"stuff")
-from ..common.utils import normalizeReference, isSpace
+from ..common.utils import isSpace, normalizeReference
from .state_inline import StateInline
diff --git a/markdown_it/rules_inline/newline.py b/markdown_it/rules_inline/newline.py
index b4b8a67f..3034e408 100644
--- a/markdown_it/rules_inline/newline.py
+++ b/markdown_it/rules_inline/newline.py
@@ -1,8 +1,8 @@
# Proceess '\n'
import re
-from .state_inline import StateInline
from ..common.utils import charCodeAt, isSpace
+from .state_inline import StateInline
endSpace = re.compile(r" +$")
diff --git a/markdown_it/rules_inline/state_inline.py b/markdown_it/rules_inline/state_inline.py
index 54555411..283532cc 100644
--- a/markdown_it/rules_inline/state_inline.py
+++ b/markdown_it/rules_inline/state_inline.py
@@ -1,23 +1,26 @@
-from collections import namedtuple
-from typing import Dict, List, MutableMapping, Optional, TYPE_CHECKING
+from __future__ import annotations
-import attr
+from collections import namedtuple
+from collections.abc import MutableMapping
+from dataclasses import dataclass
+from typing import TYPE_CHECKING
-from ..token import Token
+from .._compat import DATACLASS_KWARGS
+from ..common.utils import isMdAsciiPunct, isPunctChar, isWhiteSpace
from ..ruler import StateBase
-from ..common.utils import isWhiteSpace, isPunctChar, isMdAsciiPunct
+from ..token import Token
if TYPE_CHECKING:
from markdown_it import MarkdownIt
-@attr.s(slots=True)
+@dataclass(**DATACLASS_KWARGS)
class Delimiter:
# Char code of the starting marker (number).
- marker: int = attr.ib()
+ marker: int
# Total length of these series of delimiters.
- length: int = attr.ib()
+ length: int
# An amount of characters before this one that's equivalent to
# current one. In plain English: if this delimiter does not open
@@ -25,21 +28,21 @@ class Delimiter:
#
# Used to skip sequences like "*****" in one step, for 1st asterisk
# value will be 0, for 2nd it's 1 and so on.
- jump: int = attr.ib()
+ jump: int
# A position of the token this delimiter corresponds to.
- token: int = attr.ib()
+ token: int
# If this delimiter is matched as a valid opener, `end` will be
# equal to its position, otherwise it's `-1`.
- end: int = attr.ib()
+ end: int
# Boolean flags that determine if this delimiter could open or close
# an emphasis.
- open: bool = attr.ib()
- close: bool = attr.ib()
+ open: bool
+ close: bool
- level: bool = attr.ib(default=None)
+ level: bool | None = None
Scanned = namedtuple("Scanned", ["can_open", "can_close", "length"])
@@ -47,13 +50,13 @@ class Delimiter:
class StateInline(StateBase):
def __init__(
- self, src: str, md: "MarkdownIt", env: MutableMapping, outTokens: List[Token]
+ self, src: str, md: MarkdownIt, env: MutableMapping, outTokens: list[Token]
):
self.src = src
self.env = env
self.md = md
self.tokens = outTokens
- self.tokens_meta: List[Optional[dict]] = [None] * len(outTokens)
+ self.tokens_meta: list[dict | None] = [None] * len(outTokens)
self.pos = 0
self.posMax = len(self.src)
@@ -63,16 +66,16 @@ def __init__(
# Stores { start: end } pairs. Useful for backtrack
# optimization of pairs parse (emphasis, strikes).
- self.cache: Dict[int, int] = {}
+ self.cache: dict[int, int] = {}
# List of emphasis-like delimiters for current tag
- self.delimiters: List[Delimiter] = []
+ self.delimiters: list[Delimiter] = []
# Stack of delimiter lists for upper level tags
- self._prev_delimiters: List[List[Delimiter]] = []
+ self._prev_delimiters: list[list[Delimiter]] = []
# backticklength => last seen position
- self.backticks: Dict[int, int] = {}
+ self.backticks: dict[int, int] = {}
self.backticksScanned = False
def __repr__(self):
diff --git a/markdown_it/rules_inline/strikethrough.py b/markdown_it/rules_inline/strikethrough.py
index 87af4b46..107ea26b 100644
--- a/markdown_it/rules_inline/strikethrough.py
+++ b/markdown_it/rules_inline/strikethrough.py
@@ -1,6 +1,7 @@
# ~~strike through~~
-from typing import List
-from .state_inline import StateInline, Delimiter
+from __future__ import annotations
+
+from .state_inline import Delimiter, StateInline
def tokenize(state: StateInline, silent: bool):
@@ -51,7 +52,7 @@ def tokenize(state: StateInline, silent: bool):
return True
-def _postProcess(state: StateInline, delimiters: List[Delimiter]):
+def _postProcess(state: StateInline, delimiters: list[Delimiter]):
loneMarkers = []
maximum = len(delimiters)
@@ -93,7 +94,7 @@ def _postProcess(state: StateInline, delimiters: List[Delimiter]):
