From 178aa5a5c827de59d42c8316d7a8f1c295eb829f Mon Sep 17 00:00:00 2001
From: Makoto Kato <m_kato@ga2.so-net.ne.jp>
Date: Mon, 7 Aug 2023 06:23:59 +0000
Subject: [PATCH] Bug 1719535 - Part 9. Trim ASCII space at the tail for
 content serializer. r=TYLin

XML/Plain text Serializer uses line break segmenter to wrap text. New
segmenter that is compatible with UAX#14 has different rules for old segmenter.

Old segmenter have break opportunity before ASCII space, but UAX#14 doesn't
have it (https://www.unicode.org/reports/tr14/#LB7).

So we have to trim ASCII space at the tail for text wrap.

Depends on D167677

Differential Revision: https://phabricator.services.mozilla.com/D180773
---
 dom/serializers/nsPlainTextSerializer.cpp  | 14 +++++++++++++-
 dom/serializers/nsXMLContentSerializer.cpp | 13 +++++++++++++
 2 files changed, 26 insertions(+), 1 deletion(-)

diff --git a/dom/serializers/nsPlainTextSerializer.cpp b/dom/serializers/nsPlainTextSerializer.cpp
index f64dd902bd5f..3cc7489062cb 100644
--- a/dom/serializers/nsPlainTextSerializer.cpp
+++ b/dom/serializers/nsPlainTextSerializer.cpp
@@ -131,7 +131,19 @@ int32_t nsPlainTextSerializer::CurrentLine::FindWrapIndexForContent(
     // mContent until we find a width less than or equal to wrap column.
     uint32_t width = 0;
     intl::LineBreakIteratorUtf16 lineBreakIter(mContent);
-    while (const Maybe<uint32_t> nextGoodSpace = lineBreakIter.Next()) {
+    while (Maybe<uint32_t> nextGoodSpace = lineBreakIter.Next()) {
+      // Trim space at the tail. UAX#14 doesn't have break opportunity for
+      // ASCII space at the tail.
+      const Maybe<uint32_t> originalNextGoodSpace = nextGoodSpace;
+      while (*nextGoodSpace > 0 &&
+             mContent.CharAt(*nextGoodSpace - 1) == 0x20) {
+        nextGoodSpace = Some(*nextGoodSpace - 1);
+      }
+      if (*nextGoodSpace == 0) {
+        // Restore the original nextGoodSpace.
+        nextGoodSpace = originalNextGoodSpace;
+      }
+
       width += GetUnicharStringWidth(Span<const char16_t>(
           mContent.get() + goodSpace, *nextGoodSpace - goodSpace));
       if (prefixwidth + width > aWrapColumn) {
diff --git a/dom/serializers/nsXMLContentSerializer.cpp b/dom/serializers/nsXMLContentSerializer.cpp
index 08cf7fda56a3..ab0fcdf4135b 100644
--- a/dom/serializers/nsXMLContentSerializer.cpp
+++ b/dom/serializers/nsXMLContentSerializer.cpp
@@ -1560,6 +1560,19 @@ bool nsXMLContentSerializer::AppendWrapped_NonWhitespaceSequence(
             MOZ_ASSERT(nextWrapPosition.isSome(),
                        "We should've exited the loop when reaching the end of "
                        "text in the previous iteration!");
+
+            // Trim space at the tail. UAX#14 doesn't have break opportunity
+            // for ASCII space at the tail.
+            const Maybe<uint32_t> originalNextWrapPosition = nextWrapPosition;
+            while (*nextWrapPosition > 0 &&
+                   subSeq.at(*nextWrapPosition - 1) == 0x20) {
+              nextWrapPosition = Some(*nextWrapPosition - 1);
+            }
+            if (*nextWrapPosition == 0) {
+              // Restore the original nextWrapPosition.
+              nextWrapPosition = originalNextWrapPosition;
+            }
+
             if (aSequenceStart + *nextWrapPosition > aPos) {
               break;
             }