Return to json.c CVS log

Up to [ELWIX - Embedded LightWeight unIX -] / libelwix / src

finish parser

/*************************************************************************
* (C) 2017 AITNET ltd - Sofia/Bulgaria - <misho@aitnet.org>
*  by Michael Pounov <misho@elwix.org>
*
* $Author: misho $
* $Id: json.c,v 1.1.2.3 2017/11/27 19:37:22 misho Exp $
*
**************************************************************************
The ELWIX and AITNET software is distributed under the following
terms:

All of the documentation and software included in the ELWIX and AITNET
Releases is copyrighted by ELWIX - Sofia/Bulgaria <info@elwix.org>

Copyright 2004 - 2017
	by Michael Pounov <misho@elwix.org>.  All rights reserved.

Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions
are met:
1. Redistributions of source code must retain the above copyright
   notice, this list of conditions and the following disclaimer.
2. Redistributions in binary form must reproduce the above copyright
   notice, this list of conditions and the following disclaimer in the
   documentation and/or other materials provided with the distribution.
3. All advertising materials mentioning features or use of this software
   must display the following acknowledgement:
This product includes software developed by Michael Pounov <misho@elwix.org>
ELWIX - Embedded LightWeight unIX and its contributors.
4. Neither the name of AITNET nor the names of its contributors
   may be used to endorse or promote products derived from this software
   without specific prior written permission.

THIS SOFTWARE IS PROVIDED BY AITNET AND CONTRIBUTORS ``AS IS'' AND
ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
SUCH DAMAGE.
*/
#include "global.h"


/* JSON error strings */
const char *jerrstr[] = {
	"No error",
	"Not enough tokens were provided",
	"Invalid character",
	"JSON string isn't full",
	"Invalid parameter", 
	NULL
};


/*
 * json_init() - Initialize JSON handler
 *
 * @json = JSON handler, if there is NULL then dynamically will be allocated
 * @jstrict = JSON strict mode, when we select strict mode every unquoted value is error
 * return: =NULL error or !=NULL ready for use JSON handler and should be free with json_free()
 */
json_t *
json_init(json_t * __restrict json, int jstrict)
{
	json_t *j = json;

	if (!j) {
		j = e_malloc(sizeof(json_t));
		if (!j) {
			LOGERR;
			return NULL;
		}
	}

	memset(j, 0, sizeof(json_t));
	j->h_parent = -1;
	j->h_strict = jstrict;

	/* handler is dynamically allocated! */
	if (!json)
		j->h_alloc = j;

	return j;
}

/*
 * json_free() - Free JSON handler
 *
 * @json = JSON handler
 * return: none
 */
void
json_free(json_t * __restrict json)
{
	if (json) {
		if (json->h_alloc)
			e_free(json);
		else
			memset(json, 0, sizeof(json_t));
	}
}

static jtok_t *
json_gettoken(json_t * __restrict json, jtok_t * __restrict jtoks, u_int toksnum)
{
	jtok_t *tok;

	assert(json || !(!jtoks && toksnum));

	if (json->h_next >= toksnum) {
		elwix_SetErr(J_ERR_NOMEM, "%s", jerrstr[J_ERR_NOMEM]);
		return NULL;
	} else
		tok = &jtoks[json->h_next++];
	tok->tok_start = tok->tok_end = tok->tok_parent = -1;
	tok->tok_size = 0;

	return tok;
}

inline void
json_filltoken(jtok_t * __restrict tok, jtype_t type, long start, long end, long parent)
{
	assert(tok);

	tok->tok_type = type;
	tok->tok_start = start;
	tok->tok_end = end;
	tok->tok_parent = parent;
	tok->tok_size = 0;
}

static int
json_parse_string(json_t * __restrict json, const char *jstr, size_t jlen, jtok_t * __restrict jtoks, u_int toksnum)
{
	jtok_t	*tok;
	u_long pos;
	char ch;
	register int i;

	assert(json || jstr || !(!jtoks && toksnum));

	for (pos = json->h_pos++; json->h_pos < jlen && jstr[json->h_pos]; json->h_pos++) {
		ch = jstr[json->h_pos];

