commit bash-20070405 snapshot

[thirdparty/bash.git] / builtins / read.def

This file is read.def, from which is created read.c.
It implements the builtin "read" in Bash.

Copyright (C) 1987-2007 Free Software Foundation, Inc.

This file is part of GNU Bash, the Bourne Again SHell.

Bash 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 2, or (at your option) any later
version.

Bash 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 Bash; see the file COPYING.  If not, write to the Free Software
Foundation, 59 Temple Place, Suite 330, Boston, MA 02111 USA.

$PRODUCES read.c

$BUILTIN read
$FUNCTION read_builtin
$SHORT_DOC read [-ers] [-a array] [-d delim] [-n nchars] [-p prompt] [-t timeout] [-u fd] [name ...]
One line is read from the standard input, or from file descriptor FD if the
-u option is supplied, and the first word is assigned to the first NAME,
the second word to the second NAME, and so on, with leftover words assigned
to the last NAME.  Only the characters found in $IFS are recognized as word
delimiters.  If no NAMEs are supplied, the line read is stored in the REPLY
variable.  If the -r option is given, this signifies `raw' input, and
backslash escaping is disabled.  The -d option causes read to continue
until the first character of DELIM is read, rather than newline.  If the -p
option is supplied, the string PROMPT is output without a trailing newline
before attempting to read.  If -a is supplied, the words read are assigned
to sequential indices of ARRAY, starting at zero.  If -e is supplied and
the shell is interactive, readline is used to obtain the line.  If -n is
supplied with a non-zero NCHARS argument, read returns after NCHARS
characters have been read.  The -s option causes input coming from a
terminal to not be echoed.

The -t option causes read to time out and return failure if a complete line
of input is not read within TIMEOUT seconds.  If the TMOUT variable is set,
its value is the default timeout.  The return code is zero, unless end-of-file
is encountered, read times out, or an invalid file descriptor is supplied as
the argument to -u.
$END

#include <config.h>

#include "bashtypes.h"
#include "posixstat.h"

#include <stdio.h>

#if defined (HAVE_UNISTD_H)
#  include <unistd.h>
#endif

#include <signal.h>
#include <errno.h>

#ifdef __CYGWIN__
#  include <fcntl.h>
#  include <io.h>
#endif

#include "../bashintl.h"

#include "../shell.h"
#include "common.h"
#include "bashgetopt.h"

#include <shtty.h>

#if defined (READLINE)
#include "../bashline.h"
#include <readline/readline.h>
#endif

#if defined (BUFFERED_INPUT)
#  include "input.h"
#endif

#if !defined(errno)
extern int errno;
#endif

#if defined (READLINE)
static void reset_attempted_completion_function __P((char *));
static char *edit_line __P((char *));
static void set_eol_delim __P((int));
static void reset_eol_delim __P((char *));
#endif
static SHELL_VAR *bind_read_variable __P((char *, char *));

static sighandler sigalrm __P((int));
static void reset_alarm __P((void));

static procenv_t alrmbuf;
static SigHandler *old_alrm;
static unsigned char delim;

static sighandler
sigalrm (s)
     int s;
{
  longjmp (alrmbuf, 1);
}

static void
reset_alarm ()
{
  set_signal_handler (SIGALRM, old_alrm);
  alarm (0);
}

/* Read the value of the shell variables whose names follow.
   The reading is done from the current input stream, whatever
   that may be.  Successive words of the input line are assigned
   to the variables mentioned in LIST.  The last variable in LIST
   gets the remainder of the words on the line.  If no variables
   are mentioned in LIST, then the default variable is $REPLY. */
int
read_builtin (list)
     WORD_LIST *list;
{
  register char *varname;
  int size, i, nr, pass_next, saw_escape, eof, opt, retval, code, print_ps2;
  int input_is_tty, input_is_pipe, unbuffered_read, skip_ctlesc, skip_ctlnul;
  int raw, edit, nchars, silent, have_timeout, fd;
  unsigned int tmout;
  intmax_t intval;
  char c;
  char *input_string, *orig_input_string, *ifs_chars, *prompt, *arrayname;
  char *e, *t, *t1, *ps2;
  struct stat tsb;
  SHELL_VAR *var;
#if defined (ARRAY_VARS)
  WORD_LIST *alist;
#endif
#if defined (READLINE)
  char *rlbuf;
  int rlind;
#endif

