Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Fri,  7 Feb 2020 17:35:45 -0800
In-Reply-To: <20200208013552.241832-1-drosen@google.com>
Message-Id: <20200208013552.241832-2-drosen@google.com>
Mime-Version: 1.0
References: <20200208013552.241832-1-drosen@google.com>
Subject: [PATCH v7 1/8] unicode: Add utf8_casefold_iter
From:   Daniel Rosenberg <drosen@google.com>
To:     "Theodore Ts'o" <tytso@mit.edu>, linux-ext4@vger.kernel.org,
        Jaegeuk Kim <jaegeuk@kernel.org>, Chao Yu <chao@kernel.org>,
        linux-f2fs-devel@lists.sourceforge.net,
        Eric Biggers <ebiggers@kernel.org>,
        linux-fscrypt@vger.kernel.org,
        Alexander Viro <viro@zeniv.linux.org.uk>,
        Richard Weinberger <richard@nod.at>
Cc:     linux-mtd@lists.infradead.org,
        Andreas Dilger <adilger.kernel@dilger.ca>,
        Jonathan Corbet <corbet@lwn.net>, linux-doc@vger.kernel.org,
        linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org,
        Gabriel Krisman Bertazi <krisman@collabora.com>,
        kernel-team@android.com, Daniel Rosenberg <drosen@google.com>
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

This function will allow other uses of unicode to act upon a casefolded
string without needing to allocate their own copy of one.

The actor function can return an nonzero value to exit early.

Signed-off-by: Daniel Rosenberg <drosen@google.com>
---
 fs/unicode/utf8-core.c  | 25 ++++++++++++++++++++++++-
 include/linux/unicode.h | 10 ++++++++++
 2 files changed, 34 insertions(+), 1 deletion(-)

diff --git a/fs/unicode/utf8-core.c b/fs/unicode/utf8-core.c
index 2a878b739115d..db050bf59a32b 100644
--- a/fs/unicode/utf8-core.c
+++ b/fs/unicode/utf8-core.c
@@ -122,9 +122,32 @@ int utf8_casefold(const struct unicode_map *um, const struct qstr *str,
 	}
 	return -EINVAL;
 }
-
 EXPORT_SYMBOL(utf8_casefold);
 
+int utf8_casefold_iter(const struct unicode_map *um, const struct qstr *str,
+		    struct utf8_itr_context *ctx)
+{
+	const struct utf8data *data = utf8nfdicf(um->version);
+	struct utf8cursor cur;
+	int c;
+	int res = 0;
+	int pos = 0;
+
+	if (utf8ncursor(&cur, data, str->name, str->len) < 0)
+		return -EINVAL;
+
+	while ((c = utf8byte(&cur))) {
+		if (c < 0)
+			return c;
+		res = ctx->actor(ctx, c, pos);
+		pos++;
+		if (res)
+			return res;
+	}
+	return res;
+}
+EXPORT_SYMBOL(utf8_casefold_iter);
+
 int utf8_normalize(const struct unicode_map *um, const struct qstr *str,
 		   unsigned char *dest, size_t dlen)
 {
diff --git a/include/linux/unicode.h b/include/linux/unicode.h
index 990aa97d80496..2ae12f8710ae2 100644
--- a/include/linux/unicode.h
+++ b/include/linux/unicode.h
@@ -10,6 +10,13 @@ struct unicode_map {
 	int version;
 };
 
+struct utf8_itr_context;
+typedef int (*utf8_itr_actor_t)(struct utf8_itr_context *, int byte, int pos);
+
+struct utf8_itr_context {
+	utf8_itr_actor_t actor;
+};
+
 int utf8_validate(const struct unicode_map *um, const struct qstr *str);
 
 int utf8_strncmp(const struct unicode_map *um,
@@ -27,6 +34,9 @@ int utf8_normalize(const struct unicode_map *um, const struct qstr *str,
 int utf8_casefold(const struct unicode_map *um, const struct qstr *str,
 		  unsigned char *dest, size_t dlen);
 
+int utf8_casefold_iter(const struct unicode_map *um, const struct qstr *str,
+		    struct utf8_itr_context *ctx);
+
 struct unicode_map *utf8_load(const char *version);
 void utf8_unload(struct unicode_map *um);
 
-- 
2.25.0.341.g760bfbb309-goog