/* Extended regular expression matching and search library.
- Copyright (C) 2002-2012 Free Software Foundation, Inc.
+ Copyright (C) 2002-2013 Free Software Foundation, Inc.
This file is part of the GNU C Library.
Contributed by Isamu Hasegawa <isamu@yamato.ibm.com>.
bitset_t sbcset,
re_charset_t *mbcset,
Idx *char_class_alloc,
- const unsigned char *class_name,
+ const char *class_name,
reg_syntax_t syntax);
#else /* not RE_ENABLE_I18N */
static reg_errcode_t build_equiv_class (bitset_t sbcset,
const unsigned char *name);
static reg_errcode_t build_charclass (RE_TRANSLATE_TYPE trans,
bitset_t sbcset,
- const unsigned char *class_name,
+ const char *class_name,
reg_syntax_t syntax);
#endif /* not RE_ENABLE_I18N */
static bin_tree_t *build_charclass_op (re_dfa_t *dfa,
RE_TRANSLATE_TYPE trans,
- const unsigned char *class_name,
- const unsigned char *extra,
+ const char *class_name,
+ const char *extra,
bool non_match, reg_errcode_t *err);
static bin_tree_t *create_tree (re_dfa_t *dfa,
bin_tree_t *left, bin_tree_t *right,
#endif
static inline void
-__attribute ((always_inline))
+__attribute__ ((always_inline))
re_set_fastmap (char *fastmap, bool icase, int ch)
{
fastmap[ch] = 1;
internal_function
init_word_char (re_dfa_t *dfa)
{
- dfa->word_ops_used = 1;
int i = 0;
int j;
int ch = 0;
+ dfa->word_ops_used = 1;
if (BE (dfa->map_notascii == 0, 1))
{
bitset_word_t bits0 = 0x00000000;
case OP_WORD:
case OP_NOTWORD:
tree = build_charclass_op (dfa, regexp->trans,
- (const unsigned char *) "alnum",
- (const unsigned char *) "_",
+ "alnum",
+ "_",
token->type == OP_NOTWORD, err);
if (BE (*err != REG_NOERROR && tree == NULL, 0))
return NULL;
case OP_SPACE:
case OP_NOTSPACE:
tree = build_charclass_op (dfa, regexp->trans,
- (const unsigned char *) "space",
- (const unsigned char *) "",
+ "space",
+ "",
token->type == OP_NOTSPACE, err);
if (BE (*err != REG_NOERROR && tree == NULL, 0))
return NULL;
wchar_t wc;
wint_t start_wc;
wint_t end_wc;
- wchar_t cmp_buf[6] = {L'\0', L'\0', L'\0', L'\0', L'\0', L'\0'};
start_ch = ((start_elem->type == SB_CHAR) ? start_elem->opr.ch
: ((start_elem->type == COLL_SYM) ? start_elem->opr.name[0]
? __btowc (end_ch) : end_elem->opr.wch);
if (start_wc == WEOF || end_wc == WEOF)
return REG_ECOLLATE;
- cmp_buf[0] = start_wc;
- cmp_buf[4] = end_wc;
-
- if (BE ((syntax & RE_NO_EMPTY_RANGES)
- && wcscoll (cmp_buf, cmp_buf + 4) > 0, 0))
+ else if (BE ((syntax & RE_NO_EMPTY_RANGES) && start_wc > end_wc, 0))
return REG_ERANGE;
/* Got valid collation sequence values, add them as a new entry.
/* Build the table for single byte characters. */
for (wc = 0; wc < SBC_MAX; ++wc)
{
- cmp_buf[2] = wc;
- if (wcscoll (cmp_buf, cmp_buf + 2) <= 0
- && wcscoll (cmp_buf + 2, cmp_buf + 4) <= 0)
+ if (start_wc <= wc && wc <= end_wc)
bitset_set (sbcset, wc);
}
}
/* Local function for parse_bracket_exp used in _LIBC environment.
Seek the collating symbol entry corresponding to NAME.
- Return the index of the symbol in the SYMB_TABLE. */
+ Return the index of the symbol in the SYMB_TABLE,
+ or -1 if not found. */
auto inline int32_t
- __attribute ((always_inline))
- seek_collating_symbol_entry (name, name_len)
- const unsigned char *name;
- size_t name_len;
+ __attribute__ ((always_inline))
+ seek_collating_symbol_entry (const unsigned char *name, size_t name_len)
{
- int32_t hash = elem_hash ((const char *) name, name_len);
- int32_t elem = hash % table_size;
- if (symb_table[2 * elem] != 0)
- {
- int32_t second = hash % (table_size - 2) + 1;
-
- do
- {
- /* First compare the hashing value. */
- if (symb_table[2 * elem] == hash
- /* Compare the length of the name. */
- && name_len == extra[symb_table[2 * elem + 1]]
- /* Compare the name. */
- && memcmp (name, &extra[symb_table[2 * elem + 1] + 1],
- name_len) == 0)
- {
- /* Yep, this is the entry. */
- break;
- }
+ int32_t elem;
- /* Next entry. */
- elem += second;
- }
- while (symb_table[2 * elem] != 0);
- }
- return elem;
+ for (elem = 0; elem < table_size; elem++)
+ if (symb_table[2 * elem] != 0)
+ {
+ int32_t idx = symb_table[2 * elem + 1];
+ /* Skip the name of collating element name. */
+ idx += 1 + extra[idx];
+ if (/* Compare the length of the name. */
+ name_len == extra[idx]
+ /* Compare the name. */
+ && memcmp (name, &extra[idx + 1], name_len) == 0)
+ /* Yep, this is the entry. */
+ return elem;
+ }
+ return -1;
}
/* Local function for parse_bracket_exp used in _LIBC environment.
