Merge pull request #3314 from boxydog/more_ruff_fixes2

.git-blame-ignore-revs

@@ -11,3 +11,5 @@ db241feaa445375dc05e189e69287000ffe5fa8e
 0bd02c00c078fe041b65fbf4eab13601bb42676d
 # Apply more Ruff checks to code
 9d30c5608a58d202b1c02d55651e6ac746bfb173
+# Apply yet more Ruff checks to code
+7577dd7603f7cb3a09922d1edb65b6eafb6e2ac7

pelican/__init__.py

@@ -417,7 +417,7 @@ def parse_arguments(argv=None):
         "--relative-urls",
         dest="relative_paths",
         action="store_true",
-        help="Use relative urls in output, " "useful for site development",
+        help="Use relative urls in output, useful for site development",
     )
 
     parser.add_argument(
@@ -433,7 +433,7 @@ def parse_arguments(argv=None):
         "--ignore-cache",
         action="store_true",
         dest="ignore_cache",
-        help="Ignore content cache " "from previous runs by not loading cache files.",
+        help="Ignore content cache from previous runs by not loading cache files.",
     )
 
     parser.add_argument(
@@ -488,7 +488,7 @@ def parse_arguments(argv=None):
         "-b",
         "--bind",
         dest="bind",
-        help="IP to bind to when serving files via HTTP " "(default: 127.0.0.1)",
+        help="IP to bind to when serving files via HTTP (default: 127.0.0.1)",
     )
 
     parser.add_argument(

pelican/contents.py

@@ -72,7 +72,7 @@ class Content:
         self._context = context
         self.translations = []
 
-        local_metadata = dict()
+        local_metadata = {}
         local_metadata.update(metadata)
 
         # set metadata as attributes
@@ -357,7 +357,7 @@ class Content:
             origin = joiner(siteurl, Author(path, self.settings).url)
         else:
             logger.warning(
-                "Replacement Indicator '%s' not recognized, " "skipping replacement",
+                "Replacement Indicator '%s' not recognized, skipping replacement",
                 what,
             )
 

pelican/generators.py

@@ -156,7 +156,7 @@ class Generator:
 
         return False
 
-    def get_files(self, paths, exclude=[], extensions=None):
+    def get_files(self, paths, exclude=None, extensions=None):
         """Return a list of files to use, based on rules
 
         :param paths: the list pf paths to search (relative to self.path)
@@ -164,6 +164,8 @@ class Generator:
         :param extensions: the list of allowed extensions (if False, all
             extensions are allowed)
         """
+        if exclude is None:
+            exclude = []
         # backward compatibility for older generators
         if isinstance(paths, str):
             paths = [paths]
@@ -1068,7 +1070,7 @@ class StaticGenerator(Generator):
         except OSError as err:
             if err.errno == errno.EXDEV:  # 18: Invalid cross-device link
                 logger.debug(
-                    "Cross-device links not valid. " "Creating symbolic links instead."
+                    "Cross-device links not valid. Creating symbolic links instead."
                 )
                 self.fallback_to_symlinks = True
                 self._link_staticfile(sc)

pelican/paginator.py

@@ -131,9 +131,8 @@ class Page:
                 if not self.has_next():
                     rule = p
                     break
-            else:
+            elif p.min_page <= self.number:
-                if p.min_page <= self.number:
+                rule = p
-                    rule = p
 
         if not rule:
             return ""

pelican/readers.py

@@ -199,7 +199,7 @@ class RstReader(BaseReader):
             self._language_code = lang_code
         else:
             logger.warning(
-                "Docutils has no localization for '%s'." " Using 'en' instead.",
+                "Docutils has no localization for '%s'. Using 'en' instead.",
                 lang_code,
             )
             self._language_code = "en"
@@ -320,7 +320,7 @@ class MarkdownReader(BaseReader):
             elif not DUPLICATES_DEFINITIONS_ALLOWED.get(name, True):
                 if len(value) > 1:
                     logger.warning(
-                        "Duplicate definition of `%s` " "for %s. Using first one.",
+                        "Duplicate definition of `%s` for %s. Using first one.",
                         name,
                         self._source_path,
                     )

