summaryrefslogtreecommitdiffstats
path: root/pym/getbinpkg.py
blob: d20a549ed7dd7be77cc445c8d2dd0897cf54cf3d (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
# getbinpkg.py -- Portage binary-package helper functions
# Copyright 2003-2004 Gentoo Foundation
# Distributed under the terms of the GNU General Public License v2
# $Id$

if not hasattr(__builtins__, "set"):
	from sets import Set as set

from output import red, yellow, green
import htmllib,HTMLParser,formatter,sys,os,xpak,time,tempfile,base64,urllib2

try:
	import cPickle
except ImportError:
	import pickle as cPickle

try:
	import ftplib
except SystemExit, e:
	raise
except Exception, e:
	sys.stderr.write(red("!!! CANNOT IMPORT FTPLIB: ")+str(e)+"\n")

try:
	import httplib
except SystemExit, e:
	raise
except Exception, e:
	sys.stderr.write(red("!!! CANNOT IMPORT HTTPLIB: ")+str(e)+"\n")

def make_metadata_dict(data):
	myid,myglob = data
	
	mydict = {}
	for x in xpak.getindex_mem(myid):
		mydict[x] = xpak.getitem(data,x)

	return mydict

class ParseLinks(HTMLParser.HTMLParser):
	"""Parser class that overrides HTMLParser to grab all anchors from an html
	page and provide suffix and prefix limitors"""
	def __init__(self):
		self.PL_anchors = []
		HTMLParser.HTMLParser.__init__(self)

	def get_anchors(self):
		return self.PL_anchors
		
	def get_anchors_by_prefix(self,prefix):
		newlist = []
		for x in self.PL_anchors:
			if x.startswith(prefix):
				if x not in newlist:
					newlist.append(x[:])
		return newlist
		
	def get_anchors_by_suffix(self,suffix):
		newlist = []
		for x in self.PL_anchors:
			if x.endswith(suffix):
				if x not in newlist:
					newlist.append(x[:])
		return newlist
		
	def	handle_endtag(self,tag):
		pass

	def	handle_starttag(self,tag,attrs):
		if tag == "a":
			for x in attrs:
				if x[0] == 'href':
					if x[1] not in self.PL_anchors:
						self.PL_anchors.append(urllib2.unquote(x[1]))


def create_conn(baseurl,conn=None):
	"""(baseurl,conn) --- Takes a protocol://site:port/address url, and an
	optional connection. If connection is already active, it is passed on.
	baseurl is reduced to address and is returned in tuple (conn,address)"""

	parts = baseurl.split("://",1)
	if len(parts) != 2:
		raise ValueError, "Provided URL does not contain protocol identifier. '%s'" % baseurl
	protocol,url_parts = parts
	del parts

	url_parts = url_parts.split("/")
	host = url_parts[0]
	if len(url_parts) < 2:
		address = "/"
	else:
		address = "/"+"/".join(url_parts[1:])
	del url_parts

	userpass_host = host.split("@",1)
	if len(userpass_host) == 1:
		host = userpass_host[0]
		userpass = ["anonymous"]
	else:
		host = userpass_host[1]
		userpass = userpass_host[0].split(":")
	del userpass_host

	if len(userpass) > 2:
		raise ValueError, "Unable to interpret username/password provided."
	elif len(userpass) == 2:
		username = userpass[0]
		password = userpass[1]
	elif len(userpass) == 1:
		username = userpass[0]
		password = None
	del userpass

	http_headers = {}
	http_params = {}
	if username and password:
		http_headers = {
			"Authorization": "Basic %s" %
			  base64.encodestring("%s:%s" % (username, password)).replace(
			    "\012",
			    ""
			  ),
		}

