Skip to content

馃悰 fix(markdown): preserve Unicode space emphasis #1291

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鈥檒l occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
gaborbernat merged 3 commits into from
Oct 10, 2026
Merged

馃悰 fix(markdown): preserve Unicode space emphasis #1291

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
05ec692
馃悰 fix(markdown): preserve Unicode space emphasis
gaborbernat Oct 10, 2026
32cc296
馃摑 docs(changelog): note Unicode space emphasis
gaborbernat Oct 10, 2026
7ce4636
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Oct 10, 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
1 change: 1 addition & 0 deletions docs/changelog/1291.bugfix.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
Preserve emphasis around nonbreaking and other Unicode spaces in Markdown output.
29 changes: 17 additions & 12 deletions src/turbohtml/_c/serialize/markdown.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -490,21 +490,26 @@ static void md_settle_pending(md_ctx *ctx) {
/* What a character is to the CommonMark flanking rules: whitespace, ASCII punctuation,
or (0) anything else. */
enum { MD_EDGE_SPACE = 1, MD_EDGE_PUNCT = 2 };
static const uint8_t MD_EDGE[128] = {
['\t'] = MD_EDGE_SPACE, ['\n'] = MD_EDGE_SPACE, ['\f'] = MD_EDGE_SPACE, ['\r'] = MD_EDGE_SPACE,
[' '] = MD_EDGE_SPACE, ['!'] = MD_EDGE_PUNCT, ['"'] = MD_EDGE_PUNCT, ['#'] = MD_EDGE_PUNCT,
['$'] = MD_EDGE_PUNCT, ['%'] = MD_EDGE_PUNCT, ['&'] = MD_EDGE_PUNCT, ['\''] = MD_EDGE_PUNCT,
['('] = MD_EDGE_PUNCT, [')'] = MD_EDGE_PUNCT, ['*'] = MD_EDGE_PUNCT, ['+'] = MD_EDGE_PUNCT,
[','] = MD_EDGE_PUNCT, ['-'] = MD_EDGE_PUNCT, ['.'] = MD_EDGE_PUNCT, ['/'] = MD_EDGE_PUNCT,
[':'] = MD_EDGE_PUNCT, [';'] = MD_EDGE_PUNCT, ['<'] = MD_EDGE_PUNCT, ['='] = MD_EDGE_PUNCT,
['>'] = MD_EDGE_PUNCT, ['?'] = MD_EDGE_PUNCT, ['@'] = MD_EDGE_PUNCT, ['['] = MD_EDGE_PUNCT,
['\\'] = MD_EDGE_PUNCT, [']'] = MD_EDGE_PUNCT, ['^'] = MD_EDGE_PUNCT, ['_'] = MD_EDGE_PUNCT,
['`'] = MD_EDGE_PUNCT, ['{'] = MD_EDGE_PUNCT, ['|'] = MD_EDGE_PUNCT, ['}'] = MD_EDGE_PUNCT,
['~'] = MD_EDGE_PUNCT,
/* U+3000 is the highest Zs space; direct indexing keeps the ASCII lookup unchanged. */
static const uint8_t MD_EDGE[0x3001] = {
['\t'] = MD_EDGE_SPACE, ['\n'] = MD_EDGE_SPACE, ['\f'] = MD_EDGE_SPACE, ['\r'] = MD_EDGE_SPACE,
[' '] = MD_EDGE_SPACE, ['!'] = MD_EDGE_PUNCT, ['"'] = MD_EDGE_PUNCT, ['#'] = MD_EDGE_PUNCT,
['$'] = MD_EDGE_PUNCT, ['%'] = MD_EDGE_PUNCT, ['&'] = MD_EDGE_PUNCT, ['\''] = MD_EDGE_PUNCT,
['('] = MD_EDGE_PUNCT, [')'] = MD_EDGE_PUNCT, ['*'] = MD_EDGE_PUNCT, ['+'] = MD_EDGE_PUNCT,
[','] = MD_EDGE_PUNCT, ['-'] = MD_EDGE_PUNCT, ['.'] = MD_EDGE_PUNCT, ['/'] = MD_EDGE_PUNCT,
[':'] = MD_EDGE_PUNCT, [';'] = MD_EDGE_PUNCT, ['<'] = MD_EDGE_PUNCT, ['='] = MD_EDGE_PUNCT,
['>'] = MD_EDGE_PUNCT, ['?'] = MD_EDGE_PUNCT, ['@'] = MD_EDGE_PUNCT, ['['] = MD_EDGE_PUNCT,
['\\'] = MD_EDGE_PUNCT, [']'] = MD_EDGE_PUNCT, ['^'] = MD_EDGE_PUNCT, ['_'] = MD_EDGE_PUNCT,
['`'] = MD_EDGE_PUNCT, ['{'] = MD_EDGE_PUNCT, ['|'] = MD_EDGE_PUNCT, ['}'] = MD_EDGE_PUNCT,
['~'] = MD_EDGE_PUNCT, [0xA0] = MD_EDGE_SPACE, [0x1680] = MD_EDGE_SPACE, [0x2000] = MD_EDGE_SPACE,
[0x2001] = MD_EDGE_SPACE, [0x2002] = MD_EDGE_SPACE, [0x2003] = MD_EDGE_SPACE, [0x2004] = MD_EDGE_SPACE,
[0x2005] = MD_EDGE_SPACE, [0x2006] = MD_EDGE_SPACE, [0x2007] = MD_EDGE_SPACE, [0x2008] = MD_EDGE_SPACE,
[0x2009] = MD_EDGE_SPACE, [0x200A] = MD_EDGE_SPACE, [0x202F] = MD_EDGE_SPACE, [0x205F] = MD_EDGE_SPACE,
[0x3000] = MD_EDGE_SPACE,
};

static inline uint8_t md_edge(Py_UCS4 ch) {
return ch < 128 ? MD_EDGE[ch] : 0;
return ch < sizeof(MD_EDGE) ? MD_EDGE[ch] : 0;
}

static int md_is_ascii_punct(Py_UCS4 ch) {
Expand Down
18 changes: 18 additions & 0 deletions tests/serialize/test_markdown.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -134,6 +134,24 @@ def test_inline_emphasis(html: str, expected: str) -> None:
assert md(html) == expected


@pytest.mark.parametrize(
("html", "expected"),
[
pytest.param("<p><i>&nbsp;</i></p>", "<em>\u00a0</em>", id="emphasis-only-nbsp"),
pytest.param("<p><b>&nbsp;x</b></p>", "<strong>\u00a0x</strong>", id="strong-leading-nbsp"),
pytest.param("<p><b>x&nbsp;</b></p>", "<strong>x\u00a0</strong>", id="strong-trailing-nbsp"),
pytest.param("<p>a<b>&nbsp;</b>z</p>", "a<strong>\u00a0</strong>z", id="strong-between-text"),
],
)
def test_nonbreaking_space_emphasis(html: str, expected: str) -> None:
assert md(html) == expected


@pytest.mark.parametrize("space", ["\u00a0", "\u1680", "\u2000", "\u200a", "\u202f", "\u205f", "\u3000"])
def test_unicode_space_emphasis(space: str) -> None:
assert md(f"<p><b>{space}</b></p>") == f"<strong>{space}</strong>"


@pytest.mark.parametrize("tag", ["code", "kbd", "samp"])
@pytest.mark.parametrize(
("content", "expected"),
Expand Down
Loading