File: JSON_Tokenizer.cc

package info (click to toggle)
eclipse-titan 6.5.0-1
  • links: PTS
  • area: main
  • in suites: buster
  • size: 101,128 kB
  • sloc: cpp: 259,139; ansic: 47,560; yacc: 22,554; makefile: 14,074; sh: 12,630; lex: 9,101; xml: 5,362; java: 4,849; perl: 3,784; awk: 48; php: 32; python: 13
file content (445 lines) | stat: -rw-r--r-- 11,429 bytes parent folder | download
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
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
/******************************************************************************
 * Copyright (c) 2000-2018 Ericsson Telecom AB
 * All rights reserved. This program and the accompanying materials
 * are made available under the terms of the Eclipse Public License v2.0
 * which accompanies this distribution, and is available at
 * https://www.eclipse.org/org/documents/epl-2.0/EPL-2.0.html
 *
 * Contributors:
 *   Balasko, Jeno
 *   Baranyi, Botond
 *   Szabo, Bence Janos
 *
 ******************************************************************************/

#include <cstring>

#include "JSON_Tokenizer.hh"
#include "memory.h"
#include <cstdio>

static const char TABS[] =
  "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t"
  "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t"
  "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t"
  "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t";
const size_t MAX_TABS = sizeof(TABS) - 1; // 64

void JSON_Tokenizer::init(const char* p_buf, const size_t p_buf_len)
{
  if (p_buf != 0 && p_buf_len != 0) {
    buf_ptr = mcopystrn(p_buf, p_buf_len);
  } else {
    buf_ptr = 0;
  }
  buf_len = p_buf_len;
  buf_pos = 0;
  depth = 0;
  previous_token = JSON_TOKEN_NONE;
}

JSON_Tokenizer::~JSON_Tokenizer()
{
  Free(buf_ptr);
}

void JSON_Tokenizer::put_c(const char c)
{
  buf_ptr = mputprintf(buf_ptr, "%c", c);
  ++buf_len;
}
  
void JSON_Tokenizer::put_s(const char* s)
{
  buf_ptr = mputstr(buf_ptr, s);
  buf_len += strlen(s);
}

void JSON_Tokenizer::put_depth()
{
  put_s(TABS + ((depth > MAX_TABS) ? 0 : MAX_TABS - depth));
}

bool JSON_Tokenizer::skip_white_spaces()
{
  while(buf_pos < buf_len) {
    switch(buf_ptr[buf_pos]) {
    case ' ':
    case '\r':
    case '\n':
    case '\t':
    case '\f':
      ++buf_pos;
      break;
    default:
      return true;
    }
  }
  return false;
}

bool JSON_Tokenizer::check_for_string() 
{
  if ('\"' == buf_ptr[buf_pos]) {
    ++buf_pos;
  } else {
    return false;
  }
  while (buf_pos < buf_len) {
    if ('\"' == buf_ptr[buf_pos]) {
      return true;
    }
    else if ('\\' == buf_ptr[buf_pos]) {
      // skip escaped character (so escaped quotes (\") are not mistaken for the ending quotes)
      ++buf_pos;
    }
    ++buf_pos;
  }
  return false;
}

bool JSON_Tokenizer::check_for_number(bool* is_float /* = NULL */)
{
  bool first_digit = false; // first non-zero digit reached
  bool zero = false; // first zero digit reached
  bool decimal_point = false; // decimal point (.) reached
  bool exponent_mark = false; // exponential mark (e or E) reached
  bool exponent_sign = false; // sign of the exponential (- or +) reached
  
  if ('-' == buf_ptr[buf_pos]) {
    ++buf_pos;
  }
  
  while (buf_pos < buf_len) {
    switch(buf_ptr[buf_pos]) {
    case '.':
      if (decimal_point || exponent_mark || (!first_digit && !zero)) {
        return false;
      }
      decimal_point = true;
      first_digit = false;
      zero = false;
      break;
    case 'e':
    case 'E':
      if (exponent_mark || (!first_digit && !zero)) {
        return false;
      }
      exponent_mark = true;
      first_digit = false;
      zero = false;
      break;
    case '0':
      if (!first_digit && (exponent_mark || (!decimal_point && zero))) {
        return false;
      }
      zero = true;
      break;
    case '1':
    case '2':
    case '3':
    case '4':
    case '5':
    case '6':
    case '7':
    case '8':
    case '9':
      if (!first_digit && zero && (!decimal_point || exponent_mark)) {
        return false;
      }
      first_digit = true;
      break;
    case '-':
    case '+':
      if (exponent_sign || !exponent_mark || zero || first_digit) {
        return false;
      }
      exponent_sign = true;
      break;
    default:
      if (is_float != NULL) {
        *is_float = decimal_point || exponent_mark;
      }
      return first_digit || zero;
    }
    
