Autoformat: black + clang-format + clang-tidy

.clang-format

@@ -0,0 +1,13 @@
+BasedOnStyle: LLVM
+AlignConsecutiveMacros: AcrossEmptyLines
+AllowShortFunctionsOnASingleLine: Inline
+AlwaysBreakAfterReturnType: TopLevelDefinitions
+BinPackArguments: false
+BinPackParameters: false
+BreakBeforeBraces: Linux
+ColumnLimit: 88
+IndentPPDirectives: AfterHash
+IndentWidth: 4
+SpaceAfterCStyleCast: true
+StatementMacros:
+  - PyObject_HEAD

.gitignore

@@ -13,5 +13,6 @@ dist
 docs/_build
 scripts/*.log
 htmlcov/
+compile_commands.json
 .idea/
 .pytest_cache/

scripts/memtest.py

@@ -41,6 +41,7 @@
 
 LOOPS = 10000
 
+
 class Color:
     GRAY = "\x1b[30;1m"
     GREEN = "\x1b[92m"
@@ -63,11 +64,11 @@ def _parse_file(self, name, text):
             data = {"name": None, "label": None, "input": None, "output": None}
             for line in test.strip().splitlines():
                 if line.startswith("name:"):
-                    data["name"] = line[len("name:"):].strip()
+                    data["name"] = line[len("name:") :].strip()
                 elif line.startswith("label:"):
-                    data["label"] = line[len("label:"):].strip()
+                    data["label"] = line[len("label:") :].strip()
                 elif line.startswith("input:"):
-                    raw = line[len("input:"):].strip()
+                    raw = line[len("input:") :].strip()
                     if raw[0] == '"' and raw[-1] == '"':
                         raw = raw[1:-1]
                     raw = raw.encode("raw_unicode_escape")
@@ -81,7 +82,7 @@ def _load(self):
         def load_file(filename):
             with open(filename, "rU") as fp:
                 text = fp.read()
-                name = path.split(filename)[1][:0-len(extension)]
+                name = path.split(filename)[1][: 0 - len(extension)]
                 self._parse_file(name, text)
 
         root = path.split(path.dirname(path.abspath(__file__)))[0]
@@ -119,8 +120,11 @@ def run(self):
 
         tmpl = "{0}[{1:03}/{2}]{3} {4}: "
         for i, (name, text) in enumerate(self._tests, 1):
-            sys.stdout.write(tmpl.format(Color.GRAY, i, len(self._tests),
-                                         Color.RESET, name.ljust(width)))
+            sys.stdout.write(
+                tmpl.format(
+                    Color.GRAY, i, len(self._tests), Color.RESET, name.ljust(width)
+                )
+            )
             sys.stdout.flush()
             parent, child = Pipe()
             p = Process(target=_runner, args=(text, child))
@@ -156,6 +160,7 @@ def _runner(text, child):
     child.send("OK")
     child.recv()
 
+
 if __name__ == "__main__":
     setlocale(LC_ALL, "")
     MemoryTest().run()

setup.py

@@ -52,8 +52,10 @@
 
 # Remove the command line argument as it isn't understood by setuptools:
 
-sys.argv = [arg for arg in sys.argv
-            if arg not in ("--without-extension", "--with-extension")]
+sys.argv = [
+    arg for arg in sys.argv if arg not in ("--without-extension", "--with-extension")
+]
+
 
 def build_ext_patched(self):
     try:
@@ -63,33 +65,40 @@ def build_ext_patched(self):
         print("Falling back to pure Python mode.")
         del self.extensions[:]
 
+
 if fallback:
     build_ext.run, build_ext_original = build_ext_patched, build_ext.run
 
 # Project-specific part begins here:
 
-tokenizer = Extension("mwparserfromhell.parser._tokenizer",
-                      sources=sorted(glob("src/mwparserfromhell/parser/ctokenizer/*.c")),
-                      depends=sorted(glob("src/mwparserfromhell/parser/ctokenizer/*.h")))
+tokenizer = Extension(
+    "mwparserfromhell.parser._tokenizer",
+    sources=sorted(glob("src/mwparserfromhell/parser/ctokenizer/*.c")),
+    depends=sorted(glob("src/mwparserfromhell/parser/ctokenizer/*.h")),
+)
 
