""" Read and write ZIP files. XXX references to utf-8 need further investigation. """ import io import os import importlib.util import sys import time import stat import shutil import struct import binascii import threading if sys.version_info[0:2] < (3, 6): import pathlib try: import zlib # We may need its compression method crc32 = zlib.crc32 except ImportError: zlib = None crc32 = binascii.crc32 try: import bz2 # We may need its compression method except ImportError: bz2 = None try: import lzma # We may need its compression method except ImportError: lzma = None __all__ = ["BadZipFile", "BadZipfile", "error", "ZIP_STORED", "ZIP_DEFLATED", "ZIP_BZIP2", "ZIP_LZMA", "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 = BadZipFile # Pre-3.2 compatibility names ZIP64_LIMIT = (1 << 31) - 1 ZIP_FILECOUNT_LIMIT = (1 << 16) - 1 ZIP_MAX_COMMENT = (1 << 16) - 1 # constants for Zip file compression methods ZIP_STORED = 0 ZIP_DEFLATED = 8 ZIP_BZIP2 = 12 ZIP_LZMA = 14 # Other ZIP compression methods not supported DEFAULT_VERSION = 20 ZIP64_VERSION = 45 BZIP2_VERSION = 46 LZMA_VERSION = 63 # we recognize (but not necessarily support) all features up to that version MAX_EXTRACT_VERSION = 63 # Extensible data field codes: # Zip64 extended information extra field EXTRA_ZIP64 = 0x0001 # 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 = b"<4s4H2LH" stringEndArchive = b"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 = b"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 _MASK_ENCRYPTED = 1 << 0 _MASK_COMPRESS_OPTION_1 = 1 << 1 _MASK_COMPRESS_OPTION_2 = 1 << 2 _MASK_USE_DATA_DESCRIPTOR = 1 << 3 # Bit 4: Reserved for use with compression method 8, for enhanced deflating. _MASK_RESERVED_BIT_4 = 1 << 4 _MASK_COMPRESSED_PATCH = 1 << 5 _MASK_STRONG_ENCRYPTION = 1 << 6 _MASK_UNUSED_BIT_7 = 1 << 7 _MASK_UNUSED_BIT_8 = 1 << 8 _MASK_UNUSED_BIT_9 = 1 << 9 _MASK_UNUSED_BIT_10 = 1 << 10 _MASK_UTF_FILENAME = 1 << 11 # Bit 12: Reserved by PKWARE for enhanced compression. _MASK_RESERVED_BIT_12 = 1 << 12 _MASK_ENCRYPTED_CENTRAL_DIR = 1 << 13 # Bit 14, 15: Reserved by PKWARE _MASK_RESERVED_BIT_14 = 1 << 14 _MASK_RESERVED_BIT_15 = 1 << 15 # The "local file header" structure, magic number, size, and indices # (section V.A in the format document) structFileHeader = "<4s2B4HL2L2H" stringFileHeader = b"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 = b"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 = b"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 _DD_SIGNATURE = 0x08074b50 _EXTRA_FIELD_STRUCT = struct.Struct('= 0: # found the magic number; attempt to unpack and interpret recData = data[start:start+sizeEndCentDir] if len(recData) != sizeEndCentDir: # Zip file is corrupted. return None endrec = list(struct.unpack(structEndArchive, recData)) commentSize = endrec[_ECD_COMMENT_SIZE] # as claimed by the zip file comment = data[start+sizeEndCentDir:start+sizeEndCentDir+commentSize] endrec.append(comment) endrec.append(maxCommentStart + start) # Try to read the "Zip64 end of central directory" structure return _EndRecData64(fpin, maxCommentStart + start - filesize, endrec) # Unable to find a valid end of central directory structure return None class ZipInfo (object): """Class with attributes describing each file in the ZIP archive.""" __slots__ = ( 'orig_filename', 'filename', 'date_time', 'compress_type', '_compresslevel', '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 if date_time[0] < 1980: raise ValueError('ZIP does not support timestamps before 1980') # Standard values: self.compress_type = ZIP_STORED # Type of compression for the file self._compresslevel = None # Level for the compressor self.comment = b"" # Comment for each file self.extra = b"" # 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 = DEFAULT_VERSION # Version which created ZIP archive self.extract_version = DEFAULT_VERSION # 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 __repr__(self): result = ['<%s filename=%r' % (self.__class__.__name__, self.filename)] if self.compress_type != ZIP_STORED: result.append(' compress_type=%s' % compressor_names.get(self.compress_type, self.compress_type)) hi = self.external_attr >> 16 lo = self.external_attr & 0xFFFF if hi: result.append(' filemode=%r' % stat.filemode(hi)) if lo: result.append(' external_attr=%#x' % lo) isdir = self.is_dir() if not isdir or self.file_size: result.append(' file_size=%r' % self.file_size) if ((not isdir or self.compress_size) and (self.compress_type != ZIP_STORED or self.file_size != self.compress_size)): result.append(' compress_size=%r' % self.compress_size) result.append('>') return ''.join(result) @property def is_encrypted(self): return self.flag_bits & _MASK_ENCRYPTED @property def is_utf_filename(self): """Return True if filenames are encoded in UTF-8. Bit 11: Language encoding flag (EFS). If this bit is set, the filename and comment fields for this file MUST be encoded using UTF-8. """ return self.flag_bits & _MASK_UTF_FILENAME @property def is_compressed_patch_data(self): # Zip 2.7: compressed patched data return self.flag_bits & _MASK_COMPRESSED_PATCH @property def is_strong_encryption(self): return self.flag_bits & _MASK_STRONG_ENCRYPTION @property def use_datadescripter(self): """Returns True if datadescripter is in use. If bit 3 of flags is set, the data descripter is must exist. It is byte aligned and