
The current implementation of `sdssplitargs` does repeated `sdscatlen`
to build the parsed arguments, which isn't very efficient because it
does a lot of extra reallocations and moves through the sds code a lot.
It also typically results in memory overhead, because `sdscatlen`
over-allocates, which is usually not needed since args are usually not
modified after being created.
The new implementation of sdssplitargs does two passes, the first to
parse the argument to figure out the final length and the second to
actually copy the string. It's generally about 2x faster for larger
strings (~100 bytes), and about 20% faster for small strings (~10
bytes). This is generally faster since as long as everything is in the
CPU cache, it's going to be fast.
There are a couple of sanity tests, none existed before, as well as some
fuzzying which was used to find some bugs and also to do the
benchmarking. The original benchmarking code can be seen
6576aeb86a
.
```
test_sdssplitargs_benchmark - unit/test_sds.c:530] Using random seed: 1729883235
[test_sdssplitargs_benchmark - unit/test_sds.c:577] Improvement: 56.44%, new:13039us, old:29930us
[test_sdssplitargs_benchmark - unit/test_sds.c:577] Improvement: 56.58%, new:12057us, old:27771us
[test_sdssplitargs_benchmark - unit/test_sds.c:577] Improvement: 59.18%, new:9048us, old:22165us
[test_sdssplitargs_benchmark - unit/test_sds.c:577] Improvement: 54.61%, new:12381us, old:27278us
[test_sdssplitargs_benchmark - unit/test_sds.c:577] Improvement: 51.17%, new:16012us, old:32793us
[test_sdssplitargs_benchmark - unit/test_sds.c:577] Improvement: 49.18%, new:16041us, old:31563us
[test_sdssplitargs_benchmark - unit/test_sds.c:577] Improvement: 58.40%, new:12450us, old:29930us
[test_sdssplitargs_benchmark - unit/test_sds.c:577] Improvement: 56.49%, new:13066us, old:30031us
[test_sdssplitargs_benchmark - unit/test_sds.c:577] Improvement: 58.75%, new:12744us, old:30894us
[test_sdssplitargs_benchmark - unit/test_sds.c:577] Improvement: 52.44%, new:16885us, old:35504us
[test_sdssplitargs_benchmark - unit/test_sds.c:577] Improvement: 62.57%, new:8107us, old:21659us
[test_sdssplitargs_benchmark - unit/test_sds.c:577] Improvement: 62.12%, new:8320us, old:21966us
[test_sdssplitargs_benchmark - unit/test_sds.c:577] Improvement: 45.23%, new:13960us, old:25487us
[test_sdssplitargs_benchmark - unit/test_sds.c:577] Improvement: 57.95%, new:9188us, old:21849us
```
---------
Signed-off-by: Madelyn Olson <madelyneolson@gmail.com>
1288 lines
42 KiB
C
1288 lines
42 KiB
C
/* SDSLib 2.0 -- A C dynamic strings library
|
|
*
|
|
* Copyright (c) 2006-2015, Redis Ltd.
|
|
* Copyright (c) 2015, Oran Agra
|
|
* All rights reserved.
|
|
*
|
|
* Redistribution and use in source and binary forms, with or without
|
|
* modification, are permitted provided that the following conditions are met:
|
|
*
|
|
* * Redistributions of source code must retain the above copyright notice,
|
|
* this list of conditions and the following disclaimer.
|
|
* * Redistributions in binary form must reproduce the above copyright
|
|
* notice, this list of conditions and the following disclaimer in the
|
|
* documentation and/or other materials provided with the distribution.
|
|
* * Neither the name of Redis nor the names of its contributors may be used
|
|
* to endorse or promote products derived from this software without
|
|
* specific prior written permission.
|
|
*
|
|
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
|
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
|
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
|
* ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
|
|
* LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
|
|
* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
|
|
* SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
|
|
* INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
|
|
* CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
|
|
* ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
|
|
* POSSIBILITY OF SUCH DAMAGE.
|
|
*/
|
|
|
|
#include <stdio.h>
|
|
#include <stdlib.h>
|
|
#include <string.h>
|
|
#include <ctype.h>
|
|
#include <limits.h>
|
|
#include "serverassert.h"
|
|
#include "sds.h"
|
|
#include "sdsalloc.h"
|
|
#include "util.h"
|
|
|
|
const char *SDS_NOINIT = "SDS_NOINIT";
|
|
|
|
static inline int sdsHdrSize(char type) {
|
|
switch (type & SDS_TYPE_MASK) {
|
|
case SDS_TYPE_5: return sizeof(struct sdshdr5);
|
|
case SDS_TYPE_8: return sizeof(struct sdshdr8);
|
|
case SDS_TYPE_16: return sizeof(struct sdshdr16);
|
|
case SDS_TYPE_32: return sizeof(struct sdshdr32);
|
|
case SDS_TYPE_64: return sizeof(struct sdshdr64);
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static inline char sdsReqType(size_t string_size) {
|
|
if (string_size < 1 << 5) return SDS_TYPE_5;
|
|
if (string_size <= (1 << 8) - sizeof(struct sdshdr8) - 1) return SDS_TYPE_8;
|
|
if (string_size <= (1 << 16) - sizeof(struct sdshdr16) - 1) return SDS_TYPE_16;
|
|
#if (LONG_MAX == LLONG_MAX)
|
|
if (string_size <= (1ll << 32) - sizeof(struct sdshdr32) - 1) return SDS_TYPE_32;
|
|
return SDS_TYPE_64;
|
|
#else
|
|
return SDS_TYPE_32;
|
|
#endif
|
|
}
|
|
|
|
static inline size_t sdsTypeMaxSize(char type) {
|
|
if (type == SDS_TYPE_5) return (1 << 5) - 1;
|
|
if (type == SDS_TYPE_8) return (1 << 8) - 1;
|
|
if (type == SDS_TYPE_16) return (1 << 16) - 1;
|
|
#if (LONG_MAX == LLONG_MAX)
|
|
if (type == SDS_TYPE_32) return (1ll << 32) - 1;
|
|
#endif
|
|
return -1; /* this is equivalent to the max SDS_TYPE_64 or SDS_TYPE_32 */
|
|
}
|
|
|
|
static inline int adjustTypeIfNeeded(char *type, int *hdrlen, size_t bufsize) {
|
|
size_t usable = bufsize - *hdrlen - 1;
|
|
if (*type != SDS_TYPE_5 && usable > sdsTypeMaxSize(*type)) {
|
|
*type = sdsReqType(usable);
|
|
*hdrlen = sdsHdrSize(*type);
|
|
return 1;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
/* Create a new sds string with the content specified by the 'init' pointer
|
|
* and 'initlen'.
|
|
* If NULL is used for 'init' the string is initialized with zero bytes.
