summaryrefslogtreecommitdiff
path: root/protocols/Twitter/tinyjson.hpp
blob: 19e1210d84cbaeaf16ea424dc2e80e000ebdd0ac (plain)
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
/*
 * TinyJson 1.3.0
 * A Minimalistic JSON Reader Based On Boost.Spirit, Boost.Any, and Boost.Smart_Ptr.
 *
 * Copyright (c) 2008 Thomas Jansen (thomas@beef.de)
 *
 * Distributed under the Boost Software License, Version 1.0. (See accompanying
 * file LICENSE_1_0.txt or copy at http://www.boost.org/LICENSE_1_0.txt)
 *
 * See http://blog.beef.de/projects/tinyjson/ for documentation.
 *
 * (view source with tab-size = 3)
 *
 * 16 Mar 2009 - allow root of JSON to be array (Jim Porter)
 * 29 Mar 2008 - use strict_real_p for number parsing, small cleanup (Thomas Jansen)
 * 26 Mar 2008 - made json::grammar a template (Boris Schaeling)
 * 20 Mar 2008 - optimized by using boost::shared_ptr (Thomas Jansen)
 * 29 Jan 2008 - Small bugfixes (Thomas Jansen)
 * 04 Jan 2008 - Released to the public (Thomas Jansen)
 * 13 Nov 2007 - initial release (Thomas Jansen) *
 *
 * 29 Mar 2008
 */


#ifndef	TINYJSON_HPP
#define	TINYJSON_HPP

#include	<boost/shared_ptr.hpp>
#include	<boost/any.hpp>
#include	<boost/spirit/core.hpp>
#include	<boost/spirit/utility/loops.hpp>
#include	<boost/lexical_cast.hpp>

#include	<string>
#include	<stack>
#include	<utility>
#include	<deque>
#include	<map>


namespace json
{
	boost::spirit::int_parser<long long> const
        longlong_p   = boost::spirit::int_parser<long long>();

	// ==========================================================================================================
	// ===                                    U N I C O D E _ C O N V E R T                                   ===
	// ==========================================================================================================

	template< typename Char >
	struct unicodecvt
	{
		static std::basic_string< Char > convert(int iUnicode)
		{
			return std::basic_string< Char >(1, static_cast< Char >(iUnicode));
		}
	};


	// ---[ TEMPLATE SPECIALIZATION FOR CHAR ]--------------------------------------------------------------------

	template<>
	struct unicodecvt< char >
	{
		static std::string convert(int iUnicode)
		{
			std::string strString;

			if (iUnicode < 0x0080)
			{
				// character 0x0000 - 0x007f...

				strString.push_back(0x00 | ((iUnicode & 0x007f) >> 0));
			}
			else if (iUnicode < 0x0800)
			{
				// character 0x0080 - 0x07ff...

				strString.push_back(0xc0 | ((iUnicode & 0x07c0) >> 6));
				strString.push_back(0x80 | ((iUnicode & 0x003f) >> 0));
			}
			else
			{
				// character 0x0800 - 0xffff...

				strString.push_back(0xe0 | ((iUnicode & 0x00f000) >> 12));
				strString.push_back(0x80 | ((iUnicode & 0x000fc0) >>  6));
				strString.push_back(0x80 | ((iUnicode & 0x00003f) >>  0));
			}

			return strString;
		}
	};


	// ==========================================================================================================
	// ===                                   T H E   J S O N   G R A M M A R                                  ===
	// ==========================================================================================================

	template< typename Char >
	class grammar : public boost::spirit::grammar< grammar< Char > >
	{
	public:

		// ---[ TYPEDEFINITIONS ]---------------------------------------------------------------------------------

		typedef	boost::shared_ptr< boost::any >							variant;			//  pointer to a shared variant

		typedef	std::stack< variant >										stack;			//     a stack of json variants
		typedef	std::pair< std::basic_string< Char >, variant >		pair;				// a pair as it appears in json

		typedef	std::deque< variant >										array;			//    an array of json variants
		typedef	std::map< std::basic_string< Char >, variant >		object;			//    an object with json pairs

	protected:

		// ---[ SEMANTIC ACTION: PUSH A STRING ON THE STACK (AND ENCODE AS UTF-8) ]-------------------------------

		struct push_string
		{
			stack & m_stack;
			push_string(stack & stack) : m_stack(stack) { }

			template <typename Iterator>
			void operator() (Iterator szStart, Iterator szEnd) const
			{
				// 1: skip the quotes...

