From 61ef0c16fb901a7c8992e8f46318c609146c0fbc Mon Sep 17 00:00:00 2001
From: simon <simon@cda61777-01e9-0310-a592-d414129be87e>
Date: Tue, 24 Mar 2009 22:24:31 +0000
Subject: [PATCH] Support in the cross-platform code for translating to and
 from UTF-16 when exchanging wchar_t strings with the front end. Enabled by a
 #define in the platform's header file (one should not promiscuously translate
 UTF-16 surrogate pairs on 32-bit wchar_t platforms since that could give rise
 to redundant encoding attacks), which is present on Windows.

git-svn-id: svn://svn.tartarus.org/sgt/putty@8495 cda61777-01e9-0310-a592-d414129be87e
---
 ldiscucs.c         | 28 ++++++++++++++++++++++++----
 terminal.c         | 13 +++++++++++--
 windows/winstuff.h |  3 +++
 3 files changed, 38 insertions(+), 6 deletions(-)

diff --git a/ldiscucs.c b/ldiscucs.c
index 4ac28d7e..a9e1e133 100644
--- a/ldiscucs.c
+++ b/ldiscucs.c
@@ -49,19 +49,39 @@ void luni_send(void *handle, wchar_t * widebuf, int len, int interactive)
     if (in_utf(ldisc->term)) {
 	/* UTF is a simple algorithm */
 	for (p = linebuffer, i = 0; i < len; i++) {
-	    wchar_t ch = widebuf[i];
-	    /* We only deal with 16-bit wide chars */
-	    if ((ch&0xF800) == 0xD800) ch = '.';
+	    unsigned long ch = widebuf[i];
+
+	    if ((ch & 0xF800) == 0xD800) {
+#ifdef PLATFORM_IS_UTF16
+		if (i+1 < len) {
+		    unsigned long ch2 = widebuf[i+1];
+		    if ((ch & 0xFC00) == 0xD800 &&
+			(ch2 & 0xFC00) == 0xDC00) {
+			ch = 0x10000 + ((ch & 0x3FF) << 10) + (ch2 & 0x3FF);
+			i++;
+		    }
+		} else
+#endif
+		{
+		    /* Unrecognised UTF-16 sequence */
+		    ch = '.';
+		}
+	    }
 
 	    if (ch < 0x80) {
 		*p++ = (char) (ch);
 	    } else if (ch < 0x800) {
 		*p++ = (0xC0 | (ch >> 6));
 		*p++ = (0x80 | (ch & 0x3F));
-	    } else {
+	    } else if (ch < 0x10000) {
 		*p++ = (0xE0 | (ch >> 12));
 		*p++ = (0x80 | ((ch >> 6) & 0x3F));
 		*p++ = (0x80 | (ch & 0x3F));
+	    } else {
+		*p++ = (0xF0 | (ch >> 18));
+		*p++ = (0x80 | ((ch >> 12) & 0x3F));
+		*p++ = (0x80 | ((ch >> 6) & 0x3F));
+		*p++ = (0x80 | (ch & 0x3F));
 	    }
 	}
     } else {
diff --git a/terminal.c b/terminal.c
index 4f0d8225..996a01fb 100644
--- a/terminal.c
+++ b/terminal.c
@@ -5262,8 +5262,17 @@ static void clipme(Terminal *term, pos top, pos bottom, int rect, int desel)
 
 		set = (uc & CSET_MASK);
 		c = (uc & ~CSET_MASK);
-		cbuf[0] = uc;
-		cbuf[1] = 0;
+#ifdef PLATFORM_IS_UTF16
+		if (uc > 0x10000 && uc < 0x110000) {
+		    cbuf[0] = 0xD800 | ((uc - 0x10000) >> 10);
+		    cbuf[1] = 0xDC00 | ((uc - 0x10000) & 0x3FF);
+		    cbuf[2] = 0;
+		} else
+#endif
+		{
+		    cbuf[0] = uc;
+		    cbuf[1] = 0;
+		}
 
 		if (DIRECT_FONT(uc)) {
 		    if (c >= ' ' && c != 0x7F) {
diff --git a/windows/winstuff.h b/windows/winstuff.h
index 6308ea68..64f3232d 100644
--- a/windows/winstuff.h
+++ b/windows/winstuff.h
@@ -36,6 +36,9 @@ struct FontSpec {
     (fq) == FQ_NONANTIALIASED ? NONANTIALIASED_QUALITY : \
     CLEARTYPE_QUALITY)
 
+#define PLATFORM_IS_UTF16 /* enable UTF-16 processing when exchanging
+			   * wchar_t strings with environment */
+
 /*
  * Where we can, we use GetWindowLongPtr and friends because they're
  * more useful on 64-bit platforms, but they're a relatively recent
-- 
2.11.0