Parent: [ccb27e] (diff)

Child: [52fa78] (diff)

Download this file

smallut.cpp    343 lines (316 with data), 6.9 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
#ifndef lint
static char rcsid[] = "@(#$Id: smallut.cpp,v 1.10 2005-11-25 14:36:45 dockes Exp $ (C) 2004 J.F.Dockes";
#endif
#ifndef TEST_SMALLUT
#include <string>
#include <ctype.h>
#include <unistd.h>
#include <errno.h>
#include <sys/types.h>
#include <sys/stat.h>
#include "smallut.h"
#include "debuglog.h"
#include "pathut.h"
#ifndef NO_NAMESPACES
using namespace std;
#endif /* NO_NAMESPACES */
#define MIN(A,B) ((A)<(B)?(A):(B))
bool maketmpdir(string& tdir)
{
const char *tmpdir = getenv("RECOLL_TMPDIR");
if (!tmpdir)
tmpdir = getenv("TMPDIR");
if (!tmpdir)
tmpdir = "/tmp";
tdir = tmpdir;
path_cat(tdir, "rcltmpXXXXXX");
{
char *cp = strdup(tdir.c_str());
if (!cp) {
LOGERR(("maketmpdir: out of memory (for file name !)\n"));
tdir.erase();
return false;
}
#ifdef HAVE_MKDTEMP
if (!mkdtemp(cp)) {
#else
if (!mktemp(cp)) {
#endif // HAVE_MKDTEMP
free(cp);
LOGERR(("maketmpdir: mktemp failed\n"));
tdir.erase();
return false;
}
tdir = cp;
free(cp);
}
#ifndef HAVE_MKDTEMP
if (mkdir(tdir.c_str(), 0700) < 0) {
LOGERR(("maketmpdir: mkdir %s failed\n", tdir.c_str()));
tdir.erase();
return false;
}
#endif
return true;
}
string stringlistdisp(const list<string>& sl)
{
string s;
for (list<string>::const_iterator it = sl.begin(); it!= sl.end(); it++)
s += "[" + *it + "] ";
if (!s.empty())
s.erase(s.length()-1);
return s;
}
int stringicmp(const string & s1, const string& s2)
{
string::const_iterator it1 = s1.begin();
string::const_iterator it2 = s2.begin();
int size1 = s1.length(), size2 = s2.length();
char c1, c2;
if (size1 > size2) {
while (it1 != s1.end()) {
c1 = ::toupper(*it1);
c2 = ::toupper(*it2);
if (c1 != c2) {
return c1 > c2 ? 1 : -1;
}
++it1; ++it2;
}
return size1 == size2 ? 0 : 1;
} else {
while (it2 != s2.end()) {
c1 = ::toupper(*it1);
c2 = ::toupper(*it2);
if (c1 != c2) {
return c1 > c2 ? 1 : -1;
}
++it1; ++it2;
}
return size1 == size2 ? 0 : -1;
}
}
// s1 is already lowercase
int stringlowercmp(const string & s1, const string& s2)
{
string::const_iterator it1 = s1.begin();
string::const_iterator it2 = s2.begin();
int size1 = s1.length(), size2 = s2.length();
char c2;
if (size1 > size2) {
while (it1 != s1.end()) {
c2 = ::tolower(*it2);
if (*it1 != c2) {
return *it1 > c2 ? 1 : -1;
}
++it1; ++it2;
}
return size1 == size2 ? 0 : 1;
} else {
while (it2 != s2.end()) {
c2 = ::tolower(*it2);
if (*it1 != c2) {
return *it1 > c2 ? 1 : -1;
}
++it1; ++it2;
}
return size1 == size2 ? 0 : -1;
}
}
// s1 is already uppercase
int stringuppercmp(const string & s1, const string& s2)
{
string::const_iterator it1 = s1.begin();
string::const_iterator it2 = s2.begin();
int size1 = s1.length(), size2 = s2.length();
char c2;
if (size1 > size2) {
while (it1 != s1.end()) {
c2 = ::toupper(*it2);
if (*it1 != c2) {
return *it1 > c2 ? 1 : -1;
}
++it1; ++it2;
}
return size1 == size2 ? 0 : 1;
} else {
while (it2 != s2.end()) {
c2 = ::toupper(*it2);
