Skip to content

Fix ASCII HTML block starts per CommonMark 0.31.2 #440

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
rupayon123 wants to merge 2 commits into
base: master
Choose a base branch
from
+33 −4
Open

Fix ASCII HTML block starts per CommonMark 0.31.2 #440

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
13f28fb
Fix ASCII HTML block start matching
rupayon123 Sep 26, 2026
3650b27
Keep HTML block regressions compatible with strict mypy
rupayon123 Sep 26, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 9 additions & 4 deletions markdown_it/rules_block/html_block.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,16 +14,21 @@
# last argument defines whether it can terminate a paragraph or not
HTML_SEQUENCES: list[tuple[re.Pattern[str], re.Pattern[str], bool]] = [
(
re.compile(r"^<(script|pre|style|textarea)(?=(\s|>|$))", re.IGNORECASE),
re.compile(r"<\/(script|pre|style|textarea)>", re.IGNORECASE),
re.compile(
r"^<(script|pre|style|textarea)(?=(\s|>|$))", re.IGNORECASE | re.ASCII
),
re.compile(r"<\/(script|pre|style|textarea)>", re.IGNORECASE | re.ASCII),
True,
),
(re.compile(r"^<!--"), re.compile(r"-->"), True),
(re.compile(r"^<\?"), re.compile(r"\?>"), True),
(re.compile(r"^<![A-Z]"), re.compile(r">"), True),
(re.compile(r"^<![A-Za-z]"), re.compile(r">"), True),
(re.compile(r"^<!\[CDATA\["), re.compile(r"\]\]>"), True),
(
re.compile("^</?(" + "|".join(block_names) + ")(?=(\\s|/?>|$))", re.IGNORECASE),
re.compile(
"^</?(" + "|".join(block_names) + ")(?=(\\s|/?>|$))",
re.IGNORECASE | re.ASCII,
),
re.compile(r"^$"),
True,
),
Expand Down
24 changes: 24 additions & 0 deletions tests/test_html_block_ascii.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,24 @@
"""CommonMark HTML block starts use ASCII letters for tag and declarations."""

from markdown_it import MarkdownIt


def test_ascii_declaration_ends_paragraph() -> None:
md = MarkdownIt("commonmark")
for declaration in ("<!doctype html>", "<!DOCTYPE html>"):
assert md.render(f"para\n{declaration}\n") == f"<p>para</p>\n{declaration}\n"


def test_unicode_casefold_does_not_start_html_block() -> None:
md = MarkdownIt("commonmark")
for tag in ("\u017fcript", "\u017ftyle", "d\u0130v", "d\u0131v"):
assert md.render(f"para\n<{tag}>\ntext\n") == (
f"<p>para\n&lt;{tag}&gt;\ntext</p>\n"
)


def test_ascii_mixed_case_tag_still_starts_html_block() -> None:
md = MarkdownIt("commonmark")
assert md.render("para\n<ScRiPt>\ntext\n</sCrIpT>\n") == (
"<p>para</p>\n<ScRiPt>\ntext\n</sCrIpT>\n"
)