strbuf.h

   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  */
  64 struct strbuf {
  65         size_t alloc;
  66         size_t len;
  67         char *buf;
  68 };
  69
  70 extern 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  */
  82 extern 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  */
  88 extern 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  */
  95 extern 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  */
 105 extern void strbuf_attach(struct strbuf *, void *, size_t, size_t);
 106
 107 /**
 108  * Swap the contents of two string buffers.
 109  */
 110 static inline void strbuf_swap(struct strbuf *a, struct strbuf *b)
 111 {
 112         SWAP(*a, *b);
 113 }
 114
 115
 116 /**
 117  * Functions related to the size of the buffer
 118  * -------------------------------------------
 119  */
 120
 121 /**
 122  * Determine the amount of allocated but unused memory.
 123  */
 124 static inline size_t strbuf_avail(const struct strbuf *sb)
 125 {
 126         return sb->alloc ? sb->alloc - sb->len - 1 : 0;
 127 }
 128
 129 /**
 130  * Ensure that at least this amount of unused memory is available after
 131  * `len`. This is used when you know a typical size for what you will add
 132  * and want to avoid repetitive automatic resizing of the underlying buffer.
 133  * This is never a needed operation, but can be critical for performance in
 134  * some cases.
 135  */
 136 extern void strbuf_grow(struct strbuf *, size_t);
 137
 138 /**
 139  * Set the length of the buffer to a given value. This function does *not*
 140  * allocate new memory, so you should not perform a `strbuf_setlen()` to a
 141  * length that is larger than `len + strbuf_avail()`. `strbuf_setlen()` is
 142  * just meant as a 'please fix invariants from this strbuf I just messed
 143  * with'.
 144  */
 145 static inline void strbuf_setlen(struct strbuf *sb, size_t len)
 146 {
 147         if (len > (sb->alloc ? sb->alloc - 1 : 0))
 148                 die("BUG: strbuf_setlen() beyond buffer");
 149         sb->len = len;
 150         sb->buf[len] = '\0';
 151 }
 152
 153 /**
 154  * Empty the buffer by setting the size of it to zero.
 155  */
 156 #define strbuf_reset(sb)  strbuf_setlen(sb, 0)
 157
 158
 159 /**
 160  * Functions related to the contents of the buffer
 161  * -----------------------------------------------
 162  */
 163
 164 /**
 165  * Strip whitespace from the beginning (`ltrim`), end (`rtrim`), or both side
 166  * (`trim`) of a string.
 167  */
 168 extern void strbuf_trim(struct strbuf *);
 169 extern void strbuf_rtrim(struct strbuf *);
 170 extern void strbuf_ltrim(struct strbuf *);
 171
 172 /**
 173  * Replace the contents of the strbuf with a reencoded form.  Returns -1
 174  * on error, 0 on success.
 175  */
 176 extern int strbuf_reencode(struct strbuf *sb, const char *from, const char *to);
 177
 178 /**
 179  * Lowercase each character in the buffer using `tolower`.
 180  */
 181 extern void strbuf_tolower(struct strbuf *sb);
 182
 183 /**
 184  * Compare two buffers. Returns an integer less than, equal to, or greater
 185  * than zero if the first buffer is found, respectively, to be less than,
 186  * to match, or be greater than the second buffer.
 187  */
 188 extern int strbuf_cmp(const struct strbuf *, const struct strbuf *);
 189
 190
 191 /**
 192  * Adding data to the buffer
 193  * -------------------------
 194  *
 195  * NOTE: All of the functions in this section will grow the buffer as
 196  * necessary.  If they fail for some reason other than memory shortage and the
 197  * buffer hadn't been allocated before (i.e. the `struct strbuf` was set to
 198  * `STRBUF_INIT`), then they will free() it.
 199  */
 200
 201 /**
 202  * Add a single character to the buffer.
 203  */
 204 static inline void strbuf_addch(struct strbuf *sb, int c)
 205 {
 206         if (!strbuf_avail(sb))
 207                 strbuf_grow(sb, 1);
 208         sb->buf[sb->len++] = c;
 209         sb->buf[sb->len] = '\0';
 210 }
 211
 212 /**
 213  * Add a character the specified number of times to the buffer.
