jenkins-bot has submitted this change. (
https://gerrit.wikimedia.org/r/c/pywikibot/core/+/1121419?usp=email )
Change subject: [bugfix] Enable url without api, requests or script path in
Site constuctor
......................................................................
[bugfix] Enable url without api, requests or script path in Site constuctor
Enable url with empty path of urllib.parse.ParseResult in Site
constructor and Family.from_url method. This means that
//commons.wikimedia.org is a valid url for them. The previous
implementation requires a valid path e.g. //meta.wikimedia.org/w/api.php
with apipath.
Therefore if path of the URL scheme is empty, do not check for any
site._interwiki_urls() which holds all possible paths.
Some tests added.
Bug: T386665
Change-Id: Icd538fe05005e02d1061e30b8e160018218fe986
---
M pywikibot/__init__.py
M pywikibot/family.py
M tests/basesite_tests.py
M tests/family_tests.py
4 files changed, 48 insertions(+), 21 deletions(-)
Approvals:
Xqt: Looks good to me, approved
jenkins-bot: Verified
diff --git a/pywikibot/__init__.py b/pywikibot/__init__.py
index 2f6c4c0..9449596 100644
--- a/pywikibot/__init__.py
+++ b/pywikibot/__init__.py
@@ -171,6 +171,9 @@
.. versionchanged:: 7.3
Short creation if site code is equal to family name like
`Site('commons')`, `Site('meta')` or `Site('wikidata')`.
+ .. versionchanged:: 10.0
+ *url* does not have to contain an api, requests or script path
+ any longer.
:param code: language code (override config.mylang)
code may also be a sitename like 'wikipedia:test'
diff --git a/pywikibot/family.py b/pywikibot/family.py
index 70d1934..77e8da6 100644
--- a/pywikibot/family.py
+++ b/pywikibot/family.py
@@ -1,6 +1,6 @@
"""Objects representing MediaWiki families."""
#
-# (C) Pywikibot team, 2004-2024
+# (C) Pywikibot team, 2004-2025
#
# Distributed under the terms of the MIT license.
#
@@ -579,23 +579,27 @@
def from_url(self, url: str) -> str | None:
"""Return whether this family matches the given url.
- It is first checking if a domain of this family is in the domain of
- the URL. If that is the case it's checking all codes and verifies that
- a path generated via
- :py:obj:`APISite.articlepath<pywikibot.site.APISite.articlepath>` and
- :py:obj:`Family.path` matches the path of the URL together with
- the hostname for that code.
+ It is first checking if a domain of this family is in the domain
+ of the URL. If that is the case it's checking all codes and
+ verifies that a path generated via :attr:`APISite.articlepath
+ <pywikibot.site.APISite.articlepath>` and :attr:`Family.path`
+ matches the path of the URL together with the hostname for that
+ code.
- It is using :py:obj:`Family.domains` to first check if a domain
- applies and then iterates over :py:obj:`Family.codes` to actually
+ It is using :attr:`Family.domains` to first check if a domain
+ applies and then iterates over :attr:`Family.codes` to actually
determine which code applies.
- :param url: the URL which may contain a ``$1``. If it's missing it is
- assumed to be at the end.
- :return: The language code of the url. None if that url is not from
- this family.
- :raises RuntimeError: When there are multiple languages in this family
- which would work with the given URL.
+ .. versionchanged:: 10.0
+ *url* parameter does not have to contain a api/query/script
+ path
+
+ :param url: the URL which may contain a ``$1``. If it's missing
+ it is assumed to be at the end.
+ :return: The language code of the URL. None if that URL is not
+ from his family.
+ :raises RuntimeError: When there are multiple languages in this
+ family which would work with the given URL.
"""
parsed = urlparse.urlparse(url)
if parsed.scheme not in {'http', 'https', ''}:
@@ -625,6 +629,9 @@
site = pywikibot.Site(code, self.name)
pywikibot.log(f'Found candidate {site}')
+ if not path:
+ return site.code
+
for iw_url in site._interwiki_urls():
iw_url, *_ = iw_url.partition('{}')
if path.startswith(iw_url):
diff --git a/tests/basesite_tests.py b/tests/basesite_tests.py
index 1c7b497..eae3719 100755
--- a/tests/basesite_tests.py
+++ b/tests/basesite_tests.py
@@ -1,7 +1,7 @@
#!/usr/bin/env python3
"""Tests for the site module."""
