Issue #5863: Rewrite BZ2File in pure Python, and allow it to accept
file-like objects using a new `fileobj` constructor argument. Patch by
Nadeem Vawda.
diff --git a/Lib/bz2.py b/Lib/bz2.py
new file mode 100644
index 0000000..667fffd
--- /dev/null
+++ b/Lib/bz2.py
@@ -0,0 +1,392 @@
+"""Interface to the libbzip2 compression library.
+
+This module provides a file interface, classes for incremental
+(de)compression, and functions for one-shot (de)compression.
+"""
+
+__all__ = ["BZ2File", "BZ2Compressor", "BZ2Decompressor", "compress",
+ "decompress"]
+
+__author__ = "Nadeem Vawda <nadeem.vawda@gmail.com>"
+
+import io
+import threading
+import warnings
+
+from _bz2 import BZ2Compressor, BZ2Decompressor
+
+
+_MODE_CLOSED = 0
+_MODE_READ = 1
+_MODE_READ_EOF = 2
+_MODE_WRITE = 3
+
+_BUFFER_SIZE = 8192
+
+
+class BZ2File(io.BufferedIOBase):
+
+ """A file object providing transparent bzip2 (de)compression.
+
+ A BZ2File can act as a wrapper for an existing file object, or refer
+ directly to a named file on disk.
+
+ Note that BZ2File provides a *binary* file interface - data read is
+ returned as bytes, and data to be written should be given as bytes.
+ """
+
+ def __init__(self, filename=None, mode="r", buffering=None,
+ compresslevel=9, fileobj=None):
+ """Open a bzip2-compressed file.
+
+ If filename is given, open the named file. Otherwise, operate on
+ the file object given by fileobj. Exactly one of these two
+ parameters should be provided.
+
+ mode can be 'r' for reading (default), or 'w' for writing.
+
+ buffering is ignored. Its use is deprecated.
+
+ If mode is 'w', compresslevel can be a number between 1 and 9
+ specifying the level of compression: 1 produces the least
+ compression, and 9 (default) produces the most compression.
+ """
+ # This lock must be recursive, so that BufferedIOBase's
+ # readline(), readlines() and writelines() don't deadlock.
+ self._lock = threading.RLock()
+ self._fp = None
+ self._closefp = False
+ self._mode = _MODE_CLOSED
+ self._pos = 0
+ self._size = -1
+
+ if buffering is not None:
+ warnings.warn("Use of 'buffering' argument is deprecated",
+ DeprecationWarning)
+
+ if not (1 <= compresslevel <= 9):
+ raise ValueError("compresslevel must be between 1 and 9")
+
+ if mode in ("", "r", "rb"):
+ mode = "rb"
+ mode_code = _MODE_READ
+ self._decompressor = BZ2Decompressor()
+ self._buffer = None
+ elif mode in ("w", "wb"):
+ mode = "wb"
+ mode_code = _MODE_WRITE
+ self._compressor = BZ2Compressor()
+ else:
+ raise ValueError("Invalid mode: {!r}".format(mode))
+
+ if filename is not None and fileobj is None:
+ self._fp = open(filename, mode)
+ self._closefp = True
+ self._mode = mode_code
+ elif fileobj is not None and filename is None:
+ self._fp = fileobj
+ self._mode = mode_code
+ else:
+ raise ValueError("Must give exactly one of filename and fileobj")
+
+ def close(self):
+ """Flush and close the file.
+
+ May be called more than once without error. Once the file is
+ closed, any other operation on it will raise a ValueError.
+ """
+ with self._lock:
+ if self._mode == _MODE_CLOSED:
+ return
+ try:
+ if self._mode in (_MODE_READ, _MODE_READ_EOF):
+ self._decompressor = None
+ elif self._mode == _MODE_WRITE:
+ self._fp.write(self._compressor.flush())
+ self._compressor = None
+ finally:
+ try:
+ if self._closefp:
+ self._fp.close()
+ finally:
+ self._fp = None
+ self._closefp = False
+ self._mode = _MODE_CLOSED
+ self._buffer = None
+
+ @property
+ def closed(self):
+ """True if this file is closed."""
