源碼分析之tinyhttpd-0.1

1. 簡介：

tinyhttpd是使用c語言開發的超輕量級http服務器，通過代碼流程可以了解http服務器的基本處理流程，

並且涉及了網絡套接字，線程，父子進程，管道等等知識點；

 

項目地址：http://sourceforge.net/projects/tinyhttpd/

 

2. 流程介紹：

(1) 服務器啟動，等待客戶端請求到來；

(2) 客戶端請求到來，創建新線程處理該請求；

(3) 讀取httpHeader中的method，截取url，其中GET方法需要記錄url問號之后的參數串;

(4) 根據url構造完整路徑，如果是/結尾，則指定為該目錄下的index.html;

(5) 獲取文件信息，如果找不到文件，返回404，找到文件則判斷文件權限；

(6) 如果是GET請求並且沒有參數，或者文件不可執行，則直接將文件內容構造http信息返回給客戶端；

(7) 如果是GET帶參數，POST，文件可執行，則執行CGI；

(8) GET請求略過httpHeader，POST方法需要記錄httpHeader中的Content-Length:xx；

(9) 創建管道用於父子進程通信，fork產生子進程；

(10) 子進程設置環境變量，將標准輸入和輸出與管道相連，並且通過exec執行CGI；

(11) 如果是POST，父進程將讀到post內容發送給子進程，並且接收子進程的輸出，輸出給客戶端；

 

3. 管道說明：

 

4. 代碼注釋：

/* J. David's webserver */
/* This is a simple webserver.
 * Created November 1999 by J. David Blackstone.
 * CSE 4344 (Network concepts), Prof. Zeigler
 * University of Texas at Arlington
 */
/* This program compiles for Sparc Solaris 2.6.
 * To compile for Linux:
 *  1) Comment out the #include <pthread.h> line.
 *  2) Comment out the line that defines the variable newthread.
 *  3) Comment out the two lines that run pthread_create().
 *  4) Uncomment the line that runs accept_request().
 *  5) Remove -lsocket from the Makefile.
 */
#include <stdio.h>
#include <sys/socket.h>
#include <sys/types.h>
#include <netinet/in.h>
#include <arpa/inet.h>
#include <unistd.h>
#include <ctype.h>
#include <strings.h>
#include <string.h>
#include <sys/stat.h>
#include <pthread.h>
#include <sys/wait.h>
#include <stdlib.h>

#define ISspace(x) isspace((int)(x))

#define SERVER_STRING "Server: jdbhttpd/0.1.0\r\n"

void accept_request(int);
void bad_request(int);
void cat(int, FILE *);
void cannot_execute(int);
void error_die(const char *);
void execute_cgi(int, const char *, const char *, const char *);
int get_line(int, char *, int);
void headers(int, const char *);
void not_found(int);
void serve_file(int, const char *);
int startup(u_short *);
void unimplemented(int);

/**********************************************************************/
/* A request has caused a call to accept() on the server port to
 * return.  Process the request appropriately.
 * Parameters: the socket connected to the client */
/**********************************************************************/
void accept_request(int client)
{
    char buf[1024];
    int numchars;
    char method[255];
    char url[255];
    char path[512];
    size_t i, j;
    struct stat st;
    int cgi = 0;      /* becomes true if server decides this is a CGI
               * program */
    char *query_string = NULL;

    //讀取第一行數據
    numchars = get_line(client, buf, sizeof(buf));
    i = 0; j = 0;
    //讀取http的頭部method字段，讀到空白為止
    while (!ISspace(buf[j]) && (i < sizeof(method) - 1))
    {
        method[i] = buf[j];
        i++; j++;
    }
    method[i] = '\0';

    //只支持GET和POST請求，其他請求方式返回未實現
    if (strcasecmp(method, "GET") && strcasecmp(method, "POST"))
    {
        unimplemented(client);
        return;
    }
    //如果是POST請求，設置cgi標志為1
    if (strcasecmp(method, "POST") == 0)
        cgi = 1;

