summaryrefslogtreecommitdiffstats
path: root/presto-utils/dumpMetadata.py
blob: 61b30d6debfb745538fc818fe6f90f48012a92f0 (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
# base classes and functions for dumping out package Metadata
#
# 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 Library 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.
# Copyright 2004 Duke University

# $Id: dumpMetadata.py,v 1.36 2006/02/21 20:10:08 pnasrat Exp $

import os
import rpm
import exceptions
import md5
import sha
import types
import struct
import re
import stat

# done to fix gzip randomly changing the checksum
import gzip
from zlib import error as zlibError
from gzip import write32u, FNAME

__all__ = ["GzipFile","open"]

class GzipFile(gzip.GzipFile):
    def _write_gzip_header(self):
        self.fileobj.write('\037\213')             # magic header
        self.fileobj.write('\010')                 # compression method
        fname = self.filename[:-3]
        flags = 0
        if fname:
            flags = FNAME
        self.fileobj.write(chr(flags))
        write32u(self.fileobj, long(0))
        self.fileobj.write('\002')
        self.fileobj.write('\377')
        if fname:
            self.fileobj.write(fname + '\000')


def _gzipOpen(filename, mode="rb", compresslevel=9):
    return GzipFile(filename, mode, compresslevel)
    


def returnFD(filename):
    try:
        fdno = os.open(filename, os.O_RDONLY)
    except OSError:
        raise MDError, "Error opening file"
    return fdno
    
def returnHdr(ts, package):
    """hand back the rpm header or raise an Error if the pkg is fubar"""
    opened_here = 0
    try:
        if type(package) is types.StringType:
            opened_here = 1
            fdno = os.open(package, os.O_RDONLY)
        else: 
            fdno = package # let's assume this is an fdno and go with it :)
    except OSError:
        raise MDError, "Error opening file"
    ts.setVSFlags((rpm._RPMVSF_NOSIGNATURES|rpm.RPMVSF_NOMD5|rpm.RPMVSF_NEEDPAYLOAD))
    try:
        hdr = ts.hdrFromFdno(fdno)
    except rpm.error:
        raise MDError, "Error opening package"
    if type(hdr) != rpm.hdr:
        raise MDError, "Error opening package"
    ts.setVSFlags(0)
    
    if opened_here:
        os.close(fdno)
        del fdno

    return hdr
    
def getChecksum(sumtype, file, CHUNK=2**16):
    """takes filename, hand back Checksum of it
       sumtype = md5 or sha
       filename = /path/to/file
       CHUNK=65536 by default"""
       
    # chunking brazenly lifted from Ryan Tomayko
    opened_here = 0
    try:
        if type(file) is not types.StringType:
            fo = file # assume it's a file-like-object
        else:
            opened_here = 1
            fo = open(file, 'rb', CHUNK)
            
        if sumtype == 'md5':
            sum = md5.new()
        elif sumtype == 'sha':
            sum = sha.new()
        else:
            raise MDError, 'Error Checksumming file, wrong checksum type %s' % sumtype
        chunk = fo.read
        while chunk: 
            chunk = fo.read(CHUNK)
            sum.update(chunk)

        if opened_here:
            fo.close()
            del fo
            
        return sum.hexdigest()
    except:
        raise MDError, 'Error opening file for checksum: %s' % file


def utf8String(string):
    """hands back a unicoded string"""
    if string is None:
        return ''
    elif isinstance(string, unicode):    
        return string
    try:
        x = unicode(string, 'ascii')
        return string
    except UnicodeError:
        encodings = ['utf-8', 'iso-8859-1', 'iso-8859-15', 'iso-8859-2']
        for enc in encodings:
            try:
                x = unicode(string, enc)
            except UnicodeError:
                pass
            else:
                if x.encode(enc) == string:
                    return x.encode('utf-8')
    newstring = ''
    for char in string:
        if ord(char) > 127:
            newstring = newstring + '?'
        else:
            newstring = newstring + char
    return newstring

