Logo Search packages:      
Sourcecode: calibre version File versions  Download package


00001 """
Read and write ZIP files. Modified by Kovid Goyal to support replacing files in
a zip archive.
from __future__ import with_statement
import struct, os, time, sys, shutil
import binascii, cStringIO
from contextlib import closing
from tempfile import SpooledTemporaryFile

from calibre import sanitize_file_name
from calibre.constants import filesystem_encoding
from calibre.ebooks.chardet import detect

    import zlib # We may need its compression method
    crc32 = zlib.crc32
except ImportError:
    zlib = None
    crc32 = binascii.crc32

__all__ = ["BadZipfile", "error", "ZIP_STORED", "ZIP_DEFLATED", "is_zipfile",
           "ZipInfo", "ZipFile", "PyZipFile", "LargeZipFile" ]

class BadZipfile(Exception):

00029 class LargeZipFile(Exception):
    Raised when writing a zipfile, the zipfile requires ZIP64 extensions
    and those extensions are disabled.

error = BadZipfile      # The exception raised by this module

ZIP64_LIMIT= (1 << 31) - 1
ZIP_MAX_COMMENT = (1 << 16) - 1

# constants for Zip file compression methods
# Other ZIP compression methods not supported

# Below are some formats and associated data for reading/writing headers using
# the struct module.  The names and structures of headers/records are those used
# in the PKWARE description of the ZIP file format:
#     http://www.pkware.com/documents/casestudies/APPNOTE.TXT
# (URL valid as of January 2008)

# The "end of central directory" structure, magic number, size, and indices
# (section V.I in the format document)
structEndArchive = "<4s4H2LH"
stringEndArchive = "PK\005\006"
sizeEndCentDir = struct.calcsize(structEndArchive)

# These last two indices are not part of the structure as defined in the
# spec, but they are used internally by this module as a convenience

# The "central directory" structure, magic number, size, and indices
# of entries in the structure (section V.F in the format document)
structCentralDir = "<4s4B4HL2L5H2L"
stringCentralDir = "PK\001\002"
sizeCentralDir = struct.calcsize(structCentralDir)

# indexes of entries in the central directory structure
_CD_TIME = 7
_CD_DATE = 8
_CD_CRC = 9

# The "local file header" structure, magic number, size, and indices
# (section V.A in the format document)
structFileHeader = "<4s2B4HL2L2H"
stringFileHeader = "PK\003\004"
sizeFileHeader = struct.calcsize(structFileHeader)

_FH_CRC = 7

# The "Zip64 end of central directory locator" structure, magic number, and size
structEndArchive64Locator = "<4sLQL"
stringEndArchive64Locator = "PK\x06\x07"
sizeEndCentDir64Locator = struct.calcsize(structEndArchive64Locator)

# The "Zip64 end of central directory" record, magic number, size, and indices
# (section V.G in the format document)
structEndArchive64 = "<4sQ2H2L4Q"
stringEndArchive64 = "PK\x06\x06"
sizeEndCentDir64 = struct.calcsize(structEndArchive64)


def decode_arcname(name):
    if not isinstance(name, unicode):
        encoding = detect(name)['encoding']
            name = name.decode(encoding)
            name = name.decode('utf-8', 'replace')
    return name.encode(filesystem_encoding, 'replace')

00149 def is_zipfile(filename):
    """Quickly see if file is a ZIP file by checking the magic number."""
        fpin = open(filename, "rb")
        endrec = _EndRecData(fpin)
        if endrec:
            return True                 # file has correct magic number
    except IOError:
    return False

00161 def _EndRecData64(fpin, offset, endrec):
    Read the ZIP64 end-of-archive records and use that to update endrec
    fpin.seek(offset - sizeEndCentDir64Locator, 2)
    data = fpin.read(sizeEndCentDir64Locator)
    sig, diskno, reloff, disks = struct.unpack(structEndArchive64Locator, data)
    if sig != stringEndArchive64Locator:
        return endrec

    if diskno != 0 or disks != 1:
        raise BadZipfile("zipfiles that span multiple disks are not supported")

    # Assume no 'zip64 extensible data'
    fpin.seek(offset - sizeEndCentDir64Locator - sizeEndCentDir64, 2)
    data = fpin.read(sizeEndCentDir64)
    sig, sz, create_version, read_version, disk_num, disk_dir, \
            dircount, dircount2, dirsize, diroffset = \
            struct.unpack(structEndArchive64, data)
    if sig != stringEndArchive64:
        return endrec

    # Update the original endrec using data from the ZIP64 record
    endrec[_ECD_DISK_NUMBER] = disk_num
    endrec[_ECD_DISK_START] = disk_dir
    endrec[_ECD_ENTRIES_THIS_DISK] = dircount
    endrec[_ECD_ENTRIES_TOTAL] = dircount2
    endrec[_ECD_SIZE] = dirsize
    endrec[_ECD_OFFSET] = diroffset
    return endrec

00193 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."""

