dfa.c

早期freebsd实现

/* dfa.c - determinisitic extended regexp routines for GNU
   Copyright (C) 1988 Free Software Foundation, Inc.
                      Written June, 1988 by Mike Haertel
		      Modified July, 1988 by Arthur David Olson
			 to assist BMG speedups

		       NO WARRANTY

  BECAUSE THIS PROGRAM IS LICENSED FREE OF CHARGE, WE PROVIDE ABSOLUTELY
NO WARRANTY, TO THE EXTENT PERMITTED BY APPLICABLE STATE LAW.  EXCEPT
WHEN OTHERWISE STATED IN WRITING, FREE SOFTWARE FOUNDATION, INC,
RICHARD M. STALLMAN AND/OR OTHER PARTIES PROVIDE THIS PROGRAM "AS IS"
WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING,
BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND
FITNESS FOR A PARTICULAR PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY
AND PERFORMANCE OF THE PROGRAM IS WITH YOU.  SHOULD THE PROGRAM PROVE
DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, REPAIR OR
CORRECTION.

 IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW WILL RICHARD M.
STALLMAN, THE FREE SOFTWARE FOUNDATION, INC., AND/OR ANY OTHER PARTY
WHO MAY MODIFY AND REDISTRIBUTE THIS PROGRAM AS PERMITTED BELOW, BE
LIABLE TO YOU FOR DAMAGES, INCLUDING ANY LOST PROFITS, LOST MONIES, OR
OTHER SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
USE OR INABILITY TO USE (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR
DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY THIRD PARTIES OR
A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS) THIS
PROGRAM, EVEN IF YOU HAVE BEEN ADVISED OF THE POSSIBILITY OF SUCH
DAMAGES, OR FOR ANY CLAIM BY ANY OTHER PARTY.

		GENERAL PUBLIC LICENSE TO COPY

  1. You may copy and distribute verbatim copies of this source file
as you receive it, in any medium, provided that you conspicuously and
appropriately publish on each copy a valid copyright notice "Copyright
 (C) 1988 Free Software Foundation, Inc."; and include following the
copyright notice a verbatim copy of the above disclaimer of warranty
and of this License.  You may charge a distribution fee for the
physical act of transferring a copy.

  2. You may modify your copy or copies of this source file or
any portion of it, and copy and distribute such modifications under
the terms of Paragraph 1 above, provided that you also do the following:

    a) cause the modified files to carry prominent notices stating
    that you changed the files and the date of any change; and

    b) cause the whole of any work that you distribute or publish,
    that in whole or in part contains or is a derivative of this
    program or any part thereof, to be licensed at no charge to all
    third parties on terms identical to those contained in this
    License Agreement (except that you may choose to grant more extensive
    warranty protection to some or all third parties, at your option).

    c) You may charge a distribution fee for the physical act of
    transferring a copy, and you may at your option offer warranty
    protection in exchange for a fee.

Mere aggregation of another unrelated program with this program (or its
derivative) on a volume of a storage or distribution medium does not bring
the other program under the scope of these terms.

  3. You may copy and distribute this program or any portion of it in
compiled, executable or object code form under the terms of Paragraphs
1 and 2 above provided that you do the following:

    a) accompany it with the complete corresponding machine-readable
    source code, which must be distributed under the terms of
    Paragraphs 1 and 2 above; or,

    b) accompany it with a written offer, valid for at least three
    years, to give any third party free (except for a nominal
    shipping charge) a complete machine-readable copy of the
    corresponding source code, to be distributed under the terms of
    Paragraphs 1 and 2 above; or,

    c) accompany it with the information you received as to where the
    corresponding source code may be obtained.  (This alternative is
    allowed only for noncommercial distribution and only if you
    received the program in object code or executable form alone.)

For an executable file, complete source code means all the source code for
all modules it contains; but, as a special exception, it need not include
source code for modules which are standard libraries that accompany the
operating system on which the executable file runs.

  4. You may not copy, sublicense, distribute or transfer this program
except as expressly provided under this License Agreement.  Any attempt
otherwise to copy, sublicense, distribute or transfer this program is void and
your rights to use the program under this License agreement shall be
automatically terminated.  However, parties who have received computer
software programs from you with this License Agreement will not have
their licenses terminated so long as such parties remain in full compliance.

