Make JsonWriter::writeEscapedOUString() handle surrogate pairs properly

It is wrong to iterate over UTF-16 code units one by one. We have
OUString::iterateCodePoints() to iterate over Unicode code points.

The two UTF-16 code units of a surrogate pair (for a non-BMP code
point) should not be encoded separately to UTF-8 bytes. It is the code
point that should be encoded (to four bytes).

Change-Id: Ica4341308deb6618c9c2da8dcee8a11ef4e8238d
Reviewed-on: https://gerrit.libreoffice.org/c/core/+/109318
Tested-by: Jenkins
Reviewed-by: Noel Grandin <noel.grandin@collabora.co.uk>
Reviewed-by: Tor Lillqvist <tml@collabora.com>
Reviewed-on: https://gerrit.libreoffice.org/c/core/+/109425
Tested-by: Jenkins CollaboraOffice <jenkinscollaboraoffice@gmail.com>

1 files changed, 15 insertions, 3 deletions

diff --git a/tools/source/misc/json_writer.cxx b/tools/source/misc/json_writer.cxx
index be891ef18423..d1e1997320a1 100644
--- a/tools/source/misc/json_writer.cxx
+++ b/tools/source/misc/json_writer.cxx
@@ -134,9 +134,10 @@ void JsonWriter::put(const char* pPropName, const OUString& rPropVal)
     mPos += 4;
 
     // Convert from UTF-16 to UTF-8 and perform escaping
-    for (int i = 0; i < rPropVal.getLength(); ++i)
+    sal_Int32 i = 0;
+    while (i < rPropVal.getLength())
     {
-        sal_Unicode ch = rPropVal[i];
+        sal_uInt32 ch = rPropVal.iterateCodePoints(&i);
         if (ch == '\\')
         {
             *mPos = static_cast<char>(ch);
@@ -163,7 +164,7 @@ void JsonWriter::put(const char* pPropName, const OUString& rPropVal)
             *mPos = 0x80 | (ch & 0x3F); /* 10xxxxxx */
             ++mPos;
         }
-        else
+        else if (ch <= 0xFFFF)
         {
             *mPos = 0xE0 | (ch >> 12); /* 1110xxxx */
             ++mPos;
@@ -172,6 +173,17 @@ void JsonWriter::put(const char* pPropName, const OUString& rPropVal)
             *mPos = 0x80 | (ch & 0x3F); /* 10xxxxxx */
             ++mPos;
         }
+        else
+        {
+            *mPos = 0xF0 | (ch >> 18); /* 11110xxx */
+            ++mPos;
+            *mPos = 0x80 | ((ch >> 12) & 0x3F); /* 10xxxxxx */
+            ++mPos;
+            *mPos = 0x80 | ((ch >> 6) & 0x3F); /* 10xxxxxx */
+            ++mPos;
+            *mPos = 0x80 | (ch & 0x3F); /* 10xxxxxx */
+            ++mPos;
+        }
     }
 
     *mPos = '"';