reader.c

操作系统源代码

#include "defs.h"

/*  The line size must be a positive integer.  One hundred was chosen	*/
/*  because few lines in Yacc input grammars exceed 100 characters.	*/
/*  Note that if a line exceeds LINESIZE characters, the line buffer	*/
/*  will be expanded to accomodate it.					*/

#define LINESIZE 100

char *cache;
int cinc, cache_size;

int ntags, tagmax;
char **tag_table;

char saw_eof, unionized;
char *cptr, *line;
int linesize;

bucket *goal;
int prec;
int gensym;
char last_was_action;

int maxitems;
bucket **pitem;

int maxrules;
bucket **plhs;

int name_pool_size;
char *name_pool;

char line_format[] = "#line %d \"%s\"\n";


cachec(c)
int c;
{
    assert(cinc >= 0);
    if (cinc >= cache_size)
    {
	cache_size += 256;
	cache = REALLOC(cache, cache_size);
	if (cache == 0) no_space();
    }
    cache[cinc] = c;
    ++cinc;
}


get_line()
{
    register FILE *f = input_file;
    register int c;
    register int i;

    if (saw_eof || (c = getc(f)) == EOF)
    {
	if (line) { FREE(line); line = 0; }
	cptr = 0;
	saw_eof = 1;
	return;
    }

    if (line == 0 || linesize != (LINESIZE + 1))
    {
	if (line) FREE(line);
	linesize = LINESIZE + 1;
	line = MALLOC(linesize);
	if (line == 0) no_space();
    }

    i = 0;
    ++lineno;
    for (;;)
    {
	line[i]  =  c;
	if (c == '\n') { cptr = line; return; }
	if (++i >= linesize)
	{
	    linesize += LINESIZE;
	    line = REALLOC(line, linesize);
	    if (line ==  0) no_space();
	}
	c = getc(f);
	if (c ==  EOF)
	{
	    line[i] = '\n';
	    saw_eof = 1;
	    cptr = line;
	    return;
	}
    }
}


char *
dup_line()
{
    register char *p, *s, *t;

    if (line == 0) return (0);
    s = line;
    while (*s != '\n') ++s;
    p = MALLOC(s - line + 1);
    if (p == 0) no_space();

    s = line;
    t = p;
    while ((*t++ = *s++) != '\n') continue;
    return (p);
}


skip_comment()
{
    register char *s;

    int st_lineno = lineno;
    char *st_line = dup_line();
    char *st_cptr = st_line + (cptr - line);

    s = cptr + 2;
    for (;;)
    {
	if (*s == '*' && s[1] == '/')
	{
	    cptr = s + 2;
	    FREE(st_line);
	    return;
	}
	if (*s == '\n')
	{
	    get_line();
	    if (line == 0)
		unterminated_comment(st_lineno, st_line, st_cptr);
	    s = cptr;
	}
	else
	    ++s;
    }
}


int
nextc()
{
    register char *s;

    if (line == 0)
    {
	get_line();
	if (line == 0)
	    return (EOF);
    }

    s = cptr;
    for (;;)
    {
	switch (*s)
	{
	case '\n':
	    get_line();
	    if (line == 0) return (EOF);
	    s = cptr;
	    break;

	case ' ':
	case '\t':
	case '\f':
	case '\r':
	case '\v':
	case ',':
	case ';':
	    ++s;
	    break;

	case '\\':
	    cptr = s;
	    return ('%');

	case '/':
	    if (s[1] == '*')
	    {
		cptr = s;
		skip_comment();
		s = cptr;
		break;
	    }
	    else if (s[1] == '/')
	    {
		get_line();
		if (line == 0) return (EOF);
		s = cptr;
		break;
	    }
	    /* fall through */

	default:
	    cptr = s;
	    return (*s);
	}
    }
}


int
keyword()
{
    register int c;
    char *t_cptr = cptr;

    c = *++cptr;
    if (isalpha(c))
    {
	cinc = 0;
	for (;;)
	{
	    if (isalpha(c))
	    {
		if (isupper(c)) c = tolower(c);
		cachec(c);
	    }
	    else if (isdigit(c) || c == '_' || c == '.' || c == '$')
		cachec(c);
	    else
		break;
	    c = *++cptr;
	}
	cachec(NUL);

