Release 4.10 scripts/asn1_compiler.c

/* Simplified ASN.1 notation parser
 *
 * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved.
 * Written by David Howells (dhowells@redhat.com)
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public Licence
 * as published by the Free Software Foundation; either version
 * 2 of the Licence, or (at your option) any later version.
 */

#include <stdarg.h>
#include <stdio.h>
#include <stdlib.h>
#include <stdint.h>
#include <stdbool.h>
#include <string.h>
#include <ctype.h>
#include <unistd.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <linux/asn1_ber_bytecode.h>


enum token_type {
	
DIRECTIVE_ABSENT,
	
DIRECTIVE_ALL,
	
DIRECTIVE_ANY,
	
DIRECTIVE_APPLICATION,
	
DIRECTIVE_AUTOMATIC,
	
DIRECTIVE_BEGIN,
	
DIRECTIVE_BIT,
	
DIRECTIVE_BMPString,
	
DIRECTIVE_BOOLEAN,
	
DIRECTIVE_BY,
	
DIRECTIVE_CHARACTER,
	
DIRECTIVE_CHOICE,
	
DIRECTIVE_CLASS,
	
DIRECTIVE_COMPONENT,
	
DIRECTIVE_COMPONENTS,
	
DIRECTIVE_CONSTRAINED,
	
DIRECTIVE_CONTAINING,
	
DIRECTIVE_DEFAULT,
	
DIRECTIVE_DEFINED,
	
DIRECTIVE_DEFINITIONS,
	
DIRECTIVE_EMBEDDED,
	
DIRECTIVE_ENCODED,
	
DIRECTIVE_ENCODING_CONTROL,
	
DIRECTIVE_END,
	
DIRECTIVE_ENUMERATED,
	
DIRECTIVE_EXCEPT,
	
DIRECTIVE_EXPLICIT,
	
DIRECTIVE_EXPORTS,
	
DIRECTIVE_EXTENSIBILITY,
	
DIRECTIVE_EXTERNAL,
	
DIRECTIVE_FALSE,
	
DIRECTIVE_FROM,
	
DIRECTIVE_GeneralString,
	
DIRECTIVE_GeneralizedTime,
	
DIRECTIVE_GraphicString,
	
DIRECTIVE_IA5String,
	
DIRECTIVE_IDENTIFIER,
	
DIRECTIVE_IMPLICIT,
	
DIRECTIVE_IMPLIED,
	
DIRECTIVE_IMPORTS,
	
DIRECTIVE_INCLUDES,
	
DIRECTIVE_INSTANCE,
	
DIRECTIVE_INSTRUCTIONS,
	
DIRECTIVE_INTEGER,
	
DIRECTIVE_INTERSECTION,
	
DIRECTIVE_ISO646String,
	
DIRECTIVE_MAX,
	
DIRECTIVE_MIN,
	
DIRECTIVE_MINUS_INFINITY,
	
DIRECTIVE_NULL,
	
DIRECTIVE_NumericString,
	
DIRECTIVE_OBJECT,
	
DIRECTIVE_OCTET,
	
DIRECTIVE_OF,
	
DIRECTIVE_OPTIONAL,
	
DIRECTIVE_ObjectDescriptor,
	
DIRECTIVE_PATTERN,
	
DIRECTIVE_PDV,
	
DIRECTIVE_PLUS_INFINITY,
	
DIRECTIVE_PRESENT,
	
DIRECTIVE_PRIVATE,
	
DIRECTIVE_PrintableString,
	
DIRECTIVE_REAL,
	
DIRECTIVE_RELATIVE_OID,
	
DIRECTIVE_SEQUENCE,
	
DIRECTIVE_SET,
	
DIRECTIVE_SIZE,
	
DIRECTIVE_STRING,
	
DIRECTIVE_SYNTAX,
	
DIRECTIVE_T61String,
	
DIRECTIVE_TAGS,
	
DIRECTIVE_TRUE,
	
DIRECTIVE_TeletexString,
	
DIRECTIVE_UNION,
	
DIRECTIVE_UNIQUE,
	
DIRECTIVE_UNIVERSAL,
	
DIRECTIVE_UTCTime,
	