  5. If you wish to incorporate parts of this program into other free
programs whose distribution conditions are different, write to the Free
Software Foundation at 675 Mass Ave, Cambridge, MA 02139.  We have not yet
worked out a simple rule that can be stated here, but we will often permit
this.  We will be guided by the two goals of preserving the free status of
all derivatives our free software and of promoting the sharing and reuse of
software.


In other words, you are welcome to use, share and improve this program.
You are forbidden to forbid anyone else to use, share and improve
what you give them.   Help stamp out software-hoarding!  */

#include "awk.h"
#include <assert.h>

#ifdef setbit  /* surprise - setbit and clrbit are macros on NeXT */
#undef setbit
#endif
#ifdef clrbit
#undef clrbit
#endif

#ifdef __STDC__
typedef void *ptr_t;
#else
typedef char *ptr_t;
#endif

typedef struct {
	char **	in;
	char *	left;
	char *	right;
	char *	is;
} must;

static ptr_t xcalloc P((int n, size_t s));
static ptr_t xmalloc P((size_t n));
static ptr_t xrealloc P((ptr_t p, size_t n));
static int tstbit P((int b, _charset c));
static void setbit P((int b, _charset c));
static void clrbit P((int b, _charset c));
static void copyset P((const _charset src, _charset dst));
static void zeroset P((_charset s));
static void notset P((_charset s));
static int equal P((const _charset s1, const _charset s2));
static int charset_index P((const _charset s));
static _token lex P((void));
static void addtok P((_token t));
static void atom P((void));
static void closure P((void));
static void branch P((void));
static void regexp P((void));
static void copy P((const _position_set *src, _position_set *dst));
static void insert P((_position p, _position_set *s));
static void merge P((_position_set *s1, _position_set *s2, _position_set *m));
static void delete P((_position p, _position_set *s));
static int state_index P((struct regexp *r, _position_set *s,
			  int newline, int letter));
static void epsclosure P((_position_set *s, struct regexp *r));
static void build_state P((int s, struct regexp *r));
static void build_state_zero P((struct regexp *r));
static char *icatalloc P((char *old, const char *new));
static char *icpyalloc P((const char *string));
static char *istrstr P((char *lookin, char *lookfor));
static void ifree P((char *cp));
static void freelist P((char **cpp));
static char **enlist P((char **cpp, char *new, size_t len));
static char **comsubs P((char *left, char *right));
static char **addlists P((char **old, char **new));
static char **inboth P((char **left, char **right));
static void resetmust P((must *mp));
static void regmust P((struct regexp *r));

#undef P

static ptr_t
xcalloc(n, s)
     int n;
     size_t s;
{
  ptr_t r = calloc(n, s);

  if (NULL == r)
    reg_error("Memory exhausted");  /* reg_error does not return */
  return r;
}

static ptr_t
xmalloc(n)
     size_t n;
{
  ptr_t r = malloc(n);

  assert(n != 0);
  if (NULL == r)
    reg_error("Memory exhausted");
  return r;
}

static ptr_t
xrealloc(p, n)
     ptr_t p;
     size_t n;
{
  ptr_t r = realloc(p, n);

  assert(n != 0);
  if (NULL == r)
    reg_error("Memory exhausted");
  return r;
}

#define CALLOC(p, t, n) ((p) = (t *) xcalloc((n), sizeof (t)))
#undef MALLOC
#define MALLOC(p, t, n) ((p) = (t *) xmalloc((n) * sizeof (t)))
#define REALLOC(p, t, n) ((p) = (t *) xrealloc((ptr_t) (p), (n) * sizeof (t)))

/* Reallocate an array of type t if nalloc is too small for index. */
#define REALLOC_IF_NECESSARY(p, t, nalloc, index) \
  if ((index) >= (nalloc))			  \
    {						  \
      while ((index) >= (nalloc))		  \
	(nalloc) *= 2;				  \
      REALLOC(p, t, nalloc);			  \
    }

