summaryrefslogtreecommitdiffstats
path: root/external_libs/cpp/yaml-cpp/src/emitterutils.cpp
blob: 3d184d6cb95d599ecd5ee1a31cb519747ed39e84 (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
#include "emitterutils.h"
#include "exp.h"
#include "indentation.h"
#include "yaml-cpp/binary.h"
#include "yaml-cpp/exceptions.h"
#include "stringsource.h"
#include <sstream>
#include <iomanip>

namespace YAML
{
	namespace Utils
	{
		namespace {
			enum {REPLACEMENT_CHARACTER = 0xFFFD};

			bool IsAnchorChar(int ch) { // test for ns-anchor-char
				switch (ch) {
					case ',': case '[': case ']': case '{': case '}': // c-flow-indicator
					case ' ': case '\t': // s-white
					case 0xFEFF: // c-byte-order-mark
					case 0xA: case 0xD: // b-char
						return false;
					case 0x85:
						return true;
				}

				if (ch < 0x20)
					return false;

				if (ch < 0x7E)
					return true;

				if (ch < 0xA0)
					return false;
				if (ch >= 0xD800 && ch <= 0xDFFF)
					return false;
				if ((ch & 0xFFFE) == 0xFFFE)
					return false;
				if ((ch >= 0xFDD0) && (ch <= 0xFDEF))
					return false;
				if (ch > 0x10FFFF)
					return false;

				return true;
			}
			
			int Utf8BytesIndicated(char ch) {
				int byteVal = static_cast<unsigned char>(ch);
				switch (byteVal >> 4) {
					case 0: case 1: case 2: case 3: case 4: case 5: case 6: case 7:
						return 1;
					case 12: case 13:
						return 2;
					case 14:
						return 3;
					case 15:
						return 4;
					default:
					  return -1;
				}
			}

			bool IsTrailingByte(char ch) {
				return (ch & 0xC0) == 0x80;
			}
			
			bool GetNextCodePointAndAdvance(int& codePoint, std::string::const_iterator& first, std::string::const_iterator last) {
				if (first == last)
					return false;
				
				int nBytes = Utf8BytesIndicated(*first);
				if (nBytes < 1) {
					// Bad lead byte
					++first;
					codePoint = REPLACEMENT_CHARACTER;
					return true;
				}
				
				if (nBytes == 1) {
					codePoint = *first++;
					return true;
				}
				
				// Gather bits from trailing bytes
				codePoint = static_cast<unsigned char>(*first) & ~(0xFF << (7 - nBytes));
				++first;
				--nBytes;
				for (; nBytes > 0; ++first, --nBytes) {
					if ((first == last) || !IsTrailingByte(*first)) {
						codePoint = REPLACEMENT_CHARACTER;
						break;
					}
					codePoint <<= 6;
					codePoint |= *first & 0x3F;
				}

				// Check for illegal code points
				if (codePoint > 0x10FFFF)
					codePoint = REPLACEMENT_CHARACTER;
				else if (codePoint >= 0xD800 && codePoint <= 0xDFFF)
					codePoint = REPLACEMENT_CHARACTER;
				else if ((codePoint & 0xFFFE) == 0xFFFE)
					codePoint = REPLACEMENT_CHARACTER;
				else if (codePoint >= 0xFDD0 && codePoint <= 0xFDEF)
					codePoint = REPLACEMENT_CHARACTER;
				return true;
			}
			
			void WriteCodePoint(ostream& out, int codePoint) {
				if (codePoint < 0 || codePoint > 0x10FFFF) {
					codePoint = REPLACEMENT_CHARACTER;
				}
				if (codePoint < 0x7F) {
					out << static_cast<char>(codePoint);
				} else if (codePoint < 0x7FF) {
					out << static_cast<char>(0xC0 | (codePoint >> 6))
					    << static_cast<char>(0x80 | (codePoint & 0x3F));
				} else if (codePoint < 0xFFFF) {
					out << static_cast<char>(0xE0 | (codePoint >> 12))
					    << static_cast<char>(0x80 | ((codePoint >> 6) & 0x3F))
					    << static_cast<char>(0x80 | (codePoint & 0x3F));
				} else {
					out << static_cast<char>(0xF0 | (codePoint >> 18))
					    << static_cast<char>(0x80 | ((codePoint >> 12) & 0x3F))
					    << static_cast<char>(0x80 | ((codePoint >> 6) & 0x3F))
					    << static_cast<char>(0x80 | (codePoint & 0x3F));
				}
			}
			