  USE_VAR(size);
  USE_VAR(i);
  USE_VAR(pass_next);
  USE_VAR(print_ps2);
  USE_VAR(saw_escape);
  USE_VAR(input_is_pipe);
/*  USE_VAR(raw); */
  USE_VAR(edit);
  USE_VAR(tmout);
  USE_VAR(nchars);
  USE_VAR(silent);
  USE_VAR(ifs_chars);
  USE_VAR(prompt);
  USE_VAR(arrayname);
#if defined (READLINE)
  USE_VAR(rlbuf);
  USE_VAR(rlind);
#endif
  USE_VAR(list);
  USE_VAR(ps2);

  i = 0;		/* Index into the string that we are reading. */
  raw = edit = 0;	/* Not reading raw input by default. */
  silent = 0;
  arrayname = prompt = (char *)NULL;
  fd = 0;		/* file descriptor to read from */

#if defined (READLINE)
  rlbuf = (char *)0;
  rlind = 0;
#endif

  tmout = 0;		/* no timeout */
  nr = nchars = input_is_tty = input_is_pipe = unbuffered_read = have_timeout = 0;
  delim = '\n';		/* read until newline */

  reset_internal_getopt ();
  while ((opt = internal_getopt (list, "ersa:d:n:p:t:u:")) != -1)
    {
      switch (opt)
	{
	case 'r':
	  raw = 1;
	  break;
	case 'p':
	  prompt = list_optarg;
	  break;
	case 's':
	  silent = 1;
	  break;
	case 'e':
#if defined (READLINE)
	  edit = 1;
#endif
	  break;
#if defined (ARRAY_VARS)
	case 'a':
	  arrayname = list_optarg;
	  break;
#endif
	case 't':
	  code = legal_number (list_optarg, &intval);
	  if (code == 0 || intval < 0 || intval != (unsigned int)intval)
	    {
	      builtin_error (_("%s: invalid timeout specification"), list_optarg);
	      return (EXECUTION_FAILURE);
	    }
	  else
	    {
	      have_timeout = 1;
	      tmout = intval;
	    }
	  break;
	case 'n':
	  code = legal_number (list_optarg, &intval);
	  if (code == 0 || intval < 0 || intval != (int)intval)
	    {
	      sh_invalidnum (list_optarg);
	      return (EXECUTION_FAILURE);
	    }
	  else
	    nchars = intval;
	  break;
	case 'u':
	  code = legal_number (list_optarg, &intval);
	  if (code == 0 || intval < 0 || intval != (int)intval)
	    {
	      builtin_error (_("%s: invalid file descriptor specification"), list_optarg);
	      return (EXECUTION_FAILURE);
	    }
	  else
	    fd = intval;
	  if (sh_validfd (fd) == 0)
	    {
	      builtin_error (_("%d: invalid file descriptor: %s"), fd, strerror (errno));
	      return (EXECUTION_FAILURE);
	    }
	  break;
	case 'd':
	  delim = *list_optarg;
	  break;
	default:
	  builtin_usage ();
	  return (EX_USAGE);
	}
    }
  list = loptend;

  /* `read -t 0 var' returns failure immediately.  XXX - should it test
     whether input is available with select/FIONREAD, and fail if those
     are unavailable? */
  if (have_timeout && tmout == 0)
    return (EXECUTION_FAILURE);

  /* IF IFS is unset, we use the default of " \t\n". */
  ifs_chars = getifs ();
  if (ifs_chars == 0)		/* XXX - shouldn't happen */
    ifs_chars = "";
  for (skip_ctlesc = skip_ctlnul = 0, e = ifs_chars; *e; e++)
    skip_ctlesc |= *e == CTLESC, skip_ctlnul |= *e == CTLNUL;

  input_string = (char *)xmalloc (size = 112);	/* XXX was 128 */

  /* $TMOUT, if set, is the default timeout for read. */
  if (have_timeout == 0 && (e = get_string_value ("TMOUT")))
    {
      code = legal_number (e, &intval);
      if (code == 0 || intval < 0 || intval != (unsigned int)intval)
	tmout = 0;
      else
	tmout = intval;
    }

  begin_unwind_frame ("read_builtin");

#if defined (BUFFERED_INPUT)
  if (interactive == 0 && default_buffered_input >= 0 && fd_is_bash_input (fd))
    sync_buffered_stream (default_buffered_input);
#endif

  input_is_tty = isatty (fd);
  if (input_is_tty == 0)
#ifndef __CYGWIN__
    input_is_pipe = (lseek (fd, 0L, SEEK_CUR) < 0) && (errno == ESPIPE);
#else
    input_is_pipe = 1;
#endif

  /* If the -p, -e or -s flags were given, but input is not coming from the
     terminal, turn them off. */
  if ((prompt || edit || silent) && input_is_tty == 0)
    {
      prompt = (char *)NULL;
      edit = silent = 0;
    }

