linux-kernel - [PATCH 1/5] lib/ucs2_string: Add ucs2 -> utf8 helper functions

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <1455276432-9931-2-git-send-email-matt@codeblueprint.co.uk>
Date:	Fri, 12 Feb 2016 11:27:08 +0000
From:	Matt Fleming <matt@...eblueprint.co.uk>
To:	Ingo Molnar <mingo@...nel.org>,
	Thomas Gleixner <tglx@...utronix.de>,
	"H . Peter Anvin" <hpa@...or.com>
Cc:	Ard Biesheuvel <ard.biesheuvel@...aro.org>,
	Peter Jones <pjones@...hat.com>, linux-kernel@...r.kernel.org,
	linux-efi@...r.kernel.org, Matt Fleming <matt@...eblueprint.co.uk>,
	"Lee, Chun-Yi" <jlee@...e.com>, Matthew Garrett <mjg59@...eos.com>
Subject: [PATCH 1/5] lib/ucs2_string: Add ucs2 -> utf8 helper functions

From: Peter Jones <pjones@...hat.com>

This adds ucs2_utf8size(), which tells us how big our ucs2 string is in
bytes, and ucs2_as_utf8, which translates from ucs2 to utf8..

Signed-off-by: Peter Jones <pjones@...hat.com>
Tested-by: "Lee, Chun-Yi" <jlee@...e.com>
Acked-by: Matthew Garrett <mjg59@...eos.com>
Signed-off-by: Matt Fleming <matt@...eblueprint.co.uk>
---
 include/linux/ucs2_string.h |  4 +++
 lib/ucs2_string.c           | 62 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 66 insertions(+)

diff --git a/include/linux/ucs2_string.h b/include/linux/ucs2_string.h
index cbb20afdbc01..bb679b48f408 100644
--- a/include/linux/ucs2_string.h
+++ b/include/linux/ucs2_string.h
@@ -11,4 +11,8 @@ unsigned long ucs2_strlen(const ucs2_char_t *s);
 unsigned long ucs2_strsize(const ucs2_char_t *data, unsigned long maxlength);
 int ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len);
 
+unsigned long ucs2_utf8size(const ucs2_char_t *src);
+unsigned long ucs2_as_utf8(u8 *dest, const ucs2_char_t *src,
+			   unsigned long maxlength);
+
 #endif /* _LINUX_UCS2_STRING_H_ */
diff --git a/lib/ucs2_string.c b/lib/ucs2_string.c
index 6f500ef2301d..17dd74e21ef9 100644
--- a/lib/ucs2_string.c
+++ b/lib/ucs2_string.c
@@ -49,3 +49,65 @@ ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len)
         }
 }
 EXPORT_SYMBOL(ucs2_strncmp);
+
+unsigned long
+ucs2_utf8size(const ucs2_char_t *src)
+{
+	unsigned long i;
+	unsigned long j = 0;
+
+	for (i = 0; i < ucs2_strlen(src); i++) {
+		u16 c = src[i];
+
+		if (c > 0x800)
+			j += 3;
+		else if (c > 0x80)
+			j += 2;
+		else
+			j += 1;
+	}
+
+	return j;
+}
+EXPORT_SYMBOL(ucs2_utf8size);
+
+/*
+ * copy at most maxlength bytes of whole utf8 characters to dest from the
+ * ucs2 string src.
+ *
+ * The return value is the number of characters copied, not including the
+ * final NUL character.
+ */
+unsigned long
+ucs2_as_utf8(u8 *dest, const ucs2_char_t *src, unsigned long maxlength)
+{
+	unsigned int i;
+	unsigned long j = 0;
+	unsigned long limit = ucs2_strnlen(src, maxlength);
+
+	for (i = 0; maxlength && i < limit; i++) {
+		u16 c = src[i];
+
+		if (c > 0x800) {
+			if (maxlength < 3)
+				break;
+			maxlength -= 3;
+			dest[j++] = 0xe0 | (c & 0xf000) >> 12;
+			dest[j++] = 0x80 | (c & 0x0fc0) >> 8;
+			dest[j++] = 0x80 | (c & 0x003f);
+		} else if (c > 0x80) {
+			if (maxlength < 2)
+				break;
+			maxlength -= 2;
+			dest[j++] = 0xc0 | (c & 0xfe0) >> 5;
+			dest[j++] = 0x80 | (c & 0x01f);
+		} else {
+			maxlength -= 1;
+			dest[j++] = c & 0x7f;
+		}
+	}
+	if (maxlength)
+		dest[j] = '\0';
+	return j;
+}
+EXPORT_SYMBOL(ucs2_as_utf8);
-- 
2.6.2