from_file tests for all formats

.github/workflows/install_and_test.yml

@@ -32,7 +32,7 @@ jobs:
       - name: Run tests
         run: pytest
       - name: Run CLI
-        run: pyspdxtools -i ./tests/spdx/data/formats/SPDXJSONExample-v2.3.spdx.json
+        run: pyspdxtools -i ./tests/spdx/data/SPDXJSONExample-v2.3.spdx.json
 
       - name: Install optional dependencies
         run: python -m pip install networkx

README.md

@@ -64,32 +64,32 @@ instead of `bin`.
 * Use `pyspdxtools -i <filename>` where `<filename>` is the location of the file. The input format is inferred automatically from the file ending.
 
 * If you are using a source distribution, try running:  
-  `pyspdxtools -i tests/data/formats/SPDXJSONExample-v2.3.spdx.json`
+  `pyspdxtools -i tests/data/SPDXJSONExample-v2.3.spdx.json`
 
 2. **CONVERTING** (for converting one format to another):
 
 * Use `pyspdxtools -i <input_file> -o <output_file>` where `<input_file>` is the location of the file to be converted
   and `<output_file>` is the location of the output file. The input and output formats are inferred automatically from the file endings.
 
 * If you are using a source distribution, try running:  
-  `pyspdxtools -i tests/data/formats/SPDXJSONExample-v2.3.spdx.json -o output.tag` 
+  `pyspdxtools -i tests/data/SPDXJSONExample-v2.3.spdx.json -o output.tag` 
 
 * If you want to skip the validation process, provide the `--novalidation` flag, like so:  
-  `pyspdxtools -i tests/data/formats/SPDXJSONExample-v2.3.spdx.json -o output.tag --novalidation`  
+  `pyspdxtools -i tests/data/SPDXJSONExample-v2.3.spdx.json -o output.tag --novalidation`  
   (use this with caution: note that undetected invalid documents may lead to unexpected behavior of the tool)
 
 * For help use `pyspdxtools --help`
 
 3. **GRAPH GENERATION** (optional feature)
 
 * This feature generates a graph representing all elements in the SPDX document and their connections based on the provided
-  relationships. The graph can be rendered to a picture. Below is an example for the file `tests/data/formats/SPDXJSONExample-v2.3.spdx.json`:
+  relationships. The graph can be rendered to a picture. Below is an example for the file `tests/data/SPDXJSONExample-v2.3.spdx.json`:
 ![SPDXJSONExample-v2.3.spdx.png](assets/SPDXJSONExample-v2.3.spdx.png)
 * Make sure you install the optional dependencies `networkx` and `pygraphviz`. To do so run `pip install ".[graph_generation]"`.
 * Use `pyspdxtools -i <input_file> --graph -o <output_file>` where `<output_file>` is an output file name with valid format for `pygraphviz` (check 
   the documentation [here](https://pygraphviz.github.io/documentation/stable/reference/agraph.html#pygraphviz.AGraph.draw)). 
 * If you are using a source distribution, try running
-  `pyspdxtools -i tests/data/formats/SPDXJSONExample-v2.3.spdx.json --graph -o SPDXJSONExample-v2.3.spdx.png` to generate 
+  `pyspdxtools -i tests/data/SPDXJSONExample-v2.3.spdx.json --graph -o SPDXJSONExample-v2.3.spdx.png` to generate 
   a png with an overview of the structure of the example file.  
 
