openharmony/third_party_f2fs-tools
1
0
Fork 0
mirror of https://gitee.com/openharmony/third_party_f2fs-tools synced 2024-11-23 01:59:54 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

f2fs-tools: Add support for Casefolding

Browse Source 
This adds support for f2fs casefolding. Similarly to ext4 casefolding,
this is controlled per-folder via the +F attribute. It can be toggled on
empty directories only. It is not currently compatible with encryption,
but that will likely change.

When enabling the casefold feature, use the -C flag. The format is:
-C encoding[:flag1,flag2,etc]

Signed-off-by: Daniel Rosenberg <drosen@google.com>
[Jaegeuk Kim: print "casefold" in sb->feature]
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
This commit is contained in:
Daniel Rosenberg 2019-07-11 13:45:41 -07:00 committed by Jaegeuk Kim
parent db84e73777
commit ce64ea0815
14 changed files with 5304 additions and 37 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
fsck/dir.c
View File

@ -106,7 +106,7 @@ static struct f2fs_dir_entry *find_in_block(void *block,
return find_target_dentry(name, len, namehash, max_slots, &d);
}
static int find_in_level(struct f2fs_sb_info *sbi,struct f2fs_node *dir,
static int find_in_level(struct f2fs_sb_info *sbi, struct f2fs_node *dir,
unsigned int level, struct dentry *de)
{
unsigned int nbucket, nblock;
@ -120,7 +120,8 @@ static int find_in_level(struct f2fs_sb_info *sbi,struct f2fs_node *dir,
unsigned int dir_level = dir->i.i_dir_level;
int ret = 0;
namehash = f2fs_dentry_hash(de->name, de->len);
namehash = f2fs_dentry_hash(get_encoding(sbi), IS_CASEFOLDED(&dir->i),
de->name, de->len);
nbucket = dir_buckets(level, dir_level);
nblock = bucket_blocks(level);
@ -223,7 +224,9 @@ int f2fs_add_link(struct f2fs_sb_info *sbi, struct f2fs_node *parent,
int level = 0, current_depth, bit_pos;
int nbucket, nblock, bidx, block;
int slots = GET_DENTRY_SLOTS(name_len);
f2fs_hash_t dentry_hash = f2fs_dentry_hash(name, name_len);
f2fs_hash_t dentry_hash = f2fs_dentry_hash(get_encoding(sbi),
IS_CASEFOLDED(&parent->i),
name, name_len);
struct f2fs_dentry_block *dentry_blk;
struct f2fs_dentry_ptr d;
struct dnode_of_data dn;

5
fsck/f2fs.h
View File

@ -513,4 +513,9 @@ static inline int is_dot_dotdot(const unsigned char *name, const int len)
return 0;
}
static inline int get_encoding(struct f2fs_sb_info *sbi)
{
return le16_to_cpu(F2FS_RAW_SUPER(sbi)->s_encoding);
}
#endif /* _F2FS_H_ */