    ++buf_pos; 
  }
  if (is_float != NULL) {
    *is_float = decimal_point || exponent_mark;
  }
  return first_digit || zero;
}

bool JSON_Tokenizer::check_for_separator()
{
  if (buf_pos < buf_len) {
    switch(buf_ptr[buf_pos]) {
    case ',':
      ++buf_pos;
      // no break
    case ':':
    case '{':
    case '}':
    case '[':
    case ']':
      return true;
    default:
      return false;
    }
  }
  return true;
}

bool JSON_Tokenizer::check_for_literal(const char* p_literal)
{
  size_t len = strlen(p_literal);
  
  if (buf_len - buf_pos >= len && 
      0 == strncmp(buf_ptr + buf_pos, p_literal, len)) {
    size_t start_pos = buf_pos;
    buf_pos += len;
    if (!skip_white_spaces() || check_for_separator()) {
      return true;
    } else {
      // must be followed by a separator (or only white spaces until the buffer ends) -> undo buffer action
      buf_pos = start_pos;
    }
  }
  return false;
}

size_t JSON_Tokenizer::get_next_token(json_token_t* p_token, char** p_token_str, size_t* p_str_len)
{
  size_t start_pos = buf_pos;
  *p_token = JSON_TOKEN_NONE;
  if (0 != p_token_str && 0 != p_str_len) {
    *p_token_str = 0;
    *p_str_len = 0;
  }
  
  if (skip_white_spaces()) {
    char c = buf_ptr[buf_pos];
    switch (c) {
    case '{':
    case '[':
      *p_token = ('{' == c) ? JSON_TOKEN_OBJECT_START : JSON_TOKEN_ARRAY_START;
      ++buf_pos;
      break;
    case '}':
    case ']':
      ++buf_pos;
      if (skip_white_spaces() && !check_for_separator()) {
        // must be followed by a separator (or only white spaces until the buffer ends)
        *p_token = JSON_TOKEN_ERROR;
      } else {
        *p_token = ('}' == c) ? JSON_TOKEN_OBJECT_END : JSON_TOKEN_ARRAY_END;
      }
      break;
    case '\"': {
      // string value or field name
      size_t string_start_pos = buf_pos;
      if(!check_for_string()) {
        // invalid string value
        *p_token = JSON_TOKEN_ERROR;
        break;
      }
      size_t string_end_pos = ++buf_pos; // step over the string's ending quotes
      if (skip_white_spaces() && ':' == buf_ptr[buf_pos]) {
        // name token - don't include the starting and ending quotes
        *p_token = JSON_TOKEN_NAME;
        if (0 != p_token_str && 0 != p_str_len) {
          *p_token_str = buf_ptr + string_start_pos + 1;
          *p_str_len = string_end_pos - string_start_pos - 2;
        }
        ++buf_pos;
      } else if (check_for_separator()) {
        // value token - include the starting and ending quotes
        *p_token = JSON_TOKEN_STRING;
        if (0 != p_token_str && 0 != p_str_len) {
          *p_token_str = buf_ptr + string_start_pos;
          *p_str_len = string_end_pos - string_start_pos;
        }
      } else {
        // value token, but there is no separator after it -> error
        *p_token = JSON_TOKEN_ERROR;
        break;
      }
      break;
    } // case: string value or field name
    default:
      if (('0' <= buf_ptr[buf_pos] && '9' >= buf_ptr[buf_pos]) ||
          '-' == buf_ptr[buf_pos]) {
        // number value
        size_t number_start_pos = buf_pos;
        if (!check_for_number()) {
          // invalid number
          *p_token = JSON_TOKEN_ERROR;
          break;
        }
        size_t number_length = buf_pos - number_start_pos;
        if (skip_white_spaces() && !check_for_separator()) {
          // must be followed by a separator (or only white spaces until the buffer ends)
          *p_token = JSON_TOKEN_ERROR;
          break;
        }
        *p_token = JSON_TOKEN_NUMBER;
        if (0 != p_token_str && 0 != p_str_len) {
          *p_token_str = buf_ptr + number_start_pos;
          *p_str_len = number_length;
        }
        break;
      } // if (number value)
      else if (check_for_literal("true")) {
        *p_token = JSON_TOKEN_LITERAL_TRUE;
        break;
      } 
      else if (check_for_literal("false")) {
        *p_token = JSON_TOKEN_LITERAL_FALSE;
        break;
      } 
      else if (check_for_literal("null")) {
        *p_token = JSON_TOKEN_LITERAL_NULL;
        break;
      }
      else {
        *p_token = JSON_TOKEN_ERROR;
        break;
      }
    } // switch (current char)
  } // if (skip_white_spaces())
  
