From b6d20bbe3b2a92a6db810a4e3ef6d67e91a38d36 Mon Sep 17 00:00:00 2001 From: Aaron Culliney Date: Wed, 9 Mar 2016 21:09:57 -0800 Subject: [PATCH] Squashed 'externals/jsmn/' content from commit 3459957 git-subtree-dir: externals/jsmn git-subtree-split: 345995799311ed1e26ea20e3eeaa47224cd1a77d --- LICENSE | 20 +++ Makefile | 41 +++++ README.md | 167 ++++++++++++++++++++ example/jsondump.c | 126 +++++++++++++++ example/simple.c | 76 +++++++++ jsmn.c | 337 ++++++++++++++++++++++++++++++++++++++++ jsmn.h | 77 +++++++++ library.json | 16 ++ test/test.h | 27 ++++ test/tests.c | 378 +++++++++++++++++++++++++++++++++++++++++++++ test/testutil.h | 94 +++++++++++ 11 files changed, 1359 insertions(+) create mode 100644 LICENSE create mode 100644 Makefile create mode 100644 README.md create mode 100644 example/jsondump.c create mode 100644 example/simple.c create mode 100644 jsmn.c create mode 100644 jsmn.h create mode 100644 library.json create mode 100644 test/test.h create mode 100644 test/tests.c create mode 100644 test/testutil.h diff --git a/LICENSE b/LICENSE new file mode 100644 index 00000000..c84fb2e9 --- /dev/null +++ b/LICENSE @@ -0,0 +1,20 @@ +Copyright (c) 2010 Serge A. Zaitsev + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in +all copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN +THE SOFTWARE. + diff --git a/Makefile b/Makefile new file mode 100644 index 00000000..a382d64d --- /dev/null +++ b/Makefile @@ -0,0 +1,41 @@ +# You can put your build options here +-include config.mk + +all: libjsmn.a + +libjsmn.a: jsmn.o + $(AR) rc $@ $^ + +%.o: %.c jsmn.h + $(CC) -c $(CFLAGS) $< -o $@ + +test: test_default test_strict test_links test_strict_links +test_default: test/tests.c + $(CC) $(CFLAGS) $(LDFLAGS) $< -o test/$@ + ./test/$@ +test_strict: test/tests.c + $(CC) -DJSMN_STRICT=1 $(CFLAGS) $(LDFLAGS) $< -o test/$@ + ./test/$@ +test_links: test/tests.c + $(CC) -DJSMN_PARENT_LINKS=1 $(CFLAGS) $(LDFLAGS) $< -o test/$@ + ./test/$@ +test_strict_links: test/tests.c + $(CC) -DJSMN_STRICT=1 -DJSMN_PARENT_LINKS=1 $(CFLAGS) $(LDFLAGS) $< -o test/$@ + ./test/$@ + +jsmn_test.o: jsmn_test.c libjsmn.a + +simple_example: example/simple.o libjsmn.a + $(CC) $(LDFLAGS) $^ -o $@ + +jsondump: example/jsondump.o libjsmn.a + $(CC) $(LDFLAGS) $^ -o $@ + +clean: + rm -f jsmn.o jsmn_test.o example/simple.o + rm -f libjsmn.a + rm -f simple_example + rm -f jsondump + +.PHONY: all clean test + diff --git a/README.md b/README.md new file mode 100644 index 00000000..6f6fb471 --- /dev/null +++ b/README.md @@ -0,0 +1,167 @@ + +JSMN +==== + +jsmn (pronounced like 'jasmine') is a minimalistic JSON parser in C. It can be +easily integrated into resource-limited or embedded projects. + +You can find more information about JSON format at [json.org][1] + +Library sources are available at https://github.com/zserge/jsmn + +The web page with some information about jsmn can be found at +[http://zserge.com/jsmn.html][2] + +Philosophy +---------- + +Most JSON parsers offer you a bunch of functions to load JSON data, parse it +and extract any value by its name. jsmn proves that checking the correctness of +every JSON packet or allocating temporary objects to store parsed JSON fields +often is an overkill. + +JSON format itself is extremely simple, so why should we complicate it? + +jsmn is designed to be **robust** (it should work fine even with erroneous +data), **fast** (it should parse data on the fly), **portable** (no superfluous +dependencies or non-standard C extensions). An of course, **simplicity** is a +key feature - simple code style, simple algorithm, simple integration into +other projects. + +Features +-------- + +* compatible with C89 +* no dependencies (even libc!) +* highly portable (tested on x86/amd64, ARM, AVR) +* about 200 lines of code +* extremely small code footprint +* API contains only 2 functions +* no dynamic memory allocation +* incremental single-pass parsing +* library code is covered with unit-tests + +Design +------ + +The rudimentary jsmn object is a **token**. Let's consider a JSON string: + + '{ "name" : "Jack", "age" : 27 }' + +It holds the following tokens: + +* Object: `{ "name" : "Jack", "age" : 27}` (the whole object) +* Strings: `"name"`, `"Jack"`, `"age"` (keys and some values) +* Number: `27` + +In jsmn, tokens do not hold any data, but point to token boundaries in JSON +string instead. In the example above jsmn will create tokens like: Object +[0..31], String [3..7], String [12..16], String [20..23], Number [27..29]. + +Every jsmn token has a type, which indicates the type of corresponding JSON +token. jsmn