✨ NEW: Add superscript plugin and tests

docs/index.md

@@ -119,6 +119,12 @@ html_string = md.render("some *Markdown*")
 .. autofunction:: mdit_py_plugins.subscript.sub_plugin
 ```
 
+## Superscript
+
+```{eval-rst}
+.. autofunction:: mdit_py_plugins.superscript.superscript_plugin
+```
+
 ## MyST plugins
 
 `myst_blocks` and `myst_role` plugins are also available, for utilisation by the [MyST renderer](https://myst-parser.readthedocs.io/en/latest/using/syntax.html)
@@ -134,8 +140,6 @@ Use the `mdit_py_plugins` as a guide to write your own, following the [markdown-
 
 There are many other plugins which could easily be ported from the JS versions (and hopefully will):
 
-- [subscript](https://github.com/markdown-it/markdown-it-sub)
-- [superscript](https://github.com/markdown-it/markdown-it-sup)
 - [abbreviation](https://github.com/markdown-it/markdown-it-abbr)
 - [emoji](https://github.com/markdown-it/markdown-it-emoji)
 - [insert](https://github.com/markdown-it/markdown-it-ins)

mdit_py_plugins/subscript/__init__.py

@@ -10,21 +10,19 @@
 from __future__ import annotations
 
 from collections.abc import Sequence
-import re
 
 from markdown_it import MarkdownIt
 from markdown_it.renderer import RendererHTML
 from markdown_it.rules_inline import StateInline
 from markdown_it.token import Token
 from markdown_it.utils import EnvType, OptionsDict
 
+from mdit_py_plugins.utils import UNESCAPE_RE, WHITESPACE_RE
+
 __all__ = ["sub_plugin"]
 
 TILDE_CHAR = "~"
 
-WHITESPACE_RE = re.compile(r"(^|[^\\])(\\\\)*\s")
-UNESCAPE_RE = re.compile(r'\\([ \\!"#$%&\'()*+,.\/:;<=>?@[\]^_`{|}~-])')
-
 
 def tokenize(state: StateInline, silent: bool) -> bool:
     """Parse a ~subscript~ token."""

mdit_py_plugins/superscript/__init__.py

@@ -0,0 +1,5 @@
+"""Superscript tag plugin, ported from Markdown-It."""
+
+from .index import superscript_plugin
+
+__all__ = ("superscript_plugin",)

mdit_py_plugins/superscript/index.py

@@ -0,0 +1,110 @@
+"""Superscript tag plugin.
+
+Ported by Elijah Greenstein from https://github.com/markdown-it/markdown-it-sup
+cf. Subscript tag plugin, https://mdit-py-plugins.readthedocs.io/en/latest/#subscripts
+
+MIT License
+Copyright (c) 2014-2015 Vitaly Puzrin, Alex Kocharin.
+
+Permission is hereby granted, free of charge, to any person
+obtaining a copy of this software and associated documentation
+files (the "Software"), to deal in the Software without
+restriction, including without limitation the rights to use,
+copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the
+Software is furnished to do so, subject to the following
+conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+OTHER DEALINGS IN THE SOFTWARE.
+"""
+
+from markdown_it import MarkdownIt
+from markdown_it.rules_inline import StateInline
+
+from mdit_py_plugins.utils import UNESCAPE_RE, WHITESPACE_RE
+
+
+def superscript_plugin(md: MarkdownIt) -> None:
+    """Superscript (``<sup>``) tag plugin for Markdown-It-Py.
+
+    This plugin is ported from `markdown-it-sup
+    <https://github.com/markdown-it/markdown-it-sup>`_. Markup is based on the
+    `Pandoc superscript extension
+    <https://pandoc.org/MANUAL.html#superscripts-and-subscripts>`_.
+
+    Place superscripted text within caret ``^`` characters. You must escape any
+    spaces in the superscripted text. Note that you cannot use newline or tab
+    characters, and that nested markup is not supported.
