summaryrefslogtreecommitdiffstats
path: root/lib/ext2fs/utf8n.h
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-19 09:25:10 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-19 09:25:10 +0000
commit5dced3d1b3deca80e01415a2e35dc7972dcbfae7 (patch)
tree6a403684e0978f0287d7f0ec0e5aab1fd31a59e1 /lib/ext2fs/utf8n.h
parentInitial commit. (diff)
downloade2fsprogs-5dced3d1b3deca80e01415a2e35dc7972dcbfae7.tar.xz
e2fsprogs-5dced3d1b3deca80e01415a2e35dc7972dcbfae7.zip
Adding upstream version 1.47.0.upstream/1.47.0
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to '')
-rw-r--r--lib/ext2fs/utf8n.h120
1 files changed, 120 insertions, 0 deletions
diff --git a/lib/ext2fs/utf8n.h b/lib/ext2fs/utf8n.h
new file mode 100644
index 0000000..c214f58
--- /dev/null
+++ b/lib/ext2fs/utf8n.h
@@ -0,0 +1,120 @@
+/*
+ * Copyright (c) 2014 SGI.
+ * All rights reserved.
+ *
+ * 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.
+ *
+ */
+
+/* This code is copied from the linux kernel. We have a userspace
+ * version here to such that hashes will match that implementation.
+ */
+
+#ifndef UTF8NORM_H
+#define UTF8NORM_H
+
+#include <stdint.h>
+#include <unistd.h>
+#include <string.h>
+
+/* Encoding a unicode version number as a single unsigned int. */
+#define UNICODE_MAJ_SHIFT (16)
+#define UNICODE_MIN_SHIFT (8)
+
+#define UNICODE_AGE(MAJ, MIN, REV) \
+ (((unsigned int)(MAJ) << UNICODE_MAJ_SHIFT) | \
+ ((unsigned int)(MIN) << UNICODE_MIN_SHIFT) | \
+ ((unsigned int)(REV)))
+
+/* Highest unicode version supported by the data tables. */
+extern int utf8version_is_supported(uint8_t maj, uint8_t min, uint8_t rev);
+extern int utf8version_latest(void);
+
+/*
+ * Look for the correct const struct utf8data for a unicode version.
+ * Returns NULL if the version requested is too new.
+ *
+ * Two normalization forms are supported: nfdi and nfdicf.
+ *
+ * nfdi:
+ * - Apply unicode normalization form NFD.
+ * - Remove any Default_Ignorable_Code_Point.
+ *
+ * nfdicf:
+ * - Apply unicode normalization form NFD.
+ * - Remove any Default_Ignorable_Code_Point.
+ * - Apply a full casefold (C + F).
+ */
+extern const struct utf8data *utf8nfdi(unsigned int maxage);
+extern const struct utf8data *utf8nfdicf(unsigned int maxage);
+
+/*
+ * Determine the maximum age of any unicode character in the string.
+ * Returns 0 if only unassigned code points are present.
+ * Returns -1 if the input is not valid UTF-8.
+ */
+extern int utf8agemax(const struct utf8data *data, const char *s);
+extern int utf8nagemax(const struct utf8data *data, const char *s, size_t len);
+
+/*
+ * Determine the minimum age of any unicode character in the string.
+ * Returns 0 if any unassigned code points are present.
+ * Returns -1 if the input is not valid UTF-8.
+ */
+extern int utf8agemin(const struct utf8data *data, const char *s);
+extern int utf8nagemin(const struct utf8data *data, const char *s, size_t len);
+
+/*
+ * 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.
+ */
+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. */
+#define UTF8HANGULLEAF (12)
+
+/*
+ * Cursor structure used by the normalizer.
+ */
+struct utf8cursor {
+ const struct utf8data *data;
+ 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.
+ */
+extern int utf8cursor(struct utf8cursor *u8c, const struct utf8data *data,
+ const char *s);
+extern int utf8ncursor(struct utf8cursor *u8c, const struct utf8data *data,
+ 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);
+
+#endif /* UTF8NORM_H */