Repository navigation
Expand file tree
/
Copy pathJSON.php
More file actions
648 lines (548 loc) · 27.9 KB
/
Copy pathJSON.php
File metadata and controls
648 lines (548 loc) · 27.9 KB
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
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
<?php
/* vim: set expandtab tabstop=4 shiftwidth=4 softtabstop=4: */
/**
* Converts to and from JSON format.
*
* JSON (JavaScript Object Notation) is a lightweight data-interchange
* format. It is easy for humans to read and write. It is easy for machines
* to parse and generate. It is based on a subset of the JavaScript
* Programming Language, Standard ECMA-262 3rd Edition - December 1999.
* This feature can also be found in Python. JSON is a text format that is
* completely language independent but uses conventions that are familiar
* to programmers of the C-family of languages, including C, C++, C#, Java,
* JavaScript, Perl, TCL, and many others. These properties make JSON an
* ideal data-interchange language.
*
* This package provides a simple encoder and decoder for JSON notation. It
* is intended for use with client-side Javascript applications that make
* use of HTTPRequest to perform server communication functions - data can
* be encoded into JSON notation for use in a client-side javascript, or
* decoded from incoming Javascript requests. JSON format is native to
* Javascript, and can be directly eval()'ed with no further parsing
* overhead
*
* All strings should be in ASCII or UTF-8 format!
*
* PHP versions 4 and 5
*
* LICENSE: Redistribution and use in source and binary forms, with or
* without modification, are permitted provided that the following
* conditions are met: Redistributions of source code must retain the
* above copyright notice, this list of conditions and the following
* disclaimer. 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.
*
* THIS SOFTWARE IS PROVIDED ``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 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.
*
* @author Michal Migurski <mike-json@teczno.com>
* @author Matt Knapp <mdknapp[at]gmail[dot]com>
* @author Brett Stimmerman <brettstimmerman[at]gmail[dot]com>
* @copyright 2005 Michal Migurski
* @license http://www.freebsd.org/copyright/freebsd-license.html
* @link http://pear.php.net/pepr/pepr-proposal-show.php?id=198
*/
// for DokuWiki
if(!defined('DOKU_INC')) die('meh.');
/**
* Marker constant for JSON::decode(), used to flag stack state
*/
define('JSON_SLICE', 1);
/**
* Marker constant for JSON::decode(), used to flag stack state
*/
define('JSON_IN_STR', 2);
/**
* Marker constant for JSON::decode(), used to flag stack state
*/
define('JSON_IN_ARR', 4);
/**
* Marker constant for JSON::decode(), used to flag stack state
*/
define('JSON_IN_OBJ', 8);
/**
* Marker constant for JSON::decode(), used to flag stack state
*/
define('JSON_IN_CMT', 16);
/**
* Behavior switch for JSON::decode()
*/
define('JSON_LOOSE_TYPE', 10);
/**
* Behavior switch for JSON::decode()
*/
define('JSON_STRICT_TYPE', 11);
/**
* Converts to and from JSON format.
*/
class JSON {
/**
* Disables the use of PHP5's native json_decode()
*
* You shouldn't change this usually because the native function is much
* faster. However, this non-native will also parse slightly broken JSON
* which might be handy when talking to a non-conform endpoint
*/
public $skipnative = false;
/**
* constructs a new JSON instance
*
* @param int $use object behavior: when encoding or decoding,
* be loose or strict about object/array usage
*
* possible values:
* JSON_STRICT_TYPE - strict typing, default
* "{...}" syntax creates objects in decode.
* JSON_LOOSE_TYPE - loose typing
* "{...}" syntax creates associative arrays in decode.
*/
function JSON($use=JSON_STRICT_TYPE) {
$this->use = $use;
}
/**
* encodes an arbitrary variable into JSON format
* If available the native PHP JSON implementation is used.
*
* @param mixed $var any number, boolean, string, array, or object to be encoded.
* see argument 1 to JSON() above for array-parsing behavior.
* if var is a strng, note that encode() always expects it
* to be in ASCII or UTF-8 format!