DIRECTIVE_UTF8String,
	
DIRECTIVE_UniversalString,
	
DIRECTIVE_VideotexString,
	
DIRECTIVE_VisibleString,
	
DIRECTIVE_WITH,
	
NR__DIRECTIVES,
	
TOKEN_ASSIGNMENT = NR__DIRECTIVES,
	
TOKEN_OPEN_CURLY,
	
TOKEN_CLOSE_CURLY,
	
TOKEN_OPEN_SQUARE,
	
TOKEN_CLOSE_SQUARE,
	
TOKEN_OPEN_ACTION,
	
TOKEN_CLOSE_ACTION,
	
TOKEN_COMMA,
	
TOKEN_NUMBER,
	
TOKEN_TYPE_NAME,
	
TOKEN_ELEMENT_NAME,
	
NR__TOKENS
};


static const unsigned char token_to_tag[NR__TOKENS] = {
	/* EOC goes first */
	[DIRECTIVE_BOOLEAN]		= ASN1_BOOL,
	[DIRECTIVE_INTEGER]		= ASN1_INT,
	[DIRECTIVE_BIT]			= ASN1_BTS,
	[DIRECTIVE_OCTET]		= ASN1_OTS,
	[DIRECTIVE_NULL]		= ASN1_NULL,
	[DIRECTIVE_OBJECT]		= ASN1_OID,
	[DIRECTIVE_ObjectDescriptor]	= ASN1_ODE,
	[DIRECTIVE_EXTERNAL]		= ASN1_EXT,
	[DIRECTIVE_REAL]		= ASN1_REAL,
	[DIRECTIVE_ENUMERATED]		= ASN1_ENUM,
	[DIRECTIVE_EMBEDDED]		= 0,
	[DIRECTIVE_UTF8String]		= ASN1_UTF8STR,
	[DIRECTIVE_RELATIVE_OID]	= ASN1_RELOID,
	/* 14 */
	/* 15 */
	[DIRECTIVE_SEQUENCE]		= ASN1_SEQ,
	[DIRECTIVE_SET]			= ASN1_SET,
	[DIRECTIVE_NumericString]	= ASN1_NUMSTR,
	[DIRECTIVE_PrintableString]	= ASN1_PRNSTR,
	[DIRECTIVE_T61String]		= ASN1_TEXSTR,
	[DIRECTIVE_TeletexString]	= ASN1_TEXSTR,
	[DIRECTIVE_VideotexString]	= ASN1_VIDSTR,
	[DIRECTIVE_IA5String]		= ASN1_IA5STR,
	[DIRECTIVE_UTCTime]		= ASN1_UNITIM,
	[DIRECTIVE_GeneralizedTime]	= ASN1_GENTIM,
	[DIRECTIVE_GraphicString]	= ASN1_GRASTR,
	[DIRECTIVE_VisibleString]	= ASN1_VISSTR,
	[DIRECTIVE_GeneralString]	= ASN1_GENSTR,
	[DIRECTIVE_UniversalString]	= ASN1_UNITIM,
	[DIRECTIVE_CHARACTER]		= ASN1_CHRSTR,
	[DIRECTIVE_BMPString]		= ASN1_BMPSTR,
};


static const char asn1_classes[4][5] = {
	[ASN1_UNIV]	= "UNIV",
	[ASN1_APPL]	= "APPL",
	[ASN1_CONT]	= "CONT",
	[ASN1_PRIV]	= "PRIV"
};


static const char asn1_methods[2][5] = {
	[ASN1_UNIV]	= "PRIM",
	[ASN1_APPL]	= "CONS"
};


static const char *const asn1_universal_tags[32] = {
	"EOC",
	"BOOL",
	"INT",
	"BTS",
	"OTS",
	"NULL",
	"OID",
	"ODE",
	"EXT",
	"REAL",
	"ENUM",
	"EPDV",
	"UTF8STR",
	"RELOID",
	NULL,		/* 14 */
	NULL,		/* 15 */
	"SEQ",
	"SET",
	"NUMSTR",
	"PRNSTR",
	"TEXSTR",
	"VIDSTR",
	"IA5STR",
	"UNITIM",
	"GENTIM",
	"GRASTR",
	"VISSTR",
	"GENSTR",
	"UNISTR",
	"CHRSTR",
	"BMPSTR",
	NULL		/* 31 */
};


static const char *filename;

static const char *grammar_name;

static const char *outputname;

static const char *headername;


