def _guessEncoding(self, path):
"""Opens a file from the given `path` and checks the file encoding.
The file must exists on the file system and end with the extension
`.csv`. The file is read line by line until the encoding could be
guessed.
On a successfull identification, the widgets of this dialog will be
updated.
Args:
path (string): Path to a csv file on the file system.
"""
if os.path.exists(path) and path.lower().endswith('csv'):
encoding = self._detector.detect(path)
if encoding is not None:
if encoding.startswith('utf'):
encoding = encoding.replace('-', '')
encoding = encoding.replace('-','_')
viewValue = _encodings.get(encoding)
self._encodingKey = encoding
index = self._encodingComboBox.findText(viewValue.upper())
self._encodingComboBox.setCurrentIndex(index)
def _guessEncoding(self, path):
"""Opens a file from the given `path` and checks the file encoding.
The file must exists on the file system and end with the extension
`.csv`. The file is read line by line until the encoding could be
guessed.
On a successfull identification, the widgets of this dialog will be
updated.
Args:
path (string): Path to a csv file on the file system.
"""
if os.path.exists(path) and path.lower().endswith('csv'):
# encoding = self._detector.detect(path)
encoding = None
if encoding is not None:
if encoding.startswith('utf'):
encoding = encoding.replace('-', '')
encoding = encoding.replace('-', '_')
viewValue = _encodings.get(encoding)
self._encodingKey = encoding
index = self._encodingComboBox.findText(viewValue.upper())
self._encodingComboBox.setCurrentIndex(index)
def get_encoding(stream): """ Return stream encoding. """ enc = None if stream in (sys.stdin, sys.stdout, sys.stderr): if sys.platform == "darwin": # There is no way to determine it reliably under OS X 10.4? return "UTF-8" elif sys.platform == "win32": if sys.version_info >= (2, 6): # Windows/Python 2.6+: If a locale is set, the actual encoding # of stdio changes, but the encoding attribute isn't updated enc = locale.getlocale()[1] if not enc: try: if stream is (sys.stdin): enc = aliases.get(str(GetConsoleCP())) else: enc = aliases.get(str(GetConsoleOutputCP())) except: pass enc = enc or getattr(stream, "encoding", None) or \ locale.getpreferredencoding() or sys.getdefaultencoding() return enc
def get_encoding(stream):
""" Return stream encoding. """
enc = None
if stream in (sys.stdin, sys.stdout, sys.stderr):
if sys.platform == "darwin":
# There is no way to determine it reliably under OS X 10.4?
return "UTF-8"
elif sys.platform == "win32":
if sys.version_info >= (2, 6):
# Windows/Python 2.6+: If a locale is set, the actual encoding
# of stdio changes, but the encoding attribute isn't updated
enc = locale.getlocale()[1]
if not enc:
try:
if stream is (sys.stdin):
enc = aliases.get(str(GetConsoleCP()))
else:
enc = aliases.get(str(GetConsoleOutputCP()))
except:
pass
enc = enc or getattr(stream, "encoding", None) or \
locale.getpreferredencoding() or sys.getdefaultencoding()
return enc
def __init__(self):
self.content_type = None
self.status = None
self.response = None
self.charset = None
self.charsets = {
key.replace('_', ''): aliases.get(key).replace('_', '-')
for key in aliases.keys()
}
self.types = {
'json': 'application/json',
'xml': 'application/xml',
'soap': 'application/soap+xml'
}
self.transactions = None
def analyze_charset_data(iana_data):
"""Extract data from the IANA character sets definitions.
@param iana_data: definitions of characters.
@type iana_data: line-iterable (file, list of string...)
"""
global charsets
# Note: All character sets definitions begin by Name: and finish by a
# white line.
NAMEKEYWORD = "Name: "
MIBKEYWORD = "MIBenum: "
ALIASKEYWORD = "Alias: "
in_setdef = False
name = None
mib = None
aliases = []
mime = None
pyenc = None
for line in iana_data:
line = line.strip()
if not in_setdef:
if line.startswith(NAMEKEYWORD): # Start of an entry.
# The name line can have extra characters:
# Name: xxxxx [ref1,ref2]
# Name: xxxxx (preffered MIME name) [ref1,ref2]
name = line.split()[1]
if "preferred MIME name" in line: mime = name
in_setdef = True
if DEBUG: print "Found", name
continue
if not line.strip():
if not name: continue
# End of an entry.
# Search a Python correspondance from one of name/alias.
for n in [name] + aliases:
pyenc = encoding_aliases.get(normenc(n), None)
if pyenc: break
if DEBUG: print "End", name
# Make object (it auto-register in dicts/lists).
CharacterSet(name, mib, aliases, mime, pyenc)
# Reset...
name = None
mib = None
aliases = []
mime = None
pyenc = None
in_setdef = False
continue
# Keep data in set definition.
if line.startswith(MIBKEYWORD):
mib = int(line[len(MIBKEYWORD):])
elif line.startswith(ALIASKEYWORD):
alias = line[len(ALIASKEYWORD):]
if alias == "None": continue
# ... yes, there are lines with "Alias: None" ...
if "preferred MIME name" in alias:
alias = alias.split()[0]
mime = alias
aliases.append(alias.strip())
def analyze_charset_data(iana_data) :
"""Extract data from the IANA character sets definitions.
@param iana_data: definitions of characters.
@type iana_data: line-iterable (file, list of string...)
"""
global charsets
# Note: All character sets definitions begin by Name: and finish by a
# white line.
NAMEKEYWORD = "Name: "
MIBKEYWORD = "MIBenum: "
ALIASKEYWORD = "Alias: "
in_setdef = False
name = None
mib = None
aliases = []
mime = None
pyenc = None
for line in iana_data :
line = line.strip()
if not in_setdef :
if line.startswith(NAMEKEYWORD) : # Start of an entry.
# The name line can have extra characters:
# Name: xxxxx [ref1,ref2]
# Name: xxxxx (preffered MIME name) [ref1,ref2]
name = line.split()[1]
if "preferred MIME name" in line : mime = name
in_setdef = True
if DEBUG : print "Found",name
continue
if not line.strip() :
if not name : continue
# End of an entry.
# Search a Python correspondance from one of name/alias.
for n in [name]+aliases :
pyenc = encoding_aliases.get(normenc(n),None)
if pyenc : break
if DEBUG : print "End",name
# Make object (it auto-register in dicts/lists).
CharacterSet(name,mib,aliases,mime,pyenc)
# Reset...
name = None
mib = None
aliases = []
mime = None
pyenc = None
in_setdef = False
continue
# Keep data in set definition.
if line.startswith(MIBKEYWORD) :
mib = int(line[len(MIBKEYWORD):])
elif line.startswith(ALIASKEYWORD) :
alias = line[len(ALIASKEYWORD):]
if alias == "None" : continue
# ... yes, there are lines with "Alias: None" ...
if "preferred MIME name" in alias :
alias = alias.split()[0]
mime = alias
aliases.append(alias.strip())
