Python BinaryIO.read方法代码示例

# 需要导入模块: from typing import BinaryIO [as 别名]
# 或者: from typing.BinaryIO import read [as 别名]
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)

# 需要导入模块: from typing import BinaryIO [as 别名]
# 或者: from typing.BinaryIO import read [as 别名]
def parse_header(source: BinaryIO) -> Tuple[OFXHeaderType, str]:
    """
    Consume source; feed to appropriate class constructor which performs
    validation/type conversion on OFX header.

    Using header, locate/read/decode (but do not parse) OFX data body.

    Returns a 2-tuple of:
        * instance of OFXHeaderV1/OFXHeaderV2 containing parsed data, and
        * decoded text of OFX data body
    """
    # Skip any empty lines at the beginning
    while True:
        # OFX header is read by nice clean machines, not meatbags -
        # should not contain emoji, 漢字, or what have you.
        line = source.readline().decode("ascii")
        if line.strip():
            break

    # If the first non-empty line contains an XML declaration, it's OFX v2
    xml_match = XML_REGEX.match(line)
    if xml_match:
        # OFXv2 spec doesn't require newlines between XML declaration,
        # OFX declaration, and data elements; `line` may or may not
        # contain the latter two.
        #
        # Just rewind, read the whole file (it must be UTF-8 encoded per
        # the spec) and slice the OFX data body from the end of the
        # OFX declaration
        source.seek(0)
        decoded_source = source.read().decode(OFXHeaderV2.codec)
        header, header_end_index = OFXHeaderV2.parse(decoded_source)
        message = decoded_source[header_end_index:]
    else:
        # OFX v1
        rawheader = line + "\n"
        # First line is OFXHEADER; need to read next 8 lines for a fixed
        # total of 9 fields required by OFX v1 spec.
        for n in range(8):
            rawheader += source.readline().decode("ascii")
        header, header_end_index = OFXHeaderV1.parse(rawheader)

        #  Input source stream position has advanced to the beginning of
        #  the OFX body tag soup, which is where subsequent calls
        #  to read()/readlines() will pick up.
        #
        #  Decode the OFX data body according to the encoding declared
        #  in the OFX header
        message = source.read().decode(header.codec)

    return header, message.strip()

# 需要导入模块: from typing import BinaryIO [as 别名]
# 或者: from typing.BinaryIO import read [as 别名]
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

# 需要导入模块: from typing import BinaryIO [as 别名]
# 或者: from typing.BinaryIO import read [as 别名]
 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)

# 需要导入模块: from typing import BinaryIO [as 别名]
# 或者: from typing.BinaryIO import read [as 别名]
    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()
        }

# 需要导入模块: from typing import BinaryIO [as 别名]
# 或者: from typing.BinaryIO import read [as 别名]
    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

# 需要导入模块: from typing import BinaryIO [as 别名]
# 或者: from typing.BinaryIO import read [as 别名]
def _rewrite_ownership_v0(
    input_file: BinaryIO, new_file: BinaryIO, header: MdvHeader, uid: int, gid: int
) -> None:
    entries_processed = 0
    entry_size = InodeMetadataV0.FORMAT.size
    for _ in range(header.entry_count):
        entries_processed += 1

        entry_data = input_file.read(entry_size)
        if len(entry_data) != entry_size:
            raise Exception("inode metadata table appears truncated")

        entry = InodeMetadataV0.parse(entry_data)
        entry.uid = uid
        entry.gid = gid
        new_file.write(entry.serialize())

    # Copy the remaining file contents as is.  This is normally all 0-filled data
    # that provides space for new entries to be written in the future.
    padding = input_file.read()
    new_file.write(padding)

# 需要导入模块: from typing import BinaryIO [as 别名]
# 或者: from typing.BinaryIO import read [as 别名]
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)

# 需要导入模块: from typing import BinaryIO [as 别名]
# 或者: from typing.BinaryIO import read [as 别名]
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

# 需要导入模块: from typing import BinaryIO [as 别名]
# 或者: from typing.BinaryIO import read [as 别名]
 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']

# 需要导入模块: from typing import BinaryIO [as 别名]
# 或者: from typing.BinaryIO import read [as 别名]
 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

# 需要导入模块: from typing import BinaryIO [as 别名]
# 或者: from typing.BinaryIO import read [as 别名]
def iter_nullstr(file: BinaryIO):
    """Read a null-terminated ASCII string from the file.
    
