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
|
#include "strings.hh"
namespace nix {
std::vector<char *> stringsToCharPtrs(const Strings & ss)
{
std::vector<char *> res;
for (auto & s : ss) res.push_back((char *) s.c_str());
res.push_back(0);
return res;
}
template<class C> C tokenizeString(std::string_view s, std::string_view separators)
{
C result;
auto pos = s.find_first_not_of(separators, 0);
while (pos != std::string_view::npos) {
auto end = s.find_first_of(separators, pos + 1);
if (end == std::string_view::npos) end = s.size();
result.insert(result.end(), std::string(s, pos, end - pos));
pos = s.find_first_not_of(separators, end);
}
return result;
}
template Strings tokenizeString(std::string_view s, std::string_view separators);
template StringSet tokenizeString(std::string_view s, std::string_view separators);
template std::vector<std::string> tokenizeString(std::string_view s, std::string_view separators);
std::string chomp(std::string_view s)
{
size_t i = s.find_last_not_of(" \n\r\t");
return i == std::string_view::npos ? "" : std::string(s, 0, i + 1);
}
std::string trim(std::string_view s, std::string_view whitespace)
{
auto i = s.find_first_not_of(whitespace);
if (i == s.npos) return "";
auto j = s.find_last_not_of(whitespace);
return std::string(s, i, j == s.npos ? j : j - i + 1);
}
std::string replaceStrings(
std::string res,
std::string_view from,
std::string_view to)
{
if (from.empty()) return res;
size_t pos = 0;
while ((pos = res.find(from, pos)) != std::string::npos) {
res.replace(pos, from.size(), to);
pos += to.size();
}
return res;
}
Rewriter::Rewriter(std::map<std::string, std::string> rewrites)
: rewrites(std::move(rewrites))
{
for (const auto & [k, v] : this->rewrites) {
assert(!k.empty());
initials.push_back(k[0]);
}
std::ranges::sort(initials);
auto [firstDupe, end] = std::ranges::unique(initials);
initials.erase(firstDupe, end);
}
std::string Rewriter::operator()(std::string s)
{
size_t j = 0;
while ((j = s.find_first_of(initials, j)) != std::string::npos) {
size_t skip = 1;
for (auto & [from, to] : rewrites) {
if (s.compare(j, from.size(), from) == 0) {
s.replace(j, from.size(), to);
skip = to.size();
break;
}
}
j += skip;
}
return s;
}
std::string toLower(const std::string & s)
{
std::string r(s);
for (auto & c : r)
c = std::tolower(c);
return r;
}
std::string shellEscape(const std::string_view s)
{
std::string r;
r.reserve(s.size() + 2);
r += "'";
for (auto & i : s)
if (i == '\'') r += "'\\''"; else r += i;
r += '\'';
return r;
}
constexpr char base64Chars[] = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
std::string base64Encode(std::string_view s)
{
std::string res;
res.reserve((s.size() + 2) / 3 * 4);
int data = 0, nbits = 0;
for (char c : s) {
data = data << 8 | (unsigned char) c;
nbits += 8;
while (nbits >= 6) {
nbits -= 6;
res.push_back(base64Chars[data >> nbits & 0x3f]);
}
}
if (nbits) res.push_back(base64Chars[data << (6 - nbits) & 0x3f]);
while (res.size() % 4) res.push_back('=');
return res;
}
std::string base64Decode(std::string_view s)
{
constexpr char npos = -1;
constexpr std::array<char, 256> base64DecodeChars = [&]() {
std::array<char, 256> result{};
for (auto& c : result)
c = npos;
for (int i = 0; i < 64; i++)
result[base64Chars[i]] = i;
return result;
}();
std::string res;
// Some sequences are missing the padding consisting of up to two '='.
// vvv
res.reserve((s.size() + 2) / 4 * 3);
unsigned int d = 0, bits = 0;
for (char c : s) {
if (c == '=') break;
if (c == '\n') continue;
char digit = base64DecodeChars[(unsigned char) c];
if (digit == npos)
throw Error("invalid character in Base64 string: '%c'", c);
bits += 6;
d = d << 6 | digit;
if (bits >= 8) {
res.push_back(d >> (bits - 8) & 0xff);
bits -= 8;
}
}
return res;
}
std::string stripIndentation(std::string_view s)
{
size_t minIndent = 10000;
size_t curIndent = 0;
bool atStartOfLine = true;
for (auto & c : s) {
if (atStartOfLine && c == ' ')
curIndent++;
else if (c == '\n') {
if (atStartOfLine)
minIndent = std::max(minIndent, curIndent);
curIndent = 0;
atStartOfLine = true;
} else {
if (atStartOfLine) {
minIndent = std::min(minIndent, curIndent);
atStartOfLine = false;
}
}
}
std::string res;
size_t pos = 0;
while (pos < s.size()) {
auto eol = s.find('\n', pos);
if (eol == s.npos) eol = s.size();
if (eol - pos > minIndent)
res.append(s.substr(pos + minIndent, eol - pos - minIndent));
res.push_back('\n');
pos = eol + 1;
}
return res;
}
std::pair<std::string_view, std::string_view> getLine(std::string_view s)
{
auto newline = s.find('\n');
if (newline == s.npos) {
return {s, ""};
} else {
auto line = s.substr(0, newline);
if (!line.empty() && line[line.size() - 1] == '\r')
line = line.substr(0, line.size() - 1);
return {line, s.substr(newline + 1)};
}
}
std::string showBytes(uint64_t bytes)
{
return fmt("%.2f MiB", bytes / (1024.0 * 1024.0));
}
}
|