i += 1
- # If a marker sequence has an odd number of characters, it's splitted
+ # If a marker sequence has an odd number of characters, it's split
# like this: `~~~~~` -> `~` + `~~` + `~~`, leaving one marker at the
# start of the sequence.
#
diff --git a/markdown_it/rules_inline/text.py b/markdown_it/rules_inline/text.py
index f36f069a..ec6ee0fa 100644
--- a/markdown_it/rules_inline/text.py
+++ b/markdown_it/rules_inline/text.py
@@ -3,14 +3,15 @@
from .state_inline import StateInline
-
# Rule to skip pure text
-# '{}$%@~+=:' reserved for extentions
+# '{}$%@~+=:' reserved for extensions
# !, ", #, $, %, &, ', (, ), *, +, ,, -, ., /, :, ;, <, =, >, ?, @, [, \, ], ^, _, `, {, |, }, or ~
# !!!! Don't confuse with "Markdown ASCII Punctuation" chars
# http://spec.commonmark.org/0.15/#ascii-punctuation-character
+
+
def isTerminatorChar(ch):
return ch in {
0x0A, # /* \n */:
diff --git a/markdown_it/token.py b/markdown_it/token.py
index 36646e07..b20875b6 100644
--- a/markdown_it/token.py
+++ b/markdown_it/token.py
@@ -1,17 +1,11 @@
-from typing import (
- Any,
- Callable,
- Dict,
- List,
- MutableMapping,
- Optional,
- Tuple,
- Type,
- Union,
-)
+from __future__ import annotations
+
+from collections.abc import Callable, MutableMapping
+import dataclasses as dc
+from typing import Any
import warnings
-import attr
+from markdown_it._compat import DATACLASS_KWARGS
def convert_attrs(value: Any) -> Any:
@@ -26,44 +20,65 @@ def convert_attrs(value: Any) -> Any:
return value
-@attr.s(slots=True)
+@dc.dataclass(**DATACLASS_KWARGS)
class Token:
- # Type of the token (string, e.g. "paragraph_open")
- type: str = attr.ib()
- # html tag name, e.g. "p"
- tag: str = attr.ib()
- # Level change (number in {-1, 0, 1} set), where:
- # - `1` means the tag is opening
- # - `0` means the tag is self-closing
- # - `-1` means the tag is closing
- nesting: int = attr.ib()
- # Html attributes. Note this differs from the upstream "list of lists" format
- attrs: Dict[str, Union[str, int, float]] = attr.ib(
- factory=dict, converter=convert_attrs
- )
- # Source map info. Format: `[ line_begin, line_end ]`
- map: Optional[List[int]] = attr.ib(default=None)
- # nesting level, the same as `state.level`
- level: int = attr.ib(default=0)
- # An array of child nodes (inline and img tokens)
- children: Optional[List["Token"]] = attr.ib(default=None)
- # In a case of self-closing tag (code, html, fence, etc.),
- # it has contents of this tag.
- content: str = attr.ib(default="")
- # '*' or '_' for emphasis, fence string for fence, etc.
- markup: str = attr.ib(default="")
- # Additional information:
- # - Info string for "fence" tokens
- # - The value "auto" for autolink "link_open" and "link_close" tokens
- info: str = attr.ib(default="")
- # A place for plugins to store any arbitrary data
- meta: dict = attr.ib(factory=dict)
- # True for block-level tokens, false for inline tokens.
- # Used in renderer to calculate line breaks
- block: bool = attr.ib(default=False)
- # If it's true, ignore this element when rendering.
- # Used for tight lists to hide paragraphs.
- hidden: bool = attr.ib(default=False)
+
+ type: str
+ """Type of the token (string, e.g. "paragraph_open")"""
+
+ tag: str
+ """HTML tag name, e.g. 'p'"""
+
+ nesting: int
+ """Level change (number in {-1, 0, 1} set), where:
+ - `1` means the tag is opening
+ - `0` means the tag is self-closing
+ - `-1` means the tag is closing
+ """
+
+ attrs: dict[str, str | int | float] = dc.field(default_factory=dict)
+ """HTML attributes.
+ Note this differs from the upstream "list of lists" format,
+ although than an instance can still be initialised with this format.
+ """
+
+ map: list[int] | None = None
+ """Source map info. Format: `[ line_begin, line_end ]`"""
+
+ level: int = 0
+ """Nesting level, the same as `state.level`"""
+
+ children: list[Token] | None = None
+ """Array of child nodes (inline and img tokens)."""
+
+ content: str = ""
+ """Inner content, in the case of a self-closing tag (code, html, fence, etc.),"""
+
+ markup: str = ""
+ """'*' or '_' for emphasis, fence string for fence, etc."""