#if defined (READLINE)
  if (edit)
    add_unwind_protect (xfree, rlbuf);
#endif

  if (prompt && edit == 0)
    {
      fprintf (stderr, "%s", prompt);
      fflush (stderr);
    }

  pass_next = 0;	/* Non-zero signifies last char was backslash. */
  saw_escape = 0;	/* Non-zero signifies that we saw an escape char */

  if (tmout > 0)
    {
      /* Turn off the timeout if stdin is a regular file (e.g. from
	 input redirection). */
      if ((fstat (fd, &tsb) < 0) || S_ISREG (tsb.st_mode))
	tmout = 0;
    }

  if (tmout > 0)
    {
      code = setjmp (alrmbuf);
      if (code)
	{
	  run_unwind_frame ("read_builtin");
	  return (EXECUTION_FAILURE);
	}
      old_alrm = set_signal_handler (SIGALRM, sigalrm);
      add_unwind_protect (reset_alarm, (char *)NULL);
#if defined (READLINE)
      if (edit)
	add_unwind_protect (reset_attempted_completion_function, (char *)NULL);
#endif
      alarm (tmout);
    }

  /* If we've been asked to read only NCHARS chars, or we're using some
     character other than newline to terminate the line, do the right
     thing to readline or the tty. */
  if (nchars > 0 || delim != '\n')
    {
#if defined (READLINE)
      if (edit)
	{
	  if (nchars > 0)
	    {
	      unwind_protect_int (rl_num_chars_to_read);
	      rl_num_chars_to_read = nchars;
	    }
	  if (delim != '\n')
	    {
	      set_eol_delim (delim);
	      add_unwind_protect (reset_eol_delim, (char *)NULL);
	    }
	}
      else
#endif
      if (input_is_tty)
	{
	  ttsave ();
	  if (silent)
	    ttcbreak ();
	  else
	    ttonechar ();
	  add_unwind_protect ((Function *)ttrestore, (char *)NULL);
	}
    }
  else if (silent)	/* turn off echo but leave term in canonical mode */
    {
      ttsave ();
      ttnoecho ();
      add_unwind_protect ((Function *)ttrestore, (char *)NULL);
    }

  /* This *must* be the top unwind-protect on the stack, so the manipulation
     of the unwind-protect stack after the realloc() works right. */
  add_unwind_protect (xfree, input_string);
  interrupt_immediately++;
  terminate_immediately = 1;

  unbuffered_read = (nchars > 0) || (delim != '\n') || input_is_pipe;

#if defined (__CYGWIN__) && defined (O_TEXT)
  setmode (0, O_TEXT);
#endif

  ps2 = 0;
  for (print_ps2 = eof = retval = 0;;)
    {
#if defined (READLINE)
      if (edit)
	{
	  if (rlbuf && rlbuf[rlind] == '\0')
	    {
	      xfree (rlbuf);
	      rlbuf = (char *)0;
	    }
	  if (rlbuf == 0)
	    {
	      rlbuf = edit_line (prompt ? prompt : "");
	      rlind = 0;
	    }
	  if (rlbuf == 0)
	    {
	      eof = 1;
	      break;
	    }
	  c = rlbuf[rlind++];
	}
      else
	{
#endif

      if (print_ps2)
	{
	  if (ps2 == 0)
	    ps2 = get_string_value ("PS2");
	  fprintf (stderr, "%s", ps2 ? ps2 : "");
	  fflush (stderr);
	  print_ps2 = 0;
	}

      if (unbuffered_read)
	retval = zread (fd, &c, 1);
      else
	retval = zreadc (fd, &c);

      if (retval <= 0)
	{
	  eof = 1;
	  break;
	}

#if defined (READLINE)
	}
#endif

      if (i + 2 >= size)
	{
	  input_string = (char *)xrealloc (input_string, size += 128);
	  remove_unwind_protect ();
	  add_unwind_protect (xfree, input_string);
	}

      /* If the next character is to be accepted verbatim, a backslash
	 newline pair still disappears from the input. */
      if (pass_next)
	{
	  pass_next = 0;
	  if (c == '\n')
	    {
	      i--;		/* back up over the CTLESC */
	      if (interactive && raw == 0)
		print_ps2 = 1;
	    }
	  else
	    goto add_char;
	  continue;
	}