*
* @return string JSON string representation of input var
* @access public
*/
function encode($var) {
if (!$this->skipnative && function_exists('json_encode')){
return json_encode($var);
}
switch (gettype($var)) {
case 'boolean':
return $var ? 'true' : 'false';
case 'NULL':
return 'null';
case 'integer':
return sprintf('%d', $var);
case 'double':
case 'float':
return sprintf('%f', $var);
case 'string':
// STRINGS ARE EXPECTED TO BE IN ASCII OR UTF-8 FORMAT
$ascii = '';
$strlen_var = strlen($var);
/*
* Iterate over every character in the string,
* escaping with a slash or encoding to UTF-8 where necessary
*/
for ($c = 0; $c < $strlen_var; ++$c) {
$ord_var_c = ord($var{$c});
switch ($ord_var_c) {
case 0x08:
$ascii .= '\b';
break;
case 0x09:
$ascii .= '\t';
break;
case 0x0A:
$ascii .= '\n';
break;
case 0x0C:
$ascii .= '\f';
break;
case 0x0D:
$ascii .= '\r';
break;
case 0x22:
case 0x2F:
case 0x5C:
// double quote, slash, slosh
$ascii .= '\\'.$var{$c};
break;
case (($ord_var_c >= 0x20) && ($ord_var_c <= 0x7F)):
// characters U-00000000 - U-0000007F (same as ASCII)
$ascii .= $var{$c};
break;
case (($ord_var_c & 0xE0) == 0xC0):
// characters U-00000080 - U-000007FF, mask 110XXXXX
// see http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8
$char = pack('C*', $ord_var_c, ord($var{$c+1}));
$c+=1;
//$utf16 = mb_convert_encoding($char, 'UTF-16', 'UTF-8');
$utf16 = utf8_to_utf16be($char);
$ascii .= sprintf('\u%04s', bin2hex($utf16));
break;
case (($ord_var_c & 0xF0) == 0xE0):
// characters U-00000800 - U-0000FFFF, mask 1110XXXX
// see http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8
$char = pack('C*', $ord_var_c,
ord($var{$c+1}),
ord($var{$c+2}));
$c+=2;
//$utf16 = mb_convert_encoding($char, 'UTF-16', 'UTF-8');
$utf16 = utf8_to_utf16be($char);
$ascii .= sprintf('\u%04s', bin2hex($utf16));
break;
case (($ord_var_c & 0xF8) == 0xF0):
// characters U-00010000 - U-001FFFFF, mask 11110XXX
// see http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8
$char = pack('C*', $ord_var_c,
ord($var{$c+1}),
ord($var{$c+2}),
ord($var{$c+3}));
$c+=3;
//$utf16 = mb_convert_encoding($char, 'UTF-16', 'UTF-8');
$utf16 = utf8_to_utf16be($char);
$ascii .= sprintf('\u%04s', bin2hex($utf16));
break;
case (($ord_var_c & 0xFC) == 0xF8):
// characters U-00200000 - U-03FFFFFF, mask 111110XX
// see http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8
$char = pack('C*', $ord_var_c,
ord($var{$c+1}),
ord($var{$c+2}),
ord($var{$c+3}),
ord($var{$c+4}));
$c+=4;
//$utf16 = mb_convert_encoding($char, 'UTF-16', 'UTF-8');
$utf16 = utf8_to_utf16be($char);
$ascii .= sprintf('\u%04s', bin2hex($utf16));
break;
case (($ord_var_c & 0xFE) == 0xFC):
// characters U-04000000 - U-7FFFFFFF, mask 1111110X
// see http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8
$char = pack('C*', $ord_var_c,
ord($var{$c+1}),
ord($var{$c+2}),
ord($var{$c+3}),
ord($var{$c+4}),
ord($var{$c+5}));
$c+=5;
//$utf16 = mb_convert_encoding($char, 'UTF-16', 'UTF-8');
$utf16 = utf8_to_utf16be($char);
$ascii .= sprintf('\u%04s', bin2hex($utf16));
break;
}
}
return '"'.$ascii.'"';
case 'array':
/*
* As per JSON spec if any array key is not an integer
* we must treat the the whole array as an object. We
* also try to catch a sparsely populated associative
* array with numeric keys here because some JS engines
* will create an array with empty indexes up to
* max_index which can cause memory issues and because
* the keys, which may be relevant, will be remapped
* otherwise.