42
fsck/fsck.c
View File

@ -833,6 +833,7 @@ void fsck_chk_inode_blk(struct f2fs_sb_info *sbi, u32 nid,
if (blkaddr != 0) {
ret = fsck_chk_data_blk(sbi,
IS_CASEFOLDED(&node_blk->i),
blkaddr,
&child, (i_blocks == *blk_cnt),
ftype, nid, idx, ni->version,
@ -1067,7 +1068,7 @@ int fsck_chk_dnode_blk(struct f2fs_sb_info *sbi, struct f2fs_inode *inode,
if (blkaddr == 0x0)
continue;
ret = fsck_chk_data_blk(sbi,
ret = fsck_chk_data_blk(sbi, IS_CASEFOLDED(inode),
blkaddr, child,
le64_to_cpu(inode->i_blocks) == *blk_cnt, ftype,
nid, idx, ni->version,
@ -1258,11 +1259,11 @@ static void print_dentry(__u32 depth, __u8 *name,
enc_name);
}
static int f2fs_check_hash_code(struct f2fs_dir_entry *dentry,
static int f2fs_check_hash_code(int encoding, int casefolded,
struct f2fs_dir_entry *dentry,
const unsigned char *name, u32 len, int enc_name)
{
f2fs_hash_t hash_code = f2fs_dentry_hash(name, len);
f2fs_hash_t hash_code = f2fs_dentry_hash(encoding, casefolded, name, len);
/* fix hash_code made by old buggy code */
if (dentry->hash_code != hash_code) {
char new[F2FS_PRINT_NAMELEN];
@ -1291,10 +1292,11 @@ static int __get_current_level(int dir_level, u32 pgofs)
return i;
}
static int f2fs_check_dirent_position(u8 *name, u16 name_len, u32 pgofs,
static int f2fs_check_dirent_position(int encoding, int casefolded,
u8 *name, u16 name_len, u32 pgofs,
u8 dir_level, u32 pino)
{
f2fs_hash_t namehash = f2fs_dentry_hash(name, name_len);
f2fs_hash_t namehash = f2fs_dentry_hash(encoding, casefolded, name, name_len);
unsigned int nbucket, nblock;
unsigned int bidx, end_block;
int level;
@ -1318,6 +1320,7 @@ static int f2fs_check_dirent_position(u8 *name, u16 name_len, u32 pgofs,
}
static int __chk_dots_dentries(struct f2fs_sb_info *sbi,
int casefolded,
struct f2fs_dir_entry *dentry,
struct child_info *child,
u8 *name, int len,
@ -1351,7 +1354,7 @@ static int __chk_dots_dentries(struct f2fs_sb_info *sbi,
}
}
if (f2fs_check_hash_code(dentry, name, len, enc_name))
if (f2fs_check_hash_code(get_encoding(sbi), casefolded, dentry, name, len, enc_name))
fixed = 1;
if (name[len] != '\0') {
@ -1371,7 +1374,8 @@ static void nullify_dentry(struct f2fs_dir_entry *dentry, int offs,
memset(*filename, 0, F2FS_SLOT_LEN);
}
static int __chk_dentries(struct f2fs_sb_info *sbi, struct child_info *child,
static int __chk_dentries(struct f2fs_sb_info *sbi, int casefolded,
struct child_info *child,
u8 *bitmap, struct f2fs_dir_entry *dentry,
__u8 (*filenames)[F2FS_SLOT_LEN],
int max, int last_blk, int enc_name)
@ -1464,7 +1468,7 @@ static int __chk_dentries(struct f2fs_sb_info *sbi, struct child_info *child,
if ((name[0] == '.' && name_len == 1) ||
(name[0] == '.' && name[1] == '.' &&
name_len == 2)) {
ret = __chk_dots_dentries(sbi, &dentry[i],
ret = __chk_dots_dentries(sbi, casefolded, &dentry[i],
child, name, name_len, &filenames[i],
enc_name);
switch (ret) {
@ -1489,12 +1493,12 @@ static int __chk_dentries(struct f2fs_sb_info *sbi, struct child_info *child,
}
}
if (f2fs_check_hash_code(dentry + i, name, name_len, enc_name))
if (f2fs_check_hash_code(get_encoding(sbi), casefolded, dentry + i, name, name_len, enc_name))
fixed = 1;
if (max == NR_DENTRY_IN_BLOCK) {
ret = f2fs_check_dirent_position(name, name_len,
child->pgofs,
ret = f2fs_check_dirent_position(get_encoding(sbi), casefolded,
name, name_len, child->pgofs,
child->dir_level, child->p_ino);
if (ret) {
if (c.fix_on) {
@ -1560,9 +1564,9 @@ int fsck_chk_inline_dentries(struct f2fs_sb_info *sbi,
make_dentry_ptr(&d, node_blk, inline_dentry, 2);
fsck->dentry_depth++;
dentries = __chk_dentries(sbi, child,
dentries = __chk_dentries(sbi, IS_CASEFOLDED(&node_blk->i), child,
d.bitmap, d.dentry, d.filename, d.max, 1,
file_is_encrypt(&node_blk->i));
file_is_encrypt(&node_blk->i));// pass through
if (dentries < 0) {
DBG(1, "[%3d] Inline Dentry Block Fixed hash_codes\n\n",
fsck->dentry_depth);
@ -1576,7 +1580,7 @@ int fsck_chk_inline_dentries(struct f2fs_sb_info *sbi,
return dentries;
}
int fsck_chk_dentry_blk(struct f2fs_sb_info *sbi, u32 blk_addr,
int fsck_chk_dentry_blk(struct f2fs_sb_info *sbi, int casefolded, u32 blk_addr,
struct child_info *child, int last_blk, int enc_name)
{
struct f2fs_fsck *fsck = F2FS_FSCK(sbi);
@ -1590,7 +1594,7 @@ int fsck_chk_dentry_blk(struct f2fs_sb_info *sbi, u32 blk_addr,
ASSERT(ret >= 0);
fsck->dentry_depth++;
dentries = __chk_dentries(sbi, child,
dentries = __chk_dentries(sbi, casefolded, child,
de_blk->dentry_bitmap,
de_blk->dentry, de_blk->filename,
NR_DENTRY_IN_BLOCK, last_blk, enc_name);
@ -1611,8 +1615,8 @@ int fsck_chk_dentry_blk(struct f2fs_sb_info *sbi, u32 blk_addr,
return 0;
}
int fsck_chk_data_blk(struct f2fs_sb_info *sbi, u32 blk_addr,
struct child_info *child, int last_blk,
int fsck_chk_data_blk(struct f2fs_sb_info *sbi, int casefolded,
u32 blk_addr, struct child_info *child, int last_blk,
enum FILE_TYPE ftype, u32 parent_nid, u16 idx_in_node, u8 ver,
int enc_name)
{
@ -1647,7 +1651,7 @@ int fsck_chk_data_blk(struct f2fs_sb_info *sbi, u32 blk_addr,
if (ftype == F2FS_FT_DIR) {
f2fs_set_main_bitmap(sbi, blk_addr, CURSEG_HOT_DATA);
return fsck_chk_dentry_blk(sbi, blk_addr, child,
return fsck_chk_dentry_blk(sbi, casefolded, blk_addr, child,
last_blk, enc_name);
} else {
f2fs_set_main_bitmap(sbi, blk_addr, CURSEG_WARM_DATA);

8
fsck/fsck.h
View File

@ -148,10 +148,10 @@ extern int fsck_chk_idnode_blk(struct f2fs_sb_info *, struct f2fs_inode *,
enum FILE_TYPE, struct f2fs_node *, u32 *, struct child_info *);
extern int fsck_chk_didnode_blk(struct f2fs_sb_info *, struct f2fs_inode *,
enum FILE_TYPE, struct f2fs_node *, u32 *, struct child_info *);
extern int fsck_chk_data_blk(struct f2fs_sb_info *sbi, u32, struct child_info *,
int, enum FILE_TYPE, u32, u16, u8, int);
extern int fsck_chk_dentry_blk(struct f2fs_sb_info *, u32, struct child_info *,
int, int);
extern int fsck_chk_data_blk(struct f2fs_sb_info *, int,
u32, struct child_info *, int, enum FILE_TYPE, u32, u16, u8, int);
extern int fsck_chk_dentry_blk(struct f2fs_sb_info *, int,
u32, struct child_info *, int, int);
int fsck_chk_inline_dentries(struct f2fs_sb_info *, struct f2fs_node *,
struct child_info *);
void fsck_chk_checkpoint(struct f2fs_sb_info *sbi);

22
fsck/main.c
View File

@ -54,6 +54,7 @@ void fsck_usage()
MSG(0, "\nUsage: fsck.f2fs [options] device\n");
MSG(0, "[options]:\n");
MSG(0, " -a check/fix potential corruption, reported by f2fs\n");
MSG(0, " -C encoding[:flag1,flag2] Set options for enabling casefolding\n");
MSG(0, " -d debug level [default:0]\n");
MSG(0, " -f check/fix entire partition\n");
MSG(0, " -g add default options\n");
@ -186,8 +187,9 @@ void f2fs_parse_options(int argc, char *argv[])
}
if (!strcmp("fsck.f2fs", prog)) {
const char *option_string = ":ad:fg:O:p:q:StyV";
int opt = 0;
const char *option_string = ":aC:d:fg:O:p:q:StyV";
int opt = 0, val;
char *token;
struct option long_opt[] = {
{"dry-run", no_argument, 0, 1},
{0, 0, 0, 0}
@ -278,6 +280,22 @@ void f2fs_parse_options(int argc, char *argv[])
break;
}
break;
case 'C':
token = strtok(optarg, ":");
val = f2fs_str2encoding(token);
if (val < 0) {
MSG(0, "\tError: Unknown encoding %s\n", token);
fsck_usage();
}
c.s_encoding = val;
token = strtok(NULL, "");
val = f2fs_str2encoding_flags(&token, &c.s_encoding_flags);
if (val) {
MSG(0, "\tError: Unknown flag %s\n", token);
fsck_usage();
}
c.feature |= cpu_to_le32(F2FS_FEATURE_CASEFOLD);
break;
case 'V':
show_version(prog);
exit(0);

