Skip to content

fix: normalizer does not strip br nodes inside blockquote #720

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

Merged
hejsztynx merged 1 commit into from
Jul 22, 2026
+33 −7
Merged

fix: normalizer does not strip br nodes inside blockquote #720

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
6 changes: 5 additions & 1 deletion cpp/parser/GumboNormalizer.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -598,7 +598,11 @@ static void flatten_bq_node(GumboNode *node, buffer_t *ib, buffer_t *out) {
return;
}
if (is_br_node(node)) {
flush_inline_p(ib, out, NULL);
// Emit the canonical <br> so it is not silently dropped.
// With buffered inline content it just terminates the current paragraph.
if (!flush_inline_p(ib, out, NULL)) {
buffer_append_str(out, "<br>");
}
return;
}
if (is_block_producing(node) || is_blockquote_node(node)) {
Expand Down
16 changes: 12 additions & 4 deletions cpp/tests/GumboParserTest.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -401,7 +401,7 @@ TEST(GumboParserTest, DivRemappings) {
"</b>hello<div><br></div><div>hi</div></li></ul></div></div></"
"blockquote></span>"),
"<p>what do you think of this craziness</p><blockquote><p><b>another one "
"</b>hello</p><p>hi</p></blockquote>");
"</b>hello</p><br><p>hi</p></blockquote>");
}

TEST(GumboParserTest, ListFlattening) {
Expand Down Expand Up @@ -508,6 +508,13 @@ TEST(GumboParserTest, BrRemappings) {
"href='https://google.com'>Net</a></p>"),
"<p><b>Asdasdasd</b></p><br><br><p>Sent with <a "
"href=\"https://google.com\">Net</a></p>");
// A <br> between blockquote paragraphs is preserved.
EXPECT_EQ(
GumboParser::normalizeHtml(
"<blockquote><p>this is a pretty short blockquote.</p><br><p>This is "
"a line after an empty line.</p></blockquote>"),
"<blockquote><p>this is a pretty short blockquote.</p><br><p>This is a "
"line after an empty line.</p></blockquote>");
}

// Preserve text alignment
Expand Down Expand Up @@ -581,9 +588,10 @@ TEST(GumboParserTest, InterBlockWhitespace) {
EXPECT_EQ(GumboParser::normalizeHtml(
"<p>Asdasd</p>\n\n<p>Asdasd</p>\n\n<p>Asdasda</p>"),
"<p>Asdasd</p><p>Asdasd</p><p>Asdasda</p>");
EXPECT_EQ(GumboParser::normalizeHtml(
"<html>\n<p>Asdasd</p>\n<p>Asdasd</p>\n<p>Asdasda</p>\n</html>"),
"<p>Asdasd</p><p>Asdasd</p><p>Asdasda</p>");
EXPECT_EQ(
GumboParser::normalizeHtml(
"<html>\n<p>Asdasd</p>\n<p>Asdasd</p>\n<p>Asdasda</p>\n</html>"),
"<p>Asdasd</p><p>Asdasd</p><p>Asdasda</p>");
EXPECT_EQ(GumboParser::normalizeHtml("<p>Asdasd</p> <p>Asdasd</p>"),
"<p>Asdasd</p><p>Asdasd</p>");

Expand Down
12 changes: 11 additions & 1 deletion src/web/__tests__/htmlNormalizer.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -359,7 +359,7 @@ describe('htmlNormalizer', () => {
],
[
'<div>what do you think of this craziness</div><span><blockquote><div><div><ul><li><b>another one </b>hello<div><br></div><div>hi</div></li></ul></div></div></blockquote></span>',
'<p>what do you think of this craziness</p><blockquote><p><b>another one </b>hello</p><p>hi</p></blockquote>',
'<p>what do you think of this craziness</p><blockquote><p><b>another one </b>hello</p><br><p>hi</p></blockquote>',
],
])('%s → %s', (input, expected) => {
expect(normalizeHtml(input)).toBe(expected);
Expand Down Expand Up @@ -477,6 +477,16 @@ describe('htmlNormalizer', () => {
'<p><b>Asdasdasd</b></p><br><br><p>Sent with <a href="https://google.com">Net</a></p>'
);
});

test('<br> between blockquote paragraphs is preserved', () => {
expect(
normalizeHtml(
'<blockquote><p>this is a pretty short blockquote.</p><br><p>This is a line after an empty line.</p></blockquote>'
)
).toBe(
'<blockquote><p>this is a pretty short blockquote.</p><br><p>This is a line after an empty line.</p></blockquote>'
);
});
});

describe('character escaping', () => {
Expand Down
6 changes: 5 additions & 1 deletion src/web/normalization/htmlNormalizer.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -401,7 +401,11 @@ function flattenBqNode(
}
if (!isElement(node)) return;
if (isBrNode(node)) {
flushInlineP(ib, out);
// Emit the canonical <br> so it is not silently dropped.
// With buffered inline content it just terminates the current paragraph.
if (!flushInlineP(ib, out)) {
out.buf += '<br>';
}
return;
}
if (isBlockProducing(node) || isBlockquoteNode(node)) {
Expand Down
Loading