emma
/
searpent
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

changed json parsing to jansson

This commit is contained in:
Emma Tebibyte 2023-06-15 13:20:05 -06:00
parent a799a25e5c
commit b78e4b0971
Signed by: emma
GPG Key ID: 6D661C738815E7DD
3 changed files with 27 additions and 498 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Makefile
View File

@ -10,7 +10,7 @@
PREFIX = /usr/local/bin
build: build_dir searpent.c
cc -o build/searpent -l curl searpent.c
cc -o build/searpent -l curl -l jansson searpent.c
build_dir:
mkdir -p build

471
jsmn.h
View File

@ -1,471 +0,0 @@
/*
* MIT License
*
* Copyright (c) 2010 Serge 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.
*/
#ifndef JSMN_H
#define JSMN_H
#include <stddef.h>
#ifdef __cplusplus
extern "C" {
#endif
#ifdef JSMN_STATIC
#define JSMN_API static
#else
#define JSMN_API extern
#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 << 0,
JSMN_ARRAY = 1 << 1,
JSMN_STRING = 1 << 2,
JSMN_PRIMITIVE = 1 << 3
} 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.
* type type (object, array, string etc.)
* start start position in JSON data string
* end end position in JSON data string
*/
typedef struct jsmntok {
jsmntype_t type;
int start;
int end;
int size;
#ifdef JSMN_PARENT_LINKS
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 jsmn_parser {
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
*/
JSMN_API 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.
*/
JSMN_API int jsmn_parse(jsmn_parser *parser, const char *js, const size_t len,
jsmntok_t *tokens, const unsigned int num_tokens);
#ifndef JSMN_HEADER
/**
* Allocates a fresh unused token from the token pool.
*/
static jsmntok_t *jsmn_alloc_token(jsmn_parser *parser, jsmntok_t *tokens,
const 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->parent = -1;
#endif
return tok;
}
/**
* Fills token type and boundaries.
*/
static void jsmn_fill_token(jsmntok_t *token, const jsmntype_t type,
const int start, const 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,
const size_t len, jsmntok_t *tokens,
const 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;
default:
/* to quiet a warning from gcc*/
break;
}
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,
const size_t len, jsmntok_t *tokens,
const size_t num_tokens) {
jsmntok_t *token;
int start = parser->pos;
/* Skip starting quote */
parser->pos++;
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;
}
/**
* Parse JSON string and fill tokens.
*/
JSMN_API int jsmn_parse(jsmn_parser *parser, const char *js, const size_t len,
jsmntok_t *tokens, const 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) {
jsmntok_t *t = &tokens[parser->toksuper];
#ifdef JSMN_STRICT
/* In strict mode an object or array can't become a key */
if (t->type == JSMN_OBJECT) {
return JSMN_ERROR_INVAL;
}
#endif
t->size++;
#ifdef JSMN_PARENT_LINKS
token->parent = 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) {
if (token->type != type || parser->toksuper == -1) {
return JSMN_ERROR_INVAL;
}
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++;
}
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) {
const 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++;
}
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.
*/
JSMN_API void jsmn_init(jsmn_parser *parser) {
parser->pos = 0;
parser->toknext = 0;
parser->toksuper = -1;
}
#endif /* JSMN_HEADER */
#ifdef __cplusplus
}
#endif
#endif /* JSMN_H */

52
searpent.c
View File

@ -22,7 +22,9 @@
#include <string.h>
#include <sysexits.h>
#include <curl/curl.h>
#include "jsmn.h"
#include <jansson.h>
#define SEARX_QUERY_JSON "search?format=json&q="
typedef struct curl_read_data_t {
size_t len;
@ -31,14 +33,14 @@ typedef struct curl_read_data_t {
size_t write_data(void *buffer, size_t size, size_t nmemb, void *userp) {
curl_read_data_t *data = (curl_read_data_t *)userp;
printf("recv'd %d\n", nmemb);
size_t old_len;
if (data->len == 0) {
data->len = nmemb;
data->data = (char *) malloc(nmemb);
memcpy(data->data, buffer, nmemb);
} else {
size_t old_len = data->len;
old_len = data->len;
data->len += nmemb;
data->data = (char *) realloc(data->data, data->len);
memcpy(data->data + old_len, buffer, nmemb);
@ -47,60 +49,58 @@ size_t write_data(void *buffer, size_t size, size_t nmemb, void *userp) {
return nmemb;
}
curl_read_data_t search(char *term) {
curl_read_data_t search(char *argv[], char *term) {
char *url = "https://searx.mxchange.org/";
size_t buf_size = strlen(url) + strlen(term) + 32;
size_t buf_size = sizeof(SEARX_QUERY_JSON) + strlen(url) + strlen(term);
char *search_url = malloc(buf_size);
snprintf(search_url, buf_size, "%ssearch?q=%s&format=json", url, term);
char *error;
CURL *handle;
CURLcode res;
snprintf(search_url, buf_size, "%s%s%s", url, SEARX_QUERY_JSON, term);
curl_read_data_t json;
json.len = 0;
json.data = NULL;
CURL *handle = curl_easy_init();
handle = curl_easy_init();
if (handle) {
CURLcode res;
char error[CURL_ERROR_SIZE];
error[CURL_ERROR_SIZE];
curl_easy_setopt(handle, CURLOPT_URL, search_url);
curl_easy_setopt(handle, CURLOPT_WRITEFUNCTION, write_data);
curl_easy_setopt(handle, CURLOPT_WRITEDATA, &json);
curl_easy_setopt(handle, CURLOPT_ERRORBUFFER, error);
res = curl_easy_perform(handle);
curl_easy_cleanup(handle);
puts(error);
fprintf(stderr, "%s: %s", argv[0], error);
} else {
puts("failed to init curl\n");
fprintf(stderr, "%s: failed to initialize curl.\n");
}
return json;
}
void parse_json(curl_read_data_t json) {
jsmn_parser parser;
jsmntok_t tokens[json.len];
jsmn_init(&parser);
int tokens_parsed = jsmn_parse(
&parser,
json.data,
json.len,
tokens,
json.len
);
void parse_json(char *argv[], char* json) {
int out;
json_error_t *error;
json_t *json_val = json_loads(json, JSON_DECODE_ANY, error);
out = json_unpack(json_val, "{s:o}");
}
int main(int argc, char *argv[]) {
curl_read_data_t json;
if (argc < 1) {
printf("Usage: %s terms...", argv[0]);
fprintf(stderr, "Usage: %s terms...", argv[0]);
return EX_USAGE;
}
for (int i = 1; i < argc; i++) {
curl_read_data_t json = search(argv[i]);
printf("total recv'd: %d\n", json.len);
json = search(argv, argv[i]);
write(1, json.data, json.len);
parse_json(json);
parse_json(argv, json.data);
}
return EX_OK;
}