27
fsck/mount.c
View File

@ -465,6 +465,9 @@ void print_sb_state(struct f2fs_super_block *sb)
if (f & cpu_to_le32(F2FS_FEATURE_SB_CHKSUM)) {
MSG(0, "%s", " sb_checksum");
}
if (f & cpu_to_le32(F2FS_FEATURE_CASEFOLD)) {
MSG(0, "%s", " casefold");
}
MSG(0, "\n");
MSG(0, "Info: superblock encrypt level = %d, salt = ",
sb->encryption_level);
@ -2762,24 +2765,41 @@ static int check_sector_size(struct f2fs_super_block *sb)
return 0;
}
static void tune_sb_features(struct f2fs_sb_info *sbi)
static int tune_sb_features(struct f2fs_sb_info *sbi)
{
int sb_changed = 0;
struct f2fs_super_block *sb = F2FS_RAW_SUPER(sbi);
if (c.feature & cpu_to_le32(F2FS_FEATURE_ENCRYPT) &&
c.feature & cpu_to_le32(F2FS_FEATURE_CASEFOLD)) {
ERR_MSG("ERROR: Cannot set both encrypt and casefold. Skipping.\n");
return -1;
}
if (!(sb->feature & cpu_to_le32(F2FS_FEATURE_ENCRYPT)) &&
c.feature & cpu_to_le32(F2FS_FEATURE_ENCRYPT)) {
sb->feature |= cpu_to_le32(F2FS_FEATURE_ENCRYPT);
MSG(0, "Info: Set Encryption feature\n");
sb_changed = 1;
}
if (!(sb->feature & cpu_to_le32(F2FS_FEATURE_CASEFOLD)) &&
c.feature & cpu_to_le32(F2FS_FEATURE_CASEFOLD)) {
if (!c.s_encoding) {
ERR_MSG("ERROR: Must specify encoding to enable casefolding.\n");
return -1;
}
sb->feature |= cpu_to_le32(F2FS_FEATURE_CASEFOLD);
MSG(0, "Info: Set Casefold feature\n");
sb_changed = 1;
}
/* TODO: quota needs to allocate inode numbers */
c.feature = sb->feature;
if (!sb_changed)
return;
return 0;
update_superblock(sb, SB_MASK_ALL);
return 0;
}
int f2fs_do_mount(struct f2fs_sb_info *sbi)
@ -2826,7 +2846,8 @@ int f2fs_do_mount(struct f2fs_sb_info *sbi)
c.bug_on = 0;
tune_sb_features(sbi);
if (tune_sb_features(sbi))
return -1;
/* precompute checksum seed for metadata */
if (c.feature & cpu_to_le32(F2FS_FEATURE_INODE_CHKSUM))

37
include/f2fs_fs.h
View File

@ -356,6 +356,8 @@ struct f2fs_configuration {
__u8 sb_version[VERSION_LEN + 1];
__u8 version[VERSION_LEN + 1];
char *vol_label;
u_int16_t s_encoding;
u_int16_t s_encoding_flags;
int heap;
int32_t kd;
int32_t dump_fd;
@ -564,6 +566,9 @@ enum {
#define FS_IMMUTABLE_FL 0x00000010 /* Immutable file */
#define F2FS_ENC_UTF8_12_1 1
#define F2FS_ENC_STRICT_MODE_FL (1 << 0)
/* This flag is used by node and meta inodes, and by recovery */
#define GFP_F2FS_ZERO (GFP_NOFS | __GFP_ZERO)
@ -589,6 +594,7 @@ enum {
#define F2FS_FEATURE_LOST_FOUND 0x0200
#define F2FS_FEATURE_VERITY 0x0400 /* reserved */
#define F2FS_FEATURE_SB_CHKSUM 0x0800
#define F2FS_FEATURE_CASEFOLD 0x1000
#define MAX_VOLUME_NAME 512
@ -642,7 +648,9 @@ struct f2fs_super_block {
struct f2fs_device devs[MAX_DEVICES]; /* device list */
__le32 qf_ino[F2FS_MAX_QUOTAS]; /* quota inode numbers */
__u8 hot_ext_count; /* # of hot file extension */
__u8 reserved[310]; /* valid reserved region */
__le16 s_encoding; /* Filename charset encoding */
__le16 s_encoding_flags; /* Filename charset encoding flags */
__u8 reserved[306]; /* valid reserved region */
__le32 crc; /* checksum of superblock */
} __attribute__((packed));
@ -797,6 +805,9 @@ struct f2fs_extent {
#define file_is_encrypt(fi) ((fi)->i_advise & FADVISE_ENCRYPT_BIT)
#define file_enc_name(fi) ((fi)->i_advise & FADVISE_ENC_NAME_BIT)
#define F2FS_CASEFOLD_FL 0x40000000 /* Casefolded file */
#define IS_CASEFOLDED(dir) ((dir)->i_flags & F2FS_CASEFOLD_FL)
struct f2fs_inode {
__le16 i_mode; /* file mode */
__u8 i_advise; /* file hints */
@ -1188,7 +1199,7 @@ extern int dev_reada_block(__u64);
extern int dev_read_version(void *, __u64, size_t);
extern void get_kernel_version(__u8 *);
extern void get_kernel_uname_version(__u8 *);
f2fs_hash_t f2fs_dentry_hash(const unsigned char *, int);
f2fs_hash_t f2fs_dentry_hash(int, int, const unsigned char *, int);
static inline bool f2fs_has_extra_isize(struct f2fs_inode *inode)
{
@ -1373,6 +1384,7 @@ struct feature feature_table[] = { \
{ "lost_found", F2FS_FEATURE_LOST_FOUND }, \
{ "verity", F2FS_FEATURE_VERITY }, /* reserved */ \
{ "sb_checksum", F2FS_FEATURE_SB_CHKSUM }, \
{ "casefold", F2FS_FEATURE_CASEFOLD }, \
{ NULL, 0x0}, \
};
@ -1446,4 +1458,25 @@ static inline int parse_root_owner(char *ids,
return 0;
}
/*
* NLS definitions
*/
struct f2fs_nls_table {
int version;
const struct f2fs_nls_ops *ops;
};
struct f2fs_nls_ops {
int (*casefold)(const struct f2fs_nls_table *charset,
const unsigned char *str, size_t len,
unsigned char *dest, size_t dlen);
};
extern const struct f2fs_nls_table *f2fs_load_nls_table(int encoding);
#define F2FS_ENC_UTF8_12_0 1
extern int f2fs_str2encoding(const char *string);
extern int f2fs_get_encoding_flags(int encoding);
extern int f2fs_str2encoding_flags(char **param, __u16 *flags);
#endif /*__F2FS_FS_H */