	if (strcmp(cache, "token") == 0 || strcmp(cache, "term") == 0)
	    return (TOKEN);
	if (strcmp(cache, "type") == 0)
	    return (TYPE);
	if (strcmp(cache, "left") == 0)
	    return (LEFT);
	if (strcmp(cache, "right") == 0)
	    return (RIGHT);
	if (strcmp(cache, "nonassoc") == 0 || strcmp(cache, "binary") == 0)
	    return (NONASSOC);
	if (strcmp(cache, "start") == 0)
	    return (START);
	if (strcmp(cache, "union") == 0)
	    return (UNION);
	if (strcmp(cache, "ident") == 0)
	    return (IDENT);
    }
    else
    {
	++cptr;
	if (c == '{')
	    return (TEXT);
	if (c == '%' || c == '\\')
	    return (MARK);
	if (c == '<')
	    return (LEFT);
	if (c == '>')
	    return (RIGHT);
	if (c == '0')
	    return (TOKEN);
	if (c == '2')
	    return (NONASSOC);
    }
    syntax_error(lineno, line, t_cptr);
    /*NOTREACHED*/
}


copy_ident()
{
    register int c;
    register FILE *f = output_file;

    c = nextc();
    if (c == EOF) unexpected_EOF();
    if (c != '"') syntax_error(lineno, line, cptr);
    ++outline;
    fprintf(f, "#ident \"");
    for (;;)
    {
	c = *++cptr;
	if (c == '\n')
	{
	    fprintf(f, "\"\n");
	    return;
	}
	putc(c, f);
	if (c == '"')
	{
	    putc('\n', f);
	    ++cptr;
	    return;
	}
    }
}


copy_text()
{
    register int c;
    int quote;
    register FILE *f = text_file;
    int need_newline = 0;
    int t_lineno = lineno;
    char *t_line = dup_line();
    char *t_cptr = t_line + (cptr - line - 2);

    if (*cptr == '\n')
    {
	get_line();
	if (line == 0)
	    unterminated_text(t_lineno, t_line, t_cptr);
    }
    if (!lflag) fprintf(f, line_format, lineno, input_file_name);

loop:
    c = *cptr++;
    switch (c)
    {
    case '\n':
    next_line:
	putc('\n', f);
	need_newline = 0;
	get_line();
	if (line) goto loop;
	unterminated_text(t_lineno, t_line, t_cptr);

    case '\'':
    case '"':
	{
	    int s_lineno = lineno;
	    char *s_line = dup_line();
	    char *s_cptr = s_line + (cptr - line - 1);

	    quote = c;
	    putc(c, f);
	    for (;;)
	    {
		c = *cptr++;
		putc(c, f);
		if (c == quote)
		{
		    need_newline = 1;
		    FREE(s_line);
		    goto loop;
		}
		if (c == '\n')
		    unterminated_string(s_lineno, s_line, s_cptr);
		if (c == '\\')
		{
		    c = *cptr++;
		    putc(c, f);
		    if (c == '\n')
		    {
			get_line();
			if (line == 0)
			    unterminated_string(s_lineno, s_line, s_cptr);
		    }
		}
	    }
	}

    case '/':
	putc(c, f);
	need_newline = 1;
	c = *cptr;
	if (c == '/')
	{
	    putc('*', f);
	    while ((c = *++cptr) != '\n')
	    {
		if (c == '*' && cptr[1] == '/')
		    fprintf(f, "* ");
		else
		    putc(c, f);
	    }
	    fprintf(f, "*/");
	    goto next_line;
	}
	if (c == '*')
	{
	    int c_lineno = lineno;
	    char *c_line = dup_line();
	    char *c_cptr = c_line + (cptr - line - 1);

	    putc('*', f);
	    ++cptr;
	    for (;;)
	    {
		c = *cptr++;
		putc(c, f);
		if (c == '*' && *cptr == '/')
		{
		    putc('/', f);
		    ++cptr;
		    FREE(c_line);
		    goto loop;
		}
		if (c == '\n')
		{
		    get_line();
		    if (line == 0)
			unterminated_comment(c_lineno, c_line, c_cptr);
		}
	    }
	}
	need_newline = 1;
	goto loop;