if (*it1 != c2) {
return *it1 > c2 ? 1 : -1;
}
++it1; ++it2;
}
return size1 == size2 ? 0 : -1;
}
}
// Compare charset names, removing the more common spelling variations
bool samecharset(const string &cs1, const string &cs2)
{
string mcs1, mcs2;
// Remove all - and _, turn to lowecase
for (unsigned int i = 0; i < cs1.length();i++) {
if (cs1[i] != '_' && cs1[i] != '-') {
mcs1 += ::tolower(cs1[i]);
}
}
for (unsigned int i = 0; i < cs2.length();i++) {
if (cs2[i] != '_' && cs2[i] != '-') {
mcs2 += ::tolower(cs2[i]);
}
}
return mcs1 == mcs2;
}
bool stringToStrings(const string &s, std::list<string> &tokens)
{
string current;
tokens.clear();
enum states {SPACE, TOKEN, INQUOTE, ESCAPE};
states state = SPACE;
for (unsigned int i = 0; i < s.length(); i++) {
switch (s[i]) {
case '"':
switch(state) {
case SPACE:
state=INQUOTE; continue;
case TOKEN:
current += '"';
continue;
case INQUOTE:
tokens.push_back(current);
current = "";
state = SPACE;
continue;
case ESCAPE:
current += '"';
state = INQUOTE;
continue;
}
break;
case '\\':
switch(state) {
case SPACE:
case TOKEN:
current += '\\';
state=TOKEN;
continue;
case INQUOTE:
state = ESCAPE;
continue;
case ESCAPE:
current += '\\';
state = INQUOTE;
continue;
}
break;
case ' ':
case '\t':
switch(state) {
case SPACE:
continue;
case TOKEN:
tokens.push_back(current);
current = "";
state = SPACE;
continue;
case INQUOTE:
case ESCAPE:
current += s[i];
continue;
}
break;
default:
switch(state) {
case ESCAPE:
state = INQUOTE;
break;
case SPACE:
state = TOKEN;
break;
case TOKEN:
case INQUOTE:
break;
}
current += s[i];
}
}
switch(state) {
case SPACE:
break;
case TOKEN:
tokens.push_back(current);
break;
case INQUOTE:
case ESCAPE:
return false;
}
return true;
}
bool stringToBool(const string &s)
{
if (s.empty())
return false;
if (isdigit(s[0])) {
int val = atoi(s.c_str());
return val ? true : false;
}
if (strchr("yYoOtT", s[0]))
return true;
return false;
}
void trimstring(string &s, const char *ws)
{
string::size_type pos = s.find_first_not_of(ws);
if (pos == string::npos) {
s = "";
return;
}
s.replace(0, pos, "");
pos = s.find_last_not_of(ws);
if (pos != string::npos && pos != s.length()-1)
s.replace(pos+1, string::npos, "");
}
#else
#include <string>
#include "smallut.h"
struct spair {
const char *s1;
const char *s2;
};
struct spair pairs[] = {
{"", ""},
{"", "a"},
{"a", ""},
{"a", "a"},
{"A", "a"},
{"a", "A"},
{"A", "A"},
{"12", "12"},
{"a", "ab"},
{"ab", "a"},
{"A", "Ab"},
{"a", "Ab"},
};
int npairs = sizeof(pairs) / sizeof(struct spair);
int main(int argc, char **argv)
{
for (int i = 0; i < npairs; i++) {
{
int c = stringicmp(pairs[i].s1, pairs[i].s2);
printf("'%s' %s '%s' ", pairs[i].s1,
c == 0 ? "==" : c < 0 ? "<" : ">", pairs[i].s2);
}
{
int cl = stringlowercmp(pairs[i].s1, pairs[i].s2);
printf("L '%s' %s '%s' ", pairs[i].s1,
cl == 0 ? "==" : cl < 0 ? "<" : ">", pairs[i].s2);
}
{
int cu = stringuppercmp(pairs[i].s1, pairs[i].s2);
printf("U '%s' %s '%s' ", pairs[i].s1,
cu == 0 ? "==" : cu < 0 ? "<" : ">", pairs[i].s2);
}
printf("\n");
}
}
#endif