def convert_to_utf8(self, filename):
# try to open the file and exit if some IOError occurs
"""
:param filename:
"""
try:
f = open(filename, 'r').read()
print fastchardet.detect(f)
except Exception:
sys.exit(1)
try:
encoding_ = fastchardet.detect(f)['encoding']
if encoding_ and encoding_=="ANSI":
data = f.decode(encoding_)
# now get the absolute path of our filename and append .bak
# to the end of it (for our backup file)
fpath = os.path.abspath(filename)
newfilename = fpath + '.bak'
# and make our backup file with shutil
shutil.copy(filename, newfilename)
# and at last convert it to utf-8
f = open(filename, 'w')
try:
f.write(data.encode('utf-8'))
except Exception, e:
print e
finally:
f.close()
def convert_to_utf8(self, filename):
# try to open the file and exit if some IOError occurs
"""
:param filename:
"""
try:
f = open(filename, 'r').read()
print fastchardet.detect(f)
except Exception:
sys.exit(1)
try:
encoding_ = fastchardet.detect(f)['encoding']
if encoding_ and encoding_ == "ANSI":
data = f.decode(encoding_)
# now get the absolute path of our filename and append .bak
# to the end of it (for our backup file)
fpath = os.path.abspath(filename)
newfilename = fpath + '.bak'
# and make our backup file with shutil
shutil.copy(filename, newfilename)
# and at last convert it to utf-8
f = open(filename, 'w')
try:
f.write(data.encode('utf-8'))
except Exception, e:
print e
finally:
f.close()
def _parse_l10n_doc(name, doc, no_encoding=False):
'Parses an L10n document.'
extension = name.split('.')[-1].lower()
handlers = {'dtd': dtd.DTDParser,
'properties': properties.PropertiesParser}
# These are expected encodings for the various files.
handler_formats = ('ASCII', 'UTF_8')
if extension not in handlers:
return None
wrapper = StringIO(doc)
loc_doc = handlers[extension](wrapper)
# Allow the parse to specify files to skip for encoding checks
if not no_encoding:
try:
# This is much faster than fastchardet, and succeeds more often
# than fails.
doc.decode('utf-8')
encoding = 'UTF_8'
except UnicodeDecodeError:
encoding = fastchardet.detect(doc)['encoding'].upper()
loc_doc.expected_encoding = encoding in handler_formats
loc_doc.suitable_encoding = handler_formats
return loc_doc
def test_unicode():
"""
Make sure that things turn out right when we're silly sallies and pass
unicode in.
"""
assert fastchardet.detect(unicode('foo'))['encoding'] == 'unicode'
def _parse_l10n_doc(name, doc, no_encoding=False):
'Parses an L10n document.'
extension = name.split('.')[-1].lower()
handlers = {
'dtd': dtd.DTDParser,
'properties': properties.PropertiesParser
}
# These are expected encodings for the various files.
handler_formats = ('ASCII', 'UTF_8')
if extension not in handlers:
return None
wrapper = StringIO(doc)
loc_doc = handlers[extension](wrapper)
# Allow the parse to specify files to skip for encoding checks
if not no_encoding:
try:
# This is much faster than fastchardet, and succeeds more often
# than fails.
doc.decode('utf-8')
encoding = 'UTF_8'
except UnicodeDecodeError:
encoding = fastchardet.detect(doc)['encoding'].upper()
loc_doc.expected_encoding = encoding in handler_formats
loc_doc.suitable_encoding = handler_formats
return loc_doc
def test_unicode():
"""
Make sure that things turn out right when we're silly sallies and pass
unicode in.
"""
assert fastchardet.detect(unicode("foo"))["encoding"] == "unicode"
def test_esoteric():
"""Make sure that fastchardet can detect other encodings."""
a = lambda code: fastchardet.detect(code)['encoding']
# High Bytes
print a('High Byte:\x91')
assert a('High Byte:\x91') == 'windows-1252'
# UTF-8 without BOM
print a('\xc2\xbc + \xc2\xbd = \xcd\xbe')
assert a('\xc2\xbc + \xc2\xbd = \xcd\xbe') == 'utf_8'
def test_esoteric():
"""Make sure that fastchardet can detect other encodings."""
a = lambda code: fastchardet.detect(code)["encoding"]
# High Bytes
print a("High Byte:\x91")
assert a("High Byte:\x91") == "windows-1252"
# UTF-8 without BOM
print a("\xc2\xbc + \xc2\xbd = \xcd\xbe")
assert a("\xc2\xbc + \xc2\xbd = \xcd\xbe") == "utf_8"
def _parse_l10n_doc(name, doc, no_encoding=False):
"Parses an L10n document."
extension = name.split(".")[-1].lower()
handlers = {"dtd": dtd.DTDParser, "properties": properties.PropertiesParser}
# These are expected encodings for the various files.
handler_formats = ("ASCII", "UTF_8")
if extension not in handlers:
return None
wrapper = StringIO(doc)
loc_doc = handlers[extension](wrapper)
# Allow the parse to specify files to skip for encoding checks
if not no_encoding:
encoding = fastchardet.detect(doc)["encoding"].upper()
loc_doc.expected_encoding = encoding in handler_formats
loc_doc.suitable_encoding = handler_formats
return loc_doc
def _parse_l10n_doc(name, doc, no_encoding=False):
"Parses an L10n document."
extension = name.split(".")[-1].lower()
handlers = {
"dtd": dtd.DTDParser,
"properties": properties.PropertiesParser
}
# These are expected encodings for the various files.
handler_formats = ("ASCII", "UTF_8")
if extension not in handlers:
return None
wrapper = StringIO(doc)
loc_doc = handlers[extension](wrapper)
# Allow the parse to specify files to skip for encoding checks
if not no_encoding:
encoding = fastchardet.detect(doc)["encoding"].upper()
loc_doc.expected_encoding = encoding in handler_formats
loc_doc.suitable_encoding = handler_formats
return loc_doc
def test_utf8():
"""Determine that fastchardet properly detects UTF-8."""
assert fastchardet.detect("""\xEF\xBB\xBF
Haldo, UTF-8
""")['encoding'] == 'utf_8'
def test_ascii():
"""Determines that fastchardet detects ASCII properly."""
assert fastchardet.detect('This is plain ASCII')['encoding'] == 'ascii'
def test_utfn():
"""Determine that fastchardet properly detects UTF-N."""
assert fastchardet.detect("""\xFF\xFE\x00\x00
Haldo, UTF-Not 8
""")['encoding'] == 'utf_n'
def test_utf8():
"""Determine that fastchardet properly detects UTF-8."""
assert fastchardet.detect("""\xEF\xBB\xBF
Haldo, UTF-8
""")["encoding"] == "utf_8"
def test_ascii():
"""Determines that fastchardet detects ASCII properly."""
assert fastchardet.detect("This is plain ASCII")["encoding"] == "ascii"
def test_utfn():
"""Determine that fastchardet properly detects UTF-N."""
assert fastchardet.detect("""\xFF\xFE\x00\x00
Haldo, UTF-Not 8
""")["encoding"] == "utf_n"
