/usr/lib/python2.7/dist-packages/pygopherd/zipfile.py is in pygopherd 2.0.18.3+nmu4ubuntu1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 | "Read and write ZIP files."
# Written by James C. Ahlstrom jim@interet.com
# All rights transferred to CNRI pursuant to the Python contribution agreement
import struct, os, time, types
import binascii
from StringIO import StringIO
from socket import _fileobject as BaseFileSimulator
_STRING_TYPES = (types.StringType,)
if hasattr(types, "UnicodeType"):
_STRING_TYPES = _STRING_TYPES + (types.UnicodeType,)
try:
import zlib # We may need its compression method
except ImportError:
zlib = None
__all__ = ["BadZipfile", "error", "ZIP_STORED", "ZIP_DEFLATED", "is_zipfile",
"ZipInfo", "ZipFile", "PyZipFile"]
class BadZipfile(Exception):
pass
error = BadZipfile # The exception raised by this module
# constants for Zip file compression methods
ZIP_STORED = 0
ZIP_DEFLATED = 8
# Other ZIP compression methods not supported
# Here are some struct module formats for reading headers
structEndArchive = "<4s4H2lH" # 9 items, end of archive, 22 bytes
stringEndArchive = "PK\005\006" # magic number for end of archive record
structCentralDir = "<4s4B4H3l5HLl"# 19 items, central directory, 46 bytes
stringCentralDir = "PK\001\002" # magic number for central directory
structFileHeader = "<4s2B4H3l2H" # 12 items, file header record, 30 bytes
stringFileHeader = "PK\003\004" # magic number for file header
# indexes of entries in the central directory structure
_CD_SIGNATURE = 0
_CD_CREATE_VERSION = 1
_CD_CREATE_SYSTEM = 2
_CD_EXTRACT_VERSION = 3
_CD_EXTRACT_SYSTEM = 4 # is this meaningful?
_CD_FLAG_BITS = 5
_CD_COMPRESS_TYPE = 6
_CD_TIME = 7
_CD_DATE = 8
_CD_CRC = 9
_CD_COMPRESSED_SIZE = 10
_CD_UNCOMPRESSED_SIZE = 11
_CD_FILENAME_LENGTH = 12
_CD_EXTRA_FIELD_LENGTH = 13
_CD_COMMENT_LENGTH = 14
_CD_DISK_NUMBER_START = 15
_CD_INTERNAL_FILE_ATTRIBUTES = 16
_CD_EXTERNAL_FILE_ATTRIBUTES = 17
_CD_LOCAL_HEADER_OFFSET = 18
# indexes of entries in the local file header structure
_FH_SIGNATURE = 0
_FH_EXTRACT_VERSION = 1
_FH_EXTRACT_SYSTEM = 2 # is this meaningful?
_FH_GENERAL_PURPOSE_FLAG_BITS = 3
_FH_COMPRESSION_METHOD = 4
_FH_LAST_MOD_TIME = 5
_FH_LAST_MOD_DATE = 6
_FH_CRC = 7
_FH_COMPRESSED_SIZE = 8
_FH_UNCOMPRESSED_SIZE = 9
_FH_FILENAME_LENGTH = 10
_FH_EXTRA_FIELD_LENGTH = 11
def is_zipfile(filename):
"""Quickly see if file is a ZIP file by checking the magic number."""
try:
fpin = open(filename, "rb")
endrec = _EndRecData(fpin)
fpin.close()
if endrec:
return True # file has correct magic number
except IOError:
pass
return False
def _EndRecData(fpin):
"""Return data from the "End of Central Directory" record, or None.