 ## Library usage

tests/spdx/parser/all_formats/test_parse_from_file.py

@@ -0,0 +1,57 @@
+# SPDX-FileCopyrightText: 2022 spdx contributors
+#
+# SPDX-License-Identifier: Apache-2.0
+
+import os
+
+import pytest
+
+from spdx.model.document import Document
+from spdx.parser.json import json_parser
+from spdx.parser.rdf import rdf_parser
+from spdx.parser.tagvalue import tagvalue_parser
+from spdx.parser.xml import xml_parser
+from spdx.parser.yaml import yaml_parser
+
+
+@pytest.mark.parametrize(
+    "parser, format_name, extension",
+    [
+        (json_parser, "JSON", ".json"),
+        (xml_parser, "XML", ".xml"),
+        (yaml_parser, "YAML", ".yaml"),
+        (rdf_parser, "Rdf", ".rdf.xml"),
+        (tagvalue_parser, "Tag", ""),
+    ],
+)
+class TestParseFromFile:
+    def test_parse_from_file_not_found(self, parser, format_name, extension):
+        with pytest.raises(FileNotFoundError) as err:
+            wrong_file_path = os.path.join(os.path.dirname(__file__), f"hnjfkjsedhnflsiafg.spdx{extension}")
+            parser.parse_from_file(wrong_file_path)
+
+        assert err.value.args[1] == "No such file or directory"
+
+    def test_parse_from_file_with_2_3_example(self, parser, format_name, extension):
+        doc = parser.parse_from_file(
+            os.path.join(os.path.dirname(__file__), f"../../data/SPDX{format_name}Example-v2.3.spdx{extension}")
+        )
+        assert type(doc) == Document
+        assert len(doc.annotations) == 5
+        assert len(doc.files) == 5
+        assert len(doc.packages) == 4
+        assert len(doc.snippets) == 1
+        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):
+        doc = parser.parse_from_file(
+            os.path.join(os.path.dirname(__file__), f"../../data/SPDX{format_name}Example-v2.2.spdx{extension}")
+        )
+        assert type(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

tests/spdx/parser/rdf/test_license_expression_parser.py

@@ -24,7 +24,7 @@ def test_license_expression_parser():
 
 def test_license_expression_parser_with_coupled_licenses():
     doc = rdf_parser.parse_from_file(
-        os.path.join(os.path.dirname(__file__), "../../data/formats/SPDXRdfExample-v2.3.spdx.rdf.xml")
+        os.path.join(os.path.dirname(__file__), "../../data/SPDXRdfExample-v2.3.spdx.rdf.xml")
     )
 
     packages_by_spdx_id = {package.spdx_id: package for package in doc.packages}

tests/spdx/parser/tagvalue/test_tag_value_parser.py

@@ -2,12 +2,10 @@
 # SPDX-FileCopyrightText: 2023 spdx contributors
 #
 # SPDX-License-Identifier: Apache-2.0
-import os
 
 import pytest
 
 from spdx.constants import DOCUMENT_SPDX_ID
-from spdx.model.document import Document
 from spdx.model.relationship import Relationship, RelationshipType
 from spdx.parser.error import SPDXParsingError
 from spdx.parser.tagvalue.parser import Parser
@@ -22,22 +20,6 @@ def test_parse_unknown_tag():
         parser.parse(unknown_tag_str)
 
 
-def test_tag_value_parser():
-    parser = Parser()
-    fn = os.path.join(os.path.dirname(__file__), "../../data/formats/SPDXTagExample-v2.3.spdx")
-
-    with open(fn) as f:
-        data = f.read()
-        doc = parser.parse(data)
-    assert type(doc) == Document
-    assert len(doc.annotations) == 5
-    assert len(doc.files) == 5
-    assert len(doc.packages) == 4
-    assert len(doc.snippets) == 1
-    assert len(doc.relationships) == 13
-    assert len(doc.extracted_licensing_info) == 5
-
-
 def test_building_contains_relationship():
     parser = Parser()
     document_str = "\n".join(

tests/spdx/test_graph_generation.py

@@ -60,7 +60,7 @@ def test_generate_graph_from_spdx(
     edges_count: int,
     relationship_node_keys: List[str],
 ) -> None:
-    document = parse_file(str(Path(__file__).resolve().parent.parent / "spdx" / "data" / "formats" / file_name))
+    document = parse_file(str(Path(__file__).resolve().parent.parent / "spdx" / "data" / file_name))
     graph = generate_relationship_graph_from_spdx(document)
 
     assert document.creation_info.spdx_id in graph.nodes()