+ return self._mode == _MODE_CLOSED
+
+ def fileno(self):
+ """Return the file descriptor for the underlying file."""
+ return self._fp.fileno()
+
+ def seekable(self):
+ """Return whether the file supports seeking."""
+ return self.readable()
+
+ def readable(self):
+ """Return whether the file was opened for reading."""
+ return self._mode in (_MODE_READ, _MODE_READ_EOF)
+
+ def writable(self):
+ """Return whether the file was opened for writing."""
+ return self._mode == _MODE_WRITE
+
+ # Mode-checking helper functions.
+
+ def _check_not_closed(self):
+ if self.closed:
+ raise ValueError("I/O operation on closed file")
+
+ def _check_can_read(self):
+ if not self.readable():
+ self._check_not_closed()
+ raise io.UnsupportedOperation("File not open for reading")
+
+ def _check_can_write(self):
+ if not self.writable():
+ self._check_not_closed()
+ raise io.UnsupportedOperation("File not open for writing")
+
+ def _check_can_seek(self):
+ if not self.seekable():
+ self._check_not_closed()
+ raise io.UnsupportedOperation("Seeking is only supported "
+ "on files opening for reading")
+
+ # Fill the readahead buffer if it is empty. Returns False on EOF.
+ def _fill_buffer(self):
+ if self._buffer:
+ return True
+ if self._decompressor.eof:
+ self._mode = _MODE_READ_EOF
+ self._size = self._pos
+ return False
+ rawblock = self._fp.read(_BUFFER_SIZE)
+ if not rawblock:
+ raise EOFError("Compressed file ended before the "
+ "end-of-stream marker was reached")
+ self._buffer = self._decompressor.decompress(rawblock)
+ return True
+
+ # Read data until EOF.
+ # If return_data is false, consume the data without returning it.
+ def _read_all(self, return_data=True):
+ blocks = []
+ while self._fill_buffer():
+ if return_data:
+ blocks.append(self._buffer)
+ self._pos += len(self._buffer)
+ self._buffer = None
+ if return_data:
+ return b"".join(blocks)
+
+ # Read a block of up to n bytes.
+ # If return_data is false, consume the data without returning it.
+ def _read_block(self, n, return_data=True):
+ blocks = []
+ while n > 0 and self._fill_buffer():
+ if n < len(self._buffer):
+ data = self._buffer[:n]
+ self._buffer = self._buffer[n:]
+ else:
+ data = self._buffer
+ self._buffer = None
+ if return_data:
+ blocks.append(data)
+ self._pos += len(data)
+ n -= len(data)
+ if return_data:
+ return b"".join(blocks)
+
+ def peek(self, n=0):
+ """Return buffered data without advancing the file position.
+
+ Always returns at least one byte of data, unless at EOF.
+ The exact number of bytes returned is unspecified.
+ """
+ with self._lock:
+ self._check_can_read()
+ if self._mode == _MODE_READ_EOF or not self._fill_buffer():
+ return b""
+ return self._buffer
+
+ def read(self, size=-1):
+ """Read up to size uncompressed bytes from the file.
+
+ If size is negative or omitted, read until EOF is reached.
+ Returns b'' if the file is already at EOF.
+ """
+ with self._lock:
+ self._check_can_read()
+ if self._mode == _MODE_READ_EOF or size == 0:
+ return b""
+ elif size < 0:
+ return self._read_all()
+ else:
+ return self._read_block(size)
+
+ def read1(self, size=-1):
+ """Read up to size uncompressed bytes with at most one read
+ from the underlying stream.
+
+ Returns b'' if the file is at EOF.
