selectolax 0.3.24__cp310-cp310-musllinux_1_2_aarch64.whl → 0.3.26__cp310-cp310-musllinux_1_2_aarch64.whl

selectolax/lexbor.pyi

@@ -1,14 +1,27 @@
-from typing import Iterator, TypeVar, NoReturn
+from typing import Any, Iterator, Literal, TypeVar, NoReturn, overload
 
 DefaultT = TypeVar("DefaultT")
 
 class LexborAttributes:
     @staticmethod
-    def create(node: "LexborAttributes") -> "LexborAttributes": ...
+    def create(node: LexborAttributes) -> LexborAttributes: ...
     def keys(self) -> Iterator[str]: ...
-    def items(self) -> Iterator[tuple[str, str]]: ...
-    def values(self) -> Iterator[str]: ...
-    def get(self, key: str, default: DefaultT | None = None) -> str | DefaultT | None: ...
+    def items(self) -> Iterator[tuple[str, str | None]]: ...
+    def values(self) -> Iterator[str | None]: ...
+    def __iter__(self) -> Iterator[str]: ...
+    def __len__(self) -> int: ...
+    def __getitem__(self, key: str) -> str | None: ...
+    def __setitem__(self, key: str, value: str) -> None: ...
+    def __delitem__(self, key: str) -> None: ...
+    def __contains__(self, key: str) -> bool: ...
+    def __repr__(self) -> str: ...
+    @overload
+    def get(self, key: str, default: DefaultT) -> DefaultT | str | None: ...
+    @overload
+    def get(self, key: str, default: None = ...) -> str | None: ...
+    @overload
+    def sget(self, key: str, default: str | DefaultT) -> str | DefaultT: ...
+    @overload
     def sget(self, key: str, default: str = "") -> str: ...
 
 class LexborSelector:
@@ -20,37 +33,38 @@ class LexborSelector:
     def any_matches(self) -> bool: ...
     def text_contains(
         self, text: str, deep: bool = True, separator: str = "", strip: bool = False
-    ) -> "LexborSelector": ...
+    ) -> LexborSelector: ...
     def any_text_contains(
         self, text: str, deep: bool = True, separator: str = "", strip: bool = False
     ) -> bool: ...
     def attribute_longer_than(
         self, attribute: str, length: int, start: str | None = None
-    ) -> "LexborSelector": ...
+    ) -> LexborSelector: ...
     def any_attribute_longer_than(
         self, attribute: str, length: int, start: str | None = None
     ) -> bool: ...
 
 class LexborCSSSelector:
     def __init__(self): ...
-    def find(self, query: str, node: "LexborNode") -> list["LexborNode"]: ...
-    def any_matches(self, query: str, node: "LexborNode") -> bool: ...
+    def find(self, query: str, node: LexborNode) -> list[LexborNode]: ...
+    def any_matches(self, query: str, node: LexborNode) -> bool: ...
 
 class LexborNode:
+    parser: LexborHTMLParser
     @property
     def mem_id(self) -> int: ...
     @property
-    def child(self) -> None | "LexborNode": ...
+    def child(self) -> LexborNode | None: ...
     @property
-    def first_child(self) -> None | "LexborNode": ...
+    def first_child(self) -> LexborNode | None: ...
     @property
-    def parent(self) -> None | "LexborNode": ...
+    def parent(self) -> LexborNode | None: ...
     @property
-    def next(self) -> None | "LexborNode": ...
+    def next(self) -> LexborNode | None: ...
     @property
-    def prev(self) -> None | "LexborNode": ...
+    def prev(self) -> LexborNode | None: ...
     @property
-    def last_child(self) -> None | "LexborNode": ...
+    def last_child(self) -> LexborNode | None: ...
     @property
     def html(self) -> str | None: ...
     def __hash__(self) -> int: ...
@@ -58,10 +72,19 @@ class LexborNode:
     def text(
         self, deep: bool = True, separator: str = "", strip: bool = False
     ) -> str: ...
-    def css(self, query: str) -> list["LexborNode"]: ...
+    def css(self, query: str) -> list[LexborNode]: ...
+    @overload
     def css_first(
-        self, query: str, default: DefaultT | None = None, strict: bool = False
-    ) -> "LexborNode" | DefaultT | None: ...
+        self, query: str, default: Any = ..., strict: Literal[True] = ...
+    ) -> LexborNode: ...
+    @overload
+    def css_first(
+        self, query: str, default: DefaultT, strict: bool = False
+    ) -> LexborNode | DefaultT: ...
+    @overload
+    def css_first(
+        self, query: str, default: None = ..., strict: bool = False
+    ) -> LexborNode | None: ...
     def any_css_matches(self, selectors: tuple[str]) -> bool: ...
     def css_matches(self, selector: str) -> bool: ...
     @property
@@ -73,22 +96,23 @@ class LexborNode:
     @property
     def attributes(self) -> dict[str, str | None]: ...
     @property
-    def attrs(self) -> "LexborAttributes": ...
+    def attrs(self) -> LexborAttributes: ...
     @property
-    def id(self) -> None | str: ...
-    def iter(self, include_text: bool = False) -> Iterator["LexborNode"]: ...
+    def id(self) -> str | None: ...
+    def iter(self, include_text: bool = False) -> Iterator[LexborNode]: ...
     def unwrap(self) -> None: ...
     def unwrap_tags(self, tags: list[str]) -> None: ...
-    def traverse(self, include_text: bool = False) -> Iterator["LexborNode"]: ...
-    def replace_with(self, value: bytes | str | "LexborNode") -> None: ...
-    def insert_before(self, value: bytes | str | "LexborNode") -> None: ...
-    def insert_after(self, value: bytes | str | "LexborNode") -> None: ...
+    def traverse(self, include_text: bool = False) -> Iterator[LexborNode]: ...
+    def replace_with(self, value: bytes | str | LexborNode) -> None: ...
+    def insert_before(self, value: bytes | str | LexborNode) -> None: ...
+    def insert_after(self, value: bytes | str | LexborNode) -> None: ...
+    def insert_child(self, value: bytes | str | LexborNode) -> None: ...
     @property
     def raw_value(self) -> NoReturn: ...
     def scripts_contain(self, query: str) -> bool: ...
     def scripts_srcs_contain(self, queries: tuple[str]) -> bool: ...
     def remove(self, recursive: bool = True) -> None: ...
-    def select(self, query: str | None = None) -> "LexborSelector": ...
+    def select(self, query: str | None = None) -> LexborSelector: ...
     @property
     def text_content(self) -> str | None: ...
 