      /* This may cause problems if IFS contains CTLESC */
      if (c == '\\' && raw == 0)
	{
	  pass_next++;
	  if (skip_ctlesc == 0)
	    {
	      saw_escape++;
	      input_string[i++] = CTLESC;
	    }
	  continue;
	}

      if ((unsigned char)c == delim)
	break;

      if ((skip_ctlesc == 0 && c == CTLESC) || (skip_ctlnul == 0 && c == CTLNUL))
	{
	  saw_escape++;
	  input_string[i++] = CTLESC;
	}

add_char:
      input_string[i++] = c;
      nr++;

      if (nchars > 0 && nr >= nchars)
	break;
    }
  input_string[i] = '\0';

#if 1
  if (retval < 0)
    {
      builtin_error (_("read error: %d: %s"), fd, strerror (errno));
      run_unwind_frame ("read_builtin");
      return (EXECUTION_FAILURE);
    }
#endif

  if (tmout > 0)
    reset_alarm ();

  if (nchars > 0 || delim != '\n')
    {
#if defined (READLINE)
      if (edit)
	{
	  if (nchars > 0)
	    rl_num_chars_to_read = 0;
	  if (delim != '\n')
	    reset_eol_delim ((char *)NULL);
	}
      else
#endif
      if (input_is_tty)
	ttrestore ();
    }
  else if (silent)
    ttrestore ();

  if (unbuffered_read == 0)
    zsyncfd (fd);

  interrupt_immediately--;
  terminate_immediately = 0;
  discard_unwind_frame ("read_builtin");

  retval = eof ? EXECUTION_FAILURE : EXECUTION_SUCCESS;

#if defined (ARRAY_VARS)
  /* If -a was given, take the string read, break it into a list of words,
     an assign them to `arrayname' in turn. */
  if (arrayname)
    {
      if (legal_identifier (arrayname) == 0)
	{
	  sh_invalidid (arrayname);
	  xfree (input_string);
	  return (EXECUTION_FAILURE);
	}

      var = find_or_make_array_variable (arrayname, 1);
      if (var == 0)
	{
	  xfree (input_string);
	  return EXECUTION_FAILURE;	/* readonly or noassign */
	}
      array_flush (array_cell (var));

      alist = list_string (input_string, ifs_chars, 0);
      if (alist)
	{
	  if (saw_escape)
	    dequote_list (alist);
	  else
	    word_list_remove_quoted_nulls (alist);
	  assign_array_var_from_word_list (var, alist, 0);
	  dispose_words (alist);
	}
      xfree (input_string);
      return (retval);
    }
#endif /* ARRAY_VARS */ 

  /* If there are no variables, save the text of the line read to the
     variable $REPLY.  ksh93 strips leading and trailing IFS whitespace,
     so that `read x ; echo "$x"' and `read ; echo "$REPLY"' behave the
     same way, but I believe that the difference in behaviors is useful
     enough to not do it.  Without the bash behavior, there is no way
     to read a line completely without interpretation or modification
     unless you mess with $IFS (e.g., setting it to the empty string).
     If you disagree, change the occurrences of `#if 0' to `#if 1' below. */
  if (list == 0)
    {
#if 0
      orig_input_string = input_string;
      for (t = input_string; ifs_chars && *ifs_chars && spctabnl(*t) && isifs(*t); t++)
	;
      input_string = t;
      input_string = strip_trailing_ifs_whitespace (input_string, ifs_chars, saw_escape);
#endif

      if (saw_escape)
	{
	  t = dequote_string (input_string);
	  var = bind_variable ("REPLY", t, 0);
	  free (t);
	}
      else
	var = bind_variable ("REPLY", input_string, 0);
      VUNSETATTR (var, att_invisible);

      free (input_string);
      return (retval);
    }

  /* This code implements the Posix.2 spec for splitting the words
     read and assigning them to variables. */
  orig_input_string = input_string;

  /* Remove IFS white space at the beginning of the input string.  If
     $IFS is null, no field splitting is performed. */
  for (t = input_string; ifs_chars && *ifs_chars && spctabnl(*t) && isifs(*t); t++)
    ;
  input_string = t;

  for (; list->next; list = list->next)
    {
      varname = list->word->word;
#if defined (ARRAY_VARS)
      if (legal_identifier (varname) == 0 && valid_array_reference (varname) == 0)
#else
      if (legal_identifier (varname) == 0)
#endif
	{
	  sh_invalidid (varname);
	  xfree (orig_input_string);
	  return (EXECUTION_FAILURE);
	}