    # Determine file size
    fpin.seek(0, 2)
    filesize = fpin.tell()

    # Check to see if this is ZIP file with no archive comment (the
    # "end of central directory" structure should be the last item in the
    # file if this is the case).
    fpin.seek(-sizeEndCentDir, 2)
    data = fpin.read()
    if data[0:4] == stringEndArchive and data[-2:] == "\000\000":
        # the signature is correct and there's no comment, unpack structure
        endrec = struct.unpack(structEndArchive, data)

        # Append a blank comment and record start offset
        endrec.append(filesize - sizeEndCentDir)
        if endrec[_ECD_OFFSET] == 0xffffffff:
            # the value for the "offset of the start of the central directory"
            # indicates that there is a "Zip64 end of central directory"
            # structure present, so go look for it
            return _EndRecData64(fpin, -sizeEndCentDir, endrec)

        return endrec

    # Either this is not a ZIP file, or it is a ZIP file with an archive
    # comment.  Search the end of the file for the "end of central directory"
    # record signature. The comment is the last item in the ZIP file and may be
    # up to 64K long.  It is assumed that the "end of central directory" magic
    # number does not appear in the comment.
    maxCommentStart = max(filesize - (1 << 16) - sizeEndCentDir, 0)
    fpin.seek(maxCommentStart, 0)
    data = fpin.read()
    start = data.rfind(stringEndArchive)
    if start >= 0:
        # found the magic number; attempt to unpack and interpret
        recData = data[start:start+sizeEndCentDir]
        endrec = list(struct.unpack(structEndArchive, recData))
        comment = data[start+sizeEndCentDir:]
        # check that comment length is correct
        # Kovid: Added == 0 check as some zip files apparently dont set this
        if endrec[_ECD_COMMENT_SIZE] == 0 or endrec[_ECD_COMMENT_SIZE] == len(comment):
            # Append the archive comment and start offset
            endrec.append(maxCommentStart + start)
            if endrec[_ECD_OFFSET] == 0xffffffff:
                # There is apparently a "Zip64 end of central directory"
                # structure present, so go look for it
                return _EndRecData64(fpin, start - filesize, endrec)
            return endrec

    # Unable to find a valid end of central directory structure

00254 class ZipInfo (object):
    """Class with attributes describing each file in the ZIP archive."""

    __slots__ = (

    def __init__(self, filename="NoName", date_time=(1980,1,1,0,0,0)):
        self.orig_filename = filename   # Original file name in archive

        # Terminate the file name at the first null byte.  Null bytes in file
        # names are used as tricks by viruses in archives.
        null_byte = filename.find(chr(0))
        if null_byte >= 0:
            filename = filename[0:null_byte]
        # 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 != "/" and os.sep in filename:
            filename = filename.replace(os.sep, "/")

        self.filename = filename        # Normalized file name
        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
        if sys.platform == 'win32':
            self.create_system = 0          # System which created ZIP archive
            # Assume everything else is unix-y
            self.create_system = 3          # 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
        self.file_offset   = 0
        # Other attributes are set by class ZipFile:
        # header_offset         Byte offset to the file header
        # CRC                   CRC-32 of the uncompressed file
        # compress_size         Size of the compressed file
        # file_size             Size of the uncompressed file

00319     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
            CRC = self.CRC
            compress_size = self.compress_size
            file_size = self.file_size

        extra = self.extra

        if file_size > ZIP64_LIMIT or compress_size > ZIP64_LIMIT:
            # File is larger than what fits into a 4 byte integer,
            # fall back to the ZIP64 extension
            fmt = '<HHQQ'
            extra = extra + struct.pack(fmt,
                    1, struct.calcsize(fmt)-4, file_size, compress_size)
            file_size = 0xffffffff
            compress_size = 0xffffffff
            self.extract_version = max(45, self.extract_version)
            self.create_version = max(45, self.extract_version)

        filename, flag_bits = self._encodeFilenameFlags()
        header = struct.pack(structFileHeader, stringFileHeader,
                 self.extract_version, self.reserved, flag_bits,
                 self.compress_type, dostime, dosdate, CRC,
                 compress_size, file_size,
                 len(filename), len(extra))
        return header + filename + extra

    def _encodeFilenameFlags(self):
        if isinstance(self.filename, unicode):
                return self.filename.encode('ascii'), self.flag_bits
                return self.filename.encode('utf-8'), self.flag_bits | 0x800
            return self.filename, self.flag_bits

    def _decodeFilename(self):
        if self.flag_bits & 0x800:
            return self.filename.decode('utf-8')
            return self.filename

    def _decodeExtra(self):
        # Try to decode the extra field.
        extra = self.extra
        unpack = struct.unpack
        while extra:
            tp, ln = unpack('<HH', extra[:4])
            if tp == 1:
                if ln >= 24:
                    counts = unpack('<QQQ', extra[4:28])
                elif ln == 16:
                    counts = unpack('<QQ', extra[4:20])
                elif ln == 8:
                    counts = unpack('<Q', extra[4:12])
                elif ln == 0:
                    counts = ()
                    raise RuntimeError, "Corrupt extra field %s"%(ln,)

                idx = 0

                # ZIP64 extension (large files and/or large archives)
                if self.file_size in (0xffffffffffffffffL, 0xffffffffL):
                    self.file_size = counts[idx]
                    idx += 1

                if self.compress_size == 0xFFFFFFFFL:
                    self.compress_size = counts[idx]
                    idx += 1

                if self.header_offset == 0xffffffffL:
                    self.header_offset = counts[idx]

            extra = extra[ln+4:]

00404 class _ZipDecrypter:
    """Class to handle decryption of files stored within a ZIP archive.

