-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathtt_string_vector.cpp
More file actions
401 lines (362 loc) · 10.4 KB
/
Copy pathtt_string_vector.cpp
File metadata and controls
401 lines (362 loc) · 10.4 KB
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
/////////////////////////////////////////////////////////////////////////////
// Purpose: Class for reading and writing line-oriented strings/files
// Author: Ralph Walden
// Copyright: Copyright (c) 2019-2024 KeyWorks Software (Ralph Walden)
// License: Apache License -- see ../../LICENSE
/////////////////////////////////////////////////////////////////////////////
#include <fstream>
#include "tt_string_vector.h"
#include "tt_view_vector.h" // tt_view_vector -- Class for reading and writing line-oriented strings/files
void tt_string_vector::SetString(std::string_view str, char separator, tt::TRIM trim)
{
clear();
if (str.empty())
return;
// If the separator is a quote, then assume each substring is contained within quotes.
if (separator == '"')
{
auto start = str.find_first_of(separator);
if (start == tt::npos)
{
return;
}
str.remove_prefix(start);
emplace_back();
auto& first_item = back();
auto end = first_item.ExtractSubString(str);
if (first_item.empty())
{
// Ignore empty items
pop_back();
}
else
{
if (trim != tt::TRIM::none)
{
first_item.trim(trim);
}
}
while (end != tt::npos && end + 1 < str.length())
{
start = str.find_first_of(separator, end + 1);
if (start == tt::npos)
{
return;
}
str.remove_prefix(start);
emplace_back();
auto& last_item = back();
end = last_item.ExtractSubString(str);
if (last_item.empty())
{
// Ignore empty items
pop_back();
}
else
{
if (trim != tt::TRIM::none)
{
last_item.trim(trim);
}
}
}
return;
}
size_t start = 0;
size_t end = str.find_first_of(separator);
// The last string will not have a separator, so end == tt::npos, but we still need to add that final string
for (;;)
{
emplace_back();
if (trim == tt::TRIM::both || trim == tt::TRIM::left)
{
auto begin = str.find_first_not_of(" \t\n\r\f\v", start);
if (begin != tt::npos)
{
start = begin;
}
else
{
if (end != tt::npos)
{
start = end;
}
else
{
// We're at the end, there's nothing here but whitespace, so we're done
break;
}
}
}
if (trim == tt::TRIM::both || trim == tt::TRIM::right)
{
auto temp_end = end;
if (end == tt::npos)
temp_end = str.length();
while (temp_end > start && tt::is_whitespace(str.at(temp_end - 1)))
{
--temp_end;
}
back().assign(str.substr(start, temp_end - start));
}
else if (end == tt::npos)
{
back().assign(str.substr(start, str.length() - start));
}
else
{
back().assign(str.substr(start, end - start));
}
// The last string will not have a separator after it so end will already be set to tt::npos
if (end == tt::npos)
break;
start = end + sizeof(char);
if (start >= str.length())
break;
end = str.find_first_of(separator, start);
}
}
void tt_string_vector::SetString(std::string_view str, std::string_view separator, tt::TRIM trim)
{
clear();
size_t start = 0;
size_t end = str.find_first_of(separator);
// The last string will not have a separator, so end == tt::npos, but we still need to add that final string
for (;;)
{
emplace_back();
if (trim == tt::TRIM::both || trim == tt::TRIM::left)
{
auto begin = str.find_first_not_of(" \t\n\r\f\v", start);
if (begin != tt::npos)
{
start = begin;
}
else
{
if (end != tt::npos)
{
start = end;
}
else
{
// We're at the end, there's nothing here but whitespace, so we're done
break;
}
}
}
if (trim == tt::TRIM::both || trim == tt::TRIM::right)
{
auto temp_end = end;
if (end == tt::npos)
temp_end = str.length();
while (temp_end > start && tt::is_whitespace(str.at(temp_end - 1)))
{
--temp_end;
}
back().assign(str.substr(start, temp_end - start));
}
else if (end == tt::npos)
{
back().assign(str.substr(start, str.length() - start));
}
else
{
back().assign(str.substr(start, end - start));
}
// The last string will not have a separator after it so end will already be set to tt::npos
if (end == tt::npos)
break;
start = end + separator.length();
if (start >= str.length())
break;
end = str.find_first_of(separator, start);
}
}
size_t tt_string_vector::find(size_t start, std::string_view str, tt::CASE checkcase) const
{
for (; start < size(); ++start)
{
if (tt::is_sameas(at(start), str, checkcase))
return start;
}
return tt::npos;
}
size_t tt_string_vector::findprefix(size_t start, std::string_view str, tt::CASE checkcase) const
{
if (checkcase == tt::CASE::exact)
{
for (; start < size(); ++start)
{
if (tt::is_sameprefix(at(start), str, checkcase))
return start;
}
}
else
{
for (; start < size(); ++start)
{
if (tt::is_sameprefix(at(start), str, checkcase))
return start;
}
}
return tt::npos;
}
bool tt_string_vector::ReadFile(std::string_view filename)
{
m_filename.assign(filename);
clear();
#if defined(_WIN32)
auto path = std::filesystem::path(m_filename.c_str());
std::ifstream file(path, std::ios::binary);
#else
std::ifstream file(m_filename, std::ios::binary);
#endif // _WIN32
if (!file.is_open())
return false;
std::string buf(std::istreambuf_iterator<char>(file), {});
if (buf.size() > 2)
{
// Check for BOM LE or BOM UTF-8 -- other types are not supported.