static const char *const directives[NR__DIRECTIVES] = {

#define _(X) [DIRECTIVE_##X] = #X
	_(ABSENT),
	_(ALL),
	_(ANY),
	_(APPLICATION),
	_(AUTOMATIC),
	_(BEGIN),
	_(BIT),
	_(BMPString),
	_(BOOLEAN),
	_(BY),
	_(CHARACTER),
	_(CHOICE),
	_(CLASS),
	_(COMPONENT),
	_(COMPONENTS),
	_(CONSTRAINED),
	_(CONTAINING),
	_(DEFAULT),
	_(DEFINED),
	_(DEFINITIONS),
	_(EMBEDDED),
	_(ENCODED),
	[DIRECTIVE_ENCODING_CONTROL] = "ENCODING-CONTROL",
	_(END),
	_(ENUMERATED),
	_(EXCEPT),
	_(EXPLICIT),
	_(EXPORTS),
	_(EXTENSIBILITY),
	_(EXTERNAL),
	_(FALSE),
	_(FROM),
	_(GeneralString),
	_(GeneralizedTime),
	_(GraphicString),
	_(IA5String),
	_(IDENTIFIER),
	_(IMPLICIT),
	_(IMPLIED),
	_(IMPORTS),
	_(INCLUDES),
	_(INSTANCE),
	_(INSTRUCTIONS),
	_(INTEGER),
	_(INTERSECTION),
	_(ISO646String),
	_(MAX),
	_(MIN),
	[DIRECTIVE_MINUS_INFINITY] = "MINUS-INFINITY",
	[DIRECTIVE_NULL] = "NULL",
	_(NumericString),
	_(OBJECT),
	_(OCTET),
	_(OF),
	_(OPTIONAL),
	_(ObjectDescriptor),
	_(PATTERN),
	_(PDV),
	[DIRECTIVE_PLUS_INFINITY] = "PLUS-INFINITY",
	_(PRESENT),
	_(PRIVATE),
	_(PrintableString),
	_(REAL),
	[DIRECTIVE_RELATIVE_OID] = "RELATIVE-OID",
	_(SEQUENCE),
	_(SET),
	_(SIZE),
	_(STRING),
	_(SYNTAX),
	_(T61String),
	_(TAGS),
	_(TRUE),
	_(TeletexString),
	_(UNION),
	_(UNIQUE),
	_(UNIVERSAL),
	_(UTCTime),
	_(UTF8String),
	_(UniversalString),
	_(VideotexString),
	_(VisibleString),
	_(WITH)
};


struct action {
	
struct action	*next;
	
char		*name;
	
unsigned char	index;
};


static struct action *action_list;

static unsigned nr_actions;


struct token {
	
unsigned short	line;
	
enum token_type	token_type : 8;
	
unsigned char	size;
	
struct action	*action;
	
char		*content;
	
struct type	*type;
};


static struct token *token_list;

static unsigned nr_tokens;

static bool verbose_opt;

static bool debug_opt;


#define verbose(fmt, ...) do { if (verbose_opt) printf(fmt, ## __VA_ARGS__); } while (0)

#define debug(fmt, ...) do { if (debug_opt) printf(fmt, ## __VA_ARGS__); } while (0)



static int directive_compare(const void *_key, const void *_pdir)
{
	const struct token *token = _key;
	const char *const *pdir = _pdir, *dir = *pdir;
	size_t dlen, clen;
	int val;

	dlen = strlen(dir);
	clen = (dlen < token->size) ? dlen : token->size;

	//debug("cmp(%s,%s) = ", token->content, dir);

	val = memcmp(token->content, dir, clen);
	if (val != 0) {
		//debug("%d [cmp]\n", val);
		return val;
	}

	if (dlen == token->size) {
		//debug("0\n");
		return 0;
	}
	//debug("%d\n", (int)dlen - (int)token->size);
	return dlen - token->size; /* shorter -> negative */
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
david howells
david howells
116
97.48%
2
66.67%
arnd bergmann
arnd bergmann
3
2.52%
1
33.33%
Total
119
100.00%
3
100.00%

/*
 * Tokenise an ASN.1 grammar
 */


static void tokenise(char *buffer, char *end)
{
	struct token *tokens;
	char *line, *nl, *start, *p, *q;
	unsigned tix, lineno;

