From baeefc095809d87b3d2a45007c3e78e4da74f770 Mon Sep 17 00:00:00 2001
From: Jehan <jehan@girinstud.io>
Date: Tue, 13 Dec 2022 23:28:40 +0100
Subject: [PATCH] src: process pending language data when we are going to pass
 buffer size.

We were experiencing segmentation fault when processing long texts
because we were ending up trying to access out-of-range data (from
codePointBuffer). Verify when this will happen and process data to reset
the index before adding more code points.
---
 src/nsMBCSGroupProber.cpp | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/src/nsMBCSGroupProber.cpp b/src/nsMBCSGroupProber.cpp
index 8388832..8318cbd 100644
--- a/src/nsMBCSGroupProber.cpp
+++ b/src/nsMBCSGroupProber.cpp
@@ -327,8 +327,19 @@ nsProbingState nsMBCSGroupProber::HandleData(const char* aBuf, PRUint32 aLen,
     else
     {
       for (PRUint32 i = 0; i < NUM_OF_PROBERS; i++)
+      {
         if (codePointBuffer[i])
+        {
+          if (codePointBufferIdx[i] == codePointBufferSize[i] - 1)
+          {
+            for (PRUint32 j = 0; j < NUM_OF_LANGUAGES; j++)
+              langDetectors[i][j]->HandleData(codePointBuffer[i], codePointBufferIdx[i]);
+            codePointBufferIdx[i] = 0;
+          }
+
           codePointBuffer[i][(codePointBufferIdx[i])++] = aBuf[pos];
+        }
+      }
     }
   }