+
+ info: str = ""
+ """Additional information:
+ - Info string for "fence" tokens
+ - The value "auto" for autolink "link_open" and "link_close" tokens
+ - The string value of the item marker for ordered-list "list_item_open" tokens
+ """
+
+ meta: dict = dc.field(default_factory=dict)
+ """A place for plugins to store any arbitrary data"""
+
+ block: bool = False
+ """True for block-level tokens, false for inline tokens.
+ Used in renderer to calculate line breaks
+ """
+
+ hidden: bool = False
+ """If true, ignore this element when rendering.
+ Used for tight lists to hide paragraphs.
+ """
+
+ def __post_init__(self):
+ self.attrs = convert_attrs(self.attrs)
def attrIndex(self, name: str) -> int:
warnings.warn(
@@ -74,20 +89,20 @@ def attrIndex(self, name: str) -> int:
return -1
return list(self.attrs.keys()).index(name)
- def attrItems(self) -> List[Tuple[str, Union[str, int, float]]]:
+ def attrItems(self) -> list[tuple[str, str | int | float]]:
"""Get (key, value) list of attrs."""
return list(self.attrs.items())
- def attrPush(self, attrData: Tuple[str, Union[str, int, float]]) -> None:
+ def attrPush(self, attrData: tuple[str, str | int | float]) -> None:
"""Add `[ name, value ]` attribute to list. Init attrs if necessary."""
name, value = attrData
self.attrSet(name, value)
- def attrSet(self, name: str, value: Union[str, int, float]) -> None:
+ def attrSet(self, name: str, value: str | int | float) -> None:
"""Set `name` attribute to `value`. Override old value if exists."""
self.attrs[name] = value
- def attrGet(self, name: str) -> Union[None, str, int, float]:
+ def attrGet(self, name: str) -> None | str | int | float:
"""Get the value of attribute `name`, or null if it does not exist."""
return self.attrs.get(name, None)
@@ -106,18 +121,18 @@ def attrJoin(self, name: str, value: str) -> None:
else:
self.attrs[name] = value
- def copy(self) -> "Token":
+ def copy(self, **changes: Any) -> Token:
"""Return a shallow copy of the instance."""
- return attr.evolve(self)
+ return dc.replace(self, **changes)
def as_dict(
self,
*,
children: bool = True,
as_upstream: bool = True,
- meta_serializer: Optional[Callable[[dict], Any]] = None,
- filter: Optional[Callable[[attr.Attribute, Any], bool]] = None,
- dict_factory: Type[MutableMapping[str, Any]] = dict,
+ meta_serializer: Callable[[dict], Any] | None = None,
+ filter: Callable[[str, Any], bool] | None = None,
+ dict_factory: Callable[..., MutableMapping[str, Any]] = dict,
) -> MutableMapping[str, Any]:
"""Return the token as a dictionary.
@@ -127,16 +142,15 @@ def as_dict(
:param meta_serializer: hook for serializing ``Token.meta``
:param filter: A callable whose return code determines whether an
attribute or element is included (``True``) or dropped (``False``).
- Is called with the `attr.Attribute` as the first argument and the
- value as the second argument.
+ Is called with the (key, value) pair.
:param dict_factory: A callable to produce dictionaries from.
For example, to produce ordered dictionaries instead of normal Python
dictionaries, pass in ``collections.OrderedDict``.
"""
- mapping = attr.asdict(
- self, recurse=False, filter=filter, dict_factory=dict_factory
- )
+ mapping = dict_factory((f.name, getattr(self, f.name)) for f in dc.fields(self))
+ if filter:
+ mapping = dict_factory((k, v) for k, v in mapping.items() if filter(k, v))
if as_upstream and "attrs" in mapping:
mapping["attrs"] = (
None
@@ -159,73 +173,9 @@ def as_dict(
return mapping
@classmethod
- def from_dict(cls, dct: MutableMapping[str, Any]) -> "Token":
+ def from_dict(cls, dct: MutableMapping[str, Any]) -> Token:
"""Convert a dict to a Token."""
token = cls(**dct)
if token.children:
token.children = [cls.from_dict(c) for c in token.children] # type: ignore[arg-type]
return token
-
-
-@attr.s(slots=True)
-class NestedTokens:
- """A class that closely resembles a Token,
- but for a an opening/closing Token pair, and their containing children.
- """
-
- opening: Token = attr.ib()
- closing: Token = attr.ib()
- children: List[Union[Token, "NestedTokens"]] = attr.ib(factory=list)
-
- def __getattr__(self, name):
- return getattr(self.opening, name)
-
- def attrGet(self, name: str) -> Union[None, str, int, float]:
- """ Get the value of attribute `name`, or null if it does not exist."""
