From 73500267c930baadadb0d02284909731baf151f7 Mon Sep 17 00:00:00 2001 From: Peter Jones Date: Mon, 8 Feb 2016 14:48:11 -0500 Subject: lib/ucs2_string: Add ucs2 -> utf8 helper functions 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 Tested-by: Lee, Chun-Yi Acked-by: Matthew Garrett Signed-off-by: Matt Fleming --- lib/ucs2_string.c | 62 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 62 insertions(+) (limited to 'lib') diff --git a/lib/ucs2_string.c b/lib/ucs2_string.c index 6f500ef2301d..17dd74e21ef9 100644 --- a/lib/ucs2_string.c +++ b/lib/ucs2_string.c @@ -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); -- cgit v1.2.3 From a68075908a37850918ad96b056acc9ac4ce1bd90 Mon Sep 17 00:00:00 2001 From: Jason Andryuk Date: Fri, 12 Feb 2016 23:13:33 +0000 Subject: lib/ucs2_string: Correct ucs2 -> utf8 conversion The comparisons should be >= since 0x800 and 0x80 require an additional bit to store. For the 3 byte case, the existing shift would drop off 2 more bits than intended. For the 2 byte case, there should be 5 bits bits in byte 1, and 6 bits in byte 2. Signed-off-by: Jason Andryuk Reviewed-by: Laszlo Ersek Cc: Peter Jones Cc: Matthew Garrett Cc: "Lee, Chun-Yi" Signed-off-by: Matt Fleming --- lib/ucs2_string.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'lib') diff --git a/lib/ucs2_string.c b/lib/ucs2_string.c index 17dd74e21ef9..f0b323abb4c6 100644 --- a/lib/ucs2_string.c +++ b/lib/ucs2_string.c @@ -59,9 +59,9 @@ ucs2_utf8size(const ucs2_char_t *src) for (i = 0; i < ucs2_strlen(src); i++) { u16 c = src[i]; - if (c > 0x800) + if (c >= 0x800) j += 3; - else if (c > 0x80) + else if (c >= 0x80) j += 2; else j += 1; @@ -88,19 +88,19 @@ ucs2_as_utf8(u8 *dest, const ucs2_char_t *src, unsigned long maxlength) for (i = 0; maxlength && i < limit; i++) { u16 c = src[i]; - if (c > 0x800) { + 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 & 0x0fc0) >> 6; dest[j++] = 0x80 | (c & 0x003f); - } else if (c > 0x80) { + } else if (c >= 0x80) { if (maxlength < 2) break; maxlength -= 2; - dest[j++] = 0xc0 | (c & 0xfe0) >> 5; - dest[j++] = 0x80 | (c & 0x01f); + dest[j++] = 0xc0 | (c & 0x7c0) >> 6; + dest[j++] = 0x80 | (c & 0x03f); } else { maxlength -= 1; dest[j++] = c & 0x7f; -- cgit v1.2.3