1#ifndef STRBUF_H 2#define STRBUF_H 3 4/** 5 * strbuf's are meant to be used with all the usual C string and memory 6 * APIs. Given that the length of the buffer is known, it's often better to 7 * use the mem* functions than a str* one (memchr vs. strchr e.g.). 8 * Though, one has to be careful about the fact that str* functions often 9 * stop on NULs and that strbufs may have embedded NULs. 10 * 11 * A strbuf is NUL terminated for convenience, but no function in the 12 * strbuf API actually relies on the string being free of NULs. 13 * 14 * strbufs have some invariants that are very important to keep in mind: 15 * 16 * - The `buf` member is never NULL, so it can be used in any usual C 17 * string operations safely. strbuf's _have_ to be initialized either by 18 * `strbuf_init()` or by `= STRBUF_INIT` before the invariants, though. 19 * 20 * Do *not* assume anything on what `buf` really is (e.g. if it is 21 * allocated memory or not), use `strbuf_detach()` to unwrap a memory 22 * buffer from its strbuf shell in a safe way. That is the sole supported 23 * way. This will give you a malloced buffer that you can later `free()`. 24 * 25 * However, it is totally safe to modify anything in the string pointed by 26 * the `buf` member, between the indices `0` and `len-1` (inclusive). 27 * 28 * - The `buf` member is a byte array that has at least `len + 1` bytes 29 * allocated. The extra byte is used to store a `'\0'`, allowing the 30 * `buf` member to be a valid C-string. Every strbuf function ensure this 31 * invariant is preserved. 32 * 33 * NOTE: It is OK to "play" with the buffer directly if you work it this 34 * way: 35 * 36 * strbuf_grow(sb, SOME_SIZE); <1> 37 * strbuf_setlen(sb, sb->len + SOME_OTHER_SIZE); 38 * 39 * <1> Here, the memory array starting at `sb->buf`, and of length 40 * `strbuf_avail(sb)` is all yours, and you can be sure that 41 * `strbuf_avail(sb)` is at least `SOME_SIZE`. 42 * 43 * NOTE: `SOME_OTHER_SIZE` must be smaller or equal to `strbuf_avail(sb)`. 44 * 45 * Doing so is safe, though if it has to be done in many places, adding the 46 * missing API to the strbuf module is the way to go. 47 * 48 * WARNING: Do _not_ assume that the area that is yours is of size `alloc 49 * - 1` even if it's true in the current implementation. Alloc is somehow a 50 * "private" member that should not be messed with. Use `strbuf_avail()` 51 * instead. 52*/ 53 54/** 55 * Data Structures 56 * --------------- 57 */ 58 59/** 60 * This is the string buffer structure. The `len` member can be used to 61 * determine the current length of the string, and `buf` member provides 62 * access to the string itself. 63 */ 64struct strbuf { 65 size_t alloc; 66 size_t len; 67 char *buf; 68}; 69 70extern char strbuf_slopbuf[]; 71#define STRBUF_INIT { 0, 0, strbuf_slopbuf } 72 73/** 74 * Functions 75 * --------- 76 */ 77 78/** 79 * * Life Cycle 80 */ 81 82/** 83 * Initialize the structure. The second parameter can be zero or a bigger 84 * number to allocate memory, in case you want to prevent further reallocs. 85 */ 86extern void strbuf_init(struct strbuf *, size_t); 87 88/** 89 * Release a string buffer and the memory it used. You should not use the 90 * string buffer after using this function, unless you initialize it again. 91 */ 92extern void strbuf_release(struct strbuf *); 93 94/** 95 * Detach the string from the strbuf and returns it; you now own the 96 * storage the string occupies and it is your responsibility from then on 97 * to release it with `free(3)` when you are done with it. 98 */ 99extern char *strbuf_detach(struct strbuf *, size_t *); 100 101/** 102 * Attach a string to a buffer. You should specify the string to attach, 103 * the current length of the string and the amount of allocated memory. 