Skip to content

erp5
erp5
Commit d41e23bd authored by Nicolas Wavrant's avatar Nicolas Wavrant
Browse files
Options

create a Mixin out of EmailDocument 

This mixin contains all the methods returning values based on the mail message
itself contained in the data property of the EmailDocument.
parent 997ab603
Hide whitespace changes
Inline Side-by-side
Showing with 305 additions and 237 deletions
product/ERP5/Document/EmailDocument.py
View file @ d41e23bd
......@@ -37,6 +37,7 @@ from Products.ERP5Type import Permissions, PropertySheet
from Products.ERP5.Document.TextDocument import TextDocument
from Products.ERP5.Document.File import File
from Products.ERP5.Document.Document import ConversionError
from Products.ERP5.mixin.mail_message import MailMessageMixin, testCharsetAndConvert
from Products.ERP5.mixin.document_proxy import DocumentProxyMixin, DocumentProxyError
from Products.ERP5.Tool.NotificationTool import buildEmailMessage
from Products.ERP5Type.Utils import guessEncodingFromText
......@@ -122,7 +123,7 @@ for method_id in ('getContentType',
setattr(EmailDocumentProxyMixin, method_id,
ProxiedMethod(method_id))
class EmailDocument(TextDocument):
class EmailDocument(TextDocument, MailMessageMixin):
"""
EmailDocument is a File which stores its metadata in a form which
is similar to a TextDocument.
......@@ -187,37 +188,6 @@ class EmailDocument(TextDocument):
except AttributeError:
pass
def _getMessageTextPart(self):
"""
Return the main text part of the message data
Based on rfc: http://tools.ietf.org/html/rfc2046#section-5.1.4)
"""
# Default value if no text is found
found_part = None
part_list = [self._getMessage()]
while part_list:
part = part_list.pop(0)
if part.is_multipart():
if part.get_content_subtype() == 'alternative':
# Try to get the favourite text format defined on preference
preferred_content_type = self.getPortalObject().portal_preferences.\
getPreferredTextFormat('text/html')
favourite_part = None
for subpart in part.get_payload():
if subpart.get_content_type() == preferred_content_type:
part_list.insert(0, subpart)
else:
part_list.append(subpart)
else:
part_list.extend(part.get_payload())
elif part.get_content_maintype() == 'text':
found_part = part
break
return found_part
security.declareProtected(Permissions.AccessContentsInformation,
'isSupportBaseDataConversion')
def isSupportBaseDataConversion(self):
......@@ -225,193 +195,6 @@ class EmailDocument(TextDocument):
"""
return False
security.declareProtected(Permissions.AccessContentsInformation, 'getContentInformation')
def getContentInformation(self):
"""
Returns the content information from the header information.
This is used by the metadata discovery system.
Header information is converted in UTF-8 since this is the standard
way of representing strings in ERP5.
"""
result = {}
for (name, value) in self._getMessage().items():
try:
decoded_header = decode_header(value)
except HeaderParseError, error_message:
decoded_header = ()
LOG('EmailDocument.getContentInformation', INFO,
'Failed to decode %s header of %s with error: %s' %
(name, self.getPath(), error_message))
for text, encoding in decoded_header:
text, encoding = testCharsetAndConvert(text, 'text/plain', encoding)
if name in result:
result[name] = '%s %s' % (result[name], text)
else:
result[name] = text
return result
security.declareProtected(Permissions.AccessContentsInformation, 'getAttachmentInformationList')
def getAttachmentInformationList(self, **kw):
"""
Returns a list of dictionnaries for every attachment. Each dictionnary
represents the metadata of the attachment.
**kw - support for listbox (TODO: improve it)
"""
result = []
for i, part in enumerate(self._getMessage().walk()):
if not part.is_multipart():
kw = dict(part.items())
kw['uid'] = 'part_%s' % i
kw['index'] = i
filename = part.get_filename()
if not filename:
# get_filename return name only from Content-Disposition header
# of the message but sometimes this value is stored in
# Content-Type header
content_type_header = kw.get('Content-Type',
kw.get('Content-type', ''))
filename_list = re.findall(filename_regexp,
content_type_header,
re.MULTILINE)
if filename_list:
filename = filename_list[0]
if filename:
kw['filename'] = filename
else:
content_disposition = kw.get('Content-Disposition',
kw.get('Content-disposition', None))
prefix = 'part_'
if content_disposition:
if content_disposition.split(';')[0] == 'attachment':
prefix = 'attachment_'
elif content_disposition.split(';')[0] == 'inline':
prefix = 'inline_'
kw['filename'] = '%s%s' % (prefix, i)
kw['content_type'] = part.get_content_type()
result.append(kw)
return result
security.declareProtected(Permissions.AccessContentsInformation, 'getAttachmentData')
def getAttachmentData(self, index, REQUEST=None):
"""
Returns the decoded data of an attachment.
"""
for i, part in enumerate(self._getMessage().walk()):
if index == i:
# This part should be handled in skin script
# but it was a bit easier to access items here
kw = dict(part.items())
content_type = part.get_content_type()
if REQUEST is not None:
filename = part.get_filename()
if not filename:
# get_filename return name only from Content-Disposition header
# of the message but sometimes this value is stored in
# Content-Type header
content_type_header = kw.get('Content-Type',
kw.get('Content-type', ''))
filename_list = re.findall(filename_regexp,
content_type_header,
re.MULTILINE)
if filename_list:
filename = filename_list[0]
RESPONSE = REQUEST.RESPONSE
RESPONSE.setHeader('Accept-Ranges', 'bytes')
if content_type and filename:
RESPONSE.setHeader('Content-Type', content_type)
RESPONSE.setHeader('Content-disposition',
'attachment; filename="%s"' % filename)
