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
|
#include "base/assert.hpp"
#include "base/string_utils.hpp"
#include "std/cmath.hpp"
#include "std/iomanip.hpp"
#include "std/iterator.hpp"
#include "std/target_os.hpp"
#include <boost/algorithm/string/trim.hpp>
namespace strings
{
bool UniString::IsEqualAscii(char const * s) const
{
return (size() == strlen(s) && equal(begin(), end(), s));
}
SimpleDelimiter::SimpleDelimiter(char const * delimChars)
{
string const s(delimChars);
string::const_iterator it = s.begin();
while (it != s.end())
m_delims.push_back(utf8::unchecked::next(it));
}
bool SimpleDelimiter::operator()(UniChar c) const
{
for (UniString::const_iterator it = m_delims.begin(); it != m_delims.end(); ++it)
if (*it == c)
return true;
return false;
}
UniChar LastUniChar(string const & s)
{
if (s.empty())
return 0;
utf8::unchecked::iterator<string::const_iterator> iter(s.end());
--iter;
return *iter;
}
bool to_int(char const * s, int & i, int base /*= 10*/)
{
char * stop;
long const x = strtol(s, &stop, base);
if (*stop == 0)
{
i = static_cast<int>(x);
ASSERT_EQUAL(static_cast<long>(i), x, ());
return true;
}
return false;
}
bool to_uint64(char const * s, uint64_t & i)
{
char * stop;
#ifdef OMIM_OS_WINDOWS_NATIVE
i = _strtoui64(s, &stop, 10);
#else
i = strtoull(s, &stop, 10);
#endif
return *stop == 0;
}
bool to_int64(char const * s, int64_t & i)
{
char * stop;
#ifdef OMIM_OS_WINDOWS_NATIVE
i = _strtoi64(s, &stop, 10);
#else
i = strtoll(s, &stop, 10);
#endif
return *stop == 0;
}
bool to_double(char const * s, double & d)
{
char * stop;
d = strtod(s, &stop);
return *stop == 0 && s != stop && isfinite(d);
}
UniString MakeLowerCase(UniString const & s)
{
UniString result(s);
MakeLowerCaseInplace(result);
return result;
}
void MakeLowerCaseInplace(string & s)
{
UniString uniStr;
utf8::unchecked::utf8to32(s.begin(), s.end(), back_inserter(uniStr));
MakeLowerCaseInplace(uniStr);
s.clear();
utf8::unchecked::utf32to8(uniStr.begin(), uniStr.end(), back_inserter(s));
}
string MakeLowerCase(string const & s)
{
string result(s);
MakeLowerCaseInplace(result);
return result;
}
UniString Normalize(UniString const & s)
{
UniString result(s);
NormalizeInplace(result);
return result;
}
void NormalizeDigits(string & utf8)
{
size_t const n = utf8.size();
size_t const m = n >= 2 ? n - 2 : 0;
size_t i = 0;
while (i < n && utf8[i] != '\xEF')
++i;
size_t j = i;
// Following invariant holds before/between/after loop iterations below:
// * utf8[0, i) represents a checked part of the input string.
// * utf8[0, j) represents a normalized version of the utf8[0, i).
while (i < m)
{
if (utf8[i] == '\xEF' && utf8[i + 1] == '\xBC')
{
auto const n = utf8[i + 2];
if (n >= '\x90' && n <= '\x99')
{
utf8[j++] = n - 0x90 + '0';
i += 3;
}
else
{
utf8[j++] = utf8[i++];
utf8[j++] = utf8[i++];
}
}
else
{
utf8[j++] = utf8[i++];
}
}
while (i < n)
utf8[j++] = utf8[i++];
utf8.resize(j);
}
void NormalizeDigits(UniString & us)
{
size_t const size = us.size();
for (size_t i = 0; i < size; ++i)
{
UniChar const c = us[i];
if (c >= 0xFF10 /* '0' */ && c <= 0xFF19 /* '9' */)
us[i] = c - 0xFF10 + '0';
}
}
namespace
{
char ascii_to_lower(char in)
{
char const diff = 'z' - 'Z';
static_assert(diff == 'a' - 'A', "");
static_assert(diff > 0, "");
if (in >= 'A' && in <= 'Z')
return (in + diff);
return in;
}
}
void AsciiToLower(string & s)
{
transform(s.begin(), s.end(), s.begin(), &ascii_to_lower);
}
void Trim(string & s)
{
boost::trim(s);
}
void Trim(string & s, char const * anyOf)
{
boost::trim_if(s, boost::is_any_of(anyOf));
}
bool EqualNoCase(string const & s1, string const & s2)
{
return MakeLowerCase(s1) == MakeLowerCase(s2);
}
UniString MakeUniString(string const & utf8s)
{
UniString result;
utf8::unchecked::utf8to32(utf8s.begin(), utf8s.end(), back_inserter(result));
return result;
}
string ToUtf8(UniString const & s)
{
string result;
utf8::unchecked::utf32to8(s.begin(), s.end(), back_inserter(result));
return result;
}
bool IsASCIIString(string const & str)
{
for (size_t i = 0; i < str.size(); ++i)
if (str[i] & 0x80)
return false;
return true;
}
bool StartsWith(UniString const & s, UniString const & p)
{
if (p.size() > s.size())
return false;
for (size_t i = 0; i < p.size(); ++i)
{
if (s[i] != p[i])
return false;
}
return true;
}
bool StartsWith(string const & s1, char const * s2)
{
return (s1.compare(0, strlen(s2), s2) == 0);
}
bool EndsWith(string const & s1, char const * s2)
{
size_t const n = s1.size();
size_t const m = strlen(s2);
if (n < m)
return false;
return (s1.compare(n - m, m, s2) == 0);
}
bool EndsWith(string const & s1, string const & s2)
{
return s1.size() >= s2.size() && s1.compare(s1.size() - s2.size(), s2.size(), s2) == 0;
}
string to_string_dac(double d, int dac)
{
dac = min(numeric_limits<double>::digits10, dac);
ostringstream ss;
if (d < 1. && d > -1.)
{
string res;
if (d >= 0.)
{
ss << setprecision(dac + 1) << d + 1;
res = ss.str();
res[0] = '0';
}
else
{
ss << setprecision(dac + 1) << d - 1;
res = ss.str();
res[1] = '0';
}
return res;
}
// Calc digits before comma (log10).
double fD = fabs(d);
while (fD >= 1.0 && dac < numeric_limits<double>::digits10)
{
fD /= 10.0;
++dac;
}
ss << setprecision(dac) << d;
return ss.str();
}
bool IsHTML(string const & utf8)
{
string::const_iterator it = utf8.begin();
size_t ltCount = 0;
size_t gtCount = 0;
while (it != utf8.end())
{
UniChar const c = utf8::unchecked::next(it);
if (c == '<')
++ltCount;
else if (c == '>')
++gtCount;
}
return (ltCount > 0 && gtCount > 0);
}
bool AlmostEqual(string const & str1, string const & str2, size_t mismatchedCount)
{
pair<string::const_iterator, string::const_iterator> mis(str1.begin(), str2.begin());
auto const str1End = str1.end();
auto const str2End = str2.end();
for (size_t i = 0; i <= mismatchedCount; ++i)
{
mis = mismatch(mis.first, str1End, mis.second);
if (mis.first == str1End && mis.second == str2End)
return true;
if (mis.first != str1End)
++mis.first;
if (mis.second != str2End)
++mis.second;
}
return false;
}
} // namespace strings
|