Merge pull request #3 from m3brown/tests

Set up test framework

.gitignore

@@ -0,0 +1,162 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

Dockerfile.test

@@ -0,0 +1,9 @@
+FROM python:3.12-alpine
+
+COPY *.py *.txt tests /script/
+
+RUN pip install --no-cache-dir -r /script/requirements-test.txt \
+    && rm -rf /tmp/* /var/tmp/* /var/cache/apk/* /var/cache/distfiles/*
+
+WORKDIR /script
+CMD ["python", "-m", "pytest"]

README.md

@@ -57,6 +57,12 @@ Or with Docker exec:
 docker exec -it immich-auto-stack /script/immich_auto_stack.sh
 ```
 
+## Running tests
+
+```sh
+docker build -f Dockerfile.test -t immich-auto-stack-pytest .
+docker run immich-auto-stack-pytest
+=======
 ## Customizing the criteria
 
 Configurable criteria allows for the customization of how files are grouped
@@ -79,8 +85,6 @@ The default in pretty json is:
 
 Functionally, this JSON config is the same as the lamdba implementation currently in place:
 
-
-
 ```python
 lambda x: (
   x["originalFileName"].split(".")[0],
@@ -95,6 +99,13 @@ The CRITERIA env var.
 docker -e CRITERIA='[{"key": "originalFileName", "split": {"key": "_", "index": 0}}]' ...
 ```
 
+This is the equivalent of: 
+```python
+lambda x: (
+  x["originalFileName"].split("_")[0]
+)
+```
+
 The parser also supports regex, which adds a lot more flexibility.
 The index will select a substring using `re.match.group(index)`. For example:
 

pyproject.toml

@@ -0,0 +1,4 @@
+[tool.pytest.ini_options]
+pythonpath = [
+  "."
+]

requirements-test.txt

@@ -0,0 +1,11 @@
+-r requirements.txt
+
+exceptiongroup==1.2.2
+Faker==27.0.0
+iniconfig==2.0.0
+packaging==24.1
+pluggy==1.5.0
+pytest==8.3.2
+python-dateutil==2.9.0.post0
+six==1.16.0
+tomli==2.0.1

tests/test_stackBy.py

@@ -0,0 +1,105 @@
+from faker import Faker
+import pytest
+from unittest.mock import ANY
+
+from immich_auto_stack import stackBy
+
+
+def mock_criteria(x):
+    return (x["originalFileName"].split(".")[0], x["localDateTime"])
+
+
+fake = Faker()
+
+
+def asset_factory(file_base=None, date_time=None, extension="jpg"):
+    file_name = (file_base or fake.unique.file_name(extension="")) + "." + extension
+    return {
+        "originalFileName": file_name,
+        "localDateTime": date_time or fake.unique.date_time(),
+    }
+
+
+@pytest.mark.parametrize(
+    "test_base1,test_ext1,test_base2,test_ext2",
+    [
+        ("test_filename", "raw", "test_filename2", "raw"),
+        ("test_Filename", "raw", "test_filename", "raw"),
+        ("_", "raw", "__", "raw"),
+        ("test_filename", "Jpg", "test_filename2", "Jpg"),
+        ("test_filename", "tar.jpg", "test_filename2", "tar.jpg"),
+    ],
+)
+def test_stackBy_creates_two_groups_for_different_filenames(
+    test_base1, test_ext1, test_base2, test_ext2
+):
+    # Arrange
+    file1_1 = asset_factory(file_base=test_base1, extension=test_ext1)
+    file1_2 = asset_factory(file_base=test_base1, date_time=file1_1["localDateTime"])
+    file2_1 = asset_factory(file_base=test_base2, extension=test_ext2)
+    file2_2 = asset_factory(file_base=test_base2, date_time=file2_1["localDateTime"])
+    expected_result = [
+        ((test_base1, file1_1["localDateTime"]), ANY),
+        ((test_base2, file2_1["localDateTime"]), ANY),
+    ]
+
+    # Act
+    result = stackBy(data=[file1_1, file2_1, file1_2, file2_2], criteria=mock_criteria)
+
+    # Assert
+    assert result == expected_result
+
+
+@pytest.mark.parametrize(
+    "extensions",
+    [
+        ["raw", "jpg"],
+        ["raw", "jpg", "txt", "XMP"],
+        ["raw", "png", "_"],
+        ["jpg", "5"],
+    ],
+)
+def test_stackBy_creates_list_of_file_assets_within_group(extensions):
+    # Arrange
+    extensions.sort()
+    test_file_base = "test_filename"
+    test_date_time = fake.date_time()
+    assets = [
+        asset_factory(file_base=test_file_base, extension=e, date_time=test_date_time)
+        for e in extensions
+    ]
+    expected_result = [((test_file_base, test_date_time), assets)]
+
+    # Act
+    result = stackBy(data=assets, criteria=mock_criteria)
+
+    # Assert
+    assert result == expected_result
+    assert len(result[0][1]) > 1
+
+
+def test_stackBy_does_not_group_files_with_same_date_time_but_different_filename():
+    # Arrange
+    test_date_time = fake.date_time()
+    file_1 = asset_factory(date_time=test_date_time)
+    file_2 = asset_factory(date_time=test_date_time)
+    expected_result = []
+
+    # Act
+    result = stackBy(data=[file_1, file_2], criteria=mock_criteria)
+
+    # Assert
+    assert result == expected_result
+
+
+def test_stackBy_does_not_group_files_with_same_filename_but_different_datetime():
+    # Arrange
+    file_1 = asset_factory(file_base="test_filename", extension="jpg")
+    file_2 = asset_factory(file_base="test_filename", extension="raw")
+    expected_result = []
+
+    # Act
+    result = stackBy(data=[file_1, file_2], criteria=mock_criteria)
+
+    # Assert
+    assert result == expected_result