[Markdown] Add missing stubs (#14285)

stubs/Markdown/@tests/stubtest_allowlist.txt

@@ -1,3 +1,4 @@
 # Deprecated types are infered as functions:
 markdown.extensions.abbr.AbbrPreprocessor
 markdown.extensions.abbr.AbbrInlineProcessor
+markdown.postprocessors.UnescapePostprocessor

stubs/Markdown/METADATA.toml

@@ -1,6 +1,2 @@
 version = "3.8.*"
 upstream_repository = "https://github.com/Python-Markdown/markdown"
-partial_stub = true
-
-[tool.stubtest]
-ignore_missing_stub = true

stubs/Markdown/markdown/__main__.pyi

@@ -0,0 +1,10 @@
+import optparse
+from logging import Logger
+from typing import Any
+
+logger: Logger
+
+def parse_options(
+    args: list[str] | None = None, values: optparse.Values | None = None
+) -> tuple[dict[str, Any], Any]: ...  # first item is opts dict, second item is Values.verbose field
+def run() -> None: ...

stubs/Markdown/markdown/core.pyi

@@ -1,5 +1,6 @@
 from codecs import _ReadableStream, _WritableStream
 from collections.abc import Callable, Mapping, Sequence
+from logging import Logger
 from typing import Any, ClassVar, Literal
 from typing_extensions import Self
 from xml.etree.ElementTree import Element
@@ -8,6 +9,10 @@ from . import blockparser, inlinepatterns, postprocessors, preprocessors, treepr
 from .extensions import Extension
 from .util import HtmlStash, Registry
 
+__all__ = ["Markdown", "markdown", "markdownFromFile"]
+
+logger: Logger
+
 class Markdown:
     preprocessors: Registry[preprocessors.Preprocessor]
     inlinePatterns: Registry[inlinepatterns.Pattern]

stubs/Markdown/markdown/extensions/abbr.pyi

@@ -19,6 +19,7 @@ class AbbrTreeprocessor(Treeprocessor):
     RE: Pattern[str] | None
     abbrs: dict[str, str]
     def __init__(self, md: Markdown | None = None, abbrs: dict[str, str] | None = None) -> None: ...
+    def create_element(self, title: str, text: str, tail: str) -> Element: ...
     def iter_element(self, el: Element, parent: Element | None = None) -> None: ...
 
 # Techinically it is the same type as `AbbrPreprocessor` just not deprecated.

stubs/Markdown/markdown/extensions/md_in_html.pyi

@@ -1,8 +1,34 @@
-from xml.etree.ElementTree import Element
+from collections.abc import Iterable, Mapping
+from typing import Literal
+from xml.etree.ElementTree import Element, TreeBuilder
 
 from markdown.blockprocessors import BlockProcessor
 from markdown.extensions import Extension
+from markdown.htmlparser import HTMLExtractor
 from markdown.postprocessors import RawHtmlPostprocessor
+from markdown.preprocessors import Preprocessor
+
+class HTMLExtractorExtra(HTMLExtractor):
+    block_level_tags: set[str]
+    span_tags: set[str]
+    raw_tags: set[str]
+    block_tags: set[str]
+    span_and_blocks_tags: set[str]
+    mdstack: list[str]
+    treebuilder: TreeBuilder
+    mdstate: list[Literal["block", "span", "off"] | None]
+    mdstarted: list[bool]
+    def get_element(self) -> Element: ...
+    def get_state(self, tag: str, attrs: Mapping[str, str]) -> Literal["block", "span", "off"] | None: ...
+    def handle_starttag(self, tag: str, attrs: Iterable[tuple[str, str | None]]) -> None: ...
+    def handle_endtag(self, tag: str) -> None: ...
+    def handle_startendtag(self, tag: str, attrs: Iterable[tuple[str, str | None]]) -> None: ...
+    def handle_data(self, data: str) -> None: ...
+    def handle_empty_tag(self, data: str, is_block: bool) -> None: ...
+    def parse_pi(self, i: int) -> int: ...
+    def parse_html_declaration(self, i: int) -> int: ...
+
+class HtmlBlockPreprocessor(Preprocessor): ...
 
 class MarkdownInHtmlProcessor(BlockProcessor):
     def parse_element_content(self, element: Element) -> None: ...

stubs/Markdown/markdown/extensions/meta.pyi

@@ -1,9 +1,11 @@
+from logging import Logger
 from re import Pattern
 
 from markdown.core import Markdown
 from markdown.extensions import Extension
 from markdown.preprocessors import Preprocessor
 