Return the value if succeeded, UINT_MAX otherwise. */
auto inline unsigned int
- __attribute ((always_inline))
- lookup_collation_sequence_value (br_elem)
- bracket_elem_t *br_elem;
+ __attribute__ ((always_inline))
+ lookup_collation_sequence_value (bracket_elem_t *br_elem)
{
if (br_elem->type == SB_CHAR)
{
int32_t elem, idx;
elem = seek_collating_symbol_entry (br_elem->opr.name,
sym_name_len);
- if (symb_table[2 * elem] != 0)
+ if (elem != -1)
{
/* We found the entry. */
idx = symb_table[2 * elem + 1];
/* Return the collation sequence value. */
return *(unsigned int *) (extra + idx);
}
- else if (symb_table[2 * elem] == 0 && sym_name_len == 1)
+ else if (sym_name_len == 1)
{
/* No valid character. Match it as a single byte
character. */
update it. */
auto inline reg_errcode_t
- __attribute ((always_inline))
- build_range_exp (sbcset, mbcset, range_alloc, start_elem, end_elem)
- re_charset_t *mbcset;
- Idx *range_alloc;
- bitset_t sbcset;
- bracket_elem_t *start_elem, *end_elem;
+ __attribute__ ((always_inline))
+ build_range_exp (bitset_t sbcset, re_charset_t *mbcset, int *range_alloc,
+ bracket_elem_t *start_elem, bracket_elem_t *end_elem)
{
unsigned int ch;
uint32_t start_collseq;
0))
return REG_ERANGE;
+ /* FIXME: Implement rational ranges here, too. */
start_collseq = lookup_collation_sequence_value (start_elem);
end_collseq = lookup_collation_sequence_value (end_elem);
/* Check start/end collation sequence values. */
pointer argument since we may update it. */
auto inline reg_errcode_t
- __attribute ((always_inline))
- build_collating_symbol (sbcset, mbcset, coll_sym_alloc, name)
- re_charset_t *mbcset;
- Idx *coll_sym_alloc;
- bitset_t sbcset;
- const unsigned char *name;
+ __attribute__ ((always_inline))
+ build_collating_symbol (bitset_t sbcset, re_charset_t *mbcset,
+ Idx *coll_sym_alloc, const unsigned char *name)
{
int32_t elem, idx;
size_t name_len = strlen ((const char *) name);
if (nrules != 0)
{
elem = seek_collating_symbol_entry (name, name_len);
- if (symb_table[2 * elem] != 0)
+ if (elem != -1)
{
/* We found the entry. */
idx = symb_table[2 * elem + 1];
/* Skip the name of collating element name. */
idx += 1 + extra[idx];
}
- else if (symb_table[2 * elem] == 0 && name_len == 1)
+ else if (name_len == 1)
{
/* No valid character, treat it as a normal
character. */
#ifdef RE_ENABLE_I18N
mbcset, &char_class_alloc,
#endif /* RE_ENABLE_I18N */
- start_elem.opr.name, syntax);
+ (const char *) start_elem.opr.name,
+ syntax);
if (BE (*err != REG_NOERROR, 0))
goto parse_bracket_exp_free_return;
break;
#ifdef RE_ENABLE_I18N
build_charclass (RE_TRANSLATE_TYPE trans, bitset_t sbcset,
re_charset_t *mbcset, Idx *char_class_alloc,
- const unsigned char *class_name, reg_syntax_t syntax)
+ const char *class_name, reg_syntax_t syntax)
#else /* not RE_ENABLE_I18N */
build_charclass (RE_TRANSLATE_TYPE trans, bitset_t sbcset,
- const unsigned char *class_name, reg_syntax_t syntax)
+ const char *class_name, reg_syntax_t syntax)
#endif /* not RE_ENABLE_I18N */
{
int i;
- const char *name = (const char *) class_name;
+ const char *name = class_name;
/* In case of REG_ICASE "upper" and "lower" match the both of
upper and lower cases. */
static bin_tree_t *
build_charclass_op (re_dfa_t *dfa, RE_TRANSLATE_TYPE trans,
- const unsigned char *class_name,
- const unsigned char *extra, bool non_match,
+ const char *class_name,
+ const char *extra, bool non_match,
reg_errcode_t *err)
{
re_bitset_ptr_t sbcset;
projects / gnulib.git / blobdiff