|
|
* If SDS_NOINIT is used, the buffer is left uninitialized;
|
|
*
|
|
* The string is always null-terminated (all the sds strings are, always) so
|
|
* even if you create an sds string with:
|
|
*
|
|
* mystring = sdsnewlen("abc",3);
|
|
*
|
|
* You can print the string with printf() as there is an implicit \0 at the
|
|
* end of the string. However the string is binary safe and can contain
|
|
* \0 characters in the middle, as the length is stored in the sds header. */
|
|
sds _sdsnewlen(const void *init, size_t initlen, int trymalloc) {
|
|
void *sh;
|
|
sds s;
|
|
char type = sdsReqType(initlen);
|
|
/* Empty strings are usually created in order to append. Use type 8
|
|
* since type 5 is not good at this. */
|
|
if (type == SDS_TYPE_5 && initlen == 0) type = SDS_TYPE_8;
|
|
int hdrlen = sdsHdrSize(type);
|
|
unsigned char *fp; /* flags pointer. */
|
|
size_t bufsize, usable;
|
|
|
|
assert(initlen + hdrlen + 1 > initlen); /* Catch size_t overflow */
|
|
sh = trymalloc ? s_trymalloc_usable(hdrlen + initlen + 1, &bufsize)
|
|
: s_malloc_usable(hdrlen + initlen + 1, &bufsize);
|
|
if (sh == NULL) return NULL;
|
|
if (init == SDS_NOINIT)
|
|
init = NULL;
|
|
else if (!init)
|
|
memset(sh, 0, hdrlen + initlen + 1);
|
|
|
|
adjustTypeIfNeeded(&type, &hdrlen, bufsize);
|
|
usable = bufsize - hdrlen - 1;
|
|
|
|
s = (char *)sh + hdrlen;
|
|
fp = ((unsigned char *)s) - 1;
|
|
|
|
switch (type) {
|
|
case SDS_TYPE_5: {
|
|
*fp = type | (initlen << SDS_TYPE_BITS);
|
|
break;
|
|
}
|
|
case SDS_TYPE_8: {
|
|
SDS_HDR_VAR(8, s);
|
|
sh->len = initlen;
|
|
assert(usable <= sdsTypeMaxSize(type));
|
|
sh->alloc = usable;
|
|
*fp = type;
|
|
break;
|
|
}
|
|
case SDS_TYPE_16: {
|
|
SDS_HDR_VAR(16, s);
|
|
sh->len = initlen;
|
|
assert(usable <= sdsTypeMaxSize(type));
|
|
sh->alloc = usable;
|
|
*fp = type;
|
|
break;
|
|
}
|
|
case SDS_TYPE_32: {
|
|
SDS_HDR_VAR(32, s);
|
|
sh->len = initlen;
|
|
assert(usable <= sdsTypeMaxSize(type));
|
|
sh->alloc = usable;
|
|
*fp = type;
|
|
break;
|
|
}
|
|
case SDS_TYPE_64: {
|
|
SDS_HDR_VAR(64, s);
|
|
sh->len = initlen;
|
|
assert(usable <= sdsTypeMaxSize(type));
|
|
sh->alloc = usable;
|
|
*fp = type;
|
|
break;
|
|
}
|
|
}
|
|
if (initlen && init) memcpy(s, init, initlen);
|
|
s[initlen] = '\0';
|
|
return s;
|
|
}
|
|
|
|
sds sdsnewlen(const void *init, size_t initlen) {
|
|
return _sdsnewlen(init, initlen, 0);
|
|
}
|
|
|
|
sds sdstrynewlen(const void *init, size_t initlen) {
|
|
return _sdsnewlen(init, initlen, 1);
|
|
}
|
|
|
|
/* Create an empty (zero length) sds string. Even in this case the string
|
|
* always has an implicit null term. */
|
|
sds sdsempty(void) {
|
|
return sdsnewlen("", 0);
|
|
}
|
|
|
|
/* Create a new sds string starting from a null terminated C string. */
|
|
sds sdsnew(const char *init) {
|
|
size_t initlen = (init == NULL) ? 0 : strlen(init);
|
|
return sdsnewlen(init, initlen);
|
|
}
|
|
|
|
/* Duplicate an sds string. */
|
|
sds sdsdup(const sds s) {
|
|
return sdsnewlen(s, sdslen(s));
|
|
}
|
|
|
|
/*
|
|
* This method returns the minimum amount of bytes required to store the sds (header + data + NULL terminator).
|
|
*/
|
|
static inline size_t sdsminlen(sds s) {
|
|
return sdslen(s) + sdsHdrSize(s[-1]) + 1;
|
|
}
|
|
|
|
/* This method copies the sds `s` into `buf` which is the target character buffer. */
|
|
size_t sdscopytobuffer(unsigned char *buf, size_t buf_len, sds s, uint8_t *hdr_size) {
|
|
size_t required_keylen = sdsminlen(s);
|
|
if (buf == NULL) {
|
|
return required_keylen;
|
|
}
|
|
assert(buf_len >= required_keylen);
|
|
memcpy(buf, sdsAllocPtr(s), required_keylen);
|
|
*hdr_size = sdsHdrSize(s[-1]);
|
|
return required_keylen;
|
|
}
|
|
|
|
/* Free an sds string. No operation is performed if 's' is NULL. */
|
|
void sdsfree(sds s) {
|
|
if (s == NULL) return;
|
|
s_free_with_size(sdsAllocPtr(s), sdsAllocSize(s));
|
|
}
|
|
|
|
/* Set the sds string length to the length as obtained with strlen(), so
|
|
* considering as content only up to the first null term character.
|
|
*
|
|
* This function is useful when the sds string is hacked manually in some
|
|
* way, like in the following example:
|
|
*
|
|
* s = sdsnew("foobar");
|
|
* s[2] = '\0';
|
|
* sdsupdatelen(s);
|
|
* printf("%d\n", sdslen(s));
|
|
*
|
|
* The output will be "2", but if we comment out the call to sdsupdatelen()
|
|
* the output will be "6" as the string was modified but the logical length
|
|
* remains 6 bytes. */
|
|
void sdsupdatelen(sds s) {
|
|
size_t reallen = strlen(s);
|
|
sdssetlen(s, reallen);
|
|
}
|
|
|
|
/* Modify an sds string in-place to make it empty (zero length).
|
|
* However all the existing buffer is not discarded but set as free space
|
|
* so that next append operations will not require allocations up to the
|
|
* number of bytes previously available. */
|
|
void sdsclear(sds s) {
|
|
sdssetlen(s, 0);
|
|
s[0] = '\0';
|
|
}
|
|
|
|
/* Enlarge the free space at the end of the sds string so that the caller
|
|
* is sure that after calling this function can overwrite up to addlen
|
|
* bytes after the end of the string, plus one more byte for nul term.
|
|
* If there's already sufficient free space, this function returns without any
|
|
* action, if there isn't sufficient free space, it'll allocate what's missing,
|
|
* and possibly more:
|
|
* When greedy is 1, enlarge more than needed, to avoid need for future reallocs
|
|
* on incremental growth.
|
|
* When greedy is 0, enlarge just enough so that there's free space for 'addlen'.