*
* As per the ECMA and JSON specification an object may
* have any string as a property. Unfortunately due to
* a hole in the ECMA specification if the key is a
* ECMA reserved word or starts with a digit the
* parameter is only accessible using ECMAScript's
* bracket notation.
*/
// treat as a JSON object
if (is_array($var) && count($var) && (array_keys($var) !== range(0, count($var) - 1))) {
return sprintf('{%s}', join(',', array_map(array($this, 'name_value'),
array_keys($var),
array_values($var))));
}
// treat it like a regular array
return sprintf('[%s]', join(',', array_map(array($this, 'encode'), $var)));
case 'object':
$vars = get_object_vars($var);
return sprintf('{%s}', join(',', array_map(array($this, 'name_value'),
array_keys($vars),
array_values($vars))));
default:
return '';
}
}
/**
* encodes an arbitrary variable into JSON format, alias for encode()
*/
function enc($var) {
return $this->encode($var);
}
/** function name_value
* array-walking function for use in generating JSON-formatted name-value pairs
*
* @param string $name name of key to use
* @param mixed $value reference to an array element to be encoded
*
* @return string JSON-formatted name-value pair, like '"name":value'
* @access private
*/
function name_value($name, $value) {
return (sprintf("%s:%s", $this->encode(strval($name)), $this->encode($value)));
}
/**
* reduce a string by removing leading and trailing comments and whitespace
*
* @param $str string string value to strip of comments and whitespace
*
* @return string string value stripped of comments and whitespace
* @access private
*/
function reduce_string($str) {
$str = preg_replace(array(
// eliminate single line comments in '// ...' form
'#^\s*//(.+)$#m',
// eliminate multi-line comments in '/* ... */' form, at start of string
'#^\s*/\*(.+)\*/#Us',
// eliminate multi-line comments in '/* ... */' form, at end of string
'#/\*(.+)\*/\s*$#Us'
), '', $str);
// eliminate extraneous space
return trim($str);
}
/**
* decodes a JSON string into appropriate variable
* If available the native PHP JSON implementation is used.
*
* @param string $str JSON-formatted string
*
* @return mixed number, boolean, string, array, or object
* corresponding to given JSON input string.
* See argument 1 to JSON() above for object-output behavior.
* Note that decode() always returns strings
* in ASCII or UTF-8 format!
* @access public
*/
function decode($str) {
if (!$this->skipnative && function_exists('json_decode')){
return json_decode($str,($this->use == JSON_LOOSE_TYPE));
}
$str = $this->reduce_string($str);
switch (strtolower($str)) {
case 'true':
return true;
case 'false':
return false;
case 'null':
return null;
default:
if (is_numeric($str)) {
// Lookie-loo, it's a number
// This would work on its own, but I'm trying to be
// good about returning integers where appropriate:
// return (float)$str;
// Return float or int, as appropriate
return ((float)$str == (integer)$str)
? (integer)$str
: (float)$str;
} elseif (preg_match('/^("|\').+("|\')$/s', $str, $m) && $m[1] == $m[2]) {
// STRINGS RETURNED IN UTF-8 FORMAT
$delim = substr($str, 0, 1);
$chrs = substr($str, 1, -1);
$utf8 = '';
$strlen_chrs = strlen($chrs);
for ($c = 0; $c < $strlen_chrs; ++$c) {
$substr_chrs_c_2 = substr($chrs, $c, 2);
