def description_of(lines, name='stdin'):
"""
Return a string describing the probable encoding of a file or
list of strings.
:param lines: The lines to get the encoding of.
:type lines: Iterable of bytes
:param name: Name of file or collection of lines
:type name: str
"""
u = UniversalDetector()
for line in lines:
line = bytearray(line)
u.feed(line)
# shortcut out of the loop to save reading further - particularly useful if we read a BOM.
if u.done:
break
u.close()
result = u.result
if PY2:
name = name.decode(sys.getfilesystemencoding(), 'ignore')
if result['encoding']:
return '{0}: {1} with confidence {2}'.format(name, result['encoding'],
result['confidence'])
else:
return '{0}: no result'.format(name)
def description_of(lines, name="stdin"):
"""
Return a string describing the probable encoding of a file or
list of strings.
:param lines: The lines to get the encoding of.
:type lines: Iterable of bytes
:param name: Name of file or collection of lines
:type name: str
"""
u = UniversalDetector()
for line in lines:
line = bytearray(line)
u.feed(line)
# shortcut out of the loop to save reading further - particularly useful if we read a BOM.
if u.done:
break
u.close()
result = u.result
if PY2:
name = name.decode(sys.getfilesystemencoding(), "ignore")
if result["encoding"]:
return "{0}: {1} with confidence {2}".format(name, result["encoding"], result["confidence"])
else:
return "{0}: no result".format(name)
def determineEncoding(self, chardet=True):
# BOMs take precedence over everything
# This will also read past the BOM if present
charEncoding = self.detectBOM(), "certain"
if charEncoding[0] is not None:
return charEncoding
# If we've been overriden, we've been overriden
charEncoding = lookupEncoding(self.override_encoding), "certain"
if charEncoding[0] is not None:
return charEncoding
# Now check the transport layer
charEncoding = lookupEncoding(self.transport_encoding), "certain"
if charEncoding[0] is not None:
return charEncoding
# Look for meta elements with encoding information
charEncoding = self.detectEncodingMeta(), "tentative"
if charEncoding[0] is not None:
return charEncoding
# Parent document encoding
charEncoding = lookupEncoding(
self.same_origin_parent_encoding), "tentative"
if charEncoding[0] is not None and not charEncoding[0].name.startswith(
"utf-16"):
return charEncoding
# "likely" encoding
charEncoding = lookupEncoding(self.likely_encoding), "tentative"
if charEncoding[0] is not None:
return charEncoding
# Guess with chardet, if available
if chardet:
try:
from pip._vendor.chardet.universaldetector import UniversalDetector
except ImportError:
pass
else:
buffers = []
detector = UniversalDetector()
while not detector.done:
buffer = self.rawStream.read(self.numBytesChardet)
assert isinstance(buffer, bytes)
if not buffer:
break
buffers.append(buffer)
detector.feed(buffer)
detector.close()
encoding = lookupEncoding(detector.result['encoding'])
self.rawStream.seek(0)
if encoding is not None:
return encoding, "tentative"
# Try the default encoding
charEncoding = lookupEncoding(self.default_encoding), "tentative"
if charEncoding[0] is not None:
return charEncoding
# Fallback to html5lib's default if even that hasn't worked
return lookupEncoding("windows-1252"), "tentative"
return charEncoding
# "likely" encoding
charEncoding = lookupEncoding(self.likely_encoding), "tentative"
if charEncoding[0] is not None:
return charEncoding
# Guess with chardet, if available
if chardet:
try:
from pip._vendor.chardet.universaldetector import UniversalDetector
except ImportError:
pass
else:
buffers = []
detector = UniversalDetector()
while not detector.done:
buffer = self.rawStream.read(self.numBytesChardet)
assert isinstance(buffer, bytes)
if not buffer:
break
buffers.append(buffer)
detector.feed(buffer)
detector.close()
encoding = lookupEncoding(detector.result['encoding'])
self.rawStream.seek(0)
if encoding is not None:
return encoding, "tentative"
# Try the default encoding
charEncoding = lookupEncoding(self.default_encoding), "tentative"
def determineEncoding(self, chardet=True):
# BOMs take precedence over everything
# This will also read past the BOM if present
charEncoding = self.detectBOM(), "certain"
if charEncoding[0] is not None:
return charEncoding
# If we've been overriden, we've been overriden
charEncoding = lookupEncoding(self.override_encoding), "certain"
if charEncoding[0] is not None:
return charEncoding
# Now check the transport layer
charEncoding = lookupEncoding(self.transport_encoding), "certain"
if charEncoding[0] is not None:
return charEncoding
# Look for meta elements with encoding information
charEncoding = self.detectEncodingMeta(), "tentative"
if charEncoding[0] is not None:
return charEncoding
# Parent document encoding
charEncoding = lookupEncoding(self.same_origin_parent_encoding), "tentative"
if charEncoding[0] is not None and not charEncoding[0].name.startswith("utf-16"):
return charEncoding
# "likely" encoding
charEncoding = lookupEncoding(self.likely_encoding), "tentative"
if charEncoding[0] is not None:
return charEncoding
# Guess with chardet, if available
if chardet:
try:
from pip._vendor.chardet.universaldetector import UniversalDetector
except ImportError:
pass
else:
buffers = []
detector = UniversalDetector()
while not detector.done:
buffer = self.rawStream.read(self.numBytesChardet)
assert isinstance(buffer, bytes)
if not buffer:
break
buffers.append(buffer)
detector.feed(buffer)
detector.close()
encoding = lookupEncoding(detector.result['encoding'])
self.rawStream.seek(0)
if encoding is not None:
return encoding, "tentative"
# Try the default encoding
charEncoding = lookupEncoding(self.default_encoding), "tentative"
if charEncoding[0] is not None:
return charEncoding
# Fallback to html5lib's default if even that hasn't worked
return lookupEncoding("windows-1252"), "tentative"