|
|
*
|
|
* Note: this does not change the *length* of the sds string as returned
|
|
* by sdslen(), but only the free buffer space we have. */
|
|
sds _sdsMakeRoomFor(sds s, size_t addlen, int greedy) {
|
|
void *sh, *newsh;
|
|
size_t avail = sdsavail(s);
|
|
size_t len, newlen, reqlen;
|
|
char type, oldtype = s[-1] & SDS_TYPE_MASK;
|
|
int hdrlen;
|
|
size_t bufsize, usable;
|
|
int use_realloc;
|
|
|
|
/* Return ASAP if there is enough space left. */
|
|
if (avail >= addlen) return s;
|
|
|
|
len = sdslen(s);
|
|
sh = (char *)s - sdsHdrSize(oldtype);
|
|
reqlen = newlen = (len + addlen);
|
|
assert(newlen > len); /* Catch size_t overflow */
|
|
if (greedy == 1) {
|
|
if (newlen < SDS_MAX_PREALLOC)
|
|
newlen *= 2;
|
|
else
|
|
newlen += SDS_MAX_PREALLOC;
|
|
}
|
|
|
|
type = sdsReqType(newlen);
|
|
|
|
/* Don't use type 5: the user is appending to the string and type 5 is
|
|
* not able to remember empty space, so sdsMakeRoomFor() must be called
|
|
* at every appending operation. */
|
|
if (type == SDS_TYPE_5) type = SDS_TYPE_8;
|
|
|
|
hdrlen = sdsHdrSize(type);
|
|
assert(hdrlen + newlen + 1 > reqlen); /* Catch size_t overflow */
|
|
use_realloc = (oldtype == type);
|
|
if (use_realloc) {
|
|
newsh = s_realloc_usable(sh, hdrlen + newlen + 1, &bufsize);
|
|
if (newsh == NULL) return NULL;
|
|
s = (char *)newsh + hdrlen;
|
|
|
|
if (adjustTypeIfNeeded(&type, &hdrlen, bufsize)) {
|
|
memmove((char *)newsh + hdrlen, s, len + 1);
|
|
s = (char *)newsh + hdrlen;
|
|
s[-1] = type;
|
|
sdssetlen(s, len);
|
|
}
|
|
} else {
|
|
/* Since the header size changes, need to move the string forward,
|
|
* and can't use realloc */
|
|
newsh = s_malloc_usable(hdrlen + newlen + 1, &bufsize);
|
|
if (newsh == NULL) return NULL;
|
|
adjustTypeIfNeeded(&type, &hdrlen, bufsize);
|
|
memcpy((char *)newsh + hdrlen, s, len + 1);
|
|
s_free(sh);
|
|
s = (char *)newsh + hdrlen;
|
|
s[-1] = type;
|
|
sdssetlen(s, len);
|
|
}
|
|
usable = bufsize - hdrlen - 1;
|
|
assert(type == SDS_TYPE_5 || usable <= sdsTypeMaxSize(type));
|
|
sdssetalloc(s, usable);
|
|
return s;
|
|
}
|
|
|
|
/* Enlarge the free space at the end of the sds string more than needed,
|
|
* This is useful to avoid repeated re-allocations when repeatedly appending to the sds. */
|
|
sds sdsMakeRoomFor(sds s, size_t addlen) {
|
|
return _sdsMakeRoomFor(s, addlen, 1);
|
|
}
|
|
|
|
/* Unlike sdsMakeRoomFor(), this one just grows to the necessary size. */
|
|
sds sdsMakeRoomForNonGreedy(sds s, size_t addlen) {
|
|
return _sdsMakeRoomFor(s, addlen, 0);
|
|
}
|
|
|
|
/* Reallocate the sds string so that it has no free space at the end. The
|
|
* contained string remains not altered, but next concatenation operations
|
|
* will require a reallocation.
|
|
*
|
|
* After the call, the passed sds string is no longer valid and all the
|
|
* references must be substituted with the new pointer returned by the call. */
|
|
sds sdsRemoveFreeSpace(sds s, int would_regrow) {
|
|
return sdsResize(s, sdslen(s), would_regrow);
|
|
}
|
|
|
|
/* Resize the allocation, this can make the allocation bigger or smaller,
|
|
* if the size is smaller than currently used len, the data will be truncated.
|
|
*
|
|
* The when the would_regrow argument is set to 1, it prevents the use of
|
|
* SDS_TYPE_5, which is desired when the sds is likely to be changed again. */
|
|
sds sdsResize(sds s, size_t size, int would_regrow) {
|
|
void *sh, *newsh = NULL;
|
|
char type, oldtype = s[-1] & SDS_TYPE_MASK;
|
|
int hdrlen, oldhdrlen = sdsHdrSize(oldtype);
|
|
size_t len = sdslen(s);
|
|
sh = (char *)s - oldhdrlen;
|
|
|
|
/* Return ASAP if the size is already good. */
|
|
if (sdsalloc(s) == size) return s;
|
|
|
|
/* Truncate len if needed. */
|
|
if (size < len) len = size;
|
|
|
|
/* Check what would be the minimum SDS header that is just good enough to
|
|
* fit this string. */
|
|
type = sdsReqType(size);
|
|
if (would_regrow) {
|
|
/* Don't use type 5, it is not good for strings that are expected to grow back. */
|
|
if (type == SDS_TYPE_5) type = SDS_TYPE_8;
|
|
}
|
|
hdrlen = sdsHdrSize(type);
|
|
|
|
/* If the type is the same, or can hold the size in it with low overhead
|
|
* (larger than SDS_TYPE_8), we just realloc(), letting the allocator
|
|
* to do the copy only if really needed. Otherwise if the change is
|
|
* huge, we manually reallocate the string to use the different header
|
|
* type. */
|
|
int use_realloc = (oldtype == type || (type < oldtype && type > SDS_TYPE_8));
|
|
size_t newlen = use_realloc ? oldhdrlen + size + 1 : hdrlen + size + 1;
|
|
size_t bufsize = 0;
|
|
size_t newsize;
|
|
|
|
if (use_realloc) {
|
|
int alloc_already_optimal = 0;
|
|
#if defined(USE_JEMALLOC)
|
|
/* je_nallocx returns the expected allocation size for the newlen.
|
|
* We aim to avoid calling realloc() when using Jemalloc if there is no
|
|
* change in the allocation size, as it incurs a cost even if the
|
|
* allocation size stays the same. */
|
|
bufsize = sdsAllocSize(s);
|
|
alloc_already_optimal = (je_nallocx(newlen, 0) == bufsize);
|
|
#endif
|
|
if (!alloc_already_optimal) {
|
|
newsh = s_realloc_usable(sh, newlen, &bufsize);
|
|
if (newsh == NULL) return NULL;
|
|
s = (char *)newsh + oldhdrlen;
|
|
|
|
if (adjustTypeIfNeeded(&oldtype, &oldhdrlen, bufsize)) {
|
|
memmove((char *)newsh + oldhdrlen, s, len + 1);
|
|
s = (char *)newsh + oldhdrlen;
|
|
s[-1] = oldtype;
|
|
sdssetlen(s, len);
|
|
}
|
|
}
|
|
newsize = bufsize - oldhdrlen - 1;
|
|
assert(oldtype == SDS_TYPE_5 || newsize <= sdsTypeMaxSize(oldtype));
|
|
} else {
|
|
newsh = s_malloc_usable(newlen, &bufsize);
|
|
if (newsh == NULL) return NULL;
|
|
adjustTypeIfNeeded(&type, &hdrlen, bufsize);
|
|
memcpy((char *)newsh + hdrlen, s, len + 1);
|
|
s_free(sh);
|
|
s = (char *)newsh + hdrlen;
|
|
s[-1] = type;
|
|
newsize = bufsize - hdrlen - 1;
|
|
assert(type == SDS_TYPE_5 || newsize <= sdsTypeMaxSize(type));
|
|
}
|
|
|
|
s[len] = '\0';
|
|
sdssetlen(s, len);
|
|
sdssetalloc(s, newsize);
|
|
return s;
|
|
}
|
|
|
|
/* Return the total size of the allocation of the specified sds string,
|
|
* including:
|
|
* 1) The sds header before the pointer.
