ftp.c

一个从网络上自动下载文件的自由工具

/* File Transfer Protocol support.
   Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003,
   2004, 2005, 2006, 2007, 2008 Free Software Foundation, Inc.

This file is part of GNU Wget.

GNU Wget is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 3 of the License, or
(at your option) any later version.

GNU Wget is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
GNU General Public License for more details.

You should have received a copy of the GNU General Public License
along with Wget.  If not, see <http://www.gnu.org/licenses/>.

Additional permission under GNU GPL version 3 section 7

If you modify this program, or any covered work, by linking or
combining it with the OpenSSL project's OpenSSL library (or a
modified version of that library), containing parts covered by the
terms of the OpenSSL or SSLeay licenses, the Free Software Foundation
grants you additional permission to convey the resulting work.
Corresponding Source for a non-source form of such a combination
shall include the source code for the parts of OpenSSL used as well
as that of the covered work.  */

#include <config.h>

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#ifdef HAVE_UNISTD_H
# include <unistd.h>
#endif
#include <assert.h>
#include <errno.h>
#include <time.h>

#include "wget.h"
#include "utils.h"
#include "url.h"
#include "retr.h"
#include "ftp.h"
#include "connect.h"
#include "host.h"
#include "netrc.h"
#include "convert.h"            /* for downloaded_file */
#include "recur.h"              /* for INFINITE_RECURSION */

/* File where the "ls -al" listing will be saved.  */
#ifdef MSDOS
#define LIST_FILENAME "_listing"
#else
#define LIST_FILENAME ".listing"
#endif

typedef struct
{
  int st;                       /* connection status */
  int cmd;                      /* command code */
  int csock;                    /* control connection socket */
  double dltime;                /* time of the download in msecs */
  enum stype rs;                /* remote system reported by ftp server */ 
  char *id;                     /* initial directory */
  char *target;                 /* target file name */
  struct url *proxy;            /* FTWK-style proxy */
} ccon;


/* Look for regexp "( *[0-9]+ *byte" (literal parenthesis) anywhere in
   the string S, and return the number converted to wgint, if found, 0
   otherwise.  */
static wgint
ftp_expected_bytes (const char *s)
{
  wgint res;

  while (1)
    {
      while (*s && *s != '(')
        ++s;
      if (!*s)
        return 0;
      ++s;                      /* skip the '(' */
      res = str_to_wgint (s, (char **) &s, 10);
      if (!*s)
        return 0;
      while (*s && ISSPACE (*s))
        ++s;
      if (!*s)
        return 0;
      if (TOLOWER (*s) != 'b')
        continue;
      if (strncasecmp (s, "byte", 4))
        continue;
      else
        break;
    }
  return res;
}

#ifdef ENABLE_IPV6
/* 
 * This function sets up a passive data connection with the FTP server.
 * It is merely a wrapper around ftp_epsv, ftp_lpsv and ftp_pasv.
 */
static uerr_t
ftp_do_pasv (int csock, ip_address *addr, int *port)
{
  uerr_t err;

  /* We need to determine the address family and need to call
     getpeername, so while we're at it, store the address to ADDR.
     ftp_pasv and ftp_lpsv can simply override it.  */
  if (!socket_ip_address (csock, addr, ENDPOINT_PEER))
    abort ();

  /* If our control connection is over IPv6, then we first try EPSV and then 
   * LPSV if the former is not supported. If the control connection is over 
   * IPv4, we simply issue the good old PASV request. */
  switch (addr->family)
    {
    case AF_INET:
      if (!opt.server_response)
        logputs (LOG_VERBOSE, "==> PASV ... ");
      err = ftp_pasv (csock, addr, port);
      break;
    case AF_INET6:
      if (!opt.server_response)
        logputs (LOG_VERBOSE, "==> EPSV ... ");
      err = ftp_epsv (csock, addr, port);

      /* If EPSV is not supported try LPSV */
      if (err == FTPNOPASV)
        {
          if (!opt.server_response)
            logputs (LOG_VERBOSE, "==> LPSV ... ");
          err = ftp_lpsv (csock, addr, port);
        }
      break;
    default:
      abort ();
    }

  return err;
}

/* 
 * This function sets up an active data connection with the FTP server.
 * It is merely a wrapper around ftp_eprt, ftp_lprt and ftp_port.
 */
static uerr_t
ftp_do_port (int csock, int *local_sock)
{
  uerr_t err;
  ip_address cip;

  if (!socket_ip_address (csock, &cip, ENDPOINT_PEER))
    abort ();

  /* If our control connection is over IPv6, then we first try EPRT and then 
   * LPRT if the former is not supported. If the control connection is over 
   * IPv4, we simply issue the good old PORT request. */
  switch (cip.family)
    {
    case AF_INET:
      if (!opt.server_response)
        logputs (LOG_VERBOSE, "==> PORT ... ");
      err = ftp_port (csock, local_sock);
      break;
    case AF_INET6:
      if (!opt.server_response)
        logputs (LOG_VERBOSE, "==> EPRT ... ");
      err = ftp_eprt (csock, local_sock);

