[html5lib] Improve stubs

stubs/html5lib/METADATA.toml

@@ -1,7 +1,5 @@
 version = "1.1.*"
 upstream_repository = "https://github.com/html5lib/html5lib-python"
-partial_stub = true
 
 [tool.stubtest]
-ignore_missing_stub = true
 extras = ["all"]

stubs/html5lib/html5lib/__init__.pyi

@@ -1,6 +1,10 @@
+from typing import Final
+
 from .html5parser import HTMLParser as HTMLParser, parse as parse, parseFragment as parseFragment
 from .serializer import serialize as serialize
 from .treebuilders import getTreeBuilder as getTreeBuilder
 from .treewalkers import getTreeWalker as getTreeWalker
 
-__version__: str
+__all__ = ["HTMLParser", "parse", "parseFragment", "getTreeBuilder", "getTreeWalker", "serialize"]
+
+__version__: Final[str]

stubs/html5lib/html5lib/_ihatexml.pyi

@@ -1,39 +1,41 @@
-from typing import Any
+import re
+from _typeshed import Incomplete
+from collections.abc import Iterable
 
 baseChar: str
 ideographic: str
 combiningCharacter: str
 digit: str
 extender: str
-letter: Any
-name: Any
-nameFirst: Any
-reChar: Any
-reCharRange: Any
+letter: str
+name: str
+nameFirst: str
+reChar: re.Pattern[str]
+reCharRange: re.Pattern[str]
 
-def charStringToList(chars): ...
-def normaliseCharList(charList): ...
+def charStringToList(chars: str) -> list[str]: ...
+def normaliseCharList(charList: Iterable[str]) -> list[str]: ...
 
-max_unicode: Any
+max_unicode: int
 
-def missingRanges(charList): ...
+def missingRanges(charList: Iterable[str]) -> list[str]: ...
 def listToRegexpStr(charList): ...
-def hexToInt(hex_str): ...
-def escapeRegexp(string): ...
+def hexToInt(hex_str: str | bytes | bytearray) -> int: ...
+def escapeRegexp(string: str) -> str: ...
 
-nonXmlNameBMPRegexp: Any
-nonXmlNameFirstBMPRegexp: Any
-nonPubidCharRegexp: Any
+nonXmlNameBMPRegexp: re.Pattern[str]
+nonXmlNameFirstBMPRegexp: re.Pattern[str]
+nonPubidCharRegexp: re.Pattern[str]
 
 class InfosetFilter:
-    replacementRegexp: Any
-    dropXmlnsLocalName: Any
-    dropXmlnsAttrNs: Any
-    preventDoubleDashComments: Any
-    preventDashAtCommentEnd: Any
-    replaceFormFeedCharacters: Any
-    preventSingleQuotePubid: Any
-    replaceCache: Any
+    replacementRegexp: re.Pattern[str]
+    dropXmlnsLocalName: Incomplete
+    dropXmlnsAttrNs: Incomplete
+    preventDoubleDashComments: Incomplete
+    preventDashAtCommentEnd: Incomplete
+    replaceFormFeedCharacters: Incomplete
+    preventSingleQuotePubid: Incomplete
+    replaceCache: Incomplete
     def __init__(
         self,
         dropXmlnsLocalName: bool = False,

stubs/html5lib/html5lib/_inputstream.pyi

@@ -1,6 +1,6 @@
-from _typeshed import SupportsRead
+from _typeshed import Incomplete, SupportsRead
 from codecs import CodecInfo
-from typing import Any, Protocol, overload
+from typing import Protocol, overload
 from typing_extensions import TypeAlias
 
 # Is actually webencodings.Encoding
@@ -13,20 +13,20 @@ _UnicodeInputStream: TypeAlias = str | SupportsRead[str]
 _BinaryInputStream: TypeAlias = bytes | SupportsRead[bytes]
 _InputStream: TypeAlias = _UnicodeInputStream | _BinaryInputStream  # noqa: Y047  # used in other files
 
-spaceCharactersBytes: Any
-asciiLettersBytes: Any
-asciiUppercaseBytes: Any
-spacesAngleBrackets: Any
+spaceCharactersBytes: Incomplete
+asciiLettersBytes: Incomplete
+asciiUppercaseBytes: Incomplete
+spacesAngleBrackets: Incomplete
 invalid_unicode_no_surrogate: str
-invalid_unicode_re: Any
-non_bmp_invalid_codepoints: Any
-ascii_punctuation_re: Any
-charsUntilRegEx: Any
+invalid_unicode_re: Incomplete
+non_bmp_invalid_codepoints: Incomplete
+ascii_punctuation_re: Incomplete
+charsUntilRegEx: Incomplete
 
 class BufferedStream:
-    stream: Any
-    buffer: Any
-    position: Any
+    stream: Incomplete
+    buffer: Incomplete
+    position: Incomplete
     def __init__(self, stream) -> None: ...
     def tell(self): ...
     def seek(self, pos) -> None: ...
@@ -47,10 +47,10 @@ def HTMLInputStream(
 ) -> HTMLBinaryInputStream: ...
 
