strbuf: introduce strbuf_getline_{lf,nul}()
[git/git.git] / 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 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 */
126 static 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 */
138 extern 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 */
147 static 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 (`ltrim`), end (`rtrim`), or both side
168 * (`trim`) of a string.
169 */
170 extern void strbuf_trim(struct strbuf *);
171 extern void strbuf_rtrim(struct strbuf *);
172 extern void strbuf_ltrim(struct strbuf *);
173
174 /**
175 * Replace the contents of the strbuf with a reencoded form. Returns -1
176 * on error, 0 on success.
177 */
178 extern int strbuf_reencode(struct strbuf *sb, const char *from, const char *to);
179
180 /**
181 * Lowercase each character in the buffer using `tolower`.
182 */
183 extern void strbuf_tolower(struct strbuf *sb);
184
185 /**
186 * Compare two buffers. Returns an integer less than, equal to, or greater
187 * than zero if the first buffer is found, respectively, to be less than,
188 * to match, or be greater than the second buffer.
189 */
190 extern int strbuf_cmp(const struct strbuf *, const struct strbuf *);
191
192
193 /**
194 * Adding data to the buffer
195 * -------------------------
196 *
197 * NOTE: All of the functions in this section will grow the buffer as
198 * necessary. If they fail for some reason other than memory shortage and the
199 * buffer hadn't been allocated before (i.e. the `struct strbuf` was set to
200 * `STRBUF_INIT`), then they will free() it.
201 */
202
203 /**
204 * Add a single character to the buffer.
205 */
206 static inline void strbuf_addch(struct strbuf *sb, int c)
207 {
208 if (!strbuf_avail(sb))
209 strbuf_grow(sb, 1);
210 sb->buf[sb->len++] = c;
211 sb->buf[sb->len] = '\0';
212 }
213
214 /**
215 * Add a character the specified number of times to the buffer.
216 */
217 extern void strbuf_addchars(struct strbuf *sb, int c, size_t n);
218
219 /**
220 * Insert data to the given position of the buffer. The remaining contents
221 * will be shifted, not overwritten.
222 */
223 extern void strbuf_insert(struct strbuf *, size_t pos, const void *, size_t);
224
225 /**
226 * Remove given amount of data from a given position of the buffer.
227 */
228 extern void strbuf_remove(struct strbuf *, size_t pos, size_t len);
229
230 /**
231 * Remove the bytes between `pos..pos+len` and replace it with the given
232 * data.
233 */
234 extern void strbuf_splice(struct strbuf *, size_t pos, size_t len,
235 const void *, size_t);
236
237 /**
238 * Add a NUL-terminated string to the buffer. Each line will be prepended
239 * by a comment character and a blank.
240 */
241 extern void strbuf_add_commented_lines(struct strbuf *out, const char *buf, size_t size);
242
243
244 /**
245 * Add data of given length to the buffer.
246 */
247 extern void strbuf_add(struct strbuf *, const void *, size_t);
248
249 /**
250 * Add a NUL-terminated string to the buffer.
251 *
252 * NOTE: This function will *always* be implemented as an inline or a macro
253 * using strlen, meaning that this is efficient to write things like:
254 *
255 * strbuf_addstr(sb, "immediate string");
256 *
257 */
258 static inline void strbuf_addstr(struct strbuf *sb, const char *s)
259 {
260 strbuf_add(sb, s, strlen(s));
261 }
262
263 /**
264 * Copy the contents of another buffer at the end of the current one.
265 */
266 static inline void strbuf_addbuf(struct strbuf *sb, const struct strbuf *sb2)
267 {
268 strbuf_grow(sb, sb2->len);
269 strbuf_add(sb, sb2->buf, sb2->len);
270 }
271
272 /**
273 * Copy part of the buffer from a given position till a given length to the
274 * end of the buffer.
275 */
276 extern void strbuf_adddup(struct strbuf *sb, size_t pos, size_t len);
277
278 /**
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.
282 *
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
288 * over it.
289 *
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.
293 *
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.
297 *
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.
301 */
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);
304
305 /**
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.
310 */
311 struct strbuf_expand_dict_entry {
312 const char *placeholder;
313 const char *value;
314 };
315 extern size_t strbuf_expand_dict_cb(struct strbuf *sb, const char *placeholder, void *context);
316
317 /**
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.
322 */
323 extern void strbuf_addbuf_percentquote(struct strbuf *dst, const struct strbuf *src);
324
325 /**
326 * Append the given byte size as a human-readable string (i.e. 12.23 KiB,
327 * 3.50 MiB).
