def determine_encoding(self):
while not self.eof and (self.raw_buffer is None or len(self.raw_buffer) < 2):
self.update_raw()
if isinstance(self.raw_buffer, bytes):
if self.raw_buffer.startswith(codecs.BOM_UTF16_LE):
self.raw_decode = codecs.utf_16_le_decode
self.encoding = 'utf-16-le'
elif self.raw_buffer.startswith(codecs.BOM_UTF16_BE):
self.raw_decode = codecs.utf_16_be_decode
self.encoding = 'utf-16-be'
else:
self.raw_decode = codecs.utf_8_decode
self.encoding = 'utf-8'
self.update(1)
python类BOM_UTF16_BE的实例源码
def detectBOM(self):
"""Attempts to detect at BOM at the start of the stream. If
an encoding can be determined from the BOM return the name of the
encoding otherwise return None"""
bomDict = {
codecs.BOM_UTF8: 'utf-8',
codecs.BOM_UTF16_LE: 'utf-16le', codecs.BOM_UTF16_BE: 'utf-16be',
codecs.BOM_UTF32_LE: 'utf-32le', codecs.BOM_UTF32_BE: 'utf-32be'
}
# Go to beginning of file and read in 4 bytes
string = self.rawStream.read(4)
assert isinstance(string, bytes)
# Try detecting the BOM using bytes from the string
encoding = bomDict.get(string[:3]) # UTF-8
seek = 3
if not encoding:
# Need to detect UTF-32 before UTF-16
encoding = bomDict.get(string) # UTF-32
seek = 4
if not encoding:
encoding = bomDict.get(string[:2]) # UTF-16
seek = 2
# Set the read position past the BOM if one was found, otherwise
# set it to the start of the stream
if encoding:
self.rawStream.seek(seek)
return lookupEncoding(encoding)
else:
self.rawStream.seek(0)
return None
def guess_json_utf(data):
"""
:rtype: str
"""
# JSON always starts with two ASCII characters, so detection is as
# easy as counting the nulls and from their location and count
# determine the encoding. Also detect a BOM, if present.
sample = data[:4]
if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
return 'utf-32' # BOM included
if sample[:3] == codecs.BOM_UTF8:
return 'utf-8-sig' # BOM included, MS style (discouraged)
if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
return 'utf-16' # BOM included
nullcount = sample.count(_null)
if nullcount == 0:
return 'utf-8'
if nullcount == 2:
if sample[::2] == _null2: # 1st and 3rd are null
return 'utf-16-be'
if sample[1::2] == _null2: # 2nd and 4th are null
return 'utf-16-le'
# Did not detect 2 valid UTF-16 ascii-range characters
if nullcount == 3:
if sample[:3] == _null3:
return 'utf-32-be'
if sample[1:] == _null3:
return 'utf-32-le'
# Did not detect a valid UTF-32 ascii-range character
return None
def guess_json_utf(data):
"""
:rtype: str
"""
# JSON always starts with two ASCII characters, so detection is as
# easy as counting the nulls and from their location and count
# determine the encoding. Also detect a BOM, if present.
sample = data[:4]
if sample in (codecs.BOM_UTF32_LE, codecs.BOM_UTF32_BE):
return 'utf-32' # BOM included
if sample[:3] == codecs.BOM_UTF8:
return 'utf-8-sig' # BOM included, MS style (discouraged)
if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
return 'utf-16' # BOM included
nullcount = sample.count(_null)
if nullcount == 0:
return 'utf-8'
if nullcount == 2:
if sample[::2] == _null2: # 1st and 3rd are null
return 'utf-16-be'
if sample[1::2] == _null2: # 2nd and 4th are null
return 'utf-16-le'
# Did not detect 2 valid UTF-16 ascii-range characters
if nullcount == 3:
if sample[:3] == _null3:
return 'utf-32-be'
if sample[1:] == _null3:
return 'utf-32-le'
# Did not detect a valid UTF-32 ascii-range character
return None
def detect_encoding(b):
bstartswith = b.startswith
if bstartswith((codecs.BOM_UTF32_BE, codecs.BOM_UTF32_LE)):
return 'utf-32'
if bstartswith((codecs.BOM_UTF16_BE, codecs.BOM_UTF16_LE)):
return 'utf-16'
if bstartswith(codecs.BOM_UTF8):
return 'utf-8-sig'
if len(b) >= 4:
if not b[0]:
# 00 00 -- -- - utf-32-be
# 00 XX -- -- - utf-16-be
return 'utf-16-be' if b[1] else 'utf-32-be'
if not b[1]:
# XX 00 00 00 - utf-32-le
# XX 00 00 XX - utf-16-le
# XX 00 XX -- - utf-16-le
return 'utf-16-le' if b[2] or b[3] else 'utf-32-le'
elif len(b) == 2:
if not b[0]:
# 00 XX - utf-16-be
return 'utf-16-be'
if not b[1]:
# XX 00 - utf-16-le
return 'utf-16-le'
# default
return 'utf-8'
def guess_json_utf(data):
"""
:rtype: str
"""
