[PATCH] Allow inserting non-BMP characters

[Philipp Stephani <p.stephani2@gmail.com>]

* src/character.h (char_low_surrogate_p, char_high_surrogate_p)
(surrogates_to_codepoint): New functions.

* src/nsterm.m (insertText:): Properly handle surrogate pairs.
---
 src/character.h | 26 ++++++++++++++++++++++++++
 src/nsterm.m    | 27 ++++++++++++++++++++-------
 2 files changed, 46 insertions(+), 7 deletions(-)

diff --git a/src/character.h b/src/character.h
index c716885d46..8fa79c6bd9 100644
--- a/src/character.h
+++ b/src/character.h
@@ -614,6 +614,32 @@ char_surrogate_p (int c)
   return 0xD800 <= c && c <= 0xDFFF;
 }
 
+/* Return true if C is a low surrogate.  */
+
+INLINE bool
+char_low_surrogate_p (int c)
+{
+  return 0xDC00 <= c && c <= 0xDFFF;
+}
+
+/* Return true if C is a high surrogate.  */
+
+INLINE bool
+char_high_surrogate_p (int c)
+{
+  return 0xD800 <= c && c <= 0xDBFF;
+}
+
+/* Return the Unicode code point for the given UTF-16 surrogates.  */
+
+INLINE int
+surrogates_to_codepoint (int low, int high)
+{
+  eassert (char_low_surrogate_p (low));
+  eassert (char_high_surrogate_p (high));
+  return 0x10000 + (low - 0xDC00) + ((high - 0xD800) * 0x400);
+}
+
 /* Data type for Unicode general category.
 
    The order of members must be in sync with the 8th element of the
diff --git a/src/nsterm.m b/src/nsterm.m
index 07ac8f978f..da8d4dce6b 100644
--- a/src/nsterm.m
+++ b/src/nsterm.m
@@ -6283,14 +6283,13 @@ flag set (this is probably a bug in the OS).
          by doCommandBySelector: deleteBackward: */
 - (void)insertText: (id)aString
 {
-  int code;
-  int len = [(NSString *)aString length];
-  int i;
+  NSString *s = aString;
+  NSUInteger len = [s length];
 
   NSTRACE ("[EmacsView insertText:]");
 
   if (NS_KEYLOG)
-    NSLog (@"insertText '%@'\tlen = %d", aString, len);
+    NSLog (@"insertText '%@'\tlen = %lu", aString, (unsigned long) len);
   processingCompose = NO;
 
   if (!emacs_event)
@@ -6301,9 +6300,22 @@ - (void)insertText: (id)aString
     [self deleteWorkingText];
 
   /* now insert the string as keystrokes */
-  for (i =0; i<len; i++)
-    {
-      code = [aString characterAtIndex: i];
+  USE_SAFE_ALLOCA;
+  unichar *utf16_buffer;
+  SAFE_NALLOCA (utf16_buffer, 1, len);
+  [s getCharacters:utf16_buffer range:NSMakeRange (0, len)];
+  for (NSUInteger i = 0; i < len; i++)
+    {
+      NSUInteger code = utf16_buffer[i];
+      if (char_high_surrogate_p (code) && i < len - 1)
+        {
+          unichar low = utf16_buffer[i + 1];
+          if (char_low_surrogate_p (low))
+            {
+              code = surrogates_to_codepoint (low, code);
+              ++i;
+            }
+        }
       /* TODO: still need this? */
       if (code == 0x2DC)
         code = '~'; /* 0x7E */
@@ -6314,6 +6326,7 @@ - (void)insertText: (id)aString
       emacs_event->code = code;
       EV_TRAILER ((id)nil);
     }
+  SAFE_FREE ();
 }
 
 
-- 
2.15.1