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
|
// **************************************************************************
// * This file is part of the zenXML project. It is distributed under the *
// * Boost Software License: http://www.boost.org/LICENSE_1_0.txt *
// * Copyright (C) Zenju (zenju AT gmx DOT de) - All Rights Reserved *
// **************************************************************************
#ifndef ZEN_XML_PARSER_HEADER_81248670213764583021432
#define ZEN_XML_PARSER_HEADER_81248670213764583021432
#include <cstdio>
#include <cstddef> //ptrdiff_t; req. on Linux
#include <zen/string_traits.h>
#include "dom.h"
#include "error.h"
namespace zen
{
/**
\file
\brief Convert an XML document object model (class XmlDoc) to and from a byte stream representation.
*/
///Save XML document as a byte stream
/**
\param doc Input XML document
\param lineBreak Line break, default: carriage return + new line
\param indent Indentation, default: four space characters
\return Output byte stream
*/
std::string serialize(const XmlDoc& doc,
const std::string& lineBreak = "\r\n",
const std::string& indent = " "); //throw ()
///Exception thrown due to an XML parsing error
struct XmlParsingError : public XmlError
{
XmlParsingError(size_t rowNo, size_t colNo) : row(rowNo), col(colNo) {}
///Input file row where the parsing error occured
size_t row; //beginning with 0
///Input file column where the parsing error occured
size_t col; //
};
///Load XML document from a byte stream
/**
\param stream Input byte stream
\param doc Output XML document
\throw XmlParsingError
*/
void parse(const std::string& stream, XmlDoc& doc); //throw XmlParsingError
//---------------------------- implementation ----------------------------
//see: http://www.w3.org/TR/xml/
namespace implementation
{
inline
std::pair<char, char> hexify(unsigned char c)
{
auto hexifyDigit = [](int num) -> char //input [0, 15], output 0-9, A-F
{
assert(0 <= num&& num <= 15); //guaranteed by design below!
return static_cast<char>(num <= 9 ? //no signed/unsigned char problem here!
'0' + num :
'A' + (num - 10));
};
return std::make_pair(hexifyDigit(c / 16), hexifyDigit(c % 16));
}
inline
char unhexify(char high, char low)
{
auto unhexifyDigit = [](char hex) -> int //input 0-9, a-f, A-F; output range: [0, 15]
{
if ('0' <= hex && hex <= '9') //no signed/unsigned char problem here!
return hex - '0';
else if ('A' <= hex && hex <= 'F')
return (hex - 'A') + 10;
else if ('a' <= hex && hex <= 'f')
return (hex - 'a') + 10;
assert(false);
return 0;
};
return static_cast<unsigned char>(16 * unhexifyDigit(high) + unhexifyDigit(low)); //[!] convert to unsigned char first, then to char (which may be signed)
};
template <class Predicate> inline
std::string normalize(const std::string& str, Predicate pred) //pred: unary function taking a char, return true if value shall be encoded as hex
{
std::string output;
std::for_each(str.begin(), str.end(),
[&](char c)
{
if (c == '&') //
output += "&";
else if (c == '<') //normalization mandatory: http://www.w3.org/TR/xml/#syntax
output += "<";
else if (c == '>') //
output += ">";
else if (pred(c))
{
if (c == '\'')
output += "'";
else if (c == '\"')
output += """;
else
{
output += "&#x";
const auto hexDigits = hexify(c); //hexify beats "printNumber<std::string>("&#x%02X;", c)" by a nice factor of 3!
output += hexDigits.first;
output += hexDigits.second;
output += ';';
}
}
else
output += c;
});
return output;
}
inline
std::string normalizeName(const std::string& str)
{
return normalize(str, [](char c) { return isWhiteSpace(c) || c == '=' || c == '/' || c == '\'' || c == '\"'; });
}
inline
std::string normalizeElementValue(const std::string& str)
{
return normalize(str, [](char c) { return static_cast<unsigned char>(c) < 32; });
}
inline
std::string normalizeAttribValue(const std::string& str)
{
return normalize(str, [](char c) { return static_cast<unsigned char>(c) < 32 || c == '\'' || c == '\"'; });
}
namespace
{
std::string denormalize(const std::string& str)
{
std::string output;
for (auto it = str.begin(); it != str.end(); ++it)
{
const char c = *it;
if (c == '&')
{
auto checkEntity = [&](const char* placeholder, char realVal) -> bool
{
size_t strLen = strLength(placeholder);
if (str.end() - it >= static_cast<int>(strLen) && std::equal(it, it + strLen, placeholder))
{
output += realVal;
it += strLen - 1;
return true;
}
return false;
};
if (checkEntity("&", '&'))
continue;
if (checkEntity("<", '<'))
continue;
if (checkEntity(">", '>'))
continue;
if (checkEntity("'", '\''))
continue;
if (checkEntity(""", '\"'))
continue;
if (str.end() - it >= 6 &&
it[1] == '#' &&
it[2] == 'x' &&
it[5] == ';')
{
output += unhexify(it[3], it[4]);
it += 5;
continue;
//unhexify beats "::sscanf(&it[3], "%02X", &tmp)" by a factor of 3000 for ~250000 calls!!!