# JSON always starts with two ASCII characters, so detection is as
# easy as counting the nulls and from their location and count
# determine the encoding. Also detect a BOM, if present.
sample = data[:4]
if sample in (codecs.BOM_UTF32_LE, codecs.BOM_UTF32_BE):
return 'utf-32' # BOM included
if sample[:3] == codecs.BOM_UTF8:
return 'utf-8-sig' # BOM included, MS style (discouraged)
if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
return 'utf-16' # BOM included
nullcount = sample.count(_null)
if nullcount == 0:
return 'utf-8'
if nullcount == 2:
if sample[::2] == _null2: # 1st and 3rd are null
return 'utf-16-be'
if sample[1::2] == _null2: # 2nd and 4th are null
return 'utf-16-le'
# Did not detect 2 valid UTF-16 ascii-range characters
if nullcount == 3:
if sample[:3] == _null3:
return 'utf-32-be'
if sample[1:] == _null3:
return 'utf-32-le'
# Did not detect a valid UTF-32 ascii-range character
return None
def has_bom(fn):
with open(fn, 'rb') as f:
sample = f.read(4)
return (sample[:3] == b'\xef\xbb\xbf' or
sample.startswith((codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE)))
def detectBOM(self):
"""Attempts to detect at BOM at the start of the stream. If
an encoding can be determined from the BOM return the name of the
encoding otherwise return None"""
bomDict = {
codecs.BOM_UTF8: 'utf-8',
codecs.BOM_UTF16_LE: 'utf-16-le', codecs.BOM_UTF16_BE: 'utf-16-be',
codecs.BOM_UTF32_LE: 'utf-32-le', codecs.BOM_UTF32_BE: 'utf-32-be'
}
# Go to beginning of file and read in 4 bytes
string = self.rawStream.read(4)
assert isinstance(string, bytes)
# Try detecting the BOM using bytes from the string
encoding = bomDict.get(string[:3]) # UTF-8
seek = 3
if not encoding:
# Need to detect UTF-32 before UTF-16
encoding = bomDict.get(string) # UTF-32
seek = 4
if not encoding:
encoding = bomDict.get(string[:2]) # UTF-16
seek = 2
# Set the read position past the BOM if one was found, otherwise
# set it to the start of the stream
self.rawStream.seek(encoding and seek or 0)
return encoding
def guess_json_utf(data):
# JSON always starts with two ASCII characters, so detection is as
# easy as counting the nulls and from their location and count
# determine the encoding. Also detect a BOM, if present.
sample = data[:4]
if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
return 'utf-32' # BOM included
if sample[:3] == codecs.BOM_UTF8:
return 'utf-8-sig' # BOM included, MS style (discouraged)
if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
return 'utf-16' # BOM included
nullcount = sample.count(_null)
if nullcount == 0:
return 'utf-8'
if nullcount == 2:
if sample[::2] == _null2: # 1st and 3rd are null
return 'utf-16-be'
if sample[1::2] == _null2: # 2nd and 4th are null
return 'utf-16-le'
# Did not detect 2 valid UTF-16 ascii-range characters
if nullcount == 3:
if sample[:3] == _null3:
return 'utf-32-be'
if sample[1:] == _null3:
return 'utf-32-le'
# Did not detect a valid UTF-32 ascii-range character
return None
def guess_json_utf(data):
