Add snapshot tests (#253)

* added snapshots and new testdata

.gitignore

@@ -132,3 +132,7 @@ dmypy.json
 
 # vscode settings
 .vscode/
+
+# version number for ebdamame; gets auto-generated during the command
+# python -m build
+src/ebdamame/version.py

.pre-commit-config.yaml

@@ -1,18 +1,18 @@
 # to update all repo revisions just run: pre-commit autoupdate
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.3.0
+    rev: v5.0.0
     hooks:
       - id: check-yaml
       - id: end-of-file-fixer
       - id: trailing-whitespace
   - repo: https://github.com/psf/black
-    rev: 22.10.0
+    rev: 24.10.0
     hooks:
       - id: black
         language_version: python3
   - repo: https://github.com/pycqa/isort
-    rev: 5.10.1
+    rev: 5.13.2
     hooks:
       - id: isort
         name: isort (python)

pyproject.toml

@@ -47,7 +47,8 @@ test_packaging = [
 tests = [
     "pytest==8.3.3",
     "pytest-datafiles==3.0.0",
-    "pytest-subtests==0.13.1"
+    "pytest-subtests==0.13.1",
+    "syrupy==4.7.2"
 ]
 type_check = [
     "mypy==1.12.1"
@@ -96,3 +97,7 @@ exclude = ["/unittests"]
 [tool.hatch.build.targets.wheel]
 only-include = ["src"]
 sources = ["src"]
+
+[tool.pytest.ini_options]
+pythonpath = ["."]
+markers = ["snapshot: mark a test as a snapshot test"]

requirements.txt

@@ -17,6 +17,8 @@ charset-normalizer==3.3.2
     # via requests
 click==8.1.7
     # via -r requirements.in
+colorama==0.4.6
+    # via click
 idna==3.7
     # via requests
 lxml==5.2.1

tox.ini

@@ -19,6 +19,14 @@ deps =
 setenv = PYTHONPATH = {toxinidir}/src
 commands = python -m pytest --basetemp={envtmpdir} {posargs}
 
+[testenv:snapshots]
+# the tests environment is called by the Github action that runs the unit tests
+deps =
+    -r requirements.txt
+    .[tests]
+setenv = PYTHONPATH = {toxinidir}/src
+commands = python -m pytest -m snapshot --basetemp={envtmpdir} {posargs} --snapshot-update
+
 [testenv:linting]
 # the linting environment is called by the Github Action that runs the linter
 deps =

unittests/test_highlevel.py

@@ -212,27 +212,38 @@ def test_convert_docx_table_to_ebd_table(
         actual = converter.convert_docx_tables_to_ebd_table()
         assert actual == expected
 
+    @pytest.mark.snapshot
     @pytest.mark.datafiles("unittests/test_data/ebd20221128.docx")
     @pytest.mark.datafiles("unittests/test_data/ebd20230619_v33.docx")
     @pytest.mark.datafiles("unittests/test_data/ebd20230629_v34.docx")
+    @pytest.mark.datafiles("unittests/test_data/ebd20240403_v35.docx")
+    @pytest.mark.datafiles("unittests/test_data/ebd20250404_v40b.docx")
     @pytest.mark.parametrize(
         "get_ebd_keys_and_files",
-        [
+        [  # some are commented to improve performance make sure to update snapshots if needed
+            # pytest.param(
+            #    "ebd20221128.docx",  # this is used as positional argument for the indirect fixture
+            # ),
+            # pytest.param(
+            #    "ebd20230619_v33.docx",  # this is used as positional argument for the indirect fixture
+            #    id="19.06.2023 v3.3 / FV2304",
+            # ),
             pytest.param(
-                "ebd20221128.docx",  # this is used as positional argument for the indirect fixture
+                "ebd20230629_v34.docx",
+                id="19.06.2023 v3.4 / FV2310",
             ),
             pytest.param(
-                "ebd20230619_v33.docx",  # this is used as positional argument for the indirect fixture
-                id="19.06.2023 v3.3 / FV2304",
+                "ebd20240403_v35.docx",
+                id="08.10.2024 v3.5 / FV2410",
             ),
             pytest.param(
-                "ebd20230629_v34.docx",
-                id="19.06.2023 v3.4 / FV2310",
+                "ebd20250404_v40b.docx",
+                id="08.10.2024 v3.5 / FV2504",
             ),
         ],
         indirect=["get_ebd_keys_and_files"],  # see `def get_ebd_keys_and_files(datafiles, request)`
     )
-    def test_extraction(self, datafiles, get_ebd_keys_and_files: List[Tuple[str, str]], subtests):
+    def test_extraction(self, datafiles, get_ebd_keys_and_files: List[Tuple[str, str]], subtests, snapshot):
         """
         tests the extraction and conversion without specific assertions
         """
@@ -260,10 +271,11 @@ def test_extraction(self, datafiles, get_ebd_keys_and_files: List[Tuple[str, str
                     )
                     actual = converter.convert_docx_tables_to_ebd_table()
                     assert isinstance(actual, EbdTable)
+                    assert actual == snapshot(name=ebd_key)
                 # In the long run, all these catchers shall be removed.
                 except AttributeError as attribute_error:
                     if attribute_error.name == "_column_index_step_number":
-                        pytest.skip("https://github.com/Hochfrequenz/ebdamame/issues/71")
+                        pytest.skip(f"{ebd_key}\t https://github.com/Hochfrequenz/ebdamame/issues/71")
                 except TableNotFoundError:
                     # https://github.com/Hochfrequenz/ebdamame/issues/9
                     pass  # ignore for now
@@ -284,6 +296,8 @@ def test_extraction(self, datafiles, get_ebd_keys_and_files: List[Tuple[str, str
                         case "The cell content 'gültiges daten-ergebnis' does not belong to a ja/nein cell":
                             # https://github.com/Hochfrequenz/ebdamame/issues/74
                             issue_number = "74"
+                        case "No cell containing a valid step number found.":
+                            issue_number = "to be added"
                         case _:
                             raise
                     error_msg = f"Error while scraping '{ebd_key}' (#{issue_number}): {value_error}"