utils.c

Wget很好的处理了http和ftp的下载,很值得学习的经典代码

/* Various utility functions.
   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>
#include <time.h>
#ifdef HAVE_SYS_TIME_H
# include <sys/time.h>
#endif
#ifdef HAVE_UNISTD_H
# include <unistd.h>
#endif
#ifdef HAVE_MMAP
# include <sys/mman.h>
#endif
#ifdef HAVE_PROCESS_H
# include <process.h>  /* getpid() */
#endif
#ifdef HAVE_UTIME_H
# include <utime.h>
#endif
#ifdef HAVE_SYS_UTIME_H
# include <sys/utime.h>
#endif
#include <errno.h>
#include <fcntl.h>
#include <assert.h>
#include <stdarg.h>
#include <locale.h>

/* For TIOCGWINSZ and friends: */
#ifdef HAVE_SYS_IOCTL_H
# include <sys/ioctl.h>
#endif
#ifdef HAVE_TERMIOS_H
# include <termios.h>
#endif

/* Needed for Unix version of run_with_timeout. */
#include <signal.h>
#include <setjmp.h>

#ifndef HAVE_SIGSETJMP
/* If sigsetjmp is a macro, configure won't pick it up. */
# ifdef sigsetjmp
#  define HAVE_SIGSETJMP
# endif
#endif

#if defined HAVE_SIGSETJMP || defined HAVE_SIGBLOCK
# define USE_SIGNAL_TIMEOUT
#endif

#include "wget.h"
#include "utils.h"
#include "hash.h"

#ifdef TESTING
#include "test.h"
#endif 

/* Utility function: like xstrdup(), but also lowercases S.  */

char *
xstrdup_lower (const char *s)
{
  char *copy = xstrdup (s);
  char *p = copy;
  for (; *p; p++)
    *p = TOLOWER (*p);
  return copy;
}

/* Copy the string formed by two pointers (one on the beginning, other
   on the char after the last char) to a new, malloc-ed location.
   0-terminate it.  */
char *
strdupdelim (const char *beg, const char *end)
{
  char *res = xmalloc (end - beg + 1);
  memcpy (res, beg, end - beg);
  res[end - beg] = '\0';
  return res;
}

/* Parse a string containing comma-separated elements, and return a
   vector of char pointers with the elements.  Spaces following the
   commas are ignored.  */
char **
sepstring (const char *s)
{
  char **res;
  const char *p;
  int i = 0;

  if (!s || !*s)
    return NULL;
  res = NULL;
  p = s;
  while (*s)
    {
      if (*s == ',')
        {
          res = xrealloc (res, (i + 2) * sizeof (char *));
          res[i] = strdupdelim (p, s);
          res[++i] = NULL;
          ++s;
          /* Skip the blanks following the ','.  */
          while (ISSPACE (*s))
            ++s;
          p = s;
        }
      else
        ++s;
    }
  res = xrealloc (res, (i + 2) * sizeof (char *));
  res[i] = strdupdelim (p, s);
  res[i + 1] = NULL;
  return res;
}

/* Like sprintf, but prints into a string of sufficient size freshly
   allocated with malloc, which is returned.  If unable to print due
   to invalid format, returns NULL.  Inability to allocate needed
   memory results in abort, as with xmalloc.  This is in spirit
   similar to the GNU/BSD extension asprintf, but somewhat easier to
   use.

   Internally the function either calls vasprintf or loops around
   vsnprintf until the correct size is found.  Since Wget also ships a
   fallback implementation of vsnprintf, this should be portable.  */

char *
aprintf (const char *fmt, ...)
{
#if defined HAVE_VASPRINTF && !defined DEBUG_MALLOC
  /* Use vasprintf. */
  int ret;
  va_list args;
  char *str;
  va_start (args, fmt);
  ret = vasprintf (&str, fmt, args);
  va_end (args);
  if (ret < 0 && errno == ENOMEM)
    abort ();                   /* for consistency with xmalloc/xrealloc */
  else if (ret < 0)
    return NULL;
  return str;
#else  /* not HAVE_VASPRINTF */

  /* vasprintf is unavailable.  snprintf into a small buffer and
     resize it as necessary. */
  int size = 32;
  char *str = xmalloc (size);

  /* #### This code will infloop and eventually abort in xrealloc if
     passed a FMT that causes snprintf to consistently return -1.  */

  while (1)
    {
      int n;
      va_list args;

      va_start (args, fmt);
      n = vsnprintf (str, size, fmt, args);
      va_end (args);

      /* If the printing worked, return the string. */
      if (n > -1 && n < size)
        return str;

      /* Else try again with a larger buffer. */
      if (n > -1)               /* C99 */
        size = n + 1;           /* precisely what is needed */
      else
        size <<= 1;             /* twice the old size */
      str = xrealloc (str, size);
    }
#endif /* not HAVE_VASPRINTF */
}

/* Concatenate the NULL-terminated list of string arguments into
   freshly allocated space.  */

char *
concat_strings (const char *str0, ...)
{
  va_list args;
  int saved_lengths[5];         /* inspired by Apache's apr_pstrcat */
  char *ret, *p;

  const char *next_str;
  int total_length = 0;
  int argcount;

  /* Calculate the length of and allocate the resulting string. */

  argcount = 0;
  va_start (args, str0);
  for (next_str = str0; next_str != NULL; next_str = va_arg (args, char *))
    {
      int len = strlen (next_str);
      if (argcount < countof (saved_lengths))
        saved_lengths[argcount++] = len;
      total_length += len;
    }
  va_end (args);
  p = ret = xmalloc (total_length + 1);