The data is a list of the nine items in the ZIP "End of central dir"
record followed by a tenth item, the file seek offset of this record."""
fpin.seek(-22, 2) # Assume no archive comment.
filesize = fpin.tell() + 22 # Get file size
data = fpin.read()
if data[0:4] == stringEndArchive and data[-2:] == "\000\000":
endrec = struct.unpack(structEndArchive, data)
endrec = list(endrec)
endrec.append("") # Append the archive comment
endrec.append(filesize - 22) # Append the record start offset
return endrec
# Search the last END_BLOCK bytes of the file for the record signature.
# The comment is appended to the ZIP file and has a 16 bit length.
# So the comment may be up to 64K long. We limit the search for the
# signature to a few Kbytes at the end of the file for efficiency.
# also, the signature must not appear in the comment.
END_BLOCK = min(filesize, 1024 * 4)
fpin.seek(filesize - END_BLOCK, 0)
data = fpin.read()
start = data.rfind(stringEndArchive)
if start >= 0: # Correct signature string was found
endrec = struct.unpack(structEndArchive, data[start:start+22])
endrec = list(endrec)
comment = data[start+22:]
if endrec[7] == len(comment): # Comment length checks out
# Append the archive comment and start offset
endrec.append(comment)
endrec.append(filesize - END_BLOCK + start)
return endrec
return # Error, return None
class ZipInfo:
"""Class with attributes describing each file in the ZIP archive."""
def __init__(self, filename="NoName", date_time=(1980,1,1,0,0,0)):
self.filename = _normpath(filename) # Name of the file in the archive
self.date_time = date_time # year, month, day, hour, min, sec
# Standard values:
self.compress_type = ZIP_STORED # Type of compression for the file
self.comment = "" # Comment for each file
self.extra = "" # ZIP extra data
self.create_system = 0 # System which created ZIP archive
self.create_version = 20 # Version which created ZIP archive
self.extract_version = 20 # Version needed to extract archive
self.reserved = 0 # Must be zero
self.flag_bits = 0 # ZIP flag bits
self.volume = 0 # Volume number of file header
self.internal_attr = 0 # Internal attributes
self.external_attr = 0 # External file attributes
# Other attributes are set by class ZipFile:
# header_offset Byte offset to the file header
# file_offset Byte offset to the start of the file data
# CRC CRC-32 of the uncompressed file
# compress_size Size of the compressed file
# file_size Size of the uncompressed file
def FileHeader(self):
"""Return the per-file header as a string."""
dt = self.date_time
dosdate = (dt[0] - 1980) << 9 | dt[1] << 5 | dt[2]
dostime = dt[3] << 11 | dt[4] << 5 | (dt[5] // 2)
if self.flag_bits & 0x08:
# Set these to zero because we write them after the file data
CRC = compress_size = file_size = 0
else:
CRC = self.CRC
compress_size = self.compress_size
file_size = self.file_size
header = struct.pack(structFileHeader, stringFileHeader,
self.extract_version, self.reserved, self.flag_bits,
self.compress_type, dostime, dosdate, CRC,
compress_size, file_size,
len(self.filename), len(self.extra))
return header + self.filename + self.extra
# This is used to ensure paths in generated ZIP files always use
# forward slashes as the directory separator, as required by the
# ZIP format specification.
if os.sep != "/":
def _normpath(path):
return path.replace(os.sep, "/")
else:
def _normpath(path):
return path
class FileSimulator(BaseFileSimulator):
def close(self):
pass
class ZipDecompressor:
def __init__(self, fd, zinfo):
self.fp = fd
self.zinfo = zinfo
self.buffer = ''
self.bytesread = 0
self.byteswritten = 0 # Used for deflation only
self.crc = binascii.crc32("")
self.filepos = self.fp.tell()
if zinfo.compress_type == ZIP_STORED:
self.read = self.read_stored
elif zinfo.compress_type == ZIP_DEFLATED:
self.read = self.read_deflated
self.dc = zlib.decompressobj(-15)
self.recv = self.read
def copyto(self, destfd, size = -1):
copied = 0
if size < 1:
size = self.zinfo.file_size
while copied < size:
data = self.read(min(4096, size - copied))
destfd.write(data)
copied += len(data)
def _finalize(self):
if self.crc != self.zinfo.CRC:
raise BadZipfile, "Bad CRC-32 for file %s" % self.zinfo.filename
def flush(self):
while self.byteswritten < self.zinfo.file_size:
self.read(min(4096, self.zinfo.file_size - self.byteswritten))
self._finalize()
def close(self):
pass
def read_stored(self, count = -1):
if count < 1 or count > self.zinfo.compress_size - self.bytesread:
count = self.zinfo.compress_size - self.bytesread
if count < 1:
return ''
count = count + self.bytesread
self.fp.seek(self.zinfo.file_offset + self.bytesread)
retval = ''
while self.bytesread < count:
data = self.fp.read(min(4096, count - self.bytesread))
retval += data
self.bytesread += len(data)
self.byteswritten = self.bytesread
self.crc = binascii.crc32(retval, self.crc)
if self.bytesread == self.zinfo.compress_size:
self._finalize()
return retval
def read_deflated(self, count = -1):
if count < 1 or count > self.zinfo.file_size - self.byteswritten:
count = self.zinfo.file_size - self.byteswritten
if count < 1:
return ''
count = count
self.fp.seek(self.zinfo.file_offset + self.bytesread)
