maintenance: update setup and add tests (#150)

* maintenance: update setup * adjust pytest paths * restore pytest.ini for now * add tests
adbar · May 29, 2024 · 9fb989d · 9fb989d
1 parent f33c1d9
commit 9fb989d
Show file tree

Hide file tree

Showing 6 changed files with 28 additions and 14 deletions.
diff --git a/.github/FUNDING.yml b/.github/FUNDING.yml
@@ -0,0 +1,12 @@
+# These are supported funding model platforms
+
+github: # Replace with up to 4 GitHub Sponsors-enabled usernames e.g., [user1, user2]
+patreon: # Replace with a single Patreon username
+open_collective: # Replace with a single Open Collective username
+ko_fi: adbarbaresi
+tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
+community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
+liberapay: # adbarbaresi
+issuehunt: # Replace with a single IssueHunt username
+otechie: # Replace with a single Otechie username
+custom: # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2']
diff --git a/MANIFEST.in b/MANIFEST.in
@@ -1,4 +1,4 @@
-include README.rst LICENSE pytest.ini CHANGELOG.md CONTRIBUTING.md
+include README.md CHANGELOG.md CONTRIBUTING.md LICENSE pyproject.toml
 include htmldate/py.typed
 include tests/unit_tests.py
 include tests/testlist.txt

diff --git a/setup.py b/setup.py
@@ -120,8 +120,8 @@ def get_version(package):
         "charset_normalizer >= 3.3.2; python_version >= '3.7'",
         "dateparser >= 1.1.2",  # 1.1.3+ slower
         # see tests on Github Actions
-        "lxml == 4.9.2; platform_system == 'Darwin' and python_version <= '3.8'",
-        "lxml >= 4.9.4, < 6; platform_system != 'Darwin' or python_version > '3.8'",
+        "lxml == 4.9.2 ; platform_system == 'Darwin' and python_version <= '3.8'",
+        "lxml >= 5.2.2, < 6 ; platform_system != 'Darwin' or python_version > '3.8'",
         "python-dateutil >= 2.8.2",
         "urllib3 >= 1.26, < 2; python_version < '3.7'",
         "urllib3 >= 1.26, < 3; python_version >= '3.7'",

diff --git a/tests/__init__.py b/tests/__init__.py
diff --git a/tests/eval-requirements.txt b/tests/eval-requirements.txt
@@ -1,12 +1,12 @@
 # package
-htmldate>=1.6.0
+htmldate>=1.8.1
 
 # alternatives
 articleDateExtractor==0.20
 date_guesser==2.1.4
-goose3==3.1.17
+goose3==3.1.19
 newspaper3k==0.2.8
-news-please==1.5.35
+news-please==1.5.44
 
 # helpers
 tabulate==0.9.0
diff --git a/tests/unit_tests.py b/tests/unit_tests.py
@@ -107,6 +107,7 @@ def test_input():
         assert load_html(123) is None
     assert "incompatible" in str(err.value)
     assert load_html("<" * 100) is None
+    assert load_html("<xml><body>ABC</body></xml>") is None
     assert load_html("<html><body>XYZ</body></html>") is not None
     assert load_html(b"<html><body>XYZ</body></html>") is not None
     assert load_html(b"<" * 100) is None
@@ -1660,6 +1661,14 @@ def test_dependencies():
         )
 
 
+def test_deferred():
+    "Test deferred extraction"
+    htmlstring = '<html><head><meta property="og:published_time" content="2017-09-01"/></head><body></body></html>'
+    url = "https://example.org/2017/08/30/this.html"
+    assert find_date(htmlstring, url=url, deferred_url_extractor=True) == "2017-09-01"
+    assert find_date(htmlstring, url=url, deferred_url_extractor=False) == "2017-08-30"
+
+
 if __name__ == "__main__":
     # function-level
     test_input()
@@ -1675,6 +1684,7 @@ def test_dependencies():
     # test_header()
 
     # module-level
+    test_deferred()
     test_no_date()
     test_exact_date()
     test_search_html()