Upgrade sds to latest version

SDS is now broken out of Redis into its own project, so include
the latest version from the SDS repo.

This is a backport of the Redis commit doing the same to the bundled hiredis:
320fa02b9b

hiredis.c

@@ -650,7 +650,7 @@ int redisReaderGetReply(redisReader *r, void **reply) {
     /* Discard part of the buffer when we've consumed at least 1k, to avoid
      * doing unnecessary calls to memmove() in sds.c. */
     if (r->pos >= 1024) {
-        r->buf = sdsrange(r->buf,r->pos,-1);
+        sdsrange(r->buf,r->pos,-1);
         r->pos = 0;
         r->len = sdslen(r->buf);
     }
@@ -1189,7 +1189,7 @@ int redisBufferWrite(redisContext *c, int *done) {
                 sdsfree(c->obuf);
                 c->obuf = sdsempty();
             } else {
-                c->obuf = sdsrange(c->obuf,nwritten,-1);
+                sdsrange(c->obuf,nwritten,-1);
             }
         }
     }

sds.c

@@ -1,6 +1,6 @@
-/* SDSLib, A C dynamic strings library
+/* SDS (Simple Dynamic Strings), A C dynamic strings library.
  *
- * Copyright (c) 2006-2010, Salvatore Sanfilippo <antirez at gmail dot com>
+ * Copyright (c) 2006-2014, Salvatore Sanfilippo <antirez at gmail dot com>
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -32,83 +32,188 @@
 #include <stdlib.h>
 #include <string.h>
 #include <ctype.h>
+#include <assert.h>
+
 #include "sds.h"
 
-#ifdef SDS_ABORT_ON_OOM
-static void sdsOomAbort(void) {
-    fprintf(stderr,"SDS: Out Of Memory (SDS_ABORT_ON_OOM defined)\n");
-    abort();
-}
-#endif
-
+/* 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.
+ *
+ * The string is always null-termined (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) {
     struct sdshdr *sh;
 
-    sh = malloc(sizeof(struct sdshdr)+initlen+1);
-#ifdef SDS_ABORT_ON_OOM
-    if (sh == NULL) sdsOomAbort();
-#else
+    if (init) {
+        sh = malloc(sizeof *sh+initlen+1);
+    } else {
+        sh = calloc(sizeof *sh+initlen+1,1);
+    }
     if (sh == NULL) return NULL;
-#endif
     sh->len = initlen;
     sh->free = 0;
-    if (initlen) {
-        if (init) memcpy(sh->buf, init, initlen);
-        else memset(sh->buf,0,initlen);
-    }
+    if (initlen && init)
+        memcpy(sh->buf, init, initlen);
     sh->buf[initlen] = '\0';
     return (char*)sh->buf;
 }
 
+/* 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 termined 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));
 }
 
+/* Free an sds string. No operation is performed if 's' is NULL. */
 void sdsfree(sds s) {
     if (s == NULL) return;
     free(s-sizeof(struct sdshdr));
 }
 
+/* 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) {
-    struct sdshdr *sh = (void*) (s-(sizeof(struct sdshdr)));
+    struct sdshdr *sh = (void*) (s-sizeof *sh);;
     int reallen = strlen(s);
     sh->free += (sh->len-reallen);
     sh->len = reallen;
 }
 
-static sds sdsMakeRoomFor(sds s, size_t addlen) {
+/* Modify an sds string on-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) {
+    struct sdshdr *sh = (void*) (s-sizeof *sh);;
+    sh->free += sh->len;
+    sh->len = 0;
+    sh->buf[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.
+ * 
+ * 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) {
     struct sdshdr *sh, *newsh;
     size_t free = sdsavail(s);
     size_t len, newlen;
 
     if (free >= addlen) return s;
     len = sdslen(s);
-    sh = (void*) (s-(sizeof(struct sdshdr)));
-    newlen = (len+addlen)*2;
-    newsh = realloc(sh, sizeof(struct sdshdr)+newlen+1);
-#ifdef SDS_ABORT_ON_OOM
-    if (newsh == NULL) sdsOomAbort();
-#else
+    sh = (void*) (s-sizeof *sh);;
+    newlen = (len+addlen);
+    if (newlen < SDS_MAX_PREALLOC)
+        newlen *= 2;
+    else
+        newlen += SDS_MAX_PREALLOC;
+    newsh = realloc(sh, sizeof *newsh+newlen+1);
     if (newsh == NULL) return NULL;
-#endif
 