immediately follows the last byte of compressed data. crc-32 4 bytes compressed size 4 bytes uncompressed size 4 bytes """ return self.flag_bits & _MASK_USE_DATA_DESCRIPTOR def encode_datadescripter(self, zip64, crc, compress_size, file_size): fmt = ' ZIP64_LIMIT or compress_size > ZIP64_LIMIT if zip64 is None: zip64 = requires_zip64 if zip64: extra = struct.pack( ' ZIP64_LIMIT: zip64_fields.append(self.file_size) file_size = 0xffffffff else: file_size = self.file_size if self.compress_size > ZIP64_LIMIT: zip64_fields.append(self.compress_size) compress_size = 0xffffffff else: compress_size = self.compress_size if self.header_offset > ZIP64_LIMIT: zip64_fields.append(self.header_offset) header_offset = 0xffffffff else: header_offset = self.header_offset # For completeness - We don't support writing disks with multiple parts # so the number of disks is always going to be 0. Definitely not # more than 65,535. # ZIP64_DISK_LIMIT = (1 << 16) - 1 # if self.disk_start > ZIP64_DISK_LIMIT: # zip64_fields.append(self.disk_start) # disk_num = 0xffff # else: # header_offset = self.disk_start min_version = 0 if zip64_fields: extra = struct.pack( '= 4: tp, ln = struct.unpack(' len(extra): raise BadZipFile( "Corrupt extra field %04x (size=%d)" % (tp, ln) ) try: extra_decoders[tp](ln, extra) except KeyError: # We don't support this particular Extra Data field pass extra = extra[ln+4:] @classmethod def from_file(cls, filename, arcname=None, *, strict_timestamps=True): """Construct an appropriate ZipInfo for a file on the filesystem. filename should be the path to a file or directory on the filesystem. arcname is the name which it will have within the archive (by default, this will be the same as filename, but without a drive letter and with leading path separators removed). """ # os.PathLike and os.fspath were added in python 3.6 if sys.version_info[0:2] >= (3, 6): if isinstance(filename, os.PathLike): filename = os.fspath(filename) else: if isinstance(filename, pathlib.PurePath): filename = str(filename) st = os.stat(filename) isdir = stat.S_ISDIR(st.st_mode) mtime = time.localtime(st.st_mtime) date_time = mtime[0:6] if not strict_timestamps and date_time[0] < 1980: date_time = (1980, 1, 1, 0, 0, 0) elif not strict_timestamps and date_time[0] > 2107: date_time = (2107, 12, 31, 23, 59, 59) # 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:] if isdir: arcname += '/' zinfo = cls(arcname, date_time) zinfo.external_attr = (st.st_mode & 0xFFFF) << 16 # Unix attributes if isdir: zinfo.file_size = 0 zinfo.external_attr |= 0x10 # MS-DOS directory flag else: zinfo.file_size = st.st_size return zinfo def is_dir(self): """Return True if this archive member is a directory.""" return self.filename[-1] == '/' # 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(). _crctable = None def _gen_crc(crc): for j in range(8): if crc & 1: crc = (crc >> 1) ^ 0xEDB88320 else: crc >>= 1 return crc class BaseZipDecrypter: def decrypt(self, data): raise NotImplementedError( 'BaseZipDecrypter implementations must implement `decrypt`.' ) class CRCZipDecrypter(BaseZipDecrypter): """PKWARE Encryption Decrypter 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 = CRCZipDecrypter(zinfo, mypwd, encryption_header) plain_bytes = zd.decrypt(cypher_bytes) """ encryption_header_length = 12 def __init__(self, zinfo, pwd, encryption_header): self.key0 = 305419896 self.key1 = 591751049 self.key2 = 878082192 global _crctable if _crctable is None: _crctable = list(map(_gen_crc, range(256))) self.crctable = _crctable for p in pwd: self.update_keys(p) # 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. h = self.decrypt(encryption_header[0:12]) if zinfo.use_datadescripter: # compare against the file type from extended local headers check_byte = (zinfo._raw_time >> 8) & 0xff else: # compare against the CRC otherwise check_byte = (zinfo.CRC >> 24) & 0xff if h[11] != check_byte: raise RuntimeError("Bad password for file %r" % zinfo.filename) def crc32(self, ch, crc): """Compute the CRC32 primitive on one byte.""" return (crc >> 8) ^ self.crctable[(crc ^ ch) & 0xFF] def update_keys(self, c): self.key0 = self.crc32(c, self.key0) self.key1 = (self.key1 + (self.key0 & 0xFF)) & 0xFFFFFFFF self.key1 = (self.key1 * 134775813 + 1) & 0xFFFFFFFF self.key2 = self.crc32(self.key1 >> 24, self.key2) def decrypt(self, data): """Decrypt a bytes object.""" result = bytearray() append = result.append for c in data: k = self.key2 | 2 c ^= ((k * (k ^ 1)) >> 8) & 0xFF self.update_keys(c) append(c) return bytes(result) class LZMACompressor: # The LZMA SDK version is not related to the XZ Util's liblzma version that # the python library links to. The LZMA SDK is associated with the 7-zip # project by Igor Pavlov. If there is a breaking change in how the # properties are packed or their contents, these version identifiers can be # used to specify the strategy for decompression. While the version of the # LZMA SDK changes with each new version of 7zip, I don't believe there has # been any breaking changes since the version supplied here (but I haven't # spent much time confirming if that is true). LZMA_SDK_MAJOR_VERSION = 9 LZMA_SDK_MINOR_VERSION = 4 def __init__(self): self._comp = None def _init(self): props = lzma._encode_filter_properties({'id': lzma.FILTER_LZMA1}) self._comp = lzma.LZMACompressor(lzma.FORMAT_RAW, filters=[ lzma._decode_filter_properties(lzma.FILTER_LZMA1, props) ]) header = struct.pack( '') return ''.join(result) def readline(self, limit=-1): """Read and return a line from the stream. If limit is specified, at most limit bytes will be read. """ if limit < 0: # Shortcut common case - newline found in buffer. i = self._readbuffer.find(b'\n', self._offset) + 1 if i > 0: line = self._readbuffer[self._offset: i] self._offset = i return line return io.BufferedIOBase.readline(self, limit) def peek(self, n=1): """Returns buffered bytes without advancing the position.""" if n > len(self._readbuffer) - self._offset: chunk = self.read(n) if len(chunk) > self._offset: self._readbuffer = chunk + self._readbuffer[self._offset:] self._offset = 0 else: self._offset -= len(chunk) # Return up to 512 bytes to reduce allocation overhead for tight loops. return self._readbuffer[self._offset: self._offset + 512] def readable(self): return True def read(self, n=-1): """Read and return up to n bytes. If the argument is omitted, None, or negative, data is read and returned until EOF is reached. """ if n is None or n < 0: buf = self._readbuffer[self._offset:] self._readbuffer = b'' self._offset = 0 while not self._eof: buf += self._read1(self.MAX_N) return buf end = n + self._offset if end < len(self._readbuffer): buf = self._readbuffer[self._offset:end] self._offset = end return buf n = end - len(self._readbuffer) buf = self._readbuffer[self._offset:] self._readbuffer = b'' self._offset = 0 while n > 0 and not self._eof: data = self._read1(n) if n < len(data): self._readbuffer = data self._offset = n buf += data[:n] break buf += data n -= len(data) return buf def _update_crc(self, newdata): # Update the CRC using the given data. if self._expected_crc is None: # No need to compute the CRC if we don't have a reference value return self._running_crc = crc32(newdata, self._running_crc) def check_crc(self): if self._expected_crc is None: # No need to compute the CRC if we don't have a reference value return # Check the CRC if we're at the end of the file if self._eof and self._running_crc != self._expected_crc: raise BadZipFile("Bad CRC-32 for file %r" % self.name) def check_integrity(self): self.check_crc() def read1(self, n): """Read up to n bytes with at most one read() system call.""" if n is None or n < 0: buf = self._readbuffer[self._offset:] self._readbuffer = b'' self._offset = 0 while not self._eof: data = self._read1(self.MAX_N) if data: buf += data break return buf end = n + self._offset if end < len(self._readbuffer): buf = self._readbuffer[self._offset:end] self._offset = end return buf n = end - len(self._readbuffer) buf = self._readbuffer[self._offset:] self._readbuffer = b'' self._offset = 0 if n > 0: while not self._eof: data = self._read1(n) if n < len(data): self._readbuffer = data self._offset = n buf += data[:n] break if data: buf += data break return buf def _read1(self, n): # Read up to n compressed bytes with at most one read() system call, # decrypt and decompress them. if self._eof or n <= 0: return b'' # Read from file. if self._compress_type == ZIP_DEFLATED: # Handle unconsumed data. data = self._decompressor.unconsumed_tail if n > len(data): data += self._read2(n - len(data)) else: data = self._read2(n) if self._compress_type == ZIP_STORED: self._eof = self._compress_left <= 0 elif self._compress_type == ZIP_DEFLATED: n = max(n, self.MIN_READ_SIZE) data = self._decompressor.decompress(data, n) self._eof = (self._decompressor.eof or self._compress_left <= 0 and not self._decompressor.unconsumed_tail) if self._eof: data += self._decompressor.flush() else: data = self._decompressor.decompress(data) self._eof = self._decompressor.eof or self._compress_left <= 0 data = data[:self._left] self._left -= len(data) if self._left <= 0: self._eof = True self._update_crc(data) if self._eof: self.check_integrity() return data def _read2(self, n): if self._compress_left <= 0: return b'' n = max(n, self.MIN_READ_SIZE) n = min(n, self._compress_left) data = self._fileobj.read(n) self._compress_left -= len(data) if not data: raise EOFError if self._decrypter is not None: data = self._decrypter.decrypt(data) return data def close(self): try: if self._close_fileobj: self._fileobj.close() finally: super().close() def seekable(self): return self._seekable def seek(self, offset, whence=0): if not self._seekable: raise io.UnsupportedOperation("underlying stream is not seekable") curr_pos = self.tell() if whence == 0: # Seek from start of file new_pos = offset elif whence == 1: # Seek from current position new_pos = curr_pos + offset elif whence == 2: # Seek from EOF new_pos = self._zinfo.file_size + offset else: raise ValueError("whence must be os.SEEK_SET (0), " "os.SEEK_CUR (1), or os.SEEK_END (2)") if new_pos > self._zinfo.file_size: new_pos = self._zinfo.file_size if new_pos < 0: new_pos = 0 read_offset = new_pos - curr_pos buff_offset = read_offset + self._offset if buff_offset >= 0 and buff_offset < len(self._readbuffer): # Just move the _offset index if the new position is in the # _readbuffer self._offset = buff_offset read_offset = 0 elif read_offset < 0: # Position is before the current position. Reset the ZipExtFile self._fileobj.seek(self._compress_start) self.read_init() read_offset = new_pos while read_offset > 0: read_len = min(self.MAX_SEEK_READ, read_offset) self.read(read_len) read_offset -= read_len