	if not conn:
		if protocol == "https":
			conn = httplib.HTTPSConnection(host)
		elif protocol == "http":
			conn = httplib.HTTPConnection(host)
		elif protocol == "ftp":
			passive = 1
			if(host[-1] == "*"):
				passive = 0
				host = host[:-1]
			conn = ftplib.FTP(host)
			if password:
				conn.login(username,password)
			else:
				sys.stderr.write(yellow(" * No password provided for username")+" '"+str(username)+"'\n\n")
				conn.login(username)
			conn.set_pasv(passive)
			conn.set_debuglevel(0)
		elif protocol == "sftp":
			try:
				import paramiko
			except ImportError:
				raise NotImplementedError(
					"paramiko must be installed for sftp support")
			t = paramiko.Transport(host)
			t.connect(username=username, password=password)
			conn = paramiko.SFTPClient.from_transport(t)
		else:
			raise NotImplementedError, "%s is not a supported protocol." % protocol

	return (conn,protocol,address, http_params, http_headers)

def make_ftp_request(conn, address, rest=None, dest=None):
	"""(conn,address,rest) --- uses the conn object to request the data
	from address and issuing a rest if it is passed."""
	try:
	
		if dest:
			fstart_pos = dest.tell()
	
		conn.voidcmd("TYPE I")
		fsize = conn.size(address)

		if (rest != None) and (rest < 0):
			rest = fsize+int(rest)
		if rest < 0:
			rest = 0

		if rest != None:
			mysocket = conn.transfercmd("RETR "+str(address), rest)
		else:
			mysocket = conn.transfercmd("RETR "+str(address))

		mydata = ""
		while 1:
			somedata = mysocket.recv(8192)
			if somedata:
				if dest:
					dest.write(somedata)
				else:
					mydata = mydata + somedata
			else:
				break

		if dest:
			data_size = fstart_pos - dest.tell()
		else:
			data_size = len(mydata)

		mysocket.close()
		conn.voidresp()
		conn.voidcmd("TYPE A")

		return mydata,not (fsize==data_size),""

	except ValueError, e:
		return None,int(str(e)[:4]),str(e)
	

def make_http_request(conn, address, params={}, headers={}, dest=None):
	"""(conn,address,params,headers) --- uses the conn object to request
	the data from address, performing Location forwarding and using the
	optional params and headers."""

	rc = 0
	response = None
	while (rc == 0) or (rc == 301) or (rc == 302):
		try:
			if (rc != 0):
				conn,ignore,ignore,ignore,ignore = create_conn(address)
			conn.request("GET", address, params, headers)
		except SystemExit, e:
			raise
		except Exception, e:
			return None,None,"Server request failed: "+str(e)
		response = conn.getresponse()
		rc = response.status

		# 301 means that the page address is wrong.
		if ((rc == 301) or (rc == 302)):
			ignored_data = response.read()
			del ignored_data
			for x in str(response.msg).split("\n"):
				parts = x.split(": ",1)
				if parts[0] == "Location":
					if (rc == 301):
						sys.stderr.write(red("Location has moved: ")+str(parts[1])+"\n")
					if (rc == 302):
						sys.stderr.write(red("Location has temporarily moved: ")+str(parts[1])+"\n")
					address = parts[1]
					break
	
	if (rc != 200) and (rc != 206):
		return None,rc,"Server did not respond successfully ("+str(response.status)+": "+str(response.reason)+")"

	if dest:
		dest.write(response.read())
		return "",0,""

	return response.read(),0,""


def match_in_array(array, prefix="", suffix="", match_both=1, allow_overlap=0):
	myarray = []
	
	if not (prefix and suffix):
		match_both = 0
		
	for x in array:
		add_p = 0
		if prefix and (len(x) >= len(prefix)) and (x[:len(prefix)] == prefix):
			add_p = 1

		if match_both:
			if prefix and not add_p: # Require both, but don't have first one.
				continue
		else:
			if add_p:     # Only need one, and we have it.
				myarray.append(x[:])
				continue

		if not allow_overlap: # Not allow to overlap prefix and suffix
			if len(x) >= (len(prefix)+len(suffix)):
				y = x[len(prefix):]
			else:
				continue          # Too short to match.
		else:
			y = x               # Do whatever... We're overlapping.
		
		if suffix and (len(x) >= len(suffix)) and (x[-len(suffix):] == suffix):
			myarray.append(x)   # It matches
		else:
			continue            # Doesn't match.

	return myarray
			


def dir_get_list(baseurl,conn=None):
	"""(baseurl[,connection]) -- Takes a base url to connect to and read from.
	URL should be in the for <proto>://<site>[:port]<path>
	Connection is used for persistent connection instances."""