    i = 0;
    //跳過空白字符
    while (ISspace(buf[j]) && (j < sizeof(buf)))
        j++;
    //讀取url字串
    while (!ISspace(buf[j]) && (i < sizeof(url) - 1) && (j < sizeof(buf)))
    {
        url[i] = buf[j];
        i++; j++;
    }
    url[i] = '\0';
    //如果是GET請求，需要從url中解析參數
    if (strcasecmp(method, "GET") == 0)
    {
        query_string = url;
        //找到?位置
        while ((*query_string != '?') && (*query_string != '\0'))
            query_string++;
        //當前字符為?字符
        if (*query_string == '?')
        {
            cgi = 1; //標記cgi字段
            *query_string = '\0'; //將?替換成\0
            query_string++; //query_string指向get參數
        }
    }
    //連接url資源路徑
    sprintf(path, "htdocs%s", url);
    //如果訪問的是/結尾的目錄，那么指定為目錄下的index.html
    if (path[strlen(path) - 1] == '/')
        strcat(path, "index.html");
    //獲取文件信息失敗
    if (stat(path, &st) == -1) {
        //將header中的信息都丟棄
        while ((numchars > 0) && strcmp("\n", buf))  /* read & discard headers */
            numchars = get_line(client, buf, sizeof(buf));
        //返回404
        not_found(client);
    }
    else
    {
        //如果訪問的是目錄，那么指定為目錄下的index.html
        if ((st.st_mode & S_IFMT) == S_IFDIR)
            strcat(path, "/index.html");
        //如果具有可執行權限，標記cgi
        if ((st.st_mode & S_IXUSR) ||
                (st.st_mode & S_IXGRP) ||
                (st.st_mode & S_IXOTH)    )
            cgi = 1;
        //不需要cgi參與的文件直接進行服務
        if (!cgi)
            serve_file(client, path);
        //否則執行cgi
        else
            execute_cgi(client, path, method, query_string);
    }

    close(client);
}

/**********************************************************************/
/* Inform the client that a request it has made has a problem.
 * Parameters: client socket */
/**********************************************************************/
void bad_request(int client)
{
    char buf[1024];
    //發送BAD REQUEST提示信息到客戶端
    sprintf(buf, "HTTP/1.0 400 BAD REQUEST\r\n");
    send(client, buf, sizeof(buf), 0);
    sprintf(buf, "Content-type: text/html\r\n");
    send(client, buf, sizeof(buf), 0);
    sprintf(buf, "\r\n");
    send(client, buf, sizeof(buf), 0);
    sprintf(buf, "<P>Your browser sent a bad request, ");
    send(client, buf, sizeof(buf), 0);
    sprintf(buf, "such as a POST without a Content-Length.\r\n");
    send(client, buf, sizeof(buf), 0);
}

/**********************************************************************/
/* Put the entire contents of a file out on a socket.  This function
 * is named after the UNIX "cat" command, because it might have been
 * easier just to do something like pipe, fork, and exec("cat").
 * Parameters: the client socket descriptor
 *             FILE pointer for the file to cat */
/**********************************************************************/
void cat(int client, FILE *resource)
{
    char buf[1024];
    //循環讀取並發送文件內容
    fgets(buf, sizeof(buf), resource);
    while (!feof(resource))
    {
        send(client, buf, strlen(buf), 0);
        fgets(buf, sizeof(buf), resource);
    }
}

/**********************************************************************/
/* Inform the client that a CGI script could not be executed.
 * Parameter: the client socket descriptor. */
/**********************************************************************/
void cannot_execute(int client)
{
    char buf[1024];
    //發送500服務器內部錯誤到客戶端
    sprintf(buf, "HTTP/1.0 500 Internal Server Error\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "Content-type: text/html\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "<P>Error prohibited CGI execution.\r\n");
    send(client, buf, strlen(buf), 0);
}

/**********************************************************************/
/* Print out an error message with perror() (for system errors; based
 * on value of errno, which indicates system call errors) and exit the
 * program indicating an error. */
/**********************************************************************/
void error_die(const char *sc)
{
    //打印錯誤信息並退出
    perror(sc);
    exit(1);
}

/**********************************************************************/
/* Execute a CGI script.  Will need to set environment variables as
 * appropriate.
 * Parameters: client socket descriptor
 *             path to the CGI script */
/**********************************************************************/
void execute_cgi(int client, const char *path,
        const char *method, const char *query_string)
{
    char buf[1024];
    int cgi_output[2];
    int cgi_input[2];
    pid_t pid;
    int status;
    int i;
    char c;
    int numchars = 1;
    int content_length = -1;

    buf[0] = 'A'; buf[1] = '\0';
    //如果是GET請求則讀取並丟掉頭部信息
    if (strcasecmp(method, "GET") == 0)
        while ((numchars > 0) && strcmp("\n", buf))  /* read & discard headers */
            numchars = get_line(client, buf, sizeof(buf));
    //如果是POST請求
    else    /* POST */
    {
        //讀取一行數據
        numchars = get_line(client, buf, sizeof(buf));
        while ((numchars > 0) && strcmp("\n", buf))
        {
            //截取Content-Length:字段
            buf[15] = '\0';
            //如果找到該字段，將該字段后面的字串轉成整數長度
            if (strcasecmp(buf, "Content-Length:") == 0)
                content_length = atoi(&(buf[16]));
            //讀取頭部內容
            numchars = get_line(client, buf, sizeof(buf));
        }
        //沒有找到Content-Length，發送bad request
        if (content_length == -1) {
            bad_request(client);
            return;
        }
    }
    //發送http200頭
    sprintf(buf, "HTTP/1.0 200 OK\r\n");
    send(client, buf, strlen(buf), 0);
    //創建輸出管道，構造父子進程通信
    if (pipe(cgi_output) < 0) {
        cannot_execute(client);
        return;
    }
    //創建輸入管道，構造父子進程通信
    if (pipe(cgi_input) < 0) {
        cannot_execute(client);
        return;
    }
    //創建子進程
    if ( (pid = fork()) < 0 ) {
        cannot_execute(client);
        return;
    }
    //子進程執行CGI腳本
    if (pid == 0)  /* child: CGI script */
    {
        char meth_env[255];
        char query_env[255];
        char length_env[255];