return self.tell() def tell(self): if not self._seekable: raise io.UnsupportedOperation("underlying stream is not seekable") filepos = ( self._zinfo.file_size - self._left - len(self._readbuffer) + self._offset ) return filepos class _ZipWriteFile(io.BufferedIOBase): def __init__(self, zf, zinfo, zip64, encrypter=None): self._zinfo = zinfo self._zip64 = zip64 self._zipfile = zf self._compressor = _get_compressor(zinfo.compress_type, zinfo._compresslevel) self._encrypter = encrypter self._file_size = 0 self._compress_size = 0 self._crc = 0 self.write_local_header() if self._encrypter: self.write_encryption_header() @property def _fileobj(self): return self._zipfile.fp def writable(self): return True def write_local_header(self): header = self._zinfo.FileHeader(self._zip64) # From this point onwards, we have likely altered the contents of the # file. self._zipfile._didModify = True self._zipfile._writing = True self._fileobj.write(header) def write_encryption_header(self): buf = self._encrypter.encryption_header() self._compress_size += len(buf) self._fileobj.write(buf) def write(self, data): if self.closed: raise ValueError('I/O operation on closed file.') nbytes = len(data) self._file_size += nbytes self._crc = crc32(data, self._crc) if self._compressor: data = self._compressor.compress(data) if self._encrypter: data = self._encrypter.encrypt(data) self._compress_size += len(data) self._fileobj.write(data) return nbytes def close(self): if self.closed: return super().close() # Flush any data from the compressor, and update header info if self._compressor: buf = self._compressor.flush() else: buf = b'' if self._encrypter: buf = self._encrypter.encrypt(buf) buf += self._encrypter.flush() self._compress_size += len(buf) self._fileobj.write(buf) self._zinfo.compress_size = self._compress_size self._zinfo.CRC = self._crc self._zinfo.file_size = self._file_size if not self._zip64: if self._file_size > ZIP64_LIMIT: raise RuntimeError('File size unexpectedly exceeded ZIP64 ' 'limit') if self._compress_size > ZIP64_LIMIT: raise RuntimeError('Compressed size unexpectedly exceeded ' 'ZIP64 limit') # Write updated header info if self._zinfo.use_datadescripter: # Write CRC and file sizes after the file data self._fileobj.write(self._zinfo.datadescripter(self._zip64)) self._zipfile.start_dir = self._fileobj.tell() else: # Seek backwards and write file header (which will now include # correct CRC and file sizes) # Preserve current position in file self._zipfile.start_dir = self._fileobj.tell() self._fileobj.seek(self._zinfo.header_offset) self._fileobj.write(self._zinfo.FileHeader(self._zip64)) self._fileobj.seek(self._zipfile.start_dir) self._zipfile._writing = False # Successfully written: Add file to our caches self._zipfile.filelist.append(self._zinfo) self._zipfile.NameToInfo[self._zinfo.filename] = self._zinfo class ZipFile: """ Class with methods to open, read, write, close, list zip files. z = ZipFile(file, mode="r", compression=ZIP_STORED, allowZip64=True, compresslevel=None) 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', exclusive create 'x', or append 'a'. compression: ZIP_STORED (no compression), ZIP_DEFLATED (requires zlib), ZIP_BZIP2 (requires bz2) or ZIP_LZMA (requires lzma). allowZip64: if True ZipFile will create files with ZIP64 extensions when needed, otherwise it will raise an exception when this would be necessary. compresslevel: None (default for the given compression type) or an integer specifying the level to pass to the compressor. When using ZIP_STORED or ZIP_LZMA this keyword has no effect. When using ZIP_DEFLATED integers 0 through 9 are accepted. When using ZIP_BZIP2 integers 1 through 9 are accepted. """ fp = None # Set here since __del__ checks it _windows_illegal_name_trans_table = None zipinfo_cls = ZipInfo zipextfile_cls = ZipExtFile zipwritefile_cls = _ZipWriteFile def __init__(self, file, mode="r", compression=ZIP_STORED, allowZip64=True, compresslevel=None, *, strict_timestamps=True): """Open the ZIP file with mode read 'r', write 'w', exclusive create 'x', or append 'a'.""" if mode not in ('r', 'w', 'x', 'a'): raise ValueError("ZipFile requires mode 'r', 'w', 'x', or 'a'") _check_compression(compression) 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.compression = compression # Method of compression self.compresslevel = compresslevel self.mode = mode self.pwd = None self.encryption = None self.encryption_kwargs = None self._comment = b'' self._strict_timestamps = strict_timestamps # Check if we were passed a file-like object # os.PathLike and os.fspath were added in python 3.6 if sys.version_info[0:2] >= (3, 6): if isinstance(file, os.PathLike): file = os.fspath(file) else: if isinstance(file, pathlib.PurePath): file = str(file) if isinstance(file, str): # No, it's a filename self._filePassed = 0 self.filename = file modeDict = {'r': 'rb', 'w': 'w+b', 'x': 'x+b', 'a': 'r+b', 'r+b': 'w+b', 'w+b': 'wb', 'x+b': 'xb'} filemode = modeDict[mode] while True: try: self.fp = io.open(file, filemode) except OSError: if filemode in modeDict: filemode = modeDict[filemode] continue raise break else: self._filePassed = 1 self.fp = file self.filename = getattr(file, 'name', None) self._fileRefCnt = 1 self._lock = threading.RLock() self._seekable = True self._writing = False try: if mode == 'r': self._RealGetContents() elif mode in ('w', 'x'): # set