This fixes issue #327, is a very complex fix (unfortunately), details:

[redis.git] / src / intset.c

diff --git a/src/intset.c b/src/intset.c
index 2532582ec8ce4c706387c57bd5c97ce7103cad1c..4dd0141d852f85b401973e73c5aa77638afe3b6d 100644 (file)
--- a/src/intset.c
+++ b/src/intset.c
@@ -3,6 +3,7 @@
 #include <string.h>
 #include "intset.h"
 #include "zmalloc.h"
 #include <string.h>
 #include "intset.h"
 #include "zmalloc.h"

+#include "endian.h"

 
 /* Note that these encodings are ordered, so:
  * INTSET_ENC_INT16 < INTSET_ENC_INT32 < INTSET_ENC_INT64. */
 
 /* Note that these encodings are ordered, so:
  * INTSET_ENC_INT16 < INTSET_ENC_INT32 < INTSET_ENC_INT64. */


@@ -10,21 +11,55 @@
 #define INTSET_ENC_INT32 (sizeof(int32_t))
 #define INTSET_ENC_INT64 (sizeof(int64_t))
 
 #define INTSET_ENC_INT32 (sizeof(int32_t))
 #define INTSET_ENC_INT64 (sizeof(int64_t))
 

-/* Accessors for each type of encoding */
-#define INTSET_VALUE_ENCODING(__val) (((__val) < INT32_MIN || (__val) > INT32_MAX) ? \
-    INTSET_ENC_INT64 : (((__val) < INT16_MIN || (__val) > INT16_MAX) ? \
-    INTSET_ENC_INT32 : INTSET_ENC_INT16))
-#define INTSET_GET_ENCODED(__is,__pos,__enc) ((__enc == INTSET_ENC_INT64) ? \
-    ((int64_t*)(__is)->contents)[__pos] : ((__enc == INTSET_ENC_INT32) ? \
-    ((int32_t*)(__is)->contents)[__pos] : ((int16_t*)(__is)->contents)[__pos]))
-#define INTSET_GET(__is,__pos) (INTSET_GET_ENCODED(__is,__pos,(__is)->encoding))
-#define INTSET_SET(__is,__pos,__val) { \
-    if ((__is)->encoding == INTSET_ENC_INT64) \
-        ((int64_t*)(__is)->contents)[__pos] = (__val); \
-    else if ((__is)->encoding == INTSET_ENC_INT32) \
-        ((int32_t*)(__is)->contents)[__pos] = (__val); \
-    else \
-        ((int16_t*)(__is)->contents)[__pos] = (__val); }
+/* Return the required encoding for the provided value. */
+static uint8_t _intsetValueEncoding(int64_t v) {
+    if (v < INT32_MIN || v > INT32_MAX)
+        return INTSET_ENC_INT64;
+    else if (v < INT16_MIN || v > INT16_MAX)
+        return INTSET_ENC_INT32;
+    else
+        return INTSET_ENC_INT16;
+}
+
+/* Return the value at pos, given an encoding. */
+static int64_t _intsetGetEncoded(intset *is, int pos, uint8_t enc) {
+    int64_t v64;
+    int32_t v32;
+    int16_t v16;
+
+    if (enc == INTSET_ENC_INT64) {
+        memcpy(&v64,((int64_t*)is->contents)+pos,sizeof(v64));
+        memrev64ifbe(&v64);
+        return v64;
+    } else if (enc == INTSET_ENC_INT32) {
+        memcpy(&v32,((int32_t*)is->contents)+pos,sizeof(v32));
+        memrev32ifbe(&v32);
+        return v32;
+    } else {
+        memcpy(&v16,((int16_t*)is->contents)+pos,sizeof(v16));
+        memrev16ifbe(&v16);
+        return v16;
+    }
+}
+
+/* Return the value at pos, using the configured encoding. */
+static int64_t _intsetGet(intset *is, int pos) {
+    return _intsetGetEncoded(is,pos,is->encoding);
+}
+
+/* Set the value at pos, using the configured encoding. */
+static void _intsetSet(intset *is, int pos, int64_t value) {
+    if (is->encoding == INTSET_ENC_INT64) {
+        ((int64_t*)is->contents)[pos] = value;
+        memrev64ifbe(((int64_t*)is->contents)+pos);
+    } else if (is->encoding == INTSET_ENC_INT32) {
+        ((int32_t*)is->contents)[pos] = value;
+        memrev32ifbe(((int32_t*)is->contents)+pos);
+    } else {
+        ((int16_t*)is->contents)[pos] = value;
+        memrev16ifbe(((int16_t*)is->contents)+pos);
+    }
+}

