summaryrefslogtreecommitdiffstats
path: root/pym/xpak.py
blob: ef6d2905a8341696041ed01cbda380cf23831bad (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
# Copyright 2001-2004 Gentoo Foundation
# Distributed under the terms of the GNU General Public License v2
# $Id: /var/cvsroot/gentoo-src/portage/pym/xpak.py,v 1.13.2.3 2005/02/26 11:22:38 carpaski Exp $


# The format for a tbz2/xpak:
#
#  tbz2: tar.bz2 + xpak + (xpak_offset) + "STOP"
#  xpak: "XPAKPACK" + (index_len) + (data_len) + index + data + "XPAKSTOP"
# index: (pathname_len) + pathname + (data_offset) + (data_len)
#        index entries are concatenated end-to-end.
#  data: concatenated data chunks, end-to-end.
#
# [tarball]XPAKPACKIIIIDDDD[index][data]XPAKSTOPOOOOSTOP
#
# (integer) == encodeint(integer)  ===> 4 characters (big-endian copy)
# '+' means concatenate the fields ===> All chunks are strings

import sys,os,string
from stat import *

def addtolist(mylist,curdir):
	"""(list, dir) --- Takes an array(list) and appends all files from dir down
	the directory tree. Returns nothing. list is modified."""
	for x in os.listdir("."):
		if os.path.isdir(x):
			os.chdir(x)
			addtolist(mylist,curdir+x+"/")
			os.chdir("..")
		else:
			if curdir+x not in mylist:
				mylist.append(curdir+x)

def encodeint(myint):
	"""Takes a 4 byte integer and converts it into a string of 4 characters.
	Returns the characters in a string."""
	part1=chr((myint >> 24 ) & 0x000000ff)
	part2=chr((myint >> 16 ) & 0x000000ff)
	part3=chr((myint >> 8 ) & 0x000000ff)
	part4=chr(myint & 0x000000ff)
	return part1+part2+part3+part4

def decodeint(mystring):
	"""Takes a 4 byte string and converts it into a 4 byte integer.
	Returns an integer."""
	myint=0
	myint=myint+ord(mystring[3])
	myint=myint+(ord(mystring[2]) << 8)
	myint=myint+(ord(mystring[1]) << 16)
	myint=myint+(ord(mystring[0]) << 24)
	return myint

def xpak(rootdir,outfile=None):
	"""(rootdir,outfile) -- creates an xpak segment of the directory 'rootdir'
	and under the name 'outfile' if it is specified. Otherwise it returns the
	xpak segment."""
	try:
		origdir=os.getcwd()
	except SystemExit, e:
		raise
	except:
		os.chdir("/")
		origdir="/"
	os.chdir(rootdir)
	mylist=[]

	addtolist(mylist,"")
	mylist.sort()

	#Our list index has been created
	
	indexglob=""
	indexpos=0
	dataglob=""
	datapos=0
	for x in mylist:
		a=open(x,"r")
		newglob=a.read()
		a.close()
		mydatasize=len(newglob)
		indexglob=indexglob+encodeint(len(x))+x+encodeint(datapos)+encodeint(mydatasize)
		indexpos=indexpos+4+len(x)+4+4
		dataglob=dataglob+newglob
		datapos=datapos+mydatasize
	os.chdir(origdir)
	if outfile:
		outf=open(outfile,"w")
		outf.write("XPAKPACK"+encodeint(len(indexglob))+encodeint(len(dataglob)))
		outf.write(indexglob)
		outf.write(dataglob)
		outf.write("XPAKSTOP")
		outf.close()
	else:
		myret="XPAKPACK"+encodeint(len(indexglob))+encodeint(len(dataglob))
		myret=myret+indexglob+dataglob+"XPAKSTOP"
		return myret

def xsplit(infile):
	"""(infile) -- Splits the infile into two files.
	'infile.index' contains the index segment.
	'infile.dat' contails the data segment."""
	myfile=open(infile,"r")
	mydat=myfile.read()
	myfile.close()
	
	splits = xsplit_mem(mydat)
	if not splits:
		return
	
	myfile=open(infile+".index","w")
	myfile.write(splits[0])
	myfile.close()
	myfile=open(infile+".dat","w")
	myfile.write(splits[1])
	myfile.close()
	return