 214  */
 215 extern void strbuf_addchars(struct strbuf *sb, int c, size_t n);
 216
 217 /**
 218  * Insert data to the given position of the buffer. The remaining contents
 219  * will be shifted, not overwritten.
 220  */
 221 extern void strbuf_insert(struct strbuf *, size_t pos, const void *, size_t);
 222
 223 /**
 224  * Remove given amount of data from a given position of the buffer.
 225  */
 226 extern void strbuf_remove(struct strbuf *, size_t pos, size_t len);
 227
 228 /**
 229  * Remove the bytes between `pos..pos+len` and replace it with the given
 230  * data.
 231  */
 232 extern void strbuf_splice(struct strbuf *, size_t pos, size_t len,
 233                           const void *, size_t);
 234
 235 /**
 236  * Add a NUL-terminated string to the buffer. Each line will be prepended
 237  * by a comment character and a blank.
 238  */
 239 extern void strbuf_add_commented_lines(struct strbuf *out, const char *buf, size_t size);
 240
 241
 242 /**
 243  * Add data of given length to the buffer.
 244  */
 245 extern void strbuf_add(struct strbuf *, const void *, size_t);
 246
 247 /**
 248  * Add a NUL-terminated string to the buffer.
 249  *
 250  * NOTE: This function will *always* be implemented as an inline or a macro
 251  * using strlen, meaning that this is efficient to write things like:
 252  *
 253  *     strbuf_addstr(sb, "immediate string");
 254  *
 255  */
 256 static inline void strbuf_addstr(struct strbuf *sb, const char *s)
 257 {
 258         strbuf_add(sb, s, strlen(s));
 259 }
 260
 261 /**
 262  * Copy the contents of another buffer at the end of the current one.
 263  */
 264 extern void strbuf_addbuf(struct strbuf *sb, const struct strbuf *sb2);
 265
 266 /**
 267  * Copy part of the buffer from a given position till a given length to the
 268  * end of the buffer.
 269  */
 270 extern void strbuf_adddup(struct strbuf *sb, size_t pos, size_t len);
 271
 272 /**
 273  * This function can be used to expand a format string containing
 274  * placeholders. To that end, it parses the string and calls the specified
 275  * function for every percent sign found.
 276  *
 277  * The callback function is given a pointer to the character after the `%`
 278  * and a pointer to the struct strbuf.  It is expected to add the expanded
 279  * version of the placeholder to the strbuf, e.g. to add a newline
 280  * character if the letter `n` appears after a `%`.  The function returns
 281  * the length of the placeholder recognized and `strbuf_expand()` skips
 282  * over it.
 283  *
 284  * The format `%%` is automatically expanded to a single `%` as a quoting
 285  * mechanism; callers do not need to handle the `%` placeholder themselves,
 286  * and the callback function will not be invoked for this placeholder.
 287  *
 288  * All other characters (non-percent and not skipped ones) are copied
 289  * verbatim to the strbuf.  If the callback returned zero, meaning that the
 290  * placeholder is unknown, then the percent sign is copied, too.
 291  *
 292  * In order to facilitate caching and to make it possible to give
 293  * parameters to the callback, `strbuf_expand()` passes a context pointer,
 294  * which can be used by the programmer of the callback as she sees fit.
 295  */
 296 typedef size_t (*expand_fn_t) (struct strbuf *sb, const char *placeholder, void *context);
 297 extern void strbuf_expand(struct strbuf *sb, const char *format, expand_fn_t fn, void *context);
 298
 299 /**
 300  * Used as callback for `strbuf_expand()`, expects an array of
 301  * struct strbuf_expand_dict_entry as context, i.e. pairs of
 302  * placeholder and replacement string.  The array needs to be
 303  * terminated by an entry with placeholder set to NULL.
 304  */
 305 struct strbuf_expand_dict_entry {
 306         const char *placeholder;
 307         const char *value;
 308 };
 309 extern size_t strbuf_expand_dict_cb(struct strbuf *sb, const char *placeholder, void *context);
 310
 311 /**
 312  * Append the contents of one strbuf to another, quoting any
 313  * percent signs ("%") into double-percents ("%%") in the
 314  * destination. This is useful for literal data to be fed to either
 315  * strbuf_expand or to the *printf family of functions.