+ """
+ with self._lock:
+ self._check_can_read()
+ if (size == 0 or self._mode == _MODE_READ_EOF or
+ not self._fill_buffer()):
+ return b""
+ if 0 < size < len(self._buffer):
+ data = self._buffer[:size]
+ self._buffer = self._buffer[size:]
+ else:
+ data = self._buffer
+ self._buffer = None
+ self._pos += len(data)
+ return data
+
+ def readinto(self, b):
+ """Read up to len(b) bytes into b.
+
+ Returns the number of bytes read (0 for EOF).
+ """
+ with self._lock:
+ return io.BufferedIOBase.readinto(self, b)
+
+ def readline(self, size=-1):
+ """Read a line of uncompressed bytes from the file.
+
+ The terminating newline (if present) is retained. If size is
+ non-negative, no more than size bytes will be read (in which
+ case the line may be incomplete). Returns b'' if already at EOF.
+ """
+ if not hasattr(size, "__index__"):
+ raise TypeError("Integer argument expected")
+ size = size.__index__()
+ with self._lock:
+ return io.BufferedIOBase.readline(self, size)
+
+ def readlines(self, size=-1):
+ """Read a list of lines of uncompressed bytes from the file.
+
+ size can be specified to control the number of lines read: no
+ further lines will be read once the total size of the lines read
+ so far equals or exceeds size.
+ """
+ if not hasattr(size, "__index__"):
+ raise TypeError("Integer argument expected")
+ size = size.__index__()
+ with self._lock:
+ return io.BufferedIOBase.readlines(self, size)
+
+ def write(self, data):
+ """Write a byte string to the file.
+
+ Returns the number of uncompressed bytes written, which is
+ always len(data). Note that due to buffering, the file on disk
+ may not reflect the data written until close() is called.
+ """
+ with self._lock:
+ self._check_can_write()
+ compressed = self._compressor.compress(data)
+ self._fp.write(compressed)
+ self._pos += len(data)
+ return len(data)
+
+ def writelines(self, seq):
+ """Write a sequence of byte strings to the file.
+
+ Returns the number of uncompressed bytes written.
+ seq can be any iterable yielding byte strings.
+
+ Line separators are not added between the written byte strings.
+ """
+ with self._lock:
+ return io.BufferedIOBase.writelines(self, seq)
+
+ # Rewind the file to the beginning of the data stream.
+ def _rewind(self):
+ self._fp.seek(0, 0)
+ self._mode = _MODE_READ
+ self._pos = 0
+ self._decompressor = BZ2Decompressor()
+ self._buffer = None
+
+ def seek(self, offset, whence=0):
+ """Change the file position.
+
+ The new position is specified by offset, relative to the
+ position indicated by whence. Values for whence are:
+
+ 0: start of stream (default); offset must not be negative
+ 1: current stream position
+ 2: end of stream; offset must not be positive
+
+ Returns the new file position.
+
+ Note that seeking is emulated, so depending on the parameters,
+ this operation may be extremely slow.
+ """
+ with self._lock:
+ self._check_can_seek()
+
+ # Recalculate offset as an absolute file position.
+ if whence == 0:
+ pass
+ elif whence == 1:
+ offset = self._pos + offset
+ elif whence == 2:
+ # Seeking relative to EOF - we need to know the file's size.
+ if self._size < 0:
+ self._read_all(return_data=False)
+ offset = self._size + offset
+ else:
+ raise ValueError("Invalid value for whence: {}".format(whence))
+
+ # Make it so that offset is the number of bytes to skip forward.
+ if offset < self._pos:
+ self._rewind()
+ else:
+ offset -= self._pos
+
+ # Read and discard data until we reach the desired position.
+ if self._mode != _MODE_READ_EOF:
+ self._read_block(offset, return_data=False)
+
+ return self._pos
+
+ def tell(self):
+ """Return the current file position."""
+ with self._lock:
+ self._check_not_closed()
+ return self._pos
+
+
+def compress(data, compresslevel=9):
+ """Compress a block of data.
+
+ compresslevel, if given, must be a number between 1 and 9.
+
+ For incremental compression, use a BZ2Compressor object instead.