def xsplit_mem(mydat):
	if mydat[0:8]!="XPAKPACK":
		return None
	if mydat[-8:]!="XPAKSTOP":
		return None
	indexsize=decodeint(mydat[8:12])
	datasize=decodeint(mydat[12:16])
	return (mydat[16:indexsize+16], mydat[indexsize+16:-8])

def getindex(infile):
	"""(infile) -- grabs the index segment from the infile and returns it."""
	myfile=open(infile,"r")
	myheader=myfile.read(16)
	if myheader[0:8]!="XPAKPACK":
		myfile.close()
		return
	indexsize=decodeint(myheader[8:12])
	myindex=myfile.read(indexsize)
	myfile.close()
	return myindex

def getboth(infile):
	"""(infile) -- grabs the index and data segments from the infile.
	Returns an array [indexSegment,dataSegment]"""
	myfile=open(infile,"r")
	myheader=myfile.read(16)
	if myheader[0:8]!="XPAKPACK":
		myfile.close()
		return
	indexsize=decodeint(myheader[8:12])
	datasize=decodeint(myheader[12:16])
	myindex=myfile.read(indexsize)
	mydata=myfile.read(datasize)
	myfile.close()
	return [myindex,mydata]

def listindex(myindex):
	"""Print to the terminal the filenames listed in the indexglob passed in."""
	for x in getindex_mem(myindex):
		print x

def getindex_mem(myindex):
	"""Returns the filenames listed in the indexglob passed in."""
	myindexlen=len(myindex)
	startpos=0
	myret=[]
	while ((startpos+8)<myindexlen):
		mytestlen=decodeint(myindex[startpos:startpos+4])
		myret=myret+[myindex[startpos+4:startpos+4+mytestlen]]
		startpos=startpos+mytestlen+12
	return myret

def searchindex(myindex,myitem):
	"""(index,item) -- Finds the offset and length of the file 'item' in the
	datasegment via the index 'index' provided."""
	mylen=len(myitem)
	myindexlen=len(myindex)
	startpos=0
	while ((startpos+8)<myindexlen):
		mytestlen=decodeint(myindex[startpos:startpos+4])
		if mytestlen==mylen:
			if myitem==myindex[startpos+4:startpos+4+mytestlen]:
				#found
				datapos=decodeint(myindex[startpos+4+mytestlen:startpos+8+mytestlen]);
				datalen=decodeint(myindex[startpos+8+mytestlen:startpos+12+mytestlen]);
				return [datapos,datalen]
		startpos=startpos+mytestlen+12
		
def getitem(myid,myitem):
	myindex=myid[0]
	mydata=myid[1]
	myloc=searchindex(myindex,myitem)
	if not myloc:
		return None
	return mydata[myloc[0]:myloc[0]+myloc[1]]

def xpand(myid,mydest):
	myindex=myid[0]
	mydata=myid[1]
	try:
		origdir=os.getcwd()
	except SystemExit, e:
		raise
	except:
		os.chdir("/")
		origdir="/"
	os.chdir(mydest)
	myindexlen=len(myindex)
	startpos=0
	while ((startpos+8)<myindexlen):
		namelen=decodeint(myindex[startpos:startpos+4])
		datapos=decodeint(myindex[startpos+4+namelen:startpos+8+namelen]);
		datalen=decodeint(myindex[startpos+8+namelen:startpos+12+namelen]);
		myname=myindex[startpos+4:startpos+4+namelen]
		dirname=os.path.dirname(myname)
		if dirname:
			if not os.path.exists(dirname):
				os.makedirs(dirname)
		mydat=open(myname,"w")
		mydat.write(mydata[datapos:datapos+datalen])
		mydat.close()
		startpos=startpos+namelen+12
	os.chdir(origdir)

class tbz2:
	def __init__(self,myfile):
		self.file=myfile
		self.filestat=None
		self.index=""
		self.infosize=0
		self.xpaksize=0
		self.indexsize=None
		self.datasize=None
		self.indexpos=None
		self.datapos=None
		self.scan()