 316  */
 317 extern void strbuf_addbuf_percentquote(struct strbuf *dst, const struct strbuf *src);
 318
 319 /**
 320  * Append the given byte size as a human-readable string (i.e. 12.23 KiB,
 321  * 3.50 MiB).
 322  */
 323 extern void strbuf_humanise_bytes(struct strbuf *buf, off_t bytes);
 324
 325 /**
 326  * Add a formatted string to the buffer.
 327  */
 328 __attribute__((format (printf,2,3)))
 329 extern void strbuf_addf(struct strbuf *sb, const char *fmt, ...);
 330
 331 /**
 332  * Add a formatted string prepended by a comment character and a
 333  * blank to the buffer.
 334  */
 335 __attribute__((format (printf, 2, 3)))
 336 extern void strbuf_commented_addf(struct strbuf *sb, const char *fmt, ...);
 337
 338 __attribute__((format (printf,2,0)))
 339 extern void strbuf_vaddf(struct strbuf *sb, const char *fmt, va_list ap);
 340
 341 /**
 342  * Add the time specified by `tm`, as formatted by `strftime`.
 343  */
 344 extern void strbuf_addftime(struct strbuf *sb, const char *fmt, const struct tm *tm);
 345
 346 /**
 347  * Read a given size of data from a FILE* pointer to the buffer.
 348  *
 349  * NOTE: The buffer is rewound if the read fails. If -1 is returned,
 350  * `errno` must be consulted, like you would do for `read(3)`.
 351  * `strbuf_read()`, `strbuf_read_file()` and `strbuf_getline_*()`
 352  * family of functions have the same behaviour as well.
 353  */
 354 extern size_t strbuf_fread(struct strbuf *, size_t, FILE *);
 355
 356 /**
 357  * Read the contents of a given file descriptor. The third argument can be
 358  * used to give a hint about the file size, to avoid reallocs.  If read fails,
 359  * any partial read is undone.
 360  */
 361 extern ssize_t strbuf_read(struct strbuf *, int fd, size_t hint);
 362
 363 /**
 364  * Read the contents of a given file descriptor partially by using only one
 365  * attempt of xread. The third argument can be used to give a hint about the
 366  * file size, to avoid reallocs. Returns the number of new bytes appended to
 367  * the sb.
 368  */
 369 extern ssize_t strbuf_read_once(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  * Return the number of bytes read or a negative value if some error
 375  * occurred while opening or reading the file.
 376  */
 377 extern ssize_t strbuf_read_file(struct strbuf *sb, const char *path, size_t hint);
 378
 379 /**
 380  * Read the target of a symbolic link, specified by its path.  The third
 381  * argument can be used to give a hint about the size, to avoid reallocs.
 382  */
 383 extern int strbuf_readlink(struct strbuf *sb, const char *path, size_t hint);
 384
 385 /**
 386  * Write the whole content of the strbuf to the stream not stopping at
 387  * NUL bytes.
 388  */
 389 extern ssize_t strbuf_write(struct strbuf *sb, FILE *stream);
 390
 391 /**
 392  * Read a line from a FILE *, overwriting the existing contents of
 393  * the strbuf.  The strbuf_getline*() family of functions share
 394  * this signature, but have different line termination conventions.
 395  *
 396  * Reading stops after the terminator or at EOF.  The terminator
 397  * is removed from the buffer before returning.  Returns 0 unless
 398  * there was nothing left before EOF, in which case it returns `EOF`.
 399  */
 400 typedef int (*strbuf_getline_fn)(struct strbuf *, FILE *);
 401
 402 /* Uses LF as the line terminator */
 403 extern int strbuf_getline_lf(struct strbuf *sb, FILE *fp);
 404
 405 /* Uses NUL as the line terminator */
 406 extern int strbuf_getline_nul(struct strbuf *sb, FILE *fp);
 407
 408 /*
 409  * Similar to strbuf_getline_lf(), but additionally treats a CR that
 410  * comes immediately before the LF as part of the terminator.
