7 * strbuf's are meant to be used with all the usual C string and memory
8 * APIs. Given that the length of the buffer is known, it's often better to
9 * use the mem* functions than a str* one (memchr vs. strchr e.g.).
10 * Though, one has to be careful about the fact that str* functions often
11 * stop on NULs and that strbufs may have embedded NULs.
13 * A strbuf is NUL terminated for convenience, but no function in the
14 * strbuf API actually relies on the string being free of NULs.
16 * strbufs have some invariants that are very important to keep in mind:
18 * - The `buf` member is never NULL, so it can be used in any usual C
19 * string operations safely. strbuf's _have_ to be initialized either by
20 * `strbuf_init()` or by `= STRBUF_INIT` before the invariants, though.
22 * Do *not* assume anything on what `buf` really is (e.g. if it is
23 * allocated memory or not), use `strbuf_detach()` to unwrap a memory
24 * buffer from its strbuf shell in a safe way. That is the sole supported
25 * way. This will give you a malloced buffer that you can later `free()`.
27 * However, it is totally safe to modify anything in the string pointed by
28 * the `buf` member, between the indices `0` and `len-1` (inclusive).
30 * - The `buf` member is a byte array that has at least `len + 1` bytes
31 * allocated. The extra byte is used to store a `'\0'`, allowing the
32 * `buf` member to be a valid C-string. Every strbuf function ensure this
33 * invariant is preserved.
35 * NOTE: It is OK to "play" with the buffer directly if you work it this
38 * strbuf_grow(sb, SOME_SIZE); <1>
39 * strbuf_setlen(sb, sb->len + SOME_OTHER_SIZE);
41 * <1> Here, the memory array starting at `sb->buf`, and of length
42 * `strbuf_avail(sb)` is all yours, and you can be sure that
43 * `strbuf_avail(sb)` is at least `SOME_SIZE`.
45 * NOTE: `SOME_OTHER_SIZE` must be smaller or equal to `strbuf_avail(sb)`.
47 * Doing so is safe, though if it has to be done in many places, adding the
48 * missing API to the strbuf module is the way to go.
50 * WARNING: Do _not_ assume that the area that is yours is of size `alloc
51 * - 1` even if it's true in the current implementation. Alloc is somehow a
52 * "private" member that should not be messed with. Use `strbuf_avail()`
62 * This is the string buffer structure. The `len` member can be used to
63 * determine the current length of the string, and `buf` member provides
64 * access to the string itself.
72 extern char strbuf_slopbuf
[];
73 #define STRBUF_INIT { .alloc = 0, .len = 0, .buf = strbuf_slopbuf }
76 * Life Cycle Functions
77 * --------------------
81 * Initialize the structure. The second parameter can be zero or a bigger
82 * number to allocate memory, in case you want to prevent further reallocs.
84 extern void strbuf_init(struct strbuf
*, size_t);
87 * Release a string buffer and the memory it used. After this call, the
88 * strbuf points to an empty string that does not need to be free()ed, as
89 * if it had been set to `STRBUF_INIT` and never modified.
91 * To clear a strbuf in preparation for further use without the overhead
92 * of free()ing and malloc()ing again, use strbuf_reset() instead.
94 extern void strbuf_release(struct strbuf
*);
97 * Detach the string from the strbuf and returns it; you now own the
98 * storage the string occupies and it is your responsibility from then on
99 * to release it with `free(3)` when you are done with it.
101 * The strbuf that previously held the string is reset to `STRBUF_INIT` so
102 * it can be reused after calling this function.
104 extern char *strbuf_detach(struct strbuf
*, size_t *);
107 * Attach a string to a buffer. You should specify the string to attach,
108 * the current length of the string and the amount of allocated memory.
109 * The amount must be larger than the string length, because the string you
110 * pass is supposed to be a NUL-terminated string. This string _must_ be
111 * malloc()ed, and after attaching, the pointer cannot be relied upon
112 * anymore, and neither be free()d directly.
114 extern void strbuf_attach(struct strbuf
*, void *, size_t, size_t);
117 * Swap the contents of two string buffers.
119 static inline void strbuf_swap(struct strbuf
*a
, struct strbuf
*b
)
126 * Functions related to the size of the buffer
127 * -------------------------------------------
131 * Determine the amount of allocated but unused memory.