2
lib/Makefile.am
View File

@ -2,7 +2,7 @@
lib_LTLIBRARIES = libf2fs.la
libf2fs_la_SOURCES = libf2fs.c libf2fs_io.c libf2fs_zoned.c
libf2fs_la_SOURCES = libf2fs.c libf2fs_io.c libf2fs_zoned.c nls_utf8.c
libf2fs_la_CFLAGS = -Wall
libf2fs_la_CPPFLAGS = -I$(top_srcdir)/include
libf2fs_la_LDFLAGS = -version-info $(LIBF2FS_CURRENT):$(LIBF2FS_REVISION):$(LIBF2FS_AGE)

111
lib/libf2fs.c
View File

@ -441,7 +441,7 @@ static void str2hashbuf(const unsigned char *msg, int len,
* @param len name lenth
* @return return on success hash value, errno on failure
*/
f2fs_hash_t f2fs_dentry_hash(const unsigned char *name, int len)
static f2fs_hash_t __f2fs_dentry_hash(const unsigned char *name, int len)/* Need update */
{
__u32 hash;
f2fs_hash_t f2fs_hash;
@ -474,6 +474,31 @@ f2fs_hash_t f2fs_dentry_hash(const unsigned char *name, int len)
return f2fs_hash;
}
f2fs_hash_t f2fs_dentry_hash(int encoding, int casefolded,
const unsigned char *name, int len)
{
const struct f2fs_nls_table *table = f2fs_load_nls_table(encoding);
int r, dlen;
unsigned char *buff;
if (len && casefolded) {
buff = malloc(sizeof(char) * PATH_MAX);
if (!buff)
return -ENOMEM;
dlen = table->ops->casefold(table, name, len, buff, PATH_MAX);
if (dlen < 0) {
free(buff);
goto opaque_seq;
}
r = __f2fs_dentry_hash(buff, dlen);
free(buff);
return r;
}
opaque_seq:
return __f2fs_dentry_hash(name, len);
}
unsigned int addrs_per_inode(struct f2fs_inode *i)
{
return CUR_ADDRS_PER_INODE(i) - get_inline_xattr_addrs(i);
@ -647,6 +672,8 @@ void f2fs_init_configuration(void)
c.trim = 1;
c.kd = -1;
c.fixed_time = -1;
c.s_encoding = 0;
c.s_encoding_flags = 0;
/* default root owner */
c.root_uid = getuid();
@ -1220,3 +1247,85 @@ unsigned int calc_extra_isize(void)
return size - F2FS_EXTRA_ISIZE_OFFSET;
}
#define ARRAY_SIZE(array) \
(sizeof(array) / sizeof(array[0]))
static const struct {
char *name;
__u16 encoding_magic;
__u16 default_flags;
} f2fs_encoding_map[] = {
{
.encoding_magic = F2FS_ENC_UTF8_12_1,
.name = "utf8",
.default_flags = 0,
},
};
static const struct enc_flags {
__u16 flag;
char *param;
} encoding_flags[] = {
{ F2FS_ENC_STRICT_MODE_FL, "strict" },
};
/* Return a positive number < 0xff indicating the encoding magic number
* or a negative value indicating error. */
int f2fs_str2encoding(const char *string)
{
int i;
for (i = 0 ; i < ARRAY_SIZE(f2fs_encoding_map); i++)
if (!strcmp(string, f2fs_encoding_map[i].name))
return f2fs_encoding_map[i].encoding_magic;
return -EINVAL;
}
int f2fs_get_encoding_flags(int encoding)
{
int i;
for (i = 0 ; i < ARRAY_SIZE(f2fs_encoding_map); i++)
if (f2fs_encoding_map[i].encoding_magic == encoding)
return f2fs_encoding_map[encoding].default_flags;
return 0;
}
int f2fs_str2encoding_flags(char **param, __u16 *flags)
{
char *f = strtok(*param, ",");
const struct enc_flags *fl;
int i, neg = 0;
while (f) {
neg = 0;
if (!strncmp("no", f, 2)) {
neg = 1;
f += 2;
}
for (i = 0; i < ARRAY_SIZE(encoding_flags); i++) {
fl = &encoding_flags[i];
if (!strcmp(fl->param, f)) {
if (neg) {
MSG(0, "Sub %s\n", fl->param);
*flags &= ~fl->flag;
} else {
MSG(0, "Add %s\n", fl->param);
*flags |= fl->flag;
}
goto next_flag;
}
}
*param = f;
return -EINVAL;
next_flag:
f = strtok(NULL, ":");
}
return 0;
}