+ """
+ comp = BZ2Compressor(compresslevel)
+ return comp.compress(data) + comp.flush()
+
+
+def decompress(data):
+ """Decompress a block of data.
+
+ For incremental decompression, use a BZ2Decompressor object instead.
+ """
+ if len(data) == 0:
+ return b""
+ decomp = BZ2Decompressor()
+ result = decomp.decompress(data)
+ if not decomp.eof:
+ raise ValueError("Compressed data ended before the "
+ "end-of-stream marker was reached")
+ return result
diff --git a/Lib/test/test_bz2.py b/Lib/test/test_bz2.py
index be35580..cee38e0 100644
--- a/Lib/test/test_bz2.py
+++ b/Lib/test/test_bz2.py
@@ -21,7 +21,30 @@
class BaseTest(unittest.TestCase):
"Base for other testcases."
- TEXT = b'root:x:0:0:root:/root:/bin/bash\nbin:x:1:1:bin:/bin:\ndaemon:x:2:2:daemon:/sbin:\nadm:x:3:4:adm:/var/adm:\nlp:x:4:7:lp:/var/spool/lpd:\nsync:x:5:0:sync:/sbin:/bin/sync\nshutdown:x:6:0:shutdown:/sbin:/sbin/shutdown\nhalt:x:7:0:halt:/sbin:/sbin/halt\nmail:x:8:12:mail:/var/spool/mail:\nnews:x:9:13:news:/var/spool/news:\nuucp:x:10:14:uucp:/var/spool/uucp:\noperator:x:11:0:operator:/root:\ngames:x:12:100:games:/usr/games:\ngopher:x:13:30:gopher:/usr/lib/gopher-data:\nftp:x:14:50:FTP User:/var/ftp:/bin/bash\nnobody:x:65534:65534:Nobody:/home:\npostfix:x:100:101:postfix:/var/spool/postfix:\nniemeyer:x:500:500::/home/niemeyer:/bin/bash\npostgres:x:101:102:PostgreSQL Server:/var/lib/pgsql:/bin/bash\nmysql:x:102:103:MySQL server:/var/lib/mysql:/bin/bash\nwww:x:103:104::/var/www:/bin/false\n'
+ TEXT_LINES = [
+ b'root:x:0:0:root:/root:/bin/bash\n',
+ b'bin:x:1:1:bin:/bin:\n',
+ b'daemon:x:2:2:daemon:/sbin:\n',
+ b'adm:x:3:4:adm:/var/adm:\n',
+ b'lp:x:4:7:lp:/var/spool/lpd:\n',
+ b'sync:x:5:0:sync:/sbin:/bin/sync\n',
+ b'shutdown:x:6:0:shutdown:/sbin:/sbin/shutdown\n',
+ b'halt:x:7:0:halt:/sbin:/sbin/halt\n',
+ b'mail:x:8:12:mail:/var/spool/mail:\n',
+ b'news:x:9:13:news:/var/spool/news:\n',
+ b'uucp:x:10:14:uucp:/var/spool/uucp:\n',
+ b'operator:x:11:0:operator:/root:\n',
+ b'games:x:12:100:games:/usr/games:\n',
+ b'gopher:x:13:30:gopher:/usr/lib/gopher-data:\n',
+ b'ftp:x:14:50:FTP User:/var/ftp:/bin/bash\n',
+ b'nobody:x:65534:65534:Nobody:/home:\n',
+ b'postfix:x:100:101:postfix:/var/spool/postfix:\n',
+ b'niemeyer:x:500:500::/home/niemeyer:/bin/bash\n',
+ b'postgres:x:101:102:PostgreSQL Server:/var/lib/pgsql:/bin/bash\n',
+ b'mysql:x:102:103:MySQL server:/var/lib/mysql:/bin/bash\n',
