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
|
/**
* @file
* @author 2012-2014 Stefan Radomski (stefan.radomski@cs.tu-darmstadt.de)
* @copyright Simplified BSD
*
* @cond
* This program is free software: you can redistribute it and/or modify
* it under the terms of the FreeBSD license as published by the FreeBSD
* project.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
*
* You should have received a copy of the FreeBSD license along with this
* program. If not, see <http://www.opensource.org/licenses/bsd-license>.
* @endcond
*/
#include "uscxml/messages/Data.h"
#include "uscxml/messages/Blob.h"
#include <boost/algorithm/string.hpp>
#include "uscxml/DOMUtils.h"
#include "glog/logging.h"
#ifdef HAS_STRING_H
#include <string.h>
#endif
extern "C" {
#include "jsmn.h" // minimal json parser
}
namespace uscxml {
Data::Data(const char* _data, size_t _size, const std::string& mimeType, bool adopt) {
binary = boost::shared_ptr<Blob>(new Blob((void*)_data, _size, mimeType, adopt));
}
void Data::merge(const Data& other) {
if (other.compound.size() > 0) {
if (compound.size() == 0) {
compound = other.compound;
} else {
std::map<std::string, Data>::const_iterator compIter = other.compound.begin();
while (compIter != other.compound.end()) {
if (compound.find(compIter->first) != compound.end()) {
// we do have the same key, merge
compound[compIter->first].merge(compIter->second);
} else {
compound[compIter->first] = compIter->second;
}
compIter++;
}
}
}
if (other.array.size() > 0) {
if (array.size() == 0) {
array = other.array;
} else {
std::list<Data>::const_iterator arrIter = other.array.begin();
while(arrIter != other.array.end()) {
array.push_back(*arrIter);
arrIter++;
}
}
}
if (other.atom.size() > 0) {
atom = other.atom;
type = other.type;
}
}
Data::Data(const Arabica::DOM::Node<std::string>& dom) {
// we may need to convert some keys to arrays if we have the same name as an element
std::map<std::string, std::list<Data> > arrays;
// Interpreter::dump(dom);
if (dom.hasAttributes()) {
Arabica::DOM::NamedNodeMap<std::string> attributes = dom.getAttributes();
for (int i = 0; i < attributes.getLength(); i++) {
Arabica::DOM::Node<std::string> attribute = attributes.item(i);
// Interpreter::dump(attribute);
assert(attribute.getNodeType() == Arabica::DOM::Node_base::ATTRIBUTE_NODE);
std::string key = attribute.getLocalName();
std::string value = attribute.getNodeValue();
compound[key] = Data(value, VERBATIM);
}
}
if (dom.hasChildNodes()) {
Arabica::DOM::NodeList<std::string> children = dom.getChildNodes();
for (int i = 0; i < children.getLength(); i++) {
Arabica::DOM::Node<std::string> child = children.item(i);
// Interpreter::dump(child);
std::string key;
switch (child.getNodeType()) {
case Arabica::DOM::Node_base::ELEMENT_NODE:
key = TAGNAME(child);
break;
case Arabica::DOM::Node_base::ATTRIBUTE_NODE:
key = ((Arabica::DOM::Attr<std::string>)child).getName();
break;
case Arabica::DOM::Node_base::TEXT_NODE:
default:
break;
}
if (key.length() == 0)
continue;
if (compound.find(key) != compound.end()) {
// we already have such a key .. make it an array after we processed all children
arrays[key].push_back(Data(child));
} else {
compound[key] = Data(child);
}
}
} else {
atom = dom.getNodeValue();
type = VERBATIM;
}
std::map<std::string, std::list<Data> >::iterator arrayIter = arrays.begin();
while(arrayIter != arrays.end()) {
assert(compound.find(arrayIter->first) != compound.end());