 411  * This is the most friendly version to be used to read "text" files
 412  * that can come from platforms whose native text format is CRLF
 413  * terminated.
 414  */
 415 extern int strbuf_getline(struct strbuf *, FILE *);
 416
 417
 418 /**
 419  * Like `strbuf_getline`, but keeps the trailing terminator (if
 420  * any) in the buffer.
 421  */
 422 extern int strbuf_getwholeline(struct strbuf *, FILE *, int);
 423
 424 /**
 425  * Like `strbuf_getwholeline`, but operates on a file descriptor.
 426  * It reads one character at a time, so it is very slow.  Do not
 427  * use it unless you need the correct position in the file
 428  * descriptor.
 429  */
 430 extern int strbuf_getwholeline_fd(struct strbuf *, int, int);
 431
 432 /**
 433  * Set the buffer to the path of the current working directory.
 434  */
 435 extern int strbuf_getcwd(struct strbuf *sb);
 436
 437 /**
 438  * Add a path to a buffer, converting a relative path to an
 439  * absolute one in the process.  Symbolic links are not
 440  * resolved.
 441  */
 442 extern void strbuf_add_absolute_path(struct strbuf *sb, const char *path);
 443
 444 /**
 445  * Canonize `path` (make it absolute, resolve symlinks, remove extra
 446  * slashes) and append it to `sb`.  Die with an informative error
 447  * message if there is a problem.
 448  *
 449  * The directory part of `path` (i.e., everything up to the last
 450  * dir_sep) must denote a valid, existing directory, but the last
 451  * component need not exist.
 452  *
 453  * Callers that don't mind links should use the more lightweight
 454  * strbuf_add_absolute_path() instead.
 455  */
 456 extern void strbuf_add_real_path(struct strbuf *sb, const char *path);
 457
 458
 459 /**
 460  * Normalize in-place the path contained in the strbuf. See
 461  * normalize_path_copy() for details. If an error occurs, the contents of "sb"
 462  * are left untouched, and -1 is returned.
 463  */
 464 extern int strbuf_normalize_path(struct strbuf *sb);
 465
 466 /**
 467  * Strip whitespace from a buffer. The second parameter controls if
 468  * comments are considered contents to be removed or not.
 469  */
 470 extern void strbuf_stripspace(struct strbuf *buf, int skip_comments);
 471
 472 /**
 473  * Temporary alias until all topic branches have switched to use
 474  * strbuf_stripspace directly.
 475  */
 476 static inline void stripspace(struct strbuf *buf, int skip_comments)
 477 {
 478         strbuf_stripspace(buf, skip_comments);
 479 }
 480
 481 static inline int strbuf_strip_suffix(struct strbuf *sb, const char *suffix)
 482 {
 483         if (strip_suffix_mem(sb->buf, &sb->len, suffix)) {
 484                 strbuf_setlen(sb, sb->len);
 485                 return 1;
 486         } else
 487                 return 0;
 488 }
 489
 490 /**
 491  * Split str (of length slen) at the specified terminator character.
 492  * Return a null-terminated array of pointers to strbuf objects
 493  * holding the substrings.  The substrings include the terminator,
 494  * except for the last substring, which might be unterminated if the
 495  * original string did not end with a terminator.  If max is positive,
 496  * then split the string into at most max substrings (with the last
 497  * substring containing everything following the (max-1)th terminator
 498  * character).
 499  *
 500  * The most generic form is `strbuf_split_buf`, which takes an arbitrary
 501  * pointer/len buffer. The `_str` variant takes a NUL-terminated string,
 502  * the `_max` variant takes a strbuf, and just `strbuf_split` is a convenience
 503  * wrapper to drop the `max` parameter.
 504  *
 505  * For lighter-weight alternatives, see string_list_split() and
 506  * string_list_split_in_place().