     newsh->free = newlen - len;
     return newsh->buf;
 }
 
+/* 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) {
+    struct sdshdr *sh;
+
+    sh = (void*) (s-sizeof *sh);;
+    sh = realloc(sh, sizeof *sh+sh->len+1);
+    sh->free = 0;
+    return sh->buf;
+}
+
+/* Return the total size of the allocation of the specifed 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) {
+    struct sdshdr *sh = (void*) (s-sizeof *sh);;
+
+    return sizeof(*sh)+sh->len+sh->free+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, int incr) {
+    struct sdshdr *sh = (void*) (s-sizeof *sh);;
+
+    assert(sh->free >= incr);
+    sh->len += incr;
+    sh->free -= incr;
+    assert(sh->free >= 0);
+    s[sh->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. */
+ * 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) {
-    struct sdshdr *sh = (void*)(s-(sizeof(struct sdshdr)));
+    struct sdshdr *sh = (void*) (s-sizeof *sh);
     size_t totlen, curlen = sh->len;
 
     if (len <= curlen) return s;
@@ -116,7 +221,7 @@ sds sdsgrowzero(sds s, size_t len) {
     if (s == NULL) return NULL;
 
     /* Make sure added region doesn't contain garbage */
-    sh = (void*)(s-(sizeof(struct sdshdr)));
+    sh = (void*)(s-sizeof *sh);
     memset(s+curlen,0,(len-curlen+1)); /* also set trailing \0 byte */
     totlen = sh->len+sh->free;
     sh->len = len;
@@ -124,13 +229,18 @@ sds sdsgrowzero(sds s, size_t 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) {
     struct sdshdr *sh;
     size_t curlen = sdslen(s);
 
     s = sdsMakeRoomFor(s,len);
     if (s == NULL) return NULL;
-    sh = (void*) (s-(sizeof(struct sdshdr)));
+    sh = (void*) (s-sizeof *sh);;
     memcpy(s+curlen, t, len);
     sh->len = curlen+len;
     sh->free = sh->free-len;
@@ -138,18 +248,32 @@ sds sdscatlen(sds s, const void *t, size_t len) {
     return s;
 }
 
+/* Append the specified null termianted 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));
 }
 
-sds sdscpylen(sds s, char *t, size_t len) {
-    struct sdshdr *sh = (void*) (s-(sizeof(struct sdshdr)));
+/* 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) {
+    struct sdshdr *sh = (void*) (s-sizeof *sh);;
     size_t totlen = sh->free+sh->len;
 
     if (totlen < len) {
         s = sdsMakeRoomFor(s,len-sh->len);
         if (s == NULL) return NULL;
-        sh = (void*) (s-(sizeof(struct sdshdr)));
+        sh = (void*) (s-sizeof *sh);;
         totlen = sh->free+sh->len;
     }
     memcpy(s, t, len);
@@ -159,10 +283,13 @@ sds sdscpylen(sds s, char *t, size_t len) {
     return s;
 }
 
-sds sdscpy(sds s, char *t) {
+/* Like sdscpylen() but 't' must be a null-termined 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));
 }
 
+/* Like sdscatpritf() but gets va_list instead of being variadic. */
 sds sdscatvprintf(sds s, const char *fmt, va_list ap) {
     va_list cpy;
     char *buf, *t;
@@ -170,15 +297,10 @@ sds sdscatvprintf(sds s, const char *fmt, va_list ap) {
 
     while(1) {
         buf = malloc(buflen);
-#ifdef SDS_ABORT_ON_OOM
-        if (buf == NULL) sdsOomAbort();
-#else
         if (buf == NULL) return NULL;
-#endif
         buf[buflen-2] = '\0';
         va_copy(cpy,ap);
         vsnprintf(buf, buflen, fmt, cpy);
-        va_end(cpy);
         if (buf[buflen-2] != '\0') {
             free(buf);
             buflen *= 2;
@@ -191,6 +313,22 @@ sds sdscatvprintf(sds s, const char *fmt, va_list ap) {
     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 = sdsempty("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;
@@ -200,8 +338,22 @@ sds sdscatprintf(sds s, const char *fmt, ...) {
     return t;
 }
 
