Merge branch 'master' into dependabot/github_actions/actions/upload-artifact-7

Author: chrisjsewell

.github/workflows/tests.yml

@@ -52,7 +52,8 @@ jobs:
       run: |
         pytest tests/ --cov=markdown_it --cov-report=xml --cov-report=term-missing
     - name: Upload to Codecov
-      if: matrix.python-version == '3.10' && github.repository == 'executablebooks/markdown-it-py'
+      # note currently not working for external contributions
+      if: false && matrix.python-version == '3.10' && github.repository == 'executablebooks/markdown-it-py'
       uses: codecov/codecov-action@v5
       with:
         name: markdown-it-py-pytests
@@ -112,26 +113,23 @@ jobs:
 
   publish:
 
-    name: Publish to PyPi
+    name: Publish to PyPI
     needs: [pre-commit, tests]
     if: github.event_name == 'push' && startsWith(github.event.ref, 'refs/tags')
     runs-on: ubuntu-latest
+    permissions:
+      id-token: write
+    environment:
+      name: pypi
+      url: https://pypi.org/p/markdown-it-py
     steps:
-    - name: Checkout source
-      uses: actions/checkout@v4
-    - name: Set up Python
-      uses: actions/setup-python@v5
+    - uses: actions/checkout@v4
+    - uses: actions/setup-python@v5
       with:
         python-version: '3.10'
-    - name: install flit
-      run: |
-        pip install flit~=3.4
-    - name: Build and publish
-      run: |
-        flit publish
-      env:
-        FLIT_USERNAME: __token__
-        FLIT_PASSWORD: ${{ secrets.PYPI_KEY }}
+    - run: pip install flit~=3.4
+    - run: flit build
+    - uses: pypa/gh-action-pypi-publish@release/v1
 
   allgood:
     runs-on: ubuntu-latest

.pre-commit-config.yaml

@@ -16,22 +16,22 @@ exclude: >
 repos:
 
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v5.0.0
+    rev: v6.0.0
     hooks:
     - id: check-json
     - id: check-yaml
     - id: end-of-file-fixer
     - id: trailing-whitespace
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.12.8
+    rev: v0.15.12
     hooks:
     - id: ruff
       args: [--fix]
     - id: ruff-format
 
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.17.1
+    rev: v1.20.2
     hooks:
     - id: mypy
       additional_dependencies: [mdurl, typing-extensions]

CHANGELOG.md

@@ -1,5 +1,19 @@
 # Change Log
 
+## 4.2.0 - 2026-05-07
+
+* ✨ Add `make_fence_rule()` factory for configurable fence markers in [#394](https://github.com/executablebooks/markdown-it-py/pull/394)
+
+## 4.1.0 - 2025-05-06
+
+* ✨ Add `gfm-like2` preset with task lists, alerts, and single-tilde strikethrough core plugins in [#388](https://github.com/executablebooks/markdown-it-py/pull/388)
+* ✨ Allow plugins to register inline terminator characters in [#391](https://github.com/executablebooks/markdown-it-py/pull/391)
+* 👌 Fix quadratic complexity in `fragments_join` / `text_join` in [#389](https://github.com/executablebooks/markdown-it-py/pull/389), thanks to [@petricevich](https://github.com/petricevich)
+* 👌 Add `--stdin` option to CLI for reading Markdown from standard input in [#379](https://github.com/executablebooks/markdown-it-py/pull/379), thanks to [@mcepl](https://github.com/mcepl)
+* 🔧 Add typing to Scanner in [#382](https://github.com/executablebooks/markdown-it-py/pull/382), thanks to [@Alunderin](https://github.com/Alunderin)
+
+**Full Changelog**: <https://github.com/executablebooks/markdown-it-py/compare/v4.0.0...v4.1.0>
+
 ## 4.0.0 - 2024-08-10
 
 This primarily drops support for Python 3.9, adds support for Python 3.13,

docs/contributing.md

@@ -118,7 +118,12 @@ __Note:__ Don't try to replace text with HTML markup! That's not secure.
 
 ### Why is my inline rule not executed?
 
-The inline parser skips pieces of texts to optimize speed. It stops only on [a small set of chars](https://github.com/markdown-it/markdown-it/blob/master/lib/rules_inline/text.mjs), which can be tokens. We did not made this list extensible for performance reasons too.
+The inline parser skips pieces of texts to optimize speed. It stops only on [a small set of chars](https://github.com/executablebooks/markdown-it-py/blob/master/markdown_it/parser_inline.py), which can be tokens.
 
-If you are absolutely sure that something important is missing there - create a
-ticket and we will consider adding it as a new charcode.
+If your inline rule needs to trigger on a character that is not in the default terminator set, you can register it via `md.inline.add_terminator_char`:
+
+```python
+def my_plugin(md: MarkdownIt) -> None:
+    md.inline.add_terminator_char("w")  # stop text rule on 'w'
+    md.inline.ruler.push("my_rule", my_inline_rule)
+```

docs/plugins.md

@@ -6,6 +6,8 @@ The following plugins are embedded within the core package:
 
 - [tables](https://help.github.com/articles/organizing-information-with-tables/) (GFM)
 - [strikethrough](https://help.github.com/articles/basic-writing-and-formatting-syntax/#styling-text) (GFM)
+- [task lists](https://docs.github.com/en/get-started/writing-on-github/working-with-advanced-formatting/about-task-lists) (GFM) — `- [x] done`
+- [alerts](https://docs.github.com/en/get-started/writing-on-github/getting-started-with-writing-and-formatting-on-github/basic-writing-and-formatting-syntax#alerts) (GFM) — `> [!NOTE]`
 
 These can be enabled individually:
 
