reader.c

含有BACKTARACKING的編譯軟體

    register bucket *bp;
    int s_lineno = lineno;
    char *s_line = dup_line();
    char *s_cptr = s_line + (cptr - line);

    quote = *cptr++;
    cinc = 0;
    for (;;)
    {
	c = *cptr++;
	if (c == quote) break;
	if (c == '\n') unterminated_string(s_lineno, s_line, s_cptr);
	if (c == '\\')
	{
	    char *c_cptr = cptr - 1;

	    c = *cptr++;
	    switch (c)
	    {
	    case '\n':
		get_line();
		if (line == 0) unterminated_string(s_lineno, s_line, s_cptr);
		continue;

	    case '0': case '1': case '2': case '3':
	    case '4': case '5': case '6': case '7':
		n = c - '0';
		c = *cptr;
		if (IS_OCTAL(c))
		{
		    n = (n << 3) + (c - '0');
		    c = *++cptr;
		    if (IS_OCTAL(c))
		    {
			n = (n << 3) + (c - '0');
			++cptr;
		    }
		}
		if (n > MAXCHAR) illegal_character(c_cptr);
		c = n;
	    	break;

	    case 'x':
		c = *cptr++;
		n = hexval(c);
		if (n < 0 || n >= 16)
		    illegal_character(c_cptr);
		for (;;)
		{
		    c = *cptr;
		    i = hexval(c);
		    if (i < 0 || i >= 16) break;
		    ++cptr;
		    n = (n << 4) + i;
		    if (n > MAXCHAR) illegal_character(c_cptr);
		}
		c = n;
		break;

	    case 'a': c = 7; break;
	    case 'b': c = '\b'; break;
	    case 'f': c = '\f'; break;
	    case 'n': c = '\n'; break;
	    case 'r': c = '\r'; break;
	    case 't': c = '\t'; break;
	    case 'v': c = '\v'; break;
	    }
	}
	cachec(c);
    }
    FREE(s_line);

    n = cinc;
    s = MALLOC(n);
    if (s == 0) no_space();
    
    for (i = 0; i < n; ++i)
	s[i] = cache[i];

    cinc = 0;
    if (n == 1)
	cachec('\'');
    else
	cachec('"');

    for (i = 0; i < n; ++i)
    {
	c = ((unsigned char *)s)[i];
	if (c == '\\' || c == cache[0])
	{
	    cachec('\\');
	    cachec(c);
	}
	else if (isprint(c))
	    cachec(c);
	else
	{
	    cachec('\\');
	    switch (c)
	    {
	    case 7: cachec('a'); break;
	    case '\b': cachec('b'); break;
	    case '\f': cachec('f'); break;
	    case '\n': cachec('n'); break;
	    case '\r': cachec('r'); break;
	    case '\t': cachec('t'); break;
	    case '\v': cachec('v'); break;
	    default:
		cachec(((c >> 6) & 7) + '0');
		cachec(((c >> 3) & 7) + '0');
		cachec((c & 7) + '0');
		break;
	    }
	}
    }

    if (n == 1)
	cachec('\'');
    else
	cachec('"');

    cachec(NUL);
    bp = lookup(cache);
    bp->class = TERM;
    if (n == 1 && bp->value == UNDEFINED)
	bp->value = *(unsigned char *)s;
    FREE(s);

    return (bp);
}


int
is_reserved(char *name)
{
    char *s;

    if (strcmp(name, ".") == 0 ||
	    strcmp(name, "$accept") == 0 ||
	    strcmp(name, "$end") == 0)
	return (1);

    if (name[0] == '$' && name[1] == '$' && isdigit(name[2]))
    {
	s = name + 3;
	while (isdigit(*s)) ++s;
	if (*s == NUL) return (1);
    }

    return (0);
}


bucket *
get_name(void)
{
    register int c;

    cinc = 0;
    for (c = *cptr; IS_IDENT(c); c = *++cptr)
	cachec(c);
    cachec(NUL);

    if (is_reserved(cache)) used_reserved(cache);

    return (lookup(cache));
}


int
get_number(void)
{
    register int c;
    register int n;

    n = 0;
    for (c = *cptr; isdigit(c); c = *++cptr)
	n = 10*n + (c - '0');

    return (n);
}


char *
get_tag(void)
{
    register int c;
    register int i;
    register char *s;
    int t_lineno = lineno;
    char *t_line = dup_line();
    char *t_cptr = t_line + (cptr - line);

