From 511eea450ab2552e9744fe378cee81383cdb5aa7 Mon Sep 17 00:00:00 2001
From: Simon Tatham <anakin@pobox.com>
Date: Tue, 5 Mar 2019 07:24:17 +0000
Subject: [PATCH] Factor out encode_utf8 from luni_send into utils.c.

I knew there had to already be a UTF-8 encoder _somewhere_ in this
code base, but it took me a while to find it! Now it's reusable in
other contexts.
---
 ldiscucs.c | 16 +---------------
 misc.h     |  5 +++++
 utils.c    | 22 ++++++++++++++++++++++
 3 files changed, 28 insertions(+), 15 deletions(-)

diff --git a/ldiscucs.c b/ldiscucs.c
index 774368f3..d7a0e269 100644
--- a/ldiscucs.c
+++ b/ldiscucs.c
@@ -65,21 +65,7 @@ void luni_send(Ldisc *ldisc, const wchar_t *widebuf, int len, bool interactive)
 		}
 	    }
 
-	    if (ch < 0x80) {
-		*p++ = (char) (ch);
-	    } else if (ch < 0x800) {
-		*p++ = (char) (0xC0 | (ch >> 6));
-		*p++ = (char) (0x80 | (ch & 0x3F));
-	    } else if (ch < 0x10000) {
-		*p++ = (char) (0xE0 | (ch >> 12));
-		*p++ = (char) (0x80 | ((ch >> 6) & 0x3F));
-		*p++ = (char) (0x80 | (ch & 0x3F));
-	    } else {
-		*p++ = (char) (0xF0 | (ch >> 18));
-		*p++ = (char) (0x80 | ((ch >> 12) & 0x3F));
-		*p++ = (char) (0x80 | ((ch >> 6) & 0x3F));
-		*p++ = (char) (0x80 | (ch & 0x3F));
-	    }
+            p += encode_utf8(p, ch);
 	}
     } else {
 	int rv;
diff --git a/misc.h b/misc.h
index f97f6730..d301e2ca 100644
--- a/misc.h
+++ b/misc.h
@@ -199,6 +199,11 @@ void smemclr(void *b, size_t len);
  * hinted at by the 'eq' in the name. */
 bool smemeq(const void *av, const void *bv, size_t len);
 
+/* Encode a single UTF-8 character. Assumes that illegal characters
+ * (such as things in the surrogate range, or > 0x10FFFF) have already
+ * been removed. */
+size_t encode_utf8(void *output, unsigned long ch);
+
 char *buildinfo(const char *newline);
 
 /*
diff --git a/utils.c b/utils.c
index f87596eb..9264c6e6 100644
--- a/utils.c
+++ b/utils.c
@@ -958,3 +958,25 @@ bool strendswith(const char *s, const char *t)
     size_t slen = strlen(s), tlen = strlen(t);
     return slen >= tlen && !strcmp(s + (slen - tlen), t);
 }
+
+size_t encode_utf8(void *output, unsigned long ch)
+{
+    unsigned char *start = (unsigned char *)output, *p = start;
+
+    if (ch < 0x80) {
+        *p++ = ch;
+    } else if (ch < 0x800) {
+        *p++ = 0xC0 | (ch >> 6);
+        *p++ = 0x80 | (ch & 0x3F);
+    } 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);
+    }
+    return p - start;
+}