test: add basic integration test (#1)

* chore: run integration tests on ci

* chore: update env for python development

* test: add initial integration test

* chore: update gitignore

* test: use subprocess

* test: use temporary directory for saving files

* test: creste test utils file

* chore: specify python version for ci

* test: simplify temp directory creation

* chore: order imports

.editorconfig

@@ -11,3 +11,7 @@ trim_trailing_whitespace = true
 indent_style = tab
 indent_size = 4
 trim_trailing_whitespace = true
+
+[*.py]
+indent_style = space
+indent_size = 4

.github/workflows/ci.yml

@@ -14,9 +14,14 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
       - name: golangci-lint
         uses: golangci/golangci-lint-action@v3
         with:
           version: v1.54
       - name: Unit tests
         run: go test -v ./...
+      - name: Integration tests
+        run: python -m unittest discover -v -s test

.gitignore

@@ -1,5 +1,5 @@
-# Created by https://www.toptal.com/developers/gitignore/api/macos,visualstudiocode,go
-# Edit at https://www.toptal.com/developers/gitignore?templates=macos,visualstudiocode,go
+# Created by https://www.toptal.com/developers/gitignore/api/go,macos,visualstudiocode,python
+# Edit at https://www.toptal.com/developers/gitignore?templates=go,macos,visualstudiocode,python
 
 ### Go ###
 # If you prefer the allow list template instead of the deny list, see community template:
@@ -57,6 +57,177 @@ Temporary Items
 # iCloud generated files
 *.icloud
 
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+
+# 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/#use-with-ide
+.pdm.toml
+
+# 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/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
 ### VisualStudioCode ###
 .vscode/*
 !.vscode/settings.json
@@ -76,4 +247,8 @@ Temporary Items
 .history
 .ionide
 
-# End of https://www.toptal.com/developers/gitignore/api/macos,visualstudiocode,go
+# Custom
+
+images/
+
+# End of https://www.toptal.com/developers/gitignore/api/go,macos,visualstudiocode,python

test/test_integration.py

@@ -0,0 +1,44 @@
+import subprocess
+import unittest
+from tempfile import TemporaryDirectory
+
+from utils import Server, does_directory_contains_file
+
+
+class BigIntegrationTest(unittest.TestCase):
+    server: Server
+    directory: TemporaryDirectory
+
+    def setUp(self) -> None:
+        self.server = Server()
+        self.server.start()
+        self.directory = TemporaryDirectory()
+
+    def test_download_images_from_html_and_save_to_directory(self):
+        # when the server is running, run the program to download images
+        subprocess.run(
+            [
+                "go",
+                "run",
+                "main.go",
+                "html",
+                self.server.url,
+                "-d",
+                self.directory.name,
+            ],
+            check=True,
+        )
+
+        # then check if the images were downloaded to the file system
+        self.assertTrue(does_directory_contains_file(self.directory.name, "300.jpeg"))
+        self.assertTrue(does_directory_contains_file(self.directory.name, "800.jpeg"))
+        self.assertTrue(does_directory_contains_file(self.directory.name, "1350.jpeg"))
+
+
+    def tearDown(self) -> None:
+        self.server.stop()
+        self.directory.cleanup()
+
+
+if __name__ == "__main__":
+    unittest.main()

test/testdata/index.html

@@ -0,0 +1,13 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+  <meta charset="UTF-8">
+  <meta name="viewport" content="width=device-width, initial-scale=1.0">
+  <title>Big Image Getter Static Site</title>
+</head>
+<body>
+  <img src="https://picsum.photos/200/300" />
+  <img src="https://picsum.photos/1200/800" />
+  <img src="https://picsum.photos/2400/1350" />
+</body>
+</html>

test/utils.py

@@ -0,0 +1,41 @@
+import http.server
+import os
+from threading import Thread
+from typing import Final
+
+PORT: Final[int] = 8080
+DIRECTORY: Final[str] = os.path.join(
+    os.path.dirname(os.path.realpath(__file__)), "testdata/"
+)
+
+
+def does_directory_contains_file(path: str, file: str) -> bool:
+    """
+    Checks if the given directory contains the given file
+    """
+    return os.path.isfile(os.path.join(path, file))
+
+
+class Server:
+    """
+    A simple HTTP server that serves files from the given directory
+    """
+
+    class Handler(http.server.SimpleHTTPRequestHandler):
+        def __init__(self, *args, **kwargs):
+            super().__init__(*args, directory=DIRECTORY, **kwargs)
+
+    def __init__(self):
+        self.server = http.server.HTTPServer(("", PORT), self.Handler)
+
+    def start(self) -> None:
+        thread = Thread(target=self.server.serve_forever)
+        thread.start()
+
+    def stop(self) -> None:
+        thread = Thread(target=self.server.shutdown)
+        thread.start()
+
+    @property
+    def url(self) -> str:
+        return f"http://localhost:{self.server.server_port}"