- return self.opening.attrGet(name)
-
-
-def nest_tokens(tokens: List[Token]) -> List[Union[Token, NestedTokens]]:
- """Convert the token stream to a list of tokens and nested tokens.
-
- ``NestedTokens`` contain the open and close tokens and a list of children
- of all tokens in between (recursively nested)
- """
- warnings.warn(
- "`markdown_it.token.nest_tokens` and `markdown_it.token.NestedTokens`"
- " are deprecated. Please migrate to `markdown_it.tree.SyntaxTreeNode`",
- DeprecationWarning,
- )
-
- output: List[Union[Token, NestedTokens]] = []
-
- tokens = list(reversed(tokens))
- while tokens:
- token = tokens.pop()
-
- if token.nesting == 0:
- token = token.copy()
- output.append(token)
- if token.children:
- # Ignore type checkers because `nest_tokens` doesn't respect
- # typing of `Token.children`. We add `NestedTokens` into a
- # `List[Token]` here.
- token.children = nest_tokens(token.children) # type: ignore
- continue
-
- assert token.nesting == 1, token.nesting
-
- nested_tokens = [token]
- nesting = 1
- while tokens and nesting != 0:
- token = tokens.pop()
- nested_tokens.append(token)
- nesting += token.nesting
- if nesting != 0:
- raise ValueError(f"unclosed tokens starting {nested_tokens[0]}")
-
- child = NestedTokens(nested_tokens[0], nested_tokens[-1])
- output.append(child)
- child.children = nest_tokens(nested_tokens[1:-1])
-
- return output
diff --git a/markdown_it/tree.py b/markdown_it/tree.py
index edbc35e0..09476b22 100644
--- a/markdown_it/tree.py
+++ b/markdown_it/tree.py
@@ -2,20 +2,11 @@
This module is not part of upstream JavaScript markdown-it.
"""
+from __future__ import annotations
+
+from collections.abc import Generator, Sequence
import textwrap
-from typing import (
- Generator,
- NamedTuple,
- Sequence,
- Tuple,
- Dict,
- List,
- Optional,
- Any,
- TypeVar,
- overload,
- Union,
-)
+from typing import Any, NamedTuple, TypeVar, overload
from .token import Token
from .utils import _removesuffix
@@ -50,10 +41,10 @@ def __init__(
If `create_root` is True, create a root node for the document.
"""
# Only nodes representing an unnested token have self.token
- self.token: Optional[Token] = None
+ self.token: Token | None = None
# Only containers have nester tokens
- self.nester_tokens: Optional[_NesterTokens] = None
+ self.nester_tokens: _NesterTokens | None = None
# Root node does not have self.parent
self._parent: Any = None
@@ -92,18 +83,16 @@ def __getitem__(self: _NodeType, item: int) -> _NodeType:
...
@overload
- def __getitem__(self: _NodeType, item: slice) -> List[_NodeType]:
+ def __getitem__(self: _NodeType, item: slice) -> list[_NodeType]:
...
- def __getitem__(
- self: _NodeType, item: Union[int, slice]
- ) -> Union[_NodeType, List[_NodeType]]:
+ def __getitem__(self: _NodeType, item: int | slice) -> _NodeType | list[_NodeType]:
return self.children[item]
- def to_tokens(self: _NodeType) -> List[Token]:
+ def to_tokens(self: _NodeType) -> list[Token]:
"""Recover the linear token stream."""
- def recursive_collect_tokens(node: _NodeType, token_list: List[Token]) -> None:
+ def recursive_collect_tokens(node: _NodeType, token_list: list[Token]) -> None:
if node.type == "root":
for child in node.children:
recursive_collect_tokens(child, token_list)
@@ -116,24 +105,24 @@ def recursive_collect_tokens(node: _NodeType, token_list: List[Token]) -> None:
recursive_collect_tokens(child, token_list)
token_list.append(node.nester_tokens.closing)
- tokens: List[Token] = []
+ tokens: list[Token] = []
recursive_collect_tokens(self, tokens)
return tokens
@property
- def children(self: _NodeType) -> List[_NodeType]:
+ def children(self: _NodeType) -> list[_NodeType]:
return self._children
@children.setter
- def children(self: _NodeType, value: List[_NodeType]) -> None:
+ def children(self: _NodeType, value: list[_NodeType]) -> None:
self._children = value
@property
- def parent(self: _NodeType) -> Optional[_NodeType]:
+ def parent(self: _NodeType) -> _NodeType | None:
return self._parent
@parent.setter
- def parent(self: _NodeType, value: Optional[_NodeType]) -> None:
+ def parent(self: _NodeType, value: _NodeType | None) -> None:
self._parent = value
@property
@@ -178,7 +167,7 @@ def type(self) -> str:
return _removesuffix(self.nester_tokens.opening.type, "_open")
@property
- def next_sibling(self: _NodeType) -> Optional[_NodeType]:
+ def next_sibling(self: _NodeType) -> _NodeType | None:
"""Get the next node in the sequence of siblings.
