software-mansion · kacperzolkiewski · Jul 17, 2026 · Jul 16, 2026 · Jul 16, 2026 · Jul 16, 2026
diff --git a/cpp/parser/GumboNormalizer.c b/cpp/parser/GumboNormalizer.c
@@ -548,17 +548,34 @@ static void walk_node(GumboNode *node, buffer_t *out);
 
 static void flatten_bq_node(GumboNode *node, buffer_t *ib, buffer_t *out);
 
-static void flush_inline_p(buffer_t *ib, buffer_t *out,
+/** True if buf is empty or contains only ASCII whitespace. */
+static bool is_whitespace_only(const char *data, size_t len) {
+  for (size_t i = 0; i < len; i++) {
+    unsigned char c = (unsigned char)data[i];
+    if (c != ' ' && c != '\t' && c != '\n' && c != '\r' && c != '\f')
+      return false;
+  }
+  return true;
+}
+
+/**
+ * Flush buffered inline content as a <p>. Inter-block whitespace (newlines /
+ * spaces between block tags in pretty-printed HTML) is discarded so it does
+ * not become empty paragraphs that later serialize as extra <br>s.
+ */
+static bool flush_inline_p(buffer_t *ib, buffer_t *out,
                            GumboElement *align_el) {
-  if (ib->len > 0) {
+  bool emitted = ib->len > 0 && !is_whitespace_only(ib->data, ib->len);
+  if (emitted) {
     buffer_append_str(out, "<p");
     if (align_el)
       emit_alignment(align_el, "p", out);
     buffer_append_str(out, ">");
     buffer_append(out, ib->data, ib->len);
     buffer_append_str(out, "</p>");
-    buffer_clear(ib);
   }
+  buffer_clear(ib);
+  return emitted;
 }
 
 static void flatten_bq_children(GumboNode *node, buffer_t *ib, buffer_t *out) {
@@ -730,9 +747,8 @@ static void walk_children(GumboNode *node, buffer_t *out) {
              !is_blockquote_node(children->data[i])) {
         child = children->data[i];
         if (is_br_node(child)) {
-          if (ib.len > 0)
-            flush_inline_p(&ib, out, NULL);
-          else
+          /* Whitespace-only buffer is layout noise; treat like empty → <br> */
+          if (!flush_inline_p(&ib, out, NULL))
             buffer_append_str(out, "<br>");
           i++;
           continue;

diff --git a/cpp/tests/GumboParserTest.cpp b/cpp/tests/GumboParserTest.cpp
@@ -571,3 +571,30 @@ TEST(GumboParserTest, TextAlignment) {
             "<p style=\"text-align: center\">c</p>"
             "<p style=\"text-align: right\">r</p></blockquote>");
 }
+
+TEST(GumboParserTest, InterBlockWhitespace) {
+  // Pretty-printed consecutive paragraphs must not gain empty <p>s from the
+  // newlines between them (those would later serialize as extra <br>s).
+  EXPECT_EQ(GumboParser::normalizeHtml(
+                "<p>Asdasd</p>\n<p>Asdasd</p>\n<p>Asdasda</p>"),
+            "<p>Asdasd</p><p>Asdasd</p><p>Asdasda</p>");
+  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("<p>Asdasd</p> <p>Asdasd</p>"),
+            "<p>Asdasd</p><p>Asdasd</p>");
+
+  // Significant inline content between blocks is still wrapped in <p>.
+  EXPECT_EQ(GumboParser::normalizeHtml("<p>a</p> hello <p>b</p>"),
+            "<p>a</p><p> hello </p><p>b</p>");
+
+  // Spaces inside text / between inlines must be preserved.
+  EXPECT_EQ(GumboParser::normalizeHtml("hello world"), "hello world");
+  EXPECT_EQ(GumboParser::normalizeHtml("<p>hello world</p>"),
+            "<p>hello world</p>");
+  EXPECT_EQ(GumboParser::normalizeHtml("<b>hello</b> <i>world</i>"),
+            "<b>hello</b> <i>world</i>");
+}
diff --git a/src/web/__tests__/htmlNormalizer.test.ts b/src/web/__tests__/htmlNormalizer.test.ts
@@ -575,4 +575,32 @@ describe('htmlNormalizer', () => {
       expect(normalizeHtml(input)).toBe(expected);
     });
   });
+
+  describe('InterBlockWhitespace', () => {
+    // Pretty-printed consecutive paragraphs must not gain empty <p>s from the
+    // newlines between them (those would later serialize as extra <br>s).
+    test.each([
+      [
+        '<p>Asdasd</p>\n<p>Asdasd</p>\n<p>Asdasda</p>',
+        '<p>Asdasd</p><p>Asdasd</p><p>Asdasda</p>',
+      ],
+      [
+        '<p>Asdasd</p>\n\n<p>Asdasd</p>\n\n<p>Asdasda</p>',
+        '<p>Asdasd</p><p>Asdasd</p><p>Asdasda</p>',
+      ],
+      [
+        '<html>\n<p>Asdasd</p>\n<p>Asdasd</p>\n<p>Asdasda</p>\n</html>',
+        '<p>Asdasd</p><p>Asdasd</p><p>Asdasda</p>',
+      ],
+      ['<p>Asdasd</p> <p>Asdasd</p>', '<p>Asdasd</p><p>Asdasd</p>'],
+      // Significant inline content between blocks is still wrapped in <p>.
+      ['<p>a</p> hello <p>b</p>', '<p>a</p><p> hello </p><p>b</p>'],
+      // Spaces inside text / between inlines must be preserved.
+      ['hello world', 'hello world'],
+      ['<p>hello world</p>', '<p>hello world</p>'],
+      ['<b>hello</b> <i>world</i>', '<b>hello</b> <i>world</i>'],
+    ])('%s → %s', (input, expected) => {
+      expect(normalizeHtml(input)).toBe(expected);
+    });
+  });
 });
diff --git a/src/web/normalization/htmlNormalizer.ts b/src/web/normalization/htmlNormalizer.ts
@@ -350,15 +350,33 @@ function escapeText(s: string): string {
 
 // --- Blockquote content flattening ---
 
+function isWhitespaceOnly(value: string): boolean {
+  for (let i = 0; i < value.length; i++) {
+    const c = value.charCodeAt(i);
+    // space, tab, LF, CR, FF
+    if (c !== 0x20 && c !== 0x09 && c !== 0x0a && c !== 0x0d && c !== 0x0c) {
+      return false;
+    }
+  }
+  return true;
+}
+
+/**
+ * Flush buffered inline content as a <p>. Inter-block whitespace (newlines /
+ * spaces between block tags in pretty-printed HTML) is discarded so it does
+ * not become empty paragraphs that later serialize as extra <br>s.
+ */
 function flushInlineP(
   ib: { buf: string },
   out: { buf: string },
   attrs = ''
-): void {
-  if (ib.buf.length > 0) {
+): boolean {
+  const emitted = ib.buf.length > 0 && !isWhitespaceOnly(ib.buf);
+  if (emitted) {
     out.buf += `<p${attrs}>${ib.buf}</p>`;
-    ib.buf = '';
   }
+  ib.buf = '';
+  return emitted;
 }
 
 function flattenBqChildren(
@@ -525,9 +543,8 @@ function walkChildren(node: Element, out: { buf: string }): void {
           break;
         }
         if (isElement(cur) && isBrNode(cur)) {
-          if (ib.buf.length > 0) {
-            flushInlineP(ib, out);
-          } else {
+          // Whitespace-only buffer is layout noise; treat like empty → <br>
+          if (!flushInlineP(ib, out)) {
             out.buf += '<br>';
           }
           i++;