Received-SPF: pass (google.com: domain of linux-ext4-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Christoph Hellwig <hch@lst.de>
To:     Gabriel Krisman Bertazi <krisman@collabora.com>
Cc:     Shreeya Patel <shreeya.patel@collabora.com>,
        linux-fsdevel@vger.kernel.org, linux-ext4@vger.kernel.org,
        linux-f2fs-devel@lists.sourceforge.net
Subject: [PATCH 07/11] unicode: simplify utf8len
Date:   Wed, 15 Sep 2021 09:00:02 +0200
Message-Id: <20210915070006.954653-8-hch@lst.de>
In-Reply-To: <20210915070006.954653-1-hch@lst.de>
References: <20210915070006.954653-1-hch@lst.de>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Just use the utf8nlen implementation with a (size_t)-1 len argument,
similar to utf8_lookup.  Also move the function to utf8-selftest.c, as
it isn't used anywhere else.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/unicode/utf8-norm.c     | 30 ------------------------------
 fs/unicode/utf8-selftest.c |  5 +++++
 fs/unicode/utf8n.h         |  1 -
 3 files changed, 5 insertions(+), 31 deletions(-)

diff --git a/fs/unicode/utf8-norm.c b/fs/unicode/utf8-norm.c
index 4b1b53391ce4b..348d6e97553f2 100644
--- a/fs/unicode/utf8-norm.c
+++ b/fs/unicode/utf8-norm.c
@@ -391,36 +391,6 @@ static utf8leaf_t *utf8lookup(const struct utf8data *data,
 	return utf8nlookup(data, hangul, s, (size_t)-1);
 }
 
-/*
- * Length of the normalization of s.
- * Return -1 if s is not valid UTF-8 unicode.
- *
- * A string of Default_Ignorable_Code_Point has length 0.
- */
-ssize_t utf8len(const struct utf8data *data, const char *s)
-{
-	utf8leaf_t	*leaf;
-	size_t		ret = 0;
-	unsigned char	hangul[UTF8HANGULLEAF];
-
-	if (!data)
-		return -1;
-	while (*s) {
-		leaf = utf8lookup(data, hangul, s);
-		if (!leaf)
-			return -1;
-		if (utf8agetab[LEAF_GEN(leaf)] > data->maxage)
-			ret += utf8clen(s);
-		else if (LEAF_CCC(leaf) == DECOMPOSE)
-			ret += strlen(LEAF_STR(leaf));
-		else
-			ret += utf8clen(s);
-		s += utf8clen(s);
-	}
-	return ret;
-}
-EXPORT_SYMBOL(utf8len);
-
 /*
  * Length of the normalization of s, touch at most len bytes.
  * Return -1 if s is not valid UTF-8 unicode.
diff --git a/fs/unicode/utf8-selftest.c b/fs/unicode/utf8-selftest.c
index 37f33890e012f..80fb7c75acb28 100644
--- a/fs/unicode/utf8-selftest.c
+++ b/fs/unicode/utf8-selftest.c
@@ -160,6 +160,11 @@ static const struct {
 	}
 };
 
+static ssize_t utf8len(const struct utf8data *data, const char *s)
+{
+	return utf8nlen(data, s, (size_t)-1);
+}
+
 static void check_utf8_nfdi(void)
 {
 	int i;
diff --git a/fs/unicode/utf8n.h b/fs/unicode/utf8n.h
index e4c8a767cf7a5..41182e5464dfa 100644
--- a/fs/unicode/utf8n.h
+++ b/fs/unicode/utf8n.h
@@ -39,7 +39,6 @@ extern const struct utf8data *utf8nfdicf(unsigned int maxage);
  * Returns 0 if only ignorable code points are present.
  * Returns -1 if the input is not valid UTF-8.
  */
-extern ssize_t utf8len(const struct utf8data *data, const char *s);
 extern ssize_t utf8nlen(const struct utf8data *data, const char *s, size_t len);
 
 /* Needed in struct utf8cursor below. */
-- 
2.30.2