supports the following token types: + +* Object - a container of key-value pairs, e.g.: + `{ "foo":"bar", "x":0.3 }` +* Array - a sequence of values, e.g.: + `[ 1, 2, 3 ]` +* String - a quoted sequence of chars, e.g.: `"foo"` +* Primitive - a number, a boolean (`true`, `false`) or `null` + +Besides start/end positions, jsmn tokens for complex types (like arrays +or objects) also contain a number of child items, so you can easily follow +object hierarchy. + +This approach provides enough information for parsing any JSON data and makes +it possible to use zero-copy techniques. + +Install +------- + +To clone the repository you should have Git installed. Just run: + + $ git clone https://github.com/zserge/jsmn + +Repository layout is simple: jsmn.c and jsmn.h are library files, tests are in +the jsmn\_test.c, you will also find README, LICENSE and Makefile files inside. + +To build the library, run `make`. It is also recommended to run `make test`. +Let me know, if some tests fail. + +If build was successful, you should get a `libjsmn.a` library. +The header file you should include is called `"jsmn.h"`. + +API +--- + +Token types are described by `jsmntype_t`: + + typedef enum { + JSMN_UNDEFINED = 0, + JSMN_OBJECT = 1, + JSMN_ARRAY = 2, + JSMN_STRING = 3, + JSMN_PRIMITIVE = 4 + } jsmntype_t; + +**Note:** Unlike JSON data types, primitive tokens are not divided into +numbers, booleans and null, because one can easily tell the type using the +first character: + +* 't', 'f' - boolean +* 'n' - null +* '-', '0'..'9' - number + +Token is an object of `jsmntok_t` type: + + typedef struct { + jsmntype_t type; // Token type + int start; // Token start position + int end; // Token end position + int size; // Number of child (nested) tokens + } jsmntok_t; + +**Note:** string tokens point to the first character after +the opening quote and the previous symbol before final quote. This was made +to simplify string extraction from JSON data. + +All job is done by `jsmn_parser` object. You can initialize a new parser using: + + jsmn_parser parser; + jsmntok_t tokens[10]; + + jsmn_init(&parser); + + // js - pointer to JSON string + // tokens - an array of tokens available + // 10 - number of tokens available + jsmn_parse(&parser, js, strlen(js), tokens, 10); + +This will create a parser, and then it tries to parse up to 10 JSON tokens from +the `js` string. + +A non-negative return value of `jsmn_parse` is the number of tokens actually +used by the parser. +Passing NULL instead of the tokens array would not store parsing results, but +instead the function will return the value of tokens needed to parse the given +string. This can be useful if you don't know yet how many tokens to allocate. + +If something goes wrong, you will get an error. Error will be one of these: + +* `JSMN_ERROR_INVAL` - bad token, JSON string is corrupted +* `JSMN_ERROR_NOMEM` - not enough tokens, JSON string is too large +* `JSMN_ERROR_PART` - JSON string is too short, expecting more JSON data + +If you get `JSON_ERROR_NOMEM`, you can re-allocate more tokens and call +`jsmn_parse` once more. If you read json data from the stream, you can +periodically call `jsmn_parse` and check if return value is `JSON_ERROR_PART`. +You will get this error until you reach the end of JSON data. + +Other info +---------- + +This software is distributed under [MIT license](http://www.opensource.org/licenses/mit-license.php), + so feel free to integrate it in your commercial products. + +[1]: http://www.json.org/ +[2]: http://zserge.com/jsmn.html diff --git a/example/jsondump.c b/example/jsondump.c new file mode 100644 index 00000000..cf08c5ca --- /dev/null +++ b/example/jsondump.c @@ -0,0 +1,126 @@ +#include +#include +#include +#include +#include +#include "../jsmn.h" + +/* Function realloc_it() is a wrapper function for standart realloc() + * with one difference - it frees old memory pointer in case of realloc + * failure. Thus, DO NOT use old data pointer in anyway after call to + * realloc_it(). If your code has some kind of fallback algorithm if + * memory can't be re-allocated - use standart realloc() instead. + */ +static inline void *realloc_it(void *ptrmem, size_t size) { + void *p = realloc(ptrmem, size); + if (!p) { + free (ptrmem); + fprintf(stderr, "realloc(): errno=%d\n", errno); + } + return p; +} + +/* + * An example of reading JSON from stdin and printing its content to stdout. + * The output looks like YAML, but I'm not sure if it's really compatible. + */ + +static int dump(const char *js, jsmntok_t *t, size_t count, int indent) { + int i, j, k; + if (count == 0) { + return 0; + } + if (t->type == JSMN_PRIMITIVE) { + printf("%.