				++szStart;
				--szEnd;

				// 2: traverse through the original string and check for escape codes..

				std::basic_string< typename Iterator::value_type > strString;

				while(szStart < szEnd)
				{
					// 2.1: if it's no escape code, just append to the resulting string...

					if (*szStart != static_cast< typename Iterator::value_type >('\\'))
					{
						// 2.1.1: append the character...

						strString.push_back(*szStart);
					}
					else
					{
						// 2.1.2: otherwise, check the escape code...

						++szStart;

						switch(*szStart)
						{
							default:
								
								strString.push_back(*szStart);
								break;
							
							case 'b':
								
								strString.push_back(static_cast< typename Iterator::value_type >('\b'));
								break;
							
							case 'f':
								
								strString.push_back(static_cast< typename Iterator::value_type >('\f'));
								break;
							
							case 'n':
								
								strString.push_back(static_cast< typename Iterator::value_type >('\n'));
								break;
							
							case 'r':
								
								strString.push_back(static_cast< typename Iterator::value_type >('\r'));
								break;

							case 't':
								
								strString.push_back(static_cast< typename Iterator::value_type >('\t'));
								break;

							case 'u':
							{
								// 2.1.2.1: convert the following hex value into an int...

								int iUnicode;
								std::basic_istringstream< Char >(std::basic_string< typename Iterator::value_type >(&szStart[1], 4)) >> std::hex >> iUnicode;

								szStart += 4;

								// 2.1.2.2: append the unicode int...

								strString.append(unicodecvt< typename Iterator::value_type >::convert(iUnicode));
							}
						}
					}

					// 2.2: go on with the next character...

					++szStart;
				}

				// 3: finally, push the string on the stack...

				m_stack.push(variant(new boost::any(strString)));
			}
		};


		// ---[ SEMANTIC ACTION: PUSH A REAL ON THE STACK ]-------------------------------------------------------

		struct push_double
		{
			stack & m_stack;
			push_double(stack & stack) : m_stack(stack) { }

			void operator() (double dValue) const
			{
				m_stack.push(variant(new boost::any(dValue)));
			}
		};


		// ---[ SEMANTIC ACTION: PUSH AN INT ON THE STACK ]-------------------------------------------------------

		struct push_int
		{
			stack & m_stack;
			push_int(stack & stack) : m_stack(stack) { }

			void operator() (long long iValue) const
			{
				m_stack.push(variant(new boost::any(iValue)));
			}
		};


		// ---[ SEMANTIC ACTION: PUSH A BOOLEAN ON THE STACK ]----------------------------------------------------

		struct push_boolean
		{
			stack & m_stack;
			push_boolean(stack & stack) : m_stack(stack) { }

			template <typename Iterator>
			void operator() (Iterator szStart, Iterator /* szEnd */ ) const
			{
				// 1: push a boolean that is "true" if the string starts with 't' and "false" otherwise...

				m_stack.push(variant(new boost::any(*szStart == static_cast< typename Iterator::value_type >('t'))));
			}
		};


		// ---[ SEMANTIC ACTION: PUSH A NULL VALUE ON THE STACK ]-------------------------------------------------

		struct push_null
		{
			stack & m_stack;
			push_null(stack & stack) : m_stack(stack) { }

			template <typename Iterator>
			void operator() (Iterator /* szStart */ , Iterator /* szEnd */ ) const
			{
				m_stack.push(variant(new boost::any()));
			}
		};


		// ---[ SEMANTIC ACTION: CREATE A "JSON PAIR" ON THE STACK ]----------------------------------------------

		struct create_pair
		{
			stack & m_stack;
			create_pair(stack & stack) : m_stack(stack) { }

			template <typename Iterator>
			void operator() (Iterator /* szStart */, Iterator /* szEnd */ ) const
			{
				// 1: get the variant from the stack...

