summaryrefslogtreecommitdiff
path: root/source3/python/py_tdbpack.c
blob: 06aebe61eb5ede6e9d95ae09a8ded31041c18ece (plain)
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
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
/* -*- c-file-style: "python"; indent-tabs-mode: nil; -*-
	 
   Python wrapper for Samba tdb pack/unpack functions
   Copyright (C) Martin Pool 2002


   NOTE PYTHON STYLE GUIDE
   http://www.python.org/peps/pep-0007.html
   
   
   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., 675 Mass Ave, Cambridge, MA 02139, USA.
*/



#include "Python.h"

static int pytdbpack_calc_reqd_len(char *format_str,
				   PyObject *val_seq);

static PyObject *pytdbpack_unpack_item(char,
				      char **pbuf,
				      int *plen);
static int
pytdbpack_calc_item_len(char format_ch,
			PyObject *val_obj);

static PyObject *pytdbpack_pack_data(const char *format_str,
				     PyObject *val_seq,
				     unsigned char *buf);


	
static const char * pytdbpack_docstring =
"Convert between Python values and Samba binary encodings.

This module is conceptually similar to the standard 'struct' module, but it
uses both a different binary format and a different description string.

Samba's encoding is based on that used inside DCE-RPC and SMB: a
little-endian, unpadded, non-self-describing binary format.  It is intended
that these functions be as similar as possible to the routines in Samba's
tdb/tdbutil module, with appropriate adjustments for Python datatypes.

Python strings are used to specify the format of data to be packed or
unpacked.

Strings in TDBs are typically stored in DOS codepages.  The caller of this
module must make appropriate translations if necessary, typically to and from
Unicode objects.

tdbpack format strings:

    'f':  NULL-terminated string in DOS codepage

    'P':  same as 'f'

    'd':  4 byte little-endian number

    'w':  2 byte little-endian number

    'P': \"Pointer\" value -- in the subset of DCERPC used by Samba, this is
          really just an \"exists\" or \"does not exist\" flag.  The boolean
          value of the Python object is used.
    
    'B': 4-byte LE length, followed by that many bytes of binary data.
         Corresponds to a Python byte string of the appropriate length.

    '$': Special flag indicating that the preceding format code should be
         repeated while data remains.  This is only supported for unpacking.

    Every code corresponds to a single Python object, except 'B' which
    corresponds to two values (length and contents), and '$', which produces
    however many make sense.
";


static char const pytdbpack_pack_doc[] = 
"pack(format, values) -> buffer
Pack Python objects into Samba binary format according to format string.

arguments:
    format -- string of tdbpack format characters
    values -- sequence of value objects corresponding 1:1 to format characters

returns:
    buffer -- string containing packed data

raises:
    IndexError -- if there are not the same number of format codes as of
        values
    ValueError -- if any of the format characters is illegal
    TypeError  -- if the format is not a string, or values is not a sequence,
        or any of the values is of the wrong type for the corresponding
        format character
";


static char const pytdbpack_unpack_doc[] =
"unpack(format, buffer) -> (values, rest)
Unpack Samba binary data according to format string.

arguments:
    format -- string of tdbpack characters
    buffer -- string of packed binary data

returns:
    2-tuple of:
        values -- sequence of values corresponding 1:1 to format characters
        rest -- string containing data that was not decoded, or '' if the
            whole string was consumed

raises:
    IndexError -- if there is insufficient data in the buffer for the
        format (or if the data is corrupt and contains a variable-length
        field extending past the end)
    ValueError -- if any of the format characters is illegal

notes:
    Because unconsumed data is returned, you can feed it back in to the
    unpacker to extract further fields.  Alternatively, if you wish to modify
    some fields near the start of the data, you may be able to save time by
    only unpacking and repacking the necessary part.
";



/*
  Game plan is to first of all walk through the arguments and calculate the
  total length that will be required.  We allocate a Python string of that
  size, then walk through again and fill it in.

  We just borrow references to all the passed arguments, since none of them
  need to be permanently stored.  We transfer ownership to the returned
  object.
 */	
static PyObject *
pytdbpack_pack(PyObject *self,
	       PyObject *args)
{
	char *format_str;
	PyObject *val_seq, *fast_seq, *buf_str;
	int reqd_len;
	char *packed_buf;

	/* TODO: Test passing wrong types or too many arguments */
	if (!PyArg_ParseTuple(args, "sO", &format_str, &val_seq))
		return NULL;

	/* Convert into a list or tuple (if not already one), so that we can
	 * index more easily. */
	fast_seq = PySequence_Fast(val_seq,
				   __FUNCTION__ ": argument 2 must be sequence");
	if (!fast_seq)
		return NULL;
			
	reqd_len = pytdbpack_calc_reqd_len(format_str, fast_seq);
	if (reqd_len == -1)	/* exception was thrown */
		return NULL;

	/* Allocate space.
	 