    ZIP supports a password-based form of encryption. Even though known
    plaintext attacks have been found against it, it is still useful
    to be able to get data out of such a file.

        zd = _ZipDecrypter(mypwd)
        plain_char = zd(cypher_char)
        plain_text = map(zd, cypher_text)

00417     def _GenerateCRCTable():
        """Generate a CRC-32 table.

        ZIP encryption uses the CRC32 one-byte primitive for scrambling some
        internal keys. We noticed that a direct implementation is faster than
        relying on binascii.crc32().
        poly = 0xedb88320
        table = [0] * 256
        for i in range(256):
            crc = i
            for j in range(8):
                if crc & 1:
                    crc = ((crc >> 1) & 0x7FFFFFFF) ^ poly
                    crc = ((crc >> 1) & 0x7FFFFFFF)
            table[i] = crc
        return table
    crctable = _GenerateCRCTable()

00437     def _crc32(self, ch, crc):
        """Compute the CRC32 primitive on one byte."""
        return ((crc >> 8) & 0xffffff) ^ self.crctable[(crc ^ ord(ch)) & 0xff]

    def __init__(self, pwd):
        self.key0 = 305419896
        self.key1 = 591751049
        self.key2 = 878082192
        for p in pwd:

    def _UpdateKeys(self, c):
        self.key0 = self._crc32(c, self.key0)
        self.key1 = (self.key1 + (self.key0 & 255)) & 4294967295
        self.key1 = (self.key1 * 134775813 + 1) & 4294967295
        self.key2 = self._crc32(chr((self.key1 >> 24) & 255), self.key2)

00454     def __call__(self, c):
        """Decrypt a single character."""
        c = ord(c)
        k = self.key2 | 2
        c = c ^ (((k * (k^1)) >> 8) & 255)
        c = chr(c)
        return c

00463 class ZipExtFile:
    """File-like object for reading an archive member.
       Is returned by ZipFile.open().

    def __init__(self, fileobj, zipinfo, decrypt=None):
        self.fileobj = fileobj
        self.orig_pos = fileobj.tell()
        self.decrypter = decrypt
        self.bytes_read = 0L
        self.rawbuffer = ''
        self.readbuffer = ''
        self.linebuffer = ''
        self.eof = False
        self.univ_newlines = False
        self.nlSeps = ("\n", )
        self.lastdiscard = ''

        self.compress_type = zipinfo.compress_type
        self.compress_size = zipinfo.compress_size

        self.closed  = False
        self.mode    = "r"
        self.name = zipinfo.filename

        # read from compressed files in 64k blocks
        self.compreadsize = 64*1024
        if self.compress_type == ZIP_DEFLATED:
            self.dc = zlib.decompressobj(-15)

    def set_univ_newlines(self, univ_newlines):
        self.univ_newlines = univ_newlines

        # pick line separator char(s) based on universal newlines flag
        self.nlSeps = ("\n", )
        if self.univ_newlines:
            self.nlSeps = ("\r\n", "\r", "\n")

    def __iter__(self):
        return self

    def next(self):
        nextline = self.readline()
        if not nextline:
            raise StopIteration()

        return nextline

    def close(self):
        self.closed = True

    def _checkfornewline(self):
        nl, nllen = -1, -1
        if self.linebuffer:
            # ugly check for cases where half of an \r\n pair was
            # read on the last pass, and the \r was discarded.  In this
            # case we just throw away the \n at the start of the buffer.
            if (self.lastdiscard, self.linebuffer[0]) == ('\r','\n'):
                self.linebuffer = self.linebuffer[1:]

            for sep in self.nlSeps:
                nl = self.linebuffer.find(sep)
                if nl >= 0:
                    nllen = len(sep)
                    return nl, nllen

        return nl, nllen

00531     def readline(self, size = -1):
        """Read a line with approx. size. If size is negative,
           read a whole line.
        if size < 0:
            size = sys.maxint
        elif size == 0:
            return ''

        # check for a newline already in buffer
        nl, nllen = self._checkfornewline()

        if nl >= 0:
            # the next line was already in the buffer
            nl = min(nl, size)
            # no line break in buffer - try to read more
            size -= len(self.linebuffer)
            while nl < 0 and size > 0:
                buf = self.read(min(size, 100))
                if not buf:
                self.linebuffer += buf
                size -= len(buf)

                # check for a newline in buffer
                nl, nllen = self._checkfornewline()

            # we either ran out of bytes in the file, or
            # met the specified size limit without finding a newline,
            # so return current buffer
            if nl < 0:
                s = self.linebuffer
                self.linebuffer = ''
                return s

        buf = self.linebuffer[:nl]
        self.lastdiscard = self.linebuffer[nl:nl + nllen]
        self.linebuffer = self.linebuffer[nl + nllen:]