# First, fill up the buffer.
while len(self.buffer) < count:
bytes = self.fp.read(min(self.zinfo.compress_size - self.bytesread, 4096))
self.bytesread += len(bytes)
result = self.dc.decompress(bytes)
if len(result):
self.buffer += result
self.crc = binascii.crc32(result, self.crc)
if self.bytesread == self.zinfo.compress_size:
bytes = self.dc.decompress('Z') + self.dc.flush()
if len(bytes):
self.buffer += bytes
self.crc = binascii.crc32(bytes, self.crc)
self._finalize()
retval = self.buffer[:count]
self.byteswritten += len(retval)
self.buffer = self.buffer[count:]
return retval
###########################################################################
###########################################################################
###########################################################################
# New ZipReader class
class ZipReader:
""" Class with methods to open, read, close, list zip files.
z = ZipFile(file)
file: Either the path to the file, or a file-like object.
If it is a path, the file will be opened and closed by ZipFile.
"""
fp = None # Set here since __del__ checks it
def __init__(self, file):
"""Open the ZIP file with mode read "r", write "w" or append "a"."""
self.debug = 0 # Level of printing: 0 through 3
self.locationmap = {}
# Check if we were passed a file-like object
if type(file) in _STRING_TYPES:
self._filePassed = 0
self.filename = file
self.fp = open(file, 'rb')
else:
self._filePassed = 1
self.fp = file
self.filename = getattr(file, 'name', None)
try:
self._InitZip()
except BadZipfile:
if not self._filePassed:
self.fp.close()
self.fp = None
raise
def GetContents(self):
"""Read the directory, making sure we close the file if the format
is bad.
Must use before trying to access any included files by name!
"""
self._RealGetContents()
def _InitZip(self):
fp = self.fp
endrec = _EndRecData(fp)
if not endrec:
raise BadZipfile, "File is not a zip file"
if self.debug > 1:
print endrec
self.size_cd = endrec[5] # bytes in central directory
self.offset_cd = endrec[6] # offset of central directory
self.comment = endrec[8] # archive comment
# endrec[9] is the offset of the "End of Central Dir" record
x = endrec[9] - self.size_cd
# "concat" is zero, unless zip was concatenated to another file
concat = x - self.offset_cd
self.concat = concat
if self.debug > 2:
print "given, inferred, offset", offset_cd, x, concat
# self.start_dir: Position of start of central directory
self.start_dir = self.offset_cd + concat
def _RealGetContents(self):
"""Read in the table of contents for the ZIP file."""
fp = self.fp
fp.seek(self.start_dir, 0)
total = 0
while total < self.size_cd:
centdir = self._getcentdir() # Reads 46 bytes
filename = fp.read(centdir[_CD_FILENAME_LENGTH])
self.locationmap[filename] = self.start_dir + total
# Skip past the other stuff.
total = (total + 46 + centdir[_CD_FILENAME_LENGTH]
+ centdir[_CD_EXTRA_FIELD_LENGTH]
+ centdir[_CD_COMMENT_LENGTH])
fp.seek(self.start_dir + total, 0)
def namelist(self):
"""Return a list of file names in the archive."""
return self.locationmap.keys()
def namelistiter(self):
return self.locationmap.iterkeys()
def hasfile(self, name):
return self.locationmap.has_key(name)
def infolist(self):
"""Return a list of class ZipInfo instances for files in the
archive."""