    case '%':
    case '\\':
	if (*cptr == '}')
	{
	    if (need_newline) putc('\n', f);
	    ++cptr;
	    FREE(t_line);
	    return;
	}
	/* fall through */

    default:
	putc(c, f);
	need_newline = 1;
	goto loop;
    }
}


copy_union()
{
    register int c;
    int quote;
    int depth;
    int u_lineno = lineno;
    char *u_line = dup_line();
    char *u_cptr = u_line + (cptr - line - 6);

    if (unionized) over_unionized(cptr - 6);
    unionized = 1;

    if (!lflag)
	fprintf(text_file, line_format, lineno, input_file_name);

    fprintf(text_file, "typedef union");
    if (dflag) fprintf(union_file, "typedef union");

    depth = 0;
loop:
    c = *cptr++;
    putc(c, text_file);
    if (dflag) putc(c, union_file);
    switch (c)
    {
    case '\n':
    next_line:
	get_line();
	if (line == 0) unterminated_union(u_lineno, u_line, u_cptr);
	goto loop;

    case '{':
	++depth;
	goto loop;

    case '}':
	if (--depth == 0)
	{
	    fprintf(text_file, " YYSTYPE;\n");
	    FREE(u_line);
	    return;
	}
	goto loop;

    case '\'':
    case '"':
	{
	    int s_lineno = lineno;
	    char *s_line = dup_line();
	    char *s_cptr = s_line + (cptr - line - 1);

	    quote = c;
	    for (;;)
	    {
		c = *cptr++;
		putc(c, text_file);
		if (dflag) putc(c, union_file);
		if (c == quote)
		{
		    FREE(s_line);
		    goto loop;
		}
		if (c == '\n')
		    unterminated_string(s_lineno, s_line, s_cptr);
		if (c == '\\')
		{
		    c = *cptr++;
		    putc(c, text_file);
		    if (dflag) putc(c, union_file);
		    if (c == '\n')
		    {
			get_line();
			if (line == 0)
			    unterminated_string(s_lineno, s_line, s_cptr);
		    }
		}
	    }
	}

    case '/':
	c = *cptr;
	if (c == '/')
	{
	    putc('*', text_file);
	    if (dflag) putc('*', union_file);
	    while ((c = *++cptr) != '\n')
	    {
		if (c == '*' && cptr[1] == '/')
		{
		    fprintf(text_file, "* ");
		    if (dflag) fprintf(union_file, "* ");
		}
		else
		{
		    putc(c, text_file);
		    if (dflag) putc(c, union_file);
		}
	    }
	    fprintf(text_file, "*/\n");
	    if (dflag) fprintf(union_file, "*/\n");
	    goto next_line;
	}
	if (c == '*')
	{
	    int c_lineno = lineno;
	    char *c_line = dup_line();
	    char *c_cptr = c_line + (cptr - line - 1);

	    putc('*', text_file);
	    if (dflag) putc('*', union_file);
	    ++cptr;
	    for (;;)
	    {
		c = *cptr++;
		putc(c, text_file);
		if (dflag) putc(c, union_file);
		if (c == '*' && *cptr == '/')
		{
		    putc('/', text_file);
		    if (dflag) putc('/', union_file);
		    ++cptr;
		    FREE(c_line);
		    goto loop;
		}
		if (c == '\n')
		{
		    get_line();
		    if (line == 0)
			unterminated_comment(c_lineno, c_line, c_cptr);
		}
	    }
	}
	goto loop;

    default:
	goto loop;
    }
}


int
hexval(c)
int c;
{
    if (c >= '0' && c <= '9')
	return (c - '0');
    if (c >= 'A' && c <= 'F')
	return (c - 'A' + 10);
    if (c >= 'a' && c <= 'f')
	return (c - 'a' + 10);
    return (-1);
}


bucket *
get_literal()
{
    register int c, quote;
    register int i;
    register int n;
    register char *s;
    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(name)
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()
{
    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()
{
    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()
{
    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);
}


declare_tokens(assoc)
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();
	}
    }
}