从0到1实现一个简单的数据库(三)-内存中的，仅有一个数据库表的数据库

码码呀
184 阅读5分钟

我们一开始就会对数据库设置很多的限制。现在，他将会：

  • 支持两个操作:插入一行数据和打印所有的行数据。
  • 保存在内存中(不持久化到磁盘)。
  • 支持一个简单的，硬编码的表。

我们的硬编码表存放用户并如下表展示的:

columntype
idinteger
usernamevarchar(30)
emailvarchar(255)
这是一个简单的架构，但它使我们能够支持多种数据类型和多种数据类型的大小。

insert语句就像下面的展示的:

insert  1 cstack foo@bar.com

这就意味着我们需要修改我们的prepare_statement函数来解析参数。

 if (strncmp(input_buffer->buffer, "insert", 6) == 0) {
     statement->type = STATEMENT_INSERT;
    int args_assigned = sscanf(
        input_buffer->buffer, "insert %d %s %s", &(statement->row_to_insert.id),
        statement->row_to_insert.username, statement->row_to_insert.email);
    if (args_assigned < 3) {
      return PREPARE_SYNTAX_ERROR;
    }
     return PREPARE_SUCCESS;
   }
   if (strcmp(input_buffer->buffer, "select") == 0) {

我们存储这些解析的参数到一个新的Row数据结构在语句对象中:

#define COLUMN_USERNAME_SIZE 32
#define COLUMN_EMAIL_SIZE 255
typedef struct {
  uint32_t id;
  char username[COLUMN_USERNAME_SIZE];
  char email[COLUMN_EMAIL_SIZE];
} Row;

 typedef struct {
  StatementType type;
  Row row_to_insert; 
 } Statement;

现在我们需要复制这个数据到同样的数据结构来表示一个表。SQLite用B-tree来查询，插入和删除。我们会做和SQLITE 一样的操作，就像B-tree,他将把row分组到pages,但是，它不会将这些页面作为树来排列，而是将它们作为一个数组来排列。

这里是我的计划：

  • 在成为也得内存中存储行。
  • 每个页面存储尽可能多的行
  • 每一页的行被序列化成一个紧凑的表示
  • pages仅在需要的时候分欧赔内存给它
  • 保持指向页面的指针的固定大小数组

首先，我们将定义行的紧凑表示：

+#define size_of_attribute(Struct, Attribute) sizeof(((Struct*)0)->Attribute)
+
+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 ID_OFFSET = 0;
+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;

这就意味着序列化的布局如下所示： | column | size (bytes) | offset| | ---- | ---- | ----| ----| | id | 4 | 0| | username | 32 | 4 | | email | 255 | 36 | | total | 291 | 36 |

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);
}

接下来是一个“Table”结构，它指向行的页面并跟踪行的数量

const uint32_t PAGE_SIZE = 4096;
#define TABLE_MAX_PAGES 100
const uint32_t ROWS_PER_PAGE = PAGE_SIZE / ROW_SIZE;
const uint32_t TABLE_MAX_ROWS = ROWS_PER_PAGE * TABLE_MAX_PAGES;

typedef struct {
  uint32_t num_rows;
  void* pages[TABLE_MAX_PAGES];
} Table;

我将页面大小设为4KB，因为它与大多数计算机体系结构的虚拟内存系统中使用的页面大小相同。这意味着我们在数据库中对应的一页在操作系统中也有一页与之对应。操作系统将页面作为一个整体单元进出内存，而不是将它们分开。在我们分配内存的时候，我将限制任意设置了100页。当我们转换成一个树机构时，我们数据库的最大大小只会受到文件最大大小的限制，尽管我们仍会限制一次在内存中保留多少页。

行不应该超出页面的边界，由于页在内存中可能不会相邻存在，所以这种假设使得读/写行更容易。说到这一点，下面是我们如何确定在内存中对特定行的读/写位置：

void* row_slot(Table* table, uint32_t row_num) {
  uint32_t page_num = row_num / ROWS_PER_PAGE;
  void* page = table->pages[page_num];
  if (page == NULL) {
    page = table->pages[page_num] = malloc(PAGE_SIZE);
  }
  uint32_t row_offset = row_num % ROWS_PER_PAGE;
  uint32_t byte_offset = row_offset * ROW_SIZE;
  return page + byte_offset;
}

现在我们就用execute_statement函数从我们的表结构中读/写数据。

ExecuteResult execute_insert(Statement* statement, Table* table) {
  if (table->num_rows >= TABLE_MAX_ROWS) {
    return EXECUTE_TABLE_FULL;
  }