Returns `None` if this is the last sibling.
@@ -189,7 +178,7 @@ def next_sibling(self: _NodeType) -> Optional[_NodeType]:
return None
@property
- def previous_sibling(self: _NodeType) -> Optional[_NodeType]:
+ def previous_sibling(self: _NodeType) -> _NodeType | None:
"""Get the previous node in the sequence of siblings.
Returns `None` if this is the first sibling.
@@ -282,21 +271,21 @@ def _attribute_token(self) -> Token:
@property
def tag(self) -> str:
- """html tag name, e.g. \"p\""""
+ """html tag name, e.g. \"p\" """
return self._attribute_token().tag
@property
- def attrs(self) -> Dict[str, Union[str, int, float]]:
+ def attrs(self) -> dict[str, str | int | float]:
"""Html attributes."""
return self._attribute_token().attrs
- def attrGet(self, name: str) -> Union[None, str, int, float]:
+ def attrGet(self, name: str) -> None | str | int | float:
"""Get the value of attribute `name`, or null if it does not exist."""
return self._attribute_token().attrGet(name)
@property
- def map(self) -> Optional[Tuple[int, int]]:
- """Source map info. Format: `Tuple[ line_begin, line_end ]`"""
+ def map(self) -> tuple[int, int] | None:
+ """Source map info. Format: `tuple[ line_begin, line_end ]`"""
map_ = self._attribute_token().map
if map_:
# Type ignore because `Token`s attribute types are not perfect
diff --git a/markdown_it/utils.py b/markdown_it/utils.py
index 5d1ce723..2ba2995a 100644
--- a/markdown_it/utils.py
+++ b/markdown_it/utils.py
@@ -1,5 +1,7 @@
+from __future__ import annotations
+
+from collections.abc import Callable
from pathlib import Path
-from typing import Callable, List, Optional, Union
class OptionsDict(dict):
@@ -78,16 +80,16 @@ def langPrefix(self, value: str):
self["langPrefix"] = value
@property
- def highlight(self) -> Optional[Callable[[str, str, str], str]]:
+ def highlight(self) -> Callable[[str, str, str], str] | None:
"""Highlighter function: (content, langName, langAttrs) -> escaped HTML."""
return self["highlight"]
@highlight.setter
- def highlight(self, value: Optional[Callable[[str, str, str], str]]):
+ def highlight(self, value: Callable[[str, str, str], str] | None):
self["highlight"] = value
-def read_fixture_file(path: Union[str, Path]) -> List[list]:
+def read_fixture_file(path: str | Path) -> list[list]:
text = Path(path).read_text(encoding="utf-8")
tests = []
section = 0
diff --git a/profiler.py b/profiler.py
new file mode 100644
index 00000000..414a7727
--- /dev/null
+++ b/profiler.py
@@ -0,0 +1,19 @@
+"""A script for profiling.
+
+To generate and read results:
+ - `tox -e profile`
+ - `firefox .tox/prof/output.svg`
+"""
+from pathlib import Path
+
+from markdown_it import MarkdownIt
+
+commonmark_spec = (
+ (Path(__file__).parent / "tests" / "test_cmark_spec" / "spec.md")
+ .read_bytes()
+ .decode()
+)
+
+# Run this a few times to emphasize over imports and other overhead above
+for _ in range(10):
+ MarkdownIt().render(commonmark_spec)
diff --git a/pyproject.toml b/pyproject.toml
index f7e22d4a..e0017185 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,104 @@
[build-system]
-requires = ["setuptools>=46.4.0", "wheel"]
-build-backend = "setuptools.build_meta"
+requires = ["flit_core >=3.4,<4"]
+build-backend = "flit_core.buildapi"
+
+[project]
+name = "markdown-it-py"
+dynamic = ["version"]
+description = "Python port of markdown-it. Markdown parsing, done right!"