if (buf[0] == static_cast<char>(0xFF) && buf[1] == static_cast<char>(0xFE))
{
// BOM LE format, so convert to utf-8 before parsing
auto utf8_buf = tt::utf16to8(reinterpret_cast<const wchar_t*>(buf.c_str() + 2));
ParseLines(utf8_buf);
}
else if (buf[0] == static_cast<char>(0xEF) && buf[1] == static_cast<char>(0xBB) && buf[1] == static_cast<char>(0xBF))
{
// BOM utf-8 string, so skip over the BOM and process normally
ParseLines(buf.c_str() + 3);
}
else
{
ParseLines(buf);
}
}
else
{
// A file with only 2 bytes or less is probably worthless, but parse it anyway.
ParseLines(buf);
}
return true;
}
bool tt_string_vector::WriteFile(const std::string& filename) const
{
std::ofstream file(filename, std::ios::binary);
if (!file.is_open())
return false;
for (auto iter: *this)
{
file << iter << '\n';
}
return true;
}
void tt_string_vector::ReadString(std::string_view str)
{
if (!str.empty())
ParseLines(str);
}
void tt_string_vector::ReadArray(const char** begin)
{
assert(begin);
if (!begin)
return;
while (*begin)
{
push_back(*begin);
++begin;
}
}
void tt_string_vector::ReadArray(const char** begin, size_t count)
{
assert(begin && count != tt::npos);
if (!begin || count == tt::npos)
return;
while (count > 0)
{
push_back(*begin++);
--count;
}
}
void tt_string_vector::ParseLines(std::string_view str)
{
size_t posBeginLine = 0;
for (size_t pos = 0; pos < str.size(); ++pos)
{
if (str[pos] == '\r')
{
emplace_back();
if (pos > posBeginLine)
{
back().assign(str.substr(posBeginLine, pos - posBeginLine));
}
else
{
back().assign(tt::emptystring);
}
// Some Apple format files only use \r. Windows files tend to use \r\n.
if (pos + 1 < str.size() && str[pos + 1] == '\n')
++pos;
posBeginLine = pos + 1;
}
else if (str[pos] == '\n')
{
emplace_back();
if (pos > posBeginLine)
{
back().assign(str.substr(posBeginLine, pos - posBeginLine));
}
else
{
back().assign(tt::emptystring);
}
posBeginLine = pos + 1;
}
}
}
size_t tt_string_vector::FindLineContaining(std::string_view str, size_t start, tt::CASE checkcase) const
{
for (; start < size(); ++start)
{
if (at(start).contains(str, checkcase))
return start;
}
return tt::npos;
}
size_t tt_string_vector::ReplaceInLine(std::string_view orgStr, std::string_view newStr, size_t posLine, tt::CASE checkcase)
{
for (; posLine < size(); ++posLine)
{
if (at(posLine).contains(orgStr, checkcase))
{
at(posLine).Replace(orgStr, newStr, false, checkcase);
return posLine;
}
}
return tt::npos;
}
bool tt_string_vector::is_sameas(const tt_view_vector& other, tt::CASE checkcase) const
{
if (size() != other.size())
return false;
size_t pos = 0;
for (; pos < other.size(); ++pos)
{
if (!at(pos).is_sameas(other[pos], checkcase))
break;
}
return (pos == size());
}
bool tt_string_vector::is_sameas(const tt_string_vector& other, tt::CASE checkcase) const
{
if (size() != other.size())
return false;
size_t pos = 0;
for (; pos < other.size(); ++pos)
{
if (!at(pos).is_sameas(other[pos], checkcase))
break;
}
return (pos == size());
}