	/* Assume we're going to have half as many tokens as we have
         * characters
         */
	token_list = tokens = calloc((end - buffer) / 2, sizeof(struct token));
	if (!tokens) {
		perror(NULL);
		exit(1);
	}
	tix = 0;

	lineno = 0;
	while (buffer < end) {
		/* First of all, break out a line */
		lineno++;
		line = buffer;
		nl = memchr(line, '\n', end - buffer);
		if (!nl) {
			buffer = nl = end;
		} else {
			buffer = nl + 1;
			*nl = '\0';
		}

		/* Remove "--" comments */
		p = line;
	next_comment:
		while ((p = memchr(p, '-', nl - p))) {
			if (p[1] == '-') {
				/* Found a comment; see if there's a terminator */
				q = p + 2;
				while ((q = memchr(q, '-', nl - q))) {
					if (q[1] == '-') {
						/* There is - excise the comment */
						q += 2;
						memmove(p, q, nl - q);
						goto next_comment;
					}
					q++;
				}
				*p = '\0';
				nl = p;
				break;
			} else {
				p++;
			}
		}

		p = line;
		while (p < nl) {
			/* Skip white space */
			while (p < nl && isspace(*p))
				*(p++) = 0;
			if (p >= nl)
				break;

			tokens[tix].line = lineno;
			start = p;

			/* Handle string tokens */
			if (isalpha(*p)) {
				const char **dir, *start = p;

				/* Can be a directive, type name or element
                                 * name.  Find the end of the name.
                                 */
				q = p + 1;
				while (q < nl && (isalnum(*q) || *q == '-' || *q == '_'))
					q++;
				tokens[tix].size = q - p;
				p = q;

				tokens[tix].content = malloc(tokens[tix].size + 1);
				if (!tokens[tix].content) {
					perror(NULL);
					exit(1);
				}
				memcpy(tokens[tix].content, start, tokens[tix].size);
				tokens[tix].content[tokens[tix].size] = 0;
				
				/* If it begins with a lowercase letter then
                                 * it's an element name
                                 */
				if (islower(tokens[tix].content[0])) {
					tokens[tix++].token_type = TOKEN_ELEMENT_NAME;
					continue;
				}

				/* Otherwise we need to search the directive
                                 * table
                                 */
				dir = bsearch(&tokens[tix], directives,
					      sizeof(directives) / sizeof(directives[1]),
					      sizeof(directives[1]),
					      directive_compare);
				if (dir) {
					tokens[tix++].token_type = dir - directives;
					continue;
				}

				tokens[tix++].token_type = TOKEN_TYPE_NAME;
				continue;
			}

			/* Handle numbers */
			if (isdigit(*p)) {
				/* Find the end of the number */
				q = p + 1;
				while (q < nl && (isdigit(*q)))
					q++;
				tokens[tix].size = q - p;
				p = q;
				tokens[tix].content = malloc(tokens[tix].size + 1);
				if (!tokens[tix].content) {
					perror(NULL);
					exit(1);
				}
				memcpy(tokens[tix].content, start, tokens[tix].size);
				tokens[tix].content[tokens[tix].size] = 0;
				tokens[tix++].token_type = TOKEN_NUMBER;
				continue;
			}

			if (nl - p >= 3) {
				if (memcmp(p, "::=", 3) == 0) {
					p += 3;
					tokens[tix].size = 3;
					tokens[tix].content = "::=";
					tokens[tix++].token_type = TOKEN_ASSIGNMENT;
					continue;
				}
			}

			if (nl - p >= 2) {
				if (memcmp(p, "({", 2) == 0) {
					p += 2;
					tokens[tix].size = 2;
					tokens[tix].content = "({";
					tokens[tix++].token_type = TOKEN_OPEN_ACTION;
					continue;
				}
				if (memcmp(p, "})", 2) == 0) {
					p += 2;
					tokens[tix].size = 2;
					tokens[tix].content = "})";
					tokens[tix++].token_type = TOKEN_CLOSE_ACTION;
					continue;
				}
			}