        //子進程的標准輸入輸出與管道對接
        dup2(cgi_output[1], 1); //將標准輸出重定向到cgi輸出管道的寫端
        dup2(cgi_input[0], 0); //將標准輸入重定向到cgi輸入管道的讀端

        close(cgi_output[0]); //關閉cgi輸出管道的讀端
        close(cgi_input[1]); //關閉cgi輸入管道的寫端
        //設置method環境變量
        sprintf(meth_env, "REQUEST_METHOD=%s", method);
        putenv(meth_env);
        //如果是GET方式設置請求參數環境變量
        if (strcasecmp(method, "GET") == 0) {
            sprintf(query_env, "QUERY_STRING=%s", query_string);
            putenv(query_env);
        }
        //如果是POST方式設置內容長度環境變量
        else {   /* POST */
            sprintf(length_env, "CONTENT_LENGTH=%d", content_length);
            putenv(length_env);
        }
        //執行CGI
        execl(path, path, NULL);
        exit(0);
    } else {    /* parent */
        close(cgi_output[1]); //關閉cgi輸出管道的寫端
        close(cgi_input[0]); //關閉cgi輸入管道的讀端
        //如果是POST請求，循環讀取post內容，並且輸入到cgi子進程
        if (strcasecmp(method, "POST") == 0)
            for (i = 0; i < content_length; i++) {
                recv(client, &c, 1, 0);
                write(cgi_input[1], &c, 1);
            }
        //從cgi中循環讀取輸出內容，發送到客戶端
        while (read(cgi_output[0], &c, 1) > 0)
            send(client, &c, 1, 0);

        //關閉管道
        close(cgi_output[0]);
        close(cgi_input[1]);
        //等待子進程結束
        waitpid(pid, &status, 0);
    }
}

/**********************************************************************/
/* Get a line from a socket, whether the line ends in a newline,
 * carriage return, or a CRLF combination.  Terminates the string read
 * with a null character.  If no newline indicator is found before the
 * end of the buffer, the string is terminated with a null.  If any of
 * the above three line terminators is read, the last character of the
 * string will be a linefeed and the string will be terminated with a
 * null character.
 * Parameters: the socket descriptor
 *             the buffer to save the data in
 *             the size of the buffer
 * Returns: the number of bytes stored (excluding null) */
/**********************************************************************/
int get_line(int sock, char *buf, int size)
{
    int i = 0;
    char c = '\0';
    int n;
    //接收\n結束的一行數據或接收滿緩沖區
    while ((i < size - 1) && (c != '\n'))
    {
        //接收一個字節
        n = recv(sock, &c, 1, 0);
        /* DEBUG printf("%02X\n", c); */
        if (n > 0)
        {
            //如果接收到了\r符號
            if (c == '\r')
            {
                //將下一個字字符預取出來，注意MSG_PEEK本地接收窗口不滑動，下次讀取仍然可以讀取到該字符
                n = recv(sock, &c, 1, MSG_PEEK);
                /* DEBUG printf("%02X\n", c); */
                //如果下一個字符是\n的話，那么接收這個字符
                if ((n > 0) && (c == '\n'))
                    recv(sock, &c, 1, 0);
                //不是\n的話，那么將\r替換成\n
                else
                    c = '\n';
            }
            //字符存入buf，繼續讀取
            buf[i] = c;
            i++;
        }
        else
            c = '\n';
    }
    //設置buf字符串結束符
    buf[i] = '\0';

    return(i);
}

/**********************************************************************/
/* Return the informational HTTP headers about a file. */
/* Parameters: the socket to print the headers on
 *             the name of the file */
/**********************************************************************/
void headers(int client, const char *filename)
{
    char buf[1024];
    (void)filename;  /* could use filename to determine file type */
    //發送http頭 http碼 服務器信息 內容類型等頭部信息
    strcpy(buf, "HTTP/1.0 200 OK\r\n");
    send(client, buf, strlen(buf), 0);
    strcpy(buf, SERVER_STRING);
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "Content-Type: text/html\r\n");
    send(client, buf, strlen(buf), 0);
    strcpy(buf, "\r\n");
    send(client, buf, strlen(buf), 0);
}