104 * The amount must be larger than the string length, because the string you 105 * pass is supposed to be a NUL-terminated string. This string _must_ be 106 * malloc()ed, and after attaching, the pointer cannot be relied upon 107 * anymore, and neither be free()d directly. 108 */ 109extern void strbuf_attach(struct strbuf *, void *, size_t, size_t); 110 111/** 112 * Swap the contents of two string buffers. 113 */ 114static inline void strbuf_swap(struct strbuf *a, struct strbuf *b) 115{ 116 struct strbuf tmp = *a; 117 *a = *b; 118 *b = tmp; 119} 120 121 122/** 123 * * Related to the size of the buffer 124 */ 125 126/** 127 * Determine the amount of allocated but unused memory. 128 */ 129static inline size_t strbuf_avail(const struct strbuf *sb) 130{ 131 return sb->alloc ? sb->alloc - sb->len - 1 : 0; 132} 133 134/** 135 * Ensure that at least this amount of unused memory is available after 136 * `len`. This is used when you know a typical size for what you will add 137 * and want to avoid repetitive automatic resizing of the underlying buffer. 138 * This is never a needed operation, but can be critical for performance in 139 * some cases. 140 */ 141extern void strbuf_grow(struct strbuf *, size_t); 142 143/** 144 * Set the length of the buffer to a given value. This function does *not* 145 * allocate new memory, so you should not perform a `strbuf_setlen()` to a 146 * length that is larger than `len + strbuf_avail()`. `strbuf_setlen()` is 147 * just meant as a 'please fix invariants from this strbuf I just messed 148 * with'. 149 */ 150static inline void strbuf_setlen(struct strbuf *sb, size_t len) 151{ 152 if (len > (sb->alloc ? sb->alloc - 1 : 0)) 153 die("BUG: strbuf_setlen() beyond buffer"); 154 sb->len = len; 155 sb->buf[len] = '\0'; 156} 157 158/** 159 * Empty the buffer by setting the size of it to zero. 160 */ 161#define strbuf_reset(sb) strbuf_setlen(sb, 0) 162 163 164/** 165 * * Related to the contents of the buffer 166 */ 167 168/** 169 * Strip whitespace from the beginning and end of a string. 170 * Equivalent to performing `strbuf_rtrim()` followed by `strbuf_ltrim()`. 171 */ 172extern void strbuf_trim(struct strbuf *); 173 174/** 175 * Strip whitespace from the end of a string. 176 */ 177extern void strbuf_rtrim(struct strbuf *); 178 179/** 180 * Strip whitespace from the beginning of a string. 181 */ 182extern void strbuf_ltrim(struct strbuf *); 183 184/** 185 * Replace the contents of the strbuf with a reencoded form. Returns -1 186 * on error, 0 on success. 187 */ 188extern int strbuf_reencode(struct strbuf *sb, const char *from, const char *to); 189 190/** 191 * Lowercase each character in the buffer using `tolower`. 192 */ 193extern void strbuf_tolower(struct strbuf *sb); 194 195/** 196 * Compare two buffers. Returns an integer less than, equal to, or greater 197 * than zero if the first buffer is found, respectively, to be less than, 198 * to match, or be greater than the second buffer. 199 */ 200extern int strbuf_cmp(const struct strbuf *, const struct strbuf *); 201 202 203/** 204 * * Adding data to the buffer 205 * 206 * NOTE: All of the functions in this section will grow the buffer as 207 * necessary. If they fail for some reason other than memory shortage and the 208 * buffer hadn't been allocated before (i.e. the `struct strbuf` was set to 209 * `STRBUF_INIT`), then they will free() it. 210 */ 211 212/** 213 * Add a single character to the buffer. 214 */ 215static inline void strbuf_addch(struct strbuf *sb, int c) 216{ 217 strbuf_grow(sb, 1); 218 sb->buf[sb->len++] = c; 219 sb->buf[sb->len] = '\0'; 220} 221 222/** 223 * Add a character the specified number of times to the buffer. 224 */ 225extern void strbuf_addchars(struct strbuf *sb, int c, size_t n); 226 227/** 228 * Insert data to the given position of the buffer. The remaining contents 229 * will be shifted, not overwritten. 