			bool IsValidPlainScalar(const std::string& str, bool inFlow, bool allowOnlyAscii) {
				if(str.empty())
					return false;
				
				// first check the start
				const RegEx& start = (inFlow ? Exp::PlainScalarInFlow() : Exp::PlainScalar());
				if(!start.Matches(str))
					return false;
				
				// and check the end for plain whitespace (which can't be faithfully kept in a plain scalar)
				if(!str.empty() && *str.rbegin() == ' ')
					return false;

				// then check until something is disallowed
				const RegEx& disallowed = (inFlow ? Exp::EndScalarInFlow() : Exp::EndScalar())
				                          || (Exp::BlankOrBreak() + Exp::Comment())
				                          || Exp::NotPrintable()
				                          || Exp::Utf8_ByteOrderMark()
				                          || Exp::Break()
				                          || Exp::Tab();
				StringCharSource buffer(str.c_str(), str.size());
				while(buffer) {
					if(disallowed.Matches(buffer))
						return false;
					if(allowOnlyAscii && (0x7F < static_cast<unsigned char>(buffer[0]))) 
						return false;
					++buffer;
				}
				
				return true;
			}

			void WriteDoubleQuoteEscapeSequence(ostream& out, int codePoint) {
				static const char hexDigits[] = "0123456789abcdef";

				char escSeq[] = "\\U00000000";
				int digits = 8;
				if (codePoint < 0xFF) {
					escSeq[1] = 'x';
					digits = 2;
				} else if (codePoint < 0xFFFF) {
					escSeq[1] = 'u';
					digits = 4;
				}

				// Write digits into the escape sequence
				int i = 2;
				for (; digits > 0; --digits, ++i) {
					escSeq[i] = hexDigits[(codePoint >> (4 * (digits - 1))) & 0xF];
				}

				escSeq[i] = 0; // terminate with NUL character
				out << escSeq;
			}

			bool WriteAliasName(ostream& out, const std::string& str) {
				int codePoint;
				for(std::string::const_iterator i = str.begin();
					GetNextCodePointAndAdvance(codePoint, i, str.end());
					)
				{
					if (!IsAnchorChar(codePoint))
						return false;

					WriteCodePoint(out, codePoint);
				}
				return true;
			}
		}
		
		bool WriteString(ostream& out, const std::string& str, bool inFlow, bool escapeNonAscii)
		{
			if(IsValidPlainScalar(str, inFlow, escapeNonAscii)) {
				out << str;
				return true;
			} else
				return WriteDoubleQuotedString(out, str, escapeNonAscii);
		}
		
		bool WriteSingleQuotedString(ostream& out, const std::string& str)
		{
			out << "'";
			int codePoint;
			for(std::string::const_iterator i = str.begin();
				GetNextCodePointAndAdvance(codePoint, i, str.end());
				) 
			{
				if (codePoint == '\n')
					return false;  // We can't handle a new line and the attendant indentation yet

				if (codePoint == '\'')
					out << "''";
				else
					WriteCodePoint(out, codePoint);
			}
			out << "'";
			return true;
		}
		
