1 /*
2 * Regular Expression Engine
3 *
4 * Copyright (c) 2017-2018 Fabrice Bellard
5 *
6 * Permission is hereby granted, free of charge, to any person obtaining a copy
7 * of this software and associated documentation files (the "Software"), to deal
8 * in the Software without restriction, including without limitation the rights
9 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
10 * copies of the Software, and to permit persons to whom the Software is
11 * furnished to do so, subject to the following conditions:
12 *
13 * The above copyright notice and this permission notice shall be included in
14 * all copies or substantial portions of the Software.
15 *
16 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
17 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
18 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
19 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
20 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
21 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
22 * THE SOFTWARE.
23 */
24 #ifndef LIBREGEXP_H
25 #define LIBREGEXP_H
26
27 #include <stddef.h>
28
29 #include "libunicode.h"
30
31 #define LRE_BOOL int /* for documentation purposes */
32
33 #define LRE_FLAG_GLOBAL (1 << 0)
34 #define LRE_FLAG_IGNORECASE (1 << 1)
35 #define LRE_FLAG_MULTILINE (1 << 2)
36 #define LRE_FLAG_DOTALL (1 << 3)
37 #define LRE_FLAG_UTF16 (1 << 4)
38 #define LRE_FLAG_STICKY (1 << 5)
39
40 #define LRE_FLAG_NAMED_GROUPS (1 << 7) /* named groups are present in the regexp */
41
42 uint8_t *lre_compile(int *plen, char *error_msg, int error_msg_size,
43 const char *buf, size_t buf_len, int re_flags,
44 void *opaque);
45 int lre_get_capture_count(const uint8_t *bc_buf);
46 int lre_get_flags(const uint8_t *bc_buf);
47 const char *lre_get_groupnames(const uint8_t *bc_buf);
48 int lre_exec(uint8_t **capture,
49 const uint8_t *bc_buf, const uint8_t *cbuf, int cindex, int clen,
50 int cbuf_type, void *opaque);
51
52 int lre_parse_escape(const uint8_t **pp, int allow_utf16);
53 LRE_BOOL lre_is_space(int c);
54
55 /* must be provided by the user */
56 LRE_BOOL lre_check_stack_overflow(void *opaque, size_t alloca_size);
57 void *lre_realloc(void *opaque, void *ptr, size_t size);
58
59 /* JS identifier test */
60 extern uint32_t const lre_id_start_table_ascii[4];
61 extern uint32_t const lre_id_continue_table_ascii[4];
62
lre_js_is_ident_first(int c)63 static inline int lre_js_is_ident_first(int c)
64 {
65 if ((uint32_t)c < 128) {
66 return (lre_id_start_table_ascii[c >> 5] >> (c & 31)) & 1;
67 } else {
68 #ifdef CONFIG_ALL_UNICODE
69 return lre_is_id_start(c);
70 #else
71 return !lre_is_space(c);
72 #endif
73 }
74 }
75
lre_js_is_ident_next(int c)76 static inline int lre_js_is_ident_next(int c)
77 {
78 if ((uint32_t)c < 128) {
79 return (lre_id_continue_table_ascii[c >> 5] >> (c & 31)) & 1;
80 } else {
81 /* ZWNJ and ZWJ are accepted in identifiers */
82 #ifdef CONFIG_ALL_UNICODE
83 return lre_is_id_continue(c) || c == 0x200C || c == 0x200D;
84 #else
85 return !lre_is_space(c) || c == 0x200C || c == 0x200D;
86 #endif
87 }
88 }
89
90 #undef LRE_BOOL
91
92 #endif /* LIBREGEXP_H */
93