936
lib/nls_utf8.c Normal file
View File

@ -0,0 +1,936 @@
/*
* Copyright (c) 2014 SGI.
* Copyright (c) 2018 Collabora Ltd.
* 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 adapted from the Linux Kernel. We have a
* userspace version here such that the hashes will match that
* implementation.
*/
#include "config.h"
#include <stdint.h>
#include <unistd.h>
#include <string.h>
#include <limits.h>
#include <errno.h>
#include "f2fs_fs.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)))
/* 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);
struct utf8data {
unsigned int maxage;
unsigned int offset;
};
#define __INCLUDED_FROM_UTF8NORM_C__
#include "utf8data.h"
#undef __INCLUDED_FROM_UTF8NORM_C__
#define ARRAY_SIZE(array) \
(sizeof(array) / sizeof(array[0]))
#if 0
/* Highest unicode version supported by the data tables. */
static int utf8version_is_supported(uint8_t maj, uint8_t min, uint8_t rev)
{
int i = ARRAY_SIZE(utf8agetab) - 1;
unsigned int sb_utf8version = UNICODE_AGE(maj, min, rev);
while (i >= 0 && utf8agetab[i] != 0) {
if (sb_utf8version == utf8agetab[i])
return 1;
i--;
}
return 0;
}
#endif
#if 0
static int utf8version_latest(void)
{
return utf8vers;
}
#endif
/*
* UTF-8 valid ranges.
*
* The UTF-8 encoding spreads the bits of a 32bit word over several
* bytes. This table gives the ranges that can be held and how they'd
* be represented.
*
* 0x00000000 0x0000007F: 0xxxxxxx
* 0x00000000 0x000007FF: 110xxxxx 10xxxxxx
* 0x00000000 0x0000FFFF: 1110xxxx 10xxxxxx 10xxxxxx
* 0x00000000 0x001FFFFF: 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
* 0x00000000 0x03FFFFFF: 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
* 0x00000000 0x7FFFFFFF: 1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
*
* There is an additional requirement on UTF-8, in that only the
* shortest representation of a 32bit value is to be used. A decoder
* must not decode sequences that do not satisfy this requirement.
* Thus the allowed ranges have a lower bound.
*
* 0x00000000 0x0000007F: 0xxxxxxx
* 0x00000080 0x000007FF: 110xxxxx 10xxxxxx
* 0x00000800 0x0000FFFF: 1110xxxx 10xxxxxx 10xxxxxx
* 0x00010000 0x001FFFFF: 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
* 0x00200000 0x03FFFFFF: 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
* 0x04000000 0x7FFFFFFF: 1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
*
* Actual unicode characters are limited to the range 0x0 - 0x10FFFF,
* 17 planes of 65536 values. This limits the sequences actually seen
* even more, to just the following.
*
* 0 - 0x7F: 0 - 0x7F
* 0x80 - 0x7FF: 0xC2 0x80 - 0xDF 0xBF
* 0x800 - 0xFFFF: 0xE0 0xA0 0x80 - 0xEF 0xBF 0xBF
* 0x10000 - 0x10FFFF: 0xF0 0x90 0x80 0x80 - 0xF4 0x8F 0xBF 0xBF
*
* Within those ranges the surrogates 0xD800 - 0xDFFF are not allowed.
*
* Note that the longest sequence seen with valid usage is 4 bytes,
* the same a single UTF-32 character. This makes the UTF-8
* representation of Unicode strictly smaller than UTF-32.
*
* The shortest sequence requirement was introduced by:
* Corrigendum #1: UTF-8 Shortest Form
* It can be found here:
* http://www.unicode.org/versions/corrigendum1.html
*
*/
/*
* Return the number of bytes used by the current UTF-8 sequence.
* Assumes the input points to the first byte of a valid UTF-8
* sequence.
*/
static inline int utf8clen(const char *s)
{
unsigned char c = *s;
return 1 + (c >= 0xC0) + (c >= 0xE0) + (c >= 0xF0);
}
/*
* Decode a 3-byte UTF-8 sequence.
*/
static unsigned int
utf8decode3(const char *str)
{
unsigned int uc;
uc = *str++ & 0x0F;
uc <<= 6;
uc |= *str++ & 0x3F;
uc <<= 6;
uc |= *str++ & 0x3F;
return uc;
}
/*
* Encode a 3-byte UTF-8 sequence.
*/
static int
utf8encode3(char *str, unsigned int val)
{
str[2] = (val & 0x3F) | 0x80;
val >>= 6;
str[1] = (val & 0x3F) | 0x80;
val >>= 6;
str[0] = val | 0xE0;
return 3;
}
/*
* utf8trie_t
*
* A compact binary tree, used to decode UTF-8 characters.
*
* Internal nodes are one byte for the node itself, and up to three
* bytes for an offset into the tree. The first byte contains the
* following information:
* NEXTBYTE - flag - advance to next byte if set
* BITNUM - 3 bit field - the bit number to tested
* OFFLEN - 2 bit field - number of bytes in the offset
* if offlen == 0 (non-branching node)
* RIGHTPATH - 1 bit field - set if the following node is for the
* right-hand path (tested bit is set)
* TRIENODE - 1 bit field - set if the following node is an internal
* node, otherwise it is a leaf node
* if offlen != 0 (branching node)
* LEFTNODE - 1 bit field - set if the left-hand node is internal
* RIGHTNODE - 1 bit field - set if the right-hand node is internal
*
* Due to the way utf8 works, there cannot be branching nodes with
* NEXTBYTE set, and moreover those nodes always have a righthand
* descendant.
*/
typedef const unsigned char utf8trie_t;
#define BITNUM 0x07
#define NEXTBYTE 0x08
#define OFFLEN 0x30
#define OFFLEN_SHIFT 4
#define RIGHTPATH 0x40
#define TRIENODE 0x80
#define RIGHTNODE 0x40
#define LEFTNODE 0x80
/*
* utf8leaf_t
*
* The leaves of the trie are embedded in the trie, and so the same
* underlying datatype: unsigned char.
*
* leaf[0]: The unicode version, stored as a generation number that is
* an index into utf8agetab[]. With this we can filter code
* points based on the unicode version in which they were
* defined. The CCC of a non-defined code point is 0.
* leaf[1]: Canonical Combining Class. During normalization, we need
* to do a stable sort into ascending order of all characters
* with a non-zero CCC that occur between two characters with
* a CCC of 0, or at the begin or end of a string.
* The unicode standard guarantees that all CCC values are
* between 0 and 254 inclusive, which leaves 255 available as
* a special value.
* Code points with CCC 0 are known as stoppers.
* leaf[2]: Decomposition. If leaf[1] == 255, then leaf[2] is the
* start of a NUL-terminated string that is the decomposition
* of the character.
* The CCC of a decomposable character is the same as the CCC
* of the first character of its decomposition.
* Some characters decompose as the empty string: these are
* characters with the Default_Ignorable_Code_Point property.
* These do affect normalization, as they all have CCC 0.
*
* The decompositions in the trie have been fully expanded, with the
* exception of Hangul syllables, which are decomposed algorithmically.
*
* Casefolding, if applicable, is also done using decompositions.
*
* The trie is constructed in such a way that leaves exist for all
* UTF-8 sequences that match the criteria from the "UTF-8 valid
* ranges" comment above, and only for those sequences. Therefore a