			if (nl - p >= 1) {
				tokens[tix].size = 1;
				switch (*p) {
				case '{':
					p += 1;
					tokens[tix].content = "{";
					tokens[tix++].token_type = TOKEN_OPEN_CURLY;
					continue;
				case '}':
					p += 1;
					tokens[tix].content = "}";
					tokens[tix++].token_type = TOKEN_CLOSE_CURLY;
					continue;
				case '[':
					p += 1;
					tokens[tix].content = "[";
					tokens[tix++].token_type = TOKEN_OPEN_SQUARE;
					continue;
				case ']':
					p += 1;
					tokens[tix].content = "]";
					tokens[tix++].token_type = TOKEN_CLOSE_SQUARE;
					continue;
				case ',':
					p += 1;
					tokens[tix].content = ",";
					tokens[tix++].token_type = TOKEN_COMMA;
					continue;
				default:
					break;
				}
			}

			fprintf(stderr, "%s:%u: Unknown character in grammar: '%c'\n",
				filename, lineno, *p);
			exit(1);
		}
	}

	nr_tokens = tix;
	verbose("Extracted %u tokens\n", nr_tokens);

#if 0
	{
                int n;
                for (n = 0; n < nr_tokens; n++)
                        debug("Token %3u: '%s'\n", n, token_list[n].content);
        }
#endif
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
david howells
david howells
1053
100.00%
3
100.00%
Total
1053
100.00%
3
100.00%

static void build_type_list(void);
static void parse(void);
static void dump_elements(void);
static void render(FILE *out, FILE *hdr);

/*
 *
 */


int main(int argc, char **argv)
{
	struct stat st;
	ssize_t readlen;
	FILE *out, *hdr;
	char *buffer, *p;
	char *kbuild_verbose;
	int fd;

	kbuild_verbose = getenv("KBUILD_VERBOSE");
	if (kbuild_verbose)
		verbose_opt = atoi(kbuild_verbose);

	while (argc > 4) {
		if (strcmp(argv[1], "-v") == 0)
			verbose_opt = true;
		else if (strcmp(argv[1], "-d") == 0)
			debug_opt = true;
		else
			break;
		memmove(&argv[1], &argv[2], (argc - 2) * sizeof(char *));
		argc--;
	}

	if (argc != 4) {
		fprintf(stderr, "Format: %s [-v] [-d] <grammar-file> <c-file> <hdr-file>\n",
			argv[0]);
		exit(2);
	}

	filename = argv[1];
	outputname = argv[2];
	headername = argv[3];

	fd = open(filename, O_RDONLY);
	if (fd < 0) {
		perror(filename);
		exit(1);
	}

	if (fstat(fd, &st) < 0) {
		perror(filename);
		exit(1);
	}

	if (!(buffer = malloc(st.st_size + 1))) {
		perror(NULL);
		exit(1);
	}

	if ((readlen = read(fd, buffer, st.st_size)) < 0) {
		perror(filename);
		exit(1);
	}

	if (close(fd) < 0) {
		perror(filename);
		exit(1);
	}

	if (readlen != st.st_size) {
		fprintf(stderr, "%s: Short read\n", filename);
		exit(1);
	}

	p = strrchr(argv[1], '/');
	p = p ? p + 1 : argv[1];
	grammar_name = strdup(p);
	if (!p) {
		perror(NULL);
		exit(1);
	}
	p = strchr(grammar_name, '.');
	if (p)
		*p = '\0';

	buffer[readlen] = 0;
	tokenise(buffer, buffer + readlen);
	build_type_list();
	parse();
	dump_elements();

	out = fopen(outputname, "w");
	if (!out) {
		perror(outputname);
		exit(1);
	}

	hdr = fopen(headername, "w");
	if (!hdr) {
		perror(headername);
		exit(1);
	}

	render(out, hdr);

	if (fclose(out) < 0) {
		perror(outputname);
		exit(1);
	}

	if (fclose(hdr) < 0) {
		perror(headername);
		exit(1);
	}

	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
david howells
david howells
518
97.19%
2
50.00%
arnd bergmann
arnd bergmann
14
2.63%
1
25.00%
colin king
colin king
1
0.19%
1
25.00%
Total
533
100.00%
4
100.00%


enum compound {
	
NOT_COMPOUND,
	
SET,
	
SET_OF,
	
SEQUENCE,
	
SEQUENCE_OF,
	
CHOICE,
	
ANY,
	
TYPE_REF,
	
TAG_OVERRIDE
};


struct element {
	
struct type	*type_def;
	
struct token	*name;
	
struct token	*type;
	
struct action	*action;
	
struct element	*children;
	
struct element	*next;
	
struct element	*render_next;
	
struct element	*list_next;
	
uint8_t		n_elements;