summaryrefslogtreecommitdiffstats
path: root/fs/unicode/utf8-norm.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/unicode/utf8-norm.c')
-rw-r--r--fs/unicode/utf8-norm.c45
1 files changed, 20 insertions, 25 deletions
diff --git a/fs/unicode/utf8-norm.c b/fs/unicode/utf8-norm.c
index 1ac90fa00070..7c1f28ab31a8 100644
--- a/fs/unicode/utf8-norm.c
+++ b/fs/unicode/utf8-norm.c
@@ -309,21 +309,19 @@ utf8hangul(const char *str, unsigned char *hangul)
* 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)
+static utf8leaf_t *utf8nlookup(const struct unicode_map *um,
+ enum utf8_normalization n, unsigned char *hangul, const char *s,
+ size_t len)
{
- utf8trie_t *trie = NULL;
+ utf8trie_t *trie = utf8data + um->ntab[n]->offset;
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;
@@ -385,29 +383,28 @@ static utf8leaf_t *utf8nlookup(const struct utf8data *data,
*
* Forwards to utf8nlookup().
*/
-static utf8leaf_t *utf8lookup(const struct utf8data *data,
- unsigned char *hangul, const char *s)
+static utf8leaf_t *utf8lookup(const struct unicode_map *um,
+ enum utf8_normalization n, unsigned char *hangul, const char *s)
{
- return utf8nlookup(data, hangul, s, (size_t)-1);
+ return utf8nlookup(um, n, hangul, s, (size_t)-1);
}
/*
* Length of the normalization of s, touch at most len bytes.
* Return -1 if s is not valid UTF-8 unicode.
*/
-ssize_t utf8nlen(const struct utf8data *data, const char *s, size_t len)
+ssize_t utf8nlen(const struct unicode_map *um, enum utf8_normalization n,
+ 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);
+ leaf = utf8nlookup(um, n, hangul, s, len);
if (!leaf)
return -1;
- if (utf8agetab[LEAF_GEN(leaf)] > data->maxage)
+ if (utf8agetab[LEAF_GEN(leaf)] > um->ntab[n]->maxage)
ret += utf8clen(s);
else if (LEAF_CCC(leaf) == DECOMPOSE)
ret += strlen(LEAF_STR(leaf));
@@ -430,14 +427,13 @@ EXPORT_SYMBOL(utf8nlen);
*
* Returns -1 on error, 0 on success.
*/
-int utf8ncursor(struct utf8cursor *u8c, const struct utf8data *data,
- const char *s, size_t len)
+int utf8ncursor(struct utf8cursor *u8c, const struct unicode_map *um,
+ enum utf8_normalization n, const char *s, size_t len)
{
- if (!data)
- return -1;
if (!s)
return -1;
- u8c->data = data;
+ u8c->um = um;
+ u8c->n = n;
u8c->s = s;
u8c->p = NULL;
u8c->ss = NULL;
@@ -512,9 +508,9 @@ int utf8byte(struct utf8cursor *u8c)
/* Look up the data for the current character. */
if (u8c->p) {
- leaf = utf8lookup(u8c->data, u8c->hangul, u8c->s);
+ leaf = utf8lookup(u8c->um, u8c->n, u8c->hangul, u8c->s);
} else {
- leaf = utf8nlookup(u8c->data, u8c->hangul,
+ leaf = utf8nlookup(u8c->um, u8c->n, u8c->hangul,
u8c->s, u8c->len);
}
@@ -524,7 +520,8 @@ int utf8byte(struct utf8cursor *u8c)
ccc = LEAF_CCC(leaf);
/* Characters that are too new have CCC 0. */
- if (utf8agetab[LEAF_GEN(leaf)] > u8c->data->maxage) {
+ if (utf8agetab[LEAF_GEN(leaf)] >
+ u8c->um->ntab[u8c->n]->maxage) {
ccc = STOPPER;
} else if (ccc == DECOMPOSE) {
u8c->len -= utf8clen(u8c->s);
@@ -538,7 +535,7 @@ int utf8byte(struct utf8cursor *u8c)
goto ccc_mismatch;
}
- leaf = utf8lookup(u8c->data, u8c->hangul, u8c->s);
+ leaf = utf8lookup(u8c->um, u8c->n, u8c->hangul, u8c->s);
if (!leaf)
return -1;
ccc = LEAF_CCC(leaf);
@@ -611,7 +608,6 @@ const struct utf8data *utf8nfdi(unsigned int maxage)
return NULL;
return &utf8nfdidata[i];
}
-EXPORT_SYMBOL(utf8nfdi);
const struct utf8data *utf8nfdicf(unsigned int maxage)
{
@@ -623,4 +619,3 @@ const struct utf8data *utf8nfdicf(unsigned int maxage)
return NULL;
return &utf8nfdicfdata[i];
}
-EXPORT_SYMBOL(utf8nfdicf);