      /* If EPRT is not supported try LPRT */
      if (err == FTPPORTERR)
        {
          if (!opt.server_response)
            logputs (LOG_VERBOSE, "==> LPRT ... ");
          err = ftp_lprt (csock, local_sock);
        }
      break;
    default:
      abort ();
    }
  return err;
}
#else

static uerr_t
ftp_do_pasv (int csock, ip_address *addr, int *port)
{
  if (!opt.server_response)
    logputs (LOG_VERBOSE, "==> PASV ... ");
  return ftp_pasv (csock, addr, port);
}

static uerr_t
ftp_do_port (int csock, int *local_sock)
{
  if (!opt.server_response)
    logputs (LOG_VERBOSE, "==> PORT ... ");
  return ftp_port (csock, local_sock);
}
#endif

static void
print_length (wgint size, wgint start, bool authoritative)
{
  logprintf (LOG_VERBOSE, _("Length: %s"), number_to_static_string (size));
  if (size >= 1024)
    logprintf (LOG_VERBOSE, " (%s)", human_readable (size));
  if (start > 0)
    {
      if (start >= 1024)
        logprintf (LOG_VERBOSE, _(", %s (%s) remaining"),
                   number_to_static_string (size - start),
                   human_readable (size - start));
      else
        logprintf (LOG_VERBOSE, _(", %s remaining"),
                   number_to_static_string (size - start));
    }
  logputs (LOG_VERBOSE, !authoritative ? _(" (unauthoritative)\n") : "\n");
}

/* Retrieves a file with denoted parameters through opening an FTP
   connection to the server.  It always closes the data connection,
   and closes the control connection in case of error.  */
static uerr_t
getftp (struct url *u, wgint *len, wgint restval, ccon *con)
{
  int csock, dtsock, local_sock, res;
  uerr_t err = RETROK;          /* appease the compiler */
  FILE *fp;
  char *user, *passwd, *respline;
  char *tms;
  const char *tmrate;
  int cmd = con->cmd;
  bool pasv_mode_open = false;
  wgint expected_bytes = 0;
  bool rest_failed = false;
  int flags;
  wgint rd_size;

  assert (con != NULL);
  assert (con->target != NULL);

  /* Debug-check of the sanity of the request by making sure that LIST
     and RETR are never both requested (since we can handle only one
     at a time.  */
  assert (!((cmd & DO_LIST) && (cmd & DO_RETR)));
  /* Make sure that at least *something* is requested.  */
  assert ((cmd & (DO_LIST | DO_CWD | DO_RETR | DO_LOGIN)) != 0);

  user = u->user;
  passwd = u->passwd;
  search_netrc (u->host, (const char **)&user, (const char **)&passwd, 1);
  user = user ? user : (opt.ftp_user ? opt.ftp_user : opt.user);
  if (!user) user = "anonymous";
  passwd = passwd ? passwd : (opt.ftp_passwd ? opt.ftp_passwd : opt.passwd);
  if (!passwd) passwd = "-wget@";

  dtsock = -1;
  local_sock = -1;
  con->dltime = 0;

  if (!(cmd & DO_LOGIN))
    csock = con->csock;
  else                          /* cmd & DO_LOGIN */
    {
      char type_char;
      char    *host = con->proxy ? con->proxy->host : u->host;
      int      port = con->proxy ? con->proxy->port : u->port;
      char *logname = user;

      if (con->proxy)
        {
          /* If proxy is in use, log in as username@target-site. */
          logname = concat_strings (user, "@", u->host, (char *) 0);
        }

      /* Login to the server: */

      /* First: Establish the control connection.  */

      csock = connect_to_host (host, port);
      if (csock == E_HOST)
        return HOSTERR;
      else if (csock < 0)
        return (retryable_socket_connect_error (errno)
                ? CONERROR : CONIMPOSSIBLE);

      if (cmd & LEAVE_PENDING)
        con->csock = csock;
      else
        con->csock = -1;

      /* Second: Login with proper USER/PASS sequence.  */
      logprintf (LOG_VERBOSE, _("Logging in as %s ... "), escnonprint (user));
      if (opt.server_response)
        logputs (LOG_ALWAYS, "\n");
      err = ftp_login (csock, logname, passwd);

      if (con->proxy)
        xfree (logname);

