comparison src/syntax.c @ 29835:5dec8ee96c0c

(back_comment): Simplify string-parity counting (with the added benefit of handling multiple string-styles as long as they are not nested). Jump to the slow code as soon as a comment starter is found in a "string_lossage" position. Fixes the case: " /* " /* " */.

29834:fb20d35ffa9a

     an even number of string quotes away from the safe place.

     OFROM[I] is position of the earliest comment-starter seen
     which is I+2X quotes from the comment-end.
     PARITY is current parity of quotes from the comment end.  */
  int parity = 0;
  int my_stringend = 0;
  int string_lossage = 0;
  int comment_end = from;
  int comment_end_byte = from_byte;
  int comstart_pos = 0;
  int comstart_byte;
  /* Value that PARITY had, when we reached the position
     in COMSTART_POS.  */
  int comstart_parity = 0;
  int scanstart = from - 1;
  /* Place where the containing defun starts,
     or 0 if we didn't come across it yet.  */
  int defun_start = 0;
  int defun_start_byte = 0;

      /* Ignore escaped characters, except comment-enders.  */
      if (code != Sendcomment && char_quoted (from, from_byte))
	continue;

      /* Track parity of quotes.  */
      if (code == Sstring)
	{
	  parity ^= 1;
	  if (my_stringend == 0)
	    my_stringend = c;
	  /* If we have two kinds of string delimiters.
	     There's no way to grok this scanning backwards.  */
	  else if (my_stringend != c)
	    string_lossage = 1;
	}

      if (code == Sstring_fence || code == Scomment_fence)
	{
	  parity ^= 1;
	  if (my_stringend == 0)
	    my_stringend
	      = code == Sstring_fence ? ST_STRING_STYLE : ST_COMMENT_STYLE;
	  /* If we have two kinds of string delimiters.
	     There's no way to grok this scanning backwards.  */
	  else if (my_stringend != (code == Sstring_fence 
				    ? ST_STRING_STYLE : ST_COMMENT_STYLE))
	    string_lossage = 1;
	}

      if (code == Scomment)
	/* We've already checked that it is the relevant comstyle.  */
	{
	  if (comnested && --nesting <= 0 && parity == 0 && !string_lossage)
	    /* nested comments have to be balanced, so we don't need to
	       keep looking for earlier ones.  We use here the same (slightly
	       incorrect) reasoning as below:  since it is followed by uniform
	       paired string quotes, this comment-start has to be outside of
	       strings, else the comment-end itself would be inside a string. */
	    goto done;

	  /* Record comment-starters according to that
	     quote-parity to the comment-end.  */
	  comstart_parity = parity;
	  comstart_pos = from;
	  comstart_byte = from_byte;
	}

      /* If we find another earlier comment-ender,
	 any comment-starts earlier than that don't count
	 (because they go with the earlier comment-ender).  */

  /* If the earliest comment starter
     is followed by uniform paired string quotes or none,
     we know it can't be inside a string
     since if it were then the comment ender would be inside one.
     So it does start a comment.  Skip back to it.  */
  else if (!comnested && comstart_parity == 0 && !string_lossage) 
    {
      from = comstart_pos;
      from_byte = comstart_byte;
      /* Globals are correct now.  */
    }
  else
    {
      /* We had two kinds of string delimiters mixed up
	 together.  Decode this going forwards.
	 Scan fwd from the previous comment ender
	 to the one in question; this records where we
	 last passed a comment starter.  */
      struct lisp_parse_state state;
      /* If we did not already find the defun start, find it now.  */
      if (defun_start == 0)
	{
	  defun_start = find_defun_start (comment_end, comment_end_byte);
	  defun_start_byte = find_start_value_byte;

29835:5dec8ee96c0c

     an even number of string quotes away from the safe place.

     OFROM[I] is position of the earliest comment-starter seen
     which is I+2X quotes from the comment-end.
     PARITY is current parity of quotes from the comment end.  */
  int string_style = -1;	/* Presumed outside of any string. */
  int string_lossage = 0;
  int comment_end = from;
  int comment_end_byte = from_byte;
  int comstart_pos = 0;
  int comstart_byte;
  /* Value that PARITY had, when we reached the position
     in COMSTART_POS.  */
  int scanstart = from - 1;
  /* Place where the containing defun starts,
     or 0 if we didn't come across it yet.  */
  int defun_start = 0;
  int defun_start_byte = 0;

      /* Ignore escaped characters, except comment-enders.  */
      if (code != Sendcomment && char_quoted (from, from_byte))
	continue;

      /* Track parity of quotes.  */
      switch (code)
	{
	case Sstring_fence:
	case Scomment_fence:
	  c = (code == Sstring_fence ? ST_STRING_STYLE : ST_COMMENT_STYLE);
	case Sstring:
	  /* Track parity of quotes.  */
	  if (string_style == -1)
	    /* Entering a string.  */
	    string_style = c;
	  else if (string_style == c)
	    /* Leaving the string.  */
	    string_style = -1;
	  else
	    /* If we have two kinds of string delimiters.
	       There's no way to grok this scanning backwards.  */
	    string_lossage = 1;
	  break;
	  
	case Scomment:
	  /* We've already checked that it is the relevant comstyle.  */
	  if (string_style != -1 || string_lossage)
	    /* There are odd string quotes involved, so let's be careful.
	       Test case in Pascal: " { " a { " } */
	    goto lossage;

	  if (comnested && --nesting <= 0)
	    /* nested comments have to be balanced, so we don't need to
	       keep looking for earlier ones.  We use here the same (slightly
	       incorrect) reasoning as below:  since it is followed by uniform
	       paired string quotes, this comment-start has to be outside of
	       strings, else the comment-end itself would be inside a string. */
	    goto done;

	  /* Record comment-starters according to that
	     quote-parity to the comment-end.  */
	  comstart_pos = from;
	  comstart_byte = from_byte;
	  break;

	default:
	  ;
	}

      /* If we find another earlier comment-ender,
	 any comment-starts earlier than that don't count
	 (because they go with the earlier comment-ender).  */

  /* If the earliest comment starter
     is followed by uniform paired string quotes or none,
     we know it can't be inside a string
     since if it were then the comment ender would be inside one.
     So it does start a comment.  Skip back to it.  */
  else if (!comnested)
    {
      from = comstart_pos;
      from_byte = comstart_byte;
      /* Globals are correct now.  */
    }
  else
    {
      struct lisp_parse_state state;
    lossage:
      /* We had two kinds of string delimiters mixed up
	 together.  Decode this going forwards.
	 Scan fwd from the previous comment ender
	 to the one in question; this records where we
	 last passed a comment starter.  */
      /* If we did not already find the defun start, find it now.  */
      if (defun_start == 0)
	{
	  defun_start = find_defun_start (comment_end, comment_end_byte);
	  defun_start_byte = find_start_value_byte;