 507  */
 508 extern struct strbuf **strbuf_split_buf(const char *, size_t,
 509                                         int terminator, int max);
 510
 511 static inline struct strbuf **strbuf_split_str(const char *str,
 512                                                int terminator, int max)
 513 {
 514         return strbuf_split_buf(str, strlen(str), terminator, max);
 515 }
 516
 517 static inline struct strbuf **strbuf_split_max(const struct strbuf *sb,
 518                                                 int terminator, int max)
 519 {
 520         return strbuf_split_buf(sb->buf, sb->len, terminator, max);
 521 }
 522
 523 static inline struct strbuf **strbuf_split(const struct strbuf *sb,
 524                                            int terminator)
 525 {
 526         return strbuf_split_max(sb, terminator, 0);
 527 }
 528
 529 /**
 530  * Free a NULL-terminated list of strbufs (for example, the return
 531  * values of the strbuf_split*() functions).
 532  */
 533 extern void strbuf_list_free(struct strbuf **);
 534
 535 /**
 536  * Add the abbreviation, as generated by find_unique_abbrev, of `sha1` to
 537  * the strbuf `sb`.
 538  */
 539 extern void strbuf_add_unique_abbrev(struct strbuf *sb,
 540                                      const unsigned char *sha1,
 541                                      int abbrev_len);
 542
 543 /**
 544  * Launch the user preferred editor to edit a file and fill the buffer
 545  * with the file's contents upon the user completing their editing. The
 546  * third argument can be used to set the environment which the editor is
 547  * run in. If the buffer is NULL the editor is launched as usual but the
 548  * file's contents are not read into the buffer upon completion.
 549  */
 550 extern int launch_editor(const char *path, struct strbuf *buffer, const char *const *env);
 551
 552 extern void strbuf_add_lines(struct strbuf *sb, const char *prefix, const char *buf, size_t size);
 553
 554 /**
 555  * Append s to sb, with the characters '<', '>', '&' and '"' converted
 556  * into XML entities.
 557  */
 558 extern void strbuf_addstr_xml_quoted(struct strbuf *sb, const char *s);
 559
 560 /**
 561  * "Complete" the contents of `sb` by ensuring that either it ends with the
 562  * character `term`, or it is empty.  This can be used, for example,
 563  * to ensure that text ends with a newline, but without creating an empty
 564  * blank line if there is no content in the first place.
 565  */
 566 static inline void strbuf_complete(struct strbuf *sb, char term)
 567 {
 568         if (sb->len && sb->buf[sb->len - 1] != term)
 569                 strbuf_addch(sb, term);
 570 }
 571
 572 static inline void strbuf_complete_line(struct strbuf *sb)
 573 {
 574         strbuf_complete(sb, '\n');
 575 }
 576
 577 /*
 578  * Copy "name" to "sb", expanding any special @-marks as handled by
 579  * interpret_branch_name(). The result is a non-qualified branch name
 580  * (so "foo" or "origin/master" instead of "refs/heads/foo" or
 581  * "refs/remotes/origin/master").
 582  *
 583  * Note that the resulting name may not be a syntactically valid refname.
 584  *
 585  * If "allowed" is non-zero, restrict the set of allowed expansions. See
 586  * interpret_branch_name() for details.
 587  */
 588 extern void strbuf_branchname(struct strbuf *sb, const char *name,
 589                               unsigned allowed);
 590
 591 /*
 592  * Like strbuf_branchname() above, but confirm that the result is
 593  * syntactically valid to be used as a local branch name in refs/heads/.
 594  *
 595  * The return value is "0" if the result is valid, and "-1" otherwise.
 596  */
 597 extern int strbuf_check_branch_ref(struct strbuf *sb, const char *name);
 598
 599 extern void strbuf_addstr_urlencode(struct strbuf *, const char *,
 600                                     int reserved);
 601
 602 __attribute__((format (printf,1,2)))
 603 extern int printf_ln(const char *fmt, ...);
 604 __attribute__((format (printf,2,3)))
 605 extern int fprintf_ln(FILE *fp, const char *fmt, ...);
 606
 607 char *xstrdup_tolower(const char *);
 608
 609 /**
 610  * Create a newly allocated string using printf format. You can do this easily
 611  * with a strbuf, but this provides a shortcut to save a few lines.
 612  */
 613 __attribute__((format (printf, 1, 0)))
 614 char *xstrvfmt(const char *fmt, va_list ap);
 615 __attribute__((format (printf, 1, 2)))
 616 char *xstrfmt(const char *fmt, ...);
 617
 618 #endif /* STRBUF_H */