133 static inline size_t strbuf_avail(const struct strbuf
*sb
)
135 return sb
->alloc
? sb
->alloc
- sb
->len
- 1 : 0;
139 * Ensure that at least this amount of unused memory is available after
140 * `len`. This is used when you know a typical size for what you will add
141 * and want to avoid repetitive automatic resizing of the underlying buffer.
142 * This is never a needed operation, but can be critical for performance in
145 extern void strbuf_grow(struct strbuf
*, size_t);
148 * Set the length of the buffer to a given value. This function does *not*
149 * allocate new memory, so you should not perform a `strbuf_setlen()` to a
150 * length that is larger than `len + strbuf_avail()`. `strbuf_setlen()` is
151 * just meant as a 'please fix invariants from this strbuf I just messed
154 static inline void strbuf_setlen(struct strbuf
*sb
, size_t len
)
156 if (len
> (sb
->alloc
? sb
->alloc
- 1 : 0))
157 die("BUG: strbuf_setlen() beyond buffer");
159 if (sb
->buf
!= strbuf_slopbuf
)
162 assert(!strbuf_slopbuf
[0]);
166 * Empty the buffer by setting the size of it to zero.
168 #define strbuf_reset(sb) strbuf_setlen(sb, 0)
172 * Functions related to the contents of the buffer
173 * -----------------------------------------------
177 * Strip whitespace from the beginning (`ltrim`), end (`rtrim`), or both side
178 * (`trim`) of a string.
180 extern void strbuf_trim(struct strbuf
*);
181 extern void strbuf_rtrim(struct strbuf
*);
182 extern void strbuf_ltrim(struct strbuf
*);
185 * Replace the contents of the strbuf with a reencoded form. Returns -1
186 * on error, 0 on success.
188 extern int strbuf_reencode(struct strbuf
*sb
, const char *from
, const char *to
);
191 * Lowercase each character in the buffer using `tolower`.
193 extern void strbuf_tolower(struct strbuf
*sb
);
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.
200 extern int strbuf_cmp(const struct strbuf
*, const struct strbuf
*);
204 * Adding data to the buffer
205 * -------------------------
207 * NOTE: All of the functions in this section will grow the buffer as
208 * necessary. If they fail for some reason other than memory shortage and the
209 * buffer hadn't been allocated before (i.e. the `struct strbuf` was set to
210 * `STRBUF_INIT`), then they will free() it.
214 * Add a single character to the buffer.
216 static inline void strbuf_addch(struct strbuf
*sb
, int c
)
218 if (!strbuf_avail(sb
))
220 sb
->buf
[sb
->len
++] = c
;
221 sb
->buf
[sb
->len
] = '\0';
225 * Add a character the specified number of times to the buffer.
227 extern void strbuf_addchars(struct strbuf
*sb
, int c
, size_t n
);
230 * Insert data to the given position of the buffer. The remaining contents
231 * will be shifted, not overwritten.
233 extern void strbuf_insert(struct strbuf
*, size_t pos
, const void *, size_t);
236 * Remove given amount of data from a given position of the buffer.
238 extern void strbuf_remove(struct strbuf
*, size_t pos
, size_t len
);
241 * Remove the bytes between `pos..pos+len` and replace it with the given
244 extern void strbuf_splice(struct strbuf
*, size_t pos
, size_t len
,
245 const void *, size_t);
248 * Add a NUL-terminated string to the buffer. Each line will be prepended
249 * by a comment character and a blank.
251 extern void strbuf_add_commented_lines(struct strbuf
*out
, const char *buf
, size_t size
);
255 * Add data of given length to the buffer.
257 extern void strbuf_add(struct strbuf
*, const void *, size_t);
260 * Add a NUL-terminated string to the buffer.
262 * NOTE: This function will *always* be implemented as an inline or a macro
263 * using strlen, meaning that this is efficient to write things like:
265 * strbuf_addstr(sb, "immediate string");
268 static inline void strbuf_addstr(struct strbuf
*sb
, const char *s
)
270 strbuf_add(sb
, s
, strlen(s
));
274 * Copy the contents of another buffer at the end of the current one.
276 extern void strbuf_addbuf(struct strbuf
*sb
, const struct strbuf
*sb2
);
279 * This function can be used to expand a format string containing
280 * placeholders. To that end, it parses the string and calls the specified
281 * function for every percent sign found.