the modified flag so central directory gets written # even if no files are added to the archive self._didModify = True try: self.start_dir = self.fp.tell() except (AttributeError, OSError): self.fp = _Tellable(self.fp) self.start_dir = 0 self._seekable = False else: # Some file-like objects can provide tell() but not seek() try: self.fp.seek(self.start_dir) except (AttributeError, OSError): self._seekable = False elif mode == 'a': try: # See if file is a zip file self._RealGetContents() # seek to start of directory and overwrite self.fp.seek(self.start_dir) except BadZipFile: # file is not a zip file, just append self.fp.seek(0, 2) # set the modified flag so central directory gets written # even if no files are added to the archive self._didModify = True self.start_dir = self.fp.tell() else: raise ValueError("Mode must be 'r', 'w', 'x', or 'a'") except Exception as e: fp = self.fp self.fp = None self._fpclose(fp) raise e def __enter__(self): return self def __exit__(self, type, value, traceback): self.close() def __repr__(self): result = ['<%s.%s' % (self.__class__.__module__, self.__class__.__qualname__)] if self.fp is not None: if self._filePassed: result.append(' file=%r' % self.fp) elif self.filename is not None: result.append(' filename=%r' % self.filename) result.append(' mode=%r' % self.mode) else: result.append(' [closed]') result.append('>') return ''.join(result) def _RealGetContents(self): """Read in the table of contents for the ZIP file.""" fp = self.fp try: endrec = _EndRecData(fp) except OSError: raise BadZipFile("File is not a zip file") 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_SIGNATURE] == stringEndArchive64: # If Zip64 extension structures are present, 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 = io.BytesIO(data) total = 0 while total < size_cd: centdir = fp.read(sizeCentralDir) if len(centdir) != sizeCentralDir: raise BadZipFile("Truncated central directory") centdir = struct.unpack(structCentralDir, centdir) if centdir[_CD_SIGNATURE] != stringCentralDir: raise BadZipFile("Bad magic number for central directory") if self.debug > 2: print(centdir) filename = fp.read(centdir[_CD_FILENAME_LENGTH]) flags = centdir[5] if flags & _MASK_UTF_FILENAME: # UTF-8 file names extension filename = filename.decode('utf-8') else: # Historical ZIP filename encoding filename = filename.decode('cp437') # Create ZipInfo instance to store file information x = self.zipinfo_cls(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] if x.extract_version > MAX_EXTRACT_VERSION: raise NotImplementedError("zip file version %.1f" % (x.extract_version / 10)) 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._decodeExtra() x.header_offset = x.header_offset + concat self.filelist.append(x) 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 namelist(self): """Return a list of file names in the archive.""" return [data.filename for data in self.filelist] def infolist(self): """Return a list of class ZipInfo instances for files in the archive.""" return self.filelist def printdir(self, file=None): """Print a table of contents for the zip file.""" print("%-46s %19s %12s" % ("File Name", "Modified ", "Size"), file=file) 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), file=file) def testzip(self): """Read all the files and check the CRC.""" chunk_size = 2 ** 20 for zinfo in self.filelist: try: # Read by chunks, to avoid an OverflowError or a # MemoryError with very large embedded files. with self.open(zinfo.filename, "r") as f: while f.read(chunk_size): # Check CRC-32 pass except BadZipFile: return zinfo.filename 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 def setpassword(self, pwd): """Set default password for encrypted files.""" if pwd and not isinstance(pwd, bytes): raise TypeError("pwd: expected bytes, got %s" % type(pwd).__name__) if pwd: self.pwd = pwd else: self.pwd = None def setencryption(self, encryption, **kwargs): self.encryption = encryption self.encryption_kwargs = kwargs def get_encrypter(self): raise NotImplementedError("That encryption method is not supported") @property def comment(self): """The comment text associated with the ZIP file.""" return self._comment @comment.setter def comment(self, comment): if not isinstance(comment, bytes): raise TypeError( "comment: expected bytes, got %s" % type(comment).__name__ ) # check for valid comment length if len(comment) > ZIP_MAX_COMMENT: import warnings warnings.warn('Archive comment is too long; truncating to %d bytes' % ZIP_MAX_COMMENT, stacklevel=2) comment = comment[:ZIP_MAX_COMMENT] self._comment = comment self._didModify = True def read(self, name, pwd=None): """Return file bytes (as a string) for name.""" with self.open(name, "r", pwd) as fp: return fp.read() def open(self, name, mode="r", pwd=None, *, force_zip64=False): """Return file-like object for 'name'. name is a string for the file name within the ZIP file, or a ZipInfo object. mode should be 'r' to read a file already in the ZIP file, or 'w' to write to a file newly added to the archive. pwd is the password to encrypt and decrypt files. When writing, if the file size is not known in advance but may exceed 2 GiB, pass force_zip64 to use the ZIP64 format, which can handle large files. If the size is known in advance, it is best to pass a ZipInfo instance for name, with zinfo.file_size set. """ if mode not in {"r", "w"}: raise ValueError('open() requires mode "r" or "w"') if not self.fp: raise ValueError( "Attempt to use ZIP archive that was already closed") if not pwd: pwd = self.pwd if pwd and not isinstance(pwd, bytes): raise TypeError("pwd: expected bytes, got %s" % type(pwd).