File: simple-lexers.c

package info (click to toggle)
saml 970418-9
  • links: PTS
  • area: main
  • in suites: woody
  • size: 1,188 kB
  • ctags: 1,703
  • sloc: ansic: 17,186; sh: 2,573; yacc: 497; perl: 264; makefile: 242; python: 242
file content (179 lines) | stat: -rw-r--r-- 3,986 bytes parent folder | download | duplicates (3)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
/*
 * Copyright 1996 Thierry Bousch
 * Licensed under the Gnu Public License, Version 2
 *
 * $Id: simple-lexers.c,v 1.5 1996/09/15 16:03:56 bousch Exp $
 *
 * Two lexers, to read from a file or a region of memory.
 */

#include <ctype.h>
#include <stdio.h>
#include <stdlib.h>
#include "saml-parse.h"
#include "saml-util.h"

char *saml_token = NULL;
int (*saml_lexer)(void) = NULL;

static int toklen, tok_maxlen = 0;
static int saml_common_lexer (int (*getc)(void), void (*ungetc)(int));

/*
 * State and operations for the "file" lexer
 */
static FILE *flx_fd;

static int getc_fd (void)
{
	return getc(flx_fd);
}

static void ungetc_fd (int c)
{
	ungetc(c, flx_fd);
}

static int saml_lexer_fd (void)
{
	return saml_common_lexer(getc_fd, ungetc_fd);
}

void saml_init_lexer_fd (FILE *fd)
{
	flx_fd = fd;
	saml_lexer = saml_lexer_fd;
	tok_maxlen = saml_token ? 1+strlen(saml_token) : 0;
}

/*
 * State and operations for the "memory" lexer
 */
static unsigned char *mlx_start, *mlx_end, *mlx_curr;

static int getc_mem (void)
{
	if (mlx_curr < mlx_end)
		return (int)(*mlx_curr++);
	return EOF;
}

static void ungetc_mem (int c)
{
	if (c != EOF && mlx_curr > mlx_start)
		--mlx_curr;
}

static int saml_lexer_mem (void)
{
	return saml_common_lexer(getc_mem, ungetc_mem);
}

void saml_init_lexer_mem (const void *start, size_t length)
{
	mlx_start = mlx_curr = (unsigned char *) start;
	mlx_end = mlx_start + length;
	saml_lexer = saml_lexer_mem;
	tok_maxlen = saml_token ? 1+strlen(saml_token) : 0;
}

/*
 * The lexical analyser itself
 */
static void append_to_token (int c)
{
	if (toklen >= tok_maxlen) {
		tok_maxlen += (toklen + 16);
		saml_token = realloc(saml_token, tok_maxlen);
		if (!saml_token) panic_out_of_memory();
	}
	saml_token[toklen++] = c;
}

static int saml_common_lexer (int (*getc)(void), void (*ungetc)(int))
{
	int c, bracket;
top:
	c = (*getc)();
	switch(c) {
	    case EOF:
	    	/* End of file, return zero */
	    	return STOK_EOF;

	    case '\0': case '\r':
	    case '\n': case '\f':
	    case '\t': case '\v':
	    case ' ':
	    	/* Ignore whitespace */
	    	goto top;

	    case '.':
	    	/* Another symbol for multiplication */
	    	return '*';

	    case '0': case '1': case '2': case '3': case '4':
	    case '5': case '6': case '7': case '8': case '9':
	    	/* Number */
	    	for (toklen = 0; isdigit(c); c = (*getc)())
	    		append_to_token(c);
	    	/* Push back the first non-digit */
	    	(*ungetc)(c);
	    	append_to_token(0);
	    	return STOK_INTEGER;

	    case '[':
	    	/* FORM literal */
	    	toklen = 0;
		bracket = 1;
		append_to_token(c);
		while (bracket) {
			c = (*getc)();
			if (c == EOF)  break;
			if (c == '[')  ++bracket;
			if (c == ']')  --bracket;
			append_to_token(c);
		}
		append_to_token(0);
		return STOK_LITERAL;
		
	    case 'a': case 'b': case 'c': case 'd': case 'e':
	    case 'f': case 'g': case 'h': case 'i': case 'j':
	    case 'k': case 'l': case 'm': case 'n': case 'o':
	    case 'p': case 'q': case 'r': case 's': case 't':
	    case 'u': case 'v': case 'w': case 'x': case 'y':
	    case 'z': case '_':
	    case 'A': case 'B': case 'C': case 'D': case 'E':
	    case 'F': case 'G': case 'H': case 'I': case 'J':
	    case 'K': case 'L': case 'M': case 'N': case 'O':
	    case 'P': case 'Q': case 'R': case 'S': case 'T':
	    case 'U': case 'V': case 'W': case 'X': case 'Y':
	    case 'Z':
	    	/* Literal */
	    	toklen = 0;
next_char:
    		append_to_token(c);
		c = (*getc)();
		if (isascii(c) && (c == '_' || isalnum(c)))
			goto next_char;
		while (c == '[') {
			bracket = 1;
			append_to_token(c);
			while (bracket) {
				c = (*getc)();
				if (c == EOF)  break;
				if (c == '[')  ++bracket;
				if (c == ']')  --bracket;
				append_to_token(c);
			}
			/* Found the matching bracket or EOF */
			c = (*getc)();
		}
		/* Push back the character */
		(*ungetc)(c);
		append_to_token(0);
		return STOK_LITERAL;
	    default:
	    	/* Any other character */
	    	return c;
	}
}