""" Read and write ZIP files. XXX references to utf-8 need further investigation. """ import binascii import importlib.util import io import os import shutil import stat import struct import sys import threading import time 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", "Path"] 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 # 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 # General purpose bit flags # Zip Appnote: 4.4.4 general purpose bit flag: (2 bytes) _MASK_ENCRYPTED = 1 << 0 # Bits 1 and 2 have different meanings depending on the compression used. _MASK_COMPRESS_OPTION_1 = 1 << 1 # _MASK_COMPRESS_OPTION_2 = 1 << 2 # _MASK_USE_DATA_DESCRIPTOR: If set, crc-32, compressed size and uncompressed # size are zero in the local header and the real values are written in the data # descriptor immediately following the compressed data. _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 class _Extra(bytes): FIELD_STRUCT = struct.Struct(' 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) if len(data) != sizeEndCentDir64: return endrec 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). try: fpin.seek(-sizeEndCentDir, 2) except OSError: return None data = fpin.read() if (len(data) == sizeEndCentDir and data[0:4] == stringEndArchive and data[-2:] == b"\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(b"") endrec.append(filesize - sizeEndCentDir) # Try to read the "Zip64 end of central directory" structure return _EndRecData64(fpin, -sizeEndCentDir, 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] 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 def _sanitize_filename(filename): """Terminate the file name at the first null byte and ensure paths always use forward slashes as the directory separator.""" # 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, "/") if os.altsep and os.altsep != "/" and os.altsep in filename: filename = filename.replace(os.altsep, "/") return filename 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 and # ensure paths always use forward slashes as the directory separator. filename = _sanitize_filename(filename) 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 self.compress_size = 0 # Size of the compressed file self.file_size = 0 # Size of the uncompressed file # Other attributes are set by class ZipFile: # header_offset Byte offset to the file header # CRC CRC-32 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) def FileHeader(self, zip64=None): """Return the per-file header as a bytes object. When the optional zip64 arg is None rather than a bool, we will decide based upon the file_size and compress_size, if known, False otherwise. """ 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 & _MASK_USE_DATA_DESCRIPTOR: # 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 min_version = 0 if zip64 is None: # We always explicitly pass zip64 within this module.... This # remains for anyone using ZipInfo.FileHeader as a public API. zip64 = file_size > ZIP64_LIMIT or compress_size > ZIP64_LIMIT if zip64: fmt = '= 4: tp, ln = unpack(' len(extra): raise BadZipFile("Corrupt extra field %04x (size=%d)" % (tp, ln)) if tp == 0x0001: data = extra[4:ln+4] # ZIP64 extension (large files and/or large archives) try: if self.file_size in (0xFFFF_FFFF_FFFF_FFFF, 0xFFFF_FFFF): field = "File size" self.file_size, = unpack(' 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.endswith('/') # 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 # 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_bytes = zd(cypher_bytes) def _ZipDecrypter(pwd): key0 = 305419896 key1 = 591751049 key2 = 878082192 global _crctable if _crctable is None: _crctable = list(map(_gen_crc, range(256))) crctable = _crctable def crc32(ch, crc): """Compute the CRC32 primitive on one byte.""" return (crc >> 8) ^ crctable[(crc ^ ch) & 0xFF] def update_keys(c): nonlocal key0, key1, key2 key0 = crc32(c, key0) key1 = (key1 + (key0 & 0xFF)) & 0xFFFFFFFF key1 = (key1 * 134775813 + 1) & 0xFFFFFFFF key2 = crc32(key1 >> 24, key2) for p in pwd: update_keys(p) def decrypter(data): """Decrypt a bytes object.""" result = bytearray() append = result.append for c in data: k = key2 | 2 c ^= ((k * (k^1)) >> 8) & 0xFF update_keys(c) append(c) return bytes(result) return decrypter class LZMACompressor: 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) ]) return struct.pack('> 8) & 0xff else: # compare against the CRC otherwise check_byte = (zipinfo.CRC >> 24) & 0xff h = self._init_decrypter() if h != check_byte: raise RuntimeError("Bad password for file %r" % zipinfo.orig_filename) def _init_decrypter(self): self._decrypter = _ZipDecrypter(self._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. header = self._fileobj.read(12) self._compress_left -= 12 return self._decrypter(header)[11] def __repr__(self): result = ['<%s.%s' % (self.__class__.__module__, self.__class__.__qualname__)] if not self.closed: result.append(' name=%r mode=%r' % (self.name, self.mode)) if self._compress_type != ZIP_STORED: result.append(' compress_type=%s' % compressor_names.get(self._compress_type, self._compress_type)) else: result.append(' [closed]') result.append('>') 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): if self.closed: raise ValueError("I/O operation on closed file.") 