+ b'www:x:103:104::/var/www:/bin/false\n',
+ ]
+ TEXT = b''.join(TEXT_LINES)
DATA = b'BZh91AY&SY.\xc8N\x18\x00\x01>_\x80\x00\x10@\x02\xff\xf0\x01\x07n\x00?\xe7\xff\xe00\x01\x99\xaa\x00\xc0\x03F\x86\x8c#&\x83F\x9a\x03\x06\xa6\xd0\xa6\x93M\x0fQ\xa7\xa8\x06\x804hh\x12$\x11\xa4i4\xf14S\xd2<Q\xb5\x0fH\xd3\xd4\xdd\xd5\x87\xbb\xf8\x94\r\x8f\xafI\x12\xe1\xc9\xf8/E\x00pu\x89\x12]\xc9\xbbDL\nQ\x0e\t1\x12\xdf\xa0\xc0\x97\xac2O9\x89\x13\x94\x0e\x1c7\x0ed\x95I\x0c\xaaJ\xa4\x18L\x10\x05#\x9c\xaf\xba\xbc/\x97\x8a#C\xc8\xe1\x8cW\xf9\xe2\xd0\xd6M\xa7\x8bXa<e\x84t\xcbL\xb3\xa7\xd9\xcd\xd1\xcb\x84.\xaf\xb3\xab\xab\xad`n}\xa0lh\tE,\x8eZ\x15\x17VH>\x88\xe5\xcd9gd6\x0b\n\xe9\x9b\xd5\x8a\x99\xf7\x08.K\x8ev\xfb\xf7xw\xbb\xdf\xa1\x92\xf1\xdd|/";\xa2\xba\x9f\xd5\xb1#A\xb6\xf6\xb3o\xc9\xc5y\\\xebO\xe7\x85\x9a\xbc\xb6f8\x952\xd5\xd7"%\x89>V,\xf7\xa6z\xe2\x9f\xa3\xdf\x11\x11"\xd6E)I\xa9\x13^\xca\xf3r\xd0\x03U\x922\xf26\xec\xb6\xed\x8b\xc3U\x13\x9d\xc5\x170\xa4\xfa^\x92\xacDF\x8a\x97\xd6\x19\xfe\xdd\xb8\xbd\x1a\x9a\x19\xa3\x80ankR\x8b\xe5\xd83]\xa9\xc6\x08\x82f\xf6\xb9"6l$\xb8j@\xc0\x8a\xb0l1..\xbak\x83ls\x15\xbc\xf4\xc1\x13\xbe\xf8E\xb8\x9d\r\xa8\x9dk\x84\xd3n\xfa\xacQ\x07\xb1%y\xaav\xb4\x08\xe0z\x1b\x16\xf5\x04\xe9\xcc\xb9\x08z\x1en7.G\xfc]\xc9\x14\xe1B@\xbb!8`'
DATA_CRLF = b'BZh91AY&SY\xaez\xbbN\x00\x01H\xdf\x80\x00\x12@\x02\xff\xf0\x01\x07n\x00?\xe7\xff\xe0@\x01\xbc\xc6`\x86*\x8d=M\xa9\x9a\x86\xd0L@\x0fI\xa6!\xa1\x13\xc8\x88jdi\x8d@\x03@\x1a\x1a\x0c\x0c\x83 \x00\xc4h2\x19\x01\x82D\x84e\t\xe8\x99\x89\x19\x1ah\x00\r\x1a\x11\xaf\x9b\x0fG\xf5(\x1b\x1f?\t\x12\xcf\xb5\xfc\x95E\x00ps\x89\x12^\xa4\xdd\xa2&\x05(\x87\x04\x98\x89u\xe40%\xb6\x19\'\x8c\xc4\x89\xca\x07\x0e\x1b!\x91UIFU%C\x994!DI\xd2\xfa\xf0\xf1N8W\xde\x13A\xf5\x9cr%?\x9f3;I45A\xd1\x8bT\xb1<l\xba\xcb_\xc00xY\x17r\x17\x88\x08\x08@\xa0\ry@\x10\x04$)`\xf2\xce\x89z\xb0s\xec\x9b.iW\x9d\x81\xb5-+t\x9f\x1a\'\x97dB\xf5x\xb5\xbe.[.\xd7\x0e\x81\xe7\x08\x1cN`\x88\x10\xca\x87\xc3!"\x80\x92R\xa1/\xd1\xc0\xe6mf\xac\xbd\x99\xcca\xb3\x8780>\xa4\xc7\x8d\x1a\\"\xad\xa1\xabyBg\x15\xb9l\x88\x88\x91k"\x94\xa4\xd4\x89\xae*\xa6\x0b\x10\x0c\xd6\xd4m\xe86\xec\xb5j\x8a\x86j\';\xca.\x01I\xf2\xaaJ\xe8\x88\x8cU+t3\xfb\x0c\n\xa33\x13r2\r\x16\xe0\xb3(\xbf\x1d\x83r\xe7M\xf0D\x1365\xd8\x88\xd3\xa4\x92\xcb2\x06\x04\\\xc1\xb0\xea//\xbek&\xd8\xe6+t\xe5\xa1\x13\xada\x16\xder5"w]\xa2i\xb7[\x97R \xe2IT\xcd;Z\x04dk4\xad\x8a\t\xd3\x81z\x10\xf1:^`\xab\x1f\xc5\xdc\x91N\x14$+\x9e\xae\xd3\x80'