        # line is always returned with \n as newline char (except possibly
        # for a final incomplete line in the file, which is handled above).
        return buf + "\n"

00575     def readlines(self, sizehint = -1):
        """Return a list with all (following) lines. The sizehint parameter
        is ignored in this implementation.
        result = []
        while True:
            line = self.readline()
            if not line: break
        return result

    def read_raw(self):
        pos = self.fileobj.tell()
        bytes_to_read = self.compress_size
        if self.decrypter is not None:
            bytes_to_read -= 12
        raw = b''

        if bytes_to_read > 0:
            raw = self.fileobj.read(bytes_to_read)
        return raw

    def read(self, size = None):
        # act like file() obj and return empty string if size is 0
        if size == 0:
            return ''

        # determine read size
        bytesToRead = self.compress_size - self.bytes_read

        # adjust read size for encrypted files since the first 12 bytes
        # are for the encryption/password information
        if self.decrypter is not None:
            bytesToRead -= 12

        if size is not None and size >= 0:
            if self.compress_type == ZIP_STORED:
                lr = len(self.readbuffer)
                bytesToRead = min(bytesToRead, size - lr)
            elif self.compress_type == ZIP_DEFLATED:
                if len(self.readbuffer) > size:
                    # the user has requested fewer bytes than we've already
                    # pulled through the decompressor; don't read any more
                    bytesToRead = 0
                    # user will use up the buffer, so read some more
                    lr = len(self.rawbuffer)
                    bytesToRead = min(bytesToRead, self.compreadsize - lr)

        # avoid reading past end of file contents
        if bytesToRead + self.bytes_read > self.compress_size:
            bytesToRead = self.compress_size - self.bytes_read

        # try to read from file (if necessary)
        if bytesToRead > 0:
            bytes = self.fileobj.read(bytesToRead)
            self.bytes_read += len(bytes)
            self.rawbuffer += bytes

            # handle contents of raw buffer
            if self.rawbuffer:
                newdata = self.rawbuffer
                self.rawbuffer = ''

                # decrypt new data if we were given an object to handle that
                if newdata and self.decrypter is not None:
                    newdata = ''.join(map(self.decrypter, newdata))

                # decompress newly read data if necessary
                if newdata and self.compress_type == ZIP_DEFLATED:
                    newdata = self.dc.decompress(newdata)
                    self.rawbuffer = self.dc.unconsumed_tail
                    if self.eof and len(self.rawbuffer) == 0:
                        # we're out of raw bytes (both from the file and
                        # the local buffer); flush just to make sure the
                        # decompressor is done
                        newdata += self.dc.flush()
                        # prevent decompressor from being used again
                        self.dc = None

                self.readbuffer += newdata

        # return what the user asked for
        if size is None or len(self.readbuffer) <= size:
            bytes = self.readbuffer
            self.readbuffer = ''
            bytes = self.readbuffer[:size]
            self.readbuffer = self.readbuffer[size:]

        return bytes

00672 class ZipFile:
    """ Class with methods to open, read, write, close, list and update zip files.

    z = ZipFile(file, mode="r", compression=ZIP_STORED, allowZip64=False)

    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).
    allowZip64: if True ZipFile will create files with ZIP64 extensions when
                needed, otherwise it will raise an exception when this would
                be necessary.


    fp = None                   # Set here since __del__ checks it

00689     def __init__(self, file, mode="r", compression=ZIP_DEFLATED, allowZip64=False):
        """Open the ZIP file with mode read "r", write "w" or append "a"."""
        if mode not in ("r", "w", "a"):
            raise RuntimeError('ZipFile() requires mode "r", "w", or "a" not %s'%mode)

        if compression == ZIP_STORED:
        elif compression == ZIP_DEFLATED:
            if not zlib:
                raise RuntimeError,\
                      "Compression requires the (missing) zlib module"
            raise RuntimeError, "That compression method is not supported"

        self._allowZip64 = allowZip64
        self._didModify = False
        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.extract_mapping = {}
        self.compression = compression  # Method of compression
        self.mode = key = mode.replace('b', '')[0]
        self.pwd = None
        self.comment = ''

        # 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])
            except IOError:
                if mode == 'a':
                    mode = key = 'w'
                    self.fp = open(file, modeDict[mode])
            self._filePassed = 1
            self.fp = file
            self.filename = getattr(file, 'name', None)

        if key == 'r':
        elif key == 'w':
        elif key == 'a':
            try:                        # See if file is a zip file
                # 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)
            if not self._filePassed:
                self.fp = None
            raise RuntimeError, 'Mode must be "r", "w" or "a"'

00750     def _GetContents(self):
        """Read the directory, making sure we close the file if the format
        is bad."""
        except BadZipfile:
            if not self._filePassed:
                self.fp = None

00761     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[_ECD_SIZE]             # bytes in central directory
        offset_cd = endrec[_ECD_OFFSET]         # offset of central directory
        self.comment = endrec[_ECD_COMMENT]     # archive comment

