ChangeSet 1.1290.15.18, 2004/03/03 10:04:33-08:00, david-b@pacbell.net

[PATCH] USB Gadget: make usb gadget strings talk utf-8

Teach gadget/usbstring to expect UTF-8 strings, not ISO-8859/1 ones.
This just gets rid of an API issue:  no hacks needed for non-Western
languages, and multi-language support will be lots easier.

Current drivers won't notice the API change, they use US-ASCII (which
is a strict superset of both encodings).

Future drivers may want to teach utf8_to_utf16le() about the four-byte
encodings, so they can emit surrogate pairs for those Unicode characters.


 drivers/usb/gadget/usbstring.c |   92 ++++++++++++++++++++++++++++++++++-------
 include/linux/usb_gadget.h     |    2 
 2 files changed, 79 insertions(+), 15 deletions(-)


diff -Nru a/drivers/usb/gadget/usbstring.c b/drivers/usb/gadget/usbstring.c
--- a/drivers/usb/gadget/usbstring.c	Wed Mar 17 15:48:29 2004
+++ b/drivers/usb/gadget/usbstring.c	Wed Mar 17 15:48:29 2004
@@ -16,24 +16,89 @@
 #include <linux/usb_ch9.h>
 #include <linux/usb_gadget.h>
 
+#include <asm/unaligned.h>
+
+
+static int utf8_to_utf16le(const char *s, u16 *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 (unlikely(c & 0x80)) {
+			// 2-byte sequence:
+			// 00000yyyyyxxxxxx = 110yyyyy 10xxxxxx
+			if ((c & 0xe0) == 0xc0) {
+				uchar = (c & 0x1f) << 6;
+
+				c = (u8) *s++;
+				if ((c & 0xc0) != 0xc0)
+					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) != 0xc0)
+					goto fail;
+				c &= 0x3f;
+				uchar |= c << 6;
+
+				c = (u8) *s++;
+				if ((c & 0xc0) != 0xc0)
+					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 (cpu_to_le16 (uchar), cp++);
+		count++;
+		len--;
+	}
+	return count;
+fail:
+	return -1;
+}
+
 
 /**
  * usb_gadget_get_string - fill out a string descriptor 
- * @table: of c strings using iso latin/1 characters
+ * @table: of c strings encoded using UTF-8
  * @id: string id, from low byte of wValue in get string descriptor
  * @buf: at least 256 bytes
  *
- * Finds the iso latin/1 string matching the ID, and converts it into a
+ * Finds the UTF-8 string matching the ID, and converts it into a
  * string descriptor in utf16-le.
  * Returns length of descriptor (always even) or negative errno
  *
- * If your driver needs stings in multiple languages, you'll need to
- * to use some alternate solution for languages where the ISO 8859/1
- * (latin/1) character set can't be used.  For example, they can't be
- * used with Chinese (Big5, GB2312, etc), Japanese, Korean, or many other
- * languages.  You'd likely "switch (wIndex) { ... }"  in your ep0
- * string descriptor logic, using this routine in cases where "western
- * european" characters suffice for the strings being returned.
+ * If your driver needs stings in multiple languages, you'll probably
+ * "switch (wIndex) { ... }"  in your ep0 string descriptor logic,
+ * using this routine after choosing which set of UTF-8 strings to use.
+ * Note that US-ASCII is a strict subset of UTF-8; any string bytes with
+ * the eighth bit set will be multibyte UTF-8 characters, not ISO-8859/1
+ * characters (which are also widely used in C strings).
  */
 int
 usb_gadget_get_string (struct usb_gadget_strings *table, int id, u8 *buf)
@@ -59,13 +124,12 @@
 
 	/* string descriptors have length, tag, then UTF16-LE text */
 	len = min ((size_t) 126, strlen (s->s));
+	memset (buf + 2, 0, 2 * len);	/* zero all the bytes */
+	len = utf8_to_utf16le(s->s, (u16 *)&buf[2], len);
+	if (len < 0)
+		return -EINVAL;
 	buf [0] = (len + 1) * 2;
 	buf [1] = USB_DT_STRING;
-	memset (buf + 2, 0, 2 * len);	/* zero all the high bytes */
-	while (len) {
-		buf [2 * len] = s->s [len - 1];
-		len--;
-	}
 	return buf [0];
 }
 
diff -Nru a/include/linux/usb_gadget.h b/include/linux/usb_gadget.h
--- a/include/linux/usb_gadget.h	Wed Mar 17 15:48:29 2004
+++ b/include/linux/usb_gadget.h	Wed Mar 17 15:48:29 2004
@@ -707,7 +707,7 @@
 /**
  * struct usb_string - wraps a C string and its USB id
  * @id:the (nonzero) ID for this string
- * @s:the string, in ISO-8859/1 characters
+ * @s:the string, in UTF-8 encoding
  *
  * If you're using usb_gadget_get_string(), use this to wrap a string
  * together with its ID.