项目地址 How Does a Database Work? | Let’s Build a Simple Database (cstack.github.io)。
这里我们完成上一章留下来的坑,完成从行存储到b树的变化,下一次再处理叶节点的喜欢的可以点个赞再走!
我们修改一下插入,它应该插入在合适的位置。如果有相同的key值,那么就重复了,这里我们之前的EXECUTE_PRIMARY_KEY_DUPLICATION去掉,用它的EXECUTE_DUPLICATE_KEY。
ExecuteResult execute_insert(Statement* statement, Table* table) {
Row row;
void* node = get_page(table->pager, table->root_page_num);
uint32_t num_cells = (*leaf_node_num_cells(node));
if (num_cells >= LEAF_NODE_MAX_CELLS) {
return EXECUTE_TABLE_FULL;
}
Row* row_to_insert = &(statement->row_to_insert);
uint32_t key_to_insert = row_to_insert->id;
Cursor* cursor = table_find(table, key_to_insert);
if (cursor->cell_num < num_cells) {
uint32_t key_at_index = *leaf_node_key(node, cursor->cell_num);
if (key_at_index == key_to_insert) {
return EXECUTE_DUPLICATE_KEY;
}
}
leaf_node_insert(cursor, row_to_insert->id, row_to_insert);
free(cursor);
return EXECUTE_SUCCESS;
}
定义修改
typedef enum {
EXECUTE_SUCCESS,
EXECUTE_TABLE_FULL,
EXECUTE_DUPLICATE_KEY,
EXECUTE_NOT_FOUND
} ExecuteResult;
实现修改
switch (execute_statement(&statement, table)) {
case (EXECUTE_SUCCESS):
printf("Executed.n");
break;
case (EXECUTE_DUPLICATE_KEY):
printf("Error: Duplicate key.n");
break;
case (EXECUTE_NOT_FOUND):
printf("Error: Not found.n");
break;
case (EXECUTE_TABLE_FULL):
printf("Error: Table full.n");
break;
}
我们的以前插入到最后面,现在不用了,故相应的table_end删除。
那现在我们的游标如何查找呢?这里我们实现。这里有点二分法的意思,用min_index和one_past_max_index去逼近index
Cursor* table_find(Table* table, uint32_t key) {
uint32_t root_page_num = table->root_page_num;
void* root_node = get_page(table->pager, root_page_num);
if (get_node_type(root_node) == NODE_LEAF) {
return leaf_node_find(table, root_page_num, key);
} else {
printf("Need to implement searching an internal noden");
exit(EXIT_FAILURE);
}
}
Cursor* leaf_node_find(Table* table, uint32_t page_num, uint32_t key) {
void* node = get_page(table->pager, page_num);
uint32_t num_cells = *leaf_node_num_cells(node);
Cursor* cursor = malloc(sizeof(Cursor));
cursor->table = table;
cursor->page_num = page_num;
// Binary search
uint32_t min_index = 0;
uint32_t one_past_max_index = num_cells;
while (one_past_max_index != min_index) {
uint32_t index = (min_index + one_past_max_index) / 2;
uint32_t key_at_index = *leaf_node_key(node, index);
if (key == key_at_index) {
cursor->cell_num = index;
return cursor;
}
if (key < key_at_index) {
one_past_max_index = index;
} else {
min_index = index + 1;
}
}
cursor->cell_num = min_index;
return cursor;
}
当然获取和设置节点的值需要用到get和set函数
NodeType get_node_type(void* node) {
uint8_t value = *((uint8_t*)(node + NODE_TYPE_OFFSET));
return (NodeType)value;
}
void set_node_type(void* node, NodeType type) {
uint8_t value = type;
*((uint8_t*)(node + NODE_TYPE_OFFSET)) = value;
}
这样我们初始化就set节点
void initialize_leaf_node(void* node) {
set_node_type(node, NODE_LEAF);
*leaf_node_num_cells(node) = 0;
}
这里我们可以先把查询、修改完成了。这里我为了方便,让update不能修改主键,大家可以自己去实现这个内容。
ExecuteResult execute_select(Statement* statement, Table* table) {
Cursor* cursor = table_start(table);
Row row;
void* node = get_page(table->pager, table->root_page_num);
uint32_t num_cells = *leaf_node_num_cells(node);
for(uint32_t i=0;icell_num =i;
deserialize_row(leaf_node_value(node, cursor->cell_num),&row);
if(statement->row_to_select==ID){
printf("(%d)n", row.id);
}
else if(statement->row_to_select==USERNAME){
printf("(%s)n", row.username);
}
else if(statement->row_to_select==EMAIL){
printf("(%s)n", row.email);
}
else if(statement->row_to_select==ALL){