/**********************************************************************/
/* Give a client a 404 not found status message. */
/**********************************************************************/
void not_found(int client)
{
    char buf[1024];
    //發送http頭 http碼 服務器信息 內容類型等頭部信息 html提示信息
    sprintf(buf, "HTTP/1.0 404 NOT FOUND\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, SERVER_STRING);
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "Content-Type: text/html\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "<HTML><TITLE>Not Found</TITLE>\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "<BODY><P>The server could not fulfill\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "your request because the resource specified\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "is unavailable or nonexistent.\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "</BODY></HTML>\r\n");
    send(client, buf, strlen(buf), 0);
}

/**********************************************************************/
/* Send a regular file to the client.  Use headers, and report
 * errors to client if they occur.
 * Parameters: a pointer to a file structure produced from the socket
 *              file descriptor
 *             the name of the file to serve */
/**********************************************************************/
void serve_file(int client, const char *filename)
{
    FILE *resource = NULL;
    int numchars = 1;
    char buf[1024];

    //讀取丟棄所有頭部信息
    buf[0] = 'A'; buf[1] = '\0';
    while ((numchars > 0) && strcmp("\n", buf))  /* read & discard headers */
        numchars = get_line(client, buf, sizeof(buf));

    //打開資源文件
    resource = fopen(filename, "r");
    //打開失敗，發送404
    if (resource == NULL)
        not_found(client);
    else
    {
        headers(client, filename); //發送http頭
        cat(client, resource); //發送資源文件內容
    }
    //關閉資源文件
    fclose(resource);
}

/**********************************************************************/
/* This function starts the process of listening for web connections
 * on a specified port.  If the port is 0, then dynamically allocate a
 * port and modify the original port variable to reflect the actual
 * port.
 * Parameters: pointer to variable containing the port to connect on
 * Returns: the socket */
/**********************************************************************/
int startup(u_short *port)
{
    int httpd = 0;
    struct sockaddr_in name;
    //創建tcp socket
    httpd = socket(PF_INET, SOCK_STREAM, 0);
    if (httpd == -1)
        error_die("socket");
    memset(&name, 0, sizeof(name));
    //設置sockaddr地址結構
    name.sin_family = AF_INET;
    name.sin_port = htons(*port);
    name.sin_addr.s_addr = htonl(INADDR_ANY);
    //綁定到本地地址port指定端口
    if (bind(httpd, (struct sockaddr *)&name, sizeof(name)) < 0)
        error_die("bind");
    //如果沒有指定端口，則由系統指定，此處或得到系統指定的端口
    if (*port == 0)  /* if dynamically allocating a port */
    {
        int namelen = sizeof(name);
        if (getsockname(httpd, (struct sockaddr *)&name, &namelen) == -1)
            error_die("getsockname");
        *port = ntohs(name.sin_port);
    }
    //服務器開始監聽
    if (listen(httpd, 5) < 0)
        error_die("listen");
    return(httpd);
}

/**********************************************************************/
/* Inform the client that the requested web method has not been
 * implemented.
 * Parameter: the client socket */
/**********************************************************************/
void unimplemented(int client)
{
    char buf[1024];
    //發送未實現的請求方法和提示消息給客戶端
    sprintf(buf, "HTTP/1.0 501 Method Not Implemented\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, SERVER_STRING);
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "Content-Type: text/html\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "<HTML><HEAD><TITLE>Method Not Implemented\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "</TITLE></HEAD>\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "<BODY><P>HTTP request method not supported.\r\n");
    send(client, buf, strlen(buf), 0);
    sprintf(buf, "</BODY></HTML>\r\n");
    send(client, buf, strlen(buf), 0);
}

/**********************************************************************/

int main(void)
{
    int server_sock = -1;
    u_short port = 0;
    int client_sock = -1;
    struct sockaddr_in client_name;
    int client_name_len = sizeof(client_name);
    pthread_t newthread;

    server_sock = startup(&port);
    printf("httpd running on port %d\n", port);

    while (1)
    {
        //等待客戶端連接到來
        client_sock = accept(server_sock,
                (struct sockaddr *)&client_name,
                &client_name_len);
        if (client_sock == -1)
            error_die("accept");
        /* accept_request(client_sock); */
        //開啟一個新線程處理客戶端請求
        if (pthread_create(&newthread , NULL, accept_request, client_sock) != 0)
            perror("pthread_create");
    }
    //關閉服務器
    close(server_sock);

    return(0);
}