1 /* 2 tre-internal.h - TRE internal definitions 3 4 Copyright (c) 2001-2009 Ville Laurikari <vl@iki.fi> 5 All rights reserved. 6 7 Redistribution and use in source and binary forms, with or without 8 modification, are permitted provided that the following conditions 9 are met: 10 11 1. Redistributions of source code must retain the above copyright 12 notice, this list of conditions and the following disclaimer. 13 14 2. Redistributions in binary form must reproduce the above copyright 15 notice, this list of conditions and the following disclaimer in the 16 documentation and/or other materials provided with the distribution. 17 18 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDER AND CONTRIBUTORS 19 ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT 20 LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR 21 A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT 22 HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, 23 SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT 24 LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, 25 DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY 26 THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT 27 (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE 28 OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 29 30 */ 31 32 #include <regex.h> 33 #include <wchar.h> 34 #include <wctype.h> 35 #include "../include/features.h" 36 37 #undef TRE_MBSTATE 38 39 #define NDEBUG 40 41 #define TRE_REGEX_T_FIELD __opaque 42 typedef int reg_errcode_t; 43 44 typedef wchar_t tre_char_t; 45 46 #define DPRINT(msg) do { } while(0) 47 48 #define elementsof(x) ( sizeof(x) / sizeof(x[0]) ) 49 50 #define tre_mbrtowc(pwc, s, n, ps) (mbtowc((pwc), (s), (n))) 51 52 /* Wide characters. */ 53 typedef wint_t tre_cint_t; 54 #define TRE_CHAR_MAX 0x10ffff 55 56 #define tre_isalnum iswalnum 57 #define tre_isalpha iswalpha 58 #define tre_isblank iswblank 59 #define tre_iscntrl iswcntrl 60 #define tre_isdigit iswdigit 61 #define tre_isgraph iswgraph 62 #define tre_islower iswlower 63 #define tre_isprint iswprint 64 #define tre_ispunct iswpunct 65 #define tre_isspace iswspace 66 #define tre_isupper iswupper 67 #define tre_isxdigit iswxdigit 68 69 #define tre_tolower towlower 70 #define tre_toupper towupper 71 #define tre_strlen wcslen 72 73 /* Use system provided iswctype() and wctype(). */ 74 typedef wctype_t tre_ctype_t; 75 #define tre_isctype iswctype 76 #define tre_ctype wctype 77 78 /* Returns number of bytes to add to (char *)ptr to make it 79 properly aligned for the type. */ 80 #undef ALIGN 81 #define ALIGN(ptr, type) \ 82 ((((long)ptr) % sizeof(type)) \ 83 ? (sizeof(type) - (((long)ptr) % sizeof(type))) \ 84 : 0) 85 86 #undef MAX 87 #undef MIN 88 #define MAX(a, b) (((a) >= (b)) ? (a) : (b)) 89 #define MIN(a, b) (((a) <= (b)) ? (a) : (b)) 90 91 /* TNFA transition type. A TNFA state is an array of transitions, 92 the terminator is a transition with NULL `state'. */ 93 typedef struct tnfa_transition tre_tnfa_transition_t; 94 95 struct tnfa_transition { 96 /* Range of accepted characters. */ 97 tre_cint_t code_min; 98 tre_cint_t code_max; 99 /* Pointer to the destination state. */ 100 tre_tnfa_transition_t *state; 101 /* ID number of the destination state. */ 102 int state_id; 103 /* -1 terminated array of tags (or NULL). */ 104 int *tags; 105 /* Assertion bitmap. */ 106 int assertions; 107 /* Assertion parameters. */ 108 union { 109 /* Character class assertion. */ 110 tre_ctype_t class; 111 /* Back reference assertion. */ 112 int backref; 113 } u; 114 /* Negative character class assertions. */ 115 tre_ctype_t *neg_classes; 116 }; 117 118 119 /* Assertions. */ 120 #define