Parent: [e5f41a] (diff)

Child: [e327ea] (diff)

Download this file

pathut.cpp    545 lines (485 with data), 12.3 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
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
#ifndef lint
static char rcsid[] = "@(#$Id: pathut.cpp,v 1.23 2008-11-24 15:47:40 dockes Exp $ (C) 2004 J.F.Dockes";
#endif
/*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the
* Free Software Foundation, Inc.,
* 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
*/
#ifndef TEST_PATHUT
#include "autoconfig.h"
#include <unistd.h>
#include <fcntl.h>
#include <sys/param.h>
#include <pwd.h>
#include <math.h>
#include <sys/types.h>
// Let's include all files where statfs can be defined and hope for no
// conflict...
#ifdef HAVE_SYS_MOUNT_H
#include <sys/mount.h>
#endif
#ifdef HAVE_SYS_STATFS_H
#include <sys/statfs.h>
#endif
#ifdef HAVE_SYS_STATVFS_H
#include <sys/statvfs.h>
#endif
#ifdef HAVE_SYS_VFS_H
#include <sys/vfs.h>
#endif
#include <cstdlib>
#include <cstring>
#include <iostream>
#include <list>
#include <stack>
#ifndef NO_NAMESPACES
using std::string;
using std::list;
using std::stack;
#endif /* NO_NAMESPACES */
#include "pathut.h"
#include "transcode.h"
#include "wipedir.h"
bool fsocc(const string &path, int *pc, long *blocks)
{
#ifdef sun
struct statvfs buf;
if (statvfs(path.c_str(), &buf) != 0) {
return false;
}
#else
struct statfs buf;
if (statfs(path.c_str(), &buf) != 0) {
return false;
}
#endif
// used blocks
double fpc = 0.0;
#define FSOCC_USED (double(buf.f_blocks - buf.f_bfree))
#define FSOCC_TOTAVAIL (FSOCC_USED + double(buf.f_bavail))
if (FSOCC_TOTAVAIL > 0) {
fpc = 100.0 * FSOCC_USED / FSOCC_TOTAVAIL;
}
*pc = int(fpc);
if (blocks) {
*blocks = 0;
#define FSOCC_MB (1024*1024)
if (buf.f_bsize > 0) {
int ratio = buf.f_bsize > FSOCC_MB ? buf.f_bsize / FSOCC_MB :
FSOCC_MB / buf.f_bsize;
*blocks = buf.f_bsize > FSOCC_MB ? long(buf.f_bavail) * ratio :
long(buf.f_bavail) / ratio;
}
}
return true;
}
static const char *tmplocation()
{
const char *tmpdir = getenv("RECOLL_TMPDIR");
if (!tmpdir)
tmpdir = getenv("TMPDIR");
if (!tmpdir)
tmpdir = "/tmp";
return tmpdir;
}
bool maketmpdir(string& tdir, string& reason)
{
tdir = path_cat(tmplocation(), "rcltmpXXXXXX");
char *cp = strdup(tdir.c_str());
if (!cp) {
reason = "maketmpdir: out of memory (for file name !)\n";
tdir.erase();
return false;
}
if (!
#ifdef HAVE_MKDTEMP
mkdtemp(cp)
#else
mktemp(cp)
#endif // HAVE_MKDTEMP
) {
free(cp);
reason = "maketmpdir: mktemp failed\n";
tdir.erase();
return false;
}
tdir = cp;
free(cp);
#ifndef HAVE_MKDTEMP
if (mkdir(tdir.c_str(), 0700) < 0) {
reason = string("maketmpdir: mkdir ") + tdir + " failed";
tdir.erase();
return false;
}
#endif
return true;
}
TempFileInternal::TempFileInternal(const string& suffix)
{
string filename = path_cat(tmplocation(), "rcltmpfXXXXXX");
char *cp = strdup(filename.c_str());
if (!cp) {
m_reason = "Out of memory (for file name !)\n";
return;
}
// Yes using mkstemp this way is awful (bot the suffix adding and
// using mkstemp() just to avoid the warnings)
int fd;
if ((fd = mkstemp(cp)) < 0) {
free(cp);
m_reason = "TempFileInternal: mkstemp failed\n";
return;
}
close(fd);
unlink(cp);
filename = cp;
free(cp);
m_filename = filename + suffix;
if (close(open(m_filename.c_str(), O_CREAT|O_EXCL, 0600)) != 0) {
m_reason = string("Could not open/create") + m_filename;
m_filename.erase();
}
}
TempFileInternal::~TempFileInternal()
{
if (!m_filename.empty())
unlink(m_filename.c_str());
}
TempDir::TempDir()
{
if (!maketmpdir(m_dirname, m_reason)) {
m_dirname.erase();
return;
}
}
TempDir::~TempDir()
{
if (!m_dirname.empty()) {
(void)wipedir(m_dirname, true, true);
m_dirname.erase();
}
}
bool TempDir::wipe()
{
if (m_dirname.empty()) {
m_reason = "TempDir::wipe: no directory !\n";
return false;
}
if (wipedir(m_dirname, false, true)) {
m_reason = "TempDir::wipe: wipedir failed\n";
return false;
}
return true;
}
void path_catslash(string &s) {
if (s.empty() || s[s.length() - 1] != '/')
s += '/';
}
string path_cat(const string &s1, const string &s2) {
string res = s1;
path_catslash(res);
res += s2;
return res;
}
string path_getfather(const string &s) {
string father = s;
// ??