		if (ch == '\"') {
			if (!jtoks)
				return 0;
			if (!(tok = json_gettoken(json, jtoks, toksnum))) {
				json->h_pos = pos;
				return -1;
			} else
				json_filltoken(tok, J_STRING, pos + 1, json->h_pos, json->h_parent);
			return 0;
		}

		if (ch == '\\' && json->h_pos + 1 < jlen) {
			switch (jstr[++json->h_pos]) {
				case '\"':
				case '/':
				case '\\':
				case 'b':
				case 'f':
				case 'r':
				case 'n':
				case 't':
					/* Allowed escaped symbols */
					break;
				case 'u':
					/* Allows escaped symbol \uXXXX */
					json->h_pos++;
					for (i = 0; i < 4 && json->h_pos < jlen && jstr[json->h_pos]; i++, json->h_pos++) {
						/* If it isn't a hex character we have an error */
						if (!((jstr[json->h_pos] >= 48 && jstr[json->h_pos] <= 57) || /* 0-9 */
								(jstr[json->h_pos] >= 65 && jstr[json->h_pos] <= 70) || /* A-F */
								(jstr[json->h_pos] >= 97 && jstr[json->h_pos] <= 102))) { /* a-f */
							json->h_pos = pos;
							elwix_SetErr(J_ERR_INVAL, "%s", jerrstr[J_ERR_INVAL]);
							return -1;
						}
					}
					json->h_pos--;
					break;
				default:
					/* Unexpected symbol */
					json->h_pos = pos;
					elwix_SetErr(J_ERR_INVAL, "%s", jerrstr[J_ERR_INVAL]);
					return -1;
			}
		}
	}

	json->h_pos = pos;
	elwix_SetErr(J_ERR_PART, "%s", jerrstr[J_ERR_PART]);
	return -1;
}

static int
json_parse_value(json_t * __restrict json, const char *jstr, size_t jlen, jtok_t * __restrict jtoks, u_int toksnum)
{
	jtok_t	*tok;
	u_long pos;

	assert(json || jstr || !(!jtoks && toksnum));

	for (pos = json->h_pos; json->h_pos < jlen && jstr[json->h_pos]; json->h_pos++) {
		switch (jstr[json->h_pos]) {
			case ':':
				if (json->h_strict)
					goto found;
				break;
			case '\t':
			case '\r':
			case '\n':
			case ' ':
			case ',':
			case ']':
			case '}':
				goto found;
		}
		if (jstr[json->h_pos] < 32 || jstr[json->h_pos] > 127) {
			json->h_pos = pos;
			elwix_SetErr(J_ERR_INVAL, "%s", jerrstr[J_ERR_INVAL]);
			return -1;
		}
	}

	if (json->h_strict) {
		json->h_pos = pos;
		elwix_SetErr(J_ERR_PART, "%s", jerrstr[J_ERR_PART]);
		return -1;
	}
found:
	if (jtoks) {
		if (!(tok = json_gettoken(json, jtoks, toksnum))) {
			json->h_pos = pos;
			return -1;
		} else
			json_filltoken(tok, J_VALUE, pos, json->h_pos, json->h_parent);
	}

	json->h_pos--;
	return 0;
}

/*
 * json_parse() - Parse JSON string
 *
 * @json = JSON handler
 * @jstr = JSON string
 * @jlen = JSON string length
 * @jtoks = Token array
 * @toksnum = Token array size, return number of allocated tokens in array
 * return: -1 error or number of found tokens 
 */
u_int
json_parse(json_t * __restrict json, const char *jstr, size_t jlen, jtok_t * __restrict jtoks, u_int toksnum)
{
	register int i;
	register u_int cx;
	jtype_t type;
	jtok_t *tok;
	char ch;

	if (!json || !jstr || (!jtoks && toksnum)) {
		elwix_SetErr(J_ERR_PARAM, "%s", jerrstr[J_ERR_PARAM]);
		return (u_int) -1;
	}

	for (cx = json->h_next; json->h_pos < jlen && jstr[json->h_pos]; json->h_pos++) {
		switch ((ch = jstr[json->h_pos])) {
			case '{':
			case '[':
				cx++;	/* start new token */
				if (!jtoks)
					break;