        # "concat" is zero, unless zip was concatenated to another file
        concat = endrec[_ECD_LOCATION] - size_cd - offset_cd
        if endrec[_ECD_LOCATION] > ZIP64_LIMIT:
            # If the offset of the "End of Central Dir" record requires Zip64
            # extension structures, account for them
            concat -= (sizeEndCentDir64 + sizeEndCentDir64Locator)

        if self.debug > 2:
            inferred = concat + offset_cd
            print "given, inferred, offset", offset_cd, inferred, concat
        # self.start_dir:  Position of start of central directory
        self.start_dir = offset_cd + concat
        fp.seek(self.start_dir, 0)
        data = fp.read(size_cd)
        fp = cStringIO.StringIO(data)
        total = 0
        while total < size_cd:
            centdir = fp.read(sizeCentralDir)
            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])
            x.header_offset = centdir[_CD_LOCAL_HEADER_OFFSET]
            (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._raw_time = t
            x.date_time = ( (d>>9)+1980, (d>>5)&0xF, d&0x1F,
                                     t>>11, (t>>5)&0x3F, (t&0x1F) * 2 )

            x.header_offset = x.header_offset + concat
            x.filename = x._decodeFilename()
            self.NameToInfo[x.filename] = x

            # update total bytes read from central directory
            total = (total + sizeCentralDir + centdir[_CD_FILENAME_LENGTH]
                     + centdir[_CD_EXTRA_FIELD_LENGTH]
                     + centdir[_CD_COMMENT_LENGTH])

            if self.debug > 2:
                print "total", total

    def _calculate_file_offsets(self):
        for zip_info in self.filelist:
            self.fp.seek(zip_info.header_offset, 0)
            fheader = self.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
            file_offset = (zip_info.header_offset + 30
                                + fheader[_FH_FILENAME_LENGTH]
                                + fheader[_FH_EXTRA_FIELD_LENGTH])
            fname = self.fp.read(fheader[_FH_FILENAME_LENGTH])
            if fname != zip_info.orig_filename:
                raise RuntimeError(
                      'File name in directory "%s" and header "%s" differ.' % (
                          zip_info.orig_filename, fname))

            zip_info.file_offset = file_offset

00847     def replace(self, filename, arcname=None, compress_type=None):
        """Delete arcname, and put the bytes from filename into the
        archive under the name arcname."""
        deleteName = arcname
        if deleteName is None:
            deleteName = filename
        self.write(filename, arcname, compress_type)

00856     def replacestr(self, zinfo, bytes):
        """Delete zinfo.filename, and write a new file into the archive. The
        contents is the string 'bytes'."""
        self.writestr(zinfo, bytes)

00862     def delete(self, name):
        """Delete the file from the archive. If it appears multiple
        times only the first instance will be deleted."""
        for i in range (0, len(self.filelist)):
            if self.filelist[i].filename == name:
                if self.debug:
                    print "Removing", name
                deleted_offset = self.filelist[i].header_offset
                deleted_size   = (self.filelist[i].file_offset - self.filelist[i].header_offset) + self.filelist[i].compress_size
                zinfo_size = struct.calcsize(structCentralDir) + len(self.filelist[i].filename) + len(self.filelist[i].extra)
                # Remove the file's data from the archive.
                current_offset = self.fp.tell()
                self.fp.seek(0, 2)
                archive_size = self.fp.tell()
                self.fp.seek(deleted_offset + deleted_size)
                buf = self.fp.read()
                self.fp.truncate(archive_size - deleted_size - zinfo_size)
                if current_offset > deleted_offset + deleted_size:
                    current_offset -= deleted_size
                elif current_offset > deleted_offset:
                    current_offset = deleted_offset
                self.fp.seek(current_offset, 0)
                # Remove file from central directory.
                del self.filelist[i]
                # Adjust the remaining offsets in the central directory.
                for j in range (i, len(self.filelist)):
                    if self.filelist[j].header_offset > deleted_offset:
                        self.filelist[j].header_offset -= deleted_size
                    if self.filelist[j].file_offset > deleted_offset:
                        self.filelist[j].file_offset -= deleted_size
                self._didModify = True
        if self.debug:
            print name, "not in archive"

00899     def namelist(self):
        """Return a list of file names in the archive."""
        l = []
        for data in self.filelist:
        return l

00906     def infolist(self):
        """Return a list of class ZipInfo instances for files in the
        return self.filelist

00911     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[:6]
            print "%-46s %s %12d" % (zinfo.filename, date, zinfo.file_size)

00918     def testzip(self):
        """Read all the files and check the CRC."""
        for zinfo in self.filelist:
                self.read(zinfo.filename)       # Check CRC-32
            except BadZipfile:
                return zinfo.filename

00926     def getinfo(self, name):
        """Return the instance of ZipInfo given 'name'."""
        info = self.NameToInfo.get(name)
        if info is None:
            raise KeyError(
                'There is no item named %r in the archive' % name)

        return info

00935     def setpassword(self, pwd):
        """Set default password for encrypted files."""
        self.pwd = pwd

00939     def read(self, name, pwd=None):
        """Return file bytes (as a string) for name."""
        return self.open(name, "r", pwd).read()