|
|
* 2) The string.
|
|
* 3) The free buffer at the end if any.
|
|
* 4) The implicit null term.
|
|
*/
|
|
size_t sdsAllocSize(sds s) {
|
|
char type = s[-1] & SDS_TYPE_MASK;
|
|
/* SDS_TYPE_5 header doesn't contain the size of the allocation */
|
|
if (type == SDS_TYPE_5) {
|
|
return s_malloc_usable_size(sdsAllocPtr(s));
|
|
} else {
|
|
return sdsHdrSize(type) + sdsalloc(s) + 1;
|
|
}
|
|
}
|
|
|
|
/* Return the pointer of the actual SDS allocation (normally SDS strings
|
|
* are referenced by the start of the string buffer). */
|
|
void *sdsAllocPtr(sds s) {
|
|
return (void *)(s - sdsHdrSize(s[-1]));
|
|
}
|
|
|
|
/* Increment the sds length and decrements the left free space at the
|
|
* end of the string according to 'incr'. Also set the null term
|
|
* in the new end of the string.
|
|
*
|
|
* This function is used in order to fix the string length after the
|
|
* user calls sdsMakeRoomFor(), writes something after the end of
|
|
* the current string, and finally needs to set the new length.
|
|
*
|
|
* Note: it is possible to use a negative increment in order to
|
|
* right-trim the string.
|
|
*
|
|
* Usage example:
|
|
*
|
|
* Using sdsIncrLen() and sdsMakeRoomFor() it is possible to mount the
|
|
* following schema, to cat bytes coming from the kernel to the end of an
|
|
* sds string without copying into an intermediate buffer:
|
|
*
|
|
* oldlen = sdslen(s);
|
|
* s = sdsMakeRoomFor(s, BUFFER_SIZE);
|
|
* nread = read(fd, s+oldlen, BUFFER_SIZE);
|
|
* ... check for nread <= 0 and handle it ...
|
|
* sdsIncrLen(s, nread);
|
|
*/
|
|
void sdsIncrLen(sds s, ssize_t incr) {
|
|
unsigned char flags = s[-1];
|
|
size_t len;
|
|
switch (flags & SDS_TYPE_MASK) {
|
|
case SDS_TYPE_5: {
|
|
unsigned char *fp = ((unsigned char *)s) - 1;
|
|
unsigned char oldlen = SDS_TYPE_5_LEN(flags);
|
|
assert((incr > 0 && oldlen + incr < 32) || (incr < 0 && oldlen >= (unsigned int)(-incr)));
|
|
*fp = SDS_TYPE_5 | ((oldlen + incr) << SDS_TYPE_BITS);
|
|
len = oldlen + incr;
|
|
break;
|
|
}
|
|
case SDS_TYPE_8: {
|
|
SDS_HDR_VAR(8, s);
|
|
assert((incr >= 0 && sh->alloc - sh->len >= incr) || (incr < 0 && sh->len >= (unsigned int)(-incr)));
|
|
len = (sh->len += incr);
|
|
break;
|
|
}
|
|
case SDS_TYPE_16: {
|
|
SDS_HDR_VAR(16, s);
|
|
assert((incr >= 0 && sh->alloc - sh->len >= incr) || (incr < 0 && sh->len >= (unsigned int)(-incr)));
|
|
len = (sh->len += incr);
|
|
break;
|
|
}
|
|
case SDS_TYPE_32: {
|
|
SDS_HDR_VAR(32, s);
|
|
assert((incr >= 0 && sh->alloc - sh->len >= (unsigned int)incr) ||
|
|
(incr < 0 && sh->len >= (unsigned int)(-incr)));
|
|
len = (sh->len += incr);
|
|
break;
|
|
}
|
|
case SDS_TYPE_64: {
|
|
SDS_HDR_VAR(64, s);
|
|
assert((incr >= 0 && sh->alloc - sh->len >= (uint64_t)incr) || (incr < 0 && sh->len >= (uint64_t)(-incr)));
|
|
len = (sh->len += incr);
|
|
break;
|
|
}
|
|
default: len = 0; /* Just to avoid compilation warnings. */
|
|
}
|
|
s[len] = '\0';
|
|
}
|
|
|
|
/* Grow the sds to have the specified length. Bytes that were not part of
|
|
* the original length of the sds will be set to zero.
|
|
*
|
|
* if the specified length is smaller than the current length, no operation
|
|
* is performed. */
|
|
sds sdsgrowzero(sds s, size_t len) {
|
|
size_t curlen = sdslen(s);
|
|
|
|
if (len <= curlen) return s;
|
|
s = sdsMakeRoomFor(s, len - curlen);
|
|
if (s == NULL) return NULL;
|
|
|
|
/* Make sure added region doesn't contain garbage */
|
|
memset(s + curlen, 0, (len - curlen + 1)); /* also set trailing \0 byte */
|
|
sdssetlen(s, len);
|
|
return s;
|
|
}
|
|
|
|
/* Append the specified binary-safe string pointed by 't' of 'len' bytes to the
|
|
* end of the specified sds string 's'.
|
|
*
|
|
* After the call, the passed sds string is no longer valid and all the
|
|
* references must be substituted with the new pointer returned by the call. */
|
|
sds sdscatlen(sds s, const void *t, size_t len) {
|
|
size_t curlen = sdslen(s);
|
|
|
|
s = sdsMakeRoomFor(s, len);
|
|
if (s == NULL) return NULL;
|
|
memcpy(s + curlen, t, len);
|
|
sdssetlen(s, curlen + len);
|
|
s[curlen + len] = '\0';
|
|
return s;
|
|
}
|
|
|
|
/* Append the specified null terminated C string to the sds string 's'.
|
|
*
|
|
* After the call, the passed sds string is no longer valid and all the
|
|
* references must be substituted with the new pointer returned by the call. */
|
|
sds sdscat(sds s, const char *t) {
|
|
return sdscatlen(s, t, strlen(t));
|
|
}
|
|
|
|
/* Append the specified sds 't' to the existing sds 's'.