  Row* row_to_insert = &(statement->row_to_insert);

  serialize_row(row_to_insert, row_slot(table, table->num_rows));
  table->num_rows += 1;

  return EXECUTE_SUCCESS;
}

ExecuteResult execute_select(Statement* statement, Table* table) {
  Row row;
  for (uint32_t i = 0; i < table->num_rows; i++) {
    deserialize_row(row_slot(table, i), &row);
    print_row(&row);
  }
  return EXECUTE_SUCCESS;
}

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);
   }
 }

最终，我们将会初始化这个表，创建一个各自释放内存的函数，并处理一些错误。

 Table* new_table() {
  Table* table = malloc(sizeof(Table));
  table->num_rows = 0;
  for (uint32_t i = 0; i < TABLE_MAX_PAGES; i++) {
     table->pages[i] = NULL;
  }
  return table;
}

void free_table(Table* table) {
    for (int i = 0; table->pages[i]; i++) {
	free(table->pages[i]);
    }
    free(table);
}

 int main(int argc, char* argv[]) {
  Table* table = new_table();
   InputBuffer* input_buffer = new_input_buffer();
   while (true) {
     print_prompt();
@@ -105,13 +203,22 @@ int main(int argc, char* argv[]) {
     switch (prepare_statement(input_buffer, &statement)) {
       case (PREPARE_SUCCESS):
         break;
      case (PREPARE_SYNTAX_ERROR):
        printf("Syntax error. Could not parse statement.\n");
        continue;
       case (PREPARE_UNRECOGNIZED_STATEMENT):
         printf("Unrecognized keyword at start of '%s'.\n",
                input_buffer->buffer);
         continue;
     }

    switch (execute_statement(&statement, table)) {
      case (EXECUTE_SUCCESS):
        printf("Executed.\n");
        break;
      case (EXECUTE_TABLE_FULL):
        printf("Error: Table full.\n");
        break;
    }
   }
 }

这些改变我们实际上能保存到我们的数据库里面了。

~ ./db
db > insert 1 cstack foo@bar.com
Executed.
db > insert 2 bob bob@example.com
Executed.
db > select
(1, cstack, foo@bar.com)
(2, bob, bob@example.com)
Executed.
db > insert foo bar 1
Syntax error. Could not parse statement.
db > .exit
~

现在我们将会有很多的时间来写一些测试，对于下面两个理由：

  • 我们计划大幅改变存储表的数据结构，测试将捕捉回归。
  • 有几个边缘案例我们还没有手动测试（例如填写表格）

我们将会在下一章讨论这些问题，下面就是本章节的代码全部展示：

 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <stdint.h>

 typedef struct {
   char* buffer;
 typedef struct {
 } InputBuffer;

typedef enum { EXECUTE_SUCCESS, EXECUTE_TABLE_FULL } ExecuteResult;
typedef enum {
  META_COMMAND_SUCCESS,
  META_COMMAND_UNRECOGNIZED_COMMAND
} MetaCommandResult;

typedef enum {
  PREPARE_SUCCESS,
  PREPARE_SYNTAX_ERROR,
  PREPARE_UNRECOGNIZED_STATEMENT
 } PrepareResult;

typedef enum { STATEMENT_INSERT, STATEMENT_SELECT } StatementType;

#define COLUMN_USERNAME_SIZE 32
#define COLUMN_EMAIL_SIZE 255
typedef struct {
  uint32_t id;
  char username[COLUMN_USERNAME_SIZE];
  char email[COLUMN_EMAIL_SIZE];
} Row;

typedef struct {
  StatementType type;
  Row row_to_insert;
} Statement;
#define size_of_attribute(Struct, Attribute) sizeof(((Struct*)0)->Attribute)

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 ID_OFFSET = 0;
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 PAGE_SIZE = 4096;
#define TABLE_MAX_PAGES 100
const uint32_t ROWS_PER_PAGE = PAGE_SIZE / ROW_SIZE;
const uint32_t TABLE_MAX_ROWS = ROWS_PER_PAGE * TABLE_MAX_PAGES;

typedef struct {
  uint32_t num_rows;
  void* pages[TABLE_MAX_PAGES];
} Table;
void print_row(Row* row) {
  printf("(%d, %s, %s)\n", row->id, row->username, row->email);
}

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);
}

void* row_slot(Table* table, uint32_t row_num) {
  uint32_t page_num = row_num / ROWS_PER_PAGE;
  void *page = table->pages[page_num];
  if (page == NULL) {
     page = table->pages[page_num] = malloc(PAGE_SIZE);
  }
  uint32_t row_offset = row_num % ROWS_PER_PAGE;
  uint32_t byte_offset = row_offset * ROW_SIZE;
  return page + byte_offset;
}

