Python typing.BinaryIO類代碼示例

def load(file_handle: typing.BinaryIO) -> TSerializable:
    """load(file) -> object

    This function reads a tnetstring from a file and parses it into a
    python object.  The file must support the read() method, and this
    function promises not to read more data than necessary.
    """
    #  Read the length prefix one char at a time.
    #  Note that the netstring spec explicitly forbids padding zeros.
    c = file_handle.read(1)
    if c == b"":  # we want to detect this special case.
        raise ValueError("not a tnetstring: empty file")
    data_length = b""
    while c.isdigit():
        data_length += c
        if len(data_length) > 9:
            raise ValueError("not a tnetstring: absurdly large length prefix")
        c = file_handle.read(1)
    if c != b":":
        raise ValueError("not a tnetstring: missing or invalid length prefix")

    data = file_handle.read(int(data_length))
    data_type = file_handle.read(1)[0]

    return parse(data_type, data)

    def put(
        self, namespace: str, metadata: Dict[str, Any], bytes_io: BinaryIO,
    ) -> None:
        """Store a file."""
        subset = dict_subset(metadata, lambda k, v: k in (
            # We are not storing the 'file_name'
            'image_width', 'image_height', 'original_id', 'version'))
        self._convert_values_to_str(subset)
        if hasattr(bytes_io, 'seekable') and bytes_io.seekable():
            bytes_io.seek(0)

        # When botocore.response.StreamingBody is passed in as bytes_io,
        # the bucket.put_object() call below fails with
        # "AttributeError: 'StreamingBody' object has no attribute 'tell'"
        # so we have to read the stream, getting the bytes:
        if not hasattr(bytes_io, 'tell'):
            bytes_io = bytes_io.read()  # type: ignore

        result = self.bucket.put_object(
            Key=self._get_path(namespace, metadata),
            # done automatically by botocore:  ContentMD5=encoded_md5,
            ContentType=metadata['mime_type'],
            ContentLength=metadata['length'], Body=bytes_io, Metadata=subset)
        # print(result)
        return result

 def __init__(self, archive: BinaryIO, offset: int, length: int, prefix: bytes):
     archive.seek(offset)
     self.name = archive.name
     self.remaining = length
     self.sources = [cast(io.BufferedIOBase, archive)]
     if prefix:
         self.sources.insert(0, cast(io.BufferedIOBase, io.BytesIO(prefix)))

    def get_index(
        self, archive: BinaryIO, version: Optional[Version] = None
    ) -> Dict[str, ComplexIndexEntry]:
        if not version:
            version = self.version() if self.version else self.detect_version()

        offset = 0
        key: Optional[int] = None
        if self.offset_and_key:
            offset, key = self.offset_and_key
        else:
            offset, key = version.find_offset_and_key(archive)
        archive.seek(offset)
        index: Dict[bytes, IndexEntry] = pickle.loads(
            zlib.decompress(archive.read()), encoding="bytes"
        )
        if key is not None:
            normal_index = UnRPA.deobfuscate_index(key, index)
        else:
            normal_index = UnRPA.normalise_index(index)

        return {
            UnRPA.ensure_str_path(path).replace("/", os.sep): data
            for path, data in normal_index.items()
        }

 async def save_to(self, name: str, fd: BinaryIO):
     async with ClientSession() as client:
         async with client.post(self.get_url, data=name.encode("utf8")) as resp:
             assert resp.status == 200
             while True:
                 data = await resp.content.read(2 << 20)
                 if not data:
                     break
                 fd.write(data)

def read_offset_array(file: BinaryIO, count: int):
    """Read an array of offsets to null-terminated strings from the file."""
    cdmat_offsets = str_read(str(count) + 'i', file)
    arr = [None] * count  # type: List[str]

    for ind, off in enumerate(cdmat_offsets):
        file.seek(off)
        arr[ind] = read_nullstr(file)
    return arr

def download_into(session: requests.Session,
                  url: str, file: BinaryIO, process_func=None) -> None:
  r = session.get(url, stream=True)
  length = int(r.headers.get('Content-Length') or 0)
  received = 0
  for chunk in r.iter_content(CHUNK_SIZE):
    received += len(chunk)
    file.write(chunk)
    if process_func:
      process_func(received, length)
  if not length and process_func:
    process_func(received, received)

 def postprocess(self, source: ArchiveView, sink: BinaryIO) -> None:
     if self.details:
         key, amount = self.details
         parts = []
         while amount > 0:
             part = source.read(amount)
             amount -= len(part)
             parts.append(part)
         sink.write(obfuscation_run(b"".join(parts), key))
     else:
         raise Exception("find_offset_and_key must be called before postprocess")
     for segment in iter(source.read1, b""):
         sink.write(segment)

def read_nullstr(file: BinaryIO, pos: int=None):
    """Read a null-terminated string from the file."""
    if pos is not None:
        if pos == 0:
            return ''
        file.seek(pos)

    text = []
    while True:
        char = file.read(1)
        if char == b'\0':
            return b''.join(text).decode('ascii')
        if not char:
            raise ValueError('Fell off end of file!')
        text.append(char)

 def add_member_stream( self,
     path: PurePosixPath, mtime: ArchiveMTime,
     content_stream: BinaryIO,
 ) -> None:
     content = content_stream.read()
     assert isinstance(content, bytes), type(content)
     return self.add_member_bytes(path, mtime, content)

def read_delimited_chunks(infile: BinaryIO, chunk_size: int) -> Generator[bytes, None, None]:
    """Yield the contents of infile in chunk_size pieces ending at newlines.
    The individual pieces, except for the last one, end in newlines and
    are smaller than chunk_size if possible.