|
|
*
|
|
* After the call, the modified sds string is no longer valid and all the
|
|
* references must be substituted with the new pointer returned by the call. */
|
|
sds sdscatsds(sds s, const sds t) {
|
|
return sdscatlen(s, t, sdslen(t));
|
|
}
|
|
|
|
/* Destructively modify the sds string 's' to hold the specified binary
|
|
* safe string pointed by 't' of length 'len' bytes. */
|
|
sds sdscpylen(sds s, const char *t, size_t len) {
|
|
if (sdsalloc(s) < len) {
|
|
s = sdsMakeRoomFor(s, len - sdslen(s));
|
|
if (s == NULL) return NULL;
|
|
}
|
|
memcpy(s, t, len);
|
|
s[len] = '\0';
|
|
sdssetlen(s, len);
|
|
return s;
|
|
}
|
|
|
|
/* Like sdscpylen() but 't' must be a null-terminated string so that the length
|
|
* of the string is obtained with strlen(). */
|
|
sds sdscpy(sds s, const char *t) {
|
|
return sdscpylen(s, t, strlen(t));
|
|
}
|
|
|
|
/* Create an sds string from a long long value. It is much faster than:
|
|
*
|
|
* sdscatprintf(sdsempty(),"%lld\n", value);
|
|
*/
|
|
sds sdsfromlonglong(long long value) {
|
|
char buf[LONG_STR_SIZE];
|
|
int len = ll2string(buf, sizeof(buf), value);
|
|
|
|
return sdsnewlen(buf, len);
|
|
}
|
|
|
|
/* Like sdscatprintf() but gets va_list instead of being variadic. */
|
|
sds sdscatvprintf(sds s, const char *fmt, va_list ap) {
|
|
va_list cpy;
|
|
char staticbuf[1024], *buf = staticbuf, *t;
|
|
size_t buflen = strlen(fmt) * 2;
|
|
int bufstrlen;
|
|
|
|
/* We try to start using a static buffer for speed.
|
|
* If not possible we revert to heap allocation. */
|
|
if (buflen > sizeof(staticbuf)) {
|
|
buf = s_malloc(buflen);
|
|
if (buf == NULL) return NULL;
|
|
} else {
|
|
buflen = sizeof(staticbuf);
|
|
}
|
|
|
|
/* Alloc enough space for buffer and \0 after failing to
|
|
* fit the string in the current buffer size. */
|
|
while (1) {
|
|
va_copy(cpy, ap);
|
|
bufstrlen = vsnprintf(buf, buflen, fmt, cpy);
|
|
va_end(cpy);
|
|
if (bufstrlen < 0) {
|
|
if (buf != staticbuf) s_free(buf);
|
|
return NULL;
|
|
}
|
|
if (((size_t)bufstrlen) >= buflen) {
|
|
if (buf != staticbuf) s_free(buf);
|
|
buflen = ((size_t)bufstrlen) + 1;
|
|
buf = s_malloc(buflen);
|
|
if (buf == NULL) return NULL;
|
|
continue;
|
|
}
|
|
break;
|
|
}
|
|
|
|
/* Finally concat the obtained string to the SDS string and return it. */
|
|
t = sdscatlen(s, buf, bufstrlen);
|
|
if (buf != staticbuf) s_free(buf);
|
|
return t;
|
|
}
|
|
|
|
/* Append to the sds string 's' a string obtained using printf-alike format
|
|
* specifier.
|
|
*
|
|
* After the call, the modified sds string is no longer valid and all the
|
|
* references must be substituted with the new pointer returned by the call.
|
|
*
|
|
* Example:
|
|
*
|
|
* s = sdsnew("Sum is: ");
|
|
* s = sdscatprintf(s,"%d+%d = %d",a,b,a+b).
|
|
*
|
|
* Often you need to create a string from scratch with the printf-alike
|
|
* format. When this is the need, just use sdsempty() as the target string:
|
|
*
|
|
* s = sdscatprintf(sdsempty(), "... your format ...", args);
|
|
*/
|
|
sds sdscatprintf(sds s, const char *fmt, ...) {
|
|
va_list ap;
|
|
char *t;
|
|
va_start(ap, fmt);
|
|
t = sdscatvprintf(s, fmt, ap);
|
|
va_end(ap);
|
|
return t;
|
|
}
|
|
|
|
/* This function is similar to sdscatprintf, but much faster as it does
|
|
* not rely on sprintf() family functions implemented by the libc that
|
|
* are often very slow. Moreover directly handling the sds string as
|
|
* new data is concatenated provides a performance improvement.
|
|
*
|
|
* However this function only handles an incompatible subset of printf-alike
|
|
* format specifiers:
|
|
*
|
|
* %s - C String
|
|
* %S - SDS string
|
|
* %i - signed int
|
|
* %I - 64 bit signed integer (long long, int64_t)
|
|
* %u - unsigned int
|
|
* %U - 64 bit unsigned integer (unsigned long long, uint64_t)
|
|
* %% - Verbatim "%" character.
|
|
*/
|
|
sds sdscatfmt(sds s, char const *fmt, ...) {
|
|
size_t initlen = sdslen(s);
|
|
const char *f = fmt;
|
|
long i;
|
|
va_list ap;
|
|
|
|
/* To avoid continuous reallocations, let's start with a buffer that
|
|
* can hold at least two times the format string itself. It's not the
|
|
* best heuristic but seems to work in practice. */
|
|
s = sdsMakeRoomFor(s, strlen(fmt) * 2);
|
|
va_start(ap, fmt);
|
|
f = fmt; /* Next format specifier byte to process. */
|
|
i = initlen; /* Position of the next byte to write to dest str. */
|
|
while (*f) {
|
|
char next, *str;
|
|
size_t l;
|
|
long long num;
|
|
unsigned long long unum;
|
|
|
|
/* Make sure there is always space for at least 1 char. */
|
|
if (sdsavail(s) == 0) {
|
|
s = sdsMakeRoomFor(s, 1);
|
|
}
|
|
|
|
switch (*f) {
|
|
case '%':
|
|
next = *(f + 1);
|
|
if (next == '\0') break;
|
|
f++;
|
|
switch (next) {
|
|
case 's':
|
|
case 'S':
|
|
str = va_arg(ap, char *);
|
|
l = (next == 's') ? strlen(str) : sdslen(str);
|
|
if (sdsavail(s) < l) {
|
|
s = sdsMakeRoomFor(s, l);
|
|
}
|
|
memcpy(s + i, str, l);
|
|
sdsinclen(s, l);
|
|
i += l;
|
|
break;
|
|
case 'i':
|
|
case 'I':
|
|
if (next == 'i')
|
|
num = va_arg(ap, int);
|
|
else
|
|
num = va_arg(ap, long long);
|
|
{
|
|
char buf[LONG_STR_SIZE];
|
|
l = ll2string(buf, sizeof(buf), num);
|
|
if (sdsavail(s) < l) {
|
|
s = sdsMakeRoomFor(s, l);
|
|
}
|
|
memcpy(s + i, buf, l);
|
|
sdsinclen(s, l);
|
|
i += l;
|
|
}
|
|
break;
|
|
case 'u':
|
|
case 'U':
|
|
if (next == 'u')
|
|
unum = va_arg(ap, unsigned int);
|
|
else
|
|
unum = va_arg(ap, unsigned long long);
|
|
{
|
|
char buf[LONG_STR_SIZE];
|
|
l = ull2string(buf, sizeof(buf), unum);
|
|
if (sdsavail(s) < l) {
|
|
s = sdsMakeRoomFor(s, l);
|
|
}
|
|
memcpy(s + i, buf, l);
|
|
sdsinclen(s, l);
|
|
i += l;
|
|
}
|
|
break;
|
|
default: /* Handle %% and generally %<unknown>. */
|
|
s[i++] = next;
|
|
sdsinclen(s, 1);
|
|
break;
|
|
}
|
|
break;
|
|
default:
|
|
s[i++] = *f;
|
|
sdsinclen(s, 1);
|
|
break;
|
|
}
|
|
f++;
|
|
}
|
|
va_end(ap);
|
|
|
|
/* Add null-term */
|
|
s[i] = '\0';
|
|
return s;
|
|
}
|
|
|
|
/* Remove the part of the string from left and from right composed just of
|
|
* contiguous characters found in 'cset', that is a null terminated C string.
