summaryrefslogtreecommitdiffstats
path: root/fs/unicode/utf8n.h
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-11 08:27:49 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-11 08:27:49 +0000
commitace9429bb58fd418f0c81d4c2835699bddf6bde6 (patch)
treeb2d64bc10158fdd5497876388cd68142ca374ed3 /fs/unicode/utf8n.h
parentInitial commit. (diff)
downloadlinux-ace9429bb58fd418f0c81d4c2835699bddf6bde6.tar.xz
linux-ace9429bb58fd418f0c81d4c2835699bddf6bde6.zip
Adding upstream version 6.6.15.upstream/6.6.15
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'fs/unicode/utf8n.h')
-rw-r--r--fs/unicode/utf8n.h83
1 files changed, 83 insertions, 0 deletions
diff --git a/fs/unicode/utf8n.h b/fs/unicode/utf8n.h
new file mode 100644
index 0000000000..bd00d58774
--- /dev/null
+++ b/fs/unicode/utf8n.h
@@ -0,0 +1,83 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2014 SGI.
+ * All rights reserved.
+ */
+
+#ifndef UTF8NORM_H
+#define UTF8NORM_H
+
+#include <linux/types.h>
+#include <linux/export.h>
+#include <linux/string.h>
+#include <linux/module.h>
+#include <linux/unicode.h>
+
+int utf8version_is_supported(const struct unicode_map *um, unsigned int version);
+
+/*
+ * Determine the length of the normalized from of the string,
+ * excluding any terminating NULL byte.
+ * Returns 0 if only ignorable code points are present.
+ * Returns -1 if the input is not valid UTF-8.
+ */
+ssize_t utf8nlen(const struct unicode_map *um, enum utf8_normalization n,
+ const char *s, size_t len);
+
+/* Needed in struct utf8cursor below. */
+#define UTF8HANGULLEAF (12)
+
+/*
+ * Cursor structure used by the normalizer.
+ */
+struct utf8cursor {
+ const struct unicode_map *um;
+ enum utf8_normalization n;
+ const char *s;
+ const char *p;
+ const char *ss;
+ const char *sp;
+ unsigned int len;
+ unsigned int slen;
+ short int ccc;
+ short int nccc;
+ unsigned char hangul[UTF8HANGULLEAF];
+};
+
+/*
+ * Initialize a utf8cursor to normalize a string.
+ * Returns 0 on success.
+ * Returns -1 on failure.
+ */
+int utf8ncursor(struct utf8cursor *u8c, const struct unicode_map *um,
+ enum utf8_normalization n, const char *s, size_t len);
+
+/*
+ * Get the next byte in the normalization.
+ * Returns a value > 0 && < 256 on success.
+ * Returns 0 when the end of the normalization is reached.
+ * Returns -1 if the string being normalized is not valid UTF-8.
+ */
+extern int utf8byte(struct utf8cursor *u8c);
+
+struct utf8data {
+ unsigned int maxage;
+ unsigned int offset;
+};
+
+struct utf8data_table {
+ const unsigned int *utf8agetab;
+ int utf8agetab_size;
+
+ const struct utf8data *utf8nfdicfdata;
+ int utf8nfdicfdata_size;
+
+ const struct utf8data *utf8nfdidata;
+ int utf8nfdidata_size;
+
+ const unsigned char *utf8data;
+};
+
+extern struct utf8data_table utf8_data_table;
+
+#endif /* UTF8NORM_H */