230 */ 231extern void strbuf_insert(struct strbuf *, size_t pos, const void *, size_t); 232 233/** 234 * Remove given amount of data from a given position of the buffer. 235 */ 236extern void strbuf_remove(struct strbuf *, size_t pos, size_t len); 237 238/** 239 * Remove the bytes between `pos..pos+len` and replace it with the given 240 * data. 241 */ 242extern void strbuf_splice(struct strbuf *, size_t pos, size_t len, 243 const void *, size_t); 244 245/** 246 * Add a NUL-terminated string to the buffer. Each line will be prepended 247 * by a comment character and a blank. 248 */ 249extern void strbuf_add_commented_lines(struct strbuf *out, const char *buf, size_t size); 250 251 252/** 253 * Add data of given length to the buffer. 254 */ 255extern void strbuf_add(struct strbuf *, const void *, size_t); 256 257/** 258 * Add a NUL-terminated string to the buffer. 259 * 260 * NOTE: This function will *always* be implemented as an inline or a macro 261 * using strlen, meaning that this is efficient to write things like: 262 * 263 * strbuf_addstr(sb, "immediate string"); 264 * 265 */ 266static inline void strbuf_addstr(struct strbuf *sb, const char *s) 267{ 268 strbuf_add(sb, s, strlen(s)); 269} 270 271/** 272 * Copy the contents of another buffer at the end of the current one. 273 */ 274static inline void strbuf_addbuf(struct strbuf *sb, const struct strbuf *sb2) 275{ 276 strbuf_grow(sb, sb2->len); 277 strbuf_add(sb, sb2->buf, sb2->len); 278} 279 280/** 281 * Copy part of the buffer from a given position till a given length to the 282 * end of the buffer. 283 */ 284extern void strbuf_adddup(struct strbuf *sb, size_t pos, size_t len); 285 286/** 287 * This function can be used to expand a format string containing 288 * placeholders. To that end, it parses the string and calls the specified 289 * function for every percent sign found. 290 * 291 * The callback function is given a pointer to the character after the `%` 292 * and a pointer to the struct strbuf. It is expected to add the expanded 293 * version of the placeholder to the strbuf, e.g. to add a newline 294 * character if the letter `n` appears after a `%`. The function returns 295 * the length of the placeholder recognized and `strbuf_expand()` skips 296 * over it. 297 * 298 * The format `%%` is automatically expanded to a single `%` as a quoting 299 * mechanism; callers do not need to handle the `%` placeholder themselves, 300 * and the callback function will not be invoked for this placeholder. 301 * 302 * All other characters (non-percent and not skipped ones) are copied 303 * verbatim to the strbuf. If the callback returned zero, meaning that the 304 * placeholder is unknown, then the percent sign is copied, too. 305 * 306 * In order to facilitate caching and to make it possible to give 307 * parameters to the callback, `strbuf_expand()` passes a context pointer, 308 * which can be used by the programmer of the callback as she sees fit. 309 */ 310typedef size_t (*expand_fn_t) (struct strbuf *sb, const char *placeholder, void *context); 311extern void strbuf_expand(struct strbuf *sb, const char *format, expand_fn_t fn, void *context); 312 313/** 314 * Used as callback for `strbuf_expand()`, expects an array of 315 * struct strbuf_expand_dict_entry as context, i.e. pairs of 316 * placeholder and replacement string. The array needs to be 317 * terminated by an entry with placeholder set to NULL. 318 */ 319struct strbuf_expand_dict_entry { 320 const char *placeholder; 321 const char *value; 322}; 323extern size_t strbuf_expand_dict_cb(struct strbuf *sb, const char *placeholder, void *context); 324 325/** 326 * Append the contents of one strbuf to another, quoting any 327 * percent signs ("%") into double-percents ("%%") in the 328 * destination. This is useful for literal data to be fed to either 329 * strbuf_expand or to the *printf family of functions. 