	if not conn:
		keepconnection = 0
	else:
		keepconnection = 1

	conn,protocol,address,params,headers = create_conn(baseurl, conn)

	listing = None
	if protocol in ["http","https"]:
		if not address.endswith("/"):
			# http servers can return a 400 error here
			# if the address doesn't end with a slash.
			address += "/"
		page,rc,msg = make_http_request(conn,address,params,headers)
		
		if page:
			parser = ParseLinks()
			parser.feed(page)
			del page
			listing = parser.get_anchors()
		else:
			import portage_exception
			raise portage_exception.PortageException(
				"Unable to get listing: %s %s" % (rc,msg))
	elif protocol in ["ftp"]:
		if address[-1] == '/':
			olddir = conn.pwd()
			conn.cwd(address)
			listing = conn.nlst()
			conn.cwd(olddir)
			del olddir
		else:
			listing = conn.nlst(address)
	elif protocol == "sftp":
		listing = conn.listdir(address)
	else:
		raise TypeError, "Unknown protocol. '%s'" % protocol

	if not keepconnection:
		conn.close()

	return listing

def file_get_metadata(baseurl,conn=None, chunk_size=3000):
	"""(baseurl[,connection]) -- Takes a base url to connect to and read from.
	URL should be in the for <proto>://<site>[:port]<path>
	Connection is used for persistent connection instances."""

	if not conn:
		keepconnection = 0
	else:
		keepconnection = 1

	conn,protocol,address,params,headers = create_conn(baseurl, conn)

	if protocol in ["http","https"]:
		headers["Range"] = "bytes=-"+str(chunk_size)
		data,rc,msg = make_http_request(conn, address, params, headers)
	elif protocol in ["ftp"]:
		data,rc,msg = make_ftp_request(conn, address, -chunk_size)
	elif protocol == "sftp":
		f = conn.open(address)
		try:
			f.seek(-chunk_size, 2)
			data = f.read()
		finally:
			f.close()
	else:
		raise TypeError, "Unknown protocol. '%s'" % protocol
	
	if data:
		xpaksize = xpak.decodeint(data[-8:-4])
		if (xpaksize+8) > chunk_size:
			myid = file_get_metadata(baseurl, conn, (xpaksize+8))
			if not keepconnection:
				conn.close()
			return myid
		else:
			xpak_data = data[len(data)-(xpaksize+8):-8]
		del data

		myid = xpak.xsplit_mem(xpak_data)
		if not myid:
			myid = None,None
		del xpak_data
	else:
		myid = None,None

	if not keepconnection:
		conn.close()

	return myid


def file_get(baseurl,dest,conn=None,fcmd=None):
	"""(baseurl,dest,fcmd=) -- Takes a base url to connect to and read from.
	URL should be in the for <proto>://[user[:pass]@]<site>[:port]<path>"""

	if not fcmd:
		return file_get_lib(baseurl,dest,conn)

	variables = {
		"DISTDIR": dest,
		"URI":     baseurl,
		"FILE":    os.path.basename(baseurl)
	}
	import shlex, StringIO
	from portage_util import varexpand
	from portage_exec import spawn
	lexer = shlex.shlex(StringIO.StringIO(fcmd), posix=True)
	lexer.whitespace_split = True
	myfetch = [varexpand(x, mydict=variables) for x in lexer]
	retval = spawn(myfetch, env=os.environ.copy())
	if retval != os.EX_OK:
		sys.stderr.write("Fetcher exited with a failure condition.\n")
		return 0
	return 1

def file_get_lib(baseurl,dest,conn=None):
	"""(baseurl[,connection]) -- Takes a base url to connect to and read from.
	URL should be in the for <proto>://<site>[:port]<path>
	Connection is used for persistent connection instances."""