/* Stuff pertaining to charsets. */

static int
tstbit(b, c)
     int b;
     _charset c;
{
  return c[b / INTBITS] & 1 << b % INTBITS;
}

static void
setbit(b, c)
     int b;
     _charset c;
{
  c[b / INTBITS] |= 1 << b % INTBITS;
}

static void
clrbit(b, c)
     int b;
     _charset c;
{
  c[b / INTBITS] &= ~(1 << b % INTBITS);
}

static void
copyset(src, dst)
     const _charset src;
     _charset dst;
{
  int i;

  for (i = 0; i < _CHARSET_INTS; ++i)
    dst[i] = src[i];
}

static void
zeroset(s)
     _charset s;
{
  int i;

  for (i = 0; i < _CHARSET_INTS; ++i)
    s[i] = 0;
}

static void
notset(s)
     _charset s;
{
  int i;

  for (i = 0; i < _CHARSET_INTS; ++i)
    s[i] = ~s[i];
}

static int
equal(s1, s2)
     const _charset s1;
     const _charset s2;
{
  int i;

  for (i = 0; i < _CHARSET_INTS; ++i)
    if (s1[i] != s2[i])
      return 0;
  return 1;
}

/* A pointer to the current regexp is kept here during parsing. */
static struct regexp *reg;

/* Find the index of charset s in reg->charsets, or allocate a new charset. */
static int
charset_index(s)
     const _charset s;
{
  int i;

  for (i = 0; i < reg->cindex; ++i)
    if (equal(s, reg->charsets[i]))
      return i;
  REALLOC_IF_NECESSARY(reg->charsets, _charset, reg->calloc, reg->cindex);
  ++reg->cindex;
  copyset(s, reg->charsets[i]);
  return i;
}

/* Syntax bits controlling the behavior of the lexical analyzer. */
static syntax_bits, syntax_bits_set;

/* Flag for case-folding letters into sets. */
static case_fold;

/* Entry point to set syntax options. */
void
regsyntax(bits, fold)
     long bits;
     int fold;
{
  syntax_bits_set = 1;
  syntax_bits = bits;
  case_fold = fold;
}

/* Lexical analyzer. */
static const char *lexstart;	/* Pointer to beginning of input string. */
static const char *lexptr;	/* Pointer to next input character. */
static lexleft;			/* Number of characters remaining. */
static caret_allowed;		/* True if backward context allows ^
				   (meaningful only if RE_CONTEXT_INDEP_OPS
				   is turned off). */
static closure_allowed;		/* True if backward context allows closures
				   (meaningful only if RE_CONTEXT_INDEP_OPS
				   is turned off). */

/* Note that characters become unsigned here. */
#define FETCH(c, eoferr)   	      \
  {			   	      \
    if (! lexleft)	   	      \
      if (eoferr != NULL)   	      \
	reg_error(eoferr);  	      \
      else		   	      \
	return _END;	   	      \
    (c) = (unsigned char) *lexptr++;  \
    --lexleft;		   	      \
  }

static _token
lex()
{
  _token c, c2;
  int invert;
  _charset cset;

  FETCH(c, (char *) 0);
  switch (c)
    {
    case '^':
      if (! (syntax_bits & RE_CONTEXT_INDEP_OPS)
	  && (!caret_allowed ||
	      ((syntax_bits & RE_TIGHT_VBAR) && lexptr - 1 != lexstart)))
	goto normal_char;
      caret_allowed = 0;
      return syntax_bits & RE_TIGHT_VBAR ? _ALLBEGLINE : _BEGLINE;

    case '$':
      if (syntax_bits & RE_CONTEXT_INDEP_OPS || !lexleft
	  || (! (syntax_bits & RE_TIGHT_VBAR)
	      && ((syntax_bits & RE_NO_BK_PARENS
		   ? lexleft > 0 && *lexptr == ')'
		   : lexleft > 1 && *lexptr == '\\' && lexptr[1] == ')')
		  || (syntax_bits & RE_NO_BK_VBAR
		      ? lexleft > 0 && *lexptr == '|'
		      : lexleft > 1 && *lexptr == '\\' && lexptr[1] == '|'))))
	return syntax_bits & RE_TIGHT_VBAR ? _ALLENDLINE : _ENDLINE;
      goto normal_char;

    case '\\':
      FETCH(c, "Unfinished \\ quote");
      switch (c)
	{
	case '1':
	case '2':
	case '3':
	case '4':
	case '5':
	case '6':
	case '7':
	case '8':
	case '9':
	  caret_allowed = 0;
	  closure_allowed = 1;
	  return _BACKREF;

	case '<':
	  caret_allowed = 0;
	  return _BEGWORD;

	case '>':
	  caret_allowed = 0;
	  return _ENDWORD;