|
|
*
|
|
* After the call, the modified sds string is no longer valid and all the
|
|
* references must be substituted with the new pointer returned by the call.
|
|
*
|
|
* Example:
|
|
*
|
|
* s = sdsnew("AA...AA.a.aa.aHelloWorld :::");
|
|
* s = sdstrim(s,"Aa. :");
|
|
* printf("%s\n", s);
|
|
*
|
|
* Output will be just "HelloWorld".
|
|
*/
|
|
sds sdstrim(sds s, const char *cset) {
|
|
char *end, *sp, *ep;
|
|
size_t len;
|
|
|
|
sp = s;
|
|
ep = end = s + sdslen(s) - 1;
|
|
while (sp <= end && strchr(cset, *sp)) sp++;
|
|
while (ep > sp && strchr(cset, *ep)) ep--;
|
|
len = (ep - sp) + 1;
|
|
if (s != sp) memmove(s, sp, len);
|
|
s[len] = '\0';
|
|
sdssetlen(s, len);
|
|
return s;
|
|
}
|
|
|
|
/* Changes the input string to be a subset of the original.
|
|
* It does not release the free space in the string, so a call to
|
|
* sdsRemoveFreeSpace may be wise after. */
|
|
void sdssubstr(sds s, size_t start, size_t len) {
|
|
/* Clamp out of range input */
|
|
size_t oldlen = sdslen(s);
|
|
if (start >= oldlen) start = len = 0;
|
|
if (len > oldlen - start) len = oldlen - start;
|
|
|
|
/* Move the data */
|
|
if (len) memmove(s, s + start, len);
|
|
s[len] = 0;
|
|
sdssetlen(s, len);
|
|
}
|
|
|
|
/* Turn the string into a smaller (or equal) string containing only the
|
|
* substring specified by the 'start' and 'end' indexes.
|
|
*
|
|
* start and end can be negative, where -1 means the last character of the
|
|
* string, -2 the penultimate character, and so forth.
|
|
*
|
|
* The interval is inclusive, so the start and end characters will be part
|
|
* of the resulting string.
|
|
*
|
|
* The string is modified in-place.
|
|
*
|
|
* NOTE: this function can be misleading and can have unexpected behaviour,
|
|
* specifically when you want the length of the new string to be 0.
|
|
* Having start==end will result in a string with one character.
|
|
* please consider using sdssubstr instead.
|
|
*
|
|
* Example:
|
|
*
|
|
* s = sdsnew("Hello World");
|
|
* sdsrange(s,1,-1); => "ello World"
|
|
*/
|
|
void sdsrange(sds s, ssize_t start, ssize_t end) {
|
|
size_t newlen, len = sdslen(s);
|
|
if (len == 0) return;
|
|
if (start < 0) start = len + start;
|
|
if (end < 0) end = len + end;
|
|
newlen = (start > end) ? 0 : (end - start) + 1;
|
|
sdssubstr(s, start, newlen);
|
|
}
|
|
|
|
/* Apply tolower() to every character of the sds string 's'. */
|
|
void sdstolower(sds s) {
|
|
size_t len = sdslen(s), j;
|
|
|
|
for (j = 0; j < len; j++) s[j] = tolower(s[j]);
|
|
}
|
|
|
|
/* Apply toupper() to every character of the sds string 's'. */
|
|
void sdstoupper(sds s) {
|
|
size_t len = sdslen(s), j;
|
|
|
|
for (j = 0; j < len; j++) s[j] = toupper(s[j]);
|
|
}
|
|
|
|
/* Compare two sds strings s1 and s2 with memcmp().
|
|
*
|
|
* Return value:
|
|
*
|
|
* positive if s1 > s2.
|
|
* negative if s1 < s2.
|
|
* 0 if s1 and s2 are exactly the same binary string.
|
|
*
|
|
* If two strings share exactly the same prefix, but one of the two has
|
|
* additional characters, the longer string is considered to be greater than
|
|
* the smaller one. */
|
|
int sdscmp(const sds s1, const sds s2) {
|
|
size_t l1, l2, minlen;
|
|
int cmp;
|
|
|
|
l1 = sdslen(s1);
|
|
l2 = sdslen(s2);
|
|
minlen = (l1 < l2) ? l1 : l2;
|
|
cmp = memcmp(s1, s2, minlen);
|
|
if (cmp == 0) return l1 > l2 ? 1 : (l1 < l2 ? -1 : 0);
|
|
return cmp;
|
|
}
|
|
|
|
/* Split 's' with separator in 'sep'. An array
|
|
* of sds strings is returned. *count will be set
|
|
* by reference to the number of tokens returned.
|
|
*
|
|
* On out of memory, zero length string, zero length
|
|
* separator, NULL is returned.
|
|
*
|
|
* Note that 'sep' is able to split a string using
|
|
* a multi-character separator. For example
|
|
* sdssplit("foo_-_bar","_-_"); will return two
|
|
* elements "foo" and "bar".
|
|
*
|
|
* This version of the function is binary-safe but
|
|
* requires length arguments. sdssplit() is just the
|
|
* same function but for zero-terminated strings.