00943     def read_raw(self, name, mode="r", pwd=None):
        """Return the raw bytes in the zipfile corresponding to name."""
        zef = self.open(name, mode=mode, pwd=pwd)
        return zef.read_raw()

00948     def open(self, name, mode="r", pwd=None):
        """Return file-like object for 'name'."""
        if mode not in ("r", "U", "rU"):
            raise RuntimeError, 'open() requires mode "r", "U", or "rU"'
        if not self.fp:
            raise RuntimeError, \
                  "Attempt to read ZIP archive that was already closed"

        # Only open a new file for instances where we were not
        # given a file object in the constructor
        if self._filePassed:
            zef_file = self.fp
            zef_file = open(self.filename, 'rb')

        # Make sure we have an info object
        if isinstance(name, ZipInfo):
            # 'name' is already an info object
            zinfo = name
            # Get info object for name
            zinfo = self.getinfo(name)

        zef_file.seek(zinfo.header_offset, 0)

        # Skip the file header:
        fheader = zef_file.read(sizeFileHeader)
        if fheader[0:4] != stringFileHeader:
            raise BadZipfile, "Bad magic number for file header"

        fheader = struct.unpack(structFileHeader, fheader)
        fname = zef_file.read(fheader[_FH_FILENAME_LENGTH])
        if fheader[_FH_EXTRA_FIELD_LENGTH]:

        if fname != zinfo.orig_filename:
            raise BadZipfile, \
                      'File name in directory "%s" and header "%s" differ.' % (
                          zinfo.orig_filename, fname)

        # check for encrypted flag & handle password
        is_encrypted = zinfo.flag_bits & 0x1
        zd = None
        if is_encrypted:
            if not pwd:
                pwd = self.pwd
            if not pwd:
                raise RuntimeError, "File %s is encrypted, " \
                      "password required for extraction" % name

            zd = _ZipDecrypter(pwd)
            # The first 12 bytes in the cypher stream is an encryption header
            #  used to strengthen the algorithm. The first 11 bytes are
            #  completely random, while the 12th contains the MSB of the CRC,
            #  or the MSB of the file time depending on the header type
            #  and is used to check the correctness of the password.
            bytes = zef_file.read(12)
            h = map(zd, bytes[0:12])
            if zinfo.flag_bits & 0x8:
                # compare against the file type from extended local headers
                check_byte = (zinfo._raw_time >> 8) & 0xff
                # compare against the CRC otherwise
                check_byte = (zinfo.CRC >> 24) & 0xff
            if ord(h[11]) != check_byte:
                raise RuntimeError("Bad password for file", name)

        # build and return a ZipExtFile
        if zd is None:
            zef = ZipExtFile(zef_file, zinfo)
            zef = ZipExtFile(zef_file, zinfo, zd)

        # set universal newlines on ZipExtFile if necessary
        if "U" in mode:
        return zef

01026     def extract(self, member, path=None, pwd=None):
        """Extract a member from the archive to the current working directory,
           using its full name. Its file information is extracted as accurately
           as possible. `member' may be a filename or a ZipInfo object. You can
           specify a different directory using `path'.
        if not isinstance(member, ZipInfo):
            member = self.getinfo(member)

        if path is None:
            path = os.getcwd()

        return self._extract_member(member, path, pwd)

01040     def extractall(self, path=None, members=None, pwd=None):
        """Extract all members from the archive to the current working
           directory. `path' specifies a different directory to extract to.
           `members' is optional and must be a subset of the list returned
           by namelist().
        if members is None:
            members = self.namelist()

        for zipinfo in members:
            self.extract(zipinfo, path, pwd)

01052     def _extract_member(self, member, targetpath, pwd):
        """Extract the ZipInfo object 'member' to a physical
           file on the path targetpath.
        # build the destination pathname, replacing
        # forward slashes to platform specific separators.
        if targetpath[-1:] == "/":
            targetpath = targetpath[:-1]

        # don't include leading "/" from file name if present
        fname = decode_arcname(member.filename)
        if fname.startswith('/'):
            fname = fname[1:]
        targetpath = os.path.join(targetpath, fname)

        targetpath = os.path.normpath(targetpath)

        # Create all upper directories if necessary.
        upperdirs = os.path.dirname(targetpath)
        if upperdirs and os.path.exists(upperdirs) and not os.path.isdir(upperdirs):
        if upperdirs and not os.path.exists(upperdirs):

        if not os.path.exists(targetpath): # Could be a previously automatically created directory
            with closing(self.open(member, pwd=pwd)) as source:
                    with open(targetpath, 'wb') as target:
                        shutil.copyfileobj(source, target)
                    targetpath = sanitize_file_name(targetpath)
                    with open(targetpath, 'wb') as target:
                        shutil.copyfileobj(source, target)
        self.extract_mapping[member.filename] = targetpath
        return targetpath

01088     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"
        if zinfo.file_size > ZIP64_LIMIT:
            if not self._allowZip64:
                raise LargeZipFile("Filesize would require ZIP64 extensions")
        if zinfo.header_offset > ZIP64_LIMIT:
            if not self._allowZip64:
                raise LargeZipFile("Zipfile size would require ZIP64 extensions")