	   This design causes an unnecessary copying of the data when Python
	   constructs an object, and that might possibly be avoided by using a
	   Buffer object of some kind instead.  I'm not doing that for now
	   though.  */
	packed_buf = malloc(reqd_len);
	if (!packed_buf) {
		PyErr_Format(PyExc_MemoryError,
			     "%s: couldn't allocate %d bytes for packed buffer",
			     __FUNCTION__, reqd_len);
		return NULL;
	}	
	
	if (!pytdbpack_pack_data(format_str, fast_seq, packed_buf)) {
		free(packed_buf);
		return NULL;
	}

	buf_str = PyString_FromStringAndSize(packed_buf, reqd_len);
	free(packed_buf);	/* get rid of tmp buf */
	
	return buf_str;
}



static PyObject *
pytdbpack_unpack(PyObject *self,
		 PyObject *args)
{
	char *format_str, *packed_str, *ppacked;
	PyObject *val_list = NULL, *ret_tuple = NULL;
	PyObject *rest_string = NULL;
	int format_len, packed_len;
	int i;
	char last_format = '#';
	
	/* get arguments */
	if (!PyArg_ParseTuple(args, "ss#", &format_str, &packed_str, &packed_len))
		return NULL;

	format_len = strlen(format_str);
	
	/* allocate list to hold results */
	val_list = PyList_New(format_len);
	if (!val_list)
		goto failed;
	ret_tuple = PyTuple_New(2);
	if (!ret_tuple)
		goto failed;
	
	/* For every object, unpack.  */
	for (ppacked = packed_str, i = 0; i < format_len; i++) {
		PyObject *val_obj;
		char format;

		format = format_str[i];
		if (format == '$') {
			if (i == 0) {
				PyErr_Format(PyExc_ValueError,
					     "%s: '$' may not be first character in format",
					     __FUNCTION__);
				goto failed;
			}
			else {
				format = last_format; /* repeat */
			}
		}

		val_obj = pytdbpack_unpack_item(format,
						&ppacked,
						&packed_len);
		if (!val_obj)
			goto failed;

		PyList_SET_ITEM(val_list, i, val_obj);
		last_format = format;
	}

	/* put leftovers in box for lunch tomorrow */
	rest_string = PyString_FromStringAndSize(ppacked, packed_len);
	if (!rest_string)
		goto failed;

	/* return (values, rest) tuple; give up references to them */
	PyTuple_SET_ITEM(ret_tuple, 0, val_list);
	val_list = NULL;
	PyTuple_SET_ITEM(ret_tuple, 1, rest_string);
	val_list = NULL;
	return ret_tuple;

  failed:
	/* handle failure: deallocate anything */
	Py_XDECREF(val_list);
	Py_XDECREF(ret_tuple);
	Py_XDECREF(rest_string);
	return NULL;
}


/*
  Internal routine that calculates how many bytes will be required to
  encode the values in the format.

  Also checks that the value list is the right size for the format list.

  Returns number of bytes (may be 0), or -1 if there's something wrong, in
  which case a Python exception has been raised.

  Arguments:

    val_seq: a Fast Sequence (list or tuple), being all the values
*/
static int
pytdbpack_calc_reqd_len(char *format_str,
			PyObject *val_seq)
{
	int len = 0;
	char *p;
	int val_i;
	int val_len;

	val_len = PySequence_Fast_GET_SIZE(val_seq);

	for (p = format_str, val_i = 0; *p; p++, val_i++) {
		char ch = *p;
		PyObject *val_obj;
		int item_len;

		if (val_i >= val_len) {
			PyErr_Format(PyExc_IndexError,
				     "samba.tdbpack.pack: value list is too short for format string");
			return -1;
		}

		/* borrow a reference to the item */
		val_obj = PySequence_Fast_GET_ITEM(val_seq, val_i);
		if (!val_obj)
			return -1;

		item_len = pytdbpack_calc_item_len(ch, val_obj);
		if (item_len == -1)
			return -1;
		else
			len += item_len;
	}

	if (val_i != val_len) {
		PyErr_Format(PyExc_IndexError,
			     "%s: value list is wrong length for format string",
			     __FUNCTION__);
		return -1;
	}

	return len;
}


static PyObject *pytdbpack_bad_type(char ch,
				    const char *expected,
				    PyObject *val_obj)
{
	PyObject *r = PyObject_Repr(val_obj);
	if (!r)
		return NULL;
	PyErr_Format(PyExc_TypeError,
		     "tdbpack: format '%c' requires %s, not %s",
		     ch, expected, PyString_AS_STRING(r));
	Py_DECREF(r);
	return val_obj;
}