283 * The callback function is given a pointer to the character after the `%`
284 * and a pointer to the struct strbuf. It is expected to add the expanded
285 * version of the placeholder to the strbuf, e.g. to add a newline
286 * character if the letter `n` appears after a `%`. The function returns
287 * the length of the placeholder recognized and `strbuf_expand()` skips
290 * The format `%%` is automatically expanded to a single `%` as a quoting
291 * mechanism; callers do not need to handle the `%` placeholder themselves,
292 * and the callback function will not be invoked for this placeholder.
294 * All other characters (non-percent and not skipped ones) are copied
295 * verbatim to the strbuf. If the callback returned zero, meaning that the
296 * placeholder is unknown, then the percent sign is copied, too.
298 * In order to facilitate caching and to make it possible to give
299 * parameters to the callback, `strbuf_expand()` passes a context pointer,
300 * which can be used by the programmer of the callback as she sees fit.
302 typedef size_t (*expand_fn_t
) (struct strbuf
*sb
, const char *placeholder
, void *context
);
303 extern void strbuf_expand(struct strbuf
*sb
, const char *format
, expand_fn_t fn
, void *context
);
306 * Used as callback for `strbuf_expand()`, expects an array of
307 * struct strbuf_expand_dict_entry as context, i.e. pairs of
308 * placeholder and replacement string. The array needs to be
309 * terminated by an entry with placeholder set to NULL.
311 struct strbuf_expand_dict_entry
{
312 const char *placeholder
;
315 extern size_t strbuf_expand_dict_cb(struct strbuf
*sb
, const char *placeholder
, void *context
);
318 * Append the contents of one strbuf to another, quoting any
319 * percent signs ("%") into double-percents ("%%") in the
320 * destination. This is useful for literal data to be fed to either
321 * strbuf_expand or to the *printf family of functions.
323 extern void strbuf_addbuf_percentquote(struct strbuf
*dst
, const struct strbuf
*src
);
326 * Append the given byte size as a human-readable string (i.e. 12.23 KiB,
329 extern void strbuf_humanise_bytes(struct strbuf
*buf
, off_t bytes
);
332 * Add a formatted string to the buffer.
334 __attribute__((format (printf
,2,3)))
335 extern void strbuf_addf(struct strbuf
*sb
, const char *fmt
, ...);
338 * Add a formatted string prepended by a comment character and a
339 * blank to the buffer.
341 __attribute__((format (printf
, 2, 3)))
342 extern void strbuf_commented_addf(struct strbuf
*sb
, const char *fmt
, ...);
344 __attribute__((format (printf
,2,0)))
345 extern void strbuf_vaddf(struct strbuf
*sb
, const char *fmt
, va_list ap
);
348 * Add the time specified by `tm`, as formatted by `strftime`.
349 * `tz_offset` is in decimal hhmm format, e.g. -600 means six hours west
350 * of Greenwich, and it's used to expand %z internally. However, tokens
351 * with modifiers (e.g. %Ez) are passed to `strftime`.
352 * `suppress_tz_name`, when set, expands %Z internally to the empty
353 * string rather than passing it to `strftime`.
355 extern void strbuf_addftime(struct strbuf
*sb
, const char *fmt
,
356 const struct tm
*tm
, int tz_offset
,
357 int suppress_tz_name
);
360 * Read a given size of data from a FILE* pointer to the buffer.
362 * NOTE: The buffer is rewound if the read fails. If -1 is returned,
363 * `errno` must be consulted, like you would do for `read(3)`.
364 * `strbuf_read()`, `strbuf_read_file()` and `strbuf_getline_*()`
365 * family of functions have the same behaviour as well.
367 extern size_t strbuf_fread(struct strbuf
*, size_t, FILE *);
370 * Read the contents of a given file descriptor. The third argument can be
371 * used to give a hint about the file size, to avoid reallocs. If read fails,
372 * any partial read is undone.
374 extern ssize_t
strbuf_read(struct strbuf
*, int fd
, size_t hint
);
377 * Read the contents of a given file descriptor partially by using only one
378 * attempt of xread. The third argument can be used to give a hint about the
379 * file size, to avoid reallocs. Returns the number of new bytes appended to
382 extern ssize_t
strbuf_read_once(struct strbuf
*, int fd
, size_t hint
);
385 * Read the contents of a file, specified by its path. The third argument
386 * can be used to give a hint about the file size, to avoid reallocs.