328 */
329 extern void strbuf_humanise_bytes(struct strbuf *buf, off_t bytes);
330
331 /**
332 * Add a formatted string to the buffer.
333 */
334 __attribute__((format (printf,2,3)))
335 extern void strbuf_addf(struct strbuf *sb, const char *fmt, ...);
336
337 /**
338 * Add a formatted string prepended by a comment character and a
339 * blank to the buffer.
340 */
341 __attribute__((format (printf, 2, 3)))
342 extern void strbuf_commented_addf(struct strbuf *sb, const char *fmt, ...);
343
344 __attribute__((format (printf,2,0)))
345 extern void strbuf_vaddf(struct strbuf *sb, const char *fmt, va_list ap);
346
347 /**
348 * Add the time specified by `tm`, as formatted by `strftime`.
349 */
350 extern void strbuf_addftime(struct strbuf *sb, const char *fmt, const struct tm *tm);
351
352 /**
353 * Read a given size of data from a FILE* pointer to the buffer.
354 *
355 * NOTE: The buffer is rewound if the read fails. If -1 is returned,
356 * `errno` must be consulted, like you would do for `read(3)`.
357 * `strbuf_read()`, `strbuf_read_file()` and `strbuf_getline()` has the
358 * same behaviour as well.
359 */
360 extern size_t strbuf_fread(struct strbuf *, size_t, FILE *);
361
362 /**
363 * Read the contents of a given file descriptor. The third argument can be
364 * used to give a hint about the file size, to avoid reallocs. If read fails,
365 * any partial read is undone.
366 */
367 extern ssize_t strbuf_read(struct strbuf *, int fd, size_t hint);
368
369 /**
370 * Read the contents of a file, specified by its path. The third argument
371 * can be used to give a hint about the file size, to avoid reallocs.
372 */
373 extern ssize_t strbuf_read_file(struct strbuf *sb, const char *path, size_t hint);
374
375 /**
376 * Read the target of a symbolic link, specified by its path. The third
377 * argument can be used to give a hint about the size, to avoid reallocs.
378 */
379 extern int strbuf_readlink(struct strbuf *sb, const char *path, size_t hint);
380
381 /**
382 * Read a line from a FILE *, overwriting the existing contents
383 * of the strbuf. The second argument specifies the line
384 * terminator character, typically `'\n'`.
385 * Reading stops after the terminator or at EOF. The terminator
386 * is removed from the buffer before returning. Returns 0 unless
387 * there was nothing left before EOF, in which case it returns `EOF`.
388 */
389 extern int strbuf_getline(struct strbuf *, FILE *, int);
390
391 /**
392 * The strbuf_getline*() family of functions share this signature, but
393 * have different line termination conventions.
394 */
395 typedef int (*strbuf_getline_fn)(struct strbuf *, FILE *);
396
397 /* Uses LF as the line terminator */
398 extern int strbuf_getline_lf(struct strbuf *sb, FILE *fp);
399
400 /* Uses NUL as the line terminator */
401 extern int strbuf_getline_nul(struct strbuf *sb, FILE *fp);
402
403 /*
404 * Similar to strbuf_getline_lf(), but additionally treats a CR that
405 * comes immediately before the LF as part of the terminator.
406 */
407 extern int strbuf_getline_crlf(struct strbuf *, FILE *);
408
409
410 /**
411 * Like `strbuf_getline`, but keeps the trailing terminator (if
412 * any) in the buffer.
413 */
414 extern int strbuf_getwholeline(struct strbuf *, FILE *, int);
415
416 /**
417 * Like `strbuf_getwholeline`, but operates on a file descriptor.
418 * It reads one character at a time, so it is very slow. Do not
419 * use it unless you need the correct position in the file
420 * descriptor.
421 */
422 extern int strbuf_getwholeline_fd(struct strbuf *, int, int);
423
424 /**
425 * Set the buffer to the path of the current working directory.
426 */
427 extern int strbuf_getcwd(struct strbuf *sb);
428
429 /**
430 * Add a path to a buffer, converting a relative path to an
431 * absolute one in the process. Symbolic links are not
432 * resolved.
433 */
434 extern void strbuf_add_absolute_path(struct strbuf *sb, const char *path);
435
436 /**
437 * Strip whitespace from a buffer. The second parameter controls if
438 * comments are considered contents to be removed or not.
439 */
440 extern void strbuf_stripspace(struct strbuf *buf, int skip_comments);
441
442 /**
443 * Temporary alias until all topic branches have switched to use
444 * strbuf_stripspace directly.
