Code for tests storing data in multiple AVLs.

(note: unretrievable data as implemented)

src/obiavl.c

@@ -30,6 +30,159 @@
 #define DEBUG_LEVEL 0	// TODO has to be defined somewhere else (cython compil flag?)
 
 
+////crc  crcTable[256];
+//static crc crcTable[] = {
+//0x00, 0xd8, 0x68, 0xb0, 0xd0, 0x8, 0xb8, 0x60, 0x78, 0xa0, 0x10, 0xc8, 0xa8, 0x70, 0xc0, 0x18, 0xf0, 0x28, 0x98, 0x40, 0x20, 0xf8, 0x48, 0x90, 0x88, 0x50, 0xe0, 0x38, 0x58, 0x80, 0x30, 0xe8, 0x38, 0xe0, 0x50, 0x88, 0xe8, 0x30, 0x80, 0x58, 0x40, 0x98, 0x28, 0xf0, 0x90, 0x48, 0xf8, 0x20, 0xc8, 0x10, 0xa0, 0x78, 0x18, 0xc0, 0x70, 0xa8, 0xb0, 0x68, 0xd8, 0, 0x60, 0xb8, 0x8, 0xd0, 0x70, 0xa8, 0x18, 0xc0, 0xa0, 0x78, 0xc8, 0x10, 0x8, 0xd0, 0x60, 0xb8, 0xd8, 0, 0xb0, 0x68, 0x80, 0x58, 0xe8, 0x30, 0x50, 0x88, 0x38, 0xe0, 0xf8, 0x20, 0x90, 0x48, 0x28, 0xf0, 0x40, 0x98, 0x48, 0x90, 0x20, 0xf8, 0x98, 0x40, 0xf0, 0x28, 0x30, 0xe8, 0x58, 0x80, 0xe0, 0x38, 0x88, 0x50, 0xb8, 0x60, 0xd0, 0x8, 0x68, 0xb0, 0, 0xd8, 0xc0, 0x18, 0xa8, 0x70, 0x10, 0xc8, 0x78, 0xa0, 0xe0, 0x38, 0x88, 0x50, 0x30, 0xe8, 0x58, 0x80, 0x98, 0x40, 0xf0, 0x28, 0x48, 0x90, 0x20, 0xf8, 0x10, 0xc8, 0x78, 0xa0, 0xc0, 0x18, 0xa8, 0x70, 0x68, 0xb0, 0, 0xd8, 0xb8, 0x60, 0xd0, 0x8, 0xd8, 0, 0xb0, 0x68, 0x8, 0xd0, 0x60, 0xb8, 0xa0, 0x78, 0xc8, 0x10, 0x70, 0xa8, 0x18, 0xc0, 0x28, 0xf0, 0x40, 0x98, 0xf8, 0x20, 0x90, 0x48, 0x50, 0x88, 0x38, 0xe0, 0x80, 0x58, 0xe8, 0x30, 0x90, 0x48, 0xf8, 0x20, 0x40, 0x98, 0x28, 0xf0, 0xe8, 0x30, 0x80, 0x58, 0x38, 0xe0, 0x50, 0x88, 0x60, 0xb8, 0x8, 0xd0, 0xb0, 0x68, 0xd8, 0, 0x18, 0xc0, 0x70, 0xa8, 0xc8, 0x10, 0xa0, 0x78, 0xa8, 0x70, 0xc0, 0x18, 0x78, 0xa0, 0x10, 0xc8, 0xd0, 0x8, 0xb8, 0x60, 0, 0xd8, 0x68, 0xb0, 0x58, 0x80, 0x30, 0xe8, 0x88, 0x50, 0xe0, 0x38, 0x20, 0xf8, 0x48, 0x90, 0xf0, 0x28, 0x98, 0x40
+//};
+//
+//
+//void crcInit(void)
+//{
+//    crc  remainder;
+//
+//    fprintf(stderr, "\n");
+//
+//    /*
+//     * Compute the remainder of each possible dividend.
+//     */
+//    for (int dividend = 0; dividend < 256; ++dividend)
+//    {
+//        /*
+//         * Start with the dividend followed by zeros.
+//         */
+//        remainder = dividend << (WIDTH - 8);
+//
+//        /*
+//         * Perform modulo-2 division, a bit at a time.
+//         */
+//        for (uint8_t bit = 8; bit > 0; --bit)
+//        {
+//            /*
+//             * Try to divide the current data bit.
+//             */
+//            if (remainder & TOPBIT)
+//            {
+//                remainder = (remainder << 1) ^ POLYNOMIAL;
+//            }
+//            else
+//            {
+//                remainder = (remainder << 1);
+//            }
+//        }
+//
+//        /*
+//         * Store the result into the table.
+//         */
+//        crcTable[dividend] = remainder;
+//        fprintf(stderr, "%#x, ", remainder);
+//    }
+//
+//}   /* crcInit() */
+//
+//
+//crc crcFast(uint8_t const message[], int nBytes)
+//{
+//    uint8_t data;
+//    crc remainder = 0;
+//
+//
+//    /*
+//     * Divide the message by the polynomial, a byte at a time.
+//     */
+//    for (int byte = 0; byte < nBytes; ++byte)
+//    {