				variant var = m_stack.top();
				m_stack.pop();

				// 2: get the name from the stack...

				std::basic_string< typename Iterator::value_type > strName;

				try
				{
					strName = boost::any_cast< std::basic_string< typename Iterator::value_type > >(*m_stack.top());
				}
				catch(boost::bad_any_cast &) { /* NOTHING */ }

				m_stack.pop();

				// 3: push a pair of both on the stack...

				m_stack.push(variant(new boost::any(pair(strName, var))));
			}
		};


		// ---[ SEMANTIC ACTION: BEGIN AN ARRAY ]-----------------------------------------------------------------

		class	array_delimiter { /* EMPTY CLASS */ };

		struct begin_array
		{
			stack & m_stack;
			begin_array(stack & stack) : m_stack(stack) { }

			template <typename Iterator>
			void operator() (Iterator /* cCharacter */) const
			{
				m_stack.push(variant(new boost::any(array_delimiter())));
			}
		};


		// ---[ SEMANTIC ACTION: CREATE AN ARRAY FROM THE VALUES ON THE STACK ]-----------------------------------

		struct end_array
		{
			stack & m_stack;
			end_array(stack & stack) : m_stack(stack) { }

			// - -[ functional operator ] - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

			template <typename Iterator>
			void operator() (Iterator /* cCharacter */) const
			{
				// 1: create an array object and push everything in it, that's on the stack...

				variant varArray(new boost::any(array()));

				while(!m_stack.empty())
				{
					// 1.1: get the top most variant of the stack...

					variant var = m_stack.top();
					m_stack.pop();

					// 1.2: is it the end of the array? if yes => break the loop...

					if (boost::any_cast< array_delimiter >(var.get()) != NULL)
					{
						break;
					}

					// 1.3: otherwise, add to the array...

					boost::any_cast< array >(varArray.get())->push_front(var);
				}

				// 2: finally, push the array at the end of the stack...

				m_stack.push(varArray);
			}
		};


		// ---[ SEMANTIC ACTION: BEGIN AN OBJECT ]----------------------------------------------------------------

		class	object_delimiter { /* EMPTY CLASS */ };

		struct begin_object
		{
			stack & m_stack;
			begin_object(stack & stack) : m_stack(stack) { }

			template <typename Iterator>
			void operator() (Iterator /* cCharacter */) const
			{
				m_stack.push(variant(new boost::any(object_delimiter())));
			}
		};


		// ---[ SEMANTIC ACTION: CREATE AN OBJECT FROM THE VALUES ON THE STACK ]----------------------------------

		struct end_object
		{
			stack & m_stack;
			end_object(stack & stack) : m_stack(stack) { }

			template <typename Iterator>
			void operator() (Iterator /* cCharacter */) const
			{
				// 1: create an array object and push everything in it, that's on the stack...

				variant varObject(new boost::any(object()));

				while(!m_stack.empty())
				{
					// 1.1: get the top most variant of the stack...

					variant var = m_stack.top();
					m_stack.pop();

					// 1.2: is it the end of the array? if yes => break the loop...
					
					if (boost::any_cast< object_delimiter >(var.get()) != NULL)
					{
						break;
					}

					// 1.3: if this is not a pair, we have a problem...

					pair * pPair = boost::any_cast< pair >(var.get());
					if (!pPair)
					{
						/* BIG PROBLEM!! */

						continue;
					}

					// 1.4: set the child of this object...

					boost::any_cast< object >(varObject.get())->insert(std::make_pair(pPair->first, pPair->second));
				}

				// 2: finally, push the array at the end of the stack...

