| 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
| ||
|
Message-Id: <20180112071234.29470-8-krisman@collabora.co.uk>
Date: Fri, 12 Jan 2018 05:12:28 -0200
From: Gabriel Krisman Bertazi <krisman@...labora.co.uk>
To: tytso@....edu, david@...morbit.com, bpm@....com, olaf@....com
Cc: linux-ext4@...r.kernel.org, linux-fsdevel@...r.kernel.org,
kernel@...ts.collabora.co.uk, alvaro.soliverez@...labora.co.uk,
Gabriel Krisman Bertazi <krisman@...labora.co.uk>
Subject: [PATCH RFC 07/13] charsets: utf8: Hook-up utf-8 code to charsets library
Signed-off-by: Gabriel Krisman Bertazi <krisman@...labora.co.uk>
---
lib/charsets/Makefile | 2 +-
lib/charsets/utf8_core.c | 178 +++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 179 insertions(+), 1 deletion(-)
create mode 100644 lib/charsets/utf8_core.c
diff --git a/lib/charsets/Makefile b/lib/charsets/Makefile
index 95389c4193b0..5e2fa7c20a47 100644
--- a/lib/charsets/Makefile
+++ b/lib/charsets/Makefile
@@ -4,7 +4,7 @@ obj-$(CONFIG_CHARSETS) += charsets.o
obj-$(CONFIG_CHARSETS) += ascii.o
-utf8-y += utf8norm.o
+utf8-y += utf8_core.o utf8norm.o
obj-$(CONFIG_UTF8_NORMALIZATION) += utf8.o
$(obj)/utf8norm.o: $(obj)/utf8data.h
diff --git a/lib/charsets/utf8_core.c b/lib/charsets/utf8_core.c
new file mode 100644
index 000000000000..94427670e96e
--- /dev/null
+++ b/lib/charsets/utf8_core.c
@@ -0,0 +1,178 @@
+/*
+ * Copyright (c) 2017 Collabora Ltd.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/charsets.h>
+#include <linux/utf8norm.h>
+#include <linux/slab.h>
+#include <linux/parser.h>
+#include <linux/string.h>
+
+static int utf8_strncmp(const struct charset *charset, const char *str1,
+ const char *str2, int len)
+{
+ const struct utf8data *data = utf8nfkdi(charset->version);
+ struct utf8cursor cur1, cur2;
+ unsigned char c1, c2;
+ int r, i;
+
+ r = utf8cursor(&cur1, data, str1);
+ if (r < 0)
+ return -EIO;
+ r = utf8cursor(&cur2, data, str2);
+ if (r < 0)
+ return -EIO;
+
+ for (i = 0 ; i < len ; i++) {
+ c1 = utf8byte(&cur1);
+ c2 = utf8byte(&cur2);
+
+ if (!c1 || !c2 || c1 != c2)
+ return 1;
+
+ }
+
+ return 0;
+}
+
+static int utf8_strncasecmp(const struct charset *charset, const char *str1,
+ const char *str2, int len)
+{
+ const struct utf8data *data = utf8nfkdicf(charset->version);
+ struct utf8cursor cur1, cur2;
+ unsigned char c1, c2;
+ int r, i;
+
+ r = utf8cursor(&cur1, data, str1);
+ if (r < 0)
+ return -EIO;
+
+ r = utf8cursor(&cur2, data, str2);
+ if (r < 0)
+ return -EIO;
+
+ for (i = 0 ; i < len ; i++) {
+ c1 = utf8byte(&cur1);
+ c2 = utf8byte(&cur2);
+
+ if (!c1 || !c2 || c1 != c2)
+ return 1;
+ }
+
+ return 0;
+}
+
+int utf8_casefold(const struct charset *charset, const char *str, int len,
+ char **folded_str)
+{
+ const struct utf8data *data = utf8nfkdicf(charset->version);
+ struct utf8cursor cur;
+ int i;
+ char buffer[1024];
+
+ if (utf8cursor(&cur, data, str))
+ return -EIO;
+
+ for (i = 0; i < (1024-1); i++) {
+ buffer[i] = utf8byte(&cur);
+ if (!buffer[i])
+ break;
+ }
+ buffer[i] = '\0';
+ *folded_str = kstrdup(buffer, GFP_NOFS);
+ if (!*folded_str)
+ return -ENOMEM;
+
+ return i;
+}
+
+int utf8_normalize(const struct charset *charset, const char *str, int len,
+ char **normalization)
+{
+ const struct utf8data *data = utf8nfkdi(charset->version);
+ struct utf8cursor cur;
+ int i;
+ char buffer[1024];
+
+ if (utf8cursor(&cur, data, str))
+ return -EIO;
+
+ for (i = 0; i < (1024-1); i++) {
+ buffer[i] = utf8byte(&cur);
+ if (!buffer[i])
+ break;
+ }
+ buffer[i] = '\0';
+ *normalization = kstrdup(buffer, GFP_NOFS);
+ if (!*normalization)
+ return -ENOMEM;
+
+ return i;
+}
+
+static const struct charset_ops utf8_ops = {
+ .strncmp = utf8_strncmp,
+ .strncasecmp = utf8_strncasecmp,
+ .casefold = utf8_casefold,
+ .normalize = utf8_normalize,
+};
+
+static struct charset *utf8_load_charset(void *pargs)
+{
+ int maj, min, rev;
+ unsigned int age;
+ struct charset *charset;
+ substring_t *args = pargs;
+
+ if (match_int(&args[0], &maj) || match_int(&args[1], &min) ||
+ match_int(&args[2], &rev))
+ return NULL;
+
+ age = UNICODE_AGE(maj, min, rev);
+
+ if (!utf8version_is_supported(age))
+ return NULL;
+
+ charset = kmalloc(sizeof(struct charset), GFP_KERNEL);
+ if (!charset)
+ return NULL;
+
+ charset->info = NULL;
+ charset->version = age;
+ charset->ops = &utf8_ops;
+
+ return charset;
+}
+
+static struct charset_info utf8_info = {
+ .name = "utf8",
+ .match_token = "utf8-%d.%d.%d",
+ .load_charset = utf8_load_charset,
+};
+
+static int __init init_utf8(void)
+{
+ charset_register(&utf8_info);
+ return 0;
+}
+
+static void __exit exit_utf8(void)
+{
+}
+
+module_init(init_utf8);
+module_exit(exit_utf8);
+MODULE_AUTHOR("Gabriel Krisman Bertazi");
+MODULE_DESCRIPTION("UTF-8 charset operations for filesystems");
+MODULE_LICENSE("GPL");
+
--
2.15.1
Powered by blists - more mailing lists