-sds sdstrim(sds s, const char *cset) {
-    struct sdshdr *sh = (void*) (s-(sizeof(struct sdshdr)));
+/* Remove the part of the string from left and from right composed just of
+ * contiguous characters found in 'cset', that is a null terminted 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,"A. :");
+ * printf("%s\n", s);
+ *
+ * Output will be just "Hello World".
+ */
+void sdstrim(sds s, const char *cset) {
+    struct sdshdr *sh = (void*) (s-sizeof *sh);;
     char *start, *end, *sp, *ep;
     size_t len;
 
@@ -214,14 +366,29 @@ sds sdstrim(sds s, const char *cset) {
     sh->buf[len] = '\0';
     sh->free = sh->free+(sh->len-len);
     sh->len = len;
-    return s;
 }
 
-sds sdsrange(sds s, int start, int end) {
-    struct sdshdr *sh = (void*) (s-(sizeof(struct sdshdr)));
+/* 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.
+ *
+ * Example:
+ *
+ * s = sdsnew("Hello World");
+ * sdsrange(s,1,-1); => "ello World"
+ */
+void sdsrange(sds s, int start, int end) {
+    struct sdshdr *sh = (void*) (s-sizeof *sh);;
     size_t newlen, len = sdslen(s);
 
-    if (len == 0) return s;
+    if (len == 0) return;
     if (start < 0) {
         start = len+start;
         if (start < 0) start = 0;
@@ -245,22 +412,34 @@ sds sdsrange(sds s, int start, int end) {
     sh->buf[newlen] = 0;
     sh->free = sh->free+(sh->len-newlen);
     sh->len = newlen;
-    return s;
 }
 
+/* Apply tolower() to every character of the sds string 's'. */
 void sdstolower(sds s) {
     int 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) {
     int len = sdslen(s), j;
 
     for (j = 0; j < len; j++) s[j] = toupper(s[j]);
 }
 
-int sdscmp(sds s1, sds s2) {
+/* Compare two sds strings s1 and s2 with memcmp().
+ *
+ * Return value:
+ *
+ *     1 if s1 > s2.
+ *    -1 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;
 
@@ -288,18 +467,15 @@ int sdscmp(sds s1, sds s2) {
  * requires length arguments. sdssplit() is just the
  * same function but for zero-terminated strings.
  */
-sds *sdssplitlen(char *s, int len, char *sep, int seplen, int *count) {
+sds *sdssplitlen(const char *s, int len, const char *sep, int seplen, int *count) {
     int elements = 0, slots = 5, start = 0, j;
+    sds *tokens;
 
-    sds *tokens = malloc(sizeof(sds)*slots);
-#ifdef SDS_ABORT_ON_OOM
-    if (tokens == NULL) sdsOomAbort();
-#endif
+    if (seplen < 1 || len < 0) return NULL;
+
+    tokens = malloc(sizeof(sds)*slots);
     if (tokens == NULL) return NULL;
-    if (seplen < 1 || len < 0) {
-        free(tokens);
-        return NULL;
-    }
+
     if (len == 0) {
         *count = 0;
         return tokens;
@@ -311,25 +487,13 @@ sds *sdssplitlen(char *s, int len, char *sep, int seplen, int *count) {
 
             slots *= 2;
             newtokens = realloc(tokens,sizeof(sds)*slots);
-            if (newtokens == NULL) {
-#ifdef SDS_ABORT_ON_OOM
-                sdsOomAbort();
-#else
-                goto cleanup;
-#endif
-            }
+            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) {
-#ifdef SDS_ABORT_ON_OOM
-                sdsOomAbort();
-#else
-                goto cleanup;
-#endif
-            }
+            if (tokens[elements] == NULL) goto cleanup;
             elements++;
             start = j+seplen;
             j = j+seplen-1; /* skip the separator */
@@ -337,28 +501,22 @@ sds *sdssplitlen(char *s, int len, char *sep, int seplen, int *count) {
     }
     /* 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) {
-#ifdef SDS_ABORT_ON_OOM
-                sdsOomAbort();
-#else
-                goto cleanup;
-#endif
-    }
+    if (tokens[elements] == NULL) goto cleanup;
     elements++;
     *count = elements;
     return tokens;
 
-#ifndef SDS_ABORT_ON_OOM
 cleanup:
     {
         int i;
         for (i = 0; i < elements; i++) sdsfree(tokens[i]);
         free(tokens);
+        *count = 0;
         return NULL;
     }
-#endif
 }
 