330 */ 331extern void strbuf_addbuf_percentquote(struct strbuf *dst, const struct strbuf *src); 332 333/** 334 * Append the given byte size as a human-readable string (i.e. 12.23 KiB, 335 * 3.50 MiB). 336 */ 337extern void strbuf_humanise_bytes(struct strbuf *buf, off_t bytes); 338 339/** 340 * Add a formatted string to the buffer. 341 */ 342__attribute__((format (printf,2,3))) 343extern void strbuf_addf(struct strbuf *sb, const char *fmt, ...); 344 345/** 346 * Add a formatted string prepended by a comment character and a 347 * blank to the buffer. 348 */ 349__attribute__((format (printf, 2, 3))) 350extern void strbuf_commented_addf(struct strbuf *sb, const char *fmt, ...); 351 352__attribute__((format (printf,2,0))) 353extern void strbuf_vaddf(struct strbuf *sb, const char *fmt, va_list ap); 354 355/** 356 * Read a given size of data from a FILE* pointer to the buffer. 357 * 358 * NOTE: The buffer is rewound if the read fails. If -1 is returned, 359 * `errno` must be consulted, like you would do for `read(3)`. 360 * `strbuf_read()`, `strbuf_read_file()` and `strbuf_getline()` has the 361 * same behaviour as well. 362 */ 363extern size_t strbuf_fread(struct strbuf *, size_t, FILE *); 364 365/** 366 * Read the contents of a given file descriptor. The third argument can be 367 * used to give a hint about the file size, to avoid reallocs. If read fails, 368 * any partial read is undone. 369 */ 370extern ssize_t strbuf_read(struct strbuf *, int fd, size_t hint); 371 372/** 373 * Read the contents of a file, specified by its path. The third argument 374 * can be used to give a hint about the file size, to avoid reallocs. 375 */ 376extern int strbuf_read_file(struct strbuf *sb, const char *path, size_t hint); 377 378/** 379 * Read the target of a symbolic link, specified by its path. The third 380 * argument can be used to give a hint about the size, to avoid reallocs. 381 */ 382extern int strbuf_readlink(struct strbuf *sb, const char *path, size_t hint); 383 384/** 385 * Read a line from a FILE *, overwriting the existing contents 386 * of the strbuf. The second argument specifies the line 387 * terminator character, typically `'\n'`. 388 * Reading stops after the terminator or at EOF. The terminator 389 * is removed from the buffer before returning. Returns 0 unless 390 * there was nothing left before EOF, in which case it returns `EOF`. 391 */ 392extern int strbuf_getline(struct strbuf *, FILE *, int); 393 394/** 395 * Like `strbuf_getline`, but keeps the trailing terminator (if 396 * any) in the buffer. 397 */ 398extern int strbuf_getwholeline(struct strbuf *, FILE *, int); 399 400/** 401 * Like `strbuf_getwholeline`, but operates on a file descriptor. 402 * It reads one character at a time, so it is very slow. Do not 403 * use it unless you need the correct position in the file 404 * descriptor. 405 */ 406extern int strbuf_getwholeline_fd(struct strbuf *, int, int); 407 408/** 409 * Set the buffer to the path of the current working directory. 410 */ 411extern int strbuf_getcwd(struct strbuf *sb); 412 413/** 414 * Add a path to a buffer, converting a relative path to an 415 * absolute one in the process. Symbolic links are not 416 * resolved. 417 */ 418extern void strbuf_add_absolute_path(struct strbuf *sb, const char *path); 419 420/** 421 * Strip whitespace from a buffer. The second parameter controls if 422 * comments are considered contents to be removed or not. 423 */ 424extern void stripspace(struct strbuf *buf, int skip_comments); 425 426static inline int strbuf_strip_suffix(struct strbuf *sb, const char *suffix) 427{ 428 if (strip_suffix_mem(sb->buf, &sb->len, suffix)) { 429 strbuf_setlen(sb, sb->len); 430 return 1; 431 } else 432 return 0; 433} 434 435/** 436 * Split str (of length slen) at the specified terminator character. 