$ord_chrs_c = ord($chrs{$c});
switch ($substr_chrs_c_2) {
case '\b':
$utf8 .= chr(0x08);
$c+=1;
break;
case '\t':
$utf8 .= chr(0x09);
$c+=1;
break;
case '\n':
$utf8 .= chr(0x0A);
$c+=1;
break;
case '\f':
$utf8 .= chr(0x0C);
$c+=1;
break;
case '\r':
$utf8 .= chr(0x0D);
$c+=1;
break;
case '\\"':
case '\\\'':
case '\\\\':
case '\\/':
if (($delim == '"' && $substr_chrs_c_2 != '\\\'') ||
($delim == "'" && $substr_chrs_c_2 != '\\"')) {
$utf8 .= $chrs{++$c};
}
break;
default:
if (preg_match('/\\\u[0-9A-F]{4}/i', substr($chrs, $c, 6))) {
// single, escaped unicode character
$utf16 = chr(hexdec(substr($chrs, ($c+2), 2)))
. chr(hexdec(substr($chrs, ($c+4), 2)));
//$utf8 .= mb_convert_encoding($utf16, 'UTF-8', 'UTF-16');
$utf8 .= utf16be_to_utf8($utf16);
$c+=5;
} elseif(($ord_chrs_c >= 0x20) && ($ord_chrs_c <= 0x7F)) {
$utf8 .= $chrs{$c};
} elseif(($ord_chrs_c & 0xE0) == 0xC0) {
// characters U-00000080 - U-000007FF, mask 110XXXXX
//see http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8
$utf8 .= substr($chrs, $c, 2);
$c += 1;
} elseif(($ord_chrs_c & 0xF0) == 0xE0) {
// characters U-00000800 - U-0000FFFF, mask 1110XXXX
// see http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8
$utf8 .= substr($chrs, $c, 3);
$c += 2;
} elseif(($ord_chrs_c & 0xF8) == 0xF0) {
// characters U-00010000 - U-001FFFFF, mask 11110XXX
// see http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8
$utf8 .= substr($chrs, $c, 4);
$c += 3;
} elseif(($ord_chrs_c & 0xFC) == 0xF8) {
// characters U-00200000 - U-03FFFFFF, mask 111110XX
// see http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8
$utf8 .= substr($chrs, $c, 5);
$c += 4;
} elseif(($ord_chrs_c & 0xFE) == 0xFC) {
// characters U-04000000 - U-7FFFFFFF, mask 1111110X
// see http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8
$utf8 .= substr($chrs, $c, 6);
$c += 5;
}
break;
}
}
return $utf8;
} elseif (preg_match('/^\[.*\]$/s', $str) || preg_match('/^\{.*\}$/s', $str)) {
// array, or object notation
if ($str{0} == '[') {
$stk = array(JSON_IN_ARR);
$arr = array();
} else {
if ($this->use == JSON_LOOSE_TYPE) {
$stk = array(JSON_IN_OBJ);
$obj = array();
} else {
$stk = array(JSON_IN_OBJ);
$obj = new stdClass();
}
}
array_push($stk, array('what' => JSON_SLICE,
'where' => 0,
'delim' => false));
$chrs = substr($str, 1, -1);
$chrs = $this->reduce_string($chrs);
if ($chrs == '') {
if (reset($stk) == JSON_IN_ARR) {
return $arr;
} else {
return $obj;
}
}
//print("\nparsing {$chrs}\n");
$strlen_chrs = strlen($chrs);
for ($c = 0; $c <= $strlen_chrs; ++$c) {
$top = end($stk);
$substr_chrs_c_2 = substr($chrs, $c, 2);
if (($c == $strlen_chrs) || (($chrs{$c} == ',') && ($top['what'] == JSON_SLICE))) {
// found a comma that is not inside a string, array, etc.,
// OR we've reached the end of the character list
$slice = substr($chrs, $top['where'], ($c - $top['where']));
array_push($stk, array('what' => JSON_SLICE, 'where' => ($c + 1), 'delim' => false));
//print("Found split at {$c}: ".substr($chrs, $top['where'], (1 + $c - $top['where']))."\n");
if (reset($stk) == JSON_IN_ARR) {
// we are in an array, so just push an element onto the stack
array_push($arr, $this->decode($slice));
} elseif (reset($stk) == JSON_IN_OBJ) {
// we are in an object, so figure