if (father.empty())
return "./";
if (father[father.length() - 1] == '/') {
// Input ends with /. Strip it, handle special case for root
if (father.length() == 1)
return father;
father.erase(father.length()-1);
}
string::size_type slp = father.rfind('/');
if (slp == string::npos)
return "./";
father.erase(slp);
path_catslash(father);
return father;
}
string path_getsimple(const string &s) {
string simple = s;
if (simple.empty())
return simple;
string::size_type slp = simple.rfind('/');
if (slp == string::npos)
return simple;
simple.erase(0, slp+1);
return simple;
}
string path_basename(const string &s, const string &suff)
{
string simple = path_getsimple(s);
string::size_type pos = string::npos;
if (suff.length() && simple.length() > suff.length()) {
pos = simple.rfind(suff);
if (pos != string::npos && pos + suff.length() == simple.length())
return simple.substr(0, pos);
}
return simple;
}
string path_home()
{
uid_t uid = getuid();
struct passwd *entry = getpwuid(uid);
if (entry == 0) {
const char *cp = getenv("HOME");
if (cp)
return cp;
else
return "/";
}
string homedir = entry->pw_dir;
path_catslash(homedir);
return homedir;
}
extern string path_tildexpand(const string &s)
{
if (s.empty() || s[0] != '~')
return s;
string o = s;
if (s.length() == 1) {
o.replace(0, 1, path_home());
} else if (s[1] == '/') {
o.replace(0, 2, path_home());
} else {
string::size_type pos = s.find('/');
int l = (pos == string::npos) ? s.length() - 1 : pos - 1;
struct passwd *entry = getpwnam(s.substr(1, l).c_str());
if (entry)
o.replace(0, l+1, entry->pw_dir);
}
return o;
}
extern string path_absolute(const string &is)
{
if (is.length() == 0)
return is;
string s = is;
if (s[0] != '/') {
char buf[MAXPATHLEN];
if (!getcwd(buf, MAXPATHLEN)) {
return string();
}
s = path_cat(string(buf), s);
}
return s;
}
#include <smallut.h>
extern string path_canon(const string &is)
{
if (is.length() == 0)
return is;
string s = is;
if (s[0] != '/') {
char buf[MAXPATHLEN];
if (!getcwd(buf, MAXPATHLEN)) {
return string();
}
s = path_cat(string(buf), s);
}
list<string>elems;
stringToTokens(s, elems, "/");
list<string> cleaned;
for (list<string>::const_iterator it = elems.begin();
it != elems.end(); it++){
if (*it == "..") {
if (!cleaned.empty())
cleaned.pop_back();
} else if (it->empty() || *it == ".") {
} else {
cleaned.push_back(*it);
}
}
string ret;
if (!cleaned.empty()) {
for (list<string>::const_iterator it = cleaned.begin();
it != cleaned.end(); it++) {
ret += "/";
ret += *it;
}
} else {
ret = "/";
}
return ret;
}
#include <glob.h>
#include <sys/stat.h>
list<string> path_dirglob(const string &dir,
const string pattern)
{
list<string> res;
glob_t mglob;
string mypat=path_cat(dir, pattern);
if (glob(mypat.c_str(), 0, 0, &mglob)) {
return res;
}
for (int i = 0; i < int(mglob.gl_pathc); i++) {
res.push_back(mglob.gl_pathv[i]);
}
globfree(&mglob);
return res;
}
bool path_isdir(const string& path)
{
struct stat st;
if (lstat(path.c_str(), &st) < 0)
return false;
if (S_ISDIR(st.st_mode))
return true;
return false;
}
string url_encode(const string& url, string::size_type offs)
{
string out = url.substr(0, offs);
const char *cp = url.c_str();
for (string::size_type i = offs; i < url.size(); i++) {
int c;
const char *h = "0123456789ABCDEF";
c = cp[i];
if(c <= 0x1f ||
c >= 0x7f ||
c == '<' ||
c == '>' ||
c == ' ' ||
c == '\t'||
c == '"' ||
c == '#' ||
c == '%' ||
c == '{' ||
c == '}' ||
c == '|' ||
c == '\\' ||
c == '^' ||
c == '~'||
c == '[' ||
c == ']' ||
c == '`') {
out += '%';
out += h[(c >> 4) & 0xf];
out += h[c & 0xf];
} else {
out += char(c);
}
}
return out;
}
string url_gpath(const string& url)
{
// Remove the access schema part (or whatever it's called)
string::size_type colon = url.find_first_of(":");
if (colon == string::npos || colon == url.size() - 1)
return url;
// If there are non-alphanum chars before the ':', then there
// probably is no scheme. Whatever...
