"""

Read and write ZIP files.

"""

import struct, os, time, sys, shutil

import binascii, cStringIO

try:

    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):

    pass

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_FILECOUNT_LIMIT = 1 << 16

ZIP_MAX_COMMENT = (1 << 16) - 1

# constants for Zip file compression methods

ZIP_STORED = 0

ZIP_DEFLATED = 8

# 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)

_ECD_SIGNATURE = 0

_ECD_DISK_NUMBER = 1

_ECD_DISK_START = 2

_ECD_ENTRIES_THIS_DISK = 3

_ECD_ENTRIES_TOTAL = 4

_ECD_SIZE = 5

_ECD_OFFSET = 6

_ECD_COMMENT_SIZE = 7

# 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

_ECD_COMMENT = 8

_ECD_LOCATION = 9

# 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_SIGNATURE = 0

_CD_CREATE_VERSION = 1

_CD_CREATE_SYSTEM = 2

_CD_EXTRACT_VERSION = 3

_CD_EXTRACT_SYSTEM = 4

_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

# 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_SIGNATURE = 0

_FH_EXTRACT_VERSION = 1

_FH_EXTRACT_SYSTEM = 2

_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

# 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)

_CD64_SIGNATURE = 0

_CD64_DIRECTORY_RECSIZE = 1

_CD64_CREATE_VERSION = 2

_CD64_EXTRACT_VERSION = 3

_CD64_DISK_NUMBER = 4

_CD64_DISK_NUMBER_START = 5

_CD64_NUMBER_ENTRIES_THIS_DISK = 6

_CD64_NUMBER_ENTRIES_TOTAL = 7

_CD64_DIRECTORY_SIZE = 8

_CD64_OFFSET_START_CENTDIR = 9

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 _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_SIGNATURE] = sig

    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

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)

        endrec=list(endrec)

        # Append a blank comment and record start offset

        endrec.append("")

        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

        if endrec[_ECD_COMMENT_SIZE] == len(comment):

            # Append the archive comment and start offset

            endrec.append(comment)

            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

    return

class ZipInfo (object):

    """Class with attributes describing each file in the ZIP archive."""

    __slots__ = (

            'orig_filename',

            'filename',

            'date_time',

            'compress_type',

            'comment',

            'extra',

            'create_system',

            'create_version',

            'extract_version',

            'reserved',

            'flag_bits',

            'volume',

            'internal_attr',

            'external_attr',

            'header_offset',

            'CRC',

            'compress_size',

            'file_size',

            '_raw_time',

        )

    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

        else:

            # 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

        # 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

    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

        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):

            try:

                return self.filename.encode('ascii'), self.flag_bits

            except UnicodeEncodeError:

                return self.filename.encode('utf-8'), self.flag_bits | 0x800

        else:

            return self.filename, self.flag_bits

    def _decodeFilename(self):

        if self.flag_bits & 0x800:

            return self.filename.decode('utf-8')

        else:

            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 = ()

                else:

                    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:

                    old = self.header_offset

                    self.header_offset = counts[idx]

                    idx+=1

            extra = extra[ln+4:]

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.

    Usage:

        zd = _ZipDecrypter(mypwd)

        plain_char = zd(cypher_char)

        plain_text = map(zd, cypher_text)

    """

    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

                else:

                    crc = ((crc >> 1) & 0x7FFFFFFF)

            table[i] = crc

        return table

    crctable = _GenerateCRCTable()

    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:

            self._UpdateKeys(p)

    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)

    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)

        self._UpdateKeys(c)

        return c

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.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

    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)

        else:

            # no line break in buffer - try to read more

            size -= len(self.linebuffer)