def read_unicodestringnl(f):
r"""
>>> import StringIO
>>> read_unicodestringnl(StringIO.StringIO("abc\uabcd\njunk"))
u'abc\uabcd'
"""
data = f.readline()
if not data.endswith('\n'):
raise ValueError("no newline found when trying to read "
"unicodestringnl")
data = data[:-1] # lose the newline
return unicode(data, 'raw-unicode-escape')
python类read()的实例源码
def read_unicodestring4(f):
r"""
# bug 24549
#>>> import StringIO
#>>> s = u'abcd\uabcd'
#>>> enc = s.encode('utf-8')
#>>> enc
#'abcd\xea\xaf\x8d'
#>>> n = chr(len(enc)) + chr(0) * 3 # little-endian 4-byte length
#>>> t = read_unicodestring4(StringIO.StringIO(n + enc + 'junk'))
#>>> s == t
#True
#
#>>> read_unicodestring4(StringIO.StringIO(n + enc[:-1]))
#Traceback (most recent call last):
#...
#ValueError: expected 7 bytes in a unicodestring4, but only 6 remain
"""
n = read_int4(f)
if n < 0:
raise ValueError("unicodestring4 byte count < 0: %d" % n)
data = f.read(n)
if len(data) == n:
return unicode(data, 'utf-8')
raise ValueError("expected %d bytes in a unicodestring4, but only %d "
"remain" % (n, len(data)))
def read_float8(f):
r"""
#>>> import StringIO, struct
#>>> raw = struct.pack(">d", -1.25)
#>>> raw
#'\xbf\xf4\x00\x00\x00\x00\x00\x00'
#>>> read_float8(StringIO.StringIO(raw + "\n"))
#-1.25
"""
data = f.read(8)
if len(data) == 8:
return _unpack(">d", data)[0]
raise ValueError("not enough data in stream to read float8")
def read_uint1(f):
r"""
>>> import StringIO
>>> read_uint1(StringIO.StringIO('\xff'))
255
"""
data = f.read(1)
if data:
return ord(data)
raise ValueError("not enough data in stream to read uint1")
def read_uint2(f):
r"""
>>> import StringIO
>>> read_uint2(StringIO.StringIO('\xff\x00'))
255
>>> read_uint2(StringIO.StringIO('\xff\xff'))
65535
"""
data = f.read(2)
if len(data) == 2:
return _unpack("<H", data)[0]
raise ValueError("not enough data in stream to read uint2")
def read_int4(f):
r"""
>>> import StringIO
>>> read_int4(StringIO.StringIO('\xff\x00\x00\x00'))
255
>>> read_int4(StringIO.StringIO('\x00\x00\x00\x80')) == -(2**31)
True
"""
data = f.read(4)
if len(data) == 4:
return _unpack("<i", data)[0]
raise ValueError("not enough data in stream to read int4")
def read_unicodestringnl(f):
r"""
>>> import StringIO
>>> read_unicodestringnl(StringIO.StringIO("abc\uabcd\njunk"))
u'abc\uabcd'
"""
data = f.readline()
if not data.endswith('\n'):
raise ValueError("no newline found when trying to read "
"unicodestringnl")
data = data[:-1] # lose the newline
return unicode(data, 'raw-unicode-escape')
def read_unicodestring4(f):
r"""
>>> import StringIO
>>> s = u'abcd\uabcd'
>>> enc = s.encode('utf-8')
>>> enc
'abcd\xea\xaf\x8d'
>>> n = chr(len(enc)) + chr(0) * 3 # little-endian 4-byte length
>>> t = read_unicodestring4(StringIO.StringIO(n + enc + 'junk'))
>>> s == t
True
>>> read_unicodestring4(StringIO.StringIO(n + enc[:-1]))
Traceback (most recent call last):
...
