def _unmarshal_code(pathname, data, mtime): if len(data) < 16: raise ZipImportError('bad pyc data') if data[:4] != _bootstrap_external.MAGIC_NUMBER: _bootstrap._verbose_message('{!r} has bad magic', pathname) return None # signal caller to try alternative flags = _unpack_uint32(data[4:8]) if flags != 0: # Hash-based pyc. We currently refuse to handle checked hash-based # pycs. We could validate hash-based pycs against the source, but it # seems likely that most people putting hash-based pycs in a zipfile # will use unchecked ones. if (_imp.check_hash_based_pycs != 'never' and (flags != 0x1 or _imp.check_hash_based_pycs == 'always')): return None elif mtime != 0 and not _eq_mtime(_unpack_uint32(data[8:12]), mtime): _bootstrap._verbose_message('{!r} has bad mtime', pathname) return None # signal caller to try alternative # XXX the pyc's size field is ignored; timestamp collisions are probably # unimportant with zip files. code = marshal.loads(data[16:]) if not isinstance(code, _code_type): raise TypeError(f'compiled module {pathname!r} is not a code object') return code
def _unmarshal_code(self, pathname, fullpath, fullname, data): exc_details = { 'name': fullname, 'path': fullpath, } try: flags = _bootstrap_external._classify_pyc(data, fullname, exc_details) except ImportError: return None hash_based = flags & 0b1 != 0 if hash_based: check_source = flags & 0b10 != 0 if (_imp.check_hash_based_pycs != 'never' and (check_source or _imp.check_hash_based_pycs == 'always')): source_bytes = _get_pyc_source(self, fullpath) if source_bytes is not None: source_hash = _imp.source_hash( _bootstrap_external._RAW_MAGIC_NUMBER, source_bytes, ) try: _boostrap_external._validate_hash_pyc( data, source_hash, fullname, exc_details) except ImportError: return None else: source_mtime, source_size = \ _get_mtime_and_size_of_source(self, fullpath) if source_mtime: # We don't use _bootstrap_external._validate_timestamp_pyc # to allow for a more lenient timestamp check. if (not _eq_mtime(_unpack_uint32(data[8:12]), source_mtime) or _unpack_uint32(data[12:16]) != source_size): _bootstrap._verbose_message( f'bytecode is stale for {fullname!r}') return None code = marshal.loads(data[16:]) if not isinstance(code, _code_type): raise TypeError(f'compiled module {pathname!r} is not a code object') return code
def _read_directory(archive): try: fp = _io.open_code(archive) except OSError: raise ZipImportError(f"can't open Zip file: {archive!r}", path=archive) with fp: try: fp.seek(-END_CENTRAL_DIR_SIZE, 2) header_position = fp.tell() buffer = fp.read(END_CENTRAL_DIR_SIZE) except OSError: raise ZipImportError(f"can't read Zip file: {archive!r}", path=archive) if len(buffer) != END_CENTRAL_DIR_SIZE: raise ZipImportError(f"can't read Zip file: {archive!r}", path=archive) if buffer[:4] != STRING_END_ARCHIVE: # Bad: End of Central Dir signature # Check if there's a comment. try: fp.seek(0, 2) file_size = fp.tell() except OSError: raise ZipImportError(f"can't read Zip file: {archive!r}", path=archive) max_comment_start = max( file_size - MAX_COMMENT_LEN - END_CENTRAL_DIR_SIZE, 0) try: fp.seek(max_comment_start) data = fp.read() except OSError: raise ZipImportError(f"can't read Zip file: {archive!r}", path=archive) pos = data.rfind(STRING_END_ARCHIVE) if pos < 0: raise ZipImportError(f'not a Zip file: {archive!r}', path=archive) buffer = data[pos:pos + END_CENTRAL_DIR_SIZE] if len(buffer) != END_CENTRAL_DIR_SIZE: raise ZipImportError(f"corrupt Zip file: {archive!r}", path=archive) header_position = file_size - len(data) + pos header_size = _unpack_uint32(buffer[12:16]) header_offset = _unpack_uint32(buffer[16:20]) if header_position < header_size: raise ZipImportError(f'bad central directory size: {archive!r}', path=archive) if header_position < header_offset: raise ZipImportError(f'bad central directory offset: {archive!r}', path=archive) header_position -= header_size arc_offset = header_position - header_offset if arc_offset < 0: raise ZipImportError( f'bad central directory size or offset: {archive!r}', path=archive) files = {} # Start of Central Directory count = 0 try: fp.seek(header_position) except OSError: raise ZipImportError(f"can't read Zip file: {archive!r}", path=archive) while True: buffer = fp.read(46) if len(buffer) < 4: raise EOFError('EOF read where not expected') # Start of file header if buffer[:4] != b'PK\x01\x02': break # Bad: Central Dir File Header if len(buffer) != 46: raise EOFError('EOF read where not expected') flags = _unpack_uint16(buffer[8:10]) compress = _unpack_uint16(buffer[10:12]) time = _unpack_uint16(buffer[12:14]) date = _unpack_uint16(buffer[14:16]) crc = _unpack_uint32(buffer[16:20]) data_size = _unpack_uint32(buffer[20:24]) file_size = _unpack_uint32(buffer[24:28]) name_size = _unpack_uint16(buffer[28:30]) extra_size = _unpack_uint16(buffer[30:32]) comment_size = _unpack_uint16(buffer[32:34]) file_offset = _unpack_uint32(buffer[42:46]) header_size = name_size + extra_size + comment_size if file_offset > header_offset: raise ZipImportError(f'bad local header offset: {archive!r}', path=archive) file_offset += arc_offset try: name = fp.read(name_size) except OSError: raise ZipImportError(f"can't read Zip file: {archive!r}", path=archive) if len(name) != name_size: raise ZipImportError(f"can't read Zip file: {archive!r}", path=archive) # On Windows, calling fseek to skip over the fields we don't use is # slower than reading the data because fseek flushes stdio's # internal buffers. See issue #8745. try: if len(fp.read(header_size - name_size)) != header_size - name_size: raise ZipImportError(f"can't read Zip file: {archive!r}", path=archive) except OSError: raise ZipImportError(f"can't read Zip file: {archive!r}", path=archive) if flags & 0x800: # UTF-8 file names extension name = name.decode() else: # Historical ZIP filename encoding try: name = name.decode('ascii') except UnicodeDecodeError: name = name.decode('latin1').translate(cp437_table) name = name.replace('/', path_sep) path = _bootstrap_external._path_join(archive, name) t = (path, compress, data_size, file_size, file_offset, time, date, crc) files[name] = t count += 1 _bootstrap._verbose_message('zipimport: found {} names in {!r}', count, archive) return files
def _read_directory(archive): try: fp = _io.open(archive, 'rb') except OSError: raise ZipImportError(f"can't open Zip file: {archive!r}", path=archive) with fp: try: fp.seek(-END_CENTRAL_DIR_SIZE, 2) header_position = fp.tell() buffer = fp.read(END_CENTRAL_DIR_SIZE) except OSError: raise ZipImportError(f"can't read Zip file: {archive!r}", path=archive) if len(buffer) != END_CENTRAL_DIR_SIZE: raise ZipImportError(f"can't read Zip file: {archive!r}", path=archive) if buffer[:4] != STRING_END_ARCHIVE: # Bad: End of Central Dir signature # Check if there's a comment. try: fp.seek(0, 2) file_size = fp.tell() except OSError: raise ZipImportError(f"can't read Zip file: {archive!r}", path=archive) max_comment_start = max(file_size - MAX_COMMENT_LEN - END_CENTRAL_DIR_SIZE, 0) try: fp.seek(max_comment_start) data = fp.read() except OSError: raise ZipImportError(f"can't read Zip file: {archive!r}", path=archive) pos = data.rfind(STRING_END_ARCHIVE) if pos < 0: raise ZipImportError(f'not a Zip file: {archive!r}', path=archive) buffer = data[pos:pos+END_CENTRAL_DIR_SIZE] if len(buffer) != END_CENTRAL_DIR_SIZE: raise ZipImportError(f"corrupt Zip file: {archive!r}", path=archive) header_position = file_size - len(data) + pos header_size = _unpack_uint32(buffer[12:16]) header_offset = _unpack_uint32(buffer[16:20]) if header_position < header_size: raise ZipImportError(f'bad central directory size: {archive!r}', path=archive) if header_position < header_offset: raise ZipImportError(f'bad central directory offset: {archive!r}', path=archive) header_position -= header_size arc_offset = header_position - header_offset if arc_offset < 0: raise ZipImportError(f'bad central directory size or offset: {archive!r}', path=archive) files = {} # Start of Central Directory count = 0 try: fp.seek(header_position) except OSError: raise ZipImportError(f"can't read Zip file: {archive!r}", path=archive) while True: buffer = fp.read(46) if len(buffer) < 4: raise EOFError('EOF read where not expected') # Start of file header if buffer[:4] != b'PK\x01\x02': break # Bad: Central Dir File Header if len(buffer) != 46: raise EOFError('EOF read where not expected') flags = _unpack_uint16(buffer[8:10]) compress = _unpack_uint16(buffer[10:12]) time = _unpack_uint16(buffer[12:14]) date = _unpack_uint16(buffer[14:16]) crc = _unpack_uint32(buffer[16:20]) data_size = _unpack_uint32(buffer[20:24]) file_size = _unpack_uint32(buffer[24:28]) name_size = _unpack_uint16(buffer[28:30]) extra_size = _unpack_uint16(buffer[30:32]) comment_size = _unpack_uint16(buffer[32:34]) file_offset = _unpack_uint32(buffer[42:46]) header_size = name_size + extra_size + comment_size if file_offset > header_offset: raise ZipImportError(f'bad local header offset: {archive!r}', path=archive) file_offset += arc_offset try: name = fp.read(name_size) except OSError: raise ZipImportError(f"can't read Zip file: {archive!r}", path=archive) if len(name) != name_size: raise ZipImportError(f"can't read Zip file: {archive!r}", path=archive) # On Windows, calling fseek to skip over the fields we don't use is # slower than reading the data because fseek flushes stdio's # internal buffers. See issue #8745. try: if len(fp.read(header_size - name_size)) != header_size - name_size: raise ZipImportError(f"can't read Zip file: {archive!r}", path=archive) except OSError: raise ZipImportError(f"can't read Zip file: {archive!r}", path=archive) if flags & 0x800: # UTF-8 file names extension name = name.decode() else: # Historical ZIP filename encoding try: name = name.decode('ascii') except UnicodeDecodeError: name = name.decode('latin1').translate(cp437_table) name = name.replace('/', path_sep) path = _bootstrap_external._path_join(archive, name) t = (path, compress, data_size, file_size, file_offset, time, date, crc) files[name] = t count += 1 _bootstrap._verbose_message('zipimport: found {} names in {!r}', count, archive) return files