return [self.getinfo(x) for x in self.locationmap.iterkeys()]
def printdir(self):
"""Print a table of contents for the zip file."""
print "%-46s %19s %12s" % ("File Name", "Modified ", "Size")
for name in self.locationmap.iterkeys():
zinfo = self.getinfo(name)
date = "%d-%02d-%02d %02d:%02d:%02d" % zinfo.date_time
print "%-46s %s %12d" % (zinfo.filename, date, zinfo.file_size)
def testzip(self):
"""Read all the files and check the CRC."""
for name in self.locationmap.iterkeys():
try:
self.read(name) # Check CRC-32
except:
return name
def getinfo(self, name):
"""Return the instance of ZipInfo given 'name'."""
return self.getinfofrompos(self.locationmap[name])
def _getcentdir(self):
"""Read central directory info from an ALREADY-SEEKED fp!"""
centdir = self.fp.read(46)
if centdir[0:4] != stringCentralDir:
raise BadZipfile, "Bad magic number for central directory"
centdir = struct.unpack(structCentralDir, centdir)
if self.debug > 2:
print centdir
return centdir
def getinfofrompos(self, location):
if location < 0:
raise KeyError, "Attempt to get information from non-file"
fp = self.fp
fp.seek(location, 0)
centdir = self._getcentdir()
filename = fp.read(centdir[_CD_FILENAME_LENGTH])
# Create ZipInfo instance to store file information
x = ZipInfo(filename)
x.extra = fp.read(centdir[_CD_EXTRA_FIELD_LENGTH])
x.comment = fp.read(centdir[_CD_COMMENT_LENGTH])
x.header_offset = centdir[_CD_LOCAL_HEADER_OFFSET] + self.concat
# file_offset must be computed below...
(x.create_version, x.create_system, x.extract_version, x.reserved,
x.flag_bits, x.compress_type, t, d,
x.CRC, x.compress_size, x.file_size) = centdir[1:12]
x.volume, x.internal_attr, x.external_attr = centdir[15:18]
# Convert date/time code to (year, month, day, hour, min, sec)
x.date_time = ( (d>>9)+1980, (d>>5)&0xF, d&0x1F,
t>>11, (t>>5)&0x3F, (t&0x1F) * 2 )
# And now, read the info from the file's header.
data = x
fp.seek(data.header_offset, 0)
fheader = fp.read(30)
if fheader[0:4] != stringFileHeader:
raise BadZipfile, "Bad magic number for file header"
fheader = struct.unpack(structFileHeader, fheader)
# file_offset is computed here, since the extra field for
# the central directory and for the local file header
# refer to different fields, and they can have different
# lengths
data.file_offset = (data.header_offset + 30
+ fheader[_FH_FILENAME_LENGTH]
+ fheader[_FH_EXTRA_FIELD_LENGTH])
fname = fp.read(fheader[_FH_FILENAME_LENGTH])
if fname != data.filename:
raise RuntimeError, \
'File name in directory "%s" and header "%s" differ.' % (
data.filename, fname)
return data
def read(self, name):
fd = StringIO()
self.copyto(name, fd)
return fd.getvalue()
def open_zinfo(self, zi):
if not self.fp:
raise RuntimeError, \
"Attempt to read ZIP archive that was already closed"
return FileSimulator(ZipDecompressor(self.fp, zi), None, -1)
def open(self, name):
return self.open_zinfo(self.getinfo(name))
def open_pos(self, location):
return self.open_zinfo(self.getinfofrompos(location))
def copyto(self, name, fd):
"""Copy the contents of the named file to the given descriptor."""
self.open(name)._sock.copyto(fd)
def __del__(self):
"""Call the "close()" method in case the user forgot."""
self.close()
def close(self):
"""Close the file, and for mode "w" and "a" write the ending
records."""
if self.fp is None:
return
if not self._filePassed:
self.fp.close()
self.fp = None
###########################################################################
###########################################################################
###########################################################################
# Old ZipFile class
class ZipFile:
""" Class with methods to open, read, write, close, list zip files.
z = ZipFile(file, mode="r", compression=ZIP_STORED)
file: Either the path to the file, or a file-like object.