|
|
*/
|
|
sds *sdssplitlen(const char *s, ssize_t len, const char *sep, int seplen, int *count) {
|
|
int elements = 0, slots = 5;
|
|
long start = 0, j;
|
|
sds *tokens;
|
|
|
|
if (seplen < 1 || len <= 0) {
|
|
*count = 0;
|
|
return NULL;
|
|
}
|
|
tokens = s_malloc(sizeof(sds) * slots);
|
|
if (tokens == NULL) return NULL;
|
|
|
|
for (j = 0; j < (len - (seplen - 1)); j++) {
|
|
/* make sure there is room for the next element and the final one */
|
|
if (slots < elements + 2) {
|
|
sds *newtokens;
|
|
|
|
slots *= 2;
|
|
newtokens = s_realloc(tokens, sizeof(sds) * slots);
|
|
if (newtokens == NULL) goto cleanup;
|
|
tokens = newtokens;
|
|
}
|
|
/* search the separator */
|
|
if ((seplen == 1 && *(s + j) == sep[0]) || (memcmp(s + j, sep, seplen) == 0)) {
|
|
tokens[elements] = sdsnewlen(s + start, j - start);
|
|
if (tokens[elements] == NULL) goto cleanup;
|
|
elements++;
|
|
start = j + seplen;
|
|
j = j + seplen - 1; /* skip the separator */
|
|
}
|
|
}
|
|
/* Add the final element. We are sure there is room in the tokens array. */
|
|
tokens[elements] = sdsnewlen(s + start, len - start);
|
|
if (tokens[elements] == NULL) goto cleanup;
|
|
elements++;
|
|
*count = elements;
|
|
return tokens;
|
|
|
|
cleanup: {
|
|
int i;
|
|
for (i = 0; i < elements; i++) sdsfree(tokens[i]);
|
|
s_free(tokens);
|
|
*count = 0;
|
|
return NULL;
|
|
}
|
|
}
|
|
|
|
/* Free the result returned by sdssplitlen(), or do nothing if 'tokens' is NULL. */
|
|
void sdsfreesplitres(sds *tokens, int count) {
|
|
if (!tokens) return;
|
|
while (count--) sdsfree(tokens[count]);
|
|
s_free(tokens);
|
|
}
|
|
|
|
/* Append to the sds string "s" an escaped string representation where
|
|
* all the non-printable characters (tested with isprint()) are turned into
|
|
* escapes in the form "\n\r\a...." or "\x<hex-number>".
|
|
*
|
|
* After the call, the modified sds string is no longer valid and all the
|
|
* references must be substituted with the new pointer returned by the call. */
|
|
sds sdscatrepr(sds s, const char *p, size_t len) {
|
|
s = sdsMakeRoomFor(s, len + 2);
|
|
s = sdscatlen(s, "\"", 1);
|
|
while (len--) {
|
|
switch (*p) {
|
|
case '\\':
|
|
case '"': s = sdscatprintf(s, "\\%c", *p); break;
|
|
case '\n': s = sdscatlen(s, "\\n", 2); break;
|
|
case '\r': s = sdscatlen(s, "\\r", 2); break;
|
|
case '\t': s = sdscatlen(s, "\\t", 2); break;
|
|
case '\a': s = sdscatlen(s, "\\a", 2); break;
|
|
case '\b': s = sdscatlen(s, "\\b", 2); break;
|
|
default:
|
|
if (isprint(*p))
|
|
s = sdscatlen(s, p, 1);
|
|
else
|
|
s = sdscatprintf(s, "\\x%02x", (unsigned char)*p);
|
|
break;
|
|
}
|
|
p++;
|
|
}
|
|
return sdscatlen(s, "\"", 1);
|
|
}
|
|
|
|
/* Returns one if the string contains characters to be escaped
|
|
* by sdscatrepr(), zero otherwise.
|
|
*
|
|
* Typically, this should be used to help protect aggregated strings in a way
|
|
* that is compatible with sdssplitargs(). For this reason, also spaces will be
|
|
* treated as needing an escape.
|
|
*/
|
|
int sdsneedsrepr(const sds s) {
|
|
size_t len = sdslen(s);
|
|
const char *p = s;
|
|
|
|
while (len--) {
|
|
if (*p == '\\' || *p == '"' || *p == '\n' || *p == '\r' || *p == '\t' || *p == '\a' || *p == '\b' ||
|
|
!isprint(*p) || isspace(*p))
|
|
return 1;
|
|
p++;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
/* Helper function for sdssplitargs() that returns non zero if 'c'
|
|
* is a valid hex digit. */
|
|
int is_hex_digit(char c) {
|
|
return (c >= '0' && c <= '9') || (c >= 'a' && c <= 'f') || (c >= 'A' && c <= 'F');
|
|
}
|
|
|
|
/* Helper function for sdssplitargs() that converts a hex digit into an
|
|
* integer from 0 to 15 */
|
|
int hex_digit_to_int(char c) {
|
|
switch (c) {
|
|
case '0': return 0;
|
|
case '1': return 1;
|
|
case '2': return 2;
|
|
case '3': return 3;
|
|
case '4': return 4;
|
|
case '5': return 5;
|
|
case '6': return 6;
|
|
case '7': return 7;
|
|
case '8': return 8;
|
|
case '9': return 9;
|
|
case 'a':
|
|
case 'A': return 10;
|
|
case 'b':
|
|
case 'B': return 11;
|
|
case 'c':
|
|
case 'C': return 12;
|
|
case 'd':
|
|
case 'D': return 13;
|
|
case 'e':
|
|
case 'E': return 14;
|
|
case 'f':
|
|
case 'F': return 15;
|
|
default: return 0;
|
|
}
|
|
}
|
|
|
|
/* Helper function for sdssplitargs that parses a single argument. It
|
|
* populates the number characters needed to store the parsed argument
|
|
* in len, if provided, or will copy the parsed string into dst, if provided.
|
|
* If the string is able to be parsed, this function returns the number of
|
|
* characters that were parsed. If the argument can't be parsed, it
|
|
* returns 0. */
|
|
static int sdsparsearg(const char *arg, unsigned int *len, char *dst) {
|
|
const char *p = arg;
|
|
int inq = 0; /* set to 1 if we are in "quotes" */
|
|
int insq = 0; /* set to 1 if we are in 'single quotes' */
|
|
int done = 0;
|
|
|
|
while (!done) {
|
|
int new_char = -1;
|
|
if (inq) {
|
|
if (*p == '\\' && *(p + 1) == 'x' && is_hex_digit(*(p + 2)) && is_hex_digit(*(p + 3))) {
|
|
new_char = (hex_digit_to_int(*(p + 2)) * 16) + hex_digit_to_int(*(p + 3));
|
|
p += 3;
|
|
} else if (*p == '\\' && *(p + 1)) {
|
|
p++;
|
|
switch (*p) {
|
|
case 'n': new_char = '\n'; break;
|
|
case 'r': new_char = '\r'; break;
|
|
case 't': new_char = '\t'; break;
|
|
case 'b': new_char = '\b'; break;
|
|
case 'a': new_char = '\a'; break;
|
|
default: new_char = *p; break;
|
|
}
|
|
} else if (*p == '"') {
|
|
/* closing quote must be followed by a space or
|
|
* nothing at all. */
|
|
if (*(p + 1) && !isspace(*(p + 1))) return 0;
|
|
done = 1;
|
|
} else if (!*p) {
|
|
/* unterminated quotes */
|
|
return 0;
|
|
} else {
|
|
new_char = *p;
|
|
}
|
|
} else if (insq) {
|
|
if (*p == '\\' && *(p + 1) == '\'') {
|
|
p++;
|
|
new_char = *p;
|
|
} else if (*p == '\'') {
|
|
/* closing quote must be followed by a space or
|
|
* nothing at all. */
|
|
if (*(p + 1) && !isspace(*(p + 1))) return 0;
|
|
done = 1;
|
|
} else if (!*p) {
|
|
/* unterminated quotes */
|
|
return 0;
|
|
} else {
|
|
new_char = *p;
|
|
}
|
|
} else {
|
|
switch (*p) {
|
|
case ' ':
|
|
case '\n':
|
|
case '\r':
|
|
case '\t':
|
|
case '\0': done = 1; break;
|
|
case '"': inq = 1; break;
|
|
case '\'': insq = 1; break;
|
|
default: new_char = *p; break;
|
|
}
|
|
}
|
|
if (new_char != -1) {
|
|
if (len) (*len)++;
|
|
if (dst) {
|
|
*dst = (char)new_char;
|
|
dst++;
|
|
}
|
|
}
|
|
if (*p) {
|
|
p++;
|
|
}
|
|
}
|
|
return p - arg;
|
|
}
|
|
|
|
/* Split a line into arguments, where every argument can be in the
|
|
* following programming-language REPL-alike form:
|
|
*
|
|
* foo bar "newline are supported\n" and "\xff\x00otherstuff"
|
|
*
|
|
* The number of arguments is stored into *argc, and an array
|
|
* of sds is returned.