printf("(%d, %s, %s)n", row.id, row.username, row.email);
}
}
free(cursor);
return EXECUTE_SUCCESS;
}
ExecuteResult execute_update(Statement* statement, Table* table) {
Row row;
bool flag=false;
Row* row_to_update = &(statement->row_to_update_old);
void* node = get_page(table->pager, table->root_page_num);
uint32_t key_to_update = row_to_update->id;
Cursor* cursor = table_find(table, key_to_update);
Row* row_to_update_old = &(statement->row_to_update_old);
uint32_t num_cells = *leaf_node_num_cells(node);
if(statement->row_to_update_new.id!=statement->row_to_update_old.id){
return EXECUTE_PRIMARY_CHANGE;
}
for(uint32_t i=0;icell_num =i;
deserialize_row(leaf_node_value(node, cursor->cell_num),&row);
if(strcmp(statement->row_to_update_old.username,row.username )==0&&strcmp(statement->row_to_update_old.email,row.email)==0)
{
flag=true;
strcpy(row.username,statement->row_to_update_new.username);
strcpy(row.email,statement->row_to_update_new.email);
serialize_row(&row, leaf_node_value(node, cursor->cell_num));
return EXECUTE_SUCCESS;
}
serialize_row(&row, leaf_node_value(node, cursor->cell_num));
cursor_advance(cursor);
}
free(cursor);
return EXECUTE_NOT_FOUND;
}
我们添加了EXECUTE_PRIMARY_CHANGE变量,老规矩,我们修改定义及调用。
typedef enum {
EXECUTE_SUCCESS,
EXECUTE_TABLE_FULL,
EXECUTE_DUPLICATE_KEY,
EXECUTE_NOT_FOUND,
EXECUTE_PRIMARY_CHANGE
} ExecuteResult;
switch (execute_statement(&statement, table)) {
case (EXECUTE_SUCCESS):
printf("Executed.n");
break;
case (EXECUTE_PRIMARY_CHANGE):
printf("Error: Can't change primary key.n");
break;
case (EXECUTE_DUPLICATE_KEY):
printf("Error: Duplicate key.n");
break;
case (EXECUTE_NOT_FOUND):
printf("Error: Not found.n");
break;
case (EXECUTE_TABLE_FULL):
printf("Error: Table full.n");
break;
}
至于删除嘛,这个基本上和插入是相反的,我们在这里做出优化,删除的输入为"delete 主键"。另外两个参数不要了。先修改预处理
PrepareResult prepare_delete(InputBuffer* input_buffer,Statement* statement){
statement->type = STATEMENT_DELETE;
char* keyword = strtok(input_buffer->buffer, " ");
char* id_string = strtok(NULL, " ");
char* check=strtok(NULL," ");
if(check!=NULL){
return PREPARE_SYNTAX_ERROR;
}
if (id_string == NULL ) {
return PREPARE_SYNTAX_ERROR;
}
int id = atoi(id_string);
for(uint32_t i=0;i=10)
return PREPARE_ID_TOO_LONG;
statement->row_to_delete.id = id;
return PREPARE_SUCCESS;
}
再改实现
ExecuteResult execute_delete(Statement* statement, Table* table) {
bool flag=false;
void* node = get_page(table->pager, table->root_page_num);
uint32_t num_cells = (*leaf_node_num_cells(node));
Row* row_to_delete = &(statement->row_to_delete);
uint32_t key_to_delete= row_to_delete->id;
Cursor* cursor = table_find(table, key_to_delete);
if (cursor->cell_num < num_cells) {
uint32_t key_at_index = *leaf_node_key(node, cursor->cell_num);
if (key_at_index == key_to_delete) {
flag=true;
}
}
if(flag==false)
return EXECUTE_NOT_FOUND;
leaf_node_delete(cursor, row_to_delete->id, row_to_delete);
free(cursor);
return EXECUTE_SUCCESS;
}
void leaf_node_delete(Cursor* cursor, uint32_t key, Row* value) {
void* node = get_page(cursor->table->pager, cursor->page_num);
uint32_t num_cells = *leaf_node_num_cells(node);
if (num_cells <= LEAF_NODE_LESS_CELLS) {
printf("Need to implement inserting a leaf node.n");
exit(EXIT_FAILURE);
}
if (cursor->cell_numcell_num; i <=num_cells;i++) {
if(*(leaf_node_key(node, i)) > key){
memcpy(leaf_node_cell(node, i-1), leaf_node_cell(node, i),LEAF_NODE_CELL_SIZE);
}
}
}
*(leaf_node_num_cells(node)) -= 1;
cursor->cell_num-=1;
}
我们定义这个LEAF_NODE_LESS_CELL
const uint32_t LEAF_NODE_LESS_CELLS =LEAF_NODE_MAX_CELLS/2;
这样就完成了!