*s", t->end - t->start, js+t->start); + return 1; + } else if (t->type == JSMN_STRING) { + printf("'%.*s'", t->end - t->start, js+t->start); + return 1; + } else if (t->type == JSMN_OBJECT) { + printf("\n"); + j = 0; + for (i = 0; i < t->size; i++) { + for (k = 0; k < indent; k++) printf(" "); + j += dump(js, t+1+j, count-j, indent+1); + printf(": "); + j += dump(js, t+1+j, count-j, indent+1); + printf("\n"); + } + return j+1; + } else if (t->type == JSMN_ARRAY) { + j = 0; + printf("\n"); + for (i = 0; i < t->size; i++) { + for (k = 0; k < indent-1; k++) printf(" "); + printf(" - "); + j += dump(js, t+1+j, count-j, indent+1); + printf("\n"); + } + return j+1; + } + return 0; +} + +int main() { + int r; + int eof_expected = 0; + char *js = NULL; + size_t jslen = 0; + char buf[BUFSIZ]; + + jsmn_parser p; + jsmntok_t *tok; + size_t tokcount = 2; + + /* Prepare parser */ + jsmn_init(&p); + + /* Allocate some tokens as a start */ + tok = malloc(sizeof(*tok) * tokcount); + if (tok == NULL) { + fprintf(stderr, "malloc(): errno=%d\n", errno); + return 3; + } + + for (;;) { + /* Read another chunk */ + r = fread(buf, 1, sizeof(buf), stdin); + if (r < 0) { + fprintf(stderr, "fread(): %d, errno=%d\n", r, errno); + return 1; + } + if (r == 0) { + if (eof_expected != 0) { + return 0; + } else { + fprintf(stderr, "fread(): unexpected EOF\n"); + return 2; + } + } + + js = realloc_it(js, jslen + r + 1); + if (js == NULL) { + return 3; + } + strncpy(js + jslen, buf, r); + jslen = jslen + r; + +again: + r = jsmn_parse(&p, js, jslen, tok, tokcount); + if (r < 0) { + if (r == JSMN_ERROR_NOMEM) { + tokcount = tokcount * 2; + tok = realloc_it(tok, sizeof(*tok) * tokcount); + if (tok == NULL) { + return 3; + } + goto again; + } + } else { + dump(js, tok, p.toknext, 0); + eof_expected = 1; + } + } + + return 0; +} diff --git a/example/simple.c b/example/simple.c new file mode 100644 index 00000000..de448838 --- /dev/null +++ b/example/simple.c @@ -0,0 +1,76 @@ +#include +#include +#include +#include "../jsmn.h" + +/* + * A small example of jsmn parsing when JSON structure is known and number of + * tokens is predictable. + */ + +const char *JSON_STRING = + "{\"user\": \"johndoe\", \"admin\": false, \"uid\": 1000,\n " + "\"groups\": [\"users\", \"wheel\", \"audio\", \"video\"]}"; + +static int jsoneq(const char *json, jsmntok_t *tok, const char *s) { + if (tok->type == JSMN_STRING && (int) strlen(s) == tok->end - tok->start && + strncmp(json + tok->start, s, tok->end - tok->start) == 0) { + return 0; + } + return -1; +} + +int main() { + int i; + int r; + jsmn_parser p; + jsmntok_t t[128]; /* We expect no more than 128 tokens */ + + jsmn_init(&p); + r = jsmn_parse(&p, JSON_STRING, strlen(JSON_STRING), t, sizeof(t)/sizeof(t[0])); + if (r < 0) { + printf("Failed to parse JSON: %d\n", r); + return 1; + } + + /* Assume the top-level element is an object */ + if (r < 1 || t[0].type != JSMN_OBJECT) { + printf("Object expected\n"); + return 1; + } + + /* Loop over all keys of the root object */ + for (i = 1; i < r; i++) { + if (jsoneq(JSON_STRING, &t[i], "user") == 0) { + /* We may use strndup() to fetch string value */ + printf("- User: %.*s\n", t[i+1].end-t[i+1].start, + JSON_STRING + t[i+1].start); + i++; + } else if (jsoneq(JSON_STRING, &t[i], "admin") == 0) { + /* We may additionally check if the value is either "true" or "false" */ + printf("- Admin: %.*s\n", t[i+1].end-t[i+1].start, + JSON_STRING + t[i+1].start); + i++; + } else if (jsoneq(JSON_STRING, &t[i], "uid") == 0) { + /* We may want to do strtol() here to get numeric value */ + printf("- UID: %.*s\n", t[i+1].end-t[i+1].start, + JSON_STRING + t[i+1].start); + i++; + } else if (jsoneq(JSON_STRING, &t[i], "groups") == 0) { + int j; + printf("- Groups:\n"); + if (t[i+1].type != JSMN_ARRAY) { + continue; /* We expect groups to be an array of strings */ + } + for (j = 0; j < t[i+1].size; j++) { + jsmntok_t *g = &t[i+j+2]; + printf(" * %.*s\n", g->end - g->start, JSON_STRING + g->start); + } + i += t[i+1].size + 1; + } else { + printf("Unexpected key: %.