pelican/rstdirectives.py

@@ -78,7 +78,7 @@ class abbreviation(nodes.Inline, nodes.TextElement):
     pass
 
 
-def abbr_role(typ, rawtext, text, lineno, inliner, options={}, content=[]):
+def abbr_role(typ, rawtext, text, lineno, inliner, options=None, content=None):
     text = utils.unescape(text)
     m = _abbr_re.search(text)
     if m is None:

pelican/settings.py

@@ -447,7 +447,7 @@ def handle_deprecated_settings(settings: Settings) -> Settings:
             and not isinstance(settings[key], Path)
             and "%s" in settings[key]
         ):
-            logger.warning("%%s usage in %s is deprecated, use {lang} " "instead.", key)
+            logger.warning("%%s usage in %s is deprecated, use {lang} instead.", key)
             try:
                 settings[key] = _printf_s_to_format_field(settings[key], "lang")
             except ValueError:
@@ -470,7 +470,7 @@ def handle_deprecated_settings(settings: Settings) -> Settings:
             and not isinstance(settings[key], Path)
             and "%s" in settings[key]
         ):
-            logger.warning("%%s usage in %s is deprecated, use {slug} " "instead.", key)
+            logger.warning("%%s usage in %s is deprecated, use {slug} instead.", key)
             try:
                 settings[key] = _printf_s_to_format_field(settings[key], "slug")
             except ValueError:
@@ -614,7 +614,7 @@ def configure_settings(settings: Settings) -> Settings:
         if key in settings and not isinstance(settings[key], types):
             value = settings.pop(key)
             logger.warn(
-                "Detected misconfigured %s (%s), " "falling back to the default (%s)",
+                "Detected misconfigured %s (%s), falling back to the default (%s)",
                 key,
                 value,
                 DEFAULT_CONFIG[key],
@@ -676,7 +676,7 @@ def configure_settings(settings: Settings) -> Settings:
     if any(settings.get(k) for k in feed_keys):
         if not settings.get("SITEURL"):
             logger.warning(
-                "Feeds generated without SITEURL set properly may" " not be valid"
+                "Feeds generated without SITEURL set properly may not be valid"
             )
 
     if "TIMEZONE" not in settings:

pelican/tests/test_contents.py

@@ -314,7 +314,7 @@ class TestPage(TestBase):
         args["settings"] = settings
 
         # Tag
-        args["content"] = "A simple test, with a " '<a href="|tag|tagname">link</a>'
+        args["content"] = 'A simple test, with a <a href="|tag|tagname">link</a>'
         page = Page(**args)
         content = page.get_content("http://notmyidea.org")
         self.assertEqual(
@@ -326,9 +326,7 @@ class TestPage(TestBase):
         )
 
         # Category
-        args["content"] = (
+        args["content"] = 'A simple test, with a <a href="|category|category">link</a>'
-            "A simple test, with a " '<a href="|category|category">link</a>'
-        )
         page = Page(**args)
         content = page.get_content("http://notmyidea.org")
         self.assertEqual(
@@ -350,7 +348,7 @@ class TestPage(TestBase):
 
         # Classic intrasite link via filename
         args["content"] = (
-            "A simple test, with a " '<a href="|filename|article.rst">link</a>'
+            'A simple test, with a <a href="|filename|article.rst">link</a>'
         )
         content = Page(**args).get_content("http://notmyidea.org")
         self.assertEqual(
@@ -401,7 +399,7 @@ class TestPage(TestBase):
 
         # also test for summary in metadata
         parsed = (
-            "A simple summary test, with a " '<a href="|filename|article.rst">link</a>'
+            'A simple summary test, with a <a href="|filename|article.rst">link</a>'
         )
         linked = (
             "A simple summary test, with a "
@@ -594,7 +592,7 @@ class TestPage(TestBase):
 