    This continuously yields strings, with empty strings 
    indicting the end of a section.
    """
    chars = bytearray()
    while True:
        char = file.read(1)
        if char == b'\x00':
            string = chars.decode('ascii')
            chars.clear()
            
            if string == ' ':  # Blank strings are saved as ' '
                yield ''
            elif string == '':
                return  # Actual blanks end the array.
            else:
                yield string
        elif char == b'':
            raise Exception('Reached EOF without null-terminator in {}!'.format(bytes(chars)))
        else:
            chars.extend(char)

# 需要导入模块: from typing import BinaryIO [as 别名]
# 或者: from typing.BinaryIO import read [as 别名]
 def read(cls: Type["MdvHeader"], input_file: BinaryIO) -> "MdvHeader":
     data = input_file.read(cls.FORMAT.size)
     return cls.parse(data)

# 需要导入模块: from typing import BinaryIO [as 别名]
# 或者: from typing.BinaryIO import read [as 别名]
    def _load(self, f: BinaryIO):
        """Read data from the MDL file."""
        assert f.tell() == 0, "Doesn't begin at start?"
        if f.read(4) != b'IDST':
            raise ValueError('Not a model!')
        (
            self.version,
            name,
            file_len,
            # 4 bytes are unknown...
        ) = str_read('i 4x 64s i', f)

        if not 44 <= self.version <= 49:
            raise ValueError('Unknown MDL version {}!'.format(self.version))

        self.name = name.rstrip(b'\0').decode('ascii')
        self.eye_pos = str_readvec(f)
        self.illum_pos = str_readvec(f)
        # Approx dimensions
        self.hull_min = str_readvec(f)
        self.hull_max = str_readvec(f)
        
        self.view_min = str_readvec(f)
        self.view_max = str_readvec(f)

        # Break up the reading a bit to limit the stack size.
        (
            flags,

            bone_count,
            bone_off,

            bone_controller_count, bone_controller_off,

            hitbox_count, hitbox_off,
            anim_count, anim_off,
            sequence_count, sequence_off,
        ) = str_read('11I', f)

        self.flags = Flags(flags)

        (
            activitylistversion, eventsindexed,

            texture_count, texture_offset,
            cdmat_count, cdmat_offset,
            
            skinref_count, skinref_ind, skinfamily_count,
            
            bodypart_count, bodypart_offset,
            attachment_count, attachment_offset,
        ) = str_read('13i', f)

        (
            localnode_count,
            localnode_index,
            localnode_name_index,
         
            # mstudioflexdesc_t
            flexdesc_count,
            flexdesc_index,
         
            # mstudioflexcontroller_t
            flexcontroller_count,
            flexcontroller_index,
         
            # mstudioflexrule_t
            flexrules_count,
            flexrules_index,
         
            # IK probably refers to inverse kinematics
            # mstudioikchain_t
            ikchain_count,
            ikchain_index,
         
            # Information about any "mouth" on the model for speech animation
            # More than one sounds pretty creepy.
            # mstudiomouth_t
            mouths_count, 
            mouths_index,
         
            # mstudioposeparamdesc_t
            localposeparam_count,
            localposeparam_index,
        ) = str_read('15I', f)

        # VDC:
        # For anyone trying to follow along, as of this writing,
        # the next "surfaceprop_index" value is at position 0x0134 (308)
        # from the start of the file.
        assert f.tell() == 308, 'Offset wrong? {} != 308 {}'.format(f.tell(), f)

        (
            # Surface property value (single null-terminated string)
            surfaceprop_index,
         
            # Unusual: In this one index comes first, then count.
            # Key-value data is a series of strings. If you can't find
            # what you're interested in, check the associated PHY file as well.
            keyvalue_index,
#.........这里部分代码省略.........

# 需要导入模块: from typing import BinaryIO [as 别名]
# 或者: from typing.BinaryIO import read [as 别名]
def str_readvec(file: BinaryIO) -> Vec:
    """Read a vector from a file."""
    return Vec(ST_VEC.unpack(file.read(ST_VEC.size)))