ASSERT_AT_BOL 1 /* Beginning of line. */ 121 #define ASSERT_AT_EOL 2 /* End of line. */ 122 #define ASSERT_CHAR_CLASS 4 /* Character class in `class'. */ 123 #define ASSERT_CHAR_CLASS_NEG 8 /* Character classes in `neg_classes'. */ 124 #define ASSERT_AT_BOW 16 /* Beginning of word. */ 125 #define ASSERT_AT_EOW 32 /* End of word. */ 126 #define ASSERT_AT_WB 64 /* Word boundary. */ 127 #define ASSERT_AT_WB_NEG 128 /* Not a word boundary. */ 128 #define ASSERT_BACKREF 256 /* A back reference in `backref'. */ 129 #define ASSERT_LAST 256 130 131 /* Tag directions. */ 132 typedef enum { 133 TRE_TAG_MINIMIZE = 0, 134 TRE_TAG_MAXIMIZE = 1 135 } tre_tag_direction_t; 136 137 /* Instructions to compute submatch register values from tag values 138 after a successful match. */ 139 struct tre_submatch_data { 140 /* Tag that gives the value for rm_so (submatch start offset). */ 141 int so_tag; 142 /* Tag that gives the value for rm_eo (submatch end offset). */ 143 int eo_tag; 144 /* List of submatches this submatch is contained in. */ 145 int *parents; 146 }; 147 148 typedef struct tre_submatch_data tre_submatch_data_t; 149 150 151 /* TNFA definition. */ 152 typedef struct tnfa tre_tnfa_t; 153 154 struct tnfa { 155 tre_tnfa_transition_t *transitions; 156 unsigned int num_transitions; 157 tre_tnfa_transition_t *initial; 158 tre_tnfa_transition_t *final; 159 tre_submatch_data_t *submatch_data; 160 char *firstpos_chars; 161 int first_char; 162 unsigned int num_submatches; 163 tre_tag_direction_t *tag_directions; 164 int *minimal_tags; 165 int num_tags; 166 int num_minimals; 167 int end_tag; 168 int num_states; 169 int cflags; 170 int have_backrefs; 171 int have_approx; 172 }; 173 174 /* from tre-mem.h: */ 175 176 #define TRE_MEM_BLOCK_SIZE 1024 177 178 typedef struct tre_list { 179 void *data; 180 struct tre_list *next; 181 } tre_list_t; 182 183 typedef struct tre_mem_struct { 184 tre_list_t *blocks; 185 tre_list_t *current; 186 char *ptr; 187 size_t n; 188 int failed; 189 void **provided; 190 } *tre_mem_t; 191 192 #define tre_mem_new_impl __tre_mem_new_impl 193 #define tre_mem_alloc_impl __tre_mem_alloc_impl 194 #define tre_mem_destroy __tre_mem_destroy 195 196 hidden tre_mem_t tre_mem_new_impl(int provided, void *provided_block); 197 hidden void *tre_mem_alloc_impl(tre_mem_t mem, int provided, void *provided_block, 198 int zero, size_t size); 199 200 /* Returns a new memory allocator or NULL if out of memory. */ 201 #define tre_mem_new() tre_mem_new_impl(0, NULL) 202 203 /* Allocates a block of `size' bytes from `mem'. Returns a pointer to the 204 allocated block or NULL if an underlying malloc() failed. */ 205 #define tre_mem_alloc(mem, size) tre_mem_alloc_impl(mem, 0, NULL, 0, size) 206 207 /* Allocates a block of `size' bytes from `mem'. Returns a pointer to the 208 allocated block or NULL if an underlying malloc() failed. The memory 209 is set to zero. */ 210 #define tre_mem_calloc(mem, size) tre_mem_alloc_impl(mem, 0, NULL, 1, size) 211 212 #ifdef TRE_USE_ALLOCA 213 /* alloca() versions. Like above, but memory is allocated with alloca() 214 instead of malloc(). */ 215 216 #define tre_mem_newa() \ 217 tre_mem_new_impl(1, alloca(sizeof(struct tre_mem_struct))) 218 219 #define tre_mem_alloca(mem, size) \ 220 ((mem)->n >= (size) \ 221 ? tre_mem_alloc_impl((mem), 1, NULL, 0, (size)) \ 222 : tre_mem_alloc_impl((mem), 1, alloca(TRE_MEM_BLOCK_SIZE), 0, (size))) 223 #endif /* TRE_USE_ALLOCA */ 224 225 226 /* Frees the memory allocator and all memory allocated with it. */ 227 hidden void tre_mem_destroy(tre_mem_t mem); 228 229 #define xmalloc malloc 230 #define xcalloc calloc 231 #define xfree free 232 #define xrealloc realloc 233 234