/*
 * Calculate the number of bytes required to pack a single value.  While doing
 * this, also conduct some initial checks that the argument types are
 * reasonable.
 *
 * Returns -1 on exception.
 */
static int
pytdbpack_calc_item_len(char ch,
			PyObject *val_obj)
{
	if (ch == 'd' || ch == 'w') {
		if (!PyInt_Check(val_obj)) {
			pytdbpack_bad_type(ch, "Int", val_obj);
			return -1;
		}
		if (ch == 'w')
			return 2;
		else 
			return 4;
	} else if (ch == 'p') {
		return 4;
	}
	else if (ch == 'f' || ch == 'P' || ch == 'B') {
		/* nul-terminated 8-bit string */
		if (!PyString_Check(val_obj)) {
			pytdbpack_bad_type(ch, "String", val_obj);
		}
		
		if (ch == 'B') {
			/* byte buffer; just use Python string's length, plus
			   a preceding word */
			return 4 + PyString_GET_SIZE(val_obj);
		}
		else {
			/* one nul character */
			return 1 + PyString_GET_SIZE(val_obj);
		}		
	}
	else {	
		PyErr_Format(PyExc_ValueError,
			     "tdbpack: format character '%c' is not supported",
			     ch);
		
		return -1;
	}
}


/*
  XXX: glib and Samba have quicker macro for doing the endianness conversions,
  but I don't know of one in plain libc, and it's probably not a big deal.  I
  realize this is kind of dumb because we'll almost always be on x86, but
  being safe is important.
*/
static void pack_int32(unsigned long val_long, unsigned char **pbuf)
{
	(*pbuf)[0] =         val_long & 0xff;
	(*pbuf)[1] = (val_long >> 8)  & 0xff;
	(*pbuf)[2] = (val_long >> 16) & 0xff;
	(*pbuf)[3] = (val_long >> 24) & 0xff;
	(*pbuf) += 4;
}


static void pack_bytes(long len, const char *from,
		       unsigned char **pbuf)
{
	memcpy(*pbuf, from, len);
	(*pbuf) += len;
}


static void
unpack_err_too_short(void)
{
	PyErr_Format(PyExc_IndexError,
		     __FUNCTION__ ": data too short for unpack format");
}


static PyObject *
unpack_int32(char **pbuf, int *plen)
{
	long v;
	unsigned char *b;
	
	if (*plen < 4) {
		unpack_err_too_short();
		return NULL;
	}

	b = *pbuf;
	v = b[0] | b[1]<<8 | b[2]<<16 | b[3]<<24;
	
	(*pbuf) += 4;
	(*plen) -= 4;

	return PyInt_FromLong(v);
}


static PyObject *unpack_int16(char **pbuf, int *plen)
{
	long v;
	unsigned char *b;
	
	if (*plen < 2) {
		unpack_err_too_short();
		return NULL;
	}

	b = *pbuf;
	v = b[0] | b[1]<<8;
	
	(*pbuf) += 2;
	(*plen) -= 2;

	return PyInt_FromLong(v);
}


static PyObject *
unpack_string(char **pbuf, int *plen)
{
	int len;
	char *nul_ptr, *start;

	start = *pbuf;
	
	nul_ptr = memchr(start, '\0', *plen);
	if (!nul_ptr) {
		unpack_err_too_short();
		return NULL;
	}

	len = nul_ptr - start;

	*pbuf += len + 1;	/* skip \0 */
	*plen -= len + 1;

	return PyString_FromStringAndSize(start, len);
}


static PyObject *
unpack_buffer(char **pbuf, int *plen)
{
	/* first get 32-bit len */
	long slen;
	unsigned char *b;
	unsigned char *start;
	
	if (*plen < 4) {
		unpack_err_too_short();
		return NULL;
	}
	
	b = *pbuf;
	slen = b[0] | b[1]<<8 | b[2]<<16 | b[3]<<24;

	if (slen < 0) { /* surely you jest */
		PyErr_Format(PyExc_ValueError,
			     __FUNCTION__ ": buffer seems to have negative length");
		return NULL;
	}

	(*pbuf) += 4;
	(*plen) -= 4;
	start = *pbuf;

	if (*plen < slen) {
		PyErr_Format(PyExc_IndexError,
			     __FUNCTION__ ": not enough data to unpack buffer: "
			     "need %d bytes, have %d",
			     (int) slen, *plen);
		return NULL;
	}

	(*pbuf) += slen;
	(*plen) -= slen;

	return PyString_FromStringAndSize(start, slen);
}


/* Unpack a single field from packed data, according to format character CH.
   Remaining data is at *PBUF, of *PLEN.