445 */
446 static inline void stripspace(struct strbuf *buf, int skip_comments)
447 {
448 strbuf_stripspace(buf, skip_comments);
449 }
450
451 static inline int strbuf_strip_suffix(struct strbuf *sb, const char *suffix)
452 {
453 if (strip_suffix_mem(sb->buf, &sb->len, suffix)) {
454 strbuf_setlen(sb, sb->len);
455 return 1;
456 } else
457 return 0;
458 }
459
460 /**
461 * Split str (of length slen) at the specified terminator character.
462 * Return a null-terminated array of pointers to strbuf objects
463 * holding the substrings. The substrings include the terminator,
464 * except for the last substring, which might be unterminated if the
465 * original string did not end with a terminator. If max is positive,
466 * then split the string into at most max substrings (with the last
467 * substring containing everything following the (max-1)th terminator
468 * character).
469 *
470 * The most generic form is `strbuf_split_buf`, which takes an arbitrary
471 * pointer/len buffer. The `_str` variant takes a NUL-terminated string,
472 * the `_max` variant takes a strbuf, and just `strbuf_split` is a convenience
473 * wrapper to drop the `max` parameter.
474 *
475 * For lighter-weight alternatives, see string_list_split() and
476 * string_list_split_in_place().
477 */
478 extern struct strbuf **strbuf_split_buf(const char *, size_t,
479 int terminator, int max);
480
481 static inline struct strbuf **strbuf_split_str(const char *str,
482 int terminator, int max)
483 {
484 return strbuf_split_buf(str, strlen(str), terminator, max);
485 }
486
487 static inline struct strbuf **strbuf_split_max(const struct strbuf *sb,
488 int terminator, int max)
489 {
490 return strbuf_split_buf(sb->buf, sb->len, terminator, max);
491 }
492
493 static inline struct strbuf **strbuf_split(const struct strbuf *sb,
494 int terminator)
495 {
496 return strbuf_split_max(sb, terminator, 0);
497 }
498
499 /**
500 * Free a NULL-terminated list of strbufs (for example, the return
501 * values of the strbuf_split*() functions).
502 */
503 extern void strbuf_list_free(struct strbuf **);
504
505 /**
506 * Add the abbreviation, as generated by find_unique_abbrev, of `sha1` to
507 * the strbuf `sb`.
508 */
509 extern void strbuf_add_unique_abbrev(struct strbuf *sb,
510 const unsigned char *sha1,
511 int abbrev_len);
512
513 /**
514 * Launch the user preferred editor to edit a file and fill the buffer
515 * with the file's contents upon the user completing their editing. The
516 * third argument can be used to set the environment which the editor is
517 * run in. If the buffer is NULL the editor is launched as usual but the
518 * file's contents are not read into the buffer upon completion.
519 */
520 extern int launch_editor(const char *path, struct strbuf *buffer, const char *const *env);
521
522 extern void strbuf_add_lines(struct strbuf *sb, const char *prefix, const char *buf, size_t size);
523
524 /**
525 * Append s to sb, with the characters '<', '>', '&' and '"' converted
526 * into XML entities.
527 */
528 extern void strbuf_addstr_xml_quoted(struct strbuf *sb, const char *s);
529
530 /**
531 * "Complete" the contents of `sb` by ensuring that either it ends with the
532 * character `term`, or it is empty. This can be used, for example,
533 * to ensure that text ends with a newline, but without creating an empty
534 * blank line if there is no content in the first place.
535 */
536 static inline void strbuf_complete(struct strbuf *sb, char term)
537 {
538 if (sb->len && sb->buf[sb->len - 1] != term)
539 strbuf_addch(sb, term);
540 }
541
542 static inline void strbuf_complete_line(struct strbuf *sb)
543 {
544 strbuf_complete(sb, '\n');
545 }
546
547 extern int strbuf_branchname(struct strbuf *sb, const char *name);
548 extern int strbuf_check_branch_ref(struct strbuf *sb, const char *name);
549
550 extern void strbuf_addstr_urlencode(struct strbuf *, const char *,
551 int reserved);
552
553 __attribute__((format (printf,1,2)))
554 extern int printf_ln(const char *fmt, ...);
555 __attribute__((format (printf,2,3)))
556 extern int fprintf_ln(FILE *fp, const char *fmt, ...);
557
558 char *xstrdup_tolower(const char *);
559
560 /**
561 * Create a newly allocated string using printf format. You can do this easily
562 * with a strbuf, but this provides a shortcut to save a few lines.
563 */
564 __attribute__((format (printf, 1, 0)))
565 char *xstrvfmt(const char *fmt, va_list ap);
566 __attribute__((format (printf, 1, 2)))
567 char *xstrfmt(const char *fmt, ...);
568
569 #endif /* STRBUF_H */