#
-# (C) Pywikibot team, 2008-2024
+# (C) Pywikibot team, 2008-2025
#
# Distributed under the terms of the MIT license.
#
@@ -129,6 +129,20 @@
self.assertTrue(mysite.sametitle('MediaWiki:Always',
'MediaWiki:always'))
+ def test_site_with_url(self):
+ """Test site constructor with url."""
+ for fam in ('commons', 'meta'):
+ with self.subTest(family=fam):
+ site = pywikibot.Site(url=f'https://{fam}.wikimedia.org')
+ self.assertEqual(site, pywikibot.Site(fam))
+ self.assertEqual(site.family.name, fam)
+ self.assertEqual(site.code, fam)
+
+ site = pywikibot.Site(url='https://fr.wikipedia.org')
+ self.assertEqual(site, pywikibot.Site('wikipedia:fr'))
+ self.assertEqual(site.family.name, 'wikipedia')
+ self.assertEqual(site.code, 'fr')
+
if __name__ == '__main__':
with suppress(SystemExit):
diff --git a/tests/family_tests.py b/tests/family_tests.py
index 68e52ba..3bfa9ac 100755
--- a/tests/family_tests.py
+++ b/tests/family_tests.py
@@ -1,7 +1,7 @@
#!/usr/bin/env python3
"""Tests for the family module."""
#
-# (C) Pywikibot team, 2014-2024
+# (C) Pywikibot team, 2014-2025
#
# Distributed under the terms of the MIT license.
#
@@ -168,8 +168,8 @@
super().setUp()
self.articlepath = '/wiki/$1'
- def test_from_url_wikipedia_extra(self):
- """Test various URLs against wikipedia regex."""
+ def test_from_url(self):
+ """Test various URLs for Family.from_url."""
self.current_code = 'vo'
self.current_family = 'wikipedia'
@@ -181,6 +181,8 @@
self.assertEqual(f.from_url(prefix + '/w/index.php'), 'vo')
self.assertEqual(f.from_url(prefix + '/w/index.php/'), 'vo')
self.assertEqual(f.from_url(prefix + '/w/index.php?title=$1'), 'vo')
+ # url without scripts/api path
+ self.assertEqual(f.from_url(prefix), 'vo')
self.assertEqual(f.from_url(prefix + '/wiki/$1'), 'vo')
self.assertEqual(f.from_url('//vo.wikipedia.org/wiki/$1'), 'vo')
@@ -218,10 +220,11 @@
family = Family.load(family)
for code in family.codes:
self.current_code = code
- url = (f'{family.protocol(code)}://{family.hostname(code)}'
- f'{family.path(code)}/$1')
+ url = f'{family.protocol(code)}://{family.hostname(code)}'
+ url_with_path = url + f'{family.path(code)}/$1'
with self.subTest(url=url):
self.assertEqual(family.from_url(url), code)
+ self.assertEqual(family.from_url(url_with_path), code)
if __name__ == '__main__':
--
To view, visit
https://gerrit.wikimedia.org/r/c/pywikibot/core/+/1121419?usp=email
To unsubscribe, or for help writing mail filters, visit
https://gerrit.wikimedia.org/r/settings?usp=email
Gerrit-MessageType: merged
Gerrit-Project: pywikibot/core
Gerrit-Branch: master
Gerrit-Change-Id: Icd538fe05005e02d1061e30b8e160018218fe986
Gerrit-Change-Number: 1121419
Gerrit-PatchSet: 3
Gerrit-Owner: Xqt <[email protected]>
Gerrit-Reviewer: Xqt <[email protected]>
Gerrit-Reviewer: jenkins-bot
Gerrit-CC: Tacsipacsi <[email protected]>
_______________________________________________
Pywikibot-commits mailing list -- [email protected]
To unsubscribe send an email to [email protected]