   *PBUF is advanced, and *PLEN reduced to reflect the amount of data that has
   been consumed.

   Returns a reference to the unpacked Python object, or NULL for failure.
*/
static PyObject *pytdbpack_unpack_item(char ch,
				       char **pbuf,
				       int *plen)
{
	if (ch == 'w') {	/* 16-bit int */
		return unpack_int16(pbuf, plen);
	}
	else if (ch == 'd' || ch == 'p') { /* 32-bit int */
		/* pointers can just come through as integers */
		return unpack_int32(pbuf, plen);
	}
	else if (ch == 'f' || ch == 'P') { /* nul-term string  */
		return unpack_string(pbuf, plen);
	}
	else if (ch == 'B') { /* length, buffer */
		return unpack_buffer(pbuf, plen);
	}
	else {
		PyErr_Format(PyExc_ValueError,
			     __FUNCTION__ ": format character '%c' is not supported",
			     ch);
		
		return NULL;
	}
}



/*
  Pack a single item VAL_OBJ, encoded using format CH, into a buffer at *PBUF,
  and advance the pointer.  Buffer length has been pre-calculated so we are
  sure that there is enough space.

*/
static PyObject *
pytdbpack_pack_item(char ch,
		    PyObject *val_obj,
		    unsigned char **pbuf)
{
	if (ch == 'w') {
		unsigned long val_long = PyInt_AsLong(val_obj);
		(*pbuf)[0] = val_long & 0xff;
		(*pbuf)[1] = (val_long >> 8) & 0xff;
		(*pbuf) += 2;
	}
	else if (ch == 'd') {
		/* 4-byte LE number */
		pack_int32(PyInt_AsLong(val_obj), pbuf);
	}
	else if (ch == 'p') {
		/* "Pointer" value -- in the subset of DCERPC used by Samba,
		   this is really just an "exists" or "does not exist"
		   flag. */
		pack_int32(PyObject_IsTrue(val_obj), pbuf);
	}
	else if (ch == 'f' || ch == 'P') {
		int size;
		char *sval;

		size = PyString_GET_SIZE(val_obj);
		sval = PyString_AS_STRING(val_obj);
		pack_bytes(size+1, sval, pbuf); /* include nul */
	}
	else if (ch == 'B') {
		int size;
		char *sval;

		size = PyString_GET_SIZE(val_obj);
		pack_int32(size, pbuf);
		sval = PyString_AS_STRING(val_obj);
		pack_bytes(size, sval, pbuf); /* do not include nul */
	}
	else {
		/* this ought to be caught while calculating the length, but
		   just in case. */
		PyErr_Format(PyExc_ValueError,
			     "%s: format character '%c' is not supported",
			     __FUNCTION__, ch);
		
		return NULL;
	}
		
	return Py_None;
}


/*
  Pack data according to FORMAT_STR from the elements of VAL_SEQ into
  PACKED_BUF.

  The string has already been checked out, so we know that VAL_SEQ is large
  enough to hold the packed data, and that there are enough value items.
  (However, their types may not have been thoroughly checked yet.)

  In addition, val_seq is a Python Fast sequence.

  Returns NULL for error (with exception set), or None.
*/
PyObject *
pytdbpack_pack_data(const char *format_str,
		    PyObject *val_seq,
		    unsigned char *packed_buf)
{
	int i;

	for (i = 0; format_str[i]; i++) {
		char ch = format_str[i];
		PyObject *val_obj;

		/* borrow a reference to the item */
		val_obj = PySequence_Fast_GET_ITEM(val_seq, i);
		if (!val_obj)
			return NULL;

		if (!pytdbpack_pack_item(ch, val_obj, &packed_buf))
			return NULL;
	}

	return Py_None;
}





static PyMethodDef pytdbpack_methods[] = {
	{ "pack", pytdbpack_pack, METH_VARARGS, (char *) pytdbpack_pack_doc },
	{ "unpack", pytdbpack_unpack, METH_VARARGS, (char *) pytdbpack_unpack_doc },
};

DL_EXPORT(void)
inittdbpack(void)
{
	Py_InitModule3("tdbpack", pytdbpack_methods,
		       (char *) pytdbpack_docstring);
}