	def decompose(self,datadir,cleanup=1):
		"""Alias for unpackinfo() --- Complement to recompose() but optionally
		deletes the destination directory. Extracts the xpak from the tbz2 into
		the directory provided. Raises IOError if scan() fails.
		Returns result of upackinfo()."""
		if not self.scan():
			raise IOError
		if cleanup and os.path.exists(datadir):
			# XXX: Potentially bad
			os.system("rm -Rf "+datadir+"/*")
		if not os.path.exists(datadir):
			os.makedirs(datadir)
		return self.unpackinfo(datadir)
	def compose(self,datadir,cleanup=0):
		"""Alias for recompose()."""
		return recompose(datadir,cleanup)
	def recompose(self,datadir,cleanup=0):
		"""Creates an xpak segment from the datadir provided, truncates the tbz2
		to the end of regular data if an xpak segment already exists, and adds
		the new segment to the file with terminating info."""
		self.scan() # Don't care about condition... We'll rewrite the data anyway.
		myfile=open(self.file,"a+")
		if not myfile:
			raise IOError
		myfile.seek(-self.xpaksize,2) # 0,2 or -0,2 just mean EOF.
		myfile.truncate()
		xpdata=xpak(datadir)
		myfile.write(xpdata+encodeint(len(xpdata))+"STOP")
		myfile.flush()
		myfile.close()
		if cleanup:
			# XXX: Potentially bad
			os.system("rm -Rf "+datadir)
		return 1

	def scan(self):
		"""Scans the tbz2 to locate the xpak segment and setup internal values.
		This function is called by relevant functions already."""
		try:
			mystat=os.stat(self.file)
			if self.filestat:
				changed=0
				for x in [ST_SIZE, ST_MTIME, ST_CTIME]:
					if mystat[x] != self.filestat[x]:
						changed=1
				if not changed:
					return 1
			self.filestat=mystat
			a=open(self.file,"r")
			a.seek(-16,2)
			trailer=a.read()
			self.infosize=0
			self.xpaksize=0
			if trailer[-4:]!="STOP":
				a.close()
				return 0
			if trailer[0:8]!="XPAKSTOP":
				a.close()
				return 0
			self.infosize=decodeint(trailer[8:12])
			self.xpaksize=self.infosize+8
			a.seek(-(self.xpaksize),2)
			header=a.read(16)
			if header[0:8]!="XPAKPACK":
				a.close()
				return 0
			self.indexsize=decodeint(header[8:12])
			self.datasize=decodeint(header[12:16])
			self.indexpos=a.tell()
			self.index=a.read(self.indexsize)
			self.datapos=a.tell()
			a.close()
			return 2
		except SystemExit, e:
			raise
		except:
			return 0

	def filelist(self):
		"""Return an array of each file listed in the index."""
		if not self.scan():
			return None
		return getindex_mem(self.index)

	def getfile(self,myfile,mydefault=None):
		"""Finds 'myfile' in the data segment and returns it."""
		if not self.scan():
			return None
		myresult=searchindex(self.index,myfile)
		if not myresult:
			return mydefault
		a=open(self.file,"r")
		a.seek(self.datapos+myresult[0],0)
		myreturn=a.read(myresult[1])
		a.close()
		return myreturn

	def getelements(self,myfile):
		"""A split/array representation of tbz2.getfile()"""
		mydat=self.getfile(myfile)
		if not mydat:
			return []
		return string.split(mydat)

	def unpackinfo(self,mydest):
		"""Unpacks all the files from the dataSegment into 'mydest'."""
		if not self.scan():
			return 0
		try:
			origdir=os.getcwd()
		except SystemExit, e:
			raise
		except:
			os.chdir("/")
			origdir="/"
		a=open(self.file,"r")
		if not os.path.exists(mydest):
			os.makedirs(mydest)
		os.chdir(mydest)
		startpos=0
		while ((startpos+8)<self.indexsize):
			namelen=decodeint(self.index[startpos:startpos+4])
			datapos=decodeint(self.index[startpos+4+namelen:startpos+8+namelen]);
			datalen=decodeint(self.index[startpos+8+namelen:startpos+12+namelen]);
			myname=self.index[startpos+4:startpos+4+namelen]
			dirname=os.path.dirname(myname)
			if dirname:
				if not os.path.exists(dirname):
					os.makedirs(dirname)
			mydat=open(myname,"w")
			a.seek(self.datapos+datapos)
			mydat.write(a.read(datalen))
			mydat.close()
			startpos=startpos+namelen+12
		a.close()
		os.chdir(origdir)
		return 1

	def getboth(self):
		"""Returns an array [indexSegment,dataSegment]"""
		if not self.scan():
			return None

		a = open(self.file,"r")
		a.seek(self.datapos)
		mydata =a.read(self.datasize)
		a.close()

		return [self.index[:],mydata]