+log: Logger
 META_RE: Pattern[str]
 META_MORE_RE: Pattern[str]
 BEGIN_RE: Pattern[str]

stubs/Markdown/markdown/extensions/smarty.pyi

@@ -15,6 +15,8 @@ singleQuoteStartRe: str
 doubleQuoteStartRe: str
 doubleQuoteSetsRe: str
 singleQuoteSetsRe: str
+doubleQuoteSetsRe2: str
+singleQuoteSetsRe2: str
 decadeAbbrRe: str
 openingDoubleQuotesRegex: str
 closingDoubleQuotesRegex: str

stubs/Markdown/markdown/htmlparser.pyi

@@ -0,0 +1,28 @@
+import html.parser as htmlparser
+import re
+from _frozen_importlib import ModuleSpec
+from collections.abc import Sequence
+
+from markdown import Markdown
+
+spec: ModuleSpec
+blank_line_re: re.Pattern[str]
+
+class HTMLExtractor(htmlparser.HTMLParser):
+    empty_tags: set[str]
+    lineno_start_cache: list[int]
+    md: Markdown
+    def __init__(self, md: Markdown, *args, **kwargs): ...
+    inraw: bool
+    intail: bool
+    stack: list[str]
+    cleandoc: list[str]
+    @property
+    def line_offset(self) -> int: ...
+    def at_line_start(self) -> bool: ...
+    def get_endtag_text(self, tag: str) -> str: ...
+    def handle_starttag(self, tag: str, attrs: Sequence[tuple[str, str]]) -> None: ...  # type: ignore[override]
+    def handle_empty_tag(self, data: str, is_block: bool) -> None: ...
+    def handle_decl(self, data: str) -> None: ...
+    def parse_bogus_comment(self, i: int, report: int = 0) -> int: ...
+    def get_starttag_text(self) -> str: ...

stubs/Markdown/markdown/postprocessors.pyi

@@ -1,3 +1,7 @@
+import re
+from typing import ClassVar
+from typing_extensions import deprecated
+
 from markdown.core import Markdown
 
 from . import util
@@ -8,7 +12,16 @@ class Postprocessor(util.Processor):
     def run(self, text: str) -> str: ...
 
 class RawHtmlPostprocessor(Postprocessor):
+    BLOCK_LEVEL_REGEX: ClassVar[re.Pattern[str]]
     def isblocklevel(self, html: str) -> bool: ...
     def stash_to_string(self, text: str) -> str: ...
 
 class AndSubstitutePostprocessor(Postprocessor): ...
+
+@deprecated(
+    "This class is deprecated and will be removed in the future; "
+    "use [`UnescapeTreeprocessor`][markdown.treeprocessors.UnescapeTreeprocessor] instead."
+)
+class UnescapePostprocessor(Postprocessor):
+    RE: ClassVar[re.Pattern[str]]
+    def unescape(self, m: re.Match[str]) -> str: ...

stubs/Markdown/markdown/serializers.pyi

@@ -1,4 +1,9 @@
+import re
 from xml.etree.ElementTree import Element
 
+__all__ = ["to_html_string", "to_xhtml_string"]
+
+RE_AMP: re.Pattern[str]
+
 def to_html_string(element: Element) -> str: ...
 def to_xhtml_string(element: Element) -> str: ...

stubs/Markdown/markdown/test_tools.pyi

@@ -0,0 +1,30 @@
+import unittest
+from _typeshed import Unused
+from typing import Any
+
+__all__ = ["TestCase", "LegacyTestCase", "Kwargs"]
+
+class TestCase(unittest.TestCase):
+    default_kwargs: dict[str, Any]  # taken from source code
+    def assertMarkdownRenders(
+        self,
+        source: str,
+        expected: str,
+        expected_attrs: dict[str, Any] | None = None,  # values passing to self.assertEqual()
+        **kwargs,
+    ) -> None: ...
+    def dedent(self, text: str) -> str: ...
+
+class recursionlimit:
+    limit: int
+    old_limit: int
+    def __init__(self, limit: int) -> None: ...
+    def __enter__(self) -> None: ...
+    def __exit__(self, type: Unused, value: Unused, tb: Unused) -> None: ...
+
+class Kwargs(dict[str, Any]): ...
+
+class LegacyTestMeta(type):
+    def __new__(cls, name: str, bases: tuple[type, ...], dct: dict[str, Any]): ...  # dct is namespace argument for type.__new__()
+
+class LegacyTestCase(unittest.TestCase, metaclass=LegacyTestMeta): ...