01111     def write(self, filename, arcname=None, compress_type=None):
        """Put the bytes from filename into the archive under the name
        if isinstance(filename, unicode):
            filename = filename.encode('utf-8')
        if not self.fp:
            raise RuntimeError(
                  "Attempt to write to ZIP archive that was already closed")

        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:
            arcname = filename
        arcname = os.path.normpath(os.path.splitdrive(arcname)[1])
        while arcname[0] in (os.sep, os.altsep):
            arcname = arcname[1:]
        zinfo = ZipInfo(arcname, date_time)
        zinfo.external_attr = (st[0] & 0xFFFF) << 16L      # Unix attributes
        if compress_type is None:
            zinfo.compress_type = self.compression
            zinfo.compress_type = compress_type

        zinfo.file_size = st.st_size
        zinfo.flag_bits = 0x00
        zinfo.header_offset = self.fp.tell()    # Start of header bytes

        self._didModify = True
        fp = open(filename, "rb")
        # 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
        if zinfo.compress_type == ZIP_DEFLATED:
            cmpr = zlib.compressobj(zlib.Z_DEFAULT_COMPRESSION,
                 zlib.DEFLATED, -15)
            cmpr = None
        while 1:
            buf = fp.read(1024 * 8)
            if not buf:
            file_size = file_size + len(buf)
            CRC = crc32(buf, CRC) & 0xffffffff
            if cmpr:
                buf = cmpr.compress(buf)
                compress_size = compress_size + len(buf)
        if cmpr:
            buf = cmpr.flush()
            compress_size = compress_size + len(buf)
            zinfo.compress_size = compress_size
            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,
        self.fp.seek(position, 0)
        self.NameToInfo[zinfo.filename] = zinfo

01182     def writestr(self, zinfo_or_arcname, bytes, permissions=0600,
            compression=ZIP_DEFLATED, raw_bytes=False):
        """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."""
        assert not raw_bytes or (raw_bytes and
                isinstance(zinfo_or_arcname, ZipInfo))
        if not isinstance(zinfo_or_arcname, ZipInfo):
            if isinstance(zinfo_or_arcname, unicode):
                zinfo_or_arcname = zinfo_or_arcname.encode('utf-8')
            zinfo = ZipInfo(filename=zinfo_or_arcname,
            zinfo.compress_type = compression
            zinfo.external_attr = permissions << 16
            zinfo = zinfo_or_arcname

        if not self.fp:
            raise RuntimeError(
                  "Attempt to write to ZIP archive that was already closed")

        if not raw_bytes:
            zinfo.file_size = len(bytes)            # Uncompressed size
        zinfo.header_offset = self.fp.tell()    # Start of header bytes
        self._didModify = True
        if not raw_bytes:
            zinfo.CRC = crc32(bytes) & 0xffffffff       # 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
                zinfo.compress_size = zinfo.file_size
        zinfo.header_offset = self.fp.tell()    # Start of header 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,
        self.NameToInfo[zinfo.filename] = zinfo

01228     def add_dir(self, path, prefix=''):
        Add a directory recursively to the zip file with an optional prefix.
        if prefix:
            self.writestr(prefix+'/', '', 0700)
        cwd = os.path.abspath(os.getcwd())
            fp = (prefix + ('/' if prefix else '')).replace('//', '/')
            for f in os.listdir('.'):
                arcname = fp + f
                if os.path.isdir(f):
                    self.add_dir(f, prefix=arcname)
                    self.write(f, arcname)

01248     def __del__(self):
        """Call the "close()" method in case the user forgot."""

01252     def close(self):
        """Close the file, and for mode "w" and "a" write the ending
        if self.fp is None:

        if self.mode in ("w", "a") and self._didModify: # 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)
                extra = []
                if zinfo.file_size > ZIP64_LIMIT \
                        or zinfo.compress_size > ZIP64_LIMIT:
                    file_size = 0xffffffff
                    compress_size = 0xffffffff
                    file_size = zinfo.file_size
                    compress_size = zinfo.compress_size

                if zinfo.header_offset > ZIP64_LIMIT:
                    header_offset = 0xffffffffL
                    header_offset = zinfo.header_offset

                extra_data = zinfo.extra
                if extra:
                    # Append a ZIP64 field to the extra's
                    extra_data = struct.pack(
                            '<HH' + 'Q'*len(extra),
                            1, 8*len(extra), *extra) + extra_data

                    extract_version = max(45, zinfo.extract_version)
                    create_version = max(45, zinfo.create_version)
                    extract_version = zinfo.extract_version
                    create_version = zinfo.create_version

                    filename, flag_bits = zinfo._encodeFilenameFlags()
                    centdir = struct.pack(structCentralDir,
                     stringCentralDir, create_version,
                     zinfo.create_system, extract_version, zinfo.reserved,
                     flag_bits, zinfo.compress_type, dostime, dosdate,
                     zinfo.CRC, compress_size, file_size,
                     len(filename), len(extra_data), len(zinfo.comment),
                     0, zinfo.internal_attr, zinfo.external_attr,
                except DeprecationWarning:
                    print >>sys.stderr, (structCentralDir,
                     stringCentralDir, create_version,
                     zinfo.create_system, extract_version, zinfo.reserved,
                     zinfo.flag_bits, zinfo.compress_type, dostime, dosdate,
                     zinfo.CRC, compress_size, file_size,
                     len(zinfo.filename), len(extra_data), len(zinfo.comment),
                     0, zinfo.internal_attr, zinfo.external_attr,