Data arrayData;
arrays[arrayIter->first].push_front(compound[arrayIter->first]);
arrayData.array = arrays[arrayIter->first];
compound[arrayIter->first] = arrayData;
}
}
Arabica::DOM::Document<std::string> Data::toDocument() {
Arabica::DOM::DOMImplementation<std::string> domFactory = Arabica::SimpleDOM::DOMImplementation<std::string>::getDOMImplementation();
Arabica::DOM::Document<std::string> document = domFactory.createDocument("http://www.w3.org/2005/07/scxml", "message", 0);
Arabica::DOM::Element<std::string> scxmlMsg = document.getDocumentElement();
scxmlMsg.setPrefix("scxml");
scxmlMsg.setAttribute("version", "1.0");
if (compound.size() > 0 || array.size() > 0) {
Arabica::DOM::Element<std::string> payloadElem = document.createElementNS("http://www.w3.org/2005/07/scxml", "payload");
payloadElem.setPrefix("scxml");
scxmlMsg.appendChild(payloadElem);
// we do not support nested attibutes
if (compound.size() > 0) {
std::map<std::string, Data>::iterator compoundIter = compound.begin();
while(compoundIter != compound.end()) {
if (compoundIter->second.atom.size() > 0) {
Arabica::DOM::Element<std::string> propertyElem = document.createElementNS("http://www.w3.org/2005/07/scxml", "property");
propertyElem.setPrefix("scxml");
propertyElem.setAttribute("name", compoundIter->first);
Arabica::DOM::Text<std::string> textElem = document.createTextNode(compoundIter->second.atom);
propertyElem.appendChild(textElem);
payloadElem.appendChild(propertyElem);
}
compoundIter++;
}
}
}
return document;
}
Data Data::fromXML(const std::string& xmlString) {
return Data();
}
Data Data::fromJSON(const std::string& jsonString) {
Data data;
std::string trimmed = boost::trim_copy(jsonString);
if (trimmed.length() == 0)
return data;
if (trimmed.find_first_of("{[") != 0)
return data;
jsmn_parser p;
jsmntok_t* t = NULL;
// we do not know the number of tokens beforehand, start with something sensible and increase
int rv;
int frac = 16; // length/token ratio
do {
jsmn_init(&p);
frac /= 2;
int nrTokens = trimmed.size() / frac;
if (t != NULL) {
free(t);
// LOG(INFO) << "Increasing JSON length to token ratio to 1/" << frac;
}
t = (jsmntok_t*)malloc((nrTokens + 1) * sizeof(jsmntok_t));
if (t == NULL) {
LOG(ERROR) << "Cannot parse JSON, ran out of memory!";
return data;
}
memset(t, 0, (nrTokens + 1) * sizeof(jsmntok_t));
rv = jsmn_parse(&p, trimmed.c_str(), t, nrTokens);
} while (rv == JSMN_ERROR_NOMEM && frac > 1);
if (rv != 0) {
switch (rv) {
case JSMN_ERROR_NOMEM:
LOG(ERROR) << "Cannot parse JSON, not enough tokens were provided!";
break;
case JSMN_ERROR_INVAL:
LOG(ERROR) << "Cannot parse JSON, invalid character inside JSON string!";
break;
case JSMN_ERROR_PART:
LOG(ERROR) << "Cannot parse JSON, the string is not a full JSON packet, more bytes expected!";
break;
default:
break;
}
free(t);
return data;
}
if (t[0].end != trimmed.length())
return data;
// jsmntok_t* token = t;
// while(token->end) {
// std::cout << trimmed.substr(token->start, token->end - token->start) << std::endl;
// std::cout << "------" << std::endl;
// token++;
// }
std::list<Data*> dataStack;
std::list<jsmntok_t> tokenStack;
dataStack.push_back(&data);
size_t currTok = 0;
do {
// used for debugging
// jsmntok_t t2 = t[currTok];
// std::string value = trimmed.substr(t[currTok].start, t[currTok].end - t[currTok].start);
switch (t[currTok].type) {
case JSMN_STRING:
dataStack.back()->type = Data::VERBATIM;
case JSMN_PRIMITIVE: {