    Params:
        infile: stream to read from
        chunk_size: maximum size of each chunk

    Yields:
        chunk: chunk with maximum size of chunk_size if possible
    """
    leftover = b""

    while True:
        new_chunk = infile.read(chunk_size)
        chunks = split_chunks(leftover + new_chunk, chunk_size)
        leftover = b""
        # the last item in chunks has to be combined with the next chunk
        # read from the file because it may not actually stop at a
        # newline and to avoid very small chunks.
        if chunks:
            leftover = chunks[-1]
            chunks = chunks[:-1]
        for chunk in chunks:
            yield chunk

        if not new_chunk:
            if leftover:
                yield leftover
            break

def generate_reports(report_template: Report, infile: BinaryIO, chunk_size: Optional[int],
                     copy_header_line: bool) -> Generator[Report, None, None]:
    """Generate reports from a template and input file, optionally split into chunks.

    If chunk_size is None, a single report is generated with the entire
    contents of infile as the raw data. Otherwise chunk_size should be
    an integer giving the maximum number of bytes in a chunk. The data
    read from infile is then split into chunks of this size at newline
    characters (see read_delimited_chunks). For each of the chunks, this
    function yields a copy of the report_template with that chunk as the
    value of the raw attribute.

    When splitting the data into chunks, if copy_header_line is true,
    the first line the file is read before chunking and then prepended
    to each of the chunks. This is particularly useful when splitting
    CSV files.

    The infile should be a file-like object. generate_reports uses only
    two methods, readline and read, with readline only called once and
    only if copy_header_line is true. Both methods should return bytes
    objects.

    Params:
        report_template: report used as template for all yielded copies
        infile: stream to read from
        chunk_size: maximum size of each chunk
        copy_header_line: copy the first line of the infile to each chunk

    Yields:
        report: a Report object holding the chunk in the raw field
    """
    if chunk_size is None:
        report = report_template.copy()
        data = infile.read()
        if data:
            report.add("raw", data, overwrite=True)
            yield report
    else:
        header = b""
        if copy_header_line:
            header = infile.readline()
        for chunk in read_delimited_chunks(infile, chunk_size):
            report = report_template.copy()
            report.add("raw", header + chunk, overwrite=True)
            yield report

 def put(
     self, namespace: str, metadata: Dict[str, Any], bytes_io: BinaryIO,
 ) -> None:
     """Store a file (``bytes_io``) inside ``namespace``."""
     if bytes_io.tell():
         bytes_io.seek(0)
     outdir = self._dir_of(namespace)
     if not outdir.exists():
         outdir.mkdir(parents=True)  # Create namespace directory as needed
     outfile = outdir / self._get_filename(metadata)
     with open(str(outfile), mode='wb', buffering=MEGABYTE) as writer:
         while True:
             chunk = bytes_io.read(MEGABYTE)
             if chunk:
                 writer.write(chunk)
             else:
                 break
     assert outfile.lstat().st_size == metadata['length']

 def _compute_md5(
     self, bytes_io: BinaryIO, metadata: Dict[str, Any],
 ) -> None:
     from hashlib import md5
     two_megabytes = 1048576 * 2
     the_hash = md5()
     the_length = 0
     bytes_io.seek(0)
     while True:
         segment = bytes_io.read(two_megabytes)
         if segment == b'':
             break
         the_length += len(segment)
         the_hash.update(segment)
     metadata['md5'] = the_hash.hexdigest()
     previous_length = metadata.get('length')
     if previous_length is None:
         metadata['length'] = the_length
     else:
         assert previous_length == the_length, "Bug? File lengths {}, {} " \
             "don't match.".format(previous_length, the_length)
     bytes_io.seek(0)  # ...so it can be read again

def mktar_from_dockerfile(fileobject: BinaryIO) -> IO:
    """
    Create a zipped tar archive from a Dockerfile
    **Remember to close the file object**
    Args:
        fileobj: a Dockerfile
    Returns:
        a NamedTemporaryFile() object
    """

    f = tempfile.NamedTemporaryFile()
    t = tarfile.open(mode="w:gz", fileobj=f)

    if isinstance(fileobject, BytesIO):
        dfinfo = tarfile.TarInfo("Dockerfile")
        dfinfo.size = len(fileobject.getvalue())
        fileobject.seek(0)
    else:
        dfinfo = t.gettarinfo(fileobj=fileobject, arcname="Dockerfile")

    t.addfile(dfinfo, fileobject)
    t.close()
    f.seek(0)
    return f