* lookup in the trie can be used to validate the UTF-8 input.
*/
typedef const unsigned char utf8leaf_t;
#define LEAF_GEN(LEAF) ((LEAF)[0])
#define LEAF_CCC(LEAF) ((LEAF)[1])
#define LEAF_STR(LEAF) ((const char *)((LEAF) + 2))
#define MINCCC (0)
#define MAXCCC (254)
#define STOPPER (0)
#define DECOMPOSE (255)
/* Marker for hangul syllable decomposition. */
#define HANGUL ((char)(255))
/* Size of the synthesized leaf used for Hangul syllable decomposition. */
#define UTF8HANGULLEAF (12)
/*
* Hangul decomposition (algorithm from Section 3.12 of Unicode 6.3.0)
*
* AC00;<Hangul Syllable, First>;Lo;0;L;;;;;N;;;;;
* D7A3;<Hangul Syllable, Last>;Lo;0;L;;;;;N;;;;;
*
* SBase = 0xAC00
* LBase = 0x1100
* VBase = 0x1161
* TBase = 0x11A7
* LCount = 19
* VCount = 21
* TCount = 28
* NCount = 588 (VCount * TCount)
* SCount = 11172 (LCount * NCount)
*
* Decomposition:
* SIndex = s - SBase
*
* LV (Canonical/Full)
* LIndex = SIndex / NCount
* VIndex = (Sindex % NCount) / TCount
* LPart = LBase + LIndex
* VPart = VBase + VIndex
*
* LVT (Canonical)
* LVIndex = (SIndex / TCount) * TCount
* TIndex = (Sindex % TCount)
* LVPart = SBase + LVIndex
* TPart = TBase + TIndex
*
* LVT (Full)
* LIndex = SIndex / NCount
* VIndex = (Sindex % NCount) / TCount
* TIndex = (Sindex % TCount)
* LPart = LBase + LIndex
* VPart = VBase + VIndex
* if (TIndex == 0) {
* d = <LPart, VPart>
* } else {
* TPart = TBase + TIndex
* d = <LPart, TPart, VPart>
* }
*/
/* Constants */
#define SB (0xAC00)
#define LB (0x1100)
#define VB (0x1161)
#define TB (0x11A7)
#define LC (19)
#define VC (21)
#define TC (28)
#define NC (VC * TC)
#define SC (LC * NC)
/* Algorithmic decomposition of hangul syllable. */
static utf8leaf_t *
utf8hangul(const char *str, unsigned char *hangul)
{
unsigned int si;
unsigned int li;
unsigned int vi;
unsigned int ti;
unsigned char *h;
/* Calculate the SI, LI, VI, and TI values. */
si = utf8decode3(str) - SB;
li = si / NC;
vi = (si % NC) / TC;
ti = si % TC;
/* Fill in base of leaf. */
h = hangul;
LEAF_GEN(h) = 2;
LEAF_CCC(h) = DECOMPOSE;
h += 2;
/* Add LPart, a 3-byte UTF-8 sequence. */
h += utf8encode3((char *)h, li + LB);
/* Add VPart, a 3-byte UTF-8 sequence. */
h += utf8encode3((char *)h, vi + VB);
/* Add TPart if required, also a 3-byte UTF-8 sequence. */
if (ti)
h += utf8encode3((char *)h, ti + TB);
/* Terminate string. */
h[0] = '\0';
return hangul;
}
/*
* Use trie to scan s, touching at most len bytes.
* Returns the leaf if one exists, NULL otherwise.
*
* A non-NULL return guarantees that the UTF-8 sequence starting at s
* is well-formed and corresponds to a known unicode code point. The
* shorthand for this will be "is valid UTF-8 unicode".
*/
static utf8leaf_t *utf8nlookup(const struct utf8data *data,
unsigned char *hangul, const char *s, size_t len)
{
utf8trie_t *trie;
int offlen;
int offset;
int mask;
int node;
if (!data)
return NULL;
if (len == 0)
return NULL;
trie = utf8data + data->offset;
node = 1;
while (node) {
offlen = (*trie & OFFLEN) >> OFFLEN_SHIFT;
if (*trie & NEXTBYTE) {
if (--len == 0)
return NULL;
s++;
}
mask = 1 << (*trie & BITNUM);
if (*s & mask) {
/* Right leg */
if (offlen) {
/* Right node at offset of trie */
node = (*trie & RIGHTNODE);
offset = trie[offlen];
while (--offlen) {
offset <<= 8;
offset |= trie[offlen];
}
trie += offset;
} else if (*trie & RIGHTPATH) {
/* Right node after this node */
node = (*trie & TRIENODE);
trie++;
} else {
/* No right node. */
return NULL;
}
} else {
/* Left leg */
if (offlen) {
/* Left node after this node. */
node = (*trie & LEFTNODE);
trie += offlen + 1;
} else if (*trie & RIGHTPATH) {
/* No left node. */
return NULL;
} else {
/* Left node after this node */
node = (*trie & TRIENODE);
trie++;
}
}
}
/*
* Hangul decomposition is done algorithmically. These are the
* codepoints >= 0xAC00 and <= 0xD7A3. Their UTF-8 encoding is
* always 3 bytes long, so s has been advanced twice, and the
* start of the sequence is at s-2.
*/
if (LEAF_CCC(trie) == DECOMPOSE && LEAF_STR(trie)[0] == HANGUL)
trie = utf8hangul(s - 2, hangul);
return trie;
}
/*
* Use trie to scan s.
* Returns the leaf if one exists, NULL otherwise.
*
* Forwards to utf8nlookup().
*/
static utf8leaf_t *utf8lookup(const struct utf8data *data,
unsigned char *hangul, const char *s)
{
return utf8nlookup(data, hangul, s, (size_t)-1);
}
#if 0
/*
* Maximum age of any character in s.
* Return -1 if s is not valid UTF-8 unicode.
* Return 0 if only non-assigned code points are used.
*/
static int utf8agemax(const struct utf8data *data, const char *s)
{
utf8leaf_t *leaf;
int age = 0;
int leaf_age;
unsigned char hangul[UTF8HANGULLEAF];
if (!data)
return -1;
while (*s) {
leaf = utf8lookup(data, hangul, s);
if (!leaf)
return -1;
leaf_age = utf8agetab[LEAF_GEN(leaf)];
if (leaf_age <= data->maxage && leaf_age > age)
age = leaf_age;
s += utf8clen(s);
}
return age;
}
#endif
#if 0
/*
* Minimum age of any character in s.
* Return -1 if s is not valid UTF-8 unicode.
* Return 0 if non-assigned code points are used.
*/
static int utf8agemin(const struct utf8data *data, const char *s)
{
utf8leaf_t *leaf;
int age;
int leaf_age;
unsigned char hangul[UTF8HANGULLEAF];
if (!data)
return -1;
age = data->maxage;
while (*s) {
leaf = utf8lookup(data, hangul, s);
if (!leaf)
return -1;
leaf_age = utf8agetab[LEAF_GEN(leaf)];
if (leaf_age <= data->maxage && leaf_age < age)
age = leaf_age;
s += utf8clen(s);
}
return age;
}
#endif
#if 0
/*
* Maximum age of any character in s, touch at most len bytes.
* Return -1 if s is not valid UTF-8 unicode.
*/
static int utf8nagemax(const struct utf8data *data, const char *s, size_t len)
{
utf8leaf_t *leaf;
int age = 0;
int leaf_age;
unsigned char hangul[UTF8HANGULLEAF];
if (!data)
return -1;
while (len && *s) {
leaf = utf8nlookup(data, hangul, s, len);
if (!leaf)
return -1;
leaf_age = utf8agetab[LEAF_GEN(leaf)];
if (leaf_age <= data->maxage && leaf_age > age)
age = leaf_age;
len -= utf8clen(s);
s += utf8clen(s);
}
return age;
}
#endif
#if 0
/*
* Maximum age of any character in s, touch at most len bytes.
* Return -1 if s is not valid UTF-8 unicode.
*/
static int utf8nagemin(const struct utf8data *data, const char *s, size_t len)
{
utf8leaf_t *leaf;
int leaf_age;
int age;
unsigned char hangul[UTF8HANGULLEAF];
if (!data)
return -1;
age = data->maxage;
while (len && *s) {
leaf = utf8nlookup(data, hangul, s, len);
if (!leaf)
return -1;
leaf_age = utf8agetab[LEAF_GEN(leaf)];
if (leaf_age <= data->maxage && leaf_age < age)
age = leaf_age;
len -= utf8clen(s);
s += utf8clen(s);
}
return age;
}
#endif
#if 0
/*
* 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.
*/
static 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;
}
#endif
#if 0
/*