*s\n", t[i].end-t[i].start, + JSON_STRING + t[i].start); + } + } + return 0; +} diff --git a/jsmn.c b/jsmn.c new file mode 100644 index 00000000..ed39d510 --- /dev/null +++ b/jsmn.c @@ -0,0 +1,337 @@ +#include "jsmn.h" + +/** + * Allocates a fresh unused token from the token pull. + */ +static jsmntok_t *jsmn_alloc_token(jsmn_parser *parser, + jsmntok_t *tokens, size_t num_tokens) { + jsmntok_t *tok; + if (parser->toknext >= num_tokens) { + return NULL; + } + tok = &tokens[parser->toknext++]; + tok->start = tok->end = -1; + tok->size = 0; +#ifdef JSMN_PARENT_LINKS + tok->skip = 1; + tok->parent = -1; +#endif + return tok; +} + +/** + * Fills token type and boundaries. + */ +static void jsmn_fill_token(jsmntok_t *token, jsmntype_t type, + int start, int end) { + token->type = type; + token->start = start; + token->end = end; + token->size = 0; +} + +/** + * Fills next available token with JSON primitive. + */ +static int jsmn_parse_primitive(jsmn_parser *parser, const char *js, + size_t len, jsmntok_t *tokens, size_t num_tokens) { + jsmntok_t *token; + int start; + + start = parser->pos; + + for (; parser->pos < len && js[parser->pos] != '\0'; parser->pos++) { + switch (js[parser->pos]) { +#ifndef JSMN_STRICT + /* In strict mode primitive must be followed by "," or "}" or "]" */ + case ':': +#endif + case '\t' : case '\r' : case '\n' : case ' ' : + case ',' : case ']' : case '}' : + goto found; + } + if (js[parser->pos] < 32 || js[parser->pos] >= 127) { + parser->pos = start; + return JSMN_ERROR_INVAL; + } + } +#ifdef JSMN_STRICT + /* In strict mode primitive must be followed by a comma/object/array */ + parser->pos = start; + return JSMN_ERROR_PART; +#endif + +found: + if (tokens == NULL) { + parser->pos--; + return 0; + } + token = jsmn_alloc_token(parser, tokens, num_tokens); + if (token == NULL) { + parser->pos = start; + return JSMN_ERROR_NOMEM; + } + jsmn_fill_token(token, JSMN_PRIMITIVE, start, parser->pos); +#ifdef JSMN_PARENT_LINKS + token->parent = parser->toksuper; +#endif + parser->pos--; + return 0; +} + +/** + * Fills next token with JSON string. + */ +static int jsmn_parse_string(jsmn_parser *parser, const char *js, + size_t len, jsmntok_t *tokens, size_t num_tokens) { + jsmntok_t *token; + + int start = parser->pos; + + parser->pos++; + + /* Skip starting quote */ + for (; parser->pos < len && js[parser->pos] != '\0'; parser->pos++) { + char c = js[parser->pos]; + + /* Quote: end of string */ + if (c == '\"') { + if (tokens == NULL) { + return 0; + } + token = jsmn_alloc_token(parser, tokens, num_tokens); + if (token == NULL) { + parser->pos = start; + return JSMN_ERROR_NOMEM; + } + jsmn_fill_token(token, JSMN_STRING, start+1, parser->pos); +#ifdef JSMN_PARENT_LINKS + token->parent = parser->toksuper; +#endif + return 0; + } + + /* Backslash: Quoted symbol expected */ + if (c == '\\' && parser->pos + 1 < len) { + int i; + parser->pos++; + switch (js[parser->pos]) { + /* Allowed escaped symbols */ + case '\"': case '/' : case '\\' : case 'b' : + case 'f' : case 'r' : case 'n' : case 't' : + break; + /* Allows escaped symbol \uXXXX */ + case 'u': + parser->pos++; + for(i = 0; i < 4 && parser->pos < len && js[parser->pos] != '\0'; i++) { + /* If it isn't a hex character we have an error */ + if(!((js[parser->pos] >= 48 && js[parser->pos] <= 57) || /* 0-9 */ + (js[parser->pos] >= 65 && js[parser->pos] <= 70) || /* A-F */ + (js[parser->pos] >= 97 && js[parser->pos] <= 102))) { /* a-f */ + parser->pos = start; + return JSMN_ERROR_INVAL; + } + parser->pos++; + } + parser->pos--; + break; + /* Unexpected symbol */ + default: + parser->pos = start; + return JSMN_ERROR_INVAL; + } + } + } + parser->pos = start; + return JSMN_ERROR_PART; +} + +#ifdef JSMN_PARENT_LINKS +static void jsmn_percolate_skip_counts(jsmntok_t *tokens, int parent) { + jsmntok_t *token; + + token = &tokens[parent]; + token->skip++; + for (;;) { + if (token->parent == -1) { + break; + } + token = &tokens[token->parent]; + token->skip++; + } +} +#endif + +/** + * Parse JSON string and fill tokens. + */ +int jsmn_parse(jsmn_parser *parser, const char *js, size_t len, + jsmntok_t *tokens, unsigned int num_tokens) { + int r; + int i; + jsmntok_t *token; + int count = parser->toknext; + + for (; parser->pos < len && js[parser->pos] != '\0'; parser->pos++) { + char c; + jsmntype_t type; + + c = js[parser->pos]; + switch (c) { + case '{': case '[': + count++; + if (tokens == NULL) { + break; + } + token = jsmn_alloc_token(parser, tokens, num_tokens); + if (token == NULL) + return JSMN_ERROR_NOMEM; + if (parser->toksuper != -1) { + tokens[parser->toksuper].size++; +#ifdef JSMN_PARENT_LINKS + token->parent = parser->toksuper; + jsmn_percolate_skip_counts(tokens, parser->toksuper); +#endif + } + token->type = (c == '{' ? JSMN_OBJECT : JSMN_ARRAY); + token->start = parser->pos; + parser->toksuper = parser->toknext - 1; + break; + case '}': case ']': + if (tokens == NULL) + break; + type = (c == '}' ? JSMN_OBJECT : JSMN_ARRAY); +#ifdef JSMN_PARENT_LINKS + if (parser->toknext < 1) { + return JSMN_ERROR_INVAL; + } + token = &tokens[parser->toknext - 1]; + for (;;) { + if (token->start != -1 && token->end == -1) { + if (token->type != type) { + return JSMN_ERROR_INVAL; + } + token->end = parser->pos + 1; + parser->toksuper = token->parent; + break; + } + if (token->parent == -1) { + break; + } + token = &tokens[token->parent]; + } +#else + for (i = parser->toknext - 1; i >= 0; i--) { + token = &tokens[i]; + if (token->start != -1 && token->end == -1) { + if (token->type != type) { + return JSMN_ERROR_INVAL; + } + parser->toksuper = -1; + token->end = parser->pos + 1; + break; + } + } + /* Error if unmatched closing bracket */ + if (i == -1) return JSMN_ERROR_INVAL; + for (; i >= 0; i--) { + token = &tokens[i]; + if (token->start != -1 && token->end == -1) { + parser->toksuper = i; + break; + } + } +#endif + break; + case '\"': + r = jsmn_parse_string(parser, js, len, tokens, num_tokens); + if (r < 0) return r; + count++; + if (parser->toksuper != -1 && tokens != NULL) { + tokens[parser->toksuper].size++; +#ifdef JSMN_PARENT_LINKS + jsmn_percolate_skip_counts(tokens, parser->toksuper); +#endif + } + break; + case '\t' : case '\r' : case '\n' : case ' ': + break; + case ':': + parser->toksuper = parser->toknext - 1; + break; + case ',': + if (tokens != NULL && parser->toksuper != -1 && + tokens[parser->toksuper].type != JSMN_ARRAY && + tokens[parser->toksuper].type != JSMN_OBJECT) { +#ifdef JSMN_PARENT_LINKS + parser->toksuper = tokens[parser->toksuper].parent; +#else + for (i = parser->toknext - 1; i >= 0; i--) { + if (tokens[i].type == JSMN_ARRAY || tokens[i].type == JSMN_OBJECT) { + if (tokens[i].start != -1 && tokens[i].end == -1) { + parser->toksuper = i; + break; + } + } + } +#endif + } + break; +#ifdef JSMN_STRICT + /* In strict mode primitives are: numbers and booleans */ + 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' : + /* And they must not be keys of the object */ + if (tokens != NULL && parser->toksuper != -1) { + jsmntok_t *t = &tokens[parser->toksuper]; + if (t->type == JSMN_OBJECT || + (t->type == JSMN_STRING && t->size != 0)) { + return JSMN_ERROR_INVAL; + } + } +#else + /* In non-strict mode every unquoted value is a primitive */ + default: +#endif + r = jsmn_parse_primitive(parser, js, len, tokens, num_tokens); + if (r < 0) return r; + count++; + if (parser->toksuper != -1 && tokens != NULL) { + tokens[parser->toksuper].size++; +#ifdef JSMN_PARENT_LINKS + jsmn_percolate_skip_counts(tokens, parser->toksuper); +#endif + } + break; + +#ifdef JSMN_STRICT + /* Unexpected char in strict mode */ + default: + return JSMN_ERROR_INVAL; +#endif + } + } + + if (tokens != NULL) { + for (i = parser->toknext - 1; i >= 0; i--) { + /* Unmatched opened object or array */ + if (tokens[i].start != -1 && tokens[i].end == -1) { + return JSMN_ERROR_PART; + } + } + } + + return count; +} + +/** + * Creates a new parser based over a given buffer with an array of tokens + * available. + */ +void jsmn_init(jsmn_parser *parser) { + parser->pos = 0; + parser->toknext = 0; + parser->toksuper = -1; +} + diff --git a/jsmn.h b/jsmn.h new file mode 100644 index 00000000..6bdb0208 --- /dev/null +++ b/jsmn.h @@ -0,0 +1,77 @@ +#ifndef __JSMN_H_ +#define __JSMN_H_ + +#include + +#ifdef __cplusplus +extern "C" { +#endif + +/** + * JSON type identifier. Basic types are: + * o Object + * o Array + * o String + * o Other primitive: number, boolean (true/false) or null + */ +typedef enum { + JSMN_UNDEFINED = 0, + JSMN_OBJECT = 1, + JSMN_ARRAY = 2, + JSMN_STRING = 3, + JSMN_PRIMITIVE = 4 +} jsmntype_t; + +enum jsmnerr { + /* Not enough tokens were provided */ + JSMN_ERROR_NOMEM = -1, + /* Invalid character inside JSON string */ + JSMN_ERROR_INVAL = -2, + /* The string is not a full JSON packet, more bytes expected */ + JSMN_ERROR_PART = -3 +}; + +/** + * JSON token description. + * @param type type (object, array, string etc.) + * @param start start position in JSON data string + * @param end end position in JSON data string + */ +typedef struct { + jsmntype_t type; + int start; + int end; + int size; +#ifdef JSMN_PARENT_LINKS + int skip; + int parent; +#endif +} jsmntok_t; + +/** + * JSON parser. Contains an array of token blocks available. Also stores + * the string being parsed now and current position in that string + */ +typedef struct { + unsigned int pos; /* offset in the JSON string */ + unsigned int toknext; /* next token to allocate */ + int toksuper; /* superior token node, e.g parent object or array */ +} jsmn_parser; + +/** + * Create JSON parser over an array of tokens + */ +void jsmn_init(jsmn_parser *parser); + +/** + * Run JSON parser. It