	case 'b':
	  caret_allowed = 0;
	  return _LIMWORD;

	case 'B':
	  caret_allowed = 0;
	  return _NOTLIMWORD;

	case 'w':
	case 'W':
	  zeroset(cset);
	  for (c2 = 0; c2 < _NOTCHAR; ++c2)
	    if (ISALNUM(c2))
	      setbit(c2, cset);
	  if (c == 'W')
	    notset(cset);
	  caret_allowed = 0;
	  closure_allowed = 1;
	  return _SET + charset_index(cset);

	case '?':
	  if (syntax_bits & RE_BK_PLUS_QM)
	    goto qmark;
	  goto normal_char;

	case '+':
	  if (syntax_bits & RE_BK_PLUS_QM)
	    goto plus;
	  goto normal_char;

	case '|':
	  if (! (syntax_bits & RE_NO_BK_VBAR))
	    goto or;
	  goto normal_char;

	case '(':
	  if (! (syntax_bits & RE_NO_BK_PARENS))
	    goto lparen;
	  goto normal_char;

	case ')':
	  if (! (syntax_bits & RE_NO_BK_PARENS))
	    goto rparen;
	  goto normal_char;

	default:
	  goto normal_char;
	}

    case '?':
      if (syntax_bits & RE_BK_PLUS_QM)
	goto normal_char;
    qmark:
      if (! (syntax_bits & RE_CONTEXT_INDEP_OPS) && !closure_allowed)
	goto normal_char;
      return _QMARK;

    case '*':
      if (! (syntax_bits & RE_CONTEXT_INDEP_OPS) && !closure_allowed)
	goto normal_char;
      return _STAR;

    case '+':
      if (syntax_bits & RE_BK_PLUS_QM)
	goto normal_char;
    plus:
      if (! (syntax_bits & RE_CONTEXT_INDEP_OPS) && !closure_allowed)
	goto normal_char;
      return _PLUS;

    case '|':
      if (! (syntax_bits & RE_NO_BK_VBAR))
	goto normal_char;
    or:
      caret_allowed = 1;
      closure_allowed = 0;
      return _OR;

    case '\n':
      if (! (syntax_bits & RE_NEWLINE_OR))
	goto normal_char;
      goto or;

    case '(':
      if (! (syntax_bits & RE_NO_BK_PARENS))
	goto normal_char;
    lparen:
      caret_allowed = 1;
      closure_allowed = 0;
      return _LPAREN;

    case ')':
      if (! (syntax_bits & RE_NO_BK_PARENS))
	goto normal_char;
    rparen:
      caret_allowed = 0;
      closure_allowed = 1;
      return _RPAREN;

    case '.':
      zeroset(cset);
      notset(cset);
      clrbit('\n', cset);
      caret_allowed = 0;
      closure_allowed = 1;
      return _SET + charset_index(cset);

    case '[':
      zeroset(cset);
      FETCH(c, "Unbalanced [");
      if (c == '^')
	{
	  FETCH(c, "Unbalanced [");
	  invert = 1;
	}
      else
	invert = 0;
      do
	{
	  FETCH(c2, "Unbalanced [");
	  if ((syntax_bits & RE_AWK_CLASS_HACK) && c == '\\')
	    {
	      c = c2;
	      FETCH(c2, "Unbalanced [");
	    }
	  if (c2 == '-')
	    {
	      FETCH(c2, "Unbalanced [");
	      if (c2 == ']' && (syntax_bits & RE_AWK_CLASS_HACK))
		{
		  setbit(c, cset);
		  setbit('-', cset);
		  break;
	        }
	      while (c <= c2)
		  setbit(c++, cset);
	      FETCH(c, "Unbalanced [");
	    }
	  else
	    {
	      setbit(c, cset);
	      c = c2;
	    }
	}
      while (c != ']');
      if (invert)
	notset(cset);
      caret_allowed = 0;
      closure_allowed = 1;
      return _SET + charset_index(cset);

    default:
    normal_char:
      caret_allowed = 0;
      closure_allowed = 1;
      if (case_fold && ISALPHA(c))
	{
	  zeroset(cset);
	  if (isupper(c))
	    c = tolower(c);
	  setbit(c, cset);
	  setbit(toupper(c), cset);
	  return _SET + charset_index(cset);
	}
      return c;
    }
}