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 self.closed: raise ValueError("read from closed file.") 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) # 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 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) 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(data) return data def close(self): try: if self._close_fileobj: self._fileobj.close() finally: super().close() def seekable(self): if self.closed: raise ValueError("I/O operation on closed file.") return self._seekable def seek(self, offset, whence=os.SEEK_SET): if self.closed: raise ValueError("seek on closed file.") if not self._seekable: raise io.UnsupportedOperation("underlying stream is not seekable") curr_pos = self.tell() if whence == os.SEEK_SET: new_pos = offset elif whence == os.SEEK_CUR: new_pos = curr_pos + offset elif whence == os.SEEK_END: new_pos = self._orig_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._orig_file_size: new_pos = self._orig_file_size if new_pos < 0: new_pos = 0 read_offset = new_pos - curr_pos buff_offset = read_offset + self._offset # Fast seek uncompressed unencrypted file if self._compress_type == ZIP_STORED and self._decrypter is None and read_offset > 0: # disable CRC checking after first seeking - it would be invalid self._expected_crc = None # seek actual file taking already buffered data into account read_offset -= len(self._readbuffer) - self._offset self._fileobj.seek(read_offset, os.SEEK_CUR) self._left -= read_offset read_offset = 0 # flush read buffer self._readbuffer = b'' self._offset = 0 elif 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._orig_compress_start) self._running_crc = self._orig_start_crc self._expected_crc = self._orig_crc self._compress_left = self._orig_compress_size self._left = self._orig_file_size self._readbuffer = b'' self._offset = 0 self._decompressor = _get_decompressor(self._compress_type) self._eof = False read_offset = new_pos if self._decrypter is not None: self._init_decrypter() 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 self.closed: raise ValueError("tell on closed file.") if not self._seekable: raise io.UnsupportedOperation("underlying stream is not seekable") filepos = self._orig_file_size - self._left - len(self._readbuffer) + self._offset return filepos class _ZipWriteFile(io.BufferedIOBase): def __init__(self, zf, zinfo, zip64): self._zinfo = zinfo self._zip64 = zip64 self._zipfile = zf self._compressor = _get_compressor(zinfo.compress_type, zinfo._compresslevel) self._file_size = 0 self._compress_size = 0 self._crc = 0 @property def _fileobj(self): return self._zipfile.fp def writable(self): return True def write(self, data): if self.closed: raise ValueError('I/O operation on closed file.') # Accept any data that supports the buffer protocol if isinstance(data, (bytes, bytearray)): nbytes = len(data) else: data = memoryview(data) nbytes = data.nbytes self._file_size += nbytes self._crc = crc32(data, self._crc) if self._compressor: data = self._compressor.compress(data) self._compress_size += len(data) self._fileobj.write(data) return nbytes def close(self): if self.closed: return try: super().close() # Flush any data from the compressor, and update header info if self._compressor: buf = self._compressor.flush() self._compress_size += len(buf) self._fileobj.write(buf) self._zinfo.compress_size = self._compress_size else: self._zinfo.compress_size = self._file_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 too large, try using force_zip64") if self._compress_size > ZIP64_LIMIT: raise RuntimeError("Compressed size too large, try using force_zip64") # Write updated header info if self._zinfo.flag_bits & _MASK_USE_DATA_DESCRIPTOR: # Write CRC and file sizes after the file data fmt = '') 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 if self.start_dir < 0: raise BadZipFile("Bad offset for central directory") 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]) orig_filename_crc = crc32(filename) flags = centdir[_CD_FLAG_BITS] if flags & _MASK_UTF_FILENAME: # UTF-8 file names extension filename = filename.decode('utf-8') else: # Historical ZIP filename encoding filename = filename.decode(self.metadata_encoding or 'cp437') # 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] 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(orig_filename_crc) 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. Return None if all files could be read successfully, or the name of the offending file otherwise.""" 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 @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 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 decrypt files (only used for reading). 