@@ -54,13 +77,15 @@
if os.path.isfile(self.filename):
os.unlink(self.filename)
- def createTempFile(self, crlf=0):
+ def getData(self, crlf=False):
+ if crlf:
+ return self.DATA_CRLF
+ else:
+ return self.DATA
+
+ def createTempFile(self, crlf=False):
with open(self.filename, "wb") as f:
- if crlf:
- data = self.DATA_CRLF
- else:
- data = self.DATA
- f.write(data)
+ f.write(self.getData(crlf))
def testRead(self):
# "Test BZ2File.read()"
@@ -70,7 +95,7 @@
self.assertEqual(bz2f.read(), self.TEXT)
def testRead0(self):
- # Test BBZ2File.read(0)"
+ # "Test BBZ2File.read(0)"
self.createTempFile()
with BZ2File(self.filename) as bz2f:
self.assertRaises(TypeError, bz2f.read, None)
@@ -94,6 +119,28 @@
with BZ2File(self.filename) as bz2f:
self.assertEqual(bz2f.read(100), self.TEXT[:100])
+ def testPeek(self):
+ # "Test BZ2File.peek()"
+ self.createTempFile()
+ with BZ2File(self.filename) as bz2f:
+ pdata = bz2f.peek()
+ self.assertNotEqual(len(pdata), 0)
+ self.assertTrue(self.TEXT.startswith(pdata))
+ self.assertEqual(bz2f.read(), self.TEXT)
+
+ def testReadInto(self):
+ # "Test BZ2File.readinto()"
+ self.createTempFile()
+ with BZ2File(self.filename) as bz2f:
+ n = 128
+ b = bytearray(n)
+ self.assertEqual(bz2f.readinto(b), n)
+ self.assertEqual(b, self.TEXT[:n])
+ n = len(self.TEXT) - n
+ b = bytearray(len(self.TEXT))
+ self.assertEqual(bz2f.readinto(b), n)
+ self.assertEqual(b[:n], self.TEXT[-n:])
+
def testReadLine(self):
# "Test BZ2File.readline()"
self.createTempFile()
@@ -125,7 +172,7 @@
bz2f = BZ2File(self.filename)
bz2f.close()
self.assertRaises(ValueError, bz2f.__next__)
- # This call will deadlock of the above .__next__ call failed to
+ # This call will deadlock if the above .__next__ call failed to
# release the lock.
self.assertRaises(ValueError, bz2f.readlines)
@@ -217,6 +264,13 @@
self.assertEqual(bz2f.tell(), 0)
self.assertEqual(bz2f.read(), self.TEXT)
+ def testFileno(self):
+ # "Test BZ2File.fileno()"
+ self.createTempFile()
+ with open(self.filename) as rawf:
+ with BZ2File(fileobj=rawf) as bz2f:
+ self.assertEqual(bz2f.fileno(), rawf.fileno())
+
def testOpenDel(self):
# "Test opening and deleting a file many times"
self.createTempFile()
@@ -278,17 +332,65 @@
t.join()
def testMixedIterationReads(self):
- # Issue #8397: mixed iteration and reads should be forbidden.
- with bz2.BZ2File(self.filename, 'wb') as f:
- # The internal buffer size is hard-wired to 8192 bytes, we must
- # write out more than that for the test to stop half through
- # the buffer.
- f.write(self.TEXT * 100)
- with bz2.BZ2File(self.filename, 'rb') as f:
- next(f)
- self.assertRaises(ValueError, f.read)
- self.assertRaises(ValueError, f.readline)
- self.assertRaises(ValueError, f.readlines)
+ # "Test mixed iteration and reads."
+ self.createTempFile()
+ linelen = len(self.TEXT_LINES[0])
+ halflen = linelen // 2
+ with bz2.BZ2File(self.filename) as bz2f:
+ bz2f.read(halflen)
+ self.assertEqual(next(bz2f), self.TEXT_LINES[0][halflen:])
+ self.assertEqual(bz2f.read(), self.TEXT[linelen:])
+ with bz2.BZ2File(self.filename) as bz2f:
+ bz2f.readline()
+ self.assertEqual(next(bz2f), self.TEXT_LINES[1])
+ self.assertEqual(bz2f.readline(), self.TEXT_LINES[2])
+ with bz2.BZ2File(self.filename) as bz2f:
+ bz2f.readlines()
+ with self.assertRaises(StopIteration):
+ next(bz2f)
+ self.assertEqual(bz2f.readlines(), [])
+
+ def testReadBytesIO(self):
+ # "Test BZ2File.read() with BytesIO source"
+ with BytesIO(self.getData()) as bio:
+ with BZ2File(fileobj=bio) as bz2f:
+ self.assertRaises(TypeError, bz2f.read, None)
+ self.assertEqual(bz2f.read(), self.TEXT)
+ self.assertFalse(bio.closed)
+
+ def testPeekBytesIO(self):
+ # "Test BZ2File.peek() with BytesIO source"
+ with BytesIO(self.getData()) as bio:
+ with BZ2File(fileobj=bio) as bz2f:
+ pdata = bz2f.peek()
+ self.assertNotEqual(len(pdata), 0)
+ self.assertTrue(self.TEXT.startswith(pdata))
+ self.assertEqual(bz2f.read(), self.TEXT)
+
+ def testWriteBytesIO(self):
+ # "Test BZ2File.write() with BytesIO destination"
+ with BytesIO() as bio:
+ with BZ2File(fileobj=bio, mode="w") as bz2f:
+ self.assertRaises(TypeError, bz2f.write)
+ bz2f.write(self.TEXT)
+ self.assertEqual(self.decompress(bio.getvalue()), self.TEXT)
+ self.assertFalse(bio.closed)
+
+ def testSeekForwardBytesIO(self):
+ # "Test BZ2File.seek(150, 0) with BytesIO source"
+ with BytesIO(self.getData()) as bio:
+ with BZ2File(fileobj=bio) as bz2f:
+ self.assertRaises(TypeError, bz2f.seek)
+ bz2f.seek(150)
+ self.assertEqual(bz2f.read(), self.TEXT[150:])
+
+ def testSeekBackwardsBytesIO(self):
+ # "Test BZ2File.seek(-150, 1) with BytesIO source"
+ with BytesIO(self.getData()) as bio:
+ with BZ2File(fileobj=bio) as bz2f:
+ bz2f.read(500)
+ bz2f.seek(-150, 1)
+ self.assertEqual(bz2f.read(), self.TEXT[500-150:])
class BZ2CompressorTest(BaseTest):
def testCompress(self):