Initial commit of sources

1 files changed, 71 insertions, 0 deletions

diff --git a/ucs.c b/ucs.c
new file mode 100644
index 0000000..cd5a9f7
--- /dev/null
+++ b/ucs.c
@@ -0,0 +1,71 @@
+/**
+ * ucs.c
+ */
+
+#include <stdio.h>
+#include <stddef.h>
+#include "ucs.h"
+
+u32 beucs2(u16 *ucs2) {
+	u16 ch;
+	u16 *ptr;
+	u32 len;
+	
+	ptr = ucs2;
+	len = 0;
+	while ((ch = be16((u8*)ptr)) != 0) {
+		*ptr = ch;
+		ptr++;
+		len++;
+	}
+	
+	return len;
+}
+
+u32 ucs2len(u16 *ucs2) {
+	u32 len = 0;
+	while (ucs2[len] != 0) {
+		len++;
+	}
+	
+	return len;
+}
+
+char firstByteMark[7] = {0x00, 0x00, 0xC0, 0xE0, 0xF0, 0xF8, 0xFC};
+
+/* Convert UCS-2 string to UTF-8 */
+void print_ucs2_as_utf8(u16 *ucs2) {
+	const u32 byteMask = 0xBF;
+	const u32 byteMark = 0x80;
+	u32 blen = 0;
+	u32 i = 0;
+	u16 *ptr_ucs;
+	u16 ch;
+	char utf8[8]= {0,0,0,0,0,0,0,0};
+
+	ptr_ucs = ucs2;
+	while (*ptr_ucs != 0) {
+		ch = *ptr_ucs;
+
+		if (ch < 0x80) {
+			blen = 1;
+		} else if (ch < 0x800) {
+			blen = 2;
+		} else {
+			blen = 3;
+		}
+		
+		i = blen;
+		utf8[i--] = 0;
+		switch (blen) {
+			case 3: utf8[i--] = ((ch | byteMark) & byteMask); ch >>= 6;
+			case 2: utf8[i--] = ((ch | byteMark) & byteMask); ch >>= 6;
+			case 1: utf8[i--] = (ch | firstByteMark[blen]);
+		}
+
+		fwrite(utf8, blen, 1, stdout);
+
+		ptr_ucs++;
+	}
+}
+