}
output += c; //unexpected char!
}
else if (c == '\r') //map all end-of-line characters to \n http://www.w3.org/TR/xml/#sec-line-ends
{
auto itNext = it + 1;
if (itNext != str.end() && *itNext == '\n')
++it;
output += '\n';
}
else
output += c;
};
return output;
}
void serialize(const XmlElement& element, std::string& stream,
const std::string& lineBreak,
const std::string& indent,
size_t indentLevel)
{
const std::string& nameFmt = normalizeName(element.getNameAs<std::string>());
for (size_t i = 0; i < indentLevel; ++i)
stream += indent;
stream += '<' + nameFmt;
auto attr = element.getAttributes();
for (auto it = attr.first; it != attr.second; ++it)
stream += ' ' + normalizeName(it->first) + "=\"" + normalizeAttribValue(it->second) + "\"";
//no support for mixed-mode content
auto iterPair = element.getChildren();
if (iterPair.first != iterPair.second) //structured element
{
stream += '>' + lineBreak;
std::for_each(iterPair.first, iterPair.second,
[&](const XmlElement & el) { serialize(el, stream, lineBreak, indent, indentLevel + 1); });
for (size_t i = 0; i < indentLevel; ++i)
stream += indent;
stream += "</" + nameFmt + '>' + lineBreak;
}
else
{
std::string value;
element.getValue(value);
if (!value.empty()) //value element
stream += '>' + normalizeElementValue(value) + "</" + nameFmt + '>' + lineBreak;
else //empty element
stream += "/>" + lineBreak;
}
}
std::string serialize(const XmlDoc& doc,
const std::string& lineBreak,
const std::string& indent)
{
std::string version = doc.getVersionAs<std::string>();
if (!version.empty())
version = " version=\"" + normalizeAttribValue(version) + "\"";
std::string encoding = doc.getEncodingAs<std::string>();
if (!encoding.empty())
encoding = " encoding=\"" + normalizeAttribValue(encoding) + "\"";
std::string standalone = doc.getStandaloneAs<std::string>();
if (!standalone.empty())
standalone = " standalone=\"" + normalizeAttribValue(standalone) + "\"";
std::string output = "<?xml" + version + encoding + standalone + "?>" + lineBreak;
serialize(doc.root(), output, lineBreak, indent, 0);
return output;
}
}
}
inline
std::string serialize(const XmlDoc& doc,
const std::string& lineBreak,
const std::string& indent) { return implementation::serialize(doc, lineBreak, indent); }
/*
Grammar for XML parser
-------------------------------
document-expression:
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
element-expression:
element-expression:
<string attributes-expression/>
<string attributes-expression> pm-expression </string>
element-list-expression:
<empty>
element-expression element-list-expression
attributes-expression:
<empty>
string="string" attributes-expression
pm-expression:
string
element-list-expression
*/
namespace implementation
{
struct Token
{
enum Type
{
TK_LESS,
TK_GREATER,
TK_LESS_SLASH,
TK_SLASH_GREATER,
TK_EQUAL,
TK_QUOTE,
TK_DECL_BEGIN,
TK_DECL_END,
TK_NAME,
TK_END
};
Token(Type t) : type(t) {}
Token(const std::string& txt) : type(TK_NAME), name(txt) {}
Type type;
std::string name; //filled if type == TK_NAME
};
class Scanner
{
public:
Scanner(const std::string& stream) : stream_(stream), pos(stream_.begin())
{
if (zen::startsWith(stream_, BYTE_ORDER_MARK_UTF8))
pos += strLength(BYTE_ORDER_MARK_UTF8);
tokens.push_back(std::make_pair("<?xml", Token::TK_DECL_BEGIN));
tokens.push_back(std::make_pair("?>", Token::TK_DECL_END));
tokens.push_back(std::make_pair("</", Token::TK_LESS_SLASH));
tokens.push_back(std::make_pair("/>", Token::TK_SLASH_GREATER));
tokens.push_back(std::make_pair("<" , Token::TK_LESS)); //evaluate after TK_DECL_BEGIN!