        
def byteranges(file):
    """takes an rpm file or fileobject and returns byteranges for location of the header"""
    opened_here = 0
    if type(file) is not types.StringType:
        fo = file
    else:
        opened_here = 1
        fo = open(file, 'r')
    #read in past lead and first 8 bytes of sig header
    fo.seek(104)
    # 104 bytes in
    binindex = fo.read(4)
    # 108 bytes in
    (sigindex, ) = struct.unpack('>I', binindex)
    bindata = fo.read(4)
    # 112 bytes in
    (sigdata, ) = struct.unpack('>I', bindata)
    # each index is 4 32bit segments - so each is 16 bytes
    sigindexsize = sigindex * 16
    sigsize = sigdata + sigindexsize
    # we have to round off to the next 8 byte boundary
    disttoboundary = (sigsize % 8)
    if disttoboundary != 0:
        disttoboundary = 8 - disttoboundary
    # 112 bytes - 96 == lead, 8 = magic and reserved, 8 == sig header data
    hdrstart = 112 + sigsize  + disttoboundary
    
    fo.seek(hdrstart) # go to the start of the header
    fo.seek(8,1) # read past the magic number and reserved bytes

    binindex = fo.read(4) 
    (hdrindex, ) = struct.unpack('>I', binindex)
    bindata = fo.read(4)
    (hdrdata, ) = struct.unpack('>I', bindata)
    
    # each index is 4 32bit segments - so each is 16 bytes
    hdrindexsize = hdrindex * 16 
    # add 16 to the hdrsize to account for the 16 bytes of misc data b/t the
    # end of the sig and the header.
    hdrsize = hdrdata + hdrindexsize + 16
    
    # header end is hdrstart + hdrsize 
    hdrend = hdrstart + hdrsize 
    if opened_here:
        fo.close()
        del fo
    return (hdrstart, hdrend)
    

class MDError(exceptions.Exception):
    def __init__(self, args=None):
        exceptions.Exception.__init__(self)
        self.args = args



class RpmMetaData:
    """each drpm is one object, you pass it an rpm file
       it opens the file, and pulls the information out in bite-sized chunks :)
    """

    mode_cache = {}

    def __init__(self, ts, basedir, filename, options, is_drpm):
        try:
            stats = os.stat(os.path.join(basedir, filename))
            self.size = stats[6]
            self.mtime = stats[8]
            del stats
        except OSError, e:
            raise MDError, "Error Stat'ing file %s %s" % (basedir, filename)
        self.options = options
        self.localurl = options['baseurl']
        self.relativepath = filename
        fd = returnFD(os.path.join(basedir, filename))
        self.hdr = returnHdr(ts, fd)
        os.lseek(fd, 0, 0)
        fo = os.fdopen(fd, 'rb')
        self.pkgid = self.doChecksumCache(fo)
        fo.seek(0)
        (self.rangestart, self.rangeend) = byteranges(fo)
        self.is_drpm = False
        if is_drpm:
            fo.seek(self.rangeend)
            self._getOldInfo(fo)
            self.is_drpm = True
        del fo
        del fd
                    
    def arch(self):
        if self.tagByName('sourcepackage') == 1:
            return 'src'
        else:
            return self.tagByName('arch')

    def _stringToNEVR(self, string):
        i = string.rfind("-", 0, string.rfind("-")-1)
        name = string[:i]
        (epoch, ver, rel) = self._stringToVersion(string[i+1:])
        return (name, epoch, ver, rel)
        
    def _getLength(self, in_data):
        length = 0
        for val in in_data:
            length = length * 256
            length += ord(val)
        return length
        
    def _getOldInfo(self, fo):
        try:
            compobj = gzip.GzipFile("", "rb", 9, fo)
        except:
            raise zlibError("Data not stored in gzip format")
            
        if compobj.read(4)[:3] != "DLT":
            raise Exception("Not a deltarpm")
        
