2 * Copyright (C) 2003 David Brownell
4 * This program is free software; you can redistribute it and/or modify
5 * it under the terms of the GNU Lesser General Public License as published
6 * by the Free Software Foundation; either version 2.1 of the License, or
7 * (at your option) any later version.
9 * Ported to U-boot by: Thomas Smits <ts.smits@gmail.com> and
10 * Remy Bohmer <linux@bohmer.net>
14 #include <asm/errno.h>
15 #include <linux/usb/ch9.h>
16 #include <usbdescriptors.h>
17 #include <linux/usb/gadget.h>
19 #include <asm/unaligned.h>
22 static int utf8_to_utf16le(const char *s, __le16 *cp, unsigned len)
29 * this insists on correct encodings, though not minimal ones.
30 * BUT it currently rejects legit 4-byte UTF-8 code points,
31 * which need surrogate pairs. (Unicode 3.1 can use them.)
33 while (len != 0 && (c = (u8) *s++) != 0) {
37 * 00000yyyyyxxxxxx = 110yyyyy 10xxxxxx
39 if ((c & 0xe0) == 0xc0) {
40 uchar = (c & 0x1f) << 6;
43 if ((c & 0xc0) != 0x80)
49 * 3-byte sequence (most CJKV characters):
50 * zzzzyyyyyyxxxxxx = 1110zzzz 10yyyyyy 10xxxxxx
52 } else if ((c & 0xf0) == 0xe0) {
53 uchar = (c & 0x0f) << 12;
56 if ((c & 0xc0) != 0x80)
62 if ((c & 0xc0) != 0x80)
67 /* no bogus surrogates */
68 if (0xd800 <= uchar && uchar <= 0xdfff)
72 * 4-byte sequence (surrogate pairs, currently rare):
73 * 11101110wwwwzzzzyy + 110111yyyyxxxxxx
74 * = 11110uuu 10uuzzzz 10yyyyyy 10xxxxxx
76 * FIXME accept the surrogate code points (only)
82 put_unaligned_le16(uchar, cp++);
93 * usb_gadget_get_string - fill out a string descriptor
94 * @table: of c strings encoded using UTF-8
95 * @id: string id, from low byte of wValue in get string descriptor
96 * @buf: at least 256 bytes
98 * Finds the UTF-8 string matching the ID, and converts it into a
99 * string descriptor in utf16-le.
100 * Returns length of descriptor (always even) or negative errno
102 * If your driver needs stings in multiple languages, you'll probably
103 * "switch (wIndex) { ... }" in your ep0 string descriptor logic,
104 * using this routine after choosing which set of UTF-8 strings to use.
105 * Note that US-ASCII is a strict subset of UTF-8; any string bytes with
106 * the eighth bit set will be multibyte UTF-8 characters, not ISO-8859/1
107 * characters (which are also widely used in C strings).
110 usb_gadget_get_string(struct usb_gadget_strings *table, int id, u8 *buf)
112 struct usb_string *s;
115 /* descriptor 0 has the language id */
118 buf[1] = USB_DT_STRING;
119 buf[2] = (u8) table->language;
120 buf[3] = (u8) (table->language >> 8);
123 for (s = table->strings; s && s->s; s++)
127 /* unrecognized: stall. */
131 /* string descriptors have length, tag, then UTF16-LE text */
132 len = min((size_t) 126, strlen(s->s));
133 memset(buf + 2, 0, 2 * len); /* zero all the bytes */
134 len = utf8_to_utf16le(s->s, (__le16 *)&buf[2], len);
137 buf[0] = (len + 1) * 2;
138 buf[1] = USB_DT_STRING;