	if not conn:
		keepconnection = 0
	else:
		keepconnection = 1

	conn,protocol,address,params,headers = create_conn(baseurl, conn)

	sys.stderr.write("Fetching '"+str(os.path.basename(address)+"'\n"))
	if protocol in ["http","https"]:
		data,rc,msg = make_http_request(conn, address, params, headers, dest=dest)
	elif protocol in ["ftp"]:
		data,rc,msg = make_ftp_request(conn, address, dest=dest)
	elif protocol == "sftp":
		rc = 0
		try:
			f = conn.open(address)
		except SystemExit:
			raise
		except Exception:
			rc = 1
		else:
			try:
				if dest:
					bufsize = 8192
					while True:
						data = f.read(bufsize)
						if not data:
							break
						dest.write(data)
			finally:
				f.close()
	else:
		raise TypeError, "Unknown protocol. '%s'" % protocol
	
	if not keepconnection:
		conn.close()

	return rc


def dir_get_metadata(baseurl, conn=None, chunk_size=3000, verbose=1, usingcache=1, makepickle=None):
	"""(baseurl,conn,chunk_size,verbose) -- 
	"""
	if not conn:
		keepconnection = 0
	else:
		keepconnection = 1

	cache_path = "/var/cache/edb"

	if makepickle is None:
		makepickle = "/var/cache/edb/metadata.idx.most_recent"

	conn,protocol,address,params,headers = create_conn(baseurl, conn)
	out = sys.stdout

	filedict = {}

	try:
		metadatafile = open("/var/cache/edb/remote_metadata.pickle")
		metadata = cPickle.load(metadatafile)
		out.write("Loaded metadata pickle.\n")
		out.flush()
		metadatafile.close()
	except (cPickle.UnpicklingError, OSError, IOError, EOFError):
		metadata = {}
	if not metadata.has_key(baseurl):
		metadata[baseurl]={}
	if not metadata[baseurl].has_key("indexname"):
		metadata[baseurl]["indexname"]=""
	if not metadata[baseurl].has_key("timestamp"):
		metadata[baseurl]["timestamp"]=0
	if not metadata[baseurl].has_key("unmodified"):
		metadata[baseurl]["unmodified"]=0
	if not metadata[baseurl].has_key("data"):
		metadata[baseurl]["data"]={}

	if not os.access(cache_path, os.W_OK):
		sys.stderr.write("!!! Unable to write binary metadata to disk!\n")
		sys.stderr.write("!!! Permission denied: '%s'\n" % cache_path)
		return metadata[baseurl]["data"]

	import portage_exception
	try:
		filelist = dir_get_list(baseurl, conn)
	except portage_exception.PortageException, e:
		sys.stderr.write("!!! Error connecting to '%s'.\n" % baseurl)
		sys.stderr.write("!!! %s\n" % str(e))
		del e
		return metadata[baseurl]["data"]
	tbz2list = match_in_array(filelist, suffix=".tbz2")
	metalist = match_in_array(filelist, prefix="metadata.idx")
	del filelist
	
	# Determine if our metadata file is current.
	metalist.sort()
	metalist.reverse() # makes the order new-to-old.
	havecache=0
	for mfile in metalist:
		if usingcache and \
		   ((metadata[baseurl]["indexname"] != mfile) or \
			  (metadata[baseurl]["timestamp"] < int(time.time()-(60*60*24)))):
			# Try to download new cache until we succeed on one.
			data=""
			for trynum in [1,2,3]:
				mytempfile = tempfile.TemporaryFile()
				try:
					file_get(baseurl+"/"+mfile, mytempfile, conn)
					if mytempfile.tell() > len(data):
						mytempfile.seek(0)
						data = mytempfile.read()
				except ValueError, e:
					sys.stderr.write("--- "+str(e)+"\n")
					if trynum < 3:
						sys.stderr.write("Retrying...\n")
					sys.stderr.flush()
					mytempfile.close()
					continue
				if match_in_array([mfile],suffix=".gz"):
					out.write("gzip'd\n")
					out.flush()
					try:
						import gzip
						mytempfile.seek(0)
						gzindex = gzip.GzipFile(mfile[:-3],'rb',9,mytempfile)
						data = gzindex.read()
					except SystemExit, e:
						raise
					except Exception, e:
						mytempfile.close()
						sys.stderr.write("!!! Failed to use gzip: "+str(e)+"\n")
						sys.stderr.flush()
					mytempfile.close()
				try:
					metadata[baseurl]["data"] = cPickle.loads(data)
					del data
					metadata[baseurl]["indexname"] = mfile
					metadata[baseurl]["timestamp"] = int(time.time())
					metadata[baseurl]["modified"]  = 0 # It's not, right after download.
					out.write("Pickle loaded.\n")
					out.flush()
					break
				except SystemExit, e:
					raise
				except Exception, e:
					sys.stderr.write("!!! Failed to read data from index: "+str(mfile)+"\n")
					sys.stderr.write("!!! "+str(e)+"\n")
					sys.stderr.flush()
			try:
				metadatafile = open("/var/cache/edb/remote_metadata.pickle", "w+")
				cPickle.dump(metadata,metadatafile)
				metadatafile.close()
			except SystemExit, e:
				raise
			except Exception, e:
				sys.stderr.write("!!! Failed to write binary metadata to disk!\n")
				sys.stderr.write("!!! "+str(e)+"\n")
				sys.stderr.flush()
			break
	# We may have metadata... now we run through the tbz2 list and check.

