lib: add some utf16 handling helpers

We'll eventually want these in a few places in efi_loader, and also
vsprintf.

Signed-off-by: Rob Clark <robdclark@gmail.com>

1 files changed, 101 insertions, 0 deletions

diff --git a/lib/charset.c b/lib/charset.c
new file mode 100644
index 0000000000..ff76e88c77
--- /dev/null
+++ b/lib/charset.c
@@ -0,0 +1,101 @@
+/*
+ *  charset conversion utils
+ *
+ *  Copyright (c) 2017 Rob Clark
+ *
+ *  SPDX-License-Identifier:     GPL-2.0+
+ */
+
+#include <common.h>
+#include <charset.h>
+#include <malloc.h>
+
+/*
+ * utf8/utf16 conversion mostly lifted from grub
+ */
+
+size_t utf16_strlen(const uint16_t *in)
+{
+	size_t i;
+	for (i = 0; in[i]; i++);
+	return i;
+}
+
+size_t utf16_strnlen(const uint16_t *in, size_t count)
+{
+	size_t i;
+	for (i = 0; count-- && in[i]; i++);
+	return i;
+}
+
+uint16_t *utf16_strcpy(uint16_t *dest, const uint16_t *src)
+{
+	uint16_t *tmp = dest;
+
+	while ((*dest++ = *src++) != '\0')
+		/* nothing */;
+	return tmp;
+
+}
+
+uint16_t *utf16_strdup(const uint16_t *s)
+{
+	uint16_t *new;
+	if (!s || !(new = malloc((utf16_strlen(s) + 1) * 2)))
+		return NULL;
+	utf16_strcpy(new, s);
+	return new;
+}
+
+/* Convert UTF-16 to UTF-8.  */
+uint8_t *utf16_to_utf8(uint8_t *dest, const uint16_t *src, size_t size)
+{
+	uint32_t code_high = 0;
+
+	while (size--) {
+		uint32_t code = *src++;
+
+		if (code_high) {
+			if (code >= 0xDC00 && code <= 0xDFFF) {
+				/* Surrogate pair.  */
+				code = ((code_high - 0xD800) << 10) + (code - 0xDC00) + 0x10000;
+
+				*dest++ = (code >> 18) | 0xF0;
+				*dest++ = ((code >> 12) & 0x3F) | 0x80;
+				*dest++ = ((code >> 6) & 0x3F) | 0x80;
+				*dest++ = (code & 0x3F) | 0x80;
+			} else {
+				/* Error...  */
+				*dest++ = '?';
+				/* *src may be valid. Don't eat it.  */
+				src--;
+			}
+
+			code_high = 0;
+		} else {
+			if (code <= 0x007F) {
+				*dest++ = code;
+			} else if (code <= 0x07FF) {
+				*dest++ = (code >> 6) | 0xC0;
+				*dest++ = (code & 0x3F) | 0x80;
+			} else if (code >= 0xD800 && code <= 0xDBFF) {
+				code_high = code;
+				continue;
+			} else if (code >= 0xDC00 && code <= 0xDFFF) {
+				/* Error... */
+				*dest++ = '?';
+			} else if (code < 0x10000) {
+				*dest++ = (code >> 12) | 0xE0;
+				*dest++ = ((code >> 6) & 0x3F) | 0x80;
+				*dest++ = (code & 0x3F) | 0x80;
+			} else {
+				*dest++ = (code >> 18) | 0xF0;
+				*dest++ = ((code >> 12) & 0x3F) | 0x80;
+				*dest++ = ((code >> 6) & 0x3F) | 0x80;
+				*dest++ = (code & 0x3F) | 0x80;
+			}
+		}
+	}
+
+	return dest;
+}