         # An intrasite link via filename with %20 as a space
         args["content"] = (
-            "A simple test, with a " '<a href="|filename|article%20spaces.rst">link</a>'
+            'A simple test, with a <a href="|filename|article%20spaces.rst">link</a>'
         )
         content = Page(**args).get_content("http://notmyidea.org")
         self.assertEqual(
@@ -834,10 +832,10 @@ class TestStatic(LoggedTestCase):
 
         otherdir_settings = self.settings.copy()
         otherdir_settings.update(
-            dict(
+            {
-                PAGE_SAVE_AS=os.path.join("otherpages", "{slug}.html"),
+                "PAGE_SAVE_AS": os.path.join("otherpages", "{slug}.html"),
-                PAGE_URL="otherpages/{slug}.html",
+                "PAGE_URL": "otherpages/{slug}.html",
-            )
+            }
         )
         otherdir_page = Page(
             content="other page",
@@ -892,7 +890,7 @@ class TestStatic(LoggedTestCase):
         """
         customstatic = Static(
             content=None,
-            metadata=dict(save_as="customfoo.jpg", url="customfoo.jpg"),
+            metadata={"save_as": "customfoo.jpg", "url": "customfoo.jpg"},
             settings=self.settings,
             source_path=os.path.join("dir", "foo.jpg"),
             context=self.settings.copy(),
@@ -1066,9 +1064,9 @@ class TestStatic(LoggedTestCase):
 
         static = Static(
             content=None,
-            metadata=dict(
+            metadata={
-                status="draft",
+                "status": "draft",
-            ),
+            },
             settings=self.settings,
             source_path=os.path.join("dir", "foo.jpg"),
             context=self.settings.copy(),

pelican/tests/test_importer.py

@@ -71,7 +71,7 @@ class TestBloggerXmlImporter(TestCaseWithCLocale):
         )
         comment_titles = {x[0] for x in test_posts if x[8] == "comment"}
         self.assertEqual(
-            {"Mishka, always a pleasure to read your " "adventures!..."}, comment_titles
+            {"Mishka, always a pleasure to read your adventures!..."}, comment_titles
         )
 
     def test_recognise_status_with_correct_filename(self):
@@ -478,7 +478,7 @@ class TestBuildHeader(unittest.TestCase):
             attachments=["output/test1", "output/test2"],
         )
         self.assertEqual(
-            header, ("test\n####\n" ":attachments: output/test1, " "output/test2\n\n")
+            header, ("test\n####\n:attachments: output/test1, output/test2\n\n")
         )
 
     def test_galleries_added_to_markdown_header(self):
@@ -521,10 +521,10 @@ class TestWordpressXMLAttachements(TestCaseWithCLocale):
                 self.assertEqual(self.attachments[post], expected)
             elif post == "with-excerpt":
                 expected_invalid = (
-                    "http://thisurlisinvalid.notarealdomain/" "not_an_image.jpg"
+                    "http://thisurlisinvalid.notarealdomain/not_an_image.jpg"
                 )
                 expected_pelikan = (
-                    "http://en.wikipedia.org/wiki/" "File:Pelikan_Walvis_Bay.jpg"
+                    "http://en.wikipedia.org/wiki/File:Pelikan_Walvis_Bay.jpg"
                 )
                 self.assertEqual(
                     self.attachments[post], {expected_invalid, expected_pelikan}
@@ -533,9 +533,7 @@ class TestWordpressXMLAttachements(TestCaseWithCLocale):
                 expected_invalid = "http://thisurlisinvalid.notarealdomain"
                 self.assertEqual(self.attachments[post], {expected_invalid})
             else:
-                self.fail(
+                self.fail(f"all attachments should match to a filename or None, {post}")
-                    "all attachments should match to a " f"filename or None, {post}"
-                )
 
     def test_download_attachments(self):
         real_file = os.path.join(CUR_DIR, "content/article.rst")