* Length of the normalization of s, touch at most len bytes.
* Return -1 if s is not valid UTF-8 unicode.
*/
static ssize_t utf8nlen(const struct utf8data *data, const char *s, size_t len)
{
utf8leaf_t *leaf;
size_t ret = 0;
unsigned char hangul[UTF8HANGULLEAF];
if (!data)
return -1;
while (len && *s) {
leaf = utf8nlookup(data, hangul, s, len);
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);
len -= utf8clen(s);
s += utf8clen(s);
}
return ret;
}
#endif
/*
* Set up an utf8cursor for use by utf8byte().
*
* u8c : pointer to cursor.
* data : const struct utf8data to use for normalization.
* s : string.
* len : length of s.
*
* Returns -1 on error, 0 on success.
*/
static int utf8ncursor(struct utf8cursor *u8c, const struct utf8data *data,
const char *s, size_t len)
{
if (!data)
return -1;
if (!s)
return -1;
u8c->data = data;
u8c->s = s;
u8c->p = NULL;
u8c->ss = NULL;
u8c->sp = NULL;
u8c->len = len;
u8c->slen = 0;
u8c->ccc = STOPPER;
u8c->nccc = STOPPER;
/* Check we didn't clobber the maximum length. */
if (u8c->len != len)
return -1;
/* The first byte of s may not be an utf8 continuation. */
if (len > 0 && (*s & 0xC0) == 0x80)
return -1;
return 0;
}
#if 0
/*
* Set up an utf8cursor for use by utf8byte().
*
* u8c : pointer to cursor.
* data : const struct utf8data to use for normalization.
* s : NUL-terminated string.
*
* Returns -1 on error, 0 on success.
*/
static int utf8cursor(struct utf8cursor *u8c, const struct utf8data *data,
const char *s)
{
return utf8ncursor(u8c, data, s, (unsigned int)-1);
}
#endif
/*
* Get one byte from the normalized form of the string described by u8c.
*
* Returns the byte cast to an unsigned char on succes, and -1 on failure.
*
* The cursor keeps track of the location in the string in u8c->s.
* When a character is decomposed, the current location is stored in
* u8c->p, and u8c->s is set to the start of the decomposition. Note
* that bytes from a decomposition do not count against u8c->len.
*
* Characters are emitted if they match the current CCC in u8c->ccc.
* Hitting end-of-string while u8c->ccc == STOPPER means we're done,
* and the function returns 0 in that case.
*
* Sorting by CCC is done by repeatedly scanning the string. The
* values of u8c->s and u8c->p are stored in u8c->ss and u8c->sp at
* the start of the scan. The first pass finds the lowest CCC to be
* emitted and stores it in u8c->nccc, the second pass emits the
* characters with this CCC and finds the next lowest CCC. This limits
* the number of passes to 1 + the number of different CCCs in the
* sequence being scanned.
*
* Therefore:
* u8c->p != NULL -> a decomposition is being scanned.
* u8c->ss != NULL -> this is a repeating scan.
* u8c->ccc == -1 -> this is the first scan of a repeating scan.
*/
static int utf8byte(struct utf8cursor *u8c)
{
utf8leaf_t *leaf;
int ccc;
for (;;) {
/* Check for the end of a decomposed character. */
if (u8c->p && *u8c->s == '\0') {
u8c->s = u8c->p;
u8c->p = NULL;
}
/* Check for end-of-string. */
if (!u8c->p && (u8c->len == 0 || *u8c->s == '\0')) {
/* There is no next byte. */
if (u8c->ccc == STOPPER)
return 0;
/* End-of-string during a scan counts as a stopper. */
ccc = STOPPER;
goto ccc_mismatch;
} else if ((*u8c->s & 0xC0) == 0x80) {
/* This is a continuation of the current character. */
if (!u8c->p)
u8c->len--;
return (unsigned char)*u8c->s++;
}
/* Look up the data for the current character. */
if (u8c->p) {
leaf = utf8lookup(u8c->data, u8c->hangul, u8c->s);
} else {
leaf = utf8nlookup(u8c->data, u8c->hangul,
u8c->s, u8c->len);
}
/* No leaf found implies that the input is a binary blob. */
if (!leaf)
return -1;
ccc = LEAF_CCC(leaf);
/* Characters that are too new have CCC 0. */
if (utf8agetab[LEAF_GEN(leaf)] > u8c->data->maxage) {
ccc = STOPPER;
} else if (ccc == DECOMPOSE) {
u8c->len -= utf8clen(u8c->s);
u8c->p = u8c->s + utf8clen(u8c->s);
u8c->s = LEAF_STR(leaf);
/* Empty decomposition implies CCC 0. */
if (*u8c->s == '\0') {
if (u8c->ccc == STOPPER)
continue;
ccc = STOPPER;
goto ccc_mismatch;
}
leaf = utf8lookup(u8c->data, u8c->hangul, u8c->s);
if (!leaf)
return -1;
ccc = LEAF_CCC(leaf);
}
/*
* If this is not a stopper, then see if it updates
* the next canonical class to be emitted.
*/
if (ccc != STOPPER && u8c->ccc < ccc && ccc < u8c->nccc)
u8c->nccc = ccc;
/*
* Return the current byte if this is the current
* combining class.
*/
if (ccc == u8c->ccc) {
if (!u8c->p)
u8c->len--;
return (unsigned char)*u8c->s++;
}
/* Current combining class mismatch. */
ccc_mismatch:
if (u8c->nccc == STOPPER) {
/*
* Scan forward for the first canonical class
* to be emitted. Save the position from
* which to restart.
*/
u8c->ccc = MINCCC - 1;
u8c->nccc = ccc;
u8c->sp = u8c->p;
u8c->ss = u8c->s;
u8c->slen = u8c->len;
if (!u8c->p)
u8c->len -= utf8clen(u8c->s);
u8c->s += utf8clen(u8c->s);
} else if (ccc != STOPPER) {
/* Not a stopper, and not the ccc we're emitting. */
if (!u8c->p)
u8c->len -= utf8clen(u8c->s);
u8c->s += utf8clen(u8c->s);
} else if (u8c->nccc != MAXCCC + 1) {
/* At a stopper, restart for next ccc. */
u8c->ccc = u8c->nccc;
u8c->nccc = MAXCCC + 1;
u8c->s = u8c->ss;
u8c->p = u8c->sp;
u8c->len = u8c->slen;
} else {
/* All done, proceed from here. */
u8c->ccc = STOPPER;
u8c->nccc = STOPPER;
u8c->sp = NULL;
u8c->ss = NULL;
u8c->slen = 0;
}
}
}
#if 0
/*
* 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).
*/
static const struct utf8data *utf8nfdi(unsigned int maxage)
{
int i = ARRAY_SIZE(utf8nfdidata) - 1;
while (maxage < utf8nfdidata[i].maxage)
i--;
if (maxage > utf8nfdidata[i].maxage)
return NULL;
return &utf8nfdidata[i];
}
#endif
static const struct utf8data *utf8nfdicf(unsigned int maxage)
{
int i = ARRAY_SIZE(utf8nfdicfdata) - 1;
while (maxage < utf8nfdicfdata[i].maxage)
i--;
if (maxage > utf8nfdicfdata[i].maxage)
return NULL;
return &utf8nfdicfdata[i];
}
static int utf8_casefold(const struct f2fs_nls_table *table,
const unsigned char *str, size_t len,
unsigned char *dest, size_t dlen)
{
const struct utf8data *data = utf8nfdicf(table->version);
struct utf8cursor cur;
size_t nlen = 0;
if (utf8ncursor(&cur, data, (const char *) str, len) < 0)
goto invalid_seq;
for (nlen = 0; nlen < dlen; nlen++) {
int c = utf8byte(&cur);
dest[nlen] = c;
if (!c)
return nlen;
if (c == -1)
break;
}
return -ENAMETOOLONG;
invalid_seq:
if (dlen < len)
return -ENAMETOOLONG;
/* Signal invalid sequence */
return -EINVAL;
}
static const struct f2fs_nls_ops utf8_ops = {
.casefold = utf8_casefold,
};
static const struct f2fs_nls_table nls_utf8 = {
.ops = &utf8_ops,
.version = UNICODE_AGE(12, 1, 0),
};
const struct f2fs_nls_table *f2fs_load_nls_table(int encoding)
{
if (encoding == F2FS_ENC_UTF8_12_1)
return &nls_utf8;
return NULL;
}