        nevr_length = self._getLength(compobj.read(4))
        nevr = compobj.read(nevr_length).strip("\x00")
        seq_length = self._getLength(compobj.read(4))
        seq = compobj.read(seq_length)
        hex_seq = ""
        for char in seq:
            hex_seq += str("%02x" % ord(char))
        self.oldnevrstring = nevr
        self.oldnevr = self._stringToNEVR(nevr)
        self.sequence = hex_seq
        compobj.close()
            
    def _stringToVersion(self, strng):
        i = strng.find(':')
        if i != -1:
            epoch = strng[:i]
        else:
            epoch = '0'
        j = strng.find('-')
        if j != -1:
            if strng[i + 1:j] == '':
                version = None
            else:
                version = strng[i + 1:j]
            release = strng[j + 1:]
        else:
            if strng[i + 1:] == '':
                version = None
            else:
                version = strng[i + 1:]
            release = None
        return (epoch, version, release)

    ###########
    # Title: Remove duplicates from a sequence
    # Submitter: Tim Peters 
    # From: http://aspn.activestate.com/ASPN/Cookbook/Python/Recipe/52560                      
        
    def _uniq(self,s):
        """Return a list of the elements in s, but without duplicates.
    
        For example, unique([1,2,3,1,2,3]) is some permutation of [1,2,3],
        unique("abcabc") some permutation of ["a", "b", "c"], and
        unique(([1, 2], [2, 3], [1, 2])) some permutation of
        [[2, 3], [1, 2]].
    
        For best speed, all sequence elements should be hashable.  Then
        unique() will usually work in linear time.
    
        If not possible, the sequence elements should enjoy a total
        ordering, and if list(s).sort() doesn't raise TypeError it's
        assumed that they do enjoy a total ordering.  Then unique() will
        usually work in O(N*log2(N)) time.
    
        If that's not possible either, the sequence elements must support
        equality-testing.  Then unique() will usually work in quadratic
        time.
        """
    
        n = len(s)
        if n == 0:
            return []
    
        # Try using a dict first, as that's the fastest and will usually
        # work.  If it doesn't work, it will usually fail quickly, so it
        # usually doesn't cost much to *try* it.  It requires that all the
        # sequence elements be hashable, and support equality comparison.
        u = {}
        try:
            for x in s:
                u[x] = 1
        except TypeError:
            del u  # move on to the next method
        else:
            return u.keys()
    
        # We can't hash all the elements.  Second fastest is to sort,
        # which brings the equal elements together; then duplicates are
        # easy to weed out in a single pass.
        # NOTE:  Python's list.sort() was designed to be efficient in the
        # presence of many duplicate elements.  This isn't true of all
        # sort functions in all languages or libraries, so this approach
        # is more effective in Python than it may be elsewhere.
        try:
            t = list(s)
            t.sort()
        except TypeError:
            del t  # move on to the next method
        else:
            assert n > 0
            last = t[0]
            lasti = i = 1
            while i < n:
                if t[i] != last:
                    t[lasti] = last = t[i]
                    lasti += 1
                i += 1
            return t[:lasti]
    
        # Brute force is all that's left.
        u = []
        for x in s:
            if x not in u:
                u.append(x)
        return u

    def tagByName(self, tag):
        data = self.hdr[tag]
        if type(data) is types.ListType:
            if len(data) > 0:
                return data[0]
            else:
                return ''
        else:
            return data
    
    def listTagByName(self, tag):
        """take a tag that should be a list and make sure it is one"""
        lst = []
        data = self.hdr[tag]
        if data is None:
            return lst
            
        if type(data) is types.ListType:
            lst.extend(data)
        else:
            lst.append(data)
        return lst

    def epoch(self):
        if self.hdr['epoch'] is None:
            return 0
        else:
            return self.tagByName('epoch')
                    
    def doChecksumCache(self, fo):
        """return a checksum for a package:
           - check if the checksum cache is enabled
              if not - return the checksum
              if so - check to see if it has a cache file
                if so, open it and return the first line's contents
                if not, grab the checksum and write it to a file for this pkg
            """
        if not self.options['cache']:
            return getChecksum(self.options['sumtype'], fo)
        