ValueError: expected 7 bytes in a unicodestring4, but only 6 remain
"""
n = read_int4(f)
if n < 0:
raise ValueError("unicodestring4 byte count < 0: %d" % n)
data = f.read(n)
if len(data) == n:
return unicode(data, 'utf-8')
raise ValueError("expected %d bytes in a unicodestring4, but only %d "
"remain" % (n, len(data)))
def read_float8(f):
r"""
>>> import StringIO, struct
>>> raw = struct.pack(">d", -1.25)
>>> raw
'\xbf\xf4\x00\x00\x00\x00\x00\x00'
>>> read_float8(StringIO.StringIO(raw + "\n"))
-1.25
"""
data = f.read(8)
if len(data) == 8:
return _unpack(">d", data)[0]
raise ValueError("not enough data in stream to read float8")
def read_uint1(f):
r"""
>>> import io
>>> read_uint1(io.BytesIO(b'\xff'))
255
"""
data = f.read(1)
if data:
return data[0]
raise ValueError("not enough data in stream to read uint1")
def read_uint2(f):
r"""
>>> import io
>>> read_uint2(io.BytesIO(b'\xff\x00'))
255
>>> read_uint2(io.BytesIO(b'\xff\xff'))
65535
"""
data = f.read(2)
if len(data) == 2:
return _unpack("<H", data)[0]
raise ValueError("not enough data in stream to read uint2")
def read_int4(f):
r"""
>>> import io
>>> read_int4(io.BytesIO(b'\xff\x00\x00\x00'))
255
>>> read_int4(io.BytesIO(b'\x00\x00\x00\x80')) == -(2**31)
True
"""
data = f.read(4)
if len(data) == 4:
return _unpack("<i", data)[0]
raise ValueError("not enough data in stream to read int4")
def read_unicodestringnl(f):
r"""
>>> import io
>>> read_unicodestringnl(io.BytesIO(b"abc\\uabcd\njunk")) == 'abc\uabcd'
True
"""
data = f.readline()
if not data.endswith(b'\n'):
raise ValueError("no newline found when trying to read "
"unicodestringnl")
data = data[:-1] # lose the newline
return str(data, 'raw-unicode-escape')
def read_unicodestring4(f):
r"""
>>> import io
>>> s = 'abcd\uabcd'
>>> enc = s.encode('utf-8')
>>> enc
b'abcd\xea\xaf\x8d'
>>> n = bytes([len(enc), 0, 0, 0]) # little-endian 4-byte length
>>> t = read_unicodestring4(io.BytesIO(n + enc + b'junk'))
>>> s == t
True
>>> read_unicodestring4(io.BytesIO(n + enc[:-1]))
Traceback (most recent call last):
...
ValueError: expected 7 bytes in a unicodestring4, but only 6 remain
"""
n = read_int4(f)
if n < 0:
raise ValueError("unicodestring4 byte count < 0: %d" % n)
data = f.read(n)
if len(data) == n:
return str(data, 'utf-8', 'surrogatepass')
raise ValueError("expected %d bytes in a unicodestring4, but only %d "
"remain" % (n, len(data)))
def read_float8(f):
r"""
>>> import io, struct
>>> raw = struct.pack(">d", -1.25)
>>> raw
b'\xbf\xf4\x00\x00\x00\x00\x00\x00'
>>> read_float8(io.BytesIO(raw + b"\n"))
-1.25
"""
data = f.read(8)
if len(data) == 8:
return _unpack(">d", data)[0]
raise ValueError("not enough data in stream to read float8")
def read_uint1(f):
r"""
>>> import StringIO
>>> read_uint1(StringIO.StringIO('\xff'))
255
"""
data = f.read(1)
if data:
return ord(data)
raise ValueError("not enough data in stream to read uint1")
def read_uint2(f):
r"""
>>> import StringIO
>>> read_uint2(StringIO.StringIO('\xff\x00'))
255
>>> read_uint2(StringIO.StringIO('\xff\xff'))
65535
"""
data = f.read(2)
if len(data) == 2:
return _unpack("<H", data)[0]
raise ValueError("not enough data in stream to read uint2")
def read_int4(f):
r"""
>>> import StringIO
>>> read_int4(StringIO.StringIO('\xff\x00\x00\x00'))
255
>>> read_int4(StringIO.StringIO('\x00\x00\x00\x80')) == -(2**31)
True
"""
data = f.read(4)
if len(data) == 4:
return _unpack("<i", data)[0]
raise ValueError("not enough data in stream to read int4")
def read_unicodestringnl(f):
r"""
>>> import StringIO
>>> read_unicodestringnl(StringIO.StringIO("abc\uabcd\njunk"))
u'abc\uabcd'
"""
data = f.readline()
if not data.endswith('\n'):
raise ValueError("no newline found when trying to read "
"unicodestringnl")
data = data[:-1] # lose the newline
return unicode(data, 'raw-unicode-escape')
def read_unicodestring4(f):
r"""
>>> import StringIO
>>> s = u'abcd\uabcd'
>>> enc = s.encode('utf-8')
>>> enc
'abcd\xea\xaf\x8d'
>>> n = chr(len(enc)) + chr(0) * 3 # little-endian 4-byte length
>>> t = read_unicodestring4(StringIO.StringIO(n + enc + 'junk'))
>>> s == t
True
>>> read_unicodestring4(StringIO.StringIO(n + enc[:-1]))
Traceback (most recent call last):
...
ValueError: expected 7 bytes in a unicodestring4, but only 6 remain
"""
n = read_int4(f)
if n < 0:
raise ValueError("unicodestring4 byte count < 0: %d" % n)
data = f.read(n)
if len(data) == n:
return unicode(data, 'utf-8')
raise ValueError("expected %d bytes in a unicodestring4, but only %d "
"remain" % (n, len(data)))
