From 52d7e4f3dbfe27952b1727fdc908a5134ea90004 Mon Sep 17 00:00:00 2001
From: Andy <webmaster@RealityRipple.com>
Date: Thu, 9 May 2024 15:44:02 -0700
Subject: [PATCH] PR #2514 - Don't split up happy emoji sequences

Loosely based on https://phabricator.services.mozilla.com/D25101
Includes changes to `GetEmojiPresentation`, added in e38b57ca.
The `EmojiComponent` response includes hair color, skin tone, ZWJ, VS16, Combining Enclosing Keycap, and the Tag unicode characters used for subdivision flag emojis.
This means that `IsClusterExtender` should support all these characters, and be forward compatible with any future Unicode changes.
This also lets us restructure `ClusterIterator::Next` to check for EmojiComponents after a TextDefault character, without any stupid constants.
---
 intl/unicharutil/util/nsUnicodeProperties.cpp | 44 ++++++++++++++++---
 1 file changed, 38 insertions(+), 6 deletions(-)

diff --git a/intl/unicharutil/util/nsUnicodeProperties.cpp b/intl/unicharutil/util/nsUnicodeProperties.cpp
index 8a2b04a8b0..b9c8b83fb2 100644
--- a/intl/unicharutil/util/nsUnicodeProperties.cpp
+++ b/intl/unicharutil/util/nsUnicodeProperties.cpp
@@ -152,7 +152,8 @@ IsClusterExtender(uint32_t aCh, uint8_t aCategory)
 {
     return ((aCategory >= HB_UNICODE_GENERAL_CATEGORY_SPACING_MARK &&
              aCategory <= HB_UNICODE_GENERAL_CATEGORY_NON_SPACING_MARK) ||
-            (aCh >= 0x200c && aCh <= 0x200d) || // ZWJ, ZWNJ
+            (GetEmojiPresentation(aCh) == EmojiComponent) ||
+            (aCh == 0x200c) || // ZWNJ
             (aCh >= 0xff9e && aCh <= 0xff9f));  // katakana sound marks
 }
 
@@ -224,8 +225,25 @@ ClusterIterator::Next()
         }
     }
 
+    const uint32_t kZWJ = 0x200d;
+    uint32_t aNextCh = 0;
+    if (mPos + 1 < mLimit) {
+        aNextCh = *mPos;
+        uint32_t aLowCh = *(mPos + 1);
+        if (NS_IS_HIGH_SURROGATE(aNextCh) && NS_IS_LOW_SURROGATE(aLowCh)) {
+            aNextCh = SURROGATE_TO_UCS4(aNextCh, aLowCh);
+        }
+    }
+
+    bool baseIsEmoji = (GetEmojiPresentation(ch) == EmojiDefault) ||
+                       (GetEmojiPresentation(ch) == EmojiComponent) ||
+                       (GetEmojiPresentation(ch) == TextDefault &&
+                        GetEmojiPresentation(aNextCh) == EmojiComponent);
+    bool prevWasZwj = false;
+
     while (mPos < mLimit) {
         ch = *mPos;
+        size_t chLen = 1;
 
         // Check for surrogate pairs; note that isolated surrogates will just
         // be treated as generic (non-cluster-extending) characters here,
@@ -233,16 +251,30 @@ ClusterIterator::Next()
         if (NS_IS_HIGH_SURROGATE(ch) && mPos < mLimit - 1 &&
             NS_IS_LOW_SURROGATE(*(mPos + 1))) {
             ch = SURROGATE_TO_UCS4(ch, *(mPos + 1));
+            chLen = 2;
         }
 
-        if (!IsClusterExtender(ch)) {
+        uint32_t aExtCh = 0;
+        if (mPos + chLen < mLimit) {
+            aExtCh = *(mPos + chLen);
+            uint32_t aLowCh = *(mPos + chLen + 1);
+            if (NS_IS_HIGH_SURROGATE(aExtCh) && NS_IS_LOW_SURROGATE(aLowCh)) {
+                aExtCh = SURROGATE_TO_UCS4(aExtCh, aLowCh);
+            }
+        }
+        bool extendCluster =
+            IsClusterExtender(ch) ||
+            (baseIsEmoji && prevWasZwj &&
+             ((GetEmojiPresentation(ch) == EmojiDefault) ||
+              (GetEmojiPresentation(ch) == EmojiComponent) ||
+              (GetEmojiPresentation(ch) == TextDefault &&
+               GetEmojiPresentation(aExtCh) == EmojiComponent)));
+        if (!extendCluster) {
             break;
         }
 
-        mPos++;
-        if (!IS_IN_BMP(ch)) {
-            mPos++;
-        }
+        prevWasZwj = (ch == kZWJ);
+        mPos += chLen;
     }
 
     NS_ASSERTION(mText < mPos && mPos <= mLimit,