def pt_edit(self, text, content_type, keep_output_encoding=False):
text = text.strip()
is_unicode = isinstance(text, unicode)
encoding = None
output_encoding = None
if content_type.startswith('text/xml'):
if is_unicode:
encoding = None
output_encoding = 'utf-8'
else:
encoding = encodingFromXMLPreamble(text)
output_encoding = 'utf-8'
elif content_type.startswith('text/html'):
charset = charsetFromMetaEquiv(text)
if is_unicode:
if charset:
encoding = None
output_encoding = charset
else:
encoding = None
output_encoding = 'iso-8859-15'
else:
if charset:
encoding = charset
output_encoding = charset
else:
encoding = 'iso-8859-15'
output_encoding = 'iso-8859-15'
else:
utext, encoding = convertToUnicode(text,
content_type,
preferred_encodings)
output_encoding = encoding
# for content updated through WebDAV, FTP
if not keep_output_encoding:
self.output_encoding = output_encoding
if not is_unicode:
text = unicode(text, encoding)
self.ZCacheable_invalidate()
super(ZopePageTemplate, self).pt_edit(text, content_type)
def _readFile(self, reparse):
"""Read the data from the filesystem.
"""
if reparse:
file = open(self._filepath,
'rU') # not 'rb', as this is a text file!
try:
data = file.read()
finally:
file.close()
# If we already have a content_type set it must come from a
# .metadata file and we should always honor that. The content
# type is initialized as text/html by default, so we only
# attempt further detection if the default is encountered.
# One previous misbehavior remains: It is not possible to
# force a text./html type if parsing detects it as XML.
encoding = None
if getattr(self, 'content_type', 'text/html') == 'text/html':
xml_info = xml_detect_re.match(data)
if xml_info:
# Smells like xml
# set "content_type" from the XML declaration
encoding = xml_info.group(1) or 'utf-8'
self.content_type = 'text/xml; charset=%s' % encoding
if encoding is None:
charset = getattr(self, 'charset', None)
if charset is None:
if self.content_type.startswith('text/html'):
charset = charsetFromMetaEquiv(data) or 'iso-8859-15'
elif self.content_type.startswith('text/xml'):
charset = encodingFromXMLPreamble(data)
else:
raise ValueError('Unsupported content-type: %s' %
self.content_type)
if not isinstance(data, unicode):
data = unicode(data, charset)
else:
if not isinstance(data, unicode):
data = unicode(data, encoding)
self.write(data)
def _readFile(self, reparse):
"""Read the data from the filesystem.
"""
file = open(self._filepath, 'rU') # not 'rb', as this is a text file!
try:
data = file.read()
finally:
file.close()
if reparse:
# If we already have a content_type set it must come from a
# .metadata file and we should always honor that. The content
# type is initialized as text/html by default, so we only
# attempt further detection if the default is encountered.
# One previous misbehavior remains: It is not possible to
# force a text./html type if parsing detects it as XML.
encoding = None
if getattr(self, 'content_type', 'text/html') == 'text/html':
xml_info = xml_detect_re.match(data)
if xml_info:
# Smells like xml
# set "content_type" from the XML declaration
encoding = xml_info.group(1) or 'utf-8'
self.content_type = 'text/xml; charset=%s' % encoding
if encoding is None:
charset = getattr(self, 'charset', None)
if charset is None:
if self.content_type.startswith('text/html'):
charset = charsetFromMetaEquiv(data) or 'iso-8859-15'
elif self.content_type.startswith('text/xml'):
charset = encodingFromXMLPreamble(data)
else:
raise ValueError('Unsupported content-type: %s' % self.content_type)
if not isinstance(data, unicode):
data = unicode(data, charset)
else:
if not isinstance(data, unicode):
data = unicode(data, encoding)
self.write(data)
def _readFile(self, reparse):
"""Read the data from the filesystem.
"""
if reparse:
if six.PY2:
# not 'rb', as this is a text file!
file = open(self._filepath, 'rU')
else:
file = open(self._filepath, 'br')
try:
data = file.read()
if not six.PY2:
data = data.replace(b'\r\n', b'\n').replace(b'\r', b'\n')
finally:
file.close()
# If we already have a content_type set it must come from a
# .metadata file and we should always honor that. The content
# type is initialized as text/html by default, so we only
# attempt further detection if the default is encountered.
# One previous misbehavior remains: It is not possible to
# force a text/html type if parsing detects it as XML.
encoding = None
preferred = preferred_encodings[:]
if getattr(self, 'content_type', 'text/html') == 'text/html':
xml_info = xml_detect_re.match(data)
if xml_info:
# Smells like xml
# set "content_type" from the XML declaration
encoding = xml_info.group(1) or 'utf-8'
self.content_type = 'text/xml; charset=%s' % encoding
if not isinstance(data, six.text_type):
if encoding is None:
charset = getattr(self, 'charset', None)
if charset is None:
if self.content_type.startswith('text/html'):
mo = charset_re.search(self.content_type)
if mo:
charset = mo.group(1).lower()
if charset is None:
charset = charsetFromMetaEquiv(data)
elif self.content_type.startswith('text/xml'):
charset = encodingFromXMLPreamble(data)
else:
raise ValueError('Unsupported content_type: %s' %
self.content_type)
if charset is not None:
preferred.insert(0, charset)
else:
preferred.insert(0, encoding)
for enc in preferred:
try:
data = six.text_type(data, enc)
if isinstance(data, six.text_type):
break
except UnicodeDecodeError:
continue
else:
data = six.text_type(data)
self.write(data)
def _readFile(self, reparse):
"""Read the data from the filesystem.
"""
if reparse:
if six.PY2:
# not 'rb', as this is a text file!
file = open(self._filepath, 'rU')
else:
file = open(self._filepath, 'br')
try:
data = file.read()
if not six.PY2:
data = data.replace(b'\r\n', b'\n').replace(b'\r', b'\n')
finally:
file.close()
# If we already have a content_type set it must come from a
# .metadata file and we should always honor that. The content
# type is initialized as text/html by default, so we only
# attempt further detection if the default is encountered.
# One previous misbehavior remains: It is not possible to
# force a text/html type if parsing detects it as XML.
encoding = None
preferred = preferred_encodings[:]
if getattr(self, 'content_type', 'text/html') == 'text/html':
xml_info = xml_detect_re.match(data)
if xml_info:
# Smells like xml
# set "content_type" from the XML declaration
encoding = xml_info.group(1) or 'utf-8'
self.content_type = 'text/xml; charset=%s' % encoding
if not isinstance(data, six.text_type):
if encoding is None:
charset = getattr(self, 'charset', None)
if charset is None:
if self.content_type.startswith('text/html'):
mo = charset_re.search(self.content_type)
if mo:
charset = mo.group(1).lower()
if charset is None:
charset = charsetFromMetaEquiv(data)
elif self.content_type.startswith('text/xml'):
charset = encodingFromXMLPreamble(data)
else:
raise ValueError('Unsupported content_type: %s' %
self.content_type)
if charset is not None:
preferred.insert(0, charset)
else:
preferred.insert(0, encoding)
for enc in preferred:
try:
data = six.text_type(data, enc)
if isinstance(data, six.text_type):
break
except UnicodeDecodeError:
continue
else:
data = six.text_type(data)
self.write(data)