pelican/tests/test_readers.py

@@ -591,7 +591,7 @@ class MdReaderTest(ReaderTest):
             "modified": SafeDatetime(2012, 11, 1),
             "multiline": [
                 "Line Metadata should be handle properly.",
-                "See syntax of Meta-Data extension of " "Python Markdown package:",
+                "See syntax of Meta-Data extension of Python Markdown package:",
                 "If a line is indented by 4 or more spaces,",
                 "that line is assumed to be an additional line of the value",
                 "for the previous keyword.",

pelican/tests/test_utils.py

@@ -922,14 +922,14 @@ class TestSanitisedJoin(unittest.TestCase):
     def test_detect_parent_breakout(self):
         with self.assertRaisesRegex(
             RuntimeError,
-            "Attempted to break out of output directory to " "(.*?:)?/foo/test",
+            "Attempted to break out of output directory to (.*?:)?/foo/test",
         ):  # (.*?:)? accounts for Windows root
             utils.sanitised_join("/foo/bar", "../test")
 
     def test_detect_root_breakout(self):
         with self.assertRaisesRegex(
             RuntimeError,
-            "Attempted to break out of output directory to " "(.*?:)?/test",
+            "Attempted to break out of output directory to (.*?:)?/test",
         ):  # (.*?:)? accounts for Windows root
             utils.sanitised_join("/foo/bar", "/test")
 

pelican/tools/pelican_import.py

@@ -1095,7 +1095,7 @@ def fields2pelican(
 
     if posts_require_pandoc:
         logger.error(
-            "Pandoc must be installed to import the following posts:" "\n  {}".format(
+            "Pandoc must be installed to import the following posts:\n  {}".format(
                 "\n  ".join(posts_require_pandoc)
             )
         )
@@ -1232,7 +1232,7 @@ def main():
             exit(error)
 
     if args.wp_attach and input_type != "wordpress":
-        error = "You must be importing a wordpress xml " "to use the --wp-attach option"
+        error = "You must be importing a wordpress xml to use the --wp-attach option"
         exit(error)
 
     if input_type == "blogger":

pelican/tools/pelican_quickstart.py

@@ -103,11 +103,10 @@ def ask(question, answer=str, default=None, length=None):
                     break
                 else:
                     print("You must enter something")
+            elif length and len(r) != length:
+                print(f"Entry must be {length} characters long")
             else:
-                if length and len(r) != length:
+                break
-                    print(f"Entry must be {length} characters long")
-                else:
-                    break
 
         return r
 
@@ -169,7 +168,7 @@ def ask_timezone(question, default, tzurl):
             r = tz_dict[r]
             break
         else:
-            print("Please enter a valid time zone:\n" f" (check [{tzurl}])")
+            print(f"Please enter a valid time zone:\n (check [{tzurl}])")
     return r
 
 
@@ -253,7 +252,7 @@ needed by Pelican.
         default=True,
     ):
         CONF["siteurl"] = ask(
-            "What is your URL prefix? (see " "above example; no trailing slash)",
+            "What is your URL prefix? (see above example; no trailing slash)",
             str,
             CONF["siteurl"],
         )
@@ -266,7 +265,7 @@ needed by Pelican.
 
     if CONF["with_pagination"]:
         CONF["default_pagination"] = ask(
-            "How many articles per page " "do you want?",
+            "How many articles per page do you want?",
             int,
             CONF["default_pagination"],
         )
@@ -296,7 +295,7 @@ needed by Pelican.
                 "What is your username on that server?", str, CONF["ftp_user"]
             )
             CONF["ftp_target_dir"] = ask(
-                "Where do you want to put your " "web site on that server?",
+                "Where do you want to put your web site on that server?",
                 str,
                 CONF["ftp_target_dir"],
             )
@@ -314,7 +313,7 @@ needed by Pelican.
                 "What is your username on that server?", str, CONF["ssh_user"]
             )
             CONF["ssh_target_dir"] = ask(
-                "Where do you want to put your " "web site on that server?",
+                "Where do you want to put your web site on that server?",
                 str,
                 CONF["ssh_target_dir"],
             )
@@ -338,23 +337,23 @@ needed by Pelican.
             )
 