__name__) # Make sure we have an info object if isinstance(name, self.zipinfo_cls): # 'name' is already an info object zinfo = name elif mode == 'w': zinfo = self.zipinfo_cls(name) zinfo.compress_type = self.compression zinfo._compresslevel = self.compresslevel else: # Get info object for name zinfo = self.getinfo(name) if mode == 'w': return self._open_to_write(zinfo, force_zip64=force_zip64, pwd=pwd) if self._writing: raise ValueError("Can't read from the ZIP file while there " "is an open writing handle on it. " "Close the writing handle before trying to read.") return self._open_to_read(mode, zinfo, pwd) def _open_to_read(self, mode, zinfo, pwd): # Open for reading: self._fileRefCnt += 1 zef_file = _SharedFile(self.fp, zinfo.header_offset, self._fpclose, self._lock, lambda: self._writing) try: return self.zipextfile_cls(zef_file, mode, zinfo, True, pwd) except Exception as e: zef_file.close() raise e def _open_to_write(self, zinfo, force_zip64=False, pwd=None): if force_zip64 and not self._allowZip64: raise ValueError( "force_zip64 is True, but allowZip64 was False when opening " "the ZIP file." ) if self._writing: raise ValueError("Can't write to the ZIP file while there is " "another write handle open on it. " "Close the first handle before opening another.") # Sizes and CRC are overwritten with correct data after processing the # file if not hasattr(zinfo, 'file_size'): zinfo.file_size = 0 zinfo.compress_size = 0 zinfo.CRC = 0 zinfo.flag_bits = 0x00 encrypter = None if pwd is not None or self.encryption is not None: zinfo.flag_bits |= _MASK_ENCRYPTED encrypter = self.get_encrypter() encrypter.update_zipinfo(zinfo) if zinfo.compress_type == ZIP_LZMA: # Compressed data includes an end-of-stream (EOS) marker zinfo.flag_bits |= _MASK_COMPRESS_OPTION_1 if not self._seekable: zinfo.flag_bits |= _MASK_USE_DATA_DESCRIPTOR if not zinfo.external_attr: zinfo.external_attr = 0o600 << 16 # permissions: ?rw------- # Compressed size can be larger than uncompressed size zip64 = self._allowZip64 and \ (force_zip64 or zinfo.file_size * 1.05 > ZIP64_LIMIT) # noqa: E127 if self._seekable: self.fp.seek(self.start_dir) zinfo.header_offset = self.fp.tell() self._writecheck(zinfo) return self.zipwritefile_cls(self, zinfo, zip64, encrypter) 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 path is None: path = os.getcwd() else: # os.fspath were added in python 3.6 if sys.version_info[0:2] >= (3, 6): path = os.fspath(path) else: path = str(path) return self._extract_member(member, path, pwd) 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() if path is None: path = os.getcwd() else: # os.fspath were added in python 3.6 if sys.version_info[0:2] >= (3, 6): path = os.fspath(path) else: path = str(path) for zipinfo in members: self._extract_member(zipinfo, path, pwd) @classmethod def _sanitize_windows_name(cls, arcname, pathsep): """Replace bad characters and remove trailing dots from parts.""" table = cls._windows_illegal_name_trans_table if not table: illegal = ':<>|"?*' table = str.maketrans(illegal, '_' * len(illegal)) cls._windows_illegal_name_trans_table = table arcname = arcname.translate(table) # remove trailing dots arcname = (x.rstrip('.') for x in arcname.split(pathsep)) # rejoin, removing empty parts. arcname = pathsep.join(x for x in arcname if x) return arcname def _extract_member(self, member, targetpath, pwd): """Extract the ZipInfo object 'member' to a physical file on the path targetpath. """ if not isinstance(member, self.zipinfo_cls): member = self.getinfo(member) # build the destination pathname, replacing # forward slashes to platform specific separators. arcname = member.filename.replace('/', os.path.sep) if os.path.altsep: arcname = arcname.replace(os.path.altsep, os.path.sep) # interpret absolute pathname as relative, remove drive letter or # UNC path, redundant separators, "." and ".." components. arcname = os.path.splitdrive(arcname)[1] invalid_path_parts = ('', os.path.curdir, os.path.pardir) arcname = os.path.sep.join(x for x in arcname.split(os.path.sep) if x not in invalid_path_parts) if os.path.sep == '\\': # filter illegal characters on Windows arcname = self._sanitize_windows_name(arcname, os.path.sep) targetpath = os.path.join(targetpath, arcname) targetpath = os.path.normpath(targetpath) # Create all upper directories if necessary. upperdirs = os.path.dirname(targetpath) if upperdirs and not os.path.exists(upperdirs): os.makedirs(upperdirs) if member.is_dir(): if not os.path.isdir(targetpath): os.mkdir(targetpath) return targetpath with self.open(member, pwd=pwd) as source, \ open(targetpath, "wb") as target: shutil.copyfileobj(source, target) return targetpath def _writecheck(self, zinfo): """Check for errors before writing a file to the archive.""" if zinfo.filename in self.NameToInfo: import warnings warnings.warn('Duplicate name: %r' % zinfo.filename, stacklevel=3) if self.mode not in ('w', 'x', 'a'): raise ValueError("write() requires mode 'w', 'x', or 'a'") if not self.fp: raise ValueError( "Attempt to write ZIP archive that was already closed") _check_compression(zinfo.compress_type) if