+readme = "README.md"
+authors = [{name = "Chris Sewell", email = "chrisj_sewell@hotmail.com"}]
+license = {file = "LICENSE"}
+classifiers = [
+ "Development Status :: 5 - Production/Stable",
+ "Intended Audience :: Developers",
+ "License :: OSI Approved :: MIT License",
+ "Programming Language :: Python :: 3",
+ "Programming Language :: Python :: 3.7",
+ "Programming Language :: Python :: 3.8",
+ "Programming Language :: Python :: 3.9",
+ "Programming Language :: Python :: 3.10",
+ "Programming Language :: Python :: Implementation :: CPython",
+ "Programming Language :: Python :: Implementation :: PyPy",
+ "Topic :: Software Development :: Libraries :: Python Modules",
+ "Topic :: Text Processing :: Markup",
+]
+keywords = ["markdown", "lexer", "parser", "commonmark", "markdown-it"]
+requires-python = ">=3.7"
+dependencies = [
+ "mdurl~=0.1",
+ "typing_extensions>=3.7.4;python_version<'3.8'",
+]
+
+[project.urls]
+Homepage = "https://github.com/executablebooks/markdown-it-py"
+Documentation = "https://markdown-it-py.readthedocs.io/"
+
+[project.optional-dependencies]
+code_style = ["pre-commit==2.6"]
+compare = [
+ "commonmark~=0.9.1",
+ "markdown~=3.3.6",
+ "mistletoe~=0.8.1",
+ "mistune~=2.0.2",
+ "panflute~=2.1.3",
+]
+linkify = ["linkify-it-py~=1.0"]
+plugins = ["mdit-py-plugins"]
+rtd = [
+ "attrs",
+ "myst-parser",
+ "pyyaml",
+ "sphinx",
+ "sphinx-copybutton",
+ "sphinx-design",
+ "sphinx_book_theme",
+]
+testing = [
+ "coverage",
+ "pytest",
+ "pytest-cov",
+ "pytest-regressions",
+]
+benchmarking = [
+ "psutil",
+ "pytest",
+ "pytest-benchmark~=3.2",
+]
+profiling = ["gprof2dot"]
+
+[project.scripts]
+markdown-it = "markdown_it.cli.parse:main"
+
+[tool.flit.module]
+name = "markdown_it"
+
+[tool.flit.sdist]
+exclude = [
+ "docs/",
+ "tests/",
+ "benchmarking/"
+]
+
+[tool.isort]
+profile = "black"
+force_sort_within_sections = true
+
+[tool.mypy]
+show_error_codes = true
+warn_unused_ignores = true
+warn_redundant_casts = true
+no_implicit_optional = true
+strict_equality = true
+implicit_reexport = false
+
+[[tool.mypy.overrides]]
+module = ["tests.test_plugins.*", "markdown.*"]
+ignore_errors = true
+
+[[tool.mypy.overrides]]
+module = ["markdown.*"]
+ignore_missing_imports = true
[tool.pytest.ini_options]
xfail_strict = true
diff --git a/setup.cfg b/setup.cfg
deleted file mode 100644
index 2815e3eb..00000000
--- a/setup.cfg
+++ /dev/null
@@ -1,92 +0,0 @@
-[metadata]
-name = markdown-it-py
-version = attr: markdown_it.__version__
-description = Python port of markdown-it. Markdown parsing, done right!
-long_description = file: README.md
-long_description_content_type = text/markdown
-url = https://github.com/executablebooks/markdown-it-py
-author = Chris Sewell
-author_email = chrisj_sewell@hotmail.com
-license = MIT
-license_file = LICENSE
-classifiers =
- Development Status :: 5 - Production/Stable
- Intended Audience :: Developers
- License :: OSI Approved :: MIT License
- Programming Language :: Python :: 3
- Programming Language :: Python :: 3.6
- Programming Language :: Python :: 3.7
- Programming Language :: Python :: 3.8
- Programming Language :: Python :: 3.9
- Programming Language :: Python :: 3.10
- Programming Language :: Python :: Implementation :: CPython
- Programming Language :: Python :: Implementation :: PyPy
- Topic :: Software Development :: Libraries :: Python Modules
- Topic :: Text Processing :: Markup
-keywords = markdown lexer parser development
-project_urls =
- Documentation=https://markdown-it-py.readthedocs.io
-
-[options]
-packages = find:
-install_requires =
- attrs>=19,<22
- mdurl~=0.1
- typing_extensions>=3.7.4;python_version<'3.8'
-python_requires = ~=3.6
-include_package_data = True
-zip_safe = False
-
-[options.entry_points]
-console_scripts =
- markdown-it = markdown_it.cli.parse:main
-
-[options.extras_require]
-code_style =
- pre-commit==2.6
-compare =
- commonmark~=0.9.1
- markdown~=3.2.2
- mistletoe-ebp~=0.10.0
- mistune~=0.8.4
- panflute~=1.12
-linkify =
- linkify-it-py~=1.0
-plugins =
- mdit-py-plugins
-rtd =
- myst-nb==0.13.0a1
- pyyaml
- sphinx>=2,<4
- sphinx-copybutton
- sphinx-panels~=0.4.0
- sphinx_book_theme
-testing =
- coverage
- pytest
- pytest-cov
- pytest-regressions
-benchmarking =
- psutil
- pytest
- pytest-benchmark~=3.2
-
-[options.packages.find]
-exclude =
- test*
- benchmarking
-
-[mypy]
-show_error_codes = True
-warn_unused_ignores = True
-warn_redundant_casts = True
-no_implicit_optional = True
-strict_equality = True
-implicit_reexport = False
-
-[mypy-tests.test_plugins.*]
-ignore_errors = True
-
-[flake8]
-max-line-length = 100
-extend-ignore = E203
diff --git a/setup.py b/setup.py
deleted file mode 100644
index 36141267..00000000
--- a/setup.py
+++ /dev/null
@@ -1,6 +0,0 @@
-# This file is needed for editable installs (`pip install -e .`).