  /* Copy the strings into the allocated space. */

  argcount = 0;
  va_start (args, str0);
  for (next_str = str0; next_str != NULL; next_str = va_arg (args, char *))
    {
      int len;
      if (argcount < countof (saved_lengths))
        len = saved_lengths[argcount++];
      else
        len = strlen (next_str);
      memcpy (p, next_str, len);
      p += len;
    }
  va_end (args);
  *p = '\0';

  return ret;
}

/* Format the provided time according to the specified format.  The
   format is a string with format elements supported by strftime.  */

static char *
fmttime (time_t t, const char *fmt)
{
  static char output[32];
  struct tm *tm = localtime(&t);
  if (!tm)
    abort ();
  if (!strftime(output, sizeof(output), fmt, tm))
    abort ();
  return output;
}

/* Return pointer to a static char[] buffer in which zero-terminated
   string-representation of TM (in form hh:mm:ss) is printed.

   If TM is NULL, the current time will be used.  */

char *
time_str (time_t t)
{
  return fmttime(t, "%H:%M:%S");
}

/* Like the above, but include the date: YYYY-MM-DD hh:mm:ss.  */

char *
datetime_str (time_t t)
{
  return fmttime(t, "%Y-%m-%d %H:%M:%S");
}

/* The Windows versions of the following two functions are defined in
   mswindows.c. On MSDOS this function should never be called. */

#if !defined(WINDOWS) && !defined(MSDOS)
void
fork_to_background (void)
{
  pid_t pid;
  /* Whether we arrange our own version of opt.lfilename here.  */
  bool logfile_changed = false;

  if (!opt.lfilename)
    {
      /* We must create the file immediately to avoid either a race
         condition (which arises from using unique_name and failing to
         use fopen_excl) or lying to the user about the log file name
         (which arises from using unique_name, printing the name, and
         using fopen_excl later on.)  */
      FILE *new_log_fp = unique_create (DEFAULT_LOGFILE, false, &opt.lfilename);
      if (new_log_fp)
        {
          logfile_changed = true;
          fclose (new_log_fp);
        }
    }
  pid = fork ();
  if (pid < 0)
    {
      /* parent, error */
      perror ("fork");
      exit (1);
    }
  else if (pid != 0)
    {
      /* parent, no error */
      printf (_("Continuing in background, pid %d.\n"), (int) pid);
      if (logfile_changed)
        printf (_("Output will be written to `%s'.\n"), opt.lfilename);
      exit (0);                 /* #### should we use _exit()? */
    }

  /* child: give up the privileges and keep running. */
  setsid ();
  freopen ("/dev/null", "r", stdin);
  freopen ("/dev/null", "w", stdout);
  freopen ("/dev/null", "w", stderr);
}
#endif /* !WINDOWS && !MSDOS */

/* "Touch" FILE, i.e. make its mtime ("modified time") equal the time
   specified with TM.  The atime ("access time") is set to the current
   time.  */

void
touch (const char *file, time_t tm)
{
#ifdef HAVE_STRUCT_UTIMBUF
  struct utimbuf times;
#else
  struct {
    time_t actime;
    time_t modtime;
  } times;
#endif
  times.modtime = tm;
  times.actime = time (NULL);
  if (utime (file, &times) == -1)
    logprintf (LOG_NOTQUIET, "utime(%s): %s\n", file, strerror (errno));
}

/* Checks if FILE is a symbolic link, and removes it if it is.  Does
   nothing under MS-Windows.  */
int
remove_link (const char *file)
{
  int err = 0;
  struct_stat st;

  if (lstat (file, &st) == 0 && S_ISLNK (st.st_mode))
    {
      DEBUGP (("Unlinking %s (symlink).\n", file));
      err = unlink (file);
      if (err != 0)
        logprintf (LOG_VERBOSE, _("Failed to unlink symlink `%s': %s\n"),
                   file, strerror (errno));
    }
  return err;
}

/* Does FILENAME exist?  This is quite a lousy implementation, since
   it supplies no error codes -- only a yes-or-no answer.  Thus it
   will return that a file does not exist if, e.g., the directory is
   unreadable.  I don't mind it too much currently, though.  The
   proper way should, of course, be to have a third, error state,
   other than true/false, but that would introduce uncalled-for
   additional complexity to the callers.  */
bool
file_exists_p (const char *filename)
{
#ifdef HAVE_ACCESS
  return access (filename, F_OK) >= 0;
#else
  struct_stat buf;
  return stat (filename, &buf) >= 0;
#endif
}

/* Returns 0 if PATH is a directory, 1 otherwise (any kind of file).
   Returns 0 on error.  */
bool
file_non_directory_p (const char *path)
{
  struct_stat buf;
  /* Use lstat() rather than stat() so that symbolic links pointing to
     directories can be identified correctly.  */
  if (lstat (path, &buf) != 0)
    return false;
  return S_ISDIR (buf.st_mode) ? false : true;
}

/* Return the size of file named by FILENAME, or -1 if it cannot be
   opened or seeked into. */
wgint
file_size (const char *filename)
{
#if defined(HAVE_FSEEKO) && defined(HAVE_FTELLO)
  wgint size;
  /* We use fseek rather than stat to determine the file size because
     that way we can also verify that the file is readable without
     explicitly checking for permissions.  Inspired by the POST patch
     by Arnaud Wylie.  */
  FILE *fp = fopen (filename, "rb");
  if (!fp)
    return -1;
  fseeko (fp, 0, SEEK_END);
  size = ftello (fp);
  fclose (fp);
  return size;
#else
  struct_stat st;
  if (stat (filename, &st) < 0)
    return -1;
  return st.st_size;