parses a JSON data string into and array of tokens, each describing + * a single JSON object. + */ +int jsmn_parse(jsmn_parser *parser, const char *js, size_t len, + jsmntok_t *tokens, unsigned int num_tokens); + +#ifdef __cplusplus +} +#endif + +#endif /* __JSMN_H_ */ diff --git a/library.json b/library.json new file mode 100644 index 00000000..8e2f5c25 --- /dev/null +++ b/library.json @@ -0,0 +1,16 @@ +{ + "name": "jsmn", + "keywords": "json", + "description": "Minimalistic JSON parser/tokenizer in C. It can be easily integrated into resource-limited or embedded projects", + "repository": + { + "type": "git", + "url": "https://github.com/zserge/jsmn.git" + }, + "frameworks": "*", + "platforms": "*", + "examples": [ + "example/*.c" + ], + "exclude": "test" +} diff --git a/test/test.h b/test/test.h new file mode 100644 index 00000000..930ebaf9 --- /dev/null +++ b/test/test.h @@ -0,0 +1,27 @@ +#ifndef __TEST_H__ +#define __TEST_H__ + +static int test_passed = 0; +static int test_failed = 0; + +/* Terminate current test with error */ +#define fail() return __LINE__ + +/* Successfull end of the test case */ +#define done() return 0 + +/* Check single condition */ +#define check(cond) do { if (!(cond)) fail(); } while (0) + +/* Test runner */ +static void test(int (*func)(void), const char *name) { + int r = func(); + if (r == 0) { + test_passed++; + } else { + test_failed++; + printf("FAILED: %s (at line %d)\n", name, r); + } +} + +#endif /* __TEST_H__ */ diff --git a/test/tests.c b/test/tests.c new file mode 100644 index 00000000..44207461 --- /dev/null +++ b/test/tests.c @@ -0,0 +1,378 @@ +#include +#include +#include +#include + +#include "test.h" +#include "testutil.h" + +int test_empty(void) { + check(parse("{}", 1, 1, + JSMN_OBJECT, 0, 2, 0)); + check(parse("[]", 1, 1, + JSMN_ARRAY, 0, 2, 0)); + check(parse("[{},{}]", 3, 3, + JSMN_ARRAY, 0, 7, 2, + JSMN_OBJECT, 1, 3, 0, + JSMN_OBJECT, 4, 6, 0)); + return 0; +} + +int test_object(void) { + check(parse("{\"a\":0}", 3, 3, + JSMN_OBJECT, 0, 7, 1, + JSMN_STRING, "a", 1, + JSMN_PRIMITIVE, "0")); + check(parse("{\"a\":[]}", 3, 3, + JSMN_OBJECT, 0, 8, 1, + JSMN_STRING, "a", 1, + JSMN_ARRAY, 5, 7, 0)); + check(parse("{\"a\":{},\"b\":{}}", 5, 5, + JSMN_OBJECT, -1, -1, 2, + JSMN_STRING, "a", 1, + JSMN_OBJECT, -1, -1, 0, + JSMN_STRING, "b", 1, + JSMN_OBJECT, -1, -1, 0)); + check(parse("{\n \"Day\": 26,\n \"Month\": 9,\n \"Year\": 12\n }", 7, 7, + JSMN_OBJECT, -1, -1, 3, + JSMN_STRING, "Day", 1, + JSMN_PRIMITIVE, "26", + JSMN_STRING, "Month", 1, + JSMN_PRIMITIVE, "9", + JSMN_STRING, "Year", 1, + JSMN_PRIMITIVE, "12")); + check(parse("{\"a\": 0, \"b\": \"c\"}", 5, 5, + JSMN_OBJECT, -1, -1, 2, + JSMN_STRING, "a", 1, + JSMN_PRIMITIVE, 0, + JSMN_STRING, "b", 1, + JSMN_STRING, "c", 0)); + +#ifdef JSMN_STRICT + check(parse("{\"a\"\n0}", JSMN_ERROR_INVAL, 3)); + check(parse("{\"a\", 0}", JSMN_ERROR_INVAL, 3)); + check(parse("{\"a\": {2}}", JSMN_ERROR_INVAL, 3)); + check(parse("{\"a\": {2: 3}}", JSMN_ERROR_INVAL, 3)); + check(parse("{\"a\": {\"a\": 2 3}}", JSMN_ERROR_INVAL, 5)); + /* FIXME */ + /*check(parse("{\"a\"}", JSMN_ERROR_INVAL, 2));*/ + /*check(parse("{\"a\": 1, \"b\"}", JSMN_ERROR_INVAL, 4));*/ + /*check(parse("{\"a\",\"b\":1}", JSMN_ERROR_INVAL, 4));*/ + /*check(parse("{\"a\":1,}", JSMN_ERROR_INVAL, 4));*/ + /*check(parse("{\"a\":\"b\":\"c\"}", JSMN_ERROR_INVAL, 4));*/ + /*check(parse("{,}", JSMN_ERROR_INVAL, 4));*/ +#endif + return 0; +} + +int test_array(void) { + /* FIXME */ + /*check(parse("[10}", JSMN_ERROR_INVAL, 3));*/ + /*check(parse("[1,,3]", JSMN_ERROR_INVAL, 3)*/ + check(parse("[10]", 2, 2, + JSMN_ARRAY, -1, -1, 1, + JSMN_PRIMITIVE, "10")); + check(parse("{\"a\": 1]", JSMN_ERROR_INVAL, 3)); + /* FIXME */ + /*check(parse("[\"a\": 1]", JSMN_ERROR_INVAL, 3));*/ + return 0; +} + +int test_primitive(void) { + check(parse("{\"boolVar\" : true }", 3, 3, + JSMN_OBJECT, -1, -1, 1, + JSMN_STRING, "boolVar", 1, + JSMN_PRIMITIVE, "true")); + check(parse("{\"boolVar\" : false }", 3, 3, + JSMN_OBJECT, -1, -1, 1, + JSMN_STRING, "boolVar", 1, + JSMN_PRIMITIVE, "false")); + check(parse("{\"nullVar\" : null }", 3, 3, + JSMN_OBJECT, -1, -1, 1, + JSMN_STRING, "nullVar", 1, + JSMN_PRIMITIVE, "null")); + check(parse("{\"intVar\" : 12}", 3, 3, + JSMN_OBJECT, -1, -1, 1, + JSMN_STRING, "intVar", 1, + JSMN_PRIMITIVE, "12")); + check(parse("{\"floatVar\" : 12.345}", 3, 3, + JSMN_OBJECT, -1, -1, 1, + JSMN_STRING, "floatVar", 1, + JSMN_PRIMITIVE, "12.345")); + return 0; +} + +int test_string(void) { + check(parse("{\"strVar\" : \"hello world\"}", 3, 3, + JSMN_OBJECT, -1, -1, 