feat: Add pytest and initial tests

setup.py

@@ -65,6 +65,9 @@ setuptools.setup(
             "sphinx-rtd-theme",
             "recommonmark",
         ],
+        "test": [
+            "pytest"
+        ]
         # 'redis': ['redis', 'django-redis'],
         # 'pywb': ['pywb', 'redis'],
     },

tests/test_init.py

@@ -0,0 +1,40 @@
+# archivebox init
+# archivebox add
+
+import os
+import subprocess
+from pathlib import Path
+import json
+
+import pytest
+
+@pytest.fixture
+def process(tmp_path):
+    os.chdir(tmp_path)
+    process = subprocess.run(['archivebox', 'init'], capture_output=True)
+    return process
+
+
+def test_init(tmp_path, process):
+    assert "Initializing a new ArchiveBox collection in this folder..." in process.stdout.decode("utf-8")
+    
+def test_update(tmp_path, process):
+    os.chdir(tmp_path)
+    update_process = subprocess.run(['archivebox', 'init'], capture_output=True)
+    assert "Updating existing ArchiveBox collection in this folder" in update_process.stdout.decode("utf-8")
+
+def test_add_link(tmp_path, process):
+    os.chdir(tmp_path)
+    add_process = subprocess.run(['archivebox', 'add', 'http://example.com'], capture_output=True)
+    archived_item_path = list(tmp_path.glob('archive/**/*'))[0]
+
+    assert "index.json" in [x.name for x in archived_item_path.iterdir()]
+
+    with open(archived_item_path / "index.json", "r") as f:
+        output_json = json.load(f)
+    assert "IANA — IANA-managed Reserved Domains" == output_json['history']['title'][0]['output']
+
+    with open(tmp_path / "index.html", "r") as f:
+        output_html = f.read()
+    assert "IANA — IANA-managed Reserved Domains" in output_html
+

tests/test_util.py

@@ -0,0 +1,21 @@
+#@enforce_types
+#def download_url(url: str, timeout: int=None) -> str:
+#    """Download the contents of a remote url and return the text"""
+#    from .config import TIMEOUT, CHECK_SSL_VALIDITY, WGET_USER_AGENT
+#    timeout = timeout or TIMEOUT
+#    response = requests.get(
+#        url,
+#        headers={'User-Agent': WGET_USER_AGENT},
+#        verify=CHECK_SSL_VALIDITY,
+#        timeout=timeout,
+#    )
+#    if response.headers.get('Content-Type') == 'application/rss+xml':
+#        # Based on https://github.com/scrapy/w3lib/blob/master/w3lib/encoding.py
+#        _TEMPLATE = r'''%s\s*=\s*["']?\s*%s\s*["']?'''
+#        _XML_ENCODING_RE = _TEMPLATE % ('encoding', r'(?P<xmlcharset>[\w-]+)')
+#        _BODY_ENCODING_PATTERN = r'<\s*(\?xml\s[^>]+%s)' % (_XML_ENCODING_RE)
+#        _BODY_ENCODING_STR_RE = re.compile(_BODY_ENCODING_PATTERN, re.I | re.VERBOSE)
+#        match = _BODY_ENCODING_STR_RE.search(response.text[:1024])
+#        if match:
+#            response.encoding = match.group('xmlcharset')
+#    return response.text