summaryrefslogtreecommitdiff
path: root/include/linux/utf.h
diff options
context:
space:
mode:
authorTom Rini <trini@konsulko.com>2021-01-31 14:24:35 -0500
committerTom Rini <trini@konsulko.com>2021-01-31 14:24:35 -0500
commitb4804cdd5747d1d932bd338e0ca102ade51b8b6b (patch)
treedd3aa210c95de630ee7e62a58e7924e73ee0458a /include/linux/utf.h
parentfad42d3afbeb23e86fae2bb56ba863a2a5a133e1 (diff)
parent723fd5668ff2c8dd19e808778b5670d0fa6bdc4b (diff)
Merge https://gitlab.denx.de/u-boot/custodians/u-boot-usb
- Assorted gadget changes including: - dfu: Fix handling of UBI partitions in MTD backend - gadget: f_thor: fix wrong file size cast - Extend cmd: bcb - Fixes for fastboot and rockchip gadgets - dfu: Add SCRIPT and SKIP entities - dfu/thor: Add `dfu_alt_info` reinitialization from flashed script - u-boot: Reduce size of u-boot as usbd_device_* arrays are not exported
Diffstat (limited to 'include/linux/utf.h')
-rw-r--r--include/linux/utf.h75
1 files changed, 75 insertions, 0 deletions
diff --git a/include/linux/utf.h b/include/linux/utf.h
new file mode 100644
index 00000000000..e1f7d3bd1d6
--- /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 */