这部分内容教你写一个基于内存的、只能添加的、只有一个表的数据库，原文章地址：https://cstack.github.io/db_tutorial/parts/part3.html
我们将从小的地方着手，对数据库添加一些限制，目前它会:
- 支持两种操作:插入一行和打印所有行
- 仅驻留在内存中（无磁盘持久性）
- 支持单个硬编码表
我们的硬编码表将用于像这样存储用户
column | type |
id | integer |
username | varchar(32) |
email | varchar(255) |
这是一个简单的架构，但它能支持多种数据类型和多种大小的文本数据类型。
insert 语句现在将看起来如下:
insert 1 cstack foo@bar.com这意味着我们需要更新 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) {我们将使用一个新的数据结构 Row 来存储语句中的参数:
+#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; // only used by insert statement
} Statement;现在我们需要把数据复制到某些表示表的数据结构中。SQLite使用了B树进行快速查找，插入和删除。我们将从一些更简单的东西开始。像B树一样，它会把行组合为页，但不把这些页排列为树，而是把它们排列为数组。
这是我接下来的计划:
- 将行存储在称为页的内存块中
- 每一页尽可能多地存储行
- 行被序列化为每页的紧凑表示形式
- 页只在有需求的时候被分配
- 维护一组固定长度的指向页的指针
首先，我们来定义一行的紧凑表示:
+#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;这意味着每行序列化后的布局会像这样:
column | size (bytes) | offset |
id | 4 | 0 |
username | 32 | 4 |
email | 255 | 36 |
total | 291 |
同时，我们还需要代码来转化两种表示:
+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，创建一个 Table 结构指向行页并跟踪行数:
+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，因为大多数计算机体系结构的虚拟内存系统使用的页面大小也是4kb.这意味着我们数据库的一页刚好对应操作系统使用的一页。这样，操作系统将会把整页作为一个单元，整体移入或移出内存，而不把页拆解开来。
我还强制设置了一个在内存中最大分配100页的限制。当我们选择树结构时，数据库的最大大小只受到文件最大大小的限制（尽管我们仍然会限制同时在内存保留的页数）
行不应该跨越页的界限。由于页很可能不知道彼此相邻存在，在这个假设下我们的行读写更简便了。
说到这里，以下是我们如何确定特定行在内存中读写位置的代码:
+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) {
+ // 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;
+}现在我们可以使用 execute_statement 从表结构中进行读写
-void execute_statement(Statement* 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):
- printf("This is where we would do an insert.\n");
- break;
+ return execute_insert(statement, table);
case (STATEMENT_SELECT):
- printf("This is where we would do a select.\n");
- break;
+ return execute_select(statement, table);
}
}最后，我们需要初始化表，创建相应的内存表示方法，并能处理更多错误情况
+ Table* new_table() {
+ 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;
}
- execute_statement(&statement);
- printf("Executed.\n");
+ switch (execute_statement(&statement, table)) {
+ case (EXECUTE_SUCCESS):
+ printf("Executed.\n");
+ break;
+ case (EXECUTE_TABLE_FULL):
+ printf("Error: Table full.\n");
+ break;
+ }
}
}有了这些修改后，我们已经可以在数据库中保存数据了！
~ ./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
~现在是测试的好时机，原因如下：
- 我们计划大幅度修改用来存储表的数据结构，测试将发现回归
- 有几个边缘情况我们没有手动测试（例如，填满整个表）
我们将在下部分中解决这些问题，现在展示这部分代码的完整区别:
@@ -2,6 +2,7 @@
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
+#include <stdint.h>
typedef struct {
char* buffer;
@@ -10,6 +11,105 @@ 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; //only used by insert statement
+} 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) {
+ // 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 = (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 = (InputBuffer*)malloc(sizeof(InputBuffer));
input_buffer->buffer = NULL;
@@ -40,17 +140,105 @@ 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 (strcmp(input_buffer->buffer, ".exit") == 0) {
- close_input_buffer(input_buffer);
- exit(EXIT_SUCCESS);
- } else {
- printf("Unrecognized command '%s'.\n", input_buffer->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;
}
}
}
本文章为转载内容，我们尊重原作者对文章享有的著作权。如有内容错误或侵权问题，欢迎原作者联系我们进行内容更正或删除文章。