         if ask(
-            "Do you want to upload your website using " "Rackspace Cloud Files?",
+            "Do you want to upload your website using Rackspace Cloud Files?",
             answer=bool,
             default=False,
         ):
             CONF["cloudfiles"] = (True,)
             CONF["cloudfiles_username"] = ask(
-                "What is your Rackspace " "Cloud username?",
+                "What is your Rackspace Cloud username?",
                 str,
                 CONF["cloudfiles_username"],
             )
             CONF["cloudfiles_api_key"] = ask(
-                "What is your Rackspace " "Cloud API key?",
+                "What is your Rackspace Cloud API key?",
                 str,
                 CONF["cloudfiles_api_key"],
             )
             CONF["cloudfiles_container"] = ask(
-                "What is the name of your " "Cloud Files container?",
+                "What is the name of your Cloud Files container?",
                 str,
                 CONF["cloudfiles_container"],
             )
@@ -384,7 +383,7 @@ needed by Pelican.
     except OSError as e:
         print(f"Error: {e}")
 
-    conf_python = dict()
+    conf_python = {}
     for key, value in CONF.items():
         conf_python[key] = repr(value)
     render_jinja_template("pelicanconf.py.jinja2", conf_python, "pelicanconf.py")

pelican/urlwrappers.py

@@ -115,11 +115,10 @@ class URLWrapper:
         if not isinstance(value, str):
             logger.warning("%s is set to %s", setting, value)
             return value
+        elif get_page_name:
+            return os.path.splitext(value)[0].format(**self.as_dict())
         else:
-            if get_page_name:
+            return value.format(**self.as_dict())
-                return os.path.splitext(value)[0].format(**self.as_dict())
-            else:
-                return value.format(**self.as_dict())
 
     page_name = property(
         functools.partial(_from_settings, key="URL", get_page_name=True)

pelican/utils.py

@@ -25,9 +25,7 @@ from typing import (
     Collection,
     Generator,
     Iterable,
-    Optional,
     Sequence,
-    Union,
 )
 
 import dateutil.parser
@@ -167,7 +165,7 @@ class memoized:
             self.cache[args] = value
             return value
 
-    def __repr__(self) -> Optional[str]:
+    def __repr__(self) -> str | None:
         return self.func.__doc__
 
     def __get__(self, obj: Any, objtype):
@@ -181,8 +179,8 @@ def deprecated_attribute(
     old: str,
     new: str,
     since: tuple[int, ...],
-    remove: Optional[tuple[int, ...]] = None,
+    remove: tuple[int, ...] | None = None,
-    doc: Optional[str] = None,
+    doc: str | None = None,
 ):
     """Attribute deprecation decorator for gentle upgrades
 
@@ -296,9 +294,7 @@ def slugify(
     return value.strip()
 
 
-def copy(
+def copy(source: str, destination: str, ignores: Iterable[str] | None = None) -> None:
-    source: str, destination: str, ignores: Optional[Iterable[str]] = None
-) -> None:
     """Recursively copy source into destination.
 
     If source is a file, destination has to be a file as well.
@@ -364,7 +360,7 @@ def copy(
                     copy_file(src_path, dst_path)
                 else:
                     logger.warning(
-                        "Skipped copy %s (not a file or " "directory) to %s",
+                        "Skipped copy %s (not a file or directory) to %s",
                         src_path,
                         dst_path,
                     )
@@ -474,7 +470,7 @@ class _HTMLWordTruncator(HTMLParser):
         self.words_found = 0
         self.open_tags = []
         self.last_word_end = None
-        self.truncate_at: Optional[int] = None
+        self.truncate_at: int | None = None
 