+/* Free the result returned by sdssplitlen(), or do nothing if 'tokens' is NULL. */
 void sdsfreesplitres(sds *tokens, int count) {
     if (!tokens) return;
     while(count--)
@@ -366,6 +524,10 @@ void sdsfreesplitres(sds *tokens, int count) {
     free(tokens);
 }
 
+/* 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[32], *p;
     unsigned long long v;
@@ -381,10 +543,14 @@ sds sdsfromlonglong(long long value) {
     return sdsnewlen(p,32-(p-buf));
 }
 
-sds sdscatrepr(sds s, char *p, size_t len) {
+/* 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 = sdscatlen(s,"\"",1);
-    if (s == NULL) return NULL;
-
     while(len--) {
         switch(*p) {
         case '\\':
@@ -404,27 +570,64 @@ sds sdscatrepr(sds s, char *p, size_t len) {
             break;
         }
         p++;
-        if (s == NULL) return NULL;
     }
     return sdscatlen(s,"\"",1);
 }
 
+/* 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;
+    }
+}
+
 /* 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 sdsfree() all the returned
- * strings and finally free() the array itself.
+ * 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'
  */
-sds *sdssplitargs(char *line, int *argc) {
-    char *p = line;
+sds *sdssplitargs(const char *line, int *argc) {
+    const char *p = line;
     char *current = NULL;
-    char **vector = NULL, **_vector = NULL;
+    char **vector = NULL;
 
     *argc = 0;
     while(1) {
@@ -433,16 +636,23 @@ sds *sdssplitargs(char *line, int *argc) {
         if (*p) {
             /* get a token */
             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;
 
-            if (current == NULL) {
-                current = sdsempty();
-                if (current == NULL) goto err;
-            }
-
+            if (current == NULL) current = sdsempty();
             while(!done) {
                 if (inq) {
-                    if (*p == '\\' && *(p+1)) {
+                    if (*p == '\\' && *(p+1) == 'x' &&
+                                             is_hex_digit(*(p+2)) &&
+                                             is_hex_digit(*(p+3)))
+                    {
+                        unsigned char byte;
+
+                        byte = (hex_digit_to_int(*(p+2))*16)+
+                                hex_digit_to_int(*(p+3));
+                        current = sdscatlen(current,(char*)&byte,1);
+                        p += 3;
+                    } else if (*p == '\\' && *(p+1)) {
                         char c;
 
                         p++;
@@ -456,7 +666,23 @@ sds *sdssplitargs(char *line, int *argc) {
                         }
                         current = sdscatlen(current,&c,1);
                     } else if (*p == '"') {
-                        /* closing quote must be followed by a space */
+                        /* closing quote must be followed by a space or
+                         * nothing at all. */
+                        if (*(p+1) && !isspace(*(p+1))) goto err;
+                        done=1;
+                    } else if (!*p) {
+                        /* unterminated quotes */
+                        goto err;
+                    } else {
+                        current = sdscatlen(current,p,1);
+                    }
+                } else if (insq) {
+                    if (*p == '\\' && *(p+1) == '\'') {
+                        p++;
+                        current = sdscatlen(current,"'",1);
+                    } else if (*p == '\'') {
+                        /* closing quote must be followed by a space or
+                         * nothing at all. */
                         if (*(p+1) && !isspace(*(p+1))) goto err;
                         done=1;
                     } else if (!*p) {
@@ -477,23 +703,24 @@ sds *sdssplitargs(char *line, int *argc) {
                     case '"':
                         inq=1;
                         break;
+                    case '\'':
+                        insq=1;
+                        break;
                     default:
                         current = sdscatlen(current,p,1);
                         break;
                     }
                 }
                 if (*p) p++;
-                if (current == NULL) goto err;
             }
             /* add the token to the vector */
-            _vector = realloc(vector,((*argc)+1)*sizeof(char*));
-            if (_vector == NULL) goto err;
-
-            vector = _vector;
+            vector = realloc(vector,((*argc)+1)*sizeof(char*));
             vector[*argc] = current;
             (*argc)++;
             current = NULL;
         } else {
+            /* Even on empty input string return something not NULL. */
+            if (vector == NULL) vector = malloc(sizeof(void*));
             return vector;
         }
     }
@@ -501,30 +728,67 @@ sds *sdssplitargs(char *line, int *argc) {
 err:
     while((*argc)--)
         sdsfree(vector[*argc]);
-    if (vector != NULL) free(vector);
-    if (current != NULL) sdsfree(current);
+    free(vector);
+    if (current) sdsfree(current);
+    *argc = 0;
     return NULL;
 }
 