387 * Return the number of bytes read or a negative value if some error
388 * occurred while opening or reading the file.
390 extern ssize_t
strbuf_read_file(struct strbuf
*sb
, const char *path
, size_t hint
);
393 * Read the target of a symbolic link, specified by its path. The third
394 * argument can be used to give a hint about the size, to avoid reallocs.
396 extern int strbuf_readlink(struct strbuf
*sb
, const char *path
, size_t hint
);
399 * Write the whole content of the strbuf to the stream not stopping at
402 extern ssize_t
strbuf_write(struct strbuf
*sb
, FILE *stream
);
405 * Read a line from a FILE *, overwriting the existing contents of
406 * the strbuf. The strbuf_getline*() family of functions share
407 * this signature, but have different line termination conventions.
409 * Reading stops after the terminator or at EOF. The terminator
410 * is removed from the buffer before returning. Returns 0 unless
411 * there was nothing left before EOF, in which case it returns `EOF`.
413 typedef int (*strbuf_getline_fn
)(struct strbuf
*, FILE *);
415 /* Uses LF as the line terminator */
416 extern int strbuf_getline_lf(struct strbuf
*sb
, FILE *fp
);
418 /* Uses NUL as the line terminator */
419 extern int strbuf_getline_nul(struct strbuf
*sb
, FILE *fp
);
422 * Similar to strbuf_getline_lf(), but additionally treats a CR that
423 * comes immediately before the LF as part of the terminator.
424 * This is the most friendly version to be used to read "text" files
425 * that can come from platforms whose native text format is CRLF
428 extern int strbuf_getline(struct strbuf
*, FILE *);
432 * Like `strbuf_getline`, but keeps the trailing terminator (if
433 * any) in the buffer.
435 extern int strbuf_getwholeline(struct strbuf
*, FILE *, int);
438 * Like `strbuf_getwholeline`, but operates on a file descriptor.
439 * It reads one character at a time, so it is very slow. Do not
440 * use it unless you need the correct position in the file
443 extern int strbuf_getwholeline_fd(struct strbuf
*, int, int);
446 * Set the buffer to the path of the current working directory.
448 extern int strbuf_getcwd(struct strbuf
*sb
);
451 * Add a path to a buffer, converting a relative path to an
452 * absolute one in the process. Symbolic links are not
455 extern void strbuf_add_absolute_path(struct strbuf
*sb
, const char *path
);
458 * Canonize `path` (make it absolute, resolve symlinks, remove extra
459 * slashes) and append it to `sb`. Die with an informative error
460 * message if there is a problem.
462 * The directory part of `path` (i.e., everything up to the last
463 * dir_sep) must denote a valid, existing directory, but the last
464 * component need not exist.
466 * Callers that don't mind links should use the more lightweight
467 * strbuf_add_absolute_path() instead.
469 extern void strbuf_add_real_path(struct strbuf
*sb
, const char *path
);
473 * Normalize in-place the path contained in the strbuf. See
474 * normalize_path_copy() for details. If an error occurs, the contents of "sb"
475 * are left untouched, and -1 is returned.
477 extern int strbuf_normalize_path(struct strbuf
*sb
);
480 * Strip whitespace from a buffer. The second parameter controls if
481 * comments are considered contents to be removed or not.
483 extern void strbuf_stripspace(struct strbuf
*buf
, int skip_comments
);
485 static inline int strbuf_strip_suffix(struct strbuf
*sb
, const char *suffix
)
487 if (strip_suffix_mem(sb
->buf
, &sb
->len
, suffix
)) {
488 strbuf_setlen(sb
, sb
->len
);
495 * Split str (of length slen) at the specified terminator character.
496 * Return a null-terminated array of pointers to strbuf objects
497 * holding the substrings. The substrings include the terminator,
498 * except for the last substring, which might be unterminated if the
499 * original string did not end with a terminator. If max is positive,
500 * then split the string into at most max substrings (with the last
501 * substring containing everything following the (max-1)th terminator
504 * The most generic form is `strbuf_split_buf`, which takes an arbitrary
505 * pointer/len buffer. The `_str` variant takes a NUL-terminated string,
506 * the `_max` variant takes a strbuf, and just `strbuf_split` is a convenience
507 * wrapper to drop the `max` parameter.