 class HTMLUnicodeInputStream:
-    reportCharacterErrors: Any
-    newLines: Any
+    reportCharacterErrors: Incomplete
+    newLines: Incomplete
     charEncoding: tuple[_Encoding, str]
-    dataStream: Any
+    dataStream: Incomplete
     def __init__(self, source: _UnicodeInputStream) -> None: ...
     chunk: str
     chunkSize: int
@@ -69,14 +69,14 @@ class HTMLUnicodeInputStream:
     def unget(self, char) -> None: ...
 
 class HTMLBinaryInputStream(HTMLUnicodeInputStream):
-    rawStream: Any
+    rawStream: Incomplete
     numBytesMeta: int
     numBytesChardet: int
-    override_encoding: Any
-    transport_encoding: Any
-    same_origin_parent_encoding: Any
-    likely_encoding: Any
-    default_encoding: Any
+    override_encoding: Incomplete
+    transport_encoding: Incomplete
+    same_origin_parent_encoding: Incomplete
+    likely_encoding: Incomplete
+    default_encoding: Incomplete
     charEncoding: tuple[_Encoding, str]
     def __init__(
         self,
@@ -88,7 +88,7 @@ class HTMLBinaryInputStream(HTMLUnicodeInputStream):
         default_encoding: str = "windows-1252",
         useChardet: bool = True,
     ) -> None: ...
-    dataStream: Any
+    dataStream: Incomplete
     def reset(self) -> None: ...
     def openStream(self, source): ...
     def determineEncoding(self, chardet: bool = True): ...
@@ -105,7 +105,7 @@ class EncodingBytes(bytes):
     def previous(self): ...
     def setPosition(self, position) -> None: ...
     def getPosition(self): ...
-    position: Any
+    position: Incomplete
     def getCurrentByte(self): ...
     @property
     def currentByte(self): ...
@@ -115,8 +115,8 @@ class EncodingBytes(bytes):
     def jumpTo(self, bytes): ...
 
 class EncodingParser:
-    data: Any
-    encoding: Any
+    data: Incomplete
+    encoding: Incomplete
     def __init__(self, data) -> None: ...
     def getEncoding(self): ...
     def handleComment(self): ...
@@ -128,7 +128,7 @@ class EncodingParser:
     def getAttribute(self): ...
 
 class ContentAttrParser:
-    data: Any
+    data: Incomplete
     def __init__(self, data) -> None: ...
     def parse(self): ...
 

stubs/html5lib/html5lib/_tokenizer.pyi

@@ -1,20 +1,20 @@
-from typing import Any
+from _typeshed import Incomplete
 
 from ._inputstream import _InputStream
 
-entitiesTrie: Any
+entitiesTrie: Incomplete
 attributeMap = dict
 
 class HTMLTokenizer:
-    stream: Any
-    parser: Any
+    stream: Incomplete
+    parser: Incomplete
     escapeFlag: bool
-    lastFourChars: Any
-    state: Any
+    lastFourChars: Incomplete
+    state: Incomplete
     escape: bool
-    currentToken: Any
+    currentToken: Incomplete
     def __init__(self, stream: _InputStream, parser=None, **kwargs) -> None: ...
-    tokenQueue: Any
+    tokenQueue: Incomplete
     def __iter__(self): ...
     def consumeNumberEntity(self, isHex): ...
     def consumeEntity(self, allowedChar=None, fromAttribute: bool = False) -> None: ...

stubs/html5lib/html5lib/_trie/__init__.pyi

@@ -1 +1,3 @@
 from .py import Trie as Trie
+
+__all__ = ["Trie"]

stubs/html5lib/html5lib/_trie/_base.pyi

@@ -1,8 +1,8 @@
+from _typeshed import Incomplete
 from abc import ABCMeta
 from collections.abc import Mapping
-from typing import Any
 
-class Trie(Mapping[Any, Any], metaclass=ABCMeta):
+class Trie(Mapping[Incomplete, Incomplete], metaclass=ABCMeta):
     def keys(self, prefix=None): ...
     def has_keys_with_prefix(self, prefix): ...
     def longest_prefix(self, prefix): ...

stubs/html5lib/html5lib/_utils.pyi

@@ -1,17 +1,27 @@
+import xml.etree.ElementTree as default_etree
+from _typeshed import Incomplete
 from collections.abc import Mapping
-from typing import Any
+
+__all__ = [
+    "default_etree",
+    "MethodDispatcher",
+    "isSurrogatePair",
+    "surrogatePairToCodepoint",
+    "moduleFactoryFactory",
+    "supports_lone_surrogates",
+]
 
 supports_lone_surrogates: bool
 
-class MethodDispatcher(dict[Any, Any]):
-    default: Any
+class MethodDispatcher(dict[Incomplete, Incomplete]):
+    default: Incomplete
     def __init__(self, items=()) -> None: ...
     def __getitem__(self, key): ...
     def __get__(self, instance, owner=None): ...
 