				m_stack.push(varObject);
			}
		};

	public:

		stack & m_stack;
		grammar(stack & stack) : m_stack(stack) { }

		// ---[ THE ACTUAL GRAMMAR DEFINITION ]-------------------------------------------------------------------

		template <typename SCANNER>
		class definition
		{
			boost::spirit::rule< SCANNER > m_start;
			boost::spirit::rule< SCANNER > m_object;
			boost::spirit::rule< SCANNER > m_array;
			boost::spirit::rule< SCANNER > m_pair;
			boost::spirit::rule< SCANNER > m_value;
			boost::spirit::rule< SCANNER > m_string;
			boost::spirit::rule< SCANNER > m_number;
			boost::spirit::rule< SCANNER > m_boolean;
			boost::spirit::rule< SCANNER > m_null;

		public:

			boost::spirit::rule< SCANNER > const & start() const { return m_start; }

			// - -[ create the definition ] - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

			definition(grammar const & self)
			{
				using namespace boost::spirit;

				// 0: JSON can either be an object or an array

				m_start
					= m_object
					| m_array;

				// 1: an object is an unordered set of pairs (seperated by commas)...

				m_object
					= ch_p('{') [ begin_object(self.m_stack) ] >>
					  !(m_pair >> *(ch_p(',') >> m_pair)) >>
					  ch_p('}') [ end_object  (self.m_stack) ];

				// 2: an array is an ordered collection of values (seperated by commas)...

				m_array
					= ch_p('[')	[ begin_array(self.m_stack) ] >>
					  !(m_value >> *(ch_p(',') >> m_value)) >>
					  ch_p(']')	[ end_array  (self.m_stack) ];

				// 3: a pair is given by a name and a value...

				m_pair
					= ( m_string >> ch_p(':') >> m_value )
					  [ create_pair(self.m_stack) ]
					;

				// 4: a value can be a string in double quotes, a number, a boolean, an object or an array.

				m_value
					= m_string
					| m_number
					| m_object
					| m_array
					| m_boolean
					| m_null
					;

				// 5: a string is a collection of zero or more unicode characters, wrapped in double quotes...

				m_string
					= lexeme_d
						[
							( ch_p('"') >> *(
								( (anychar_p - (ch_p('"') | ch_p('\\')))
								| ch_p('\\') >>
									( ch_p('\"')
									| ch_p('\\')
									| ch_p('/')
									| ch_p('b')
									| ch_p('f')
									| ch_p('n')
									| ch_p('r')
									| ch_p('t')
									| (ch_p('u') >> repeat_p(4)[ xdigit_p ])
									)
								)) >> ch_p('"') 
							)
							[ push_string(self.m_stack) ]
						]
					;

				// 6: a number is very much like a C or java number...

				m_number
					=   strict_real_p	[ push_double(self.m_stack) ]
					  | longlong_p		[ push_int	 (self.m_stack) ]
					;

				// 7: a boolean can be "true" or "false"...

				m_boolean
					= ( str_p("true")
					  | str_p("false")
					  )
					  [ push_boolean(self.m_stack) ]
					;

				// 8: finally, a value also can be a 'null', i.e. an empty item...

				m_null
					= str_p("null")
					  [ push_null(self.m_stack) ]
					;
			}
		};
	};


	// ==========================================================================================================
	// ===                          T H E   F I N A L   P A R S I N G   R O U T I N E                         ===
	// ==========================================================================================================

	template <typename Iterator>
	typename json::grammar< typename Iterator::value_type >::variant parse(Iterator const & szFirst, Iterator const & szEnd)
	{
		// 1: parse the input...

		json::grammar< typename Iterator::value_type >::stack st;
		json::grammar< typename Iterator::value_type > gr(st);

		boost::spirit::parse_info<Iterator> pi = boost::spirit::parse(szFirst, szEnd, gr, boost::spirit::space_p);

		// 2: skip any spaces at the end of the parsed section...

		while((pi.stop != szEnd) && (*pi.stop == static_cast< typename Iterator::value_type >(' ')))
		{
			++pi.stop;
		}

		// 3: if the input's end wasn't reached or if there is more than one object on the stack => cancel...

		if ((pi.stop != szEnd) || (st.size() != 1))
		{
			return json::grammar< typename Iterator::value_type >::variant(new boost::any());
		}

		// 4: otherwise, return the result...

		return st.top();
	}
};


#endif	// TINYJSON_HPP