aboutsummaryrefslogtreecommitdiffstats
path: root/Software/Visual_Studio/MachineStudio/Modules/Tango.MachineStudio.Synchronization/Tango.MachineStudio.Synchronization.csproj
blob: f38fe5dbf94d527b73c437890144448cb2155ec8 (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
generated by cgit v1.3.1 (git 2.54.0) at 2026-07-15 16:43:03 +0000
 


 class="w">					case 0x0000: // either UTF-32 Big Endian or a binary file; use StreamReader
					case 0xfffe: // Unicode BOM (UTF-16 LE or UTF-32 LE)
					case 0xfeff: // UTF-16 BE BOM
					case 0xefbb: // start of UTF-8 BOM
						// StreamReader autodetection works
						stream.Position = 0;
						return new StreamReader(stream);
					default:
						return AutoDetect(stream, (byte)firstByte, (byte)secondByte, defaultEncoding);
				}
			} else {
				if (defaultEncoding != null) {
					return new StreamReader(stream, defaultEncoding);
				} else {
					return new StreamReader(stream);
				}
			}
		}
		
		static StreamReader AutoDetect(Stream fs, byte firstByte, byte secondByte, Encoding defaultEncoding)
		{
			int max = (int)Math.Min(fs.Length, 500000); // look at max. 500 KB
			const int ASCII = 0;
			const int Error = 1;
			const int UTF8  = 2;
			const int UTF8Sequence = 3;
			int state = ASCII;
			int sequenceLength = 0;
			byte b;
			for (int i = 0; i < max; i++) {
				if (i == 0) {
					b = firstByte;
				} else if (i == 1) {
					b = secondByte;
				} else {
					b = (byte)fs.ReadByte();
				}
				if (b < 0x80) {
					// normal ASCII character
					if (state == UTF8Sequence) {
						state = Error;
						break;
					}
				} else if (b < 0xc0) {
					// 10xxxxxx : continues UTF8 byte sequence
					if (state == UTF8Sequence) {
						--sequenceLength;
						if (sequenceLength < 0) {
							state = Error;
							break;
						} else if (sequenceLength == 0) {
							state = UTF8;
						}
					} else {
						state = Error;
						break;
					}
				} else if (b >= 0xc2 && b < 0xf5) {
					// beginning of byte sequence
					if (state == UTF8 || state == ASCII) {
						state = UTF8Sequence;
						if (b < 0xe0) {
							sequenceLength = 1; // one more byte following
						} else if (b < 0xf0) {
							sequenceLength = 2; // two more bytes following
						} else {
							sequenceLength = 3; // three more bytes following
						}
					} else {
						state = Error;
						break;
					}
				} else {
					// 0xc0, 0xc1, 0xf5 to 0xff are invalid in UTF-8 (see RFC 3629)
					state = Error;
					break;
				}
			}
			fs.Position = 0;
			switch (state) {
				case ASCII:
				case Error:
					// when the file seems to be ASCII or non-UTF8,
					// we read it using the user-specified encoding so it is saved again
					// using that encoding.
					if (IsUnicode(defaultEncoding)) {
						// the file is not Unicode, so don't read it using Unicode even if the
						// user has choosen Unicode as the default encoding.
						
						// If we don't do this, SD will end up always adding a Byte Order Mark
						// to ASCII files.
						defaultEncoding = Encoding.Default; // use system encoding instead
					}
					return new StreamReader(fs, defaultEncoding);
				default:
					return new StreamReader(fs);
			}
		}
	}
}