-class BoundMethodDispatcher(Mapping[Any, Any]):
-    instance: Any
-    dispatcher: Any
+class BoundMethodDispatcher(Mapping[Incomplete, Incomplete]):
+    instance: Incomplete
+    dispatcher: Incomplete
     def __init__(self, instance, dispatcher) -> None: ...
     def __getitem__(self, key): ...
     def get(self, key, default): ...  # type: ignore[override]

stubs/html5lib/html5lib/constants.pyi

@@ -1,37 +1,37 @@
-from typing import Any
+from _typeshed import Incomplete
 
-EOF: Any
-E: Any
-namespaces: Any
-scopingElements: Any
-formattingElements: Any
-specialElements: Any
-htmlIntegrationPointElements: Any
-mathmlTextIntegrationPointElements: Any
-adjustSVGAttributes: Any
-adjustMathMLAttributes: Any
-adjustForeignAttributes: Any
-unadjustForeignAttributes: Any
-spaceCharacters: Any
-tableInsertModeElements: Any
-asciiLowercase: Any
-asciiUppercase: Any
-asciiLetters: Any
-digits: Any
-hexDigits: Any
-asciiUpper2Lower: Any
-headingElements: Any
-voidElements: Any
-cdataElements: Any
-rcdataElements: Any
-booleanAttributes: Any
-entitiesWindows1252: Any
-xmlEntities: Any
-entities: Any
-replacementCharacters: Any
-tokenTypes: Any
-tagTokenTypes: Any
-prefixes: Any
+EOF: Incomplete
+E: dict[str, str]
+namespaces: dict[str, str]
+scopingElements: frozenset[tuple[str, str]]
+formattingElements: frozenset[tuple[str, str]]
+specialElements: frozenset[tuple[str, str]]
+htmlIntegrationPointElements: frozenset[tuple[str, str]]
+mathmlTextIntegrationPointElements: frozenset[tuple[str, str]]
+adjustSVGAttributes: dict[str, str]
+adjustMathMLAttributes: dict[str, str]
+adjustForeignAttributes: dict[str, tuple[str, str, str] | tuple[None, str, str]]
+unadjustForeignAttributes: dict[tuple[str, str], str]
+spaceCharacters: frozenset[str]
+tableInsertModeElements: frozenset[str]
+asciiLowercase: frozenset[str]
+asciiUppercase: frozenset[str]
+asciiLetters: frozenset[str]
+digits: frozenset[str]
+hexDigits: frozenset[str]
+asciiUpper2Lower: dict[int, int]
+headingElements: tuple[str, ...]
+voidElements: frozenset[str]
+cdataElements: frozenset[str]
+rcdataElements: frozenset[str]
+booleanAttributes: dict[str, frozenset[str]]
+entitiesWindows1252: tuple[int, ...]
+xmlEntities: frozenset[str]
+entities: dict[str, str]
+replacementCharacters: dict[int, str]
+tokenTypes: dict[str, int]
+tagTokenTypes: frozenset[int]
+prefixes: dict[str, str]
 
 class DataLossWarning(UserWarning): ...
 class _ReparseException(Exception): ...

stubs/html5lib/html5lib/filters/base.pyi

@@ -1,7 +1,7 @@
-from typing import Any
+from _typeshed import Incomplete
 
 class Filter:
-    source: Any
+    source: Incomplete
     def __init__(self, source) -> None: ...
     def __iter__(self): ...
     def __getattr__(self, name: str): ...

stubs/html5lib/html5lib/filters/inject_meta_charset.pyi

@@ -1,8 +1,6 @@
-from typing import Any
-
 from . import base
 
 class Filter(base.Filter):
-    encoding: Any
-    def __init__(self, source, encoding) -> None: ...
+    encoding: str | None
+    def __init__(self, source, encoding: str | None) -> None: ...
     def __iter__(self): ...

stubs/html5lib/html5lib/filters/lint.pyi

@@ -1,8 +1,8 @@
-from typing import Any
-
 from . import base
 
+spaceCharacters: str
+
 class Filter(base.Filter):
-    require_matching_tags: Any
+    require_matching_tags: bool
     def __init__(self, source, require_matching_tags: bool = True) -> None: ...
     def __iter__(self): ...

stubs/html5lib/html5lib/filters/optionaltags.pyi

@@ -1,7 +1,10 @@
+from _typeshed import Incomplete
+from collections.abc import Generator
+
 from . import base
 
 class Filter(base.Filter):
-    def slider(self) -> None: ...
+    def slider(self) -> Generator[tuple[Incomplete, Incomplete, Incomplete]]: ...
     def __iter__(self): ...
-    def is_optional_start(self, tagname, previous, next): ...
-    def is_optional_end(self, tagname, next): ...
+    def is_optional_start(self, tagname: str, previous, next) -> bool: ...
+    def is_optional_end(self, tagname: str, next) -> bool: ...