From: Gabriel Krisman Bertazi Subject: [PATCH RFC v2 07/13] charsets: utf8: Hook-up utf-8 code to charsets library Date: Thu, 25 Jan 2018 00:53:43 -0200 Message-ID: <20180125025349.31494-8-krisman@collabora.co.uk> References: <20180125025349.31494-1-krisman@collabora.co.uk> Cc: linux-ext4@vger.kernel.org, linux-fsdevel@vger.kernel.org, alvaro.soliverez@collabora.co.uk, kernel@lists.collabora.co.uk, Gabriel Krisman Bertazi To: tytso@mit.edu, david@fromorbit.com, olaf@sgi.com, viro@zeniv.linux.org.uk Return-path: Received: from bhuna.collabora.co.uk ([46.235.227.227]:52070 "EHLO bhuna.collabora.co.uk" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S933290AbeAYCzK (ORCPT ); Wed, 24 Jan 2018 21:55:10 -0500 In-Reply-To: <20180125025349.31494-1-krisman@collabora.co.uk> Sender: linux-ext4-owner@vger.kernel.org List-ID: Changes since RFC v1: - Change error return code from EIO to EINVAL. (Olaf Weber) - Fix issues with strncmp/strcmp. (Olaf Weber) - Remove stack buffer in normalization/casefold. (Olaf Weber) - Include length parameter for second string on comparison functions. - Change length type to size_t. Signed-off-by: Gabriel Krisman Bertazi --- lib/charsets/Makefile | 2 +- lib/charsets/utf8_core.c | 180 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 181 insertions(+), 1 deletion(-) create mode 100644 lib/charsets/utf8_core.c diff --git a/lib/charsets/Makefile b/lib/charsets/Makefile index d33ac8643ef9..004d0e5d6ac4 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..f1c4fcc249fb --- /dev/null +++ b/lib/charsets/utf8_core.c @@ -0,0 +1,180 @@ +/* + * 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 +#include +#include +#include +#include + +static int utf8_strncmp(const struct charset *charset, const char *str1, + size_t len1, const char *str2, size_t len2) +{ + const struct utf8data *data = utf8nfkdi(charset->version); + struct utf8cursor cur1, cur2; + int c1, c2; + int r; + + r = utf8ncursor(&cur1, data, str1, len1); + if (r < 0) + return -EINVAL; + r = utf8ncursor(&cur2, data, str2, len2); + if (r < 0) + return -EINVAL; + + do { + c1 = utf8byte(&cur1); + c2 = utf8byte(&cur2); + + if (c1 < 0 || c2 < 0) + return -EINVAL; + if (c1 != c2) + return 1; + } while (c1); + + return 0; +} + +static int utf8_strncasecmp(const struct charset *charset, const char *str1, + size_t len1, const char *str2, size_t len2) +{ + const struct utf8data *data = utf8nfkdicf(charset->version); + struct utf8cursor cur1, cur2; + unsigned char c1, c2; + int r; + + r = utf8ncursor(&cur1, data, str1, len1); + if (r < 0) + return -EINVAL; + + r = utf8ncursor(&cur2, data, str2, len2); + if (r < 0) + return -EINVAL; + + do { + c1 = utf8byte(&cur1); + c2 = utf8byte(&cur2); + + if (c1 < 0 || c2 < 0) + return -EINVAL; + if (c1 != c2) + return 1; + } while (c1); + + return 0; +} + +int utf8_casefold(const struct charset *charset, const char *str, int len, + char **folded) +{ + const struct utf8data *data = utf8nfkdicf(charset->version); + struct utf8cursor cur; + char *s; + ssize_t nlen; + + nlen = utf8nlen(data, str, len); + if (nlen < 0) + return -EINVAL; + + s = kmalloc(nlen + 1, GFP_NOFS); + if (!s) + return -ENOMEM; + *folded = s; + + utf8ncursor(&cur, data, str, len); + do { + *s = utf8byte(&cur); + } while (*s++); + + return nlen; +} + +int utf8_normalize(const struct charset *charset, const char *str, int len, + char **normalization) +{ + const struct utf8data *data = utf8nfkdi(charset->version); + struct utf8cursor cur; + char *s; + ssize_t nlen; + + nlen = utf8nlen(data, str, len); + if (nlen < 0) + return -EINVAL; + + s = kmalloc(nlen + 1, GFP_NOFS); + if (!s) + return -ENOMEM; + *normalization = s; + + utf8ncursor(&cur, data, str, len); + do { + *s = utf8byte(&cur); + } while (*s++); + + return nlen; +} + +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; + 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; + + if (!utf8version_is_supported(maj, min, rev)) + return NULL; + + charset = kmalloc(sizeof(struct charset), GFP_KERNEL); + if (!charset) + return NULL; + + charset->info = NULL; + charset->version = UNICODE_AGE(maj, min, rev); + 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