Changeset 21a639b7 in mainline

Timestamp:

2009-03-24T03:10:22Z (16 years ago)

Author:

Martin Decky <martin@…>

Branches:

lfn, master, serial, ticket/834-toolchain-update, topic/msim-upgrade, topic/simplify-dev-export

Children:

ac7c8d12

Parents:

c3ebc47

Message:

UTF-8 decoding routine

Location:

kernel/generic

Files:

• include/string.h (modified) (1 diff)
• src/lib/string.c (modified) (1 diff)

kernel/generic/include/string.h

@@ -36 +36 @@
 #define KERN_STRING_H_
 
-#include <arch/types.h>
+#include <typedefs.h>
 
+extern wchar_t utf8_decode(const char *str, index_t *index);
 extern size_t strlen(const char *str);
 extern int strcmp(const char *src, const char *dst);

kernel/generic/src/lib/string.c

@@ -43 +43 @@
 #include <console/kconsole.h>
 
+/** Decode a single UTF-8 character from a NULL-terminated string.
+ *
+ * Decode a single UTF-8 character from a plain char NULL-terminated
+ * string. Decoding starts at @index and this index is incremented
+ * if the current UTF-8 string is encoded in more than a single byte.
+ *
+ * @param str   Plain character NULL-terminated string.
+ * @param index Index (counted in plain characters) where to start
+ *              the decoding.
+ *
+ * @return Decoded character in UTF-32 or '?' if the encoding is wrong.
+ *
+ */
+wchar_t utf8_decode(const char *str, index_t *index)
+{
+        uint8_t c1;           /* First plain character from str */
+        uint8_t c2;           /* Second plain character from str */
+        uint8_t c3;           /* Third plain character from str */
+        uint8_t c4;           /* Fourth plain character from str */
+        
+        c1 = (uint8_t) str[*index];
+        
+        if ((c1 & 0x80) == 0) {
+                /* Plain ASCII (code points 0 .. 127) */
+                return (wchar_t) c1;
+        } else if ((c1 & 0xe0) == 0xc0) {
+                /* Code points 128 .. 2047 */
+                c2 = (uint8_t) str[*index + 1];
+                if ((c2 & 0xc0) == 0x80) {
+                        (*index)++;
+                        return ((wchar_t) ((c1 & 0x1f) << 6) | (c2 & 0x3f));
+                } else
+                        return ((wchar_t) '?');
+        } else if ((c1 & 0xf0) == 0xe0) {
+                /* Code points 2048 .. 65535 */
+                c2 = (uint8_t) str[*index + 1];
+                if ((c2 & 0xc0) == 0x80) {
+                        (*index)++;
+                        c3 = (uint8_t) str[*index + 1];
+                        if ((c3 & 0xc0) == 0x80) {
+                                (*index)++;
+                                return ((wchar_t) ((c1 & 0x0f) << 12) | ((c2 & 0x3f) << 6) | (c3 & 0x3f));
+                        } else
+                                return ((wchar_t) '?');
+                } else
+                        return ((wchar_t) '?');
+        } else if ((c1 & 0xf8) == 0xf0) {
+                /* Code points 65536 .. 1114111 */
+                c2 = (uint8_t) str[*index + 1];
+                if ((c2 & 0xc0) == 0x80) {
+                        (*index)++;
+                        c3 = (uint8_t) str[*index + 1];
+                        if ((c3 & 0xc0) == 0x80) {
+                                (*index)++;
+                                c4 = (uint8_t) str[*index + 1];
+                                if ((c4 & 0xc0) == 0x80) {
+                                        (*index)++;
+                                        return ((wchar_t) ((c1 & 0x07) << 18) | ((c2 & 0x3f) << 12) | ((c3 & 0x3f) << 6) | (c4 & 0x3f));
+                                } else
+                                        return ((wchar_t) '?');
+                        } else
+                                return ((wchar_t) '?');
+                } else
+                        return ((wchar_t) '?');
+        }
+        
+        return ((wchar_t) '?');
+}
+
 /** Return number of characters in a string.
  *