Table* new_table() {
  Table* table = malloc(sizeof(Table));
  table->num_rows = 0;
  for (uint32_t i = 0; i < TABLE_MAX_PAGES; i++) {
     table->pages[i] = NULL;
  }
  return table;
}

void free_table(Table* table) {
  for (int i = 0; table->pages[i]; i++) {
     free(table->pages[i]);
  }
  free(table);
}

 InputBuffer* new_input_buffer() {
   InputBuffer* input_buffer = malloc(sizeof(InputBuffer));
   input_buffer->buffer = NULL;
   void close_input_buffer(InputBuffer* input_buffer) {
     free(input_buffer);
 }

MetaCommandResult do_meta_command(InputBuffer* input_buffer, Table *table) {
  if (strcmp(input_buffer->buffer, ".exit") == 0) {
     close_input_buffer(input_buffer);
    free_table(table);
    exit(EXIT_SUCCESS);
 } else {
    return META_COMMAND_UNRECOGNIZED_COMMAND;
  }
}

PrepareResult prepare_statement(InputBuffer* input_buffer,
                                Statement* statement) {
  if (strncmp(input_buffer->buffer, "insert", 6) == 0) {
    statement->type = STATEMENT_INSERT;
    int args_assigned = sscanf(
	input_buffer->buffer, "insert %d %s %s", &(statement->row_to_insert.id),
	statement->row_to_insert.username, statement->row_to_insert.email
	);
    if (args_assigned < 3) {
	return PREPARE_SYNTAX_ERROR;
    }
    return PREPARE_SUCCESS;
  }
  if (strcmp(input_buffer->buffer, "select") == 0) {
    statement->type = STATEMENT_SELECT;
    return PREPARE_SUCCESS;
  }

  return PREPARE_UNRECOGNIZED_STATEMENT;
}

ExecuteResult execute_insert(Statement* statement, Table* table) {
  if (table->num_rows >= TABLE_MAX_ROWS) {
     return EXECUTE_TABLE_FULL;
  }

  Row* row_to_insert = &(statement->row_to_insert);

  serialize_row(row_to_insert, row_slot(table, table->num_rows));
  table->num_rows += 1;

  return EXECUTE_SUCCESS;
}

ExecuteResult execute_select(Statement* statement, Table* table) {
  Row row;
  for (uint32_t i = 0; i < table->num_rows; i++) {
     deserialize_row(row_slot(table, i), &row);
     print_row(&row);
  }
  return EXECUTE_SUCCESS;
}

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);
  }
}

 int main(int argc, char* argv[]) {
  Table* table = new_table();
   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("Unrecognized command '%s'\n", input_buffer->buffer);
          continue;
      }
    }

    Statement statement;
    switch (prepare_statement(input_buffer, &statement)) {
      case (PREPARE_SUCCESS):
        break;
      case (PREPARE_SYNTAX_ERROR):
	printf("Syntax error. Could not parse statement.\n");
	continue;
      case (PREPARE_UNRECOGNIZED_STATEMENT):
        printf("Unrecognized keyword at start of '%s'.\n",
               input_buffer->buffer);
        continue;
    }

    switch (execute_statement(&statement, table)) {
	case (EXECUTE_SUCCESS):
	    printf("Executed.\n");
	    break;
	case (EXECUTE_TABLE_FULL):
	    printf("Error: Table full.\n");
	    break;
     }
   }
 }

在这里插入图片描述 亲！！扫码或者搜索关注我的公众号，会有更多精彩内容等你哦

avatar
文章
阅读
粉丝
相关推荐
分库分表已成为过去式，使用分布式数据库才是未来
22k阅读
 · 
125点赞
浩鲸科技：为什么要用雪花ID替代数据库自增ID？
35k阅读
 · 
247点赞
降本增笑，阿里云的数据库管控又崩了
38k阅读
 · 
125点赞
为什么堂堂微信数据库表名、字段名起的如此随意？
54k阅读
 · 
401点赞
SwiftData-苹果最先进的数据库
11k阅读
 · 
38点赞
微信移动端数据库组件 WCDB
14k阅读
 · 
56点赞
万万没想到，go的数据库操作，也能像php一样溜了
25k阅读
 · 
109点赞
Go 简单实现多租户数据库隔离
4.0k阅读
 · 
52点赞
全解MySQL终章：这份爆肝30W字的数据库宝典赠与有缘的你！
38k阅读
 · 
434点赞
MYSQL数据库 Schema 设计与优化
9.5k阅读
 · 
27点赞

友情链接：