+//        data = message[byte] ^ (remainder >> (WIDTH - 8));
+//        remainder = crcTable[data] ^ (remainder << 8);
+//    }
+//
+//    /*
+//     * The final remainder is the CRC.
+//     */
+//    return (remainder);
+//
+//}   /* crcFast() */
+//
+//
+//crc compute_crc(const char* s)
+//{
+//	crc c;
+//	//uint8_t cache;
+//
+//	//cache = 15;
+//
+////	crcInit();
+//
+//	c = crcFast(s, strlen(s));
+//
+//	//fprintf(stderr, "\nlen = %d", strlen(argv[1]));
+//
+//	//fprintf(stderr, "\ncrc = %u\n\n", c);
+//	//fprintf(stderr, "\ncrc mod 8 = %u\n\n", c%8);
+//
+//	c = c >> 3;
+//	//fprintf(stderr, "\nshifted crc = %u\n\n", c);
+//
+//	//c = c & cache;
+//	//c = c % 32;
+//
+//	//fprintf(stderr, "\ncrc = %u\n\n", c);
+//
+//	return (c & 7);
+//}
+
+static unsigned char crc8_table[] = {
+    0x00, 0x3e, 0x7c, 0x42, 0xf8, 0xc6, 0x84, 0xba, 0x95, 0xab, 0xe9, 0xd7,
+    0x6d, 0x53, 0x11, 0x2f, 0x4f, 0x71, 0x33, 0x0d, 0xb7, 0x89, 0xcb, 0xf5,
+    0xda, 0xe4, 0xa6, 0x98, 0x22, 0x1c, 0x5e, 0x60, 0x9e, 0xa0, 0xe2, 0xdc,
+    0x66, 0x58, 0x1a, 0x24, 0x0b, 0x35, 0x77, 0x49, 0xf3, 0xcd, 0x8f, 0xb1,
+    0xd1, 0xef, 0xad, 0x93, 0x29, 0x17, 0x55, 0x6b, 0x44, 0x7a, 0x38, 0x06,
+    0xbc, 0x82, 0xc0, 0xfe, 0x59, 0x67, 0x25, 0x1b, 0xa1, 0x9f, 0xdd, 0xe3,
+    0xcc, 0xf2, 0xb0, 0x8e, 0x34, 0x0a, 0x48, 0x76, 0x16, 0x28, 0x6a, 0x54,
+    0xee, 0xd0, 0x92, 0xac, 0x83, 0xbd, 0xff, 0xc1, 0x7b, 0x45, 0x07, 0x39,
+    0xc7, 0xf9, 0xbb, 0x85, 0x3f, 0x01, 0x43, 0x7d, 0x52, 0x6c, 0x2e, 0x10,
+    0xaa, 0x94, 0xd6, 0xe8, 0x88, 0xb6, 0xf4, 0xca, 0x70, 0x4e, 0x0c, 0x32,
+    0x1d, 0x23, 0x61, 0x5f, 0xe5, 0xdb, 0x99, 0xa7, 0xb2, 0x8c, 0xce, 0xf0,
+    0x4a, 0x74, 0x36, 0x08, 0x27, 0x19, 0x5b, 0x65, 0xdf, 0xe1, 0xa3, 0x9d,
+    0xfd, 0xc3, 0x81, 0xbf, 0x05, 0x3b, 0x79, 0x47, 0x68, 0x56, 0x14, 0x2a,
+    0x90, 0xae, 0xec, 0xd2, 0x2c, 0x12, 0x50, 0x6e, 0xd4, 0xea, 0xa8, 0x96,
+    0xb9, 0x87, 0xc5, 0xfb, 0x41, 0x7f, 0x3d, 0x03, 0x63, 0x5d, 0x1f, 0x21,
+    0x9b, 0xa5, 0xe7, 0xd9, 0xf6, 0xc8, 0x8a, 0xb4, 0x0e, 0x30, 0x72, 0x4c,
+    0xeb, 0xd5, 0x97, 0xa9, 0x13, 0x2d, 0x6f, 0x51, 0x7e, 0x40, 0x02, 0x3c,
+    0x86, 0xb8, 0xfa, 0xc4, 0xa4, 0x9a, 0xd8, 0xe6, 0x5c, 0x62, 0x20, 0x1e,
+    0x31, 0x0f, 0x4d, 0x73, 0xc9, 0xf7, 0xb5, 0x8b, 0x75, 0x4b, 0x09, 0x37,
+    0x8d, 0xb3, 0xf1, 0xcf, 0xe0, 0xde, 0x9c, 0xa2, 0x18, 0x26, 0x64, 0x5a,
+    0x3a, 0x04, 0x46, 0x78, 0xc2, 0xfc, 0xbe, 0x80, 0xaf, 0x91, 0xd3, 0xed,
+    0x57, 0x69, 0x2b, 0x15};
+
+
+unsigned crc8(unsigned char *data, size_t len)
+{
+    unsigned char *end;
+    unsigned crc;
+
+    crc = 0;
+
+    crc ^= 0xff;
+    end = data + len;
+    do {
+        crc = crc8_table[crc ^ *data++];
+    } while (data < end);
+    return crc ^ 0xff;
+}
+
+crc compute_crc(const char* s)
+{
+    unsigned c;
+
+    c = crc8(s, strlen(s));
+    //fprintf(stderr, "%02x\n", c);
+    return (c & 7);
+}
+
+
+
+
+
 /**************************************************************************
  *
  * D E C L A R A T I O N   O F   T H E   P R I V A T E   F U N C T I O N S
@@ -605,6 +758,8 @@ int grow_avl_data(OBIDMS_avl_p avl)		// TODO Lock when needed
 	// Set new data size
 	((avl->data)->header)->data_size_max = new_data_size;
 
+	//fprintf(stderr, "\nGrowing AVL, new data size = %lld, count = %ld\n", new_data_size, (avl->header)->nb_items);
+
 	// Initialize new data to 0
 	memset(((avl->data)->data)+old_data_size, 0, new_data_size - old_data_size);
 
@@ -976,6 +1131,24 @@ OBIDMS_avl_p obi_avl(OBIDMS_p dms, const char* avl_name)
 }
 
 
+OBIDMS_avl_p* obi_create_avl_in_64_parts(OBIDMS_p dms, const char* avl_name)
+{
+	OBIDMS_avl_p* avls;
+	char* avl_name_with_idx;
+	uint8_t i;
+
+	avls = (OBIDMS_avl_p*) malloc(64*sizeof(OBIDMS_avl_p));
+
+	for (i=0; i < 64; i++)
+	{
+		asprintf(&avl_name_with_idx,"%s_%u", avl_name, i);
+		avls[i] = obi_create_avl(dms, avl_name_with_idx);
+	}
+
+	return avls;
+}
+
+
 OBIDMS_avl_p obi_create_avl(OBIDMS_p dms, const char* avl_name)
 {
 	char* 				avl_file_name;
@@ -1446,7 +1619,7 @@ index_t obi_avl_add(OBIDMS_avl_p avl, byte_t* value)
 	index_t node_idx;
 	byte_t* to_compare;
 	int comp;
-	uint8_t n = 0;
+	int n = 0;
 	int depth = 0;
 
 	// Check if first node
@@ -1499,7 +1672,10 @@ index_t obi_avl_add(OBIDMS_avl_p avl, byte_t* value)
 			next = current_node->right_child;
 		else if (comp == 0)
 			// Value already stored
+		{
+			//fprintf(stderr, "\n>>>ALREADY IN, %s, %lld\n", obi_obibytes_to_seq(value), (avl->header)->nb_items);
 			return current_node->value;
+		}
 
 		depth++;
 	}
@@ -1612,7 +1788,7 @@ byte_t* obi_str_to_obibytes(char* value)
 	*((int32_t*)(value_b+1)) = length;
 
 	// Store the initial length (in bytes) of the decoded value (same as encoded for character strings)
-	*((int32_t*)(value_b+5)) = length;
+	*((int64_t*)(value_b+5)) = length;
 
 	// Store the character string
 	strcpy(value_b+BYTE_ARRAY_HEADER_SIZE, value);

src/obiavl.h

@@ -340,5 +340,12 @@ byte_t* obi_seq_to_obibytes(char* seq);
 const char* obi_obibytes_to_seq(byte_t* value_b);
 
 
+OBIDMS_avl_p* obi_create_avl_in_64_parts(OBIDMS_p dms, const char* avl_name);
+
+typedef uint8_t crc;
+
+crc compute_crc(const char* s);
+
+
 #endif /* OBIAVL_H_ */
 

src/obidmscolumn.c

@@ -521,7 +521,7 @@ OBIDMS_column_p obi_create_column(OBIDMS_p    dms,
 	OBIDMS_column_p 			new_column;
 	OBIDMS_column_directory_p	column_directory;
 	OBIDMS_column_header_p 		header;
-	OBIDMS_avl_p				avl;
+	OBIDMS_avl_p*				avl;
 	size_t 						file_size;
 	obiversion_t 				version_number;
 	char* 						column_file_name;
@@ -723,7 +723,7 @@ OBIDMS_column_p obi_create_column(OBIDMS_p    dms,
 	// If the data type is OBI_STR or OBI_SEQ, the associated obi_avl is opened or created
 	if ((returned_data_type == OBI_STR) || (returned_data_type == OBI_SEQ))
 	{
-		avl = obi_avl(dms, avl_name);
+		avl = obi_create_avl_in_64_parts(dms, avl_name);
 		if (avl == NULL)
 		{
 			obidebug(1, "\nError opening or creating the aVL tree associated with a column");
@@ -732,7 +732,7 @@ OBIDMS_column_p obi_create_column(OBIDMS_p    dms,
 			free(new_column);
 			return NULL;
 		}
-		new_column->avl = avl;
+		memcpy(new_column->avl, avl, 64*sizeof(OBIDMS_avl_p));
 		strncpy(header->avl_name, avl_name, AVL_MAX_NAME);
 	}
 
@@ -886,7 +886,7 @@ OBIDMS_column_p obi_open_column(OBIDMS_p dms,
 			free(column);
 			return NULL;
 		}
-		column->avl = avl;
+		//column->avl = avl;	TODO
 	}
 
 	close(column_file_descriptor);
@@ -1020,12 +1020,12 @@ int obi_close_column(OBIDMS_column_p column)
 			}
 		}
 
-		// If the data type is OBI_STR or OBI_SEQ, the associated AVL tree is closed
+		// If the data type is OBI_STR or OBI_SEQ, the associated AVL tree is closed	TODO
-		if (((column->header)->returned_data_type == OBI_STR) || ((column->header)->returned_data_type == OBI_SEQ))
+//		if (((column->header)->returned_data_type == OBI_STR) || ((column->header)->returned_data_type == OBI_SEQ))
-		{
+//		{
-			if (obi_close_avl(column->avl) < 0)
+//			if (obi_close_avl(column->avl) < 0)
-				return -1;
+//				return -1;
-		}
+//		}
 
 		// Munmap data
 		if (munmap(column->data, (column->header)->data_size) < 0)

src/obidmscolumn.h

@@ -98,7 +98,7 @@ typedef struct OBIDMS_column {
 	 	 	 	 	 	 	 	 	 	 	 	 	 */
 	OBIDMS_column_header_p		header; 		 	/**< A pointer to the header of the column.
 	 	 	 	 	 	 	 	 	 	 	 	 	 */
-	OBIDMS_avl_p 				avl;				/**< A pointer to the AVL tree associated with the column if there is one.
+	OBIDMS_avl_p 				avl[64];   			/**< A pointer to the group of AVL trees associated with the column if there is one.
 	 	 	 	 	 	 	 	 	 	 	 	 	 */
 	void*                   	data;   		 	/**< A `void` pointer to the beginning of the data.
 	                                 	 	         *

src/obidmscolumn_seq.c

@@ -61,8 +61,13 @@ int obi_column_set_obiseq_with_elt_idx(OBIDMS_column_p column, index_t line_nb,
 	if (value_b == NULL)
 		return -1;
 
+	if (strlen(value_b) == 0)
+		fprintf(stderr, "\nPOUIC");
+
+	//fprintf(stderr, "\n>%s||%s", value, obi_obibytes_to_seq(value_b));
+
 	// Add in the AVL tree
-	idx = obi_avl_add(column->avl, value_b);
+	idx = obi_avl_add((column->avl)[compute_crc(value)], value_b);
 	if (idx == -1)
 		return -1;
 
@@ -130,7 +135,7 @@ const char* obi_column_get_obiseq_with_elt_idx(OBIDMS_column_p column, index_t l
 	if (idx == OBIIdx_NA)
 		return OBISeq_NA;
 
-	value_b = obi_avl_get(column->avl, idx);
+	//value_b = obi_avl_get((column->avl)[crc(value)], idx);
 	return obi_obibytes_to_seq(value_b);
 }
 

src/obidmscolumn_str.c

@@ -61,7 +61,7 @@ int obi_column_set_obistr_with_elt_idx(OBIDMS_column_p column, index_t line_nb,
 		return -1;
 
 	// Add in the AVL tree
-	idx = obi_avl_add(column->avl, value_b);
+	idx = obi_avl_add((column->avl)[compute_crc(value)], value_b);
 	if (idx == -1)
 		return -1;
 
@@ -129,7 +129,7 @@ const char* obi_column_get_obistr_with_elt_idx(OBIDMS_column_p column, index_t l
 	if (idx == OBIIdx_NA)
 		return OBIStr_NA;
 
-	value_b = obi_avl_get(column->avl, idx);
+	//value_b = obi_avl_get(column->avl, idx);
 	return obi_obibytes_to_str(value_b);
 }