        csumtag = os.path.basename(self.relativepath) + ".cache"
        csumfile = '%s/%s' % (self.options['cachedir'], csumtag)
        if os.path.exists(csumfile) and self.mtime <= os.stat(csumfile)[8]:
            csumo = open(csumfile, 'r')
            checksum = csumo.readline()
            csumo.close()
            
        else:
            checksum = getChecksum(self.options['sumtype'], fo)
            csumo = open(csumfile, 'w')
            csumo.write(checksum)
            csumo.close()
            
        return checksum


    
def generateXML(doc, node, formatns, drpmObj, sumtype, pkgDeltas):
    """takes an xml doc object and a package metadata entry node, populates a 
       package node with the md information"""
    name = drpmObj.tagByName('name')
    arch = drpmObj.arch()
    epoch = str(drpmObj.epoch())
    ver = str(drpmObj.tagByName('version'))
    rel = str(drpmObj.tagByName('release'))
    if not pkgDeltas.has_key('%s-%s:%s-%s.%s' % (name, epoch, ver, rel, arch)):
        pkgNode = node.newChild(None, "package", None)
        pkgNode.newProp('type', 'rpm')
        pkgNode.newChild(None, 'name', name)
        pkgNode.newChild(None, 'arch', arch)
        version = pkgNode.newChild(None, 'version', None)
        version.newProp('epoch', epoch)
        version.newProp('ver', ver)
        version.newProp('rel', rel)
        deltas = pkgNode.newChild(None, 'deltas', None)
        pkgDeltas['%s-%s:%s-%s.%s' % (name, epoch, ver, rel, arch)] = deltas
    else:
        deltas = pkgDeltas['%s-%s:%s-%s.%s' % (name, epoch, ver, rel, arch)]
    (oldname, oldepoch, oldver, oldrel) = drpmObj.oldnevr
    drpmNode = deltas.newChild(None, "oldrpm", None)
    if name != oldname:
        drpmNode.newChild(None, 'name', oldname)
    # oldrpm arch is not stored in drpm, so we can only work within same arch
    version = drpmNode.newChild(None, 'version', None)
    if epoch != oldepoch:
        version.newProp('epoch', oldepoch)
    if ver != oldver:
        version.newProp('ver', oldver)
    version.newProp('rel', oldrel)
    drpmNode.newChild(None, 'drpm_filename', drpmObj.relativepath)
    drpmNode.newChild(None, 'size', str(drpmObj.size))
    drpmNode.newChild(None, 'sequence', '%s-%s' % (drpmObj.oldnevrstring, drpmObj.sequence))
    checksum = drpmNode.newChild(None, 'checksum', drpmObj.pkgid)
    checksum.newProp('type', drpmObj.options['sumtype'])
    
        
def repoXML(node, cmds):
    """generate the repomd.xml file that stores the info on the other files"""
    sumtype = cmds['sumtype']
    workfiles = [(cmds['prestofile'], 'deltas')]
    
    
    for (file, ftype) in workfiles:
        zfo = _gzipOpen(os.path.join(cmds['outputdir'], cmds['tempdir'], file))
        uncsum = getChecksum(sumtype, zfo)
        zfo.close()
        csum = getChecksum(sumtype, os.path.join(cmds['outputdir'], cmds['tempdir'], file))
        timestamp = os.stat(os.path.join(cmds['outputdir'], cmds['tempdir'], file))[8]
        data = node.newChild(None, 'data', None)
        data.newProp('type', ftype)
        location = data.newChild(None, 'location', None)
        if cmds['baseurl'] is not None:
            location.newProp('xml:base', cmds['baseurl'])
        location.newProp('href', os.path.join(cmds['finaldir'], file))
        checksum = data.newChild(None, 'checksum', csum)
        checksum.newProp('type', sumtype)
        timestamp = data.newChild(None, 'timestamp', str(timestamp))
        unchecksum = data.newChild(None, 'open-checksum', uncsum)
        unchecksum.newProp('type', sumtype)