@@ -18,7 +20,8 @@ or as part of a configuration:
 
 ```python
 from markdown_it import MarkdownIt
-md = MarkdownIt("gfm-like")
+md = MarkdownIt("gfm-like")   # tables, strikethrough, linkify
+md = MarkdownIt("gfm-like2")  # + task lists, alerts, single-tilde strikethrough
 ```
 
 ```{seealso}

docs/using.md

@@ -58,6 +58,9 @@ You can define this configuration *via* directly supplying a dictionary or a pre
 - `gfm-like`: This configures the parser to approximately comply with the [GitHub Flavored Markdown specification](https://github.github.com/gfm/).
   Compared to `commonmark`, it enables the table, strikethrough and linkify components.
   **Important**, to use this configuration you must have `linkify-it-py` installed.
+- `gfm-like2`: Builds on `gfm-like` and additionally enables task lists (`- [x] done`),
+  GitHub-style alerts (`> [!NOTE]`), and single-tilde strikethrough (`~text~`).
+  **Important**, to use this configuration you must have `linkify-it-py` installed.
 
 ```{jupyter-execute}
 from markdown_it.presets import zero

markdown_it/__init__.py

@@ -1,6 +1,6 @@
 """A Python port of Markdown-It"""
 
 __all__ = ("MarkdownIt",)
-__version__ = "4.0.0"
+__version__ = "4.2.0"
 
 from .main import MarkdownIt

markdown_it/common/html_re.py

@@ -21,7 +21,9 @@
 cdata = "<!\\[CDATA\\[[\\s\\S]*?\\]\\]>"
 
 HTML_TAG_RE = re.compile(
-    "^(?:"
+    # No leading `^`: applied via `.match(src, pos)`, which anchors at `pos`
+    # without slicing `src[pos:]` (an O(len) copy per call, quadratic over a run).
+    "(?:"
     + open_tag
     + "|"
     + close_tag

markdown_it/main.py

@@ -26,6 +26,7 @@
     "zero": presets.zero.make(),
     "commonmark": presets.commonmark.make(),
     "gfm-like": presets.gfm_like.make(),
+    "gfm-like2": presets.gfm_like2.make(),
 }
 
 
@@ -125,7 +126,7 @@ def configure(
         if options_update:
             options = {**options, **options_update}  # type: ignore
 
-        self.set(options)  # type: ignore
+        self.set(options)
 
         if "components" in config:
             for name, component in config["components"].items():

markdown_it/parser_inline.py

@@ -3,6 +3,8 @@
 from __future__ import annotations
 
 from collections.abc import Callable
+import functools
+import re
 from typing import TYPE_CHECKING
 
 from . import rules_inline
@@ -15,6 +17,47 @@
     from markdown_it import MarkdownIt
 
 
+# Default set of characters that terminate a text token and allow inline rules to fire.
+# '{}$%@~+=:' reserved for extensions.
+# Note: Don't confuse with "Markdown ASCII Punctuation" chars.
+# http://spec.commonmark.org/0.15/#ascii-punctuation-character
+_DEFAULT_TERMINATORS: frozenset[str] = frozenset(
+    {
+        "\n",
+        "!",
+        "#",
+        "$",
+        "%",
+        "&",
+        "*",
+        "+",
+        "-",
+        ":",
+        "<",
+        "=",
+        ">",
+        "@",
+        "[",
+        "\\",
+        "]",
+        "^",
+        "_",
+        "`",
+        "{",
+        "}",
+        "~",
+    }
+)
+
+
+# Lazily compiled regex for the default terminator set.  The @cache ensures it is
+# compiled at most once (on first ParserInline instantiation) and shared across all
+# instances that have not added extra chars, keeping __init__ cost near zero.
+@functools.cache
+def _default_terminator_re() -> re.Pattern[str]:
+    return re.compile("[" + re.escape("".join(_DEFAULT_TERMINATORS)) + "]")
+
+
 # Parser rules
 RuleFuncInlineType = Callable[[StateInline, bool], bool]
 """(state: StateInline, silent: bool) -> matched: bool)
@@ -61,6 +104,30 @@ def __init__(self) -> None:
         self.ruler2 = Ruler[RuleFuncInline2Type]()
         for name, rule2 in _rules2:
             self.ruler2.push(name, rule2)
+        # Characters that stop the text rule, allowing other inline rules to fire.
+        # _extra_terminator_chars is only allocated when add_terminator_char() is called
+        # with a char outside the defaults, keeping __init__ allocation-free.
+        self._extra_terminator_chars: set[str] = set()
+        # Pre-compiled regex shared with all default instances (no copy in the common path).
+        self.terminator_re: re.Pattern[str] = _default_terminator_re()
+
+    def add_terminator_char(self, ch: str) -> None:
+        """Register a character that stops the ``text`` rule, allowing inline rules to fire.
+
+        This lets plugins declare which characters their inline rules react to,
+        mirroring the ``MARKER`` mechanism in the Rust markdown-it implementation.
+
+        :param ch: A single character to add to the terminator set.
+        """
+        if ch not in _DEFAULT_TERMINATORS and ch not in self._extra_terminator_chars:
+            self._extra_terminator_chars.add(ch)
+            self.terminator_re = re.compile(
+                "["
+                + re.escape(
+                    "".join(_DEFAULT_TERMINATORS | self._extra_terminator_chars)
+                )
+                + "]"
+            )
 
     def skipToken(self, state: StateInline) -> None:
         """Skip single token by running all rules in validation mode;
@@ -130,7 +197,7 @@ def tokenize(self, state: StateInline) -> None:
                     break
                 continue
 
-            state.pending += state.src[state.pos]
+            state.append_pending(state.src[state.pos])
             state.pos += 1
 
         if state.pending: