def addfile(self, tarinfo, fileobj=None):
"""
Source copied from tarfile.TarFile, except for setting tarinfo.offset and tarinfo.offset_data.
"""
self._check("awx")
tarinfo = copy.copy(tarinfo)
# NEW LINE
tarinfo.offset = self.offset
buf = tarinfo.tobuf(self.format, self.encoding, self.errors)
self.fileobj.write(buf)
self.offset += len(buf)
# NEW LINE
tarinfo.offset_data = self.offset
# If there's data to follow, append it.
if fileobj is not None:
tarfile.copyfileobj(fileobj, self.fileobj, tarinfo.size)
blocks, remainder = divmod(tarinfo.size, tarfile.BLOCKSIZE)
if remainder > 0:
self.fileobj.write(tarfile.NUL *
(tarfile.BLOCKSIZE - remainder))
blocks += 1
self.offset += blocks * tarfile.BLOCKSIZE
self.members.append(tarinfo)
def _addfile(self, armember, fileobj=None):
if self.mode == 'r':
raise IOError("File not open for writing")
armember = copy.copy(armember)
hdr = armember.getheader()
assert len(hdr) == 60, "Invalid header length"
self._fileobj.write(hdr)
if fileobj is None:
fileobj = open(armember.name, 'rb')
copyfileobj(fileobj, self._fileobj, armember.size)
self._fileobj.write(armember.getpadding())
self.members.append(armember)
self.members_dict[armember.name] = armember
def extract(self, member, path=None):
""" Extracts an archive member to specified path or current working
directory if path is None. If path is directory, extract into it, else
use specified name as file name."""
m = self.extractfile(member)
if path is None:
path = '.'
if os.path.isdir(path):
path = os.path.join(path, m.name)
fd = open(path, 'wb')
m.seek(0)
copyfileobj(m, fd, m.size)
fd.close()
def _addfile(self, armember, fileobj=None):
if self.mode == 'r':
raise IOError("File not open for writing")
armember = copy.copy(armember)
hdr = armember.getheader()
assert len(hdr) == 60, "Invalid header length"
self._fileobj.write(hdr)
if fileobj is None:
fileobj = open(armember.name, 'rb')
copyfileobj(fileobj, self._fileobj, armember.size)
self._fileobj.write(armember.getpadding())
self.members.append(armember)
self.members_dict[armember.name] = armember
def extract(self, member, path=None):
""" Extracts an archive member to specified path or current working
directory if path is None. If path is directory, extract into it, else
use specified name as file name."""
m = self.extractfile(member)
if path is None:
path = '.'
if os.path.isdir(path):
path = os.path.join(path, m.name)
fd = open(path, 'wb')
m.seek(0)
copyfileobj(m, fd, m.size)
fd.close()
def _untar(path, fname, delete=True, flatten=False):
"""
Unpack the given archive file to the same directory.
:param str path:
The folder containing the archive. Will contain the contents.
:param str fname:
The filename of the archive file.
:param bool delete:
If true, the archive will be deleted after extraction.
"""
import tarfile
logging.debug(f'unpacking {fname}')
fullpath = os.path.join(path, fname)
# very painfully manually extract files so that we can use PathManger.open
# instead, lest we are using fb internal file services
with tarfile.open(fileobj=PathManager.open(fullpath, 'rb')) as tf:
for item in tf:
item_name = item.name
while item_name.startswith("./"):
# internal file systems will actually create a literal "."
# directory, so we gotta watch out for that
item_name = item_name[2:]
if flatten:
# flatten the tar file if there are subdirectories
fn = os.path.join(path, os.path.split(item_name)[-1])
else:
fn = os.path.join(path, item_name)
logging.debug(f"Extracting to {fn}")
if item.isdir():
PathManager.mkdirs(fn)
elif item.isfile():
with PathManager.open(fn, 'wb') as wf, tf.extractfile(
item.name) as rf:
tarfile.copyfileobj(rf, wf)
else:
raise NotImplementedError(
"No support for symlinks etc. right now.")
if delete:
try:
PathManager.rm(fullpath)
except PermissionError:
logging.error(
f"Tried to delete {fullpath} but got a permission error. This "
"is known to happen in Windows and is probably not fatal.")
def append_file_chunk(self, fileobj, chunk_size):
"""
Appends a chunk to the current active filestream started
with open_filestream
"""
self._check("aw")
if not self.filestream_active:
raise FileStreamException("Cannot append file chunk without an "\
"active filestream. Start a filestream "\
"first.")
if fileobj is None:
raise FileStreamException("fileobj cannot be None.")
tarfile.copyfileobj(fileobj, self.fileobj, chunk_size)
self.offset += chunk_size
self.filestream_sum += chunk_size
def append_file_chunk(self, fileobj, chunk_size):
"""
Appends a chunk to the current active filestream started
with open_filestream
"""
self._check("aw")
if not self.filestream_active:
raise FileStreamException("Cannot append file chunk without an "\
"active filestream. Start a filestream "\
"first.")
if fileobj is None:
raise FileStreamException("fileobj cannot be None.")
tarfile.copyfileobj(fileobj, self.fileobj, chunk_size)
self.offset += chunk_size
self.filestream_sum += chunk_size
def _untar(path, fname, delete=True):
"""
Unpack the given archive file to the same directory.
:param str path:
The folder containing the archive. Will contain the contents.
:param str fname:
The filename of the archive file.
:param bool delete:
If true, the archive will be deleted after extraction.
"""
import tarfile
logging.debug(f'unpacking {fname}')
fullpath = os.path.join(path, fname)
# very painfully manually extract files so that we can use PathManger.open
# instead, lest we are using fb internal file services
with tarfile.open(fileobj=PathManager.open(fullpath, 'rb')) as tf:
for item in tf:
item_name = item.name
while item_name.startswith("./"):
# internal file systems will actually create a literal "."
# directory, so we gotta watch out for that
item_name = item_name[2:]
fn = os.path.join(path, item_name)
logging.debug(f"Extracting to {fn}")
if item.isdir():
PathManager.mkdirs(fn)
elif item.isfile():
with PathManager.open(fn, 'wb') as wf, tf.extractfile(
item.name) as rf:
tarfile.copyfileobj(rf, wf)
else:
raise NotImplementedError(
"No support for symlinks etc. right now.")
if delete:
PathManager.rm(fullpath)
def copy_from_container(src, dst, buffer_size):
container_name, container_path = src.split(":")
container = docker.from_env().containers.get(container_name)
tar_stream, tar_info = container.get_archive(container_path)
tar_bytes = b''
for bytestream in tar_stream:
tar_bytes += bytestream
tar = io.BytesIO(tar_bytes)
archives = tarfile.open(fileobj=tar, mode='r|*', bufsize=buffer_size)
with closing(archives) as tar_open:
for item in tar_open:
if os.path.isfile(dst):
dst_path = dst
else:
dst_path = os.path.join(dst, item.name)
with open(dst_path, 'wb') as dst_file:
blocks, left = divmod(item.size, buffer_size)
for block in range(blocks):
tarfile.copyfileobj(tar_open.fileobj, dst_file,
buffer_size)
if left > 0:
tarfile.copyfileobj(tar_open.fileobj, dst_file, left)
def _save_file(self, directory, tar_file, file_member):
file_name = os.path.join(directory, file_member.name.split("/")[-1])
self.log.debug("Saving file %s" % file_name)
source = tar_file.extractfile(file_member)
tarfile.copyfileobj(source, codecs.open(file_name, "w", "utf-8"))
def update_event(self, inp=-1):
self.set_output_val(0, tarfile.copyfileobj(self.input(0), self.input(1), self.input(2), self.input(3), self.input(4)))