tokens.push_back(std::make_pair(">" , Token::TK_GREATER));
tokens.push_back(std::make_pair("=" , Token::TK_EQUAL));
tokens.push_back(std::make_pair("\"", Token::TK_QUOTE));
tokens.push_back(std::make_pair("\'", Token::TK_QUOTE));
}
Token nextToken() //throw XmlParsingError
{
//skip whitespace
pos = std::find_if(pos, stream_.end(), [](char c) { return !zen::isWhiteSpace(c); });
if (pos == stream_.end())
return Token::TK_END;
for (auto it = tokens.begin(); it != tokens.end(); ++it)
if (startsWith(pos, it->first))
{
pos += it->first.size();
return it->second;
}
auto nameEnd = std::find_if(pos, stream_.end(), [](char c)
{
return c == '<' ||
c == '>' ||
c == '=' ||
c == '/' ||
c == '\'' ||
c == '\"' ||
zen::isWhiteSpace(c);
});
if (nameEnd != pos)
{
std::string name(&*pos, nameEnd - pos);
pos = nameEnd;
return implementation::denormalize(name);
}
//unknown token
throw XmlParsingError(posRow(), posCol());
}
std::string extractElementValue()
{
auto it = std::find_if(pos, stream_.end(), [](char c)
{
return c == '<' ||
c == '>';
});
std::string output(pos, it);
pos = it;
return implementation::denormalize(output);
}
std::string extractAttributeValue()
{
auto it = std::find_if(pos, stream_.end(), [](char c)
{
return c == '<' ||
c == '>' ||
c == '\'' ||
c == '\"';
});
std::string output(pos, it);
pos = it;
return implementation::denormalize(output);
}
size_t posRow() const //current row beginning with 0
{
const size_t crSum = std::count(stream_.begin(), pos, '\r'); //carriage returns
const size_t nlSum = std::count(stream_.begin(), pos, '\n'); //new lines
assert(crSum == 0 || nlSum == 0 || crSum == nlSum);
return std::max(crSum, nlSum); //be compatible with Linux/Mac/Win
}
size_t posCol() const //current col beginning with 0
{
//seek beginning of line
for (auto it = pos; it != stream_.begin(); )
{
--it;
if (*it == '\r' || *it == '\n')
return pos - it - 1;
}
return pos - stream_.begin();
}
private:
Scanner(const Scanner&);
Scanner& operator=(const Scanner&);
bool startsWith(std::string::const_iterator it, const std::string& prefix) const
{
if (stream_.end() - it < static_cast<ptrdiff_t>(prefix.size()))
return false;
return std::equal(prefix.begin(), prefix.end(), it);
}
typedef std::vector<std::pair<std::string, Token::Type> > TokenList;
TokenList tokens;
const std::string stream_;
std::string::const_iterator pos;
};
class XmlParser
{
public:
XmlParser(const std::string& stream) :
scn(stream),
tk(scn.nextToken()) {}
void parse(XmlDoc& doc) //throw XmlParsingError
{
//declaration (optional)
if (token().type == Token::TK_DECL_BEGIN)
{
nextToken();
while (token().type == Token::TK_NAME)
{
std::string attribName = token().name;
nextToken();
consumeToken(Token::TK_EQUAL);
expectToken(Token::TK_QUOTE);
std::string attribValue = scn.extractAttributeValue();
nextToken();
consumeToken(Token::TK_QUOTE);
if (attribName == "version")
doc.setVersion(attribValue);
else if (attribName == "encoding")
doc.setEncoding(attribValue);
else if (attribName == "standalone")
doc.setStandalone(attribValue);
}
consumeToken(Token::TK_DECL_END);
}
XmlDoc dummy;
XmlElement& elemTmp = dummy.root();
parseChildElements(elemTmp);
auto iterPair = elemTmp.getChildren();
if (iterPair.first != iterPair.second)
doc.root().swap(*iterPair.first);
expectToken(Token::TK_END);
};
private:
XmlParser(const XmlParser&);
XmlParser& operator=(const XmlParser&);
void parseChildElements(XmlElement& parent)
{
while (token().type == Token::TK_LESS)
{
nextToken();
expectToken(Token::TK_NAME);
std::string elementName = token().name;
nextToken();
XmlElement& newElement = parent.addChild(elementName);
parseAttributes(newElement);
if (token().type == Token::TK_SLASH_GREATER) //empty element
{
nextToken();
continue;
}
expectToken(Token::TK_GREATER);
std::string elementValue = scn.extractElementValue();
nextToken();
//no support for mixed-mode content
if (token().type == Token::TK_LESS) //structured element
parseChildElements(newElement);
else //value element
newElement.setValue(elementValue);
consumeToken(Token::TK_LESS_SLASH);
if (token().type != Token::TK_NAME ||
elementName != token().name)
throw XmlParsingError(scn.posRow(), scn.posCol());
nextToken();
consumeToken(Token::TK_GREATER);
}
};
void parseAttributes(XmlElement& element)
{
while (token().type == Token::TK_NAME)
{
std::string attribName = token().name;
nextToken();
consumeToken(Token::TK_EQUAL);
expectToken(Token::TK_QUOTE);
std::string attribValue = scn.extractAttributeValue();
nextToken();
consumeToken(Token::TK_QUOTE);
element.setAttribute(attribName, attribValue);
}
}
const Token& token() const { return tk; }
void nextToken() { tk = scn.nextToken(); }
void consumeToken(Token::Type t) //throw XmlParsingError
{
expectToken(t); //throw XmlParsingError
nextToken();
}
void expectToken(Token::Type t) //throw XmlParsingError
{
if (token().type != t)
throw XmlParsingError(scn.posRow(), scn.posCol());
}
Scanner scn;
Token tk;
};
}
inline
void parse(const std::string& stream, XmlDoc& doc) //throw XmlParsingError
{
implementation::XmlParser(stream).parse(doc); //throw XmlParsingError
}
}
#endif //ZEN_XML_PARSER_HEADER_81248670213764583021432
|