If it is a path, the file will be opened and closed by ZipFile.
mode: The mode can be either read "r", write "w" or append "a".
compression: ZIP_STORED (no compression) or ZIP_DEFLATED (requires zlib).
"""
fp = None # Set here since __del__ checks it
def __init__(self, file, mode="r", compression=ZIP_STORED):
"""Open the ZIP file with mode read "r", write "w" or append "a"."""
if compression == ZIP_STORED:
pass
elif compression == ZIP_DEFLATED:
if not zlib:
raise RuntimeError,\
"Compression requires the (missing) zlib module"
else:
raise RuntimeError, "That compression method is not supported"
self.debug = 0 # Level of printing: 0 through 3
self.NameToInfo = {} # Find file info given name
self.filelist = [] # List of ZipInfo instances for archive
self.compression = compression # Method of compression
self.mode = key = mode[0]
# Check if we were passed a file-like object
if isinstance(file, basestring):
self._filePassed = 0
self.filename = file
modeDict = {'r' : 'rb', 'w': 'wb', 'a' : 'r+b'}
self.fp = open(file, modeDict[mode])
else:
self._filePassed = 1
self.fp = file
self.filename = getattr(file, 'name', None)
if key == 'r':
self._GetContents()
elif key == 'w':
pass
elif key == 'a':
try: # See if file is a zip file
self._RealGetContents()
# seek to start of directory and overwrite
self.fp.seek(self.start_dir, 0)
except BadZipfile: # file is not a zip file, just append
self.fp.seek(0, 2)
else:
if not self._filePassed:
self.fp.close()
self.fp = None
raise RuntimeError, 'Mode must be "r", "w" or "a"'
def _GetContents(self):
"""Read the directory, making sure we close the file if the format
is bad."""
try:
self._RealGetContents()
except BadZipfile:
if not self._filePassed:
self.fp.close()
self.fp = None
raise
def _RealGetContents(self):
"""Read in the table of contents for the ZIP file."""
fp = self.fp
endrec = _EndRecData(fp)
if not endrec:
raise BadZipfile, "File is not a zip file"
if self.debug > 1:
print endrec
size_cd = endrec[5] # bytes in central directory
offset_cd = endrec[6] # offset of central directory
self.comment = endrec[8] # archive comment
# endrec[9] is the offset of the "End of Central Dir" record
x = endrec[9] - size_cd
# "concat" is zero, unless zip was concatenated to another file
concat = x - offset_cd
if self.debug > 2:
print "given, inferred, offset", offset_cd, x, concat
# self.start_dir: Position of start of central directory
self.start_dir = offset_cd + concat
fp.seek(self.start_dir, 0)
total = 0
while total < size_cd:
centdir = fp.read(46)
total = total + 46
if centdir[0:4] != stringCentralDir:
raise BadZipfile, "Bad magic number for central directory"
centdir = struct.unpack(structCentralDir, centdir)
if self.debug > 2:
print centdir
filename = fp.read(centdir[_CD_FILENAME_LENGTH])
# Create ZipInfo instance to store file information
x = ZipInfo(filename)
x.extra = fp.read(centdir[_CD_EXTRA_FIELD_LENGTH])
x.comment = fp.read(centdir[_CD_COMMENT_LENGTH])
total = (total + centdir[_CD_FILENAME_LENGTH]
+ centdir[_CD_EXTRA_FIELD_LENGTH]
+ centdir[_CD_COMMENT_LENGTH])
