From f1bea50e1ded9a3fbd0ffcd92975ecef26eab14c Mon Sep 17 00:00:00 2001
From: Rusty Russell <rusty@rustcorp.com.au>
Date: Wed, 25 Nov 2020 10:39:08 +1030
Subject: [PATCH] common/utils: simple utf8 helpers.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 common/utils.c | 37 +++++++++++++++++++++++++++++++++++++
 common/utils.h |  6 ++++++
 2 files changed, 43 insertions(+)

diff --git a/common/utils.c b/common/utils.c
index 4c99c7b1e..96e0b1188 100644
--- a/common/utils.c
+++ b/common/utils.c
@@ -3,6 +3,8 @@
 #include <ccan/list/list.h>
 #include <ccan/str/hex/hex.h>
 #include <ccan/tal/str/str.h>
+#include <ccan/utf8/utf8.h>
+#include <errno.h>
 #include <locale.h>
 
 const tal_t *wally_tal_ctx;
@@ -173,3 +175,38 @@ void *tal_dup_talarr_(const tal_t *ctx, const tal_t *src TAKES, const char *labe
 	}
 	return tal_dup_(ctx, src, 1, tal_bytelen(src), 0, label);
 }
+
+/* Check for valid UTF-8 */
+bool utf8_check(const void *vbuf, size_t buflen)
+{
+	const u8 *buf = vbuf;
+	struct utf8_state utf8_state = UTF8_STATE_INIT;
+	bool need_more = false;
+
+	for (size_t i = 0; i < buflen; i++) {
+		if (!utf8_decode(&utf8_state, buf[i])) {
+			need_more = true;
+			continue;
+		}
+		need_more = false;
+		if (errno != 0)
+			return false;
+	}
+	return !need_more;
+}
+
+char *utf8_str(const tal_t *ctx, const u8 *buf TAKES, size_t buflen)
+{
+	char *ret;
+
+	if (!utf8_check(buf, buflen)) {
+		if (taken(buf))
+			tal_free(buf);
+		return NULL;
+	}
+
+	/* Add one for nul term */
+	ret = tal_dup_arr(ctx, char, (const char *)buf, buflen, 1);
+	ret[buflen] = '\0';
+	return ret;
+}
diff --git a/common/utils.h b/common/utils.h
index fa63c6c88..851825e20 100644
--- a/common/utils.h
+++ b/common/utils.h
@@ -72,6 +72,12 @@ void tal_arr_remove_(void *p, size_t elemsize, size_t n);
 void *tal_dup_talarr_(const tal_t *ctx, const tal_t *src TAKES,
 		      const char *label);
 
+/* Check for valid UTF-8 */
+bool utf8_check(const void *buf, size_t buflen);
+
+/* Check it's UTF-8, return copy (or same if TAKES), or NULL if not valid. */
+char *utf8_str(const tal_t *ctx, const u8 *buf TAKES, size_t buflen);
+
 /* Use the POSIX C locale. */
 void setup_locale(void);