lib/ucs2_string: Add ucs2 -> utf8 helper functions
authorPeter Jones <pjones@redhat.com>
Mon, 8 Feb 2016 19:48:11 +0000 (14:48 -0500)
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Wed, 16 Mar 2016 15:41:36 +0000 (08:41 -0700)
commit 73500267c930baadadb0d02284909731baf151f7 upstream.

This adds ucs2_utf8size(), which tells us how big our ucs2 string is in
bytes, and ucs2_as_utf8, which translates from ucs2 to utf8..

Signed-off-by: Peter Jones <pjones@redhat.com>
Tested-by: Lee, Chun-Yi <jlee@suse.com>
Acked-by: Matthew Garrett <mjg59@coreos.com>
Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
include/linux/ucs2_string.h
lib/ucs2_string.c

index cbb20afdbc01cc4a600574446d5b19c33a0d90c1..bb679b48f408217a422d0cd427ede3e05e2e67bd 100644 (file)
@@ -11,4 +11,8 @@ unsigned long ucs2_strlen(const ucs2_char_t *s);
 unsigned long ucs2_strsize(const ucs2_char_t *data, unsigned long maxlength);
 int ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len);
 
+unsigned long ucs2_utf8size(const ucs2_char_t *src);
+unsigned long ucs2_as_utf8(u8 *dest, const ucs2_char_t *src,
+                          unsigned long maxlength);
+
 #endif /* _LINUX_UCS2_STRING_H_ */
index 6f500ef2301d893c9b2c737747fc355974ff4a19..17dd74e21ef93b2b2e97059bfa56b66c301a742c 100644 (file)
@@ -49,3 +49,65 @@ ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len)
         }
 }
 EXPORT_SYMBOL(ucs2_strncmp);
+
+unsigned long
+ucs2_utf8size(const ucs2_char_t *src)
+{
+       unsigned long i;
+       unsigned long j = 0;
+
+       for (i = 0; i < ucs2_strlen(src); i++) {
+               u16 c = src[i];
+
+               if (c > 0x800)
+                       j += 3;
+               else if (c > 0x80)
+                       j += 2;
+               else
+                       j += 1;
+       }
+
+       return j;
+}
+EXPORT_SYMBOL(ucs2_utf8size);
+
+/*
+ * copy at most maxlength bytes of whole utf8 characters to dest from the
+ * ucs2 string src.
+ *
+ * The return value is the number of characters copied, not including the
+ * final NUL character.
+ */
+unsigned long
+ucs2_as_utf8(u8 *dest, const ucs2_char_t *src, unsigned long maxlength)
+{
+       unsigned int i;
+       unsigned long j = 0;
+       unsigned long limit = ucs2_strnlen(src, maxlength);
+
+       for (i = 0; maxlength && i < limit; i++) {
+               u16 c = src[i];
+
+               if (c > 0x800) {
+                       if (maxlength < 3)
+                               break;
+                       maxlength -= 3;
+                       dest[j++] = 0xe0 | (c & 0xf000) >> 12;
+                       dest[j++] = 0x80 | (c & 0x0fc0) >> 8;
+                       dest[j++] = 0x80 | (c & 0x003f);
+               } else if (c > 0x80) {
+                       if (maxlength < 2)
+                               break;
+                       maxlength -= 2;
+                       dest[j++] = 0xc0 | (c & 0xfe0) >> 5;
+                       dest[j++] = 0x80 | (c & 0x01f);
+               } else {
+                       maxlength -= 1;
+                       dest[j++] = c & 0x7f;
+               }
+       }
+       if (maxlength)
+               dest[j] = '\0';
+       return j;
+}
+EXPORT_SYMBOL(ucs2_as_utf8);