1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409
|
/* $Id: vector.c 6699 2004-04-07 06:47:44Z rra $
**
** Vector handling (counted lists of char *'s).
**
** Written by Russ Allbery <rra@stanford.edu>
** This work is hereby placed in the public domain by its author.
**
** A vector is a table for handling a list of strings with less overhead than
** linked list. The intention is for vectors, once allocated, to be reused;
** this saves on memory allocations once the array of char *'s reaches a
** stable size.
**
** There are two types of vectors. Standard vectors copy strings when
** they're inserted into the vector, whereas cvectors just accept pointers
** to external strings to store. There are therefore two entry points for
** every vector function, one for vectors and one for cvectors.
**
** There's a whole bunch of code duplication here. This would be a lot
** cleaner with C++ features (either inheritance or templates would
** probably help). One could probably in some places just cast a cvector
** to a vector and perform the same operations, but I'm leery of doing that
** as I'm not sure if it's a violation of the C type aliasing rules.
*/
#include "config.h"
#include "clibrary.h"
#include <ctype.h>
#include "inn/vector.h"
#include "libinn.h"
/*
** Allocate a new, empty vector.
*/
struct vector *
vector_new(void)
{
struct vector *vector;
vector = xmalloc(sizeof(struct vector));
vector->count = 0;
vector->allocated = 0;
vector->strings = NULL;
return vector;
}
struct cvector *
cvector_new(void)
{
struct cvector *vector;
vector = xmalloc(sizeof(struct cvector));
vector->count = 0;
vector->allocated = 0;
vector->strings = NULL;
return vector;
}
/*
** Resize a vector (using realloc to resize the table).
*/
void
vector_resize(struct vector *vector, size_t size)
{
size_t i;
if (vector->count > size) {
for (i = size; i < vector->count; i++)
free(vector->strings[i]);
vector->count = size;
}
if (size == 0) {
free(vector->strings);
vector->strings = NULL;
} else {
vector->strings = xrealloc(vector->strings, size * sizeof(char *));
}
vector->allocated = size;
}
void
cvector_resize(struct cvector *vector, size_t size)
{
if (vector->count > size)
vector->count = size;
if (size == 0) {
free(vector->strings);
vector->strings = NULL;
} else {
vector->strings =
xrealloc(vector->strings, size * sizeof(const char *));
}
vector->allocated = size;
}
/*
** Add a new string to the vector, resizing the vector as necessary. The
** vector is resized an element at a time; if a lot of resizes are expected,
** vector_resize should be called explicitly with a more suitable size.
*/
void
vector_add(struct vector *vector, const char *string)
{
size_t next = vector->count;
if (vector->count == vector->allocated)
vector_resize(vector, vector->allocated + 1);
vector->strings[next] = xstrdup(string);
vector->count++;
}
void
cvector_add(struct cvector *vector, const char *string)
{
size_t next = vector->count;
if (vector->count == vector->allocated)
cvector_resize(vector, vector->allocated + 1);
vector->strings[next] = string;
vector->count++;
}
/*
** Empty a vector but keep the allocated memory for the pointer table.
*/
void
vector_clear(struct vector *vector)
{
size_t i;
for (i = 0; i < vector->count; i++)
free(vector->strings[i]);
vector->count = 0;
}
void
cvector_clear(struct cvector *vector)
{
vector->count = 0;
}
/*
** Free a vector completely.
*/
void
vector_free(struct vector *vector)
{
vector_clear(vector);
free(vector->strings);
free(vector);
}
void
cvector_free(struct cvector *vector)
{
cvector_clear(vector);
free(vector->strings);
free(vector);
}
/*
** Given a vector that we may be reusing, clear it out. If the first
** argument is NULL, allocate a new vector. Used by vector_split*.
*/
static struct vector *
vector_reuse(struct vector *vector)
{
if (vector == NULL)
return vector_new();
else {
vector_clear(vector);
return vector;
}
}
static struct cvector *
cvector_reuse(struct cvector *vector)
{
if (vector == NULL)
return cvector_new();
else {
cvector_clear(vector);
return vector;
}
}
/*
** Given a string and a separator character, count the number of strings
** that it will split into.
*/
static size_t
split_count(const char *string, char separator)
{
const char *p;
size_t count;
if (*string == '\0')
return 1;
for (count = 1, p = string; *p; p++)
if (*p == separator)
count++;
return count;