509 * For lighter-weight alternatives, see string_list_split() and
510 * string_list_split_in_place().
512 extern struct strbuf
**strbuf_split_buf(const char *, size_t,
513 int terminator
, int max
);
515 static inline struct strbuf
**strbuf_split_str(const char *str
,
516 int terminator
, int max
)
518 return strbuf_split_buf(str
, strlen(str
), terminator
, max
);
521 static inline struct strbuf
**strbuf_split_max(const struct strbuf
*sb
,
522 int terminator
, int max
)
524 return strbuf_split_buf(sb
->buf
, sb
->len
, terminator
, max
);
527 static inline struct strbuf
**strbuf_split(const struct strbuf
*sb
,
530 return strbuf_split_max(sb
, terminator
, 0);
534 * Adds all strings of a string list to the strbuf, separated by the given
535 * separator. For example, if sep is
538 * ['element1', 'element2', ..., 'elementN'],
540 * 'element1, element2, ..., elementN'
541 * to str. If only one element, just write "element1" to str.
543 extern void strbuf_add_separated_string_list(struct strbuf
*str
,
545 struct string_list
*slist
);
548 * Free a NULL-terminated list of strbufs (for example, the return
549 * values of the strbuf_split*() functions).
551 extern void strbuf_list_free(struct strbuf
**);
554 * Add the abbreviation, as generated by find_unique_abbrev, of `sha1` to
557 extern void strbuf_add_unique_abbrev(struct strbuf
*sb
,
558 const unsigned char *sha1
,
562 * Launch the user preferred editor to edit a file and fill the buffer
563 * with the file's contents upon the user completing their editing. The
564 * third argument can be used to set the environment which the editor is
565 * run in. If the buffer is NULL the editor is launched as usual but the
566 * file's contents are not read into the buffer upon completion.
568 extern int launch_editor(const char *path
, struct strbuf
*buffer
, const char *const *env
);
570 extern void strbuf_add_lines(struct strbuf
*sb
, const char *prefix
, const char *buf
, size_t size
);
573 * Append s to sb, with the characters '<', '>', '&' and '"' converted
576 extern void strbuf_addstr_xml_quoted(struct strbuf
*sb
, const char *s
);
579 * "Complete" the contents of `sb` by ensuring that either it ends with the
580 * character `term`, or it is empty. This can be used, for example,
581 * to ensure that text ends with a newline, but without creating an empty
582 * blank line if there is no content in the first place.
584 static inline void strbuf_complete(struct strbuf
*sb
, char term
)
586 if (sb
->len
&& sb
->buf
[sb
->len
- 1] != term
)
587 strbuf_addch(sb
, term
);
590 static inline void strbuf_complete_line(struct strbuf
*sb
)
592 strbuf_complete(sb
, '\n');
596 * Copy "name" to "sb", expanding any special @-marks as handled by
597 * interpret_branch_name(). The result is a non-qualified branch name
598 * (so "foo" or "origin/master" instead of "refs/heads/foo" or
599 * "refs/remotes/origin/master").
601 * Note that the resulting name may not be a syntactically valid refname.
603 * If "allowed" is non-zero, restrict the set of allowed expansions. See
604 * interpret_branch_name() for details.
606 extern void strbuf_branchname(struct strbuf
*sb
, const char *name
,
610 * Like strbuf_branchname() above, but confirm that the result is
611 * syntactically valid to be used as a local branch name in refs/heads/.
613 * The return value is "0" if the result is valid, and "-1" otherwise.
615 extern int strbuf_check_branch_ref(struct strbuf
*sb
, const char *name
);
617 extern void strbuf_addstr_urlencode(struct strbuf
*, const char *,
620 __attribute__((format (printf
,1,2)))
621 extern int printf_ln(const char *fmt
, ...);
622 __attribute__((format (printf
,2,3)))
623 extern int fprintf_ln(FILE *fp
, const char *fmt
, ...);
625 char *xstrdup_tolower(const char *);
628 * Create a newly allocated string using printf format. You can do this easily
629 * with a strbuf, but this provides a shortcut to save a few lines.
631 __attribute__((format (printf
, 1, 0)))
632 char *xstrvfmt(const char *fmt
, va_list ap
);
633 __attribute__((format (printf
, 1, 2)))
634 char *xstrfmt(const char *fmt
, ...);
636 #endif /* STRBUF_H */