# JSON always starts with two ASCII characters, so detection is as
# easy as counting the nulls and from their location and count
# determine the encoding. Also detect a BOM, if present.
sample = data[:4]
if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
return 'utf-32' # BOM included
if sample[:3] == codecs.BOM_UTF8:
return 'utf-8-sig' # BOM included, MS style (discouraged)
if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
return 'utf-16' # BOM included
nullcount = sample.count(_null)
if nullcount == 0:
return 'utf-8'
if nullcount == 2:
if sample[::2] == _null2: # 1st and 3rd are null
return 'utf-16-be'
if sample[1::2] == _null2: # 2nd and 4th are null
return 'utf-16-le'
# Did not detect 2 valid UTF-16 ascii-range characters
if nullcount == 3:
if sample[:3] == _null3:
return 'utf-32-be'
if sample[1:] == _null3:
return 'utf-32-le'
# Did not detect a valid UTF-32 ascii-range character
return None
def has_bom(fn):
with open(fn, 'rb') as f:
sample = f.read(4)
return sample.startswith((codecs.BOM_UTF8, codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE))
def detectBOM(self):
"""Attempts to detect at BOM at the start of the stream. If
an encoding can be determined from the BOM return the name of the
encoding otherwise return None"""
bomDict = {
codecs.BOM_UTF8: 'utf-8',
codecs.BOM_UTF16_LE: 'utf-16-le', codecs.BOM_UTF16_BE: 'utf-16-be',
codecs.BOM_UTF32_LE: 'utf-32-le', codecs.BOM_UTF32_BE: 'utf-32-be'
}
# Go to beginning of file and read in 4 bytes
string = self.rawStream.read(4)
assert isinstance(string, bytes)
# Try detecting the BOM using bytes from the string
encoding = bomDict.get(string[:3]) # UTF-8
seek = 3
if not encoding:
# Need to detect UTF-32 before UTF-16
encoding = bomDict.get(string) # UTF-32
seek = 4
if not encoding:
encoding = bomDict.get(string[:2]) # UTF-16
seek = 2
# Set the read position past the BOM if one was found, otherwise
# set it to the start of the stream
self.rawStream.seek(encoding and seek or 0)
return encoding
def guess_json_utf(data):
# JSON always starts with two ASCII characters, so detection is as
# easy as counting the nulls and from their location and count
# determine the encoding. Also detect a BOM, if present.
sample = data[:4]
if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
return 'utf-32' # BOM included
if sample[:3] == codecs.BOM_UTF8:
return 'utf-8-sig' # BOM included, MS style (discouraged)
if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
return 'utf-16' # BOM included
nullcount = sample.count(_null)
if nullcount == 0:
return 'utf-8'
if nullcount == 2:
if sample[::2] == _null2: # 1st and 3rd are null
return 'utf-16-be'
if sample[1::2] == _null2: # 2nd and 4th are null
return 'utf-16-le'
# Did not detect 2 valid UTF-16 ascii-range characters
if nullcount == 3:
if sample[:3] == _null3:
return 'utf-32-be'
if sample[1:] == _null3:
return 'utf-32-le'
# Did not detect a valid UTF-32 ascii-range character
return None
def detectBOM(self):
"""Attempts to detect at BOM at the start of the stream. If
an encoding can be determined from the BOM return the name of the
encoding otherwise return None"""
bomDict = {
codecs.BOM_UTF8: 'utf-8',
codecs.BOM_UTF16_LE: 'utf-16-le', codecs.BOM_UTF16_BE: 'utf-16-be',
codecs.BOM_UTF32_LE: 'utf-32-le', codecs.BOM_UTF32_BE: 'utf-32-be'
}
# Go to beginning of file and read in 4 bytes
string = self.rawStream.read(4)
assert isinstance(string, bytes)
# Try detecting the BOM using bytes from the string
encoding = bomDict.get(string[:3]) # UTF-8
seek = 3
if not encoding:
# Need to detect UTF-32 before UTF-16
encoding = bomDict.get(string) # UTF-32
seek = 4
if not encoding:
encoding = bomDict.get(string[:2]) # UTF-16
seek = 2
# Set the read position past the BOM if one was found, otherwise
# set it to the start of the stream
self.rawStream.seek(encoding and seek or 0)
return encoding
def guess_json_utf(data):
# JSON always starts with two ASCII characters, so detection is as
# easy as counting the nulls and from their location and count
# determine the encoding. Also detect a BOM, if present.
sample = data[:4]
if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
return 'utf-32' # BOM included
if sample[:3] == codecs.BOM_UTF8:
return 'utf-8-sig' # BOM included, MS style (discouraged)
if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
return 'utf-16' # BOM included
nullcount = sample.count(_null)
if nullcount == 0:
return 'utf-8'
if nullcount == 2:
if sample[::2] == _null2: # 1st and 3rd are null
return 'utf-16-be'
if sample[1::2] == _null2: # 2nd and 4th are null
return 'utf-16-le'
# Did not detect 2 valid UTF-16 ascii-range characters
if nullcount == 3:
if sample[:3] == _null3:
return 'utf-32-be'
if sample[1:] == _null3:
return 'utf-32-le'
# Did not detect a valid UTF-32 ascii-range character
return None
def guess_json_utf(data):
