[PATCH V2 04/17] usb: gadget: move utf8_to_utf16le to header file

peng.fan at nxp.com peng.fan at nxp.com
Mon Jan 25 14:43:47 CET 2021


From: Li Jun <jun.li at nxp.com>

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 <jun.li at nxp.com>
Signed-off-by: Peng Fan <peng.fan at nxp.com>
---
 drivers/usb/gadget/usbstring.c | 74 +--------------------------------
 include/linux/utf.h            | 75 ++++++++++++++++++++++++++++++++++
 2 files changed, 76 insertions(+), 73 deletions(-)
 create mode 100644 include/linux/utf.h

diff --git a/drivers/usb/gadget/usbstring.c b/drivers/usb/gadget/usbstring.c
index 83cdd8a259..e2464ad923 100644
--- a/drivers/usb/gadget/usbstring.c
+++ b/drivers/usb/gadget/usbstring.c
@@ -10,79 +10,7 @@
 #include <linux/errno.h>
 #include <linux/usb/ch9.h>
 #include <linux/usb/gadget.h>
-
-#include <asm/unaligned.h>
-
-
-static 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;
-}
-
+#include <linux/utf.h>
 
 /**
  * usb_gadget_get_string - fill out a string descriptor
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 <asm/unaligned.h>
+
+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 */
-- 
2.28.0



More information about the U-Boot mailing list