    ++cptr;
    c = nextc();
    if (c == EOF) unexpected_EOF();
    if (!isalpha(c) && c != '_' && c != '$')
	illegal_tag(t_lineno, t_line, t_cptr);

    cinc = 0;
    do { cachec(c); c = *++cptr; } while (IS_IDENT(c));
    cachec(NUL);

    c = nextc();
    if (c == EOF) unexpected_EOF();
    if (c != '>')
	illegal_tag(t_lineno, t_line, t_cptr);
    ++cptr;

    for (i = 0; i < ntags; ++i)
    {
	if (strcmp(cache, tag_table[i]) == 0)
	    return (tag_table[i]);
    }

    if (ntags >= tagmax)
    {
	tagmax += 16;
	tag_table = (char **)
			(tag_table ? REALLOC(tag_table, tagmax*sizeof(char *))
				   : MALLOC(tagmax*sizeof(char *)));
	if (tag_table == 0) no_space();
    }

    s = MALLOC(cinc);
    if  (s == 0) no_space();
    strcpy(s, cache);
    tag_table[ntags] = s;
    ++ntags;
    FREE(t_line);
    return (s);
}


void declare_tokens(int assoc)
{
    register int c;
    register bucket *bp;
    int value;
    char *tag = 0;

    if (assoc != TOKEN) ++prec;

    c = nextc();
    if (c == EOF) unexpected_EOF();
    if (c == '<')
    {
	tag = get_tag();
	c = nextc();
	if (c == EOF) unexpected_EOF();
    }

    for (;;)
    {
	if (isalpha(c) || c == '_' || c == '.' || c == '$')
	    bp = get_name();
	else if (c == '\'' || c == '"')
	    bp = get_literal();
	else
	    return;

	if (bp == goal) tokenized_start(bp->name);
	bp->class = TERM;

	if (tag)
	{
	    if (bp->tag && tag != bp->tag)
		retyped_warning(bp->name);
	    bp->tag = tag;
	}

	if (assoc != TOKEN)
	{
	    if (bp->prec && prec != bp->prec)
		reprec_warning(bp->name);
	    bp->assoc = assoc;
	    bp->prec = prec;
	}

	c = nextc();
	if (c == EOF) unexpected_EOF();
	value = UNDEFINED;
	if (isdigit(c))
	{
	    value = get_number();
	    if (bp->value != UNDEFINED && value != bp->value)
		revalued_warning(bp->name);
	    bp->value = value;
	    c = nextc();
	    if (c == EOF) unexpected_EOF();
	}
    }
}


void declare_types(void)
{
    register int c;
    register bucket *bp;
    char *tag;

    c = nextc();
    if (c == EOF) unexpected_EOF();
    if (c != '<') syntax_error(lineno, line, cptr);
    tag = get_tag();

    for (;;)
    {
	c = nextc();
	if (isalpha(c) || c == '_' || c == '.' || c == '$')
	    bp = get_name();
	else if (c == '\'' || c == '"')
	    bp = get_literal();
	else
	    return;

	if (bp->tag && tag != bp->tag)
	    retyped_warning(bp->name);
	bp->tag = tag;
    }
}


void declare_start(void)
{
    register int c;
    register bucket *bp;

    c = nextc();
    if (c == EOF) unexpected_EOF();
    if (!isalpha(c) && c != '_' && c != '.' && c != '$')
	syntax_error(lineno, line, cptr);
    bp = get_name();
    if (bp->class == TERM)
	terminal_start(bp->name);
    if (goal && goal != bp)
	restarted_warning();
    goal = bp;
}


void read_declarations(void)
{
    register int c, k;

    cache_size = 256;
    cache = MALLOC(cache_size);
    if (cache == 0) no_space();

    for (;;)
    {
	c = nextc();
	if (c == EOF) unexpected_EOF();
	if (c != '%') syntax_error(lineno, line, cptr);
	switch (k = keyword())
	{
	case MARK:
	    return;

	case IDENT:
	    copy_ident();
	    break;

	case TEXT:
	    copy_text();
	    break;

	case UNION:
	    copy_union();
	    break;

	case TOKEN:
	case LEFT:
	case RIGHT:
	case NONASSOC:
	    declare_tokens(k);
	    break;

	case TYPE:
	    declare_types();
	    break;

	case START:
	    declare_start();
	    break;
	}
    }
}


void initialize_grammar(void)
{
    nitems = 4;
    maxitems = 300;
    pitem = (bucket **) MALLOC(maxitems*sizeof(bucket *));
    if (pitem == 0) no_space();
    pitem[0] = 0;
    pitem[1] = 0;
    pitem[2] = 0;
    pitem[3] = 0;