这里给出全部的源代码。
#include#include #include #include #include #include #include #include #include #define COLUMN_USERNAME_SIZE 32 #define COLUMN_EMAIL_SIZE 255 #define size_of_attribute(Struct, Attribute) sizeof(((Struct*)0)->Attribute) #define TABLE_MAX_PAGES 100 #include typedef enum { META_COMMAND_SUCCESS, META_COMMAND_UNRECOGNIZED_COMMAND } MetaCommandResult; typedef enum { PREPARE_SUCCESS, PREPARE_NEGATIVE_ID, PREPARE_ILLEGAL_ID, PREPARE_ID_TOO_LONG, PREPARE_SYNTAX_ERROR, PREPARE_STRING_TOO_LONG, PREPARE_UNRECOGNIZED_STATEMENT } PrepareResult; typedef enum { EXECUTE_SUCCESS, EXECUTE_TABLE_FULL, EXECUTE_DUPLICATE_KEY, EXECUTE_NOT_FOUND, EXECUTE_PRIMARY_CHANGE } ExecuteResult; typedef enum { STATEMENT_INSERT, STATEMENT_SELECT, STATEMENT_DELETE, STATEMENT_UPDATE } StatementType; typedef enum { NODE_INTERNAL, NODE_LEAF } NodeType; typedef enum { ID, USERNAME, EMAIL, ALL } SelectResult; typedef struct { int file_descriptor; uint32_t file_length; uint32_t num_pages; void* pages[TABLE_MAX_PAGES]; } Pager; typedef struct { Pager* pager; uint32_t root_page_num; } Table; typedef struct { uint32_t id; char username[COLUMN_USERNAME_SIZE+1]; char email[COLUMN_EMAIL_SIZE+1]; } Row; typedef struct{ char* buffer; size_t buffer_length; ssize_t input_length; } InputBuffer; typedef struct { StatementType type; Row row_to_insert; SelectResult row_to_select; Row row_to_delete; Row row_to_update_old; Row row_to_update_new; } Statement; typedef struct { Table* table; uint32_t page_num; uint32_t cell_num; bool end_of_table; } Cursor; const uint32_t ID_OFFSET = 0; const uint32_t PAGE_SIZE = 4096; const uint32_t ID_SIZE = size_of_attribute(Row, id); const uint32_t USERNAME_SIZE = size_of_attribute(Row, username); const uint32_t EMAIL_SIZE = size_of_attribute(Row, email); const uint32_t USERNAME_OFFSET = ID_OFFSET + ID_SIZE; const uint32_t EMAIL_OFFSET = USERNAME_OFFSET + USERNAME_SIZE; const uint32_t ROW_SIZE = ID_SIZE + USERNAME_SIZE + EMAIL_SIZE; const uint32_t ROWS_PER_PAGE = PAGE_SIZE / ROW_SIZE; const uint32_t TABLE_MAX_ROWS = ROWS_PER_PAGE * TABLE_MAX_PAGES; const uint32_t NODE_TYPE_SIZE = sizeof(uint8_t); const uint32_t NODE_TYPE_OFFSET = 0; const uint32_t IS_ROOT_SIZE = sizeof(uint8_t); const uint32_t IS_ROOT_OFFSET = NODE_TYPE_SIZE; const uint32_t PARENT_POINTER_SIZE = sizeof(uint32_t); const uint32_t PARENT_POINTER_OFFSET = IS_ROOT_OFFSET + IS_ROOT_SIZE; const uint8_t COMMON_NODE_HEADER_SIZE =NODE_TYPE_SIZE + IS_ROOT_SIZE + PARENT_POINTER_SIZE; const uint32_t LEAF_NODE_NUM_CELLS_SIZE = sizeof(uint32_t); const uint32_t LEAF_NODE_NUM_CELLS_OFFSET = COMMON_NODE_HEADER_SIZE; const uint32_t LEAF_NODE_HEADER_SIZE =COMMON_NODE_HEADER_SIZE + LEAF_NODE_NUM_CELLS_SIZE; const uint32_t LEAF_NODE_KEY_SIZE = sizeof(uint32_t); const uint32_t LEAF_NODE_KEY_OFFSET = 0; const uint32_t LEAF_NODE_VALUE_SIZE = ROW_SIZE; const uint32_t LEAF_NODE_VALUE_OFFSET =LEAF_NODE_KEY_OFFSET + LEAF_NODE_KEY_SIZE; const uint32_t LEAF_NODE_CELL_SIZE = LEAF_NODE_KEY_SIZE + LEAF_NODE_VALUE_SIZE; const uint32_t LEAF_NODE_SPACE_FOR_CELLS = PAGE_SIZE - LEAF_NODE_HEADER_SIZE; const uint32_t LEAF_NODE_MAX_CELLS =LEAF_NODE_SPACE_FOR_CELLS / LEAF_NODE_CELL_SIZE; const uint32_t LEAF_NODE_LESS_CELLS =LEAF_NODE_MAX_CELLS/2; void free_table(Table* table) ; void close_input_buffer(InputBuffer* input_buffer); void pager_flush(Pager* pager, uint32_t page_num) ; Pager* pager_open(const char* filename); void* get_page(Pager* pager, uint32_t page_num); void db_close(Table* table); Cursor* table_start(Table* table); Cursor* table_end(Table* table); void* cursor_value(Cursor* cursor); void cursor_advance(Cursor* cursor); uint32_t* leaf_node_num_cells(void* node); void* leaf_node_cell(void* node, uint32_t cell_num); uint32_t* leaf_node_key(void* node, uint32_t cell_num); void* leaf_node_value(void* node, uint32_t cell_num); void leaf_node_insert(Cursor* cursor, uint32_t key, Row* value); void print_constants(); void print_leaf_node(void* node); Cursor* table_find(Table* table, uint32_t key); Cursor* leaf_node_find(Table* table, uint32_t page_num, uint32_t key); NodeType get_node_type(void* node); void set_node_type(void* node, NodeType type); void leaf_node_delete(Cursor* cursor, uint32_t key, Row* value); MetaCommandResult do_meta_command(InputBuffer* input_buffer,Table* table) { if (strcmp(input_buffer->buffer, ".exit") == 0) { close_input_buffer(input_buffer); db_close(table); exit(EXIT_SUCCESS); } else if (strcmp(input_buffer->buffer, ".btree") == 0) { printf("Tree:n"); print_leaf_node(get_page(table->pager, 0)); return META_COMMAND_SUCCESS; } else if (strcmp(input_buffer->buffer, ".constants") == 0) { printf("Constants:n"); print_constants(); return META_COMMAND_SUCCESS; } else { return META_COMMAND_UNRECOGNIZED_COMMAND; } } InputBuffer* new_input_buffer(){ InputBuffer* input_buffer=(InputBuffer*)malloc(sizeof(InputBuffer)); input_buffer->buffer=NULL; input_buffer->buffer_length=0; input_buffer->input_length=0; return input_buffer; } Table* db_open(const char* filename) { Pager* pager = pager_open(filename); Table* table = malloc(sizeof(Table)); table->pager = pager; table->root_page_num = 0; if (pager->num_pages == 0) { void* root_node = get_page(pager, 0); initialize_leaf_node(root_node); } return table; } Pager* pager_open(const char* filename) { int fd = open(filename, O_RDWR | // Read/Write mode O_CREAT, // Create file if it does not exist S_IWUSR | // User write permission S_IRUSR // User read permission ); if (fd == -1) { printf("Unable to open filen"); exit(EXIT_FAILURE); } off_t file_length = lseek(fd, 0, SEEK_END); Pager* pager = malloc(sizeof(Pager)); pager->file_descriptor = fd; pager->file_length = file_length; pager->num_pages = (file_length / PAGE_SIZE); if (file_length % PAGE_SIZE != 0) { printf("Db file is not a whole number of pages. Corrupt file.n"); exit(EXIT_FAILURE); } for (uint32_t i = 0; i < TABLE_MAX_PAGES; i++) { pager->pages[i] = NULL; } return pager; } void* get_page(Pager* pager, uint32_t page_num) { if (page_num > TABLE_MAX_PAGES) { printf("Tried to fetch page number out of bounds. %d > %dn", page_num, TABLE_MAX_PAGES); exit(EXIT_FAILURE); } if (pager->pages[page_num] == NULL) { void* page = malloc(PAGE_SIZE); uint32_t num_pages = pager->file_length / PAGE_SIZE; if (pager->file_length % PAGE_SIZE) { num_pages += 1; } if (page_num <= num_pages) { lseek(pager->file_descriptor, page_num * PAGE_SIZE, SEEK_SET); ssize_t bytes_read = read(pager->file_descriptor, page, PAGE_SIZE); if (bytes_read == -1) { printf("Error reading file: %dn", errno); exit(EXIT_FAILURE); } } pager->pages[page_num] = page; if (page_num >= pager->num_pages) { pager->num_pages = page_num + 1; } } return pager->pages[page_num]; } void db_close(Table* table) { Pager* pager = table->pager; for (uint32_t i = 0; i < pager->num_pages; i++) { if (pager->pages[i] == NULL) { continue; } pager_flush(pager, i); free(pager->pages[i]); pager->pages[i] = NULL; } int result = close(pager->file_descriptor); if (result == -1) { printf("Error closing db file.n"); exit(EXIT_FAILURE); } for (uint32_t i = 0; i < TABLE_MAX_PAGES; i++) { void* page = pager->pages[i]; if (page) { free(page); pager->pages[i] = NULL; } } free(pager); free(table); } void pager_flush(Pager* pager, uint32_t page_num) { if (pager->pages[page_num] == NULL) { printf("Tried to flush null pagen"); exit(EXIT_FAILURE); } off_t offset = lseek(pager->file_descriptor, page_num * PAGE_SIZE, SEEK_SET); if (offset == -1) { printf("Error seeking: %dn", errno); exit(EXIT_FAILURE); } ssize_t bytes_written =write(pager->file_descriptor, pager->pages[page_num], PAGE_SIZE); if (bytes_written == -1) { printf("Error writing: %dn", errno); exit(EXIT_FAILURE); } } void serialize_row(Row* source, void* destination) { memcpy(destination + ID_OFFSET, &(source->id), ID_SIZE); memcpy(destination + USERNAME_OFFSET, &(source->username), USERNAME_SIZE); memcpy(destination + EMAIL_OFFSET, &(source->email), EMAIL_SIZE); } void deserialize_row(void* source, Row* destination) { memcpy(&(destination->id), source + ID_OFFSET, ID_SIZE); memcpy(&(destination->username), source + USERNAME_OFFSET, USERNAME_SIZE); memcpy(&(destination->email), source + EMAIL_OFFSET, EMAIL_SIZE); } PrepareResult prepare_insert(InputBuffer* input_buffer, Statement* statement) { statement->type = STATEMENT_INSERT; char* keyword = strtok(input_buffer->buffer, " "); char* id_string = strtok(NULL, " "); char* username = strtok(NULL, " "); char* email = strtok(NULL, " "); char* check=strtok(NULL," "); if (id_string == NULL || username == NULL || email == NULL||check!=NULL) { return PREPARE_SYNTAX_ERROR; } for(uint32_t i=0;i =10){ return PREPARE_ID_TOO_LONG; } if (id < 0) { return PREPARE_NEGATIVE_ID; } if (strlen(username) > COLUMN_USERNAME_SIZE) { return PREPARE_STRING_TOO_LONG; } if (strlen(email) > COLUMN_EMAIL_SIZE) { return PREPARE_STRING_TOO_LONG; } statement->row_to_insert.id = id; strcpy(statement->row_to_insert.username, username); strcpy(statement->row_to_insert.email, email); return PREPARE_SUCCESS; } PrepareResult prepare_select(InputBuffer* input_buffer,Statement* statement){ statement->type=STATEMENT_SELECT; char *keyword =strtok(input_buffer->buffer," "); char * args=strtok(NULL," "); char* check=strtok(NULL," "); if(check!=NULL){ return PREPARE_SYNTAX_ERROR; } if(args==NULL){ statement->row_to_select=ALL; return PREPARE_SUCCESS; } if(strcmp(args,"id")==0){ statement->row_to_select=ID; } else if(strcmp(args,"username")==0){ statement->row_to_select=USERNAME; } else if(strcmp(args,"email")==0){ statement->row_to_select=EMAIL; } else return PREPARE_SYNTAX_ERROR; return PREPARE_SUCCESS; } PrepareResult prepare_delete(InputBuffer* input_buffer,Statement* statement){ statement->type = STATEMENT_DELETE; char* keyword = strtok(input_buffer->buffer, " "); char* id_string = strtok(NULL, " "); char* check=strtok(NULL," "); if(check!=NULL){ return PREPARE_SYNTAX_ERROR; } if (id_string == NULL ) { return PREPARE_SYNTAX_ERROR; } int id = atoi(id_string); for(uint32_t i=0;i =10) return PREPARE_ID_TOO_LONG; statement->row_to_delete.id = id; return PREPARE_SUCCESS; } PrepareResult prepare_update(InputBuffer* input_buffer,Statement* statement){ statement->type = STATEMENT_UPDATE; char* keyword = strtok(input_buffer->buffer, " "); char* id_string_old = strtok(NULL, " "); char* username_old = strtok(NULL, " "); char* email_old = strtok(NULL, " "); char* id_string_new = strtok(NULL, " "); char* username_new = strtok(NULL, " "); char* email_new = strtok(NULL, " "); char* check=strtok(NULL," "); if(check!