437 * Return a null-terminated array of pointers to strbuf objects 438 * holding the substrings. The substrings include the terminator, 439 * except for the last substring, which might be unterminated if the 440 * original string did not end with a terminator. If max is positive, 441 * then split the string into at most max substrings (with the last 442 * substring containing everything following the (max-1)th terminator 443 * character). 444 * 445 * For lighter-weight alternatives, see string_list_split() and 446 * string_list_split_in_place(). 447 */ 448extern struct strbuf **strbuf_split_buf(const char *, size_t, 449 int terminator, int max); 450 451/** 452 * Split a NUL-terminated string at the specified terminator 453 * character. See strbuf_split_buf() for more information. 454 */ 455static inline struct strbuf **strbuf_split_str(const char *str, 456 int terminator, int max) 457{ 458 return strbuf_split_buf(str, strlen(str), terminator, max); 459} 460 461/** 462 * Split a strbuf at the specified terminator character. See 463 * strbuf_split_buf() for more information. 464 */ 465static inline struct strbuf **strbuf_split_max(const struct strbuf *sb, 466 int terminator, int max) 467{ 468 return strbuf_split_buf(sb->buf, sb->len, terminator, max); 469} 470 471/** 472 * Split a strbuf at the specified terminator character. See 473 * strbuf_split_buf() for more information. 474 */ 475static inline struct strbuf **strbuf_split(const struct strbuf *sb, 476 int terminator) 477{ 478 return strbuf_split_max(sb, terminator, 0); 479} 480 481/** 482 * Free a NULL-terminated list of strbufs (for example, the return 483 * values of the strbuf_split*() functions). 484 */ 485extern void strbuf_list_free(struct strbuf **); 486 487/** 488 * Launch the user preferred editor to edit a file and fill the buffer 489 * with the file's contents upon the user completing their editing. The 490 * third argument can be used to set the environment which the editor is 491 * run in. If the buffer is NULL the editor is launched as usual but the 492 * file's contents are not read into the buffer upon completion. 493 */ 494extern int launch_editor(const char *path, struct strbuf *buffer, const char *const *env); 495 496extern void strbuf_add_lines(struct strbuf *sb, const char *prefix, const char *buf, size_t size); 497 498/** 499 * Append s to sb, with the characters '<', '>', '&' and '"' converted 500 * into XML entities. 501 */ 502extern void strbuf_addstr_xml_quoted(struct strbuf *sb, const char *s); 503 504static inline void strbuf_complete_line(struct strbuf *sb) 505{ 506 if (sb->len && sb->buf[sb->len - 1] != '\n') 507 strbuf_addch(sb, '\n'); 508} 509 510extern int strbuf_branchname(struct strbuf *sb, const char *name); 511extern int strbuf_check_branch_ref(struct strbuf *sb, const char *name); 512 513extern void strbuf_addstr_urlencode(struct strbuf *, const char *, 514 int reserved); 515 516__attribute__((format (printf,1,2))) 517extern int printf_ln(const char *fmt, ...); 518__attribute__((format (printf,2,3))) 519extern int fprintf_ln(FILE *fp, const char *fmt, ...); 520 521char *xstrdup_tolower(const char *); 522 523/** 524 * Create a newly allocated string using printf format. You can do this easily 525 * with a strbuf, but this provides a shortcut to save a few lines. 526 */ 527__attribute__((format (printf, 1, 0))) 528char *xstrvfmt(const char *fmt, va_list ap); 529__attribute__((format (printf, 1, 2))) 530char *xstrfmt(const char *fmt, ...); 531 532#endif /* STRBUF_H */