@@ -97,26 +121,52 @@ class LexborHTMLParser:
     @property
     def selector(self) -> "LexborCSSSelector": ...
     @property
-    def root(self) -> "LexborNode" | None: ...
+    def root(self) -> LexborNode | None: ...
     @property
-    def body(self) -> "LexborNode" | None: ...
+    def body(self) -> LexborNode | None: ...
     @property
-    def head(self) -> None | "LexborNode": ...
-    def tags(self, name: str) -> list["LexborNode"]: ...
+    def head(self) -> LexborNode | None: ...
+    def tags(self, name: str) -> list[LexborNode]: ...
     def text(
         self, deep: bool = True, separator: str = "", strip: bool = False
     ) -> str: ...
     @property
-    def html(self) -> None | str: ...
-    def css(self, query: str) -> list["LexborNode"]: ...
+    def html(self) -> str | None: ...
+    def css(self, query: str) -> list[LexborNode]: ...
+    @overload
+    def css_first(
+        self, query: str, default: Any = ..., strict: Literal[True] = ...
+    ) -> LexborNode: ...
+    @overload
     def css_first(
-        self, query: str, default: DefaultT | None = None, strict: bool = False
-    ) -> "LexborNode" | DefaultT | None : ...
+        self, query: str, default: DefaultT, strict: bool = False
+    ) -> LexborNode | DefaultT: ...
+    @overload
+    def css_first(
+        self, query: str, default: None = ..., strict: bool = False
+    ) -> LexborNode | None: ...
     def strip_tags(self, tags: list[str], recursive: bool = False) -> None: ...
-    def select(self, query: str | None = None) -> "LexborSelector" | None: ...
+    def select(self, query: str | None = None) -> LexborSelector | None: ...
     def any_css_matches(self, selectors: tuple[str]) -> bool: ...
     def scripts_contain(self, query: str) -> bool: ...
     def scripts_srcs_contain(self, queries: tuple[str]) -> bool: ...
     def css_matches(self, selector: str) -> bool: ...
-    def clone(self) -> "LexborHTMLParser": ...
+    def clone(self) -> LexborHTMLParser: ...
     def unwrap_tags(self, tags: list[str]) -> None: ...
+
+def create_tag(tag: str) -> LexborNode:
+    """
+    Given an HTML tag name, e.g. `"div"`, create a single empty node for that tag,
+    e.g. `"<div></div>"`.
+    """
+    ...
+
+def parse_fragment(html: str) -> list[LexborNode]:
+    """
+    Given HTML, parse it into a list of Nodes, such that the nodes
+    correspond to the given HTML.
+
+    For contrast, HTMLParser adds `<html>`, `<head>`, and `<body>` tags
+    if they are missing. This function does not add these tags.
+    """
+    ...

selectolax/lexbor.pyx

@@ -7,6 +7,7 @@ include "utils.pxi"
 include "lexbor/attrs.pxi"
 include "lexbor/node.pxi"
 include "lexbor/selection.pxi"
+include "lexbor/util.pxi"
 
 # We don't inherit from HTMLParser here, because it also includes all the C code from Modest.
 

selectolax/modest/util.pxi

@@ -0,0 +1,19 @@
+include "../utils.pxi"
+
+def create_tag(tag: str):
+    """
+    Given an HTML tag name, e.g. `"div"`, create a single empty node for that tag,
+    e.g. `"<div></div>"`.
+    """
+    return do_create_tag(tag, HTMLParser)
+
+
+def parse_fragment(html: str):
+    """
+    Given HTML, parse it into a list of Nodes, such that the nodes
+    correspond to the given HTML.
+
+    For contrast, HTMLParser adds `<html>`, `<head>`, and `<body>` tags
+    if they are missing. This function does not add these tags.
+    """
+    return do_parse_fragment(html, HTMLParser)