# JSON always starts with two ASCII characters, so detection is as
# easy as counting the nulls and from their location and count
# determine the encoding. Also detect a BOM, if present.
sample = data[:4]
if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
return 'utf-32' # BOM included
if sample[:3] == codecs.BOM_UTF8:
return 'utf-8-sig' # BOM included, MS style (discouraged)
if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
return 'utf-16' # BOM included
nullcount = sample.count(_null)
if nullcount == 0:
return 'utf-8'
if nullcount == 2:
if sample[::2] == _null2: # 1st and 3rd are null
return 'utf-16-be'
if sample[1::2] == _null2: # 2nd and 4th are null
return 'utf-16-le'
# Did not detect 2 valid UTF-16 ascii-range characters
if nullcount == 3:
if sample[:3] == _null3:
return 'utf-32-be'
if sample[1:] == _null3:
return 'utf-32-le'
# Did not detect a valid UTF-32 ascii-range character
return None
def get_original_bytes(self):
# We're a text string object, but the library is trying to get our raw
# bytes. This can happen if we auto-detected this string as text, but
# we were wrong. It's pretty common. Return the original bytes that
# would have been used to create this object, based upon the autodetect
# method.
if self.autodetect_utf16:
return codecs.BOM_UTF16_BE + self.encode("utf-16be")
elif self.autodetect_pdfdocencoding:
return encode_pdfdocencoding(self)
else:
raise Exception("no information about original bytes")
def detectBOM(self):
"""Attempts to detect at BOM at the start of the stream. If
an encoding can be determined from the BOM return the name of the
encoding otherwise return None"""
bomDict = {
codecs.BOM_UTF8: 'utf-8',
codecs.BOM_UTF16_LE: 'utf-16le', codecs.BOM_UTF16_BE: 'utf-16be',
codecs.BOM_UTF32_LE: 'utf-32le', codecs.BOM_UTF32_BE: 'utf-32be'
}
# Go to beginning of file and read in 4 bytes
string = self.rawStream.read(4)
assert isinstance(string, bytes)
# Try detecting the BOM using bytes from the string
encoding = bomDict.get(string[:3]) # UTF-8
seek = 3
if not encoding:
# Need to detect UTF-32 before UTF-16
encoding = bomDict.get(string) # UTF-32
seek = 4
if not encoding:
encoding = bomDict.get(string[:2]) # UTF-16
seek = 2
# Set the read position past the BOM if one was found, otherwise
# set it to the start of the stream
if encoding:
self.rawStream.seek(seek)
return lookupEncoding(encoding)
else:
self.rawStream.seek(0)
return None
def guess_json_utf(data):
"""
:rtype: str
"""
# JSON always starts with two ASCII characters, so detection is as
# easy as counting the nulls and from their location and count
# determine the encoding. Also detect a BOM, if present.
sample = data[:4]
if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
return 'utf-32' # BOM included
if sample[:3] == codecs.BOM_UTF8:
return 'utf-8-sig' # BOM included, MS style (discouraged)
if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
return 'utf-16' # BOM included
nullcount = sample.count(_null)
if nullcount == 0:
return 'utf-8'
if nullcount == 2:
if sample[::2] == _null2: # 1st and 3rd are null
return 'utf-16-be'
if sample[1::2] == _null2: # 2nd and 4th are null
return 'utf-16-le'
# Did not detect 2 valid UTF-16 ascii-range characters
if nullcount == 3:
if sample[:3] == _null3:
return 'utf-32-be'
if sample[1:] == _null3:
return 'utf-32-le'
# Did not detect a valid UTF-32 ascii-range character
return None
def detectBOM(self):
"""Attempts to detect at BOM at the start of the stream. If
an encoding can be determined from the BOM return the name of the
encoding otherwise return None"""
bomDict = {
codecs.BOM_UTF8: 'utf-8',
codecs.BOM_UTF16_LE: 'utf-16le', codecs.BOM_UTF16_BE: 'utf-16be',
codecs.BOM_UTF32_LE: 'utf-32le', codecs.BOM_UTF32_BE: 'utf-32be'
}
# Go to beginning of file and read in 4 bytes
string = self.rawStream.read(4)
assert isinstance(string, bytes)
# Try detecting the BOM using bytes from the string
encoding = bomDict.get(string[:3]) # UTF-8
seek = 3
if not encoding:
# Need to detect UTF-32 before UTF-16
encoding = bomDict.get(string) # UTF-32
seek = 4
if not encoding:
encoding = bomDict.get(string[:2]) # UTF-16
seek = 2
# Set the read position past the BOM if one was found, otherwise
# set it to the start of the stream
if encoding:
self.rawStream.seek(seek)
return lookupEncoding(encoding)
else:
self.rawStream.seek(0)
return None