 setup(
-    name = "mwparserfromhell",
-    packages = find_packages("src"),
-    package_dir = {"": "src"},
-    ext_modules = [tokenizer] if use_extension else [],
-    setup_requires = ["pytest-runner"] if "test" in sys.argv or "pytest" in sys.argv else [],
-    tests_require = ["pytest"],
-    version = __version__,
-    python_requires = ">= 3.5",
-    author = "Ben Kurtovic",
-    author_email = "[email protected]",
-    url = "https://github.com/earwig/mwparserfromhell",
-    description = "MWParserFromHell is a parser for MediaWiki wikicode.",
-    long_description = long_docs,
-    download_url = "https://github.com/earwig/mwparserfromhell/tarball/v{}".format(__version__),
-    keywords = "earwig mwparserfromhell wikipedia wiki mediawiki wikicode template parsing",
-    license = "MIT License",
-    classifiers = [
+    name="mwparserfromhell",
+    packages=find_packages("src"),
+    package_dir={"": "src"},
+    ext_modules=[tokenizer] if use_extension else [],
+    setup_requires=["pytest-runner"]
+    if "test" in sys.argv or "pytest" in sys.argv
+    else [],
+    tests_require=["pytest"],
+    version=__version__,
+    python_requires=">= 3.5",
+    author="Ben Kurtovic",
+    author_email="[email protected]",
+    url="https://github.com/earwig/mwparserfromhell",
+    description="MWParserFromHell is a parser for MediaWiki wikicode.",
+    long_description=long_docs,
+    download_url="https://github.com/earwig/mwparserfromhell/tarball/v{}".format(
+        __version__
+    ),
+    keywords="earwig mwparserfromhell wikipedia wiki mediawiki wikicode template parsing",
+    license="MIT License",
+    classifiers=[
         "Development Status :: 4 - Beta",
         "Environment :: Console",
         "Intended Audience :: Developers",
@@ -101,6 +110,6 @@ def build_ext_patched(self):
         "Programming Language :: Python :: 3.7",
         "Programming Language :: Python :: 3.8",
         "Programming Language :: Python :: 3.9",
-        "Topic :: Text Processing :: Markup"
+        "Topic :: Text Processing :: Markup",
     ],
 )

src/mwparserfromhell/__init__.py

@@ -30,7 +30,6 @@
 __version__ = "0.7.dev0"
 __email__ = "[email protected]"
 
-from . import (definitions, nodes, parser, smart_list, string_mixin,
-               utils, wikicode)
+from . import definitions, nodes, parser, smart_list, string_mixin, utils, wikicode
 
 parse = utils.parse_anything

src/mwparserfromhell/definitions.py

@@ -26,8 +26,14 @@
 - mwparserfromhell/parser/ctokenizer/definitions.h
 """
 
-__all__ = ["get_html_tag", "is_parsable", "is_visible", "is_single",
-           "is_single_only", "is_scheme"]
+__all__ = [
+    "get_html_tag",
+    "is_parsable",
+    "is_visible",
+    "is_single",
+    "is_single_only",
+    "is_scheme",
+]
 
 URI_SCHEMES = {
     # [wikimedia/mediawiki.git]/includes/DefaultSettings.php @ 5c660de5d0
@@ -92,7 +98,7 @@
     "score",
     "section",
     "templatedata",
-    "timeline"
+    "timeline",
 ]
 
 # [wikimedia/mediawiki.git]/includes/parser/Sanitizer.php @ 95e17ee645
@@ -103,29 +109,35 @@
     "#": "li",
     "*": "li",
     ";": "dt",
-    ":": "dd"
+    ":": "dd",
 }
 
+
 def get_html_tag(markup):
     """Return the HTML tag associated with the given wiki-markup."""
     return MARKUP_TO_HTML[markup]
 
+
 def is_parsable(tag):
     """Return if the given *tag*'s contents should be passed to the parser."""
     return tag.lower() not in PARSER_BLACKLIST
 
+
 def is_visible(tag):
     """Return whether or not the given *tag* contains visible text."""
     return tag.lower() not in INVISIBLE_TAGS
 
+
 def is_single(tag):
     """Return whether or not the given *tag* can exist without a close tag."""
     return tag.lower() in SINGLE
 
+
 def is_single_only(tag):
     """Return whether or not the given *tag* must exist without a close tag."""
     return tag.lower() in SINGLE_ONLY
 
+
 def is_scheme(scheme, slashes=True):
     """Return whether *scheme* is valid for external links."""
     scheme = scheme.lower()

src/mwparserfromhell/nodes/__init__.py

@@ -39,5 +39,15 @@
 from .template import Template
 from .wikilink import Wikilink
 
-__all__ = ["Argument", "Comment", "ExternalLink", "HTMLEntity", "Heading",
-           "Node", "Tag", "Template", "Text", "Wikilink"]
+__all__ = [
+    "Argument",
+    "Comment",
+    "ExternalLink",
+    "HTMLEntity",
+    "Heading",
+    "Node",
+    "Tag",
+    "Template",
+    "Text",
+    "Wikilink",
+]

src/mwparserfromhell/nodes/_base.py

@@ -22,6 +22,7 @@
 
 __all__ = ["Node"]
 
+
 class Node(StringMixIn):
     """Represents the base Node type, demonstrating the methods to override.
 