    nrules = 3;
    maxrules = 100;
    plhs = (bucket **) MALLOC(maxrules*sizeof(bucket *));
    if (plhs == 0) no_space();
    plhs[0] = 0;
    plhs[1] = 0;
    plhs[2] = 0;
    rprec = (short *) MALLOC(maxrules*sizeof(short));
    if (rprec == 0) no_space();
    rprec[0] = 0;
    rprec[1] = 0;
    rprec[2] = 0;
    rassoc = (char *) MALLOC(maxrules*sizeof(char));
    if (rassoc == 0) no_space();
    rassoc[0] = TOKEN;
    rassoc[1] = TOKEN;
    rassoc[2] = TOKEN;
}


void expand_items(void)
{
    maxitems += 300;
    pitem = (bucket **) REALLOC(pitem, maxitems*sizeof(bucket *));
    if (pitem == 0) no_space();
}


void expand_rules(void)
{
    maxrules += 100;
    plhs = (bucket **) REALLOC(plhs, maxrules*sizeof(bucket *));
    if (plhs == 0) no_space();
    rprec = (short *) REALLOC(rprec, maxrules*sizeof(short));
    if (rprec == 0) no_space();
    rassoc = (char *) REALLOC(rassoc, maxrules*sizeof(char));
    if (rassoc == 0) no_space();
}


void advance_to_start(void)
{
    register int c;
    register bucket *bp;
    char *s_cptr;
    int s_lineno;

    for (;;)
    {
	c = nextc();
	if (c != '%') break;
	s_cptr = cptr;
	switch (keyword())
	{
	case MARK:
	    no_grammar();

	case TEXT:
	    copy_text();
	    break;

	case START:
	    declare_start();
	    break;

	default:
	    syntax_error(lineno, line, s_cptr);
	}
    }

    c = nextc();
    if (!isalpha(c) && c != '_' && c != '.' && c != '_')
	syntax_error(lineno, line, cptr);
    bp = get_name();
    if (goal == 0)
    {
	if (bp->class == TERM)
	    terminal_start(bp->name);
	goal = bp;
    }

    s_lineno = lineno;
    c = nextc();
    if (c == EOF) unexpected_EOF();
    if (c != ':') syntax_error(lineno, line, cptr);
    start_rule(bp, s_lineno);
    ++cptr;
}


void start_rule(register bucket *bp, int s_lineno)
{
    if (bp->class == TERM)
	terminal_lhs(s_lineno);
    bp->class = NONTERM;
    if (nrules >= maxrules)
	expand_rules();
    plhs[nrules] = bp;
    rprec[nrules] = UNDEFINED;
    rassoc[nrules] = TOKEN;
}


void end_rule(void)
{
    register int i;

    if (!last_was_action && plhs[nrules]->tag)
    {
	for (i = nitems - 1; pitem[i]; --i) continue;
	if (pitem[i+1] == 0 || pitem[i+1]->tag != plhs[nrules]->tag)
	    default_action_warning();
    }

    last_was_action = 0;
    if (nitems >= maxitems) expand_items();
    pitem[nitems] = 0;
    ++nitems;
    ++nrules;
}


void insert_empty_rule(void)
{
    register bucket *bp, **bpp;

    assert(cache);
    sprintf(cache, "$$%d", ++gensym);
    bp = make_bucket(cache);
    last_symbol->next = bp;
    last_symbol = bp;
    bp->tag = plhs[nrules]->tag;
    bp->class = NONTERM;

    if ((nitems += 2) > maxitems)
	expand_items();
    bpp = pitem + nitems - 1;
    *bpp-- = bp;
    while ((bpp[0] = bpp[-1]) != 0) --bpp;

    if (++nrules >= maxrules)
	expand_rules();
    plhs[nrules] = plhs[nrules-1];
    plhs[nrules-1] = bp;
    rprec[nrules] = rprec[nrules-1];
    rprec[nrules-1] = 0;
    rassoc[nrules] = rassoc[nrules-1];
    rassoc[nrules-1] = TOKEN;
}


void add_symbol(void)
{
    register int c;
    register bucket *bp;
    int s_lineno = lineno;

    c = *cptr;
    if (c == '\'' || c == '"')
	bp = get_literal();
    else
	bp = get_name();

    c = nextc();
    if (c == ':')
    {
	end_rule();
	start_rule(bp, s_lineno);
	++cptr;
	return;
    }

    if (last_was_action)
	insert_empty_rule();
    last_was_action = 0;

    if (++nitems > maxitems)
	expand_items();
    pitem[nitems-1] = bp;
}


void copy_action(void)
{
    register int c;
    register int i, n;
    int depth;
    int quote;