1, + JSMN_STRING, "strVar", 1, + JSMN_STRING, "hello world", 0)); + check(parse("{\"strVar\" : \"escapes: \\/\\r\\n\\t\\b\\f\\\"\\\\\"}", 3, 3, + JSMN_OBJECT, -1, -1, 1, + JSMN_STRING, "strVar", 1, + JSMN_STRING, "escapes: \\/\\r\\n\\t\\b\\f\\\"\\\\", 0)); + check(parse("{\"strVar\": \"\"}", 3, 3, + JSMN_OBJECT, -1, -1, 1, + JSMN_STRING, "strVar", 1, + JSMN_STRING, "", 0)); + check(parse("{\"a\":\"\\uAbcD\"}", 3, 3, + JSMN_OBJECT, -1, -1, 1, + JSMN_STRING, "a", 1, + JSMN_STRING, "\\uAbcD", 0)); + check(parse("{\"a\":\"str\\u0000\"}", 3, 3, + JSMN_OBJECT, -1, -1, 1, + JSMN_STRING, "a", 1, + JSMN_STRING, "str\\u0000", 0)); + check(parse("{\"a\":\"\\uFFFFstr\"}", 3, 3, + JSMN_OBJECT, -1, -1, 1, + JSMN_STRING, "a", 1, + JSMN_STRING, "\\uFFFFstr", 0)); + check(parse("{\"a\":[\"\\u0280\"]}", 4, 4, + JSMN_OBJECT, -1, -1, 1, + JSMN_STRING, "a", 1, + JSMN_ARRAY, -1, -1, 1, + JSMN_STRING, "\\u0280", 0)); + + check(parse("{\"a\":\"str\\uFFGFstr\"}", JSMN_ERROR_INVAL, 3)); + check(parse("{\"a\":\"str\\u@FfF\"}", JSMN_ERROR_INVAL, 3)); + check(parse("{{\"a\":[\"\\u028\"]}", JSMN_ERROR_INVAL, 4)); + return 0; +} + +int test_partial_string(void) { + int i; + int r; + jsmn_parser p; + jsmntok_t tok[5]; + const char *js = "{\"x\": \"va\\\\ue\", \"y\": \"value y\"}"; + + jsmn_init(&p); + for (i = 1; i <= strlen(js); i++) { + r = jsmn_parse(&p, js, i, tok, sizeof(tok)/sizeof(tok[0])); + if (i == strlen(js)) { + check(r == 5); + check(tokeq(js, tok, 5, + JSMN_OBJECT, -1, -1, 2, + JSMN_STRING, "x", 1, + JSMN_STRING, "va\\\\ue", 0, + JSMN_STRING, "y", 1, + JSMN_STRING, "value y", 0)); + } else { + check(r == JSMN_ERROR_PART); + } + } + return 0; +} + +int test_partial_array(void) { +#ifdef JSMN_STRICT + int r; + int i; + jsmn_parser p; + jsmntok_t tok[10]; + const char *js = "[ 1, true, [123, \"hello\"]]"; + + jsmn_init(&p); + for (i = 1; i <= strlen(js); i++) { + r = jsmn_parse(&p, js, i, tok, sizeof(tok)/sizeof(tok[0])); + if (i == strlen(js)) { + check(r == 6); + check(tokeq(js, tok, 6, + JSMN_ARRAY, -1, -1, 3, + JSMN_PRIMITIVE, "1", + JSMN_PRIMITIVE, "true", + JSMN_ARRAY, -1, -1, 2, + JSMN_PRIMITIVE, "123", + JSMN_STRING, "hello", 0)); + } else { + check(r == JSMN_ERROR_PART); + } + } +#endif + return 0; +} + +int test_array_nomem(void) { + int i; + int r; + jsmn_parser p; + jsmntok_t toksmall[10], toklarge[10]; + const char *js; + + js = " [ 1, true, [123, \"hello\"]]"; + + for (i = 0; i < 6; i++) { + jsmn_init(&p); + memset(toksmall, 0, sizeof(toksmall)); + memset(toklarge, 0, sizeof(toklarge)); + r = jsmn_parse(&p, js, strlen(js), toksmall, i); + check(r == JSMN_ERROR_NOMEM); + + memcpy(toklarge, toksmall, sizeof(toksmall)); + + r = jsmn_parse(&p, js, strlen(js), toklarge, 10); + check(r >= 0); + check(tokeq(js, toklarge, 4, + JSMN_ARRAY, -1, -1, 3, + JSMN_PRIMITIVE, "1", + JSMN_PRIMITIVE, "true", + JSMN_ARRAY, -1, -1, 2, + JSMN_PRIMITIVE, "123", + JSMN_STRING, "hello", 0)); + } + return 0; +} + +int test_unquoted_keys(void) { +#ifndef JSMN_STRICT + int r; + jsmn_parser p; + jsmntok_t tok[10]; + const char *js; + + jsmn_init(&p); + js = "key1: \"value\"\nkey2 : 123"; + + r = jsmn_parse(&p, js, strlen(js), tok, 10); + check(r >= 0); + check(tokeq(js, tok, 4, + JSMN_PRIMITIVE, "key1", + JSMN_STRING, "value", 0, + JSMN_PRIMITIVE, "key2", + JSMN_PRIMITIVE, "123")); +#endif + return 0; +} + +int test_issue_22(void) { + int r; + jsmn_parser p; + jsmntok_t tokens[128]; + const char *js; + + js = "{ \"height\":10, \"layers\":[ { \"data\":[6,6], \"height\":10, " + "\"name\":\"Calque de Tile 1\", \"opacity\":1, \"type\":\"tilelayer\", " + "\"visible\":true, \"width\":10, \"x\":0, \"y\":0 }], " + "\"orientation\":\"orthogonal\", \"properties\": { }, \"tileheight\":32, " + "\"tilesets\":[ { \"firstgid\":1, \"image\":\"..\\/images\\/tiles.png\", " + "\"imageheight\":64, \"imagewidth\":160, \"margin\":0, \"name\":\"Tiles\", " + "\"properties\":{}, \"spacing\":0, \"tileheight\":32, \"tilewidth\":32 }], " + "\"tilewidth\":32, \"version\":1, \"width\":10 }"; + jsmn_init(&p); + r = jsmn_parse(&p, js, strlen(js), tokens, 128); + check(r >= 0); + return 0; +} + +int test_issue_27(void) { + const char *js = + "{ \"name\" : \"Jack\", \"age\" : 27 } { \"name\" : \"Anna\", "; + check(parse(js, JSMN_ERROR_PART, 8)); + return 0; +} + +int test_input_length(void) { + const char *js; + int r; + jsmn_parser p; + jsmntok_t tokens[10]; + + js = "{\"a\": 0}garbage"; + + jsmn_init(&p); + r = jsmn_parse(&p, js, 8, tokens, 10); + check(r == 3); + check(tokeq(js, tokens, 3, + JSMN_OBJECT, -1, -1, 1, + JSMN_STRING, "a", 1, + JSMN_PRIMITIVE, "0")); + return 0; +} + +int