            pos2 = self.fp.tell()
            # Write end-of-zip-archive record
            centDirOffset = pos1
            if pos1 > ZIP64_LIMIT:
                # Need to write the ZIP64 end-of-archive records
                zip64endrec = struct.pack(
                        structEndArchive64, stringEndArchive64,
                        44, 45, 45, 0, 0, count, count, pos2 - pos1, pos1)

                zip64locrec = struct.pack(
                        stringEndArchive64Locator, 0, pos2, 1)
                centDirOffset = 0xFFFFFFFF

            # check for valid comment length
            if len(self.comment) >= ZIP_MAX_COMMENT:
                if self.debug > 0:
                    msg = 'Archive comment is too long; truncating to %d bytes' \
                          % ZIP_MAX_COMMENT
                    print msg
                self.comment = self.comment[:ZIP_MAX_COMMENT]

            endrec = struct.pack(structEndArchive, stringEndArchive,
                                 0, 0, count % ZIP_FILECOUNT_LIMIT,
                                 count % ZIP_FILECOUNT_LIMIT, pos2 - pos1,
                                 centDirOffset, len(self.comment))

        if not self._filePassed:
        self.fp = None

01357 def safe_replace(zipstream, name, datastream):
    Replace a file in a zip file in a safe manner. This proceeds by extracting
    and re-creating the zipfile. This is necessary because :method:`ZipFile.replace`
    sometimes created corrupted zip files.

    :param zipstream:  Stream from a zip file
    :param name:       The name of the file to replace
    :param datastream: The data to replace the file with.
    z = ZipFile(zipstream, 'r')
    with SpooledTemporaryFile(max_size=100*1024*1024) as temp:
        ztemp = ZipFile(temp, 'w')
        for obj in z.infolist():
            if obj.filename == name:
                ztemp.writestr(obj, datastream.read())
                ztemp.writestr(obj, z.read_raw(obj), raw_bytes=True)
        shutil.copyfileobj(temp, zipstream)

01383 class PyZipFile(ZipFile):
    """Class to create ZIP archives with Python library files and packages."""

01386     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
        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)
                    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)
                # Add all *.py files and package subdirectories
                for filename in dirlist:
                    path = os.path.join(pathname, filename)
                    ext = os.path.splitext(filename)[-1]
                    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],
                        if self.debug:
                            print "Adding", arcname
                        self.write(fname, arcname)
                # 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)
                    ext = os.path.splitext(filename)[-1]
                    if ext == ".py":
                        fname, arcname = self._get_codename(path[0:-3],
                        if self.debug:
                            print "Adding", arcname
                        self.write(fname, arcname)
            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)

01451     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
                py_compile.compile(file_py, file_pyc, None, True)
            except py_compile.PyCompileError,err:
                print err.msg
            fname = file_pyc
            fname = file_pyc
        archivename = os.path.split(fname)[1]
        if basename:
            archivename = "%s/%s" % (basename, archivename)
        return (fname, archivename)

def main(args = None):
    import textwrap
            zipfile.py -l zipfile.zip        # Show listing of a zipfile
            zipfile.py -t zipfile.zip        # Test if a zipfile is valid
            zipfile.py -e zipfile.zip target # Extract zipfile into target dir
            zipfile.py -c zipfile.zip src ... # Create zipfile from sources
    if args is None:
        args = sys.argv[1:]

    if not args or args[0] not in ('-l', '-c', '-e', '-t'):
        print USAGE

    if args[0] == '-l':
        if len(args) != 2:
            print USAGE
        zf = ZipFile(args[1], 'r')

    elif args[0] == '-t':
        if len(args) != 2:
            print USAGE
        zf = ZipFile(args[1], 'r')
        print "Done testing"

    elif args[0] == '-e':
        if len(args) != 3:
            print USAGE

        zf = ZipFile(args[1], 'r')
        out = args[2]
        for path in zf.namelist():
            if path.startswith('./'):
                tgt = os.path.join(out, path[2:])
                tgt = os.path.join(out, path)

            tgtdir = os.path.dirname(tgt)
            if not os.path.exists(tgtdir):
            fp = open(tgt, 'wb')

    elif args[0] == '-c':
        if len(args) < 3:
            print USAGE

        def addToZip(zf, path, zippath):
            if os.path.isfile(path):
                zf.write(path, zippath, ZIP_DEFLATED)
            elif os.path.isdir(path):
                for nm in os.listdir(path):
                            os.path.join(path, nm), os.path.join(zippath, nm))
            # else: ignore

        zf = ZipFile(args[1], 'w', allowZip64=True)
        for src in args[2:]:
            addToZip(zf, src, os.path.basename(src))


if __name__ == "__main__":

Generated by  Doxygen 1.6.0   Back to index