	class CacheStats(object):
		from time import time
		def __init__(self, out):
			self.misses = 0
			self.hits = 0
			self.last_update = 0
			self.out = out
			self.min_display_latency = 0.2
		def update(self):
			cur_time = self.time()
			if cur_time - self.last_update >= self.min_display_latency:
				self.last_update = cur_time
				self.display()
		def display(self):
			self.out.write("\r"+yellow("cache miss: '"+str(self.misses)+"'")+\
				" --- "+green("cache hit: '"+str(self.hits)+"'"))
			self.out.flush()

	cache_stats = CacheStats(out)
	have_tty = out.isatty()
	if have_tty:
		cache_stats.display()
	binpkg_filenames = set()
	for x in tbz2list:
		x = os.path.basename(x)
		binpkg_filenames.add(x)
		if x not in metadata[baseurl]["data"]:
			cache_stats.misses += 1
			if have_tty:
				cache_stats.update()
			metadata[baseurl]["modified"] = 1
			myid = None
			for retry in xrange(3):
				try:
					myid = file_get_metadata(
						"/".join((baseurl.rstrip("/"), x.lstrip("/"))),
						conn, chunk_size)
					break
				except httplib.BadStatusLine:
					# Sometimes this error is thrown from conn.getresponse() in
					# make_http_request().  The docstring for this error in
					# httplib.py says "Presumably, the server closed the
					# connection before sending a valid response".
					conn, protocol, address, params, headers = create_conn(
						baseurl)

			if myid and myid[0]:
				metadata[baseurl]["data"][x] = make_metadata_dict(myid)
			elif verbose:
				sys.stderr.write(red("!!! Failed to retrieve metadata on: ")+str(x)+"\n")
				sys.stderr.flush()
		else:
			cache_stats.hits += 1
			if have_tty:
				cache_stats.update()
	cache_stats.display()
	# Cleanse stale cache for files that don't exist on the server anymore.
	stale_cache = set(metadata[baseurl]["data"]).difference(binpkg_filenames)
	if stale_cache:
		for x in stale_cache:
			del metadata[baseurl]["data"][x]
		metadata[baseurl]["modified"] = 1
	del stale_cache
	del binpkg_filenames
	out.write("\n")
	out.flush()

	try:
		if metadata[baseurl].has_key("modified") and metadata[baseurl]["modified"]:
			metadata[baseurl]["timestamp"] = int(time.time())
			metadatafile = open("/var/cache/edb/remote_metadata.pickle", "w+")
			cPickle.dump(metadata,metadatafile)
			metadatafile.close()
		if makepickle:
			metadatafile = open(makepickle, "w")
			cPickle.dump(metadata[baseurl]["data"],metadatafile)
			metadatafile.close()
	except SystemExit, e:
		raise
	except Exception, e:
		sys.stderr.write("!!! Failed to write binary metadata to disk!\n")
		sys.stderr.write("!!! "+str(e)+"\n")
		sys.stderr.flush()

	if not keepconnection:
		conn.close()
	
	return metadata[baseurl]["data"]