}
/*
** Given a string and a separator character, form a vector by splitting the
** string at those separators. Do a first pass to size the vector, and if
** the third argument isn't NULL, reuse it. Otherwise, allocate a new one.
*/
struct vector *
vector_split(const char *string, char separator, struct vector *vector)
{
const char *p, *start;
size_t i, count;
vector = vector_reuse(vector);
count = split_count(string, separator);
if (vector->allocated < count)
vector_resize(vector, count);
for (start = string, p = string, i = 0; *p; p++)
if (*p == separator) {
vector->strings[i++] = xstrndup(start, p - start);
start = p + 1;
}
vector->strings[i++] = xstrndup(start, p - start);
vector->count = i;
return vector;
}
/*
** Given a modifiable string and a separator character, form a cvector by
** modifying the string in-place to add nuls at the separators and then
** building a vector of pointers into the string. Do a first pass to size
** the vector, and if the third argument isn't NULL, reuse it. Otherwise,
** allocate a new one.
*/
struct cvector *
cvector_split(char *string, char separator, struct cvector *vector)
{
char *p, *start;
size_t i, count;
vector = cvector_reuse(vector);
count = split_count(string, separator);
if (vector->allocated < count)
cvector_resize(vector, count);
for (start = string, p = string, i = 0; *p; p++)
if (*p == separator) {
*p = '\0';
vector->strings[i++] = start;
start = p + 1;
}
vector->strings[i++] = start;
vector->count = i;
return vector;
}
/*
** Given a string, count the number of strings that it will split into when
** splitting on whitespace.
*/
static size_t
split_space_count(const char *string)
{
const char *p;
size_t count;
if (*string == '\0')
return 0;
for (count = 1, p = string + 1; *p != '\0'; p++)
if ((*p == ' ' || *p == '\t') && !(p[-1] == ' ' || p[-1] == '\t'))
count++;
/* If the string ends in whitespace, we've overestimated the number of
strings by one. */
if (p[-1] == ' ' || p[-1] == '\t')
count--;
return count;
}
/*
** Given a string, split it at whitespace to form a vector, copying each
** string segment. If the fourth argument isn't NULL, reuse that vector;
** otherwise, allocate a new one. Any number of consecutive whitespace
** characters is considered a single separator.
*/
struct vector *
vector_split_space(const char *string, struct vector *vector)
{
const char *p, *start;
size_t i, count;
vector = vector_reuse(vector);
count = split_space_count(string);
if (vector->allocated < count)
vector_resize(vector, count);
for (start = string, p = string, i = 0; *p; p++)
if (*p == ' ' || *p == '\t') {
if (start != p)
vector->strings[i++] = xstrndup(start, p - start);
start = p + 1;
}
if (start != p)
vector->strings[i++] = xstrndup(start, p - start);
vector->count = i;
return vector;
}
/*
** Given a string, split it at whitespace to form a vector, destructively
** modifying the string to nul-terminate each segment. If the fourth
** argument isn't NULL, reuse that vector; otherwise, allocate a new one.
** Any number of consecutive whitespace characters is considered a single
** separator.
*/
struct cvector *
cvector_split_space(char *string, struct cvector *vector)
{
char *p, *start;
size_t i, count;
vector = cvector_reuse(vector);
count = split_space_count(string);
if (vector->allocated < count)
cvector_resize(vector, count);
for (start = string, p = string, i = 0; *p; p++)
if (*p == ' ' || *p == '\t') {
if (start != p) {
*p = '\0';
vector->strings[i++] = start;
}
start = p + 1;
}
if (start != p)
vector->strings[i++] = start;
vector->count = i;
return vector;
}
/*
** Given a vector and a separator string, allocate and build a new string
** composed of all the strings in the vector separated from each other by the
** seperator string. Caller is responsible for freeing.
*/
char *
vector_join(const struct vector *vector, const char *seperator)
{
char *string;
size_t i, size, seplen;
seplen = strlen(seperator);
for (size = 0, i = 0; i < vector->count; i++)
size += strlen(vector->strings[i]);
size += (vector->count - 1) * seplen + 1;
string = xmalloc(size);
strlcpy(string, vector->strings[0], size);
for (i = 1; i < vector->count; i++) {
strlcat(string, seperator, size);
strlcat(string, vector->strings[i], size);
}
return string;
}
char *
cvector_join(const struct cvector *vector, const char *seperator)
{
char *string;
size_t i, size, seplen;
seplen = strlen(seperator);
for (size = 0, i = 0; i < vector->count; i++)
size += strlen(vector->strings[i]);
size += (vector->count - 1) * seplen + 1;
string = xmalloc(size);
strlcpy(string, vector->strings[0], size);
for (i = 1; i < vector->count; i++) {
strlcat(string, seperator, size);
strlcat(string, vector->strings[i], size);
}
return string;
}
|