      /* FTPRERR, FTPSRVERR, WRITEFAILED, FTPLOGREFUSED, FTPLOGINC */
      switch (err)
        {
        case FTPRERR:
          logputs (LOG_VERBOSE, "\n");
          logputs (LOG_NOTQUIET, _("\
Error in server response, closing control connection.\n"));
          fd_close (csock);
          con->csock = -1;
          return err;
        case FTPSRVERR:
          logputs (LOG_VERBOSE, "\n");
          logputs (LOG_NOTQUIET, _("Error in server greeting.\n"));
          fd_close (csock);
          con->csock = -1;
          return err;
        case WRITEFAILED:
          logputs (LOG_VERBOSE, "\n");
          logputs (LOG_NOTQUIET,
                   _("Write failed, closing control connection.\n"));
          fd_close (csock);
          con->csock = -1;
          return err;
        case FTPLOGREFUSED:
          logputs (LOG_VERBOSE, "\n");
          logputs (LOG_NOTQUIET, _("The server refuses login.\n"));
          fd_close (csock);
          con->csock = -1;
          return FTPLOGREFUSED;
        case FTPLOGINC:
          logputs (LOG_VERBOSE, "\n");
          logputs (LOG_NOTQUIET, _("Login incorrect.\n"));
          fd_close (csock);
          con->csock = -1;
          return FTPLOGINC;
        case FTPOK:
          if (!opt.server_response)
            logputs (LOG_VERBOSE, _("Logged in!\n"));
          break;
        default:
          abort ();
        }
      /* Third: Get the system type */
      if (!opt.server_response)
        logprintf (LOG_VERBOSE, "==> SYST ... ");
      err = ftp_syst (csock, &con->rs);
      /* FTPRERR */
      switch (err)
        {
        case FTPRERR:
          logputs (LOG_VERBOSE, "\n");
          logputs (LOG_NOTQUIET, _("\
Error in server response, closing control connection.\n"));
          fd_close (csock);
          con->csock = -1;
          return err;
        case FTPSRVERR:
          logputs (LOG_VERBOSE, "\n");
          logputs (LOG_NOTQUIET,
                   _("Server error, can't determine system type.\n"));
          break;
        case FTPOK:
          /* Everything is OK.  */
          break;
        default:
          abort ();
        }
      if (!opt.server_response && err != FTPSRVERR)
        logputs (LOG_VERBOSE, _("done.    "));

      /* Fourth: Find the initial ftp directory */

      if (!opt.server_response)
        logprintf (LOG_VERBOSE, "==> PWD ... ");
      err = ftp_pwd (csock, &con->id);
      /* FTPRERR */
      switch (err)
        {
        case FTPRERR:
          logputs (LOG_VERBOSE, "\n");
          logputs (LOG_NOTQUIET, _("\
Error in server response, closing control connection.\n"));
          fd_close (csock);
          con->csock = -1;
          return err;
        case FTPSRVERR :
          /* PWD unsupported -- assume "/". */
          xfree_null (con->id);
          con->id = xstrdup ("/");
          break;
        case FTPOK:
          /* Everything is OK.  */
          break;
        default:
          abort ();
        }
      /* VMS will report something like "PUB$DEVICE:[INITIAL.FOLDER]".
         Convert it to "/INITIAL/FOLDER" */ 
      if (con->rs == ST_VMS)
        {
          char *path = strchr (con->id, '[');
          char *pathend = path ? strchr (path + 1, ']') : NULL;
          if (!path || !pathend)
            DEBUGP (("Initial VMS directory not in the form [...]!\n"));
          else
            {
              char *idir = con->id;
              DEBUGP (("Preprocessing the initial VMS directory\n"));
              DEBUGP (("  old = '%s'\n", con->id));
              /* We do the conversion in-place by copying the stuff
                 between [ and ] to the beginning, and changing dots
                 to slashes at the same time.  */
              *idir++ = '/';
              for (++path; path < pathend; path++, idir++)
                *idir = *path == '.' ? '/' : *path;
              *idir = '\0';
              DEBUGP (("  new = '%s'\n\n", con->id));
            }
        }
      if (!opt.server_response)
        logputs (LOG_VERBOSE, _("done.\n"));

      /* Fifth: Set the FTP type.  */
      type_char = ftp_process_type (u->params);
      if (!opt.server_response)
        logprintf (LOG_VERBOSE, "==> TYPE %c ... ", type_char);
      err = ftp_type (csock, type_char);
      /* FTPRERR, WRITEFAILED, FTPUNKNOWNTYPE */
      switch (err)
        {
        case FTPRERR:
          logputs (LOG_VERBOSE, "\n");
          logputs (LOG_NOTQUIET, _("\
Error in server response, closing control connection.\n"));
          fd_close (csock);
          con->csock = -1;
          return err;
        case WRITEFAILED:
          logputs (LOG_VERBOSE, "\n");
          logputs (LOG_NOTQUIET,
                   _("Write failed, closing control connection.\n"));
          fd_close (csock);
          con->csock = -1;
          return err;
        case FTPUNKNOWNTYPE:
          logputs (LOG_VERBOSE, "\n");
          logprintf (LOG_NOTQUIET,
                     _("Unknown type `%c', closing control connection.\n"),
                     type_char);
          fd_close (csock);
          con->csock = -1;
          return err;
        case FTPOK:
          /* Everything is OK.  */
          break;
        default:
          abort ();
        }
      if (!opt.server_response)
        logputs (LOG_VERBOSE, _("done.  "));
    } /* do login */

  if (cmd & DO_CWD)
    {
      if (!*u->dir)
        logputs (LOG_VERBOSE, _("==> CWD not needed.\n"));
      else
        {