				tok = json_gettoken(json, jtoks, toksnum);
				if (!tok)
					return (u_int) -1;
				if (json->h_parent != -1) {
					jtoks[json->h_parent].tok_size++;
					tok->tok_parent = json->h_parent;
				}
				tok->tok_type = (ch == '{' ? J_OBJECT : J_ARRAY);
				tok->tok_start = json->h_pos;
				json->h_parent = json->h_next - 1;
				break;
			case '}':
			case ']':
				if (!jtoks)
					break;

				if (json->h_next < 1) {
					elwix_SetErr(J_ERR_INVAL, "%s", jerrstr[J_ERR_INVAL]);
					return (u_int) -1;
				}

				type = (ch == '}' ? J_OBJECT : J_ARRAY);
				tok = &jtoks[json->h_next - 1];
				while (42) {
					if (tok->tok_start != -1 && tok->tok_end == -1) {
						if (tok->tok_type != type) {
							elwix_SetErr(J_ERR_INVAL, "%s", jerrstr[J_ERR_INVAL]);
							return (u_int) -1;
						}
						tok->tok_end = json->h_pos + 1;
						json->h_parent = tok->tok_parent;
						break;
					}
					if (tok->tok_parent == -1) {
						if (tok->tok_type != type || json->h_parent == -1) {
							elwix_SetErr(J_ERR_INVAL, "%s", jerrstr[J_ERR_INVAL]);
							return (u_int) -1;
						}
						break;
					}
					tok = &jtoks[tok->tok_parent];
				}
				break;
			case '\"':
				if (json_parse_string(json, jstr, jlen, jtoks, toksnum) == -1) {
					elwix_SetErr(J_ERR_INVAL, "%s", jerrstr[J_ERR_INVAL]);
					return (u_int) -1;
				}
				cx++;
				if (jtoks && json->h_parent != -1)
					jtoks[json->h_parent].tok_size++;
				break;
			case '\t':
			case '\r':
			case '\n':
			case ' ':
				/* whitespace, skip */
				break;
			case ':':
				json->h_parent = json->h_next - 1;
				break;
			case ',':
				if (jtoks && json->h_parent != -1 && 
						jtoks[json->h_parent].tok_type != J_OBJECT && 
						jtoks[json->h_parent].tok_type != J_ARRAY)
					json->h_parent = jtoks[json->h_parent].tok_parent;
				break;
			case '-':
			case '0':
			case '1':
			case '2':
			case '3':
			case '4':
			case '5':
			case '6':
			case '7':
			case '8':
			case '9':
			case 't':
			case 'f':
			case 'n':
				if (json->h_strict) {
					if (jtoks && json->h_parent != -1) {
						/* they must not be keys of the object */
						if (jtoks[json->h_parent].tok_type == J_OBJECT || 
								(jtoks[json->h_parent].tok_type == J_STRING && 
								 jtoks[json->h_parent].tok_size)) {
							elwix_SetErr(J_ERR_INVAL, "%s", jerrstr[J_ERR_INVAL]);
							return (u_int) -1;
						}
					}

					if (json_parse_value(json, jstr, jlen, jtoks, toksnum) == -1)
						return (u_int) -1;
					cx++;
					if (jtoks && json->h_parent != -1)
						jtoks[json->h_parent].tok_size++;
					break;
				}
			default:
				if (json->h_strict) {
					elwix_SetErr(J_ERR_INVAL, "%s", jerrstr[J_ERR_INVAL]);
					return (u_int) -1;
				}

				if (json_parse_value(json, jstr, jlen, jtoks, toksnum) == -1)
					return (u_int) -1;
				cx++;
				if (jtoks && json->h_parent != -1)
					jtoks[json->h_parent].tok_size++;
				break;
		}
	}

	if (jtoks) {
		for (i = json->h_next - 1; i >= 0; i--) {
			/* unmatched opened object or array */
			if (jtoks[i].tok_start != -1 && jtoks[i].tok_end == -1) {
				elwix_SetErr(J_ERR_PART, "%s", jerrstr[J_ERR_PART]);
				return (u_int) -1;
			}
		}
	}

	return cx;
}