+/* 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, size_t seplen) {
+    sds join = sdsempty();
+    int j;
+
+    for (j = 0; j < argc; j++) {
+        join = sdscat(join, argv[j]);
+        if (j != argc-1) join = sdscatlen(join,sep,seplen);
+    }
+    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;
+}
+
 #ifdef SDS_TEST_MAIN
 #include <stdio.h>
-
-int __failed_tests = 0;
-int __test_num = 0;
-#define test_cond(descr,_c) do { \
-    __test_num++; printf("%d - %s: ", __test_num, descr); \
-    if(_c) printf("PASSED\n"); else {printf("FAILED\n"); __failed_tests++;} \
-} while(0);
-#define test_report() do { \
-    printf("%d tests, %d passed, %d failed\n", __test_num, \
-                    __test_num-__failed_tests, __failed_tests); \
-    if (__failed_tests) { \
-        printf("=== WARNING === We have failed tests here...\n"); \
-    } \
-} while(0);
+#include "testhelp.h"
 
 int main(void) {
     {
+        struct sdshdr *sh;
         sds x = sdsnew("foo"), y;
 
         test_cond("Create a string and obtain the length",
@@ -554,36 +818,43 @@ int main(void) {
             sdslen(x) == 3 && memcmp(x,"123\0",4) ==0)
 
         sdsfree(x);
-        x = sdstrim(sdsnew("xxciaoyyy"),"xy");
+        x = sdsnew("xxciaoyyy");
+        sdstrim(x,"xy");
         test_cond("sdstrim() correctly trims characters",
             sdslen(x) == 4 && memcmp(x,"ciao\0",5) == 0)
 
-        y = sdsrange(sdsdup(x),1,1);
+        y = sdsdup(x);
+        sdsrange(y,1,1);
         test_cond("sdsrange(...,1,1)",
             sdslen(y) == 1 && memcmp(y,"i\0",2) == 0)
 
         sdsfree(y);
-        y = sdsrange(sdsdup(x),1,-1);
+        y = sdsdup(x);
+        sdsrange(y,1,-1);
         test_cond("sdsrange(...,1,-1)",
             sdslen(y) == 3 && memcmp(y,"iao\0",4) == 0)
 
         sdsfree(y);
-        y = sdsrange(sdsdup(x),-2,-1);
+        y = sdsdup(x);
+        sdsrange(y,-2,-1);
         test_cond("sdsrange(...,-2,-1)",
             sdslen(y) == 2 && memcmp(y,"ao\0",3) == 0)
 
         sdsfree(y);
-        y = sdsrange(sdsdup(x),2,1);
+        y = sdsdup(x);
+        sdsrange(y,2,1);
         test_cond("sdsrange(...,2,1)",
             sdslen(y) == 0 && memcmp(y,"\0",1) == 0)
 
         sdsfree(y);
-        y = sdsrange(sdsdup(x),1,100);
+        y = sdsdup(x);
+        sdsrange(y,1,100);
         test_cond("sdsrange(...,1,100)",
             sdslen(y) == 3 && memcmp(y,"iao\0",4) == 0)
 
         sdsfree(y);
-        y = sdsrange(sdsdup(x),100,100);
+        y = sdsdup(x);
+        sdsrange(y,100,100);
         test_cond("sdsrange(...,100,100)",
             sdslen(y) == 0 && memcmp(y,"\0",1) == 0)
 
@@ -604,7 +875,33 @@ int main(void) {
         x = sdsnew("aar");
         y = sdsnew("bar");
         test_cond("sdscmp(bar,bar)", sdscmp(x,y) < 0)
+
+        sdsfree(y);
+        sdsfree(x);
+        x = sdsnewlen("\a\n\0foo\r",7);
+        y = sdscatrepr(sdsempty(),x,sdslen(x));
+        test_cond("sdscatrepr(...data...)",
+            memcmp(y,"\"\\a\\n\\x00foo\\r\"",15) == 0)
+
+        {
+            int oldfree;
+
+            sdsfree(x);
+            x = sdsnew("0");
+            sh = (void*) (x-(sizeof(struct sdshdr)));
+            test_cond("sdsnew() free/len buffers", sh->len == 1 && sh->free == 0);
+            x = sdsMakeRoomFor(x,1);
+            sh = (void*) (x-(sizeof(struct sdshdr)));
+            test_cond("sdsMakeRoomFor()", sh->len == 1 && sh->free > 0);
+            oldfree = sh->free;
+            x[1] = '1';
+            sdsIncrLen(x,1);
+            test_cond("sdsIncrLen() -- content", x[0] == '0' && x[1] == '1');
+            test_cond("sdsIncrLen() -- len", sh->len == 2);
+            test_cond("sdsIncrLen() -- free", sh->free == oldfree-1);
+        }
     }
     test_report()
+    return 0;
 }
 #endif