		bool WriteDoubleQuotedString(ostream& out, const std::string& str, bool escapeNonAscii)
		{
			out << "\"";
			int codePoint;
			for(std::string::const_iterator i = str.begin();
				GetNextCodePointAndAdvance(codePoint, i, str.end());
				) 
			{
				if (codePoint == '\"')
					out << "\\\"";
				else if (codePoint == '\\')
					out << "\\\\";
				else if (codePoint < 0x20 || (codePoint >= 0x80 && codePoint <= 0xA0)) // Control characters and non-breaking space
					WriteDoubleQuoteEscapeSequence(out, codePoint);
				else if (codePoint == 0xFEFF) // Byte order marks (ZWNS) should be escaped (YAML 1.2, sec. 5.2)	
					WriteDoubleQuoteEscapeSequence(out, codePoint);
				else if (escapeNonAscii && codePoint > 0x7E)
					WriteDoubleQuoteEscapeSequence(out, codePoint);
				else
					WriteCodePoint(out, codePoint);
			}
			out << "\"";
			return true;
		}

		bool WriteLiteralString(ostream& out, const std::string& str, int indent)
		{
			out << "|\n";
			out << IndentTo(indent);
			int codePoint;
			for(std::string::const_iterator i = str.begin();
				GetNextCodePointAndAdvance(codePoint, i, str.end());
				)
			{
				if (codePoint == '\n')
				  out << "\n" << IndentTo(indent);
				else
				  WriteCodePoint(out, codePoint);
			}
			return true;
		}
		
		bool WriteChar(ostream& out, char ch)
		{
			if(('a' <= ch && ch <= 'z') || ('A' <= ch && ch <= 'Z'))
				out << ch;
			else if((0x20 <= ch && ch <= 0x7e) || ch == ' ')
				out << "\"" << ch << "\"";
			else if(ch == '\t')
				out << "\"\\t\"";
			else if(ch == '\n')
				out << "\"\\n\"";
			else if(ch == '\b')
				out << "\"\\b\"";
			else {
				out << "\"";
				WriteDoubleQuoteEscapeSequence(out, ch);
				out << "\"";
			}
			return true;
		}

		bool WriteComment(ostream& out, const std::string& str, int postCommentIndent)
		{
			const unsigned curIndent = out.col();
			out << "#" << Indentation(postCommentIndent);
			int codePoint;
			for(std::string::const_iterator i = str.begin();
				GetNextCodePointAndAdvance(codePoint, i, str.end());
				)
			{
				if(codePoint == '\n')
					out << "\n" << IndentTo(curIndent) << "#" << Indentation(postCommentIndent);
				else
					WriteCodePoint(out, codePoint);
			}
			return true;
		}

		bool WriteAlias(ostream& out, const std::string& str)
		{
			out << "*";
			return WriteAliasName(out, str);
		}
		
		bool WriteAnchor(ostream& out, const std::string& str)
		{
			out << "&";
			return WriteAliasName(out, str);
		}

		bool WriteTag(ostream& out, const std::string& str, bool verbatim)
		{
			out << (verbatim ? "!<" : "!");
			StringCharSource buffer(str.c_str(), str.size());
			const RegEx& reValid = verbatim ? Exp::URI() : Exp::Tag();
			while(buffer) {
				int n = reValid.Match(buffer);
				if(n <= 0)
					return false;

				while(--n >= 0) {
					out << buffer[0];
					++buffer;
				}
			}
			if (verbatim)
				out << ">";
			return true;
		}

		bool WriteTagWithPrefix(ostream& out, const std::string& prefix, const std::string& tag)
		{
			out << "!";
			StringCharSource prefixBuffer(prefix.c_str(), prefix.size());
			while(prefixBuffer) {
				int n = Exp::URI().Match(prefixBuffer);
				if(n <= 0)
					return false;
				
				while(--n >= 0) {
					out << prefixBuffer[0];
					++prefixBuffer;
				}
			}

			out << "!";
			StringCharSource tagBuffer(tag.c_str(), tag.size());
			while(tagBuffer) {
				int n = Exp::Tag().Match(tagBuffer);
				if(n <= 0)
					return false;
				
				while(--n >= 0) {
					out << tagBuffer[0];
					++tagBuffer;
				}
			}
			return true;
		}

		bool WriteBinary(ostream& out, const Binary& binary)
		{
            WriteDoubleQuotedString(out, EncodeBase64(binary.data(), binary.size()), false);
            return true;
		}
	}
}