     def feed(self, *args, **kwargs) -> None:
         try:
@@ -573,11 +569,10 @@ class _HTMLWordTruncator(HTMLParser):
         if self.last_word_end is None:
             if self._word_prefix_regex.match(char):
                 self.last_word_end = ref_end
+        elif self._word_regex.match(char):
+            self.last_word_end = ref_end
         else:
-            if self._word_regex.match(char):
+            self.add_last_word()
-                self.last_word_end = ref_end
-            else:
-                self.add_last_word()
 
     def handle_entityref(self, name: str) -> None:
         """
@@ -638,7 +633,7 @@ def truncate_html_words(s: str, num: int, end_text: str = "…") -> str:
 
 def process_translations(
     content_list: list[Content],
-    translation_id: Optional[Union[str, Collection[str]]] = None,
+    translation_id: str | Collection[str] | None = None,
 ) -> tuple[list[Content], list[Content]]:
     """Finds translations and returns them.
 
@@ -739,7 +734,7 @@ def get_original_items(items: list[Content], with_str: str) -> list[Content]:
 
 def order_content(
     content_list: list[Content],
-    order_by: Union[str, Callable[[Content], Any], None] = "slug",
+    order_by: str | Callable[[Content], Any] | None = "slug",
 ) -> list[Content]:
     """Sorts content.
 
@@ -841,7 +836,7 @@ def wait_for_changes(
 
 
 def set_date_tzinfo(
-    d: datetime.datetime, tz_name: Optional[str] = None
+    d: datetime.datetime, tz_name: str | None = None
 ) -> datetime.datetime:
     """Set the timezone for dates that don't have tzinfo"""
     if tz_name and not d.tzinfo:
@@ -857,7 +852,7 @@ def mkdir_p(path: str) -> None:
     os.makedirs(path, exist_ok=True)
 
 
-def split_all(path: Union[str, pathlib.Path, None]) -> Optional[Sequence[str]]:
+def split_all(path: str | pathlib.Path | None) -> Sequence[str] | None:
     """Split a path into a list of components
 
     While os.path.split() splits a single component off the back of
@@ -911,7 +906,7 @@ def maybe_pluralize(count: int, singular: str, plural: str) -> str:
 
 @contextmanager
 def temporary_locale(
-    temp_locale: Optional[str] = None, lc_category: int = locale.LC_ALL
+    temp_locale: str | None = None, lc_category: int = locale.LC_ALL
 ) -> Generator[None, None, None]:
     """
     Enable code to run in a context with a temporary locale

pelican/writers.py

@@ -21,7 +21,7 @@ logger = logging.getLogger(__name__)
 class Writer:
     def __init__(self, output_path, settings=None):
         self.output_path = output_path
-        self.reminder = dict()
+        self.reminder = {}
         self.settings = settings or {}
         self._written_files = set()
         self._overridden_files = set()

pyproject.toml

@@ -182,14 +182,17 @@ ignore = [
     "INP001",  # implicit-namespace-package
     "RUF015",  # unnecessary-iterable-allocation-for-first-element
     "PLR1722",  # sys-exit-alias
+    # ruff-format wants us to ignore ISC001.  I don't love that, but okay.
+    # "warning: The following rules may cause conflicts when used with the formatter:
+    #  `ISC001`. To avoid unexpected behavior, we recommend disabling these rules,
+    #  either by removing them from the `select` or `extend-select` configuration,
+    #  or adding them to the `ignore` configuration."
     "ISC001",  # single-line-implicit-string-concatenation
-    "C408",  # unnecessary-collection-call
     "B904",  # raise-without-from-inside-except
-    "UP007",  # use `|` operator for union type annotations (PEP 604)
     "UP031",  # printf-string-formatting
-    "PLR5501",  # collapsible-else-if
+    # PERF203 has minimal performance impact, and you have to catch the exception
+    # inside the loop if you want to ignore it, so let's ignore PERF203.
     "PERF203",  # try-except-in-loop
-    "B006",  # mutable-argument-default
     # TODO: these only have one violation each in Dec 2023:
     "SLOT000",  # no-slots-in-str-subclass
     "PYI024",  # collections-named-tuple