-# Can be removed once the following is resolved
-# https://github.com/pypa/packaging-problems/issues/256
-from setuptools import setup
-
-setup()
diff --git a/tests/test_api/test_token.py b/tests/test_api/test_token.py
index df4a0390..e3806b50 100644
--- a/tests/test_api/test_token.py
+++ b/tests/test_api/test_token.py
@@ -1,6 +1,6 @@
import warnings
-from markdown_it.token import Token, nest_tokens, NestedTokens
+from markdown_it.token import Token
def test_token():
@@ -36,33 +36,3 @@ def test_token():
def test_serialization():
token = Token("name", "tag", 0, children=[Token("other", "tag2", 0)])
assert token == Token.from_dict(token.as_dict())
-
-
-def test_nest_tokens():
- tokens = nest_tokens(
- [
- Token("start", "", 0),
- Token("open", "", 1),
- Token("open_inner", "", 1),
- Token("inner", "", 0),
- Token("close_inner", "", -1),
- Token("close", "", -1),
- Token("end", "", 0),
- ]
- )
- assert [t.type for t in tokens] == ["start", "open", "end"]
- assert isinstance(tokens[0], Token)
- assert isinstance(tokens[1], NestedTokens)
- assert isinstance(tokens[2], Token)
-
- nested = tokens[1]
- assert nested.opening.type == "open"
- assert nested.closing.type == "close"
- assert len(nested.children) == 1
- assert nested.children[0].type == "open_inner"
-
- nested2 = nested.children[0]
- assert nested2.opening.type == "open_inner"
- assert nested2.closing.type == "close_inner"
- assert len(nested2.children) == 1
- assert nested2.children[0].type == "inner"
diff --git a/tests/test_cmark_spec/spec.md b/tests/test_cmark_spec/spec.md
index e6f31375..2d79f7b7 100644
--- a/tests/test_cmark_spec/spec.md
+++ b/tests/test_cmark_spec/spec.md
@@ -4533,7 +4533,7 @@ inside the code block:
Note that rules #1 and #2 only apply to two cases: (a) cases
in which the lines to be included in a list item begin with a
-characer other than a space or tab, and (b) cases in which
+character other than a space or tab, and (b) cases in which
they begin with an indented code
block. In a case like the following, where the first block begins with
three spaces of indentation, the rules do not allow us to form a list item by
diff --git a/tests/test_cmark_spec/test_spec/test_file.html b/tests/test_cmark_spec/test_spec/test_file.html
index 9f73ce6c..1c2dc3cb 100644
--- a/tests/test_cmark_spec/test_spec/test_file.html
+++ b/tests/test_cmark_spec/test_spec/test_file.html
@@ -3418,7 +3418,7 @@ List items
Note that rules #1 and #2 only apply to two cases: (a) cases
in which the lines to be included in a list item begin with a
-characer other than a space or tab, and (b) cases in which
+character other than a space or tab, and (b) cases in which
they begin with an indented code
block. In a case like the following, where the first block begins with
three spaces of indentation, the rules do not allow us to form a list item by
diff --git a/tests/test_port/fixtures/commonmark_extras.md b/tests/test_port/fixtures/commonmark_extras.md
index ca14db31..168b039d 100644
--- a/tests/test_port/fixtures/commonmark_extras.md
+++ b/tests/test_port/fixtures/commonmark_extras.md
@@ -663,3 +663,34 @@ Issue #772. Header rule should not interfere with html tags.
==
.
+
+Issue #205. Space in link destination generates IndexError
+.
+[Contact](http:// mail.com)
+
+[Contact](mailto: mail@mail.com)
+.
+
[Contact](http:// mail.com)
+[Contact](mailto: mail@mail.com)
+.
+
+Issue #204. Combination of blockquotes, list and newlines causes an IndexError
+.
+> QUOTE
++ UNORDERED LIST ITEM
+ > INDENTED QUOTE
+
+
+
+.
+
+QUOTE
+
+
+- UNORDERED LIST ITEM
+
+INDENTED QUOTE
+
+
+
+.
diff --git a/tests/test_port/fixtures/fatal.md b/tests/test_port/fixtures/fatal.md
index dfeeb2e7..7b2afcfc 100644
--- a/tests/test_port/fixtures/fatal.md
+++ b/tests/test_port/fixtures/fatal.md
@@ -1,4 +1,4 @@
-Should not throw exception on invalid chars in URL (`*` not allowed in path) [mailformed URI]
+Should not throw exception on invalid chars in URL (`*` not allowed in path) [malformed URI]
.
[foo](<%test>)
.
@@ -6,7 +6,7 @@ Should not throw exception on invalid chars in URL (`*` not allowed in path) [ma
.