test_count(void) { + jsmn_parser p; + const char *js; + + js = "{}"; + jsmn_init(&p); + check(jsmn_parse(&p, js, strlen(js), NULL, 0) == 1); + + js = "[]"; + jsmn_init(&p); + check(jsmn_parse(&p, js, strlen(js), NULL, 0) == 1); + + js = "[[]]"; + jsmn_init(&p); + check(jsmn_parse(&p, js, strlen(js), NULL, 0) == 2); + + js = "[[], []]"; + jsmn_init(&p); + check(jsmn_parse(&p, js, strlen(js), NULL, 0) == 3); + + js = "[[], []]"; + jsmn_init(&p); + check(jsmn_parse(&p, js, strlen(js), NULL, 0) == 3); + + js = "[[], [[]], [[], []]]"; + jsmn_init(&p); + check(jsmn_parse(&p, js, strlen(js), NULL, 0) == 7); + + js = "[\"a\", [[], []]]"; + jsmn_init(&p); + check(jsmn_parse(&p, js, strlen(js), NULL, 0) == 5); + + js = "[[], \"[], [[]]\", [[]]]"; + jsmn_init(&p); + check(jsmn_parse(&p, js, strlen(js), NULL, 0) == 5); + + js = "[1, 2, 3]"; + jsmn_init(&p); + check(jsmn_parse(&p, js, strlen(js), NULL, 0) == 4); + + js = "[1, 2, [3, \"a\"], null]"; + jsmn_init(&p); + check(jsmn_parse(&p, js, strlen(js), NULL, 0) == 7); + + return 0; +} + + +int test_nonstrict(void) { +#ifndef JSMN_STRICT + const char *js; + js = "a: 0garbage"; + check(parse(js, 2, 2, + JSMN_PRIMITIVE, "a", + JSMN_PRIMITIVE, "0garbage")); + + js = "Day : 26\nMonth : Sep\n\nYear: 12"; + check(parse(js, 6, 6, + JSMN_PRIMITIVE, "Day", + JSMN_PRIMITIVE, "26", + JSMN_PRIMITIVE, "Month", + JSMN_PRIMITIVE, "Sep", + JSMN_PRIMITIVE, "Year", + JSMN_PRIMITIVE, "12")); +#endif + return 0; +} + +int main(void) { + test(test_empty, "test for a empty JSON objects/arrays"); + test(test_object, "test for a JSON objects"); + test(test_array, "test for a JSON arrays"); + test(test_primitive, "test primitive JSON data types"); + test(test_string, "test string JSON data types"); + + test(test_partial_string, "test partial JSON string parsing"); + test(test_partial_array, "test partial array reading"); + test(test_array_nomem, "test array reading with a smaller number of tokens"); + test(test_unquoted_keys, "test unquoted keys (like in JavaScript)"); + test(test_input_length, "test strings that are not null-terminated"); + test(test_issue_22, "test issue #22"); + test(test_issue_27, "test issue #27"); + test(test_count, "test tokens count estimation"); + test(test_nonstrict, "test for non-strict mode"); + printf("\nPASSED: %d\nFAILED: %d\n", test_passed, test_failed); + return (test_failed > 0); +} diff --git a/test/testutil.h b/test/testutil.h new file mode 100644 index 00000000..9a1eb2d6 --- /dev/null +++ b/test/testutil.h @@ -0,0 +1,94 @@ +#ifndef __TEST_UTIL_H__ +#define __TEST_UTIL_H__ + +#include "../jsmn.c" + +static int vtokeq(const char *s, jsmntok_t *t, int numtok, va_list ap) { + if (numtok > 0) { + int i, start, end, size; + int type; + char *value; + + size = -1; + value = NULL; + for (i = 0; i < numtok; i++) { + type = va_arg(ap, int); + if (type == JSMN_STRING) { + value = va_arg(ap, char *); + size = va_arg(ap, int); + start = end = -1; + } else if (type == JSMN_PRIMITIVE) { + value = va_arg(ap, char *); + start = end = size = -1; + } else { + start = va_arg(ap, int); + end = va_arg(ap, int); + size = va_arg(ap, int); + value = NULL; + } + if (t[i].type != type) { + printf("token %d type is %d, not %d\n", i, t[i].type, type); + return 0; + } + if (start != -1 && end != -1) { + if (t[i].start != start) { + printf("token %d start is %d, not %d\n", i, t[i].start, start); + return 0; + } + if (t[i].end != end ) { + printf("token %d end is %d, not %d\n", i, t[i].end, end); + return 0; + } + } + if (size != -1 && t[i].size != size) { + printf("token %d size is %d, not %d\n", i, t[i].size, size); + return 0; + } + + if (s != NULL && value != NULL) { + const char *p = s + t[i].start; + if (strlen(value) != t[i].end - t[i].start || + strncmp(p, value, t[i].end - t[i].start) != 0) { + printf("token %d value is %.*s, not %s\n", i, t[i].end-t[i].start, + s+t[i].start, value); + return 0; + } + } + } + } + return 1; +} + +static int tokeq(const char *s, jsmntok_t *tokens, int numtok, ...) { + int ok; + va_list args; + va_start(args, numtok); + ok = vtokeq(s, tokens, numtok, args); + va_end(args); + return ok; +} + +static int parse(const char *s, int status, int numtok, ...) { + int r; + int ok = 1; + va_list args; + jsmn_parser p; + jsmntok_t *t = malloc(numtok * sizeof(jsmntok_t)); + + jsmn_init(&p); + r = jsmn_parse(&p, s, strlen(s), t, numtok); + if (r != status) { + printf("status is %d, not %d\n", r, status); + return 0; + } + + if (status >= 0) { + va_start(args, numtok); + ok = vtokeq(s, t, numtok, args); + va_end(args); + } + free(t); + return ok; +} + +#endif /* __TEST_UTIL_H__ */