 
 /* Create an empty intset. */
 intset *intsetNew(void) {
 
 /* Create an empty intset. */
 intset *intsetNew(void) {


@@ -41,20 +76,6 @@ static intset *intsetResize(intset *is, uint32_t len) {
     return is;
 }
 
     return is;
 }
 

-static intset *intsetUpgrade(intset *is, uint8_t newenc, uint8_t extra, uint8_t offset) {
-    uint8_t curenc = is->encoding;
-    int length = is->length;
-
-    /* First set new encoding and resize */
-    is->encoding = newenc;
-    is = intsetResize(is,is->length+extra);
-
-    /* Upgrade back-to-front so we don't overwrite values */
-    while(length--)
-        INTSET_SET(is,length+offset,INTSET_GET_ENCODED(is,length,curenc));
-    return is;
-}
-

 /* Search for the position of "value". Return 1 when the value was found and
  * sets "pos" to the position of the value within the intset. Return 0 when
  * the value is not present in the intset and sets "pos" to the position
 /* Search for the position of "value". Return 1 when the value was found and
  * sets "pos" to the position of the value within the intset. Return 0 when
  * the value is not present in the intset and sets "pos" to the position


@@ -70,10 +91,10 @@ static uint8_t intsetSearch(intset *is, int64_t value, uint32_t *pos) {
     } else {
         /* Check for the case where we know we cannot find the value,
          * but do know the insert position. */
     } else {
         /* Check for the case where we know we cannot find the value,
          * but do know the insert position. */

-        if (value > INTSET_GET(is,is->length-1)) {
+        if (value > _intsetGet(is,is->length-1)) {

             if (pos) *pos = is->length;
             return 0;
             if (pos) *pos = is->length;
             return 0;

-        } else if (value < INTSET_GET(is,0)) {
+        } else if (value < _intsetGet(is,0)) {

             if (pos) *pos = 0;
             return 0;
         }
             if (pos) *pos = 0;
             return 0;
         }


@@ -81,7 +102,7 @@ static uint8_t intsetSearch(intset *is, int64_t value, uint32_t *pos) {
 
     while(max >= min) {
         mid = (min+max)/2;
 
     while(max >= min) {
         mid = (min+max)/2;

-        cur = INTSET_GET(is,mid);
+        cur = _intsetGet(is,mid);

         if (value > cur) {
             min = mid+1;
         } else if (value < cur) {
         if (value > cur) {
             min = mid+1;
         } else if (value < cur) {


@@ -100,6 +121,32 @@ static uint8_t intsetSearch(intset *is, int64_t value, uint32_t *pos) {
     }
 }
 
     }
 }
 

+/* Upgrades the intset to a larger encoding and inserts the given integer. */
+static intset *intsetUpgradeAndAdd(intset *is, int64_t value) {
+    uint8_t curenc = is->encoding;
+    uint8_t newenc = _intsetValueEncoding(value);
+    int length = is->length;
+    int prepend = value < 0 ? 1 : 0;
+
+    /* First set new encoding and resize */
+    is->encoding = newenc;
+    is = intsetResize(is,is->length+1);
+
+    /* Upgrade back-to-front so we don't overwrite values.
+     * Note that the "prepend" variable is used to make sure we have an empty
+     * space at either the beginning or the end of the intset. */
+    while(length--)
+        _intsetSet(is,length+prepend,_intsetGetEncoded(is,length,curenc));
+
+    /* Set the value at the beginning or the end. */
+    if (prepend)
+        _intsetSet(is,0,value);
+    else
+        _intsetSet(is,is->length,value);
+    is->length++;
+    return is;
+}
+

 static void intsetMoveTail(intset *is, uint32_t from, uint32_t to) {
     void *src, *dst;
     uint32_t bytes = is->length-from;
 static void intsetMoveTail(intset *is, uint32_t from, uint32_t to) {
     void *src, *dst;
     uint32_t bytes = is->length-from;


@@ -121,17 +168,16 @@ static void intsetMoveTail(intset *is, uint32_t from, uint32_t to) {
 
 /* Insert an integer in the intset */
 intset *intsetAdd(intset *is, int64_t value, uint8_t *success) {
 
 /* Insert an integer in the intset */
 intset *intsetAdd(intset *is, int64_t value, uint8_t *success) {

-    uint8_t valenc = INTSET_VALUE_ENCODING(value);
-    uint32_t pos, offset;
+    uint8_t valenc = _intsetValueEncoding(value);
+    uint32_t pos;

     if (success) *success = 1;
 
     /* Upgrade encoding if necessary. If we need to upgrade, we know that
      * this value should be either appended (if > 0) or prepended (if < 0),
      * because it lies outside the range of existing values. */
     if (valenc > is->encoding) {
     if (success) *success = 1;
 
     /* Upgrade encoding if necessary. If we need to upgrade, we know that
      * this value should be either appended (if > 0) or prepended (if < 0),
      * because it lies outside the range of existing values. */
     if (valenc > is->encoding) {

-        offset = value < 0 ? 1 : 0;
-        is = intsetUpgrade(is,valenc,1,offset);
-        pos = (value < 0) ? 0 : is->length;
+        /* This always succeeds, so we don't need to curry *success. */
+        return intsetUpgradeAndAdd(is,value);

     } else {
         /* Abort if the value is already present in the set.
          * This call will populate "pos" with the right position to insert
     } else {
         /* Abort if the value is already present in the set.
          * This call will populate "pos" with the right position to insert


@@ -145,14 +191,14 @@ intset *intsetAdd(intset *is, int64_t value, uint8_t *success) {
         if (pos < is->length) intsetMoveTail(is,pos,pos+1);
     }
 
         if (pos < is->length) intsetMoveTail(is,pos,pos+1);
     }
 

-    INTSET_SET(is,pos,value);
+    _intsetSet(is,pos,value);

     is->length++;
     return is;
 }
 
 /* Delete integer from intset */
     is->length++;
     return is;
 }
 
 /* Delete integer from intset */

-intset *intsetRemove(intset *is, int64_t value, uint8_t *success) {
-    uint8_t valenc = INTSET_VALUE_ENCODING(value);
+intset *intsetRemove(intset *is, int64_t value, int *success) {
+    uint8_t valenc = _intsetValueEncoding(value);

     uint32_t pos;
     if (success) *success = 0;
 
     uint32_t pos;
     if (success) *success = 0;
 


@@ -170,20 +216,20 @@ intset *intsetRemove(intset *is, int64_t value, uint8_t *success) {
 
 /* Determine whether a value belongs to this set */
 uint8_t intsetFind(intset *is, int64_t value) {
 
 /* Determine whether a value belongs to this set */
 uint8_t intsetFind(intset *is, int64_t value) {

-    uint8_t valenc = INTSET_VALUE_ENCODING(value);
+    uint8_t valenc = _intsetValueEncoding(value);

     return valenc <= is->encoding && intsetSearch(is,value,NULL);
 }
 
 /* Return random member */
 int64_t intsetRandom(intset *is) {
     return valenc <= is->encoding && intsetSearch(is,value,NULL);
 }
 
 /* Return random member */
 int64_t intsetRandom(intset *is) {

-    return INTSET_GET(is,rand()%is->length);
+    return _intsetGet(is,rand()%is->length);

 }
 
 /* Sets the value to the value at the given position. When this position is
  * out of range the function returns 0, when in range it returns 1. */
 uint8_t intsetGet(intset *is, uint32_t pos, int64_t *value) {
     if (pos < is->length) {
 }
 
 /* Sets the value to the value at the given position. When this position is
  * out of range the function returns 0, when in range it returns 1. */
 uint8_t intsetGet(intset *is, uint32_t pos, int64_t *value) {
     if (pos < is->length) {

-        *value = INTSET_GET(is,pos);
+        *value = _intsetGet(is,pos);

         return 1;
     }
     return 0;
         return 1;
     }
     return 0;


@@ -194,13 +240,18 @@ uint32_t intsetLen(intset *is) {
     return is->length;
 }
 
     return is->length;
 }
 

+/* Return intset blob size in bytes. */
+size_t intsetBlobLen(intset *is) {
+    return sizeof(intset)+is->length*is->encoding;
+}
+

 #ifdef INTSET_TEST_MAIN
 #include <sys/time.h>
 
 void intsetRepr(intset *is) {
     int i;
     for (i = 0; i < is->length; i++) {
 #ifdef INTSET_TEST_MAIN
 #include <sys/time.h>
 
 void intsetRepr(intset *is) {
     int i;
     for (i = 0; i < is->length; i++) {

-        printf("%lld\n", (uint64_t)INTSET_GET(is,i));
+        printf("%lld\n", (uint64_t)_intsetGet(is,i));

     }
     printf("\n");
 }
     }
     printf("\n");
 }


@@ -266,16 +317,16 @@ int main(int argc, char **argv) {
     sranddev();
 
     printf("Value encodings: "); {
     sranddev();
 
     printf("Value encodings: "); {

-        assert(INTSET_VALUE_ENCODING(-32768) == INTSET_ENC_INT16);
-        assert(INTSET_VALUE_ENCODING(+32767) == INTSET_ENC_INT16);
-        assert(INTSET_VALUE_ENCODING(-32769) == INTSET_ENC_INT32);
-        assert(INTSET_VALUE_ENCODING(+32768) == INTSET_ENC_INT32);
-        assert(INTSET_VALUE_ENCODING(-2147483648) == INTSET_ENC_INT32);
-        assert(INTSET_VALUE_ENCODING(+2147483647) == INTSET_ENC_INT32);
-        assert(INTSET_VALUE_ENCODING(-2147483649) == INTSET_ENC_INT64);
-        assert(INTSET_VALUE_ENCODING(+2147483648) == INTSET_ENC_INT64);
-        assert(INTSET_VALUE_ENCODING(-9223372036854775808ull) == INTSET_ENC_INT64);
-        assert(INTSET_VALUE_ENCODING(+9223372036854775807ull) == INTSET_ENC_INT64);
+        assert(_intsetValueEncoding(-32768) == INTSET_ENC_INT16);
+        assert(_intsetValueEncoding(+32767) == INTSET_ENC_INT16);
+        assert(_intsetValueEncoding(-32769) == INTSET_ENC_INT32);
+        assert(_intsetValueEncoding(+32768) == INTSET_ENC_INT32);
+        assert(_intsetValueEncoding(-2147483648) == INTSET_ENC_INT32);
+        assert(_intsetValueEncoding(+2147483647) == INTSET_ENC_INT32);
+        assert(_intsetValueEncoding(-2147483649) == INTSET_ENC_INT64);
+        assert(_intsetValueEncoding(+2147483648) == INTSET_ENC_INT64);
+        assert(_intsetValueEncoding(-9223372036854775808ull) == INTSET_ENC_INT64);
+        assert(_intsetValueEncoding(+9223372036854775807ull) == INTSET_ENC_INT64);

         ok();
     }
 
         ok();
     }