for (string::size_type i = 0; i < colon; i++) {
if (!isalnum(url.at(i)))
return url;
}
// In addition we canonize the path to remove empty host parts
// (for compatibility with older versions of recoll where file://
// was hardcoded, but the local path was used for doc
// identification.
return path_canon(url.substr(colon+1));
}
// Printable url: this is used to transcode from the system charset
// into either utf-8 if transcoding succeeds, or url-encoded
bool printableUrl(const string &fcharset, const string &in, string &out)
{
int ecnt = 0;
if (!transcode(in, out, fcharset, "UTF-8", &ecnt) || ecnt) {
out = url_encode(in, 7);
}
return true;
}
#else // TEST_PATHUT
#include <iostream>
using namespace std;
#include "pathut.h"
const char *tstvec[] = {"", "/", "/dir", "/dir/", "/dir1/dir2",
"/dir1/dir2",
"./dir", "./dir1/", "dir", "../dir", "/dir/toto.c",
"/dir/.c", "/dir/toto.txt", "toto.txt1"
};
const string ttvec[] = {"/dir", "", "~", "~/sub", "~root", "~root/sub",
"~nosuch", "~nosuch/sub"};
int nttvec = sizeof(ttvec) / sizeof(string);
const char *thisprog;
int main(int argc, const char **argv)
{
thisprog = *argv++;argc--;
string s;
list<string>::const_iterator it;
#if 0
for (unsigned int i = 0;i < sizeof(tstvec) / sizeof(char *); i++) {
cout << tstvec[i] << " Father " << path_getfather(tstvec[i]) << endl;
}
for (unsigned int i = 0;i < sizeof(tstvec) / sizeof(char *); i++) {
cout << tstvec[i] << " Simple " << path_getsimple(tstvec[i]) << endl;
}
for (unsigned int i = 0;i < sizeof(tstvec) / sizeof(char *); i++) {
cout << tstvec[i] << " Basename " <<
path_basename(tstvec[i], ".txt") << endl;
}
#endif
#if 0
for (int i = 0; i < nttvec; i++) {
cout << "tildexp: '" << ttvec[i] << "' -> '" <<
path_tildexpand(ttvec[i]) << "'" << endl;
}
#endif
#if 0
const string canontst[] = {"/dir1/../../..", "/////", "",
"/dir1/../../.././/////dir2///////",
"../../",
"../../../../../../../../../../"
};
unsigned int nttvec = sizeof(canontst) / sizeof(string);
for (unsigned int i = 0; i < nttvec; i++) {
cout << "canon: '" << canontst[i] << "' -> '" <<
path_canon(canontst[i]) << "'" << endl;
}
#endif
#if 0
if (argc != 2) {
fprintf(stderr, "Usage: trpathut <dir> <pattern>\n");
exit(1);
}
string dir = *argv++;argc--;
string pattern = *argv++;argc--;
list<string> matched = path_dirglob(dir, pattern);
for (it = matched.begin(); it != matched.end();it++) {
cout << *it << endl;
}
#endif
#if 1
if (argc != 1) {
fprintf(stderr, "Usage: fsocc: trpathut <path>\n");
exit(1);
}
string path = *argv++;argc--;
int pc;
long blocks;
if (!fsocc(path, &pc, &blocks)) {
fprintf(stderr, "fsocc failed\n");
return 1;
}
printf("pc %d, megabytes %ld\n", pc, blocks);
#endif
return 0;
}
#endif // TEST_PATHUT