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