not self._allowZip64: requires_zip64 = None if len(self.filelist) >= ZIP_FILECOUNT_LIMIT: requires_zip64 = "Files count" elif zinfo.file_size > ZIP64_LIMIT: requires_zip64 = "Filesize" elif zinfo.header_offset > ZIP64_LIMIT: requires_zip64 = "Zipfile size" if requires_zip64: raise LargeZipFile(requires_zip64 + " would require ZIP64 extensions") def write(self, filename, arcname=None, compress_type=None, compresslevel=None): """Put the bytes from filename into the archive under the name arcname.""" if not self.fp: raise ValueError( "Attempt to write to ZIP archive that was already closed") if self._writing: raise ValueError( "Can't write to ZIP archive while an open writing handle exists" ) zinfo = self.zipinfo_cls.from_file( filename, arcname, strict_timestamps=self._strict_timestamps) if zinfo.is_dir(): zinfo.compress_size = 0 zinfo.CRC = 0 else: if compress_type is not None: zinfo.compress_type = compress_type else: zinfo.compress_type = self.compression if compresslevel is not None: zinfo._compresslevel = compresslevel else: zinfo._compresslevel = self.compresslevel if zinfo.is_dir(): with self._lock: if self._seekable: self.fp.seek(self.start_dir) zinfo.header_offset = self.fp.tell() # Start of header bytes if zinfo.compress_type == ZIP_LZMA: # Compressed data includes an end-of-stream (EOS) marker zinfo.flag_bits |= _MASK_COMPRESS_OPTION_1 self._writecheck(zinfo) self._didModify = True self.filelist.append(zinfo) self.NameToInfo[zinfo.filename] = zinfo self.fp.write(zinfo.FileHeader(False)) self.start_dir = self.fp.tell() else: with open(filename, "rb") as src, self.open(zinfo, 'w') as dest: shutil.copyfileobj(src, dest, 1024*8) def writestr(self, zinfo_or_arcname, data, compress_type=None, compresslevel=None): """Write a file into the archive. The contents is 'data', which may be either a 'str' or a 'bytes' instance; if it is a 'str', it is encoded as UTF-8 first. 'zinfo_or_arcname' is either a ZipInfo instance or the name of the file in the archive.""" if isinstance(data, str): data = data.encode("utf-8") if not isinstance(zinfo_or_arcname, self.zipinfo_cls): zinfo = self.zipinfo_cls( filename=zinfo_or_arcname, date_time=time.localtime(time.time())[:6]) zinfo.compress_type = self.compression zinfo._compresslevel = self.compresslevel if zinfo.filename[-1] == '/': zinfo.external_attr = 0o40775 << 16 # drwxrwxr-x zinfo.external_attr |= 0x10 # MS-DOS directory flag else: zinfo.external_attr = 0o600 << 16 # ?rw------- else: zinfo = zinfo_or_arcname if not self.fp: raise ValueError( "Attempt to write to ZIP archive that was already closed") if self._writing: raise ValueError( "Can't write to ZIP archive while an open writing handle exists." ) if compress_type is not None: zinfo.compress_type = compress_type if compresslevel is not None: zinfo._compresslevel = compresslevel zinfo.file_size = len(data) # Uncompressed size with self._lock: with self.open(zinfo, mode='w') as dest: dest.write(data) def __del__(self): """Call the "close()" method in case the user forgot.""" self.close() def close(self): """Close the file, and for mode 'w', 'x' and 'a' write the ending records.""" if self.fp is None: return if self._writing: raise ValueError("Can't close the ZIP file while there is " "an open writing handle on it. " "Close the writing handle before closing the zip.") try: if self.mode in ('w', 'x', 'a') and self._didModify: # write ending records with self._lock: if self._seekable: self.fp.seek(self.start_dir) self._write_end_record() finally: fp = self.fp self.fp = None self._fpclose(fp) def _write_end_record(self): for zinfo in self.filelist: # write central directory centdir, filename, extra_data = zinfo.central_directory() self.fp.write(centdir) self.fp.write(filename) self.fp.write(extra_data) self.fp.write(zinfo.comment) pos2 = self.fp.tell() # Write end-of-zip-archive record centDirCount = len(self.filelist) centDirSize = pos2 - self.start_dir centDirOffset = self.start_dir requires_zip64 = None if centDirCount > ZIP_FILECOUNT_LIMIT: requires_zip64 = "Files count" elif centDirOffset > ZIP64_LIMIT: requires_zip64 = "Central directory offset" elif centDirSize > ZIP64_LIMIT: requires_zip64 = "Central directory size" if requires_zip64: # Need to write the ZIP64 end-of-archive records if not self._allowZip64: raise LargeZipFile(requires_zip64 + " would require ZIP64 extensions") zip64endrec = struct.pack( structEndArchive64, stringEndArchive64, 44, 45, 45, 0, 0, centDirCount, centDirCount, centDirSize, centDirOffset) self.fp.write(zip64endrec) zip64locrec = struct.pack( structEndArchive64Locator, stringEndArchive64Locator, 0, pos2, 1) self.fp.write(zip64locrec) centDirCount = min(centDirCount, 0xFFFF) centDirSize = min(centDirSize, 0xFFFFFFFF) centDirOffset = min(centDirOffset, 0xFFFFFFFF) endrec = struct.pack(structEndArchive, stringEndArchive, 0, 0, centDirCount, centDirCount, centDirSize, centDirOffset, len(self._comment)) self.fp.write(endrec) self.fp.write(self._comment) self.fp.flush() def _fpclose(self, fp): assert self._fileRefCnt > 0 self._fileRefCnt -= 1 if not self._fileRefCnt and not self._filePassed: fp.close() class PyZipFile(ZipFile): """Class to create ZIP archives with Python library files and packages.""" def __init__(self, file, mode="r", compression=ZIP_STORED, allowZip64=True, optimize=-1): if sys.version_info[0:2] < (3, 5): raise NotImplementedError( "pyzipper.PyZipFile doesn't work for versions less than 3.5" ) ZipFile.