x.header_offset = centdir[_CD_LOCAL_HEADER_OFFSET] + concat
# file_offset must be computed below...
(x.create_version, x.create_system, x.extract_version, x.reserved,
x.flag_bits, x.compress_type, t, d,
x.CRC, x.compress_size, x.file_size) = centdir[1:12]
x.volume, x.internal_attr, x.external_attr = centdir[15:18]
# Convert date/time code to (year, month, day, hour, min, sec)
x.date_time = ( (d>>9)+1980, (d>>5)&0xF, d&0x1F,
t>>11, (t>>5)&0x3F, (t&0x1F) * 2 )
self.filelist.append(x)
self.NameToInfo[x.filename] = x
if self.debug > 2:
print "total", total
for data in self.filelist:
fp.seek(data.header_offset, 0)
fheader = fp.read(30)
if fheader[0:4] != stringFileHeader:
raise BadZipfile, "Bad magic number for file header"
fheader = struct.unpack(structFileHeader, fheader)
# file_offset is computed here, since the extra field for
# the central directory and for the local file header
# refer to different fields, and they can have different
# lengths
data.file_offset = (data.header_offset + 30
+ fheader[_FH_FILENAME_LENGTH]
+ fheader[_FH_EXTRA_FIELD_LENGTH])
fname = fp.read(fheader[_FH_FILENAME_LENGTH])
if fname != data.filename:
raise RuntimeError, \
'File name in directory "%s" and header "%s" differ.' % (
data.filename, fname)
def namelist(self):
"""Return a list of file names in the archive."""
l = []
for data in self.filelist:
l.append(data.filename)
return l
def infolist(self):
"""Return a list of class ZipInfo instances for files in the
archive."""
return self.filelist
def printdir(self):
"""Print a table of contents for the zip file."""
print "%-46s %19s %12s" % ("File Name", "Modified ", "Size")
for zinfo in self.filelist:
date = "%d-%02d-%02d %02d:%02d:%02d" % zinfo.date_time
print "%-46s %s %12d" % (zinfo.filename, date, zinfo.file_size)
def testzip(self):
"""Read all the files and check the CRC."""
for zinfo in self.filelist:
try:
self.read(zinfo.filename) # Check CRC-32
except:
return zinfo.filename
def getinfo(self, name):
"""Return the instance of ZipInfo given 'name'."""
return self.NameToInfo[name]
def read(self, name):
"""Return file bytes (as a string) for name."""
if self.mode not in ("r", "a"):
raise RuntimeError, 'read() requires mode "r" or "a"'
if not self.fp:
raise RuntimeError, \
"Attempt to read ZIP archive that was already closed"
zinfo = self.getinfo(name)
filepos = self.fp.tell()
self.fp.seek(zinfo.file_offset, 0)
bytes = self.fp.read(zinfo.compress_size)
self.fp.seek(filepos, 0)
if zinfo.compress_type == ZIP_STORED:
pass
elif zinfo.compress_type == ZIP_DEFLATED:
if not zlib:
raise RuntimeError, \
"De-compression requires the (missing) zlib module"
# zlib compress/decompress code by Jeremy Hylton of CNRI
dc = zlib.decompressobj(-15)
bytes = dc.decompress(bytes)
# need to feed in unused pad byte so that zlib won't choke
ex = dc.decompress('Z') + dc.flush()
if ex:
bytes = bytes + ex
else:
raise BadZipfile, \
"Unsupported compression method %d for file %s" % \
(zinfo.compress_type, name)
crc = binascii.crc32(bytes)
if crc != zinfo.CRC:
raise BadZipfile, "Bad CRC-32 for file %s" % name
return bytes
def _writecheck(self, zinfo):
"""Check for errors before writing a file to the archive."""
if zinfo.filename in self.NameToInfo:
if self.debug: # Warning for duplicate names
print "Duplicate name:", zinfo.filename
if self.mode not in ("w", "a"):
raise RuntimeError, 'write() requires mode "w" or "a"'
if not self.fp:
raise RuntimeError, \
"Attempt to write ZIP archive that was already closed"
if zinfo.compress_type == ZIP_DEFLATED and not zlib:
raise RuntimeError, \
"Compression requires the (missing) zlib module"
if zinfo.compress_type not in (ZIP_STORED, ZIP_DEFLATED):
raise RuntimeError, \
"That compression method is not supported"
def write(self, filename, arcname=None, compress_type=None):
"""Put the bytes from filename into the archive under the name
arcname."""
