From 051d426152373450fa72d20da72d158abf81e8ab Mon Sep 17 00:00:00 2001 From: Li Jun Date: Tue, 22 May 2018 15:29:05 +0800 Subject: MLK-18376-2 usb: gadget: move utf8_to_utf16le to header file As other users may use utf8_to_utf16le() to convert the utf8 to utf16 for usb, so move it to head file. Signed-off-by: Li Jun (cherry picked from commit 94870cb6b587243e0a68ee9a3ec43540d76152cc) (cherry picked from commit 80150d76172e4443179ddfe8f91c39126493cffa) (cherry picked from commit 2d84420646336bc8e9ffea23122ef6c28d3a4f89) --- include/linux/utf.h | 75 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 75 insertions(+) create mode 100644 include/linux/utf.h (limited to 'include/linux') diff --git a/include/linux/utf.h b/include/linux/utf.h new file mode 100644 index 0000000000..e1f7d3bd1d --- /dev/null +++ b/include/linux/utf.h @@ -0,0 +1,75 @@ +#ifndef _LINUX_UTF_H +#define _LINUX_UTF_H + +#include + +static inline int utf8_to_utf16le(const char *s, __le16 *cp, unsigned len) +{ + int count = 0; + u8 c; + u16 uchar; + + /* + * this insists on correct encodings, though not minimal ones. + * BUT it currently rejects legit 4-byte UTF-8 code points, + * which need surrogate pairs. (Unicode 3.1 can use them.) + */ + while (len != 0 && (c = (u8) *s++) != 0) { + if ((c & 0x80)) { + /* + * 2-byte sequence: + * 00000yyyyyxxxxxx = 110yyyyy 10xxxxxx + */ + if ((c & 0xe0) == 0xc0) { + uchar = (c & 0x1f) << 6; + + c = (u8) *s++; + if ((c & 0xc0) != 0x80) + goto fail; + c &= 0x3f; + uchar |= c; + + /* + * 3-byte sequence (most CJKV characters): + * zzzzyyyyyyxxxxxx = 1110zzzz 10yyyyyy 10xxxxxx + */ + } else if ((c & 0xf0) == 0xe0) { + uchar = (c & 0x0f) << 12; + + c = (u8) *s++; + if ((c & 0xc0) != 0x80) + goto fail; + c &= 0x3f; + uchar |= c << 6; + + c = (u8) *s++; + if ((c & 0xc0) != 0x80) + goto fail; + c &= 0x3f; + uchar |= c; + + /* no bogus surrogates */ + if (0xd800 <= uchar && uchar <= 0xdfff) + goto fail; + + /* + * 4-byte sequence (surrogate pairs, currently rare): + * 11101110wwwwzzzzyy + 110111yyyyxxxxxx + * = 11110uuu 10uuzzzz 10yyyyyy 10xxxxxx + * (uuuuu = wwww + 1) + * FIXME accept the surrogate code points (only) + */ + } else + goto fail; + } else + uchar = c; + put_unaligned_le16(uchar, cp++); + count++; + len--; + } + return count; +fail: + return -1; +} + +#endif /* _LINUX_UTF_H */ -- cgit v1.2.3