=NULL){ return PREPARE_SYNTAX_ERROR; } if (id_string_old == NULL || username_old == NULL || email_old == NULL) { return PREPARE_SYNTAX_ERROR; } if (id_string_new == NULL || username_new == NULL || email_new == NULL) { return PREPARE_SYNTAX_ERROR; } int id_old = atoi(id_string_old); int id_new = atoi(id_string_new); for(uint32_t i=0;i =10||strlen(id_string_new)>=10) return PREPARE_ID_TOO_LONG; if (id_new < 0) { return PREPARE_NEGATIVE_ID; } if (strlen(username_old) > COLUMN_USERNAME_SIZE) { return PREPARE_STRING_TOO_LONG; } if (strlen(email_old) > COLUMN_EMAIL_SIZE) { return PREPARE_STRING_TOO_LONG; } if (strlen(username_new) > COLUMN_USERNAME_SIZE) { return PREPARE_STRING_TOO_LONG; } if (strlen(email_new) > COLUMN_EMAIL_SIZE) { return PREPARE_STRING_TOO_LONG; } statement->row_to_update_old.id = id_old; strcpy(statement->row_to_update_old.username, username_old); strcpy(statement->row_to_update_old.email, email_old); statement->row_to_update_new.id = id_new; strcpy(statement->row_to_update_new.username, username_new); strcpy(statement->row_to_update_new.email, email_new); return PREPARE_SUCCESS; } PrepareResult prepare_statement(InputBuffer* input_buffer,Statement* statement) { if (strncmp(input_buffer->buffer, "insert",6) == 0) { return prepare_insert(input_buffer, statement); } else if(strncmp(input_buffer->buffer,"select",6)==0){ return prepare_select(input_buffer, statement); } else if(strncmp(input_buffer->buffer,"delete",6)==0){ return prepare_delete(input_buffer, statement); } else if(strncmp(input_buffer->buffer,"update",6)==0){ return prepare_update(input_buffer, statement); } else return PREPARE_UNRECOGNIZED_STATEMENT; } ExecuteResult execute_insert(Statement* statement, Table* table) { Row row; void* node = get_page(table->pager, table->root_page_num); uint32_t num_cells = (*leaf_node_num_cells(node)); if (num_cells >= LEAF_NODE_MAX_CELLS) { return EXECUTE_TABLE_FULL; } Row* row_to_insert = &(statement->row_to_insert); uint32_t key_to_insert = row_to_insert->id; Cursor* cursor = table_find(table, key_to_insert); if (cursor->cell_num < num_cells) { uint32_t key_at_index = *leaf_node_key(node, cursor->cell_num); if (key_at_index == key_to_insert) { return EXECUTE_DUPLICATE_KEY; } } leaf_node_insert(cursor, row_to_insert->id, row_to_insert); free(cursor); return EXECUTE_SUCCESS; } ExecuteResult execute_select(Statement* statement, Table* table) { Cursor* cursor = table_start(table); Row row; void* node = get_page(table->pager, table->root_page_num); uint32_t num_cells = *leaf_node_num_cells(node); for(uint32_t i=0;i cell_num =i; deserialize_row(leaf_node_value(node, cursor->cell_num),&row); if(statement->row_to_select==ID){ printf("(%d)n", row.id); } else if(statement->row_to_select==USERNAME){ printf("(%s)n", row.username); } else if(statement->row_to_select==EMAIL){ printf("(%s)n", row.email); } else if(statement->row_to_select==ALL){ printf("(%d, %s, %s)n", row.id, row.username, row.email); } } free(cursor); return EXECUTE_SUCCESS; } ExecuteResult execute_delete(Statement* statement, Table* table) { bool flag=false; void* node = get_page(table->pager, table->root_page_num); uint32_t num_cells = (*leaf_node_num_cells(node)); Row* row_to_delete = &(statement->row_to_delete); uint32_t key_to_delete= row_to_delete->id; Cursor* cursor = table_find(table, key_to_delete); if (cursor->cell_num < num_cells) { uint32_t key_at_index = *leaf_node_key(node, cursor->cell_num); if (key_at_index == key_to_delete) { flag=true; } } if(flag==false) return EXECUTE_NOT_FOUND; leaf_node_delete(cursor, row_to_delete->id, row_to_delete); free(cursor); return EXECUTE_SUCCESS; } ExecuteResult execute_update(Statement* statement, Table* table) { Row row; bool flag=false; Row* row_to_update = &(statement->row_to_update_old); void* node = get_page(table->pager, table->root_page_num); uint32_t key_to_update = row_to_update->id; Cursor* cursor = table_find(table, key_to_update); Row* row_to_update_old = &(statement->row_to_update_old); uint32_t num_cells = *leaf_node_num_cells(node); if(statement->row_to_update_new.id!