-Should not throw exception on broken utf-8 sequence in URL [mailformed URI]
+Should not throw exception on broken utf-8 sequence in URL [malformed URI]
.
[foo](%C3)
.
@@ -14,7 +14,7 @@ Should not throw exception on broken utf-8 sequence in URL [mailformed URI]
.
-Should not throw exception on broken utf-16 surrogates sequence in URL [mailformed URI]
+Should not throw exception on broken utf-16 surrogates sequence in URL [malformed URI]
.
[foo](�)
.
diff --git a/tests/test_port/test_misc.py b/tests/test_port/test_misc.py
index f5f821e9..62b5bf85 100644
--- a/tests/test_port/test_misc.py
+++ b/tests/test_port/test_misc.py
@@ -1,5 +1,4 @@
-from markdown_it import MarkdownIt
-from markdown_it import presets
+from markdown_it import MarkdownIt, presets
def test_highlight_arguments():
@@ -12,3 +11,34 @@ def highlight_func(str_, lang, attrs):
conf["options"]["highlight"] = highlight_func
md = MarkdownIt(config=conf)
assert md.render("``` a b c d \nhl\n```") == "==hl\n==
\n"
+
+
+def test_ordered_list_info():
+ def type_filter(tokens, type_):
+ return [t for t in tokens if t.type == type_]
+
+ md = MarkdownIt()
+
+ tokens = md.parse("1. Foo\n2. Bar\n20. Fuzz")
+ assert len(type_filter(tokens, "ordered_list_open")) == 1
+ tokens = type_filter(tokens, "list_item_open")
+ assert len(tokens) == 3
+ assert tokens[0].info == "1"
+ assert tokens[0].markup == "."
+ assert tokens[1].info == "2"
+ assert tokens[1].markup == "."
+ assert tokens[2].info == "20"
+ assert tokens[2].markup == "."
+
+ tokens = md.parse(" 1. Foo\n2. Bar\n 20. Fuzz\n 199. Flp")
+ assert len(type_filter(tokens, "ordered_list_open")) == 1
+ tokens = type_filter(tokens, "list_item_open")
+ assert len(tokens) == 4
+ assert tokens[0].info == "1"
+ assert tokens[0].markup == "."
+ assert tokens[1].info == "2"
+ assert tokens[1].markup == "."
+ assert tokens[2].info == "20"
+ assert tokens[2].markup == "."
+ assert tokens[3].info == "199"
+ assert tokens[3].markup == "."
diff --git a/tox.ini b/tox.ini
index 158faff1..f4e117e2 100644
--- a/tox.ini
+++ b/tox.ini
@@ -9,13 +9,13 @@ envlist = py37
[testenv]
usedevelop = true
-[testenv:py{36,37,38,39,310}]
+[testenv:py{37,38,39,310}]
extras =
linkify
testing
commands = pytest {posargs:tests/}
-[testenv:py{36,37,38,39,310}-plugins]
+[testenv:py{37,38,39,310}-plugins]
extras = testing
changedir = {envtmpdir}
allowlist_externals =
@@ -27,19 +27,39 @@ commands_pre =
commands =
pytest {posargs}
-[testenv:py{36,37,38,39}-bench-core]
+[testenv:py{37,38,39}-bench-core]
extras = benchmarking
commands = pytest benchmarking/bench_core.py {posargs}
-[testenv:py{36,37,38}-bench-packages]
+[testenv:py{37,38}-bench-packages]
extras = benchmarking,compare
commands = pytest benchmarking/bench_packages.py {posargs}
[testenv:docs-{update,clean}]
extras = linkify,plugins,rtd
-whitelist_externals = rm
+whitelist_externals =
+ echo
+ rm
setenv =
update: SKIP_APIDOC = true
commands =
clean: rm -rf docs/_build
sphinx-build -nW --keep-going -b {posargs:html} docs/ docs/_build/{posargs:html}
+commands_post = echo "open file://{toxinidir}/docs/_build/{posargs:html}/index.html"
+
+[testenv:profile]
+description = run profiler (use e.g. `firefox .tox/prof/output.svg` to open)
+extras = profiling
+allowlist_externals =
+ mkdir
+ dot
+commands =
+ mkdir -p "{toxworkdir}/prof"
+ python -m cProfile -o "{toxworkdir}/prof/output.pstats" profiler.py
+ gprof2dot -f pstats -o "{toxworkdir}/prof/output.dot" "{toxworkdir}/prof/output.pstats"
+ dot -Tsvg -o "{toxworkdir}/prof/output.svg" "{toxworkdir}/prof/output.dot"
+ python -c 'import pathlib; print("profiler svg output under file://\{0\}".format(pathlib.Path(r"{toxworkdir}") / "prof" / "output.svg"))'
+
+[flake8]
+max-line-length = 100
+extend-ignore = E203