|
|
*
|
|
* The caller should free the resulting array of sds strings with
|
|
* sdsfreesplitres().
|
|
*
|
|
* Note that sdscatrepr() is able to convert back a string into
|
|
* a quoted string in the same format sdssplitargs() is able to parse.
|
|
*
|
|
* The function returns the allocated tokens on success, even when the
|
|
* input string is empty, or NULL if the input contains unbalanced
|
|
* quotes or closed quotes followed by non space characters
|
|
* as in: "foo"bar or "foo'.
|
|
*
|
|
* The sds strings returned by this function are not initialized with
|
|
* extra space.
|
|
*/
|
|
sds *sdssplitargs(const char *line, int *argc) {
|
|
const char *p = line;
|
|
char **vector = NULL;
|
|
|
|
*argc = 0;
|
|
while (*p) {
|
|
/* skip blanks */
|
|
while (*p && isspace(*p)) p++;
|
|
if (!(*p)) break;
|
|
unsigned int len = 0;
|
|
if (sdsparsearg(p, &len, NULL)) {
|
|
sds current = sdsnewlen(SDS_NOINIT, len);
|
|
int parsedlen = sdsparsearg(p, NULL, current);
|
|
assert(parsedlen > 0);
|
|
p += parsedlen;
|
|
|
|
/* add the token to the vector */
|
|
vector = s_realloc(vector, ((*argc) + 1) * sizeof(char *));
|
|
vector[*argc] = current;
|
|
(*argc)++;
|
|
current = NULL;
|
|
} else {
|
|
while ((*argc)--) sdsfree(vector[*argc]);
|
|
s_free(vector);
|
|
*argc = 0;
|
|
return NULL;
|
|
}
|
|
}
|
|
/* Even on empty input string return something not NULL. */
|
|
if (vector == NULL) vector = s_malloc(sizeof(void *));
|
|
return vector;
|
|
}
|
|
|
|
/* Modify the string substituting all the occurrences of the set of
|
|
* characters specified in the 'from' string to the corresponding character
|
|
* in the 'to' array.
|
|
*
|
|
* For instance: sdsmapchars(mystring, "ho", "01", 2)
|
|
* will have the effect of turning the string "hello" into "0ell1".
|
|
*
|
|
* The function returns the sds string pointer, that is always the same
|
|
* as the input pointer since no resize is needed. */
|
|
sds sdsmapchars(sds s, const char *from, const char *to, size_t setlen) {
|
|
size_t j, i, l = sdslen(s);
|
|
|
|
for (j = 0; j < l; j++) {
|
|
for (i = 0; i < setlen; i++) {
|
|
if (s[j] == from[i]) {
|
|
s[j] = to[i];
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
return s;
|
|
}
|
|
|
|
/* Join an array of C strings using the specified separator (also a C string).
|
|
* Returns the result as an sds string. */
|
|
sds sdsjoin(char **argv, int argc, char *sep) {
|
|
sds join = sdsempty();
|
|
int j;
|
|
|
|
for (j = 0; j < argc; j++) {
|
|
join = sdscat(join, argv[j]);
|
|
if (j != argc - 1) join = sdscat(join, sep);
|
|
}
|
|
return join;
|
|
}
|
|
|
|
/* Like sdsjoin, but joins an array of SDS strings. */
|
|
sds sdsjoinsds(sds *argv, int argc, const char *sep, size_t seplen) {
|
|
sds join = sdsempty();
|
|
int j;
|
|
|
|
for (j = 0; j < argc; j++) {
|
|
join = sdscatsds(join, argv[j]);
|
|
if (j != argc - 1) join = sdscatlen(join, sep, seplen);
|
|
}
|
|
return join;
|
|
}
|
|
|
|
/* Wrappers to the allocators used by SDS. Note that SDS will actually
|
|
* just use the macros defined into sdsalloc.h in order to avoid to pay
|
|
* the overhead of function calls. Here we define these wrappers only for
|
|
* the programs SDS is linked to, if they want to touch the SDS internals
|
|
* even if they use a different allocator. */
|
|
void *sds_malloc(size_t size) {
|
|
return s_malloc(size);
|
|
}
|
|
void *sds_realloc(void *ptr, size_t size) {
|
|
return s_realloc(ptr, size);
|
|
}
|
|
void sds_free(void *ptr) {
|
|
s_free(ptr);
|
|
}
|
|
|
|
/* Perform expansion of a template string and return the result as a newly
|
|
* allocated sds.
|
|
*
|
|
* Template variables are specified using curly brackets, e.g. {variable}.
|
|
* An opening bracket can be quoted by repeating it twice.
|
|
*/
|
|
sds sdstemplate(const char *template, sdstemplate_callback_t cb_func, void *cb_arg) {
|
|
sds res = sdsempty();
|
|
const char *p = template;
|
|
|
|
while (*p) {
|
|
/* Find next variable, copy everything until there */
|
|
const char *sv = strchr(p, '{');
|
|
if (!sv) {
|
|
/* Not found: copy till rest of template and stop */
|
|
res = sdscat(res, p);
|
|
break;
|
|
} else if (sv > p) {
|
|
/* Found: copy anything up to the beginning of the variable */
|
|
res = sdscatlen(res, p, sv - p);
|
|
}
|
|
|
|
/* Skip into variable name, handle premature end or quoting */
|
|
sv++;
|
|
if (!*sv) goto error; /* Premature end of template */
|
|
if (*sv == '{') {
|
|
/* Quoted '{' */
|
|
p = sv + 1;
|
|
res = sdscat(res, "{");
|
|
continue;
|
|
}
|
|
|
|
/* Find end of variable name, handle premature end of template */
|
|
const char *ev = strchr(sv, '}');
|
|
if (!ev) goto error;
|
|
|
|
/* Pass variable name to callback and obtain value. If callback failed,
|
|
* abort. */
|
|
sds varname = sdsnewlen(sv, ev - sv);
|
|
sds value = cb_func(varname, cb_arg);
|
|
sdsfree(varname);
|
|
if (!value) goto error;
|
|
|
|
/* Append value to result and continue */
|
|
res = sdscat(res, value);
|
|
sdsfree(value);
|
|
p = ev + 1;
|
|
}
|
|
|
|
return res;
|
|
|
|
error:
|
|
sdsfree(res);
|
|
return NULL;
|
|
}
|