=statement->row_to_update_old.id){ return EXECUTE_PRIMARY_CHANGE; } for(uint32_t i=0;i cell_num =i; deserialize_row(leaf_node_value(node, cursor->cell_num),&row); if(strcmp(statement->row_to_update_old.username,row.username )==0&&strcmp(statement->row_to_update_old.email,row.email)==0) { flag=true; strcpy(row.username,statement->row_to_update_new.username); strcpy(row.email,statement->row_to_update_new.email); serialize_row(&row, leaf_node_value(node, cursor->cell_num)); return EXECUTE_SUCCESS; } serialize_row(&row, leaf_node_value(node, cursor->cell_num)); cursor_advance(cursor); } free(cursor); return EXECUTE_NOT_FOUND; } ExecuteResult execute_statement(Statement* statement, Table* table) { switch (statement->type) { case (STATEMENT_INSERT): return execute_insert(statement, table); case (STATEMENT_SELECT): return execute_select(statement, table); case (STATEMENT_DELETE): return execute_delete(statement, table); case (STATEMENT_UPDATE): return execute_update(statement, table); } } void print_prompt() { printf("sqlite> "); } void read_input(InputBuffer* input_buffer){ ssize_t bytes_read=getline(&(input_buffer->buffer), &(input_buffer->buffer_length), stdin); if(bytes_read<=0){ printf("Error: Wrong reading input.n"); exit(EXIT_FAILURE); } input_buffer->input_length=bytes_read-1; input_buffer->buffer[bytes_read -1 ]=0; } void close_input_buffer(InputBuffer* input_buffer){ free(input_buffer->buffer); free(input_buffer); } Cursor* table_start(Table* table) { Cursor* cursor = malloc(sizeof(Cursor)); cursor->table = table; cursor->page_num = table->root_page_num; cursor->cell_num = 0; void* root_node = get_page(table->pager, table->root_page_num); uint32_t num_cells = *leaf_node_num_cells(root_node); cursor->end_of_table = (num_cells == 0); return cursor; } void* cursor_value(Cursor* cursor) { uint32_t page_num = cursor->page_num; void* page = get_page(cursor->table->pager, page_num); return leaf_node_value(page, cursor->cell_num); } void cursor_advance(Cursor* cursor) { uint32_t page_num = cursor->page_num; void* node = get_page(cursor->table->pager, page_num); cursor->cell_num += 1; if (cursor->cell_num >= (*leaf_node_num_cells(node))) { cursor->end_of_table = true; } } uint32_t* leaf_node_num_cells(void* node) { return node + LEAF_NODE_NUM_CELLS_OFFSET; } void* leaf_node_cell(void* node, uint32_t cell_num) { return node + LEAF_NODE_HEADER_SIZE + cell_num * LEAF_NODE_CELL_SIZE; } uint32_t* leaf_node_key(void* node, uint32_t cell_num) { return leaf_node_cell(node, cell_num); } void* leaf_node_value(void* node, uint32_t cell_num) { return leaf_node_cell(node, cell_num) + LEAF_NODE_KEY_SIZE; } void initialize_leaf_node(void* node) { set_node_type(node, NODE_LEAF); *leaf_node_num_cells(node) = 0; } void leaf_node_insert(Cursor* cursor, uint32_t key, Row* value) { void* node = get_page(cursor->table->pager, cursor->page_num); uint32_t num_cells = *leaf_node_num_cells(node); if (num_cells >= LEAF_NODE_MAX_CELLS) { printf("Need to implement splitting a leaf node.n"); exit(EXIT_FAILURE); } if (cursor->cell_num < num_cells) { for (uint32_t i = num_cells; i > cursor->cell_num; i--) { memcpy(leaf_node_cell(node, i), leaf_node_cell(node, i - 1), LEAF_NODE_CELL_SIZE); } } *(leaf_node_num_cells(node)) += 1; *(leaf_node_key(node, cursor->cell_num)) = key; serialize_row(value, leaf_node_value(node, cursor->cell_num)); } void leaf_node_delete(Cursor* cursor, uint32_t key, Row* value) { void* node = get_page(cursor->table->pager, cursor->page_num); uint32_t num_cells = *leaf_node_num_cells(node); if (num_cells <= LEAF_NODE_LESS_CELLS) { printf("Need to implement inserting a leaf node.n"); exit(EXIT_FAILURE); } if (cursor->cell_num cell_num; i <=num_cells;i++) { if(*(leaf_node_key(node, i)) > key){ memcpy(leaf_node_cell(node, i-1), leaf_node_cell(node, i),LEAF_NODE_CELL_SIZE); } } } *(leaf_node_num_cells(node)) -= 1; cursor->cell_num-=1; } void print_constants() { printf("ROW_SIZE: %dn", ROW_SIZE); printf("COMMON_NODE_HEADER_SIZE: %dn", COMMON_NODE_HEADER_SIZE); printf("LEAF_NODE_HEADER_SIZE: %dn", LEAF_NODE_HEADER_SIZE); printf("LEAF_NODE_CELL_SIZE: %dn", LEAF_NODE_CELL_SIZE); printf("LEAF_NODE_SPACE_FOR_CELLS: %dn", LEAF_NODE_SPACE_FOR_CELLS); printf("LEAF_NODE_MAX_CELLS: %dn", LEAF_NODE_MAX_CELLS); } void print_leaf_node(void* node) { uint32_t num_cells = *leaf_node_num_cells(node); printf("leaf (size %d)n", num_cells); for (uint32_t i = 0; i < num_cells; i++) { uint32_t key = *leaf_node_key(node, i); printf(" - %d : %dn", i, key); } } Cursor* table_find(Table* table, uint32_t key) { uint32_t root_page_num = table->root_page_num; void* root_node = get_page(table->pager, root_page_num); return leaf_node_find(table, root_page_num, key); if (get_node_type(root_node) == NODE_LEAF) { return leaf_node_find(table, root_page_num, key); } else { printf("Need to implement searching an internal noden"); exit(EXIT_FAILURE); } } Cursor* leaf_node_find(Table* table, uint32_t page_num, uint32_t key) { void* node = get_page(table->pager, page_num); uint32_t num_cells = *leaf_node_num_cells(node); Cursor* cursor = malloc(sizeof(Cursor)); cursor->table = table; cursor->page_num = page_num; uint32_t min_index = 0; uint32_t one_past_max_index = num_cells; while (one_past_max_index != min_index) { uint32_t index = (min_index + one_past_max_index) / 2; uint32_t key_at_index = *leaf_node_key(node, index); if (key == key_at_index) { cursor->cell_num = index; return cursor; } if (key < key_at_index) { one_past_max_index = index; } else { min_index = index + 1; } } cursor->cell_num = min_index; return cursor; } NodeType get_node_type(void* node) { uint8_t value = *((uint8_t*)(node + NODE_TYPE_OFFSET)); return (NodeType)value; } void set_node_type(void* node, NodeType type) { uint8_t value = type; *((uint8_t*)(node + NODE_TYPE_OFFSET)) = value; } int main(int argc, char* argv[]) { if (argc != 2) { printf("Must supply a database filename.n"); exit(EXIT_FAILURE); } char* filename = argv[1]; Table* table = db_open(filename); InputBuffer* input_buffer = new_input_buffer(); while (true) { print_prompt(); read_input(input_buffer); if (input_buffer->buffer[0] == '.') { switch (do_meta_command(input_buffer,table)) { case (META_COMMAND_SUCCESS): continue; case (META_COMMAND_UNRECOGNIZED_COMMAND): printf("Error: Unrecognized command '%s'.n", input_buffer->buffer); continue; } } Statement statement; switch (prepare_statement(input_buffer, &statement)) { case (PREPARE_SUCCESS): break; case (PREPARE_STRING_TOO_LONG): printf("Error: String is too long.n"); continue; case (PREPARE_NEGATIVE_ID): printf("Error: ID must be positive.n"); continue; case (PREPARE_ID_TOO_LONG): printf("Error: Id is too long.n"); continue; case (PREPARE_SYNTAX_ERROR): printf("Error: Syntax error.n"); continue; case (PREPARE_UNRECOGNIZED_STATEMENT): printf("Error: Unrecognized keyword at start of '%s'.n",input_buffer->buffer); continue; case (PREPARE_ILLEGAL_ID): printf("Error: ILLEGAL ID.n"); continue; } switch (execute_statement(&statement, table)) { case (EXECUTE_SUCCESS): printf("Executed.n"); break; case (EXECUTE_PRIMARY_CHANGE): printf("Error: Can't change primary key.n"); break; case (EXECUTE_DUPLICATE_KEY): printf("Error: Duplicate key.n"); break; case (EXECUTE_NOT_FOUND): printf("Error: Not found.n"); break; case (EXECUTE_TABLE_FULL): printf("Error: Table full.n"); break; } } }



