mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-07-12 19:45:56 +00:00
6fe1c9980e
**Summary** Extract as much mechanical refactoring from the HTML parser change-over into the PR as possible. This leaves the next PR focused on installing the new parser and the ingest-test impact. **Reviewers:** Commits are well groomed and reviewing commit-by-commit is probably easier. **Additional Context** This PR introduces the rewritten HTML parser. Its general design is recursive, consistent with the recursive structure of HTML (tree of elements). It also adds the unit tests for that parser but it does not _install_ the parser. So the behavior of `partition_html()` is unchanged by this PR. The next PR in this series will do that and handle the ingest and other unit test changes required to reflect the dozen or so bug-fixes the new parser provides.
20 lines
581 B
Python
20 lines
581 B
Python
# pyright: reportPrivateUsage=false
|
|
|
|
from __future__ import annotations
|
|
|
|
from .._types import _ElementOrTree
|
|
from ..etree import HTMLParser, XMLParser
|
|
from ._element import _Element
|
|
|
|
def fromstring(text: str | bytes, parser: XMLParser | HTMLParser) -> _Element: ...
|
|
|
|
# Under XML Canonicalization (C14N) mode, most arguments are ignored,
|
|
# some arguments would even raise exception outright if specified.
|
|
def tostring(
|
|
element_or_tree: _ElementOrTree,
|
|
*,
|
|
encoding: str | type[str] | None = None,
|
|
pretty_print: bool = False,
|
|
with_tail: bool = True,
|
|
) -> str: ...
|