@@ -35,6 +36,7 @@ class Node(StringMixIn):
     :meth:`__showtree__` can be overridden to build a nice tree representation
     of the node, if desired, for :meth:`~.Wikicode.get_tree`.
     """
+
     def __str__(self):
         raise NotImplementedError()
 

src/mwparserfromhell/nodes/argument.py

@@ -24,6 +24,7 @@
 
 __all__ = ["Argument"]
 
+
 class Argument(Node):
     """Represents a template argument substitution, like ``{{{foo}}}``."""
 

src/mwparserfromhell/nodes/comment.py

@@ -23,6 +23,7 @@
 
 __all__ = ["Comment"]
 
+
 class Comment(Node):
     """Represents a hidden HTML comment, like ``<!-- foobar -->``."""
 

src/mwparserfromhell/nodes/external_link.py

@@ -24,6 +24,7 @@
 
 __all__ = ["ExternalLink"]
 
+
 class ExternalLink(Node):
     """Represents an external link, like ``[http://example.com/ Example]``."""
 
@@ -83,6 +84,7 @@ def brackets(self):
     def url(self, value):
         # pylint: disable=import-outside-toplevel
         from ..parser import contexts
+
         self._url = parse_anything(value, contexts.EXT_LINK_URI)
 
     @title.setter

src/mwparserfromhell/nodes/extras/attribute.py

@@ -24,6 +24,7 @@
 
 __all__ = ["Attribute"]
 
+
 class Attribute(StringMixIn):
     """Represents an attribute of an HTML tag.
 
@@ -32,8 +33,15 @@ class Attribute(StringMixIn):
     whose value is ``"foo"``.
     """
 
-    def __init__(self, name, value=None, quotes='"', pad_first=" ",
-                 pad_before_eq="", pad_after_eq=""):
+    def __init__(
+        self,
+        name,
+        value=None,
+        quotes='"',
+        pad_first=" ",
+        pad_before_eq="",
+        pad_after_eq="",
+    ):
         super().__init__()
         self.name = name
         self._quotes = None

src/mwparserfromhell/nodes/extras/parameter.py

@@ -25,6 +25,7 @@
 
 __all__ = ["Parameter"]
 
+
 class Parameter(StringMixIn):
     """Represents a paramater of a template.
 
@@ -77,6 +78,5 @@ def value(self, newval):
     def showkey(self, newval):
         newval = bool(newval)
         if not newval and not self.can_hide_key(self.name):
-            raise ValueError("parameter key {!r} cannot be hidden".format(
-                self.name))
+            raise ValueError("parameter key {!r} cannot be hidden".format(self.name))
         self._showkey = newval

src/mwparserfromhell/nodes/heading.py

@@ -24,6 +24,7 @@
 
 __all__ = ["Heading"]
 
+
 class Heading(Node):
     """Represents a section heading in wikicode, like ``== Foo ==``."""
 

src/mwparserfromhell/nodes/html_entity.py

@@ -24,6 +24,7 @@
 
 __all__ = ["HTMLEntity"]
 
+
 class HTMLEntity(Node):
     """Represents an HTML entity, like `` ``, either named or unnamed."""
 
@@ -101,19 +102,23 @@ def value(self, newval):
             except ValueError:
                 if newval not in htmlentities.entitydefs:
                     raise ValueError(
-                        "entity value {!r} is not a valid name".format(newval)) from None
+                        "entity value {!r} is not a valid name".format(newval)
+                    ) from None
                 self._named = True
                 self._hexadecimal = False
             else:
                 if intval < 0 or intval > 0x10FFFF:
                     raise ValueError(
-                        "entity value 0x{:x} is not in range(0x110000)".format(intval)) from None
+                        "entity value 0x{:x} is not in range(0x110000)".format(intval)
+                    ) from None
                 self._named = False
                 self._hexadecimal = True
         else:
             test = int(newval, 16 if self.hexadecimal else 10)
             if test < 0 or test > 0x10FFFF:
-                raise ValueError("entity value {} is not in range(0x110000)".format(test))
+                raise ValueError(
+                    "entity value {} is not in range(0x110000)".format(test)
+                )
             self._named = False
         self._value = newval
 
@@ -126,8 +131,10 @@ def named(self, newval):
             try:
                 int(self.value, 16)
             except ValueError as exc:
-                raise ValueError("current entity value {!r} is not a valid "
-                                 "Unicode codepoint".format(self.value)) from exc
+                raise ValueError(
+                    "current entity value {!r} is not a valid "
+                    "Unicode codepoint".format(self.value)
+                ) from exc
         self._named = newval
 
     @hexadecimal.setter