构建一个简单的数据库系列（三）驻在内存append only的单表数据库

最新推荐文章于 2021-03-08 00:06:14 发布

DamZ

最新推荐文章于 2021-03-08 00:06:14 发布

阅读量325

点赞数

分类专栏：数据库内核

本文链接：https://blog.csdn.net/zhq651/article/details/88624488

版权

数据库内核专栏收录该内容

17 篇文章 1 订阅

订阅专栏

英文链接：https://cstack.github.io/db_tutorial/parts/part3.html

假设表定义如下：

column	type
id	integer
username	varchar(32)
email	varchar(255)

insert语句定义为

insert column1, column2, column3 

例如：insert 1 cstack foo@bar.com

预期执行结果

db > insert 1 cstack foo@bar.com
Executed.
db > insert 2 cstack foo@bar.com
Executed.
db > insert 3 cstack foo@bar.com
Executed.
db > select
(1, cstack, foo@bar.com)
(2, cstack, foo@bar.com)
(3, cstack, foo@bar.com)
Executed.

新增逻辑：

1、解析insert到statement中
if (strncasecmp(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;
}

2、执行insert

/* 执行insert*/
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;
}

3、执行查询

/* 执行查询*/
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;
}

4、核心逻辑

/* 序列化： 将row写到内存中 */
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);
}

/* 反序列化 */
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);
}

/* 计算插入位置， 行插入槽*/
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) {
        // Allocate memory only when we try to access page
        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;
}

最终代码

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

/* 定义 元数据操作结果*/
enum MetaCommandResult_t {
    META_COMMAND_SUCCESS,
    META_COMMAND_UNRECOGNIZED_COMMAND
};
typedef enum MetaCommandResult_t MetaCommandResult;

/* 执行结果*/
enum ExecuteResult_t { EXECUTE_SUCCESS, EXECUTE_TABLE_FULL };
typedef enum ExecuteResult_t ExecuteResult;

/* sql解析结果 */
enum PrepareResult_t {
    PREPARE_SUCCESS,
    PREPARE_SYNTAX_ERROR,
    PREPARE_UNRECOGNIZED_STATEMENT
};
typedef enum PrepareResult_t PrepareResult;

/* 行定义，对应具体的业务 */
const uint32_t COLUMN_USERNAME_SIZE = 32;
const uint32_t COLUMN_EMAIL_SIZE = 255;
struct Row_t {
      uint32_t id;
      char username[COLUMN_USERNAME_SIZE];
      char email[COLUMN_EMAIL_SIZE];
};
typedef struct Row_t Row;


/* sql type*/
enum StatementType_t{
    STATEMENT_INSERT,
    STATEMENT_SELECT
};
typedef enum StatementType_t StatementType;

struct Statement_t {
    StatementType type;
    Row row_to_insert;  /* only used by insert statement */

};
typedef struct Statement_t 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;

/* 大部分系统结构的页大小都是4K ，所以这里也定义为4K 这样就不用做转换 */
const uint32_t PAGE_SIZE = 4096;
const uint32_t 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;

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

void print_row(Row* row) {
    printf("(%d, %s, %s)\n", row->id, row->username, row->email);
}

/* 序列化： 将row写到内存中 */
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);
}

/* 反序列化 */
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);
}

/* 计算插入位置， 行插入槽*/
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) {
        // Allocate memory only when we try to access page
        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;

    return table;
}

/* 接收输入*/
struct InputBuffer_t {
    char* buffer;
    size_t buffer_length;
    ssize_t input_length;
};
typedef struct InputBuffer_t InputBuffer;

/* 初始化buffer */
InputBuffer* new_input_buffer()
{
    InputBuffer* input_buffer = malloc(sizeof(InputBuffer));
    input_buffer->buffer = NULL;
    input_buffer->buffer_length = 0;
    input_buffer->input_length = 0;

    return input_buffer;
}

void print_prompt() { printf("db > "); }

/* 按行从标准输入读取 */
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 reading input\n");
        exit(EXIT_FAILURE);
    }

    // Ignore trailing newline
    input_buffer->input_length = bytes_read - 1;
    input_buffer->buffer[bytes_read - 1] = 0;
}

/* 元数据命令处理 */
MetaCommandResult do_meta_command(InputBuffer* input_buffer)
{
    if (strcmp(input_buffer->buffer, ".exit") == 0) {
        exit(EXIT_SUCCESS);
    } else {
        return META_COMMAND_UNRECOGNIZED_COMMAND;
    }
}

/* sql解析 */
PrepareResult prepare_statement(InputBuffer* input_buffer,Statement* statement)
{
    if (strncasecmp(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 (strncasecmp(input_buffer->buffer, "select", 6) == 0) {
        statement->type = STATEMENT_SELECT;
        return PREPARE_SUCCESS;
    }

    return PREPARE_UNRECOGNIZED_STATEMENT;
}

/* 执行insert*/
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;
}

/* 执行查询*/
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;
}
/* sql执行*/
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);
    }
}


/* 主函数*/
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))
            {
                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;
        }
    }
}