sds.h

@@ -1,6 +1,6 @@
-/* SDSLib, A C dynamic strings library
+/* SDS (Simple Dynamic Strings), A C dynamic strings library.
  *
- * Copyright (c) 2006-2010, Salvatore Sanfilippo <antirez at gmail dot com>
+ * Copyright (c) 2006-2014, Salvatore Sanfilippo <antirez at gmail dot com>
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -31,6 +31,8 @@
 #ifndef __SDS_H
 #define __SDS_H
 
+#define SDS_MAX_PREALLOC (1024*1024)
+
 #include <sys/types.h>
 #include <stdarg.h>
 
@@ -43,12 +45,12 @@ struct sdshdr {
 };
 
 static inline size_t sdslen(const sds s) {
-    struct sdshdr *sh = (void*)(s-(sizeof(struct sdshdr)));
+    struct sdshdr *sh = (void*)(s-sizeof *sh);
     return sh->len;
 }
 
 static inline size_t sdsavail(const sds s) {
-    struct sdshdr *sh = (void*)(s-(sizeof(struct sdshdr)));
+    struct sdshdr *sh = (void*)(s-sizeof *sh);
     return sh->free;
 }
 
@@ -58,12 +60,13 @@ sds sdsempty(void);
 size_t sdslen(const sds s);
 sds sdsdup(const sds s);
 void sdsfree(sds s);
-size_t sdsavail(sds s);
+size_t sdsavail(const sds s);
 sds sdsgrowzero(sds s, size_t len);
 sds sdscatlen(sds s, const void *t, size_t len);
 sds sdscat(sds s, const char *t);
-sds sdscpylen(sds s, char *t, size_t len);
-sds sdscpy(sds s, char *t);
+sds sdscatsds(sds s, const sds t);
+sds sdscpylen(sds s, const char *t, size_t len);
+sds sdscpy(sds s, const char *t);
 
 sds sdscatvprintf(sds s, const char *fmt, va_list ap);
 #ifdef __GNUC__
@@ -73,16 +76,26 @@ sds sdscatprintf(sds s, const char *fmt, ...)
 sds sdscatprintf(sds s, const char *fmt, ...);
 #endif
 
-sds sdstrim(sds s, const char *cset);
-sds sdsrange(sds s, int start, int end);
+void sdstrim(sds s, const char *cset);
+void sdsrange(sds s, int start, int end);
 void sdsupdatelen(sds s);
-int sdscmp(sds s1, sds s2);
-sds *sdssplitlen(char *s, int len, char *sep, int seplen, int *count);
+void sdsclear(sds s);
+int sdscmp(const sds s1, const sds s2);
+sds *sdssplitlen(const char *s, int len, const char *sep, int seplen, int *count);
 void sdsfreesplitres(sds *tokens, int count);
 void sdstolower(sds s);
 void sdstoupper(sds s);
 sds sdsfromlonglong(long long value);
-sds sdscatrepr(sds s, char *p, size_t len);
-sds *sdssplitargs(char *line, int *argc);
+sds sdscatrepr(sds s, const char *p, size_t len);
+sds *sdssplitargs(const char *line, int *argc);
+sds sdsmapchars(sds s, const char *from, const char *to, size_t setlen);
+sds sdsjoin(char **argv, int argc, char *sep, size_t seplen);
+sds sdsjoinsds(sds *argv, int argc, const char *sep, size_t seplen);
+
+/* Low level functions exposed to the user API */
+sds sdsMakeRoomFor(sds s, size_t addlen);
+void sdsIncrLen(sds s, int incr);
+sds sdsRemoveFreeSpace(sds s);
+size_t sdsAllocSize(sds s);
 
 #endif