// out the property name and set an
// element in an associative array,
// for now
if (preg_match('/^\s*(["\'].*[^\\\]["\'])\s*:\s*(\S.*),?$/Uis', $slice, $parts)) {
// "name":value pair
$key = $this->decode($parts[1]);
$val = $this->decode($parts[2]);
if ($this->use == JSON_LOOSE_TYPE) {
$obj[$key] = $val;
} else {
$obj->$key = $val;
}
} elseif (preg_match('/^\s*(\w+)\s*:\s*(\S.*),?$/Uis', $slice, $parts)) {
// name:value pair, where name is unquoted
$key = $parts[1];
$val = $this->decode($parts[2]);
if ($this->use == JSON_LOOSE_TYPE) {
$obj[$key] = $val;
} else {
$obj->$key = $val;
}
}
}
} elseif ((($chrs{$c} == '"') || ($chrs{$c} == "'")) && ($top['what'] != JSON_IN_STR)) {
// found a quote, and we are not inside a string
array_push($stk, array('what' => JSON_IN_STR, 'where' => $c, 'delim' => $chrs{$c}));
//print("Found start of string at {$c}\n");
} elseif (($chrs{$c} == $top['delim']) &&
($top['what'] == JSON_IN_STR) &&
((strlen(substr($chrs, 0, $c)) - strlen(rtrim(substr($chrs, 0, $c), '\\'))) % 2 != 1)) {
// found a quote, we're in a string, and it's not escaped
// we know that it's not escaped becase there is _not_ an
// odd number of backslashes at the end of the string so far
array_pop($stk);
//print("Found end of string at {$c}: ".substr($chrs, $top['where'], (1 + 1 + $c - $top['where']))."\n");
} elseif (($chrs{$c} == '[') &&
in_array($top['what'], array(JSON_SLICE, JSON_IN_ARR, JSON_IN_OBJ))) {
// found a left-bracket, and we are in an array, object, or slice
array_push($stk, array('what' => JSON_IN_ARR, 'where' => $c, 'delim' => false));
//print("Found start of array at {$c}\n");
} elseif (($chrs{$c} == ']') && ($top['what'] == JSON_IN_ARR)) {
// found a right-bracket, and we're in an array
array_pop($stk);
//print("Found end of array at {$c}: ".substr($chrs, $top['where'], (1 + $c - $top['where']))."\n");
} elseif (($chrs{$c} == '{') &&
in_array($top['what'], array(JSON_SLICE, JSON_IN_ARR, JSON_IN_OBJ))) {
// found a left-brace, and we are in an array, object, or slice
array_push($stk, array('what' => JSON_IN_OBJ, 'where' => $c, 'delim' => false));
//print("Found start of object at {$c}\n");
} elseif (($chrs{$c} == '}') && ($top['what'] == JSON_IN_OBJ)) {
// found a right-brace, and we're in an object
array_pop($stk);
//print("Found end of object at {$c}: ".substr($chrs, $top['where'], (1 + $c - $top['where']))."\n");
} elseif (($substr_chrs_c_2 == '/*') &&
in_array($top['what'], array(JSON_SLICE, JSON_IN_ARR, JSON_IN_OBJ))) {
// found a comment start, and we are in an array, object, or slice
array_push($stk, array('what' => JSON_IN_CMT, 'where' => $c, 'delim' => false));
$c++;
//print("Found start of comment at {$c}\n");
} elseif (($substr_chrs_c_2 == '*/') && ($top['what'] == JSON_IN_CMT)) {
// found a comment end, and we're in one now
array_pop($stk);
$c++;
for ($i = $top['where']; $i <= $c; ++$i)
$chrs = substr_replace($chrs, ' ', $i, 1);
//print("Found end of comment at {$c}: ".substr($chrs, $top['where'], (1 + $c - $top['where']))."\n");
}
}
if (reset($stk) == JSON_IN_ARR) {
return $arr;
} elseif (reset($stk) == JSON_IN_OBJ) {
return $obj;
}
}
}
}
/**
* decodes a JSON string into appropriate variable; alias for decode()
*/
function dec($var) {
return $this->decode($var);
}
}