st = os.stat(filename)
mtime = time.localtime(st.st_mtime)
date_time = mtime[0:6]
# Create ZipInfo instance to store file information
if arcname is None:
zinfo = ZipInfo(filename, date_time)
else:
zinfo = ZipInfo(arcname, date_time)
zinfo.external_attr = st[0] << 16L # Unix attributes
if compress_type is None:
zinfo.compress_type = self.compression
else:
zinfo.compress_type = compress_type
self._writecheck(zinfo)
fp = open(filename, "rb")
zinfo.flag_bits = 0x00
zinfo.header_offset = self.fp.tell() # Start of header bytes
# Must overwrite CRC and sizes with correct data later
zinfo.CRC = CRC = 0
zinfo.compress_size = compress_size = 0
zinfo.file_size = file_size = 0
self.fp.write(zinfo.FileHeader())
zinfo.file_offset = self.fp.tell() # Start of file bytes
if zinfo.compress_type == ZIP_DEFLATED:
cmpr = zlib.compressobj(zlib.Z_DEFAULT_COMPRESSION,
zlib.DEFLATED, -15)
else:
cmpr = None
while 1:
buf = fp.read(1024 * 8)
if not buf:
break
file_size = file_size + len(buf)
CRC = binascii.crc32(buf, CRC)
if cmpr:
buf = cmpr.compress(buf)
compress_size = compress_size + len(buf)
self.fp.write(buf)
fp.close()
if cmpr:
buf = cmpr.flush()
compress_size = compress_size + len(buf)
self.fp.write(buf)
zinfo.compress_size = compress_size
else:
zinfo.compress_size = file_size
zinfo.CRC = CRC
zinfo.file_size = file_size
# Seek backwards and write CRC and file sizes
position = self.fp.tell() # Preserve current position in file
self.fp.seek(zinfo.header_offset + 14, 0)
self.fp.write(struct.pack("<lll", zinfo.CRC, zinfo.compress_size,
zinfo.file_size))
self.fp.seek(position, 0)
self.filelist.append(zinfo)
self.NameToInfo[zinfo.filename] = zinfo
def writestr(self, zinfo_or_arcname, bytes):
"""Write a file into the archive. The contents is the string
'bytes'. 'zinfo_or_arcname' is either a ZipInfo instance or
the name of the file in the archive."""
if not isinstance(zinfo_or_arcname, ZipInfo):
zinfo = ZipInfo(filename=zinfo_or_arcname,
date_time=time.localtime(time.time()))
zinfo.compress_type = self.compression
else:
zinfo = zinfo_or_arcname
self._writecheck(zinfo)
zinfo.file_size = len(bytes) # Uncompressed size
zinfo.CRC = binascii.crc32(bytes) # CRC-32 checksum
if zinfo.compress_type == ZIP_DEFLATED:
co = zlib.compressobj(zlib.Z_DEFAULT_COMPRESSION,
zlib.DEFLATED, -15)
bytes = co.compress(bytes) + co.flush()
zinfo.compress_size = len(bytes) # Compressed size
else:
zinfo.compress_size = zinfo.file_size
zinfo.header_offset = self.fp.tell() # Start of header bytes
self.fp.write(zinfo.FileHeader())
zinfo.file_offset = self.fp.tell() # Start of file bytes
self.fp.write(bytes)
if zinfo.flag_bits & 0x08:
# Write CRC and file sizes after the file data
self.fp.write(struct.pack("<lll", zinfo.CRC, zinfo.compress_size,
zinfo.file_size))
self.filelist.append(zinfo)
self.NameToInfo[zinfo.filename] = zinfo
def __del__(self):
"""Call the "close()" method in case the user forgot."""
self.close()
def close(self):
"""Close the file, and for mode "w" and "a" write the ending
records."""