+
+    Example usage:
+
+    >>> from markdown_it import MarkdownIt
+    >>> from mdit_py_plugins.superscript import superscript_plugin
+    >>> md = MarkdownIt().use(superscript_plugin)
+    >>> md.render("1^st^")
+    '<p>1<sup>st</sup></p>\\n'
+    >>> md.render("this^text\\\\ has\\\\ spaces^")
+    '<p>this<sup>text has spaces</sup></p>\\n'
+    """
+
+    def superscript(state: StateInline, silent: bool) -> bool:
+        """Parse inline text for superscripted text between caret ``^`` characters."""
+        maximum = state.posMax
+        start = state.pos
+
+        if ord(state.src[start]) != 0x5E:  # Check if char is `^`
+            return False
+        if silent:  # Do not run any pairs in validation mode
+            return False
+        if start + 2 >= maximum:
+            return False
+
+        state.pos = start + 1
+        found = False
+
+        while state.pos < maximum:
+            if ord(state.src[state.pos]) == 0x5E:  # Check if char is `^`
+                found = True
+                break
+            state.md.inline.skipToken(state)
+
+        if (not found) or (start + 1 == state.pos):
+            state.pos = start
+            return False
+
+        content = state.src[start + 1 : state.pos]
+
+        # Do not allow unescaped spaces/newlines inside
+        if WHITESPACE_RE.search(content) is not None:
+            state.pos = start
+            return False
+
+        # Found!
+        state.posMax = state.pos
+        state.pos = start + 1
+
+        # Earlier we checked !silent, but this implementation does not need it
+        token_so = state.push("sup_open", "sup", 1)
+        token_so.markup = "^"
+
+        token_t = state.push("text", "", 0)
+        token_t.content = UNESCAPE_RE.sub(r"\1", content)
+
+        token_sc = state.push("sup_close", "sup", -1)
+        token_sc.markup = "^"
+
+        state.pos = state.posMax + 1
+        state.posMax = maximum
+        return True
+
+    md.inline.ruler.after("emphasis", "sup", superscript)

mdit_py_plugins/utils.py

@@ -1,3 +1,5 @@
+import re
+
 from markdown_it.rules_block import StateBlock
 
 
@@ -10,3 +12,8 @@ def is_code_block(state: StateBlock, line: int) -> bool:
         pass
 
     return (state.sCount[line] - state.blkIndent) >= 4
+
+
+# Regex for subscript and superscript plugins
+UNESCAPE_RE = re.compile(r"\\([ \\!\"#$%&'()*+,./:;<=>?@[\]^_`{|}~-])")
+WHITESPACE_RE = re.compile(r"(^|[^\\])(\\\\)*\s")

tests/fixtures/superscript.md

@@ -0,0 +1,48 @@
+.
+^test^
+.
+<p><sup>test</sup></p>
+.
+
+.
+^foo\^
+.
+<p>^foo^</p>
+.
+
+.
+2^4 + 3^5
+.
+<p>2^4 + 3^5</p>
+.
+
+.
+^foo~bar^baz^bar~foo^
+.
+<p><sup>foo~bar</sup>baz<sup>bar~foo</sup></p>
+.
+
+.
+^\ foo\ ^
+.
+<p><sup> foo </sup></p>
+.
+
+.
+^foo\\\\\\\ bar^
+.
+<p><sup>foo\\\ bar</sup></p>
+.
+
+.
+^foo\\\\\\ bar^
+.
+<p>^foo\\\ bar^</p>
+.
+
+.
+**^foo^ bar**
+.
+<p><strong><sup>foo</sup> bar</strong></p>
+.
+

tests/test_superscript.py

@@ -0,0 +1,20 @@
+from pathlib import Path
+
+from markdown_it import MarkdownIt
+from markdown_it.utils import read_fixture_file
+import pytest
+
+from mdit_py_plugins.superscript import superscript_plugin
+
+FIXTURE_PATH = Path(__file__).parent.joinpath("fixtures")
+
+
+@pytest.mark.parametrize(
+    "line,title,input,expected",
+    read_fixture_file(FIXTURE_PATH.joinpath("superscript.md")),
+)
+def test_superscript_fixtures(line, title, input, expected):
+    md = MarkdownIt("commonmark").use(superscript_plugin)
+    md.options["xhtmlOut"] = False
+    text = md.render(input)
+    assert text.rstrip() == expected.rstrip()