4109
lib/utf8data.h Normal file
View File

File diff suppressed because it is too large Load Diff

11
mkfs/f2fs_format.c
View File

@ -516,6 +516,15 @@ static int f2fs_prepare_super_block(void)
memcpy(sb->version, c.version, VERSION_LEN);
memcpy(sb->init_version, c.version, VERSION_LEN);
if (c.feature & cpu_to_le32(F2FS_FEATURE_CASEFOLD)) {
if (c.feature & cpu_to_le32(F2FS_FEATURE_ENCRYPT)) {
MSG(0, "\tError: Casefolding and encryption are not compatible\n");
return -1;
}
set_sb(s_encoding, c.s_encoding);
set_sb(s_encoding_flags, c.s_encoding_flags);
}
sb->feature = c.feature;
if (get_sb(feature) & F2FS_FEATURE_SB_CHKSUM) {
@ -1548,7 +1557,7 @@ static int f2fs_add_default_dentry_root(void)
if (c.lpf_ino) {
int len = strlen(LPF);
f2fs_hash_t hash = f2fs_dentry_hash((unsigned char *)LPF, len);
f2fs_hash_t hash = f2fs_dentry_hash(0, 0, (unsigned char *)LPF, len);
dent_blk->dentry[2].hash_code = cpu_to_le32(hash);
dent_blk->dentry[2].ino = cpu_to_le32(c.lpf_ino);

21
mkfs/f2fs_format_main.c
View File

@ -64,6 +64,7 @@ static void mkfs_usage()
MSG(0, " -z # of sections per zone [default:1]\n");
MSG(0, " -V print the version number and exit\n");
MSG(0, "sectors: number of sectors. [default: determined by device size]\n");
MSG(0, " -C [encoding:flag1,flag2] Support casefolding with optional flags\n");
exit(1);
}
@ -107,8 +108,10 @@ static void add_default_options(void)
static void f2fs_parse_options(int argc, char *argv[])
{
static const char *option_string = "qa:c:d:e:E:g:il:mo:O:R:s:S:z:t:fw:V";
static const char *option_string = "qa:c:C:d:e:E:g:il:mo:O:R:s:S:z:t:Vfw:";
int32_t option=0;
int val;
char *token;
while ((option = getopt(argc,argv,option_string)) != EOF) {
switch (option) {
@ -192,6 +195,22 @@ static void f2fs_parse_options(int argc, char *argv[])
case 'V':
show_version("mkfs.f2fs");
exit(0);
case 'C':
token = strtok(optarg, ":");
val = f2fs_str2encoding(token);
if (val < 0) {
MSG(0, "\tError: Unknown encoding %s\n", token);
mkfs_usage();
}
c.s_encoding = val;
token = strtok(NULL, "");
val = f2fs_str2encoding_flags(&token, &c.s_encoding_flags);
if (val) {
MSG(0, "\tError: Unknown flag %s\n",token);
mkfs_usage();
}
c.feature |= cpu_to_le32(F2FS_FEATURE_CASEFOLD);
break;
default:
MSG(0, "\tError: Unknown option %c\n",option);
mkfs_usage();

1
tools/fibmap.c
View File

@ -25,6 +25,7 @@
#include <sys/types.h>
#include <sys/ioctl.h>
#include <sys/stat.h>
#include <sys/sysmacros.h>
#ifdef HAVE_SYS_SYSMACROS_H
#include <sys/sysmacros.h>
#endif