From 6d20ed0590618b387d4cf6170b1339bf164ce9e3 Mon Sep 17 00:00:00 2001
From: albert-github <albert.tests@gmail.com>
Date: Sat, 11 May 2019 14:01:49 +0200
Subject: Special handling of the UTF8 nbsp sequence

The UTF8 nbsp sequence 0xc2 0xa0 is not seen as a whitespace sequence and not handled properly.
This can lead to:
```
warning: found </c> tag without matching <c>
```
when we have e.g. ```e.g. `linux`<br>``` where the space between the `.` and the backtick is actually the UTF8 nbsp sequence
Replacing the the UTF8 nbsp sequence with the `&nbsp;` sequence.
---
 src/markdown.cpp | 25 +++++++++++++++++++------
 1 file changed, 19 insertions(+), 6 deletions(-)

diff --git a/src/markdown.cpp b/src/markdown.cpp
index 6b5a894..df1ffe7 100644
--- a/src/markdown.cpp
+++ b/src/markdown.cpp
@@ -2453,19 +2453,32 @@ static QCString detab(const QCString &s,int &refIndent)
         col++;
         break;
       default: // non-whitespace => update minIndent
-        out.addChar(c);
         if (c<0 && i<size) // multibyte sequence
         {
-          out.addChar(data[i++]); // >= 2 bytes
-          if (((uchar)c&0xE0)==0xE0 && i<size)
+          // special handling of the UTF-8 nbsp character 0xc2 0xa0
+          if (c == '\xc2' && data[i] == '\xa0')
           {
-            out.addChar(data[i++]); // 3 bytes
+            out.addStr("&nbsp;");
+            i++;
           }
-          if (((uchar)c&0xF0)==0xF0 && i<size)
+          else
           {
-            out.addChar(data[i++]); // 4 byres
+            out.addChar(c);
+            out.addChar(data[i++]); // >= 2 bytes
+            if (((uchar)c&0xE0)==0xE0 && i<size)
+            {
+              out.addChar(data[i++]); // 3 bytes
+            }
+              if (((uchar)c&0xF0)==0xF0 && i<size)
+            {
+              out.addChar(data[i++]); // 4 byres
+            }
           }
         }
+        else
+        {
+          out.addChar(c);
+        }
         if (col<minIndent) minIndent=col;
         col++;
     }
-- 
cgit v0.12