  return buf_pos - start_pos;
}

void JSON_Tokenizer::put_separator() 
{
  if (JSON_TOKEN_NAME != previous_token && JSON_TOKEN_NONE != previous_token &&
      JSON_TOKEN_ARRAY_START != previous_token && JSON_TOKEN_OBJECT_START != previous_token) {
    put_c(',');
    if (pretty) {
      put_c('\n');
      put_depth();
    }
  }
}

int JSON_Tokenizer::put_next_token(json_token_t p_token, const char* p_token_str)
{
  size_t start_len = buf_len;
  switch(p_token) {
  case JSON_TOKEN_OBJECT_START: 
  case JSON_TOKEN_ARRAY_START: {
    put_separator();
    put_c( (JSON_TOKEN_OBJECT_START == p_token) ? '{' : '[' );
    if (pretty) {
      put_c('\n');
      ++depth;
      put_depth();
    }
    break;
  }
  case JSON_TOKEN_OBJECT_END: 
  case JSON_TOKEN_ARRAY_END: {
    if (pretty) {
      if (JSON_TOKEN_OBJECT_START != previous_token && JSON_TOKEN_ARRAY_START != previous_token) {
        put_c('\n');
        --depth;
        put_depth();
      } else if (MAX_TABS >= depth) {
        // empty object or array -> remove the extra tab added at the start token
        --depth;
        --buf_len;
        buf_ptr[buf_len] = 0;
      }    
    }
    put_c( (JSON_TOKEN_OBJECT_END == p_token) ? '}' : ']' );
    break;
  }
  case JSON_TOKEN_NUMBER:
  case JSON_TOKEN_STRING:
    put_separator();
    put_s(p_token_str);
    break;
  case JSON_TOKEN_LITERAL_TRUE:
    put_separator();
    put_s("true");
    break;
  case JSON_TOKEN_LITERAL_FALSE:
    put_separator();
    put_s("false");
    break;
  case JSON_TOKEN_LITERAL_NULL:
    put_separator();
    put_s("null");
    break;
  case JSON_TOKEN_NAME:
    put_separator();
    put_c('\"');
    put_s(p_token_str);
    if (pretty) {
      put_s("\" : ");
    } else {
      put_s("\":");
    }
    break;
  default:
    return 0;
  }
  
  previous_token = p_token;
  return buf_len - start_len;
}

void JSON_Tokenizer::put_raw_data(const char* p_data, size_t p_len)
{
  buf_ptr = mputstrn(buf_ptr, p_data, p_len);
  buf_len += p_len;
}

char* convert_to_json_string(const char* str)
{
  char* ret_val = mcopystrn("\"", 1);
  // control characters (like \n) cannot be placed in a JSON string, replace
  // them with JSON metacharacters
  // double quotes and backslashes need to be escaped, too
  size_t str_len = strlen(str);
  for (size_t i = 0; i < str_len; ++i) {
    switch (str[i]) {
    case '\n':
      ret_val = mputstrn(ret_val, "\\n", 2);
      break;
    case '\r':
      ret_val = mputstrn(ret_val, "\\r", 2);
      break;
    case '\t':
      ret_val = mputstrn(ret_val, "\\t", 2);
      break;
    case '\f':
      ret_val = mputstrn(ret_val, "\\f", 2);
      break;
    case '\b':
      ret_val = mputstrn(ret_val, "\\b", 2);
      break;
    case '\"':
      ret_val = mputstrn(ret_val, "\\\"", 2);
      break;
    case '\\':
      ret_val = mputstrn(ret_val, "\\\\", 2);
      break;
    default:
      if (str[i] < 32 && str[i] > 0) {
        // use the JSON \uHHHH notation for other control characters
        // (this is just for esthetic reasons, these wouldn't break the JSON 
        // string format)
        ret_val = mputprintf(ret_val, "\\u00%d%c", str[i] / 16,
          (str[i] % 16 < 10) ? (str[i] % 16 + '0') : (str[i] % 16 - 10 + 'A'));
      }
      else {
        ret_val = mputc(ret_val, str[i]);
      }
      break;
    }
  }
  return mputstrn(ret_val, "\"", 1);
}