if self.fp is None:
return
if self.mode in ("w", "a"): # write ending records
count = 0
pos1 = self.fp.tell()
for zinfo in self.filelist: # write central directory
count = count + 1
dt = zinfo.date_time
dosdate = (dt[0] - 1980) << 9 | dt[1] << 5 | dt[2]
dostime = dt[3] << 11 | dt[4] << 5 | (dt[5] // 2)
centdir = struct.pack(structCentralDir,
stringCentralDir, zinfo.create_version,
zinfo.create_system, zinfo.extract_version, zinfo.reserved,
zinfo.flag_bits, zinfo.compress_type, dostime, dosdate,
zinfo.CRC, zinfo.compress_size, zinfo.file_size,
len(zinfo.filename), len(zinfo.extra), len(zinfo.comment),
0, zinfo.internal_attr, zinfo.external_attr,
zinfo.header_offset)
self.fp.write(centdir)
self.fp.write(zinfo.filename)
self.fp.write(zinfo.extra)
self.fp.write(zinfo.comment)
pos2 = self.fp.tell()
# Write end-of-zip-archive record
endrec = struct.pack(structEndArchive, stringEndArchive,
0, 0, count, count, pos2 - pos1, pos1, 0)
self.fp.write(endrec)
self.fp.flush()
if not self._filePassed:
self.fp.close()
self.fp = None
class PyZipFile(ZipFile):
"""Class to create ZIP archives with Python library files and packages."""
def writepy(self, pathname, basename = ""):
"""Add all files from "pathname" to the ZIP archive.
If pathname is a package directory, search the directory and
all package subdirectories recursively for all *.py and enter
the modules into the archive. If pathname is a plain
directory, listdir *.py and enter all modules. Else, pathname
must be a Python *.py file and the module will be put into the
archive. Added modules are always module.pyo or module.pyc.
This method will compile the module.py into module.pyc if
necessary.
"""
dir, name = os.path.split(pathname)
if os.path.isdir(pathname):
initname = os.path.join(pathname, "__init__.py")
if os.path.isfile(initname):
# This is a package directory, add it
if basename:
basename = "%s/%s" % (basename, name)
else:
basename = name
if self.debug:
print "Adding package in", pathname, "as", basename
fname, arcname = self._get_codename(initname[0:-3], basename)
if self.debug:
print "Adding", arcname
self.write(fname, arcname)
dirlist = os.listdir(pathname)
dirlist.remove("__init__.py")
# Add all *.py files and package subdirectories
for filename in dirlist:
path = os.path.join(pathname, filename)
root, ext = os.path.splitext(filename)
if os.path.isdir(path):
if os.path.isfile(os.path.join(path, "__init__.py")):
# This is a package directory, add it
self.writepy(path, basename) # Recursive call
elif ext == ".py":
fname, arcname = self._get_codename(path[0:-3],
basename)
if self.debug:
print "Adding", arcname
self.write(fname, arcname)
else:
# This is NOT a package directory, add its files at top level
if self.debug:
print "Adding files from directory", pathname
for filename in os.listdir(pathname):
path = os.path.join(pathname, filename)
root, ext = os.path.splitext(filename)
if ext == ".py":
fname, arcname = self._get_codename(path[0:-3],
basename)
if self.debug:
print "Adding", arcname
self.write(fname, arcname)
else:
if pathname[-3:] != ".py":
raise RuntimeError, \
'Files added with writepy() must end with ".py"'
fname, arcname = self._get_codename(pathname[0:-3], basename)
if self.debug:
print "Adding file", arcname
self.write(fname, arcname)
def _get_codename(self, pathname, basename):
"""Return (filename, archivename) for the path.
Given a module name path, return the correct file path and
archive name, compiling if necessary. For example, given
/python/lib/string, return (/python/lib/string.pyc, string).
"""
file_py = pathname + ".py"
file_pyc = pathname + ".pyc"
file_pyo = pathname + ".pyo"
if os.path.isfile(file_pyo) and \
os.stat(file_pyo).st_mtime >= os.stat(file_py).st_mtime:
fname = file_pyo # Use .pyo file
elif not os.path.isfile(file_pyc) or \
os.stat(file_pyc).st_mtime < os.stat(file_py).st_mtime:
import py_compile
if self.debug:
print "Compiling", file_py
try:
py_compile.compile(file_py, file_pyc, None, True)
except py_compile.PyCompileError,err:
print err.msg
fname = file_pyc
else:
fname = file_pyc
archivename = os.path.split(fname)[1]
if basename:
archivename = "%s/%s" % (basename, archivename)
return (fname, archivename)
|