std::string value = trimmed.substr(t[currTok].start, t[currTok].end - t[currTok].start);
if (dataStack.back()->type == Data::VERBATIM) {
boost::replace_all(value, "\\\"", "\"");
boost::replace_all(value, "\\n", "\n");
}
dataStack.back()->atom = value;
dataStack.pop_back();
currTok++;
break;
}
case JSMN_OBJECT:
case JSMN_ARRAY:
tokenStack.push_back(t[currTok]);
currTok++;
break;
}
// used for debugging
// t2 = t[currTok];
// value = trimmed.substr(t[currTok].start, t[currTok].end - t[currTok].start);
// there are no more tokens
if (t[currTok].end == 0 || tokenStack.empty())
break;
// next token starts after current one => pop
while (t[currTok].end > tokenStack.back().end) {
tokenStack.pop_back();
dataStack.pop_back();
}
if (tokenStack.back().type == JSMN_OBJECT && (t[currTok].type == JSMN_PRIMITIVE || t[currTok].type == JSMN_STRING)) {
// grab key and push new data
std::string value = trimmed.substr(t[currTok].start, t[currTok].end - t[currTok].start);
dataStack.push_back(&(dataStack.back()->compound[value]));
currTok++;
}
if (tokenStack.back().type == JSMN_ARRAY) {
// push new index
dataStack.back()->array.push_back(Data());
dataStack.push_back(&(dataStack.back()->array.back()));
}
} while (true);
free(t);
return data;
}
std::ostream& operator<< (std::ostream& os, const Data& data) {
os << Data::toJSON(data);
return os;
}
std::string Data::toJSON(const Data& data) {
std::stringstream os;
std::string indent;
for (int i = 0; i < _dataIndentation; i++) {
indent += " ";
}
if (false) {
} else if (data.compound.size() > 0) {
int longestKey = 0;
std::map<std::string, Data>::const_iterator compoundIter = data.compound.begin();
while(compoundIter != data.compound.end()) {
if (compoundIter->first.size() > longestKey)
longestKey = compoundIter->first.size();
compoundIter++;
}
std::string keyPadding;
for (unsigned int i = 0; i < longestKey; i++)
keyPadding += " ";
std::string seperator;
os << std::endl << indent << "{";
compoundIter = data.compound.begin();
while(compoundIter != data.compound.end()) {
os << seperator << std::endl << indent << " \"" << compoundIter->first << "\": " << keyPadding.substr(0, longestKey - compoundIter->first.size());
_dataIndentation += 1;
os << compoundIter->second;
_dataIndentation -= 1;
seperator = ", ";
compoundIter++;
}
os << std::endl << indent << "}";
} else if (data.array.size() > 0) {
std::string seperator;
os << std::endl << indent << "[";
std::list<Data>::const_iterator arrayIter = data.array.begin();
while(arrayIter != data.array.end()) {
_dataIndentation += 1;
os << seperator << *arrayIter;
_dataIndentation -= 1;
seperator = ", ";
arrayIter++;
}
os << "]";
} else if (data.atom.size() > 0) {
// empty string is handled below
if (data.type == Data::VERBATIM) {
os << "\"";
for (int i = 0; i < data.atom.size(); i++) {
// escape string
if (false) {
} else if (data.atom[i] == '"') {
os << "\\\"";
} else if (data.atom[i] == '\n') {
os << "\\n";
} else if (data.atom[i] == '\t') {
os << "\\t";
} else {
os << data.atom[i];
}
}
os << "\"";
} else {
os << data.atom;
}
} else if (data.node) {
std::ostringstream xmlSerSS;
xmlSerSS << data.node;
std::string xmlSer = xmlSerSS.str();
boost::replace_all(xmlSer, "\"", "\\\"");
boost::replace_all(xmlSer, "\n", "\\n");
boost::replace_all(xmlSer, "\t", "\\t");
os << "\"" << xmlSer << "\"";
} else {
if (data.type == Data::VERBATIM) {
os << "\"\""; // empty string
} else {
os << "null";
}
}
return os.str();
}
}
|