      /* If there are more variables than words read from the input,
	 the remaining variables are set to the empty string. */
      if (*input_string)
	{
	  /* This call updates INPUT_STRING. */
	  t = get_word_from_string (&input_string, ifs_chars, &e);
	  if (t)
	    *e = '\0';
	  /* Don't bother to remove the CTLESC unless we added one
	     somewhere while reading the string. */
	  if (t && saw_escape)
	    {
	      t1 = dequote_string (t);
	      var = bind_read_variable (varname, t1);
	      xfree (t1);
	    }
	  else
	    var = bind_read_variable (varname, t);
	}
      else
	{
	  t = (char *)0;
	  var = bind_read_variable (varname, "");
	}

      FREE (t);
      if (var == 0)
	{
	  xfree (orig_input_string);
	  return (EXECUTION_FAILURE);
	}

      stupidly_hack_special_variables (varname);
      VUNSETATTR (var, att_invisible);
    }

  /* Now assign the rest of the line to the last variable argument. */
#if defined (ARRAY_VARS)
  if (legal_identifier (list->word->word) == 0 && valid_array_reference (list->word->word) == 0)
#else
  if (legal_identifier (list->word->word) == 0)
#endif
    {
      sh_invalidid (list->word->word);
      xfree (orig_input_string);
      return (EXECUTION_FAILURE);
    }

#if 0
  /* This has to be done this way rather than using string_list
     and list_string because Posix.2 says that the last variable gets the
     remaining words and their intervening separators. */
  input_string = strip_trailing_ifs_whitespace (input_string, ifs_chars, saw_escape);
#else
  /* Check whether or not the number of fields is exactly the same as the
     number of variables. */
  if (*input_string)
    {
      t1 = input_string;
      t = get_word_from_string (&input_string, ifs_chars, &e);
      if (*input_string == 0)
	input_string = t;
      else
	input_string = strip_trailing_ifs_whitespace (t1, ifs_chars, saw_escape);
    }
#endif

  if (saw_escape)
    {
      t = dequote_string (input_string);
      var = bind_read_variable (list->word->word, t);
      xfree (t);
    }
  else
    var = bind_read_variable (list->word->word, input_string);
  stupidly_hack_special_variables (list->word->word);
  if (var)
    VUNSETATTR (var, att_invisible);
  xfree (orig_input_string);

  return (retval);
}

static SHELL_VAR *
bind_read_variable (name, value)
     char *name, *value;
{
#if defined (ARRAY_VARS)
  if (valid_array_reference (name) == 0)
    return (bind_variable (name, value, 0));
  else
    return (assign_array_element (name, value, 0));
#else /* !ARRAY_VARS */
  return bind_variable (name, value, 0);
#endif /* !ARRAY_VARS */
}

#if defined (READLINE)
static rl_completion_func_t *old_attempted_completion_function = 0;

static void
reset_attempted_completion_function (cp)
     char *cp;
{
  if (rl_attempted_completion_function == 0 && old_attempted_completion_function)
    rl_attempted_completion_function = old_attempted_completion_function;
}

static char *
edit_line (p)
     char *p;
{
  char *ret;
  int len;

  if (bash_readline_initialized == 0)
    initialize_readline ();

  old_attempted_completion_function = rl_attempted_completion_function;
  rl_attempted_completion_function = (rl_completion_func_t *)NULL;
  ret = readline (p);
  rl_attempted_completion_function = old_attempted_completion_function;
  old_attempted_completion_function = (rl_completion_func_t *)NULL;

  if (ret == 0)
    return ret;
  len = strlen (ret);
  ret = (char *)xrealloc (ret, len + 2);
  ret[len++] = delim;
  ret[len] = '\0';
  return ret;
}

static int old_delim_ctype;
static rl_command_func_t *old_delim_func;
static int old_newline_ctype;
static rl_command_func_t *old_newline_func;

static unsigned char delim_char;

static void
set_eol_delim (c)
     int c;
{
  Keymap cmap;

  if (bash_readline_initialized == 0)
    initialize_readline ();
  cmap = rl_get_keymap ();

  /* Change newline to self-insert */
  old_newline_ctype = cmap[RETURN].type;
  old_newline_func =  cmap[RETURN].function;
  cmap[RETURN].type = ISFUNC;
  cmap[RETURN].function = rl_insert;

  /* Bind the delimiter character to accept-line. */
  old_delim_ctype = cmap[c].type;
  old_delim_func = cmap[c].function;
  cmap[c].type = ISFUNC;
  cmap[c].function = rl_newline;

  delim_char = c;
}

static void
reset_eol_delim (cp)
     char *cp;
{
  Keymap cmap;

  cmap = rl_get_keymap ();

  cmap[RETURN].type = old_newline_ctype;
  cmap[RETURN].function = old_newline_func;

  cmap[delim_char].type = old_delim_ctype;
  cmap[delim_char].function = old_delim_func;
}
#endif