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 pwd and (mode == "w"): raise ValueError("pwd is only supported for reading files") if not self.fp: raise ValueError( "Attempt to use ZIP archive that was already closed") # Make sure we have an info object if isinstance(name, ZipInfo): # 'name' is already an info object zinfo = name elif mode == 'w': zinfo = ZipInfo(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) 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.") # Open for reading: self._fileRefCnt += 1 zef_file = _SharedFile(self.fp, zinfo.header_offset, self._fpclose, self._lock, lambda: self._writing) try: # Skip the file header: fheader = zef_file.read(sizeFileHeader) if len(fheader) != sizeFileHeader: raise BadZipFile("Truncated file header") fheader = struct.unpack(structFileHeader, fheader) if fheader[_FH_SIGNATURE] != stringFileHeader: raise BadZipFile("Bad magic number for file header") fname = zef_file.read(fheader[_FH_FILENAME_LENGTH]) if fheader[_FH_EXTRA_FIELD_LENGTH]: zef_file.seek(fheader[_FH_EXTRA_FIELD_LENGTH], whence=1) if zinfo.flag_bits & _MASK_COMPRESSED_PATCH: # Zip 2.7: compressed patched data raise NotImplementedError("compressed patched data (flag bit 5)") if zinfo.flag_bits & _MASK_STRONG_ENCRYPTION: # strong encryption raise NotImplementedError("strong encryption (flag bit 6)") if fheader[_FH_GENERAL_PURPOSE_FLAG_BITS] & _MASK_UTF_FILENAME: # UTF-8 filename fname_str = fname.decode("utf-8") else: fname_str = fname.decode(self.metadata_encoding or "cp437") if fname_str != zinfo.orig_filename: raise BadZipFile( 'File name in directory %r and header %r differ.' % (zinfo.orig_filename, fname)) # check for encrypted flag & handle password is_encrypted = zinfo.flag_bits & _MASK_ENCRYPTED if is_encrypted: if not pwd: pwd = self.pwd if pwd and not isinstance(pwd, bytes): raise TypeError("pwd: expected bytes, got %s" % type(pwd).__name__) if not pwd: raise RuntimeError("File %r is encrypted, password " "required for extraction" % name) else: pwd = None return ZipExtFile(zef_file, mode, zinfo, pwd, True) except: zef_file.close() raise def _open_to_write(self, zinfo, force_zip64=False): 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.") # Size and CRC are overwritten with correct data after processing the file zinfo.compress_size = 0 zinfo.CRC = 0 zinfo.flag_bits = 0x00 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 = force_zip64 or (zinfo.file_size * 1.05 > ZIP64_LIMIT) if not self._allowZip64 and zip64: raise LargeZipFile("Filesize would require ZIP64 extensions") if self._seekable: self.fp.seek(self.start_dir) zinfo.header_offset = self.fp.tell() self._writecheck(zinfo) self._didModify = True self.fp.write(zinfo.FileHeader(zip64)) self._writing = True return _ZipWriteFile(self, zinfo, zip64) 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: path = os.fspath(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: path = os.fspath(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 and spaces 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, ZipInfo): 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) if not arcname: raise ValueError("Empty filename.") 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 = ZipInfo.from_file(filename, arcname, strict_timestamps=self._strict_timestamps) if zinfo.is_dir(): zinfo.compress_size = 0 zinfo.CRC = 0 self.mkdir(zinfo) 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 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, ZipInfo): zinfo = ZipInfo(filename=zinfo_or_arcname, date_time=time.localtime(time.time())[:6]) zinfo.compress_type = self.compression zinfo._compresslevel = self.compresslevel if zinfo.filename.endswith('/'): 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 mkdir(self, zinfo_or_directory_name, mode=511): """Creates a directory inside the zip archive.""" if isinstance(zinfo_or_directory_name, ZipInfo): zinfo = zinfo_or_directory_name if not zinfo.is_dir(): raise ValueError("The given ZipInfo does not describe a directory") elif isinstance(zinfo_or_directory_name, str): directory_name = zinfo_or_directory_name if not directory_name.endswith("/"): directory_name += "/" zinfo = ZipInfo(directory_name) zinfo.compress_size = 0 zinfo.CRC = 0 zinfo.external_attr = ((0o40000 | mode) & 0xFFFF) << 16 zinfo.file_size = 0 zinfo.external_attr |= 0x10 else: raise TypeError("Expected type str or ZipInfo") 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() 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 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: extra.append(zinfo.file_size) extra.append(zinfo.compress_size) file_size = 0xffffffff compress_size = 0xffffffff else: file_size = zinfo.file_size compress_size = zinfo.compress_size if zinfo.header_offset > ZIP64_LIMIT: extra.append(zinfo.header_offset) header_offset = 0xffffffff else: header_offset = zinfo.header_offset extra_data = zinfo.extra min_version = 0 if extra: # Append a ZIP64 field to the extra's extra_data = _Extra.strip(extra_data, (1,)) extra_data = struct.pack( ' 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) if self.mode == "a": self.fp.truncate() 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): 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. """ pathname = os.fspath(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) from ._path import ( # noqa: E402 Path, # used privately for tests CompleteDirs, # noqa: F401 ) # used privately for tests from .__main__ import main # noqa: F401, E402