__init__(self, file, mode=mode, compression=compression, allowZip64=allowZip64) self._optimize = optimize def writepy(self, pathname, basename="", filterfunc=None): """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.pyc. This method will compile the module.py into module.pyc if necessary. If filterfunc(pathname) is given, it is called with every argument. When it is False, the file or directory is skipped. """ # os.fspath were added in python 3.6 if sys.version_info[0:2] >= (3, 6): pathname = os.fspath(pathname) else: pathname = str(pathname) if filterfunc and not filterfunc(pathname): if self.debug: label = 'path' if os.path.isdir(pathname) else 'file' print('%s %r skipped by filterfunc' % (label, pathname)) return 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 = sorted(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, filterfunc=filterfunc) # Recursive call elif ext == ".py": if filterfunc and not filterfunc(path): if self.debug: print('file %r skipped by filterfunc' % path) continue 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 sorted(os.listdir(pathname)): path = os.path.join(pathname, filename) root, ext = os.path.splitext(filename) if ext == ".py": if filterfunc and not filterfunc(path): if self.debug: print('file %r skipped by filterfunc' % path) continue 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). """ def _compile(file, optimize=-1): import py_compile if self.debug: print("Compiling", file) try: py_compile.compile(file, doraise=True, optimize=optimize) except py_compile.PyCompileError as err: print(err.msg) return False return True file_py = pathname + ".py" file_pyc = pathname + ".pyc" pycache_opt0 = importlib.util.cache_from_source(file_py, optimization='') pycache_opt1 = importlib.util.cache_from_source(file_py, optimization=1) pycache_opt2 = importlib.util.cache_from_source(file_py, optimization=2) if self._optimize == -1: # legacy mode: use whatever file is present if (os.path.isfile(file_pyc) and os.stat(file_pyc).st_mtime >= os.stat(file_py).st_mtime): # Use .pyc file. arcname = fname = file_pyc elif (os.path.isfile(pycache_opt0) and os.stat(pycache_opt0).st_mtime >= os.stat(file_py).st_mtime): # Use the __pycache__/*.pyc file, but write it to the legacy pyc # file name in the archive. fname = pycache_opt0 arcname = file_pyc elif (os.path.isfile(pycache_opt1) and os.stat(pycache_opt1).st_mtime >= os.stat(file_py).st_mtime): # Use the __pycache__/*.pyc file, but write it to the legacy pyc # file name in the archive. fname = pycache_opt1 arcname = file_pyc elif (os.path.isfile(pycache_opt2) and os.stat(pycache_opt2).st_mtime >= os.stat(file_py).st_mtime): # Use the __pycache__/*.pyc file, but write it to the legacy pyc # file name in the archive. fname = pycache_opt2 arcname = file_pyc else: # Compile py into PEP 3147 pyc file. if _compile(file_py): if sys.flags.optimize == 0: fname = pycache_opt0 elif sys.flags.optimize == 1: fname = pycache_opt1 else: fname = pycache_opt2 arcname = file_pyc else: fname = arcname = file_py else: # new mode: use given optimization level if self._optimize == 0: fname = pycache_opt0 arcname = file_pyc else: arcname = file_pyc if self._optimize == 1: fname = pycache_opt1 elif self._optimize == 2: fname = pycache_opt2 else: msg = "invalid value for 'optimize': {!r}".format(self._optimize) raise ValueError(msg) if not (os.path.isfile(fname) and os.stat(fname).st_mtime >= os.stat(file_py).st_mtime): if not _compile(file_py, optimize=self._optimize): fname = arcname = file_py archivename = os.path.split(arcname)[1] if basename: archivename = "%s/%s" % (basename, archivename) return (fname, archivename) def main(args=None): import argparse description = 'A simple command-line interface for zipfile module.' parser = argparse.ArgumentParser(description=description) group = parser.add_mutually_exclusive_group(required=True) group.add_argument('-l', '--list', metavar='', help='Show listing of a zipfile') group.add_argument('-e', '--extract', nargs=2, metavar=('', ''), help='Extract zipfile into target dir') group.add_argument('-c', '--create', nargs='+', metavar=('', ''), help='Create zipfile from sources') group.add_argument('-t', '--test', metavar='', help='Test if a zipfile is valid') args = parser.parse_args(args) if args.test is not None: src = args.test with ZipFile(src, 'r') as zf: badfile = zf.testzip() if badfile: print("The following enclosed file is corrupted: {!r}".format(badfile)) print("Done testing") elif args.list is not None: src = args.list with ZipFile(src, 'r') as zf: zf.printdir() elif args.extract is not None: src, curdir = args.extract with ZipFile(src, 'r') as zf: zf.extractall(curdir) elif args.create is not None: zip_name = args.create.pop(0) files = args.create def addToZip(zf, path, zippath): if os.path.isfile(path): zf.write(path, zippath, ZIP_DEFLATED) elif os.path.isdir(path): if zippath: zf.write(path, zippath) for nm in sorted(os.listdir(path)): addToZip(zf, os.path.join(path, nm), os.path.join(zippath, nm)) # else: ignore with ZipFile(zip_name, 'w') as zf: for path in files: zippath = os.path.basename(path) if not zippath: zippath = os.path.basename(os.path.dirname(path)) if zippath in ('', os.curdir, os.pardir): zippath = '' addToZip(zf, path, zippath) if __name__ == "__main__": main()