if 'text/html' in content_type:
part_encoding = part.get_content_charset()
message_text = part.get_payload(decode=1)
text_result, encoding = testCharsetAndConvert(message_text,
content_type,
part_encoding)
# Strip out html content in safe mode.
mime, content = self.convert(format='html',
text_content=text_result,
encoding=part_encoding,
index=index) # add index to generate
# a unique cache key per attachment
else:
content = part.get_payload(decode=1)
return content
return KeyError, "No attachment with index %s" % index
# Helper methods which override header property sheet
security.declareProtected(Permissions.AccessContentsInformation, 'getSender')
def getSender(self, *args):
"""
"""
if not self.hasData():
return self._baseGetSender(*args)
return self.getContentInformation().get('From', *args)
security.declareProtected(Permissions.AccessContentsInformation, 'getRecipient')
def getRecipient(self, *args):
"""
"""
if not self.hasData():
return self._baseGetRecipient(*args)
return self.getContentInformation().get('To', *args)
security.declareProtected(Permissions.AccessContentsInformation, 'getCcRecipient')
def getCcRecipient(self, *args):
"""
"""
if not self.hasData():
return self._baseGetCcRecipient(*args)
return self.getContentInformation().get('Cc', *args)
security.declareProtected(Permissions.AccessContentsInformation, 'getGroupingReference')
def getGroupingReference(self, *args):
"""
The reference refers here to the Thread of messages.
"""
if not self.hasData():
result = self._baseGetGroupingReference(*args)
else:
if not len(args):
args = (self._baseGetGroupingReference(),)
result = self.getContentInformation().get('References', *args)
if result:
result = result.split() # Only take the first reference
if result:
result = result[0]
if result:
return result
return self.getFilename(*args)
security.declareProtected(Permissions.AccessContentsInformation,
'getSourceReference')
def getSourceReference(self, *args):
"""
The Message-ID is considered here as the source reference
of the message on the sender side (source)
"""
if not self.hasData():
return self._baseGetSourceReference(*args)
if not len(args):
args = (self._baseGetSourceReference(),)
content_information = self.getContentInformation()
return content_information.get('Message-ID') or content_information.get('Message-Id', *args)
security.declareProtected(Permissions.AccessContentsInformation, 'getDestinationReference')
def getDestinationReference(self, *args):
"""
The In-Reply-To is considered here as the reference
of the thread on the side of a former sender (destination)
This is a hack which can be acceptable since
the reference of an email is shared.
"""
if not self.hasData():
return self._baseGetDestinationReference(*args)
if not len(args):
args = (self._baseGetDestinationReference(),)
return self.getContentInformation().get('In-Reply-To', *args)
# Overriden methods
security.declareProtected(Permissions.AccessContentsInformation, 'getTitle')
def getTitle(self, default=_MARKER):
......@@ -504,7 +287,7 @@ class EmailDocument(TextDocument):
else:
return part.get_content_type()
email_parser = re.compile('[ ;,<>\'"]*([^<> ;,\'"]+?\@[^<> ;,\'"]+)[ ;,<>\'"]*',re.IGNORECASE)
email_parser = re.compile('[ ;,<>\'"]*([^<> ;,\'"]+?\@[^<> ;,\'"]+)[ ;,<>\'"]*', re.IGNORECASE)
security.declareProtected(Permissions.AccessContentsInformation, 'getContentURLList')
def getContentURLList(self):
"""
......@@ -595,20 +378,4 @@ class EmailDocument(TextDocument):
# getData must be implemented like File.getData is.
security.declareProtected(Permissions.AccessContentsInformation, 'getData')
getData = File.getData
def testCharsetAndConvert(text_content, content_type, encoding):
try:
if encoding is not None:
text_content = text_content.decode(encoding).encode('utf-8')
else:
text_content = text_content.decode().encode('utf-8')
except (UnicodeDecodeError, LookupError), error_message:
encoding = guessEncodingFromText(text_content, content_type)
if encoding is not None:
try:
text_content = text_content.decode(encoding).encode('utf-8')
except (UnicodeDecodeError, LookupError):
text_content = repr(text_content)[1:-1]
else:
text_content = repr(text_content)[1:-1]
return text_content, encoding
getContentInformation = MailMessageMixin.getContentInformation
product/ERP5/mixin/mail_message.py 0 → 100644
View file @ d41e23bd
# -*- coding: utf-8 -*-
##############################################################################
#
# Copyright (c) 2002-2018 Nexedi SA and Contributors. All Rights Reserved.
#
# WARNING: This program as such is intended to be used by professional
# programmers who take the whole responsibility of assessing all potential
# consequences resulting from its eventual inadequacies and bugs
# End users who are looking for a ready-to-use solution with commercial
# guarantees and support are strongly adviced to contract a Free Software
# Service Company
#
# This program is Free Software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License
# as published by the Free Software Foundation; either version 2
# of the License, or (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
#
##############################################################################
from AccessControl import ClassSecurityInfo
from Products.ERP5Type.Globals import InitializeClass
from Products.ERP5Type import Permissions
from Products.ERP5Type.Utils import guessEncodingFromText
from Products.ERP5.Document.TextDocument import TextDocument
from zLOG import LOG, INFO
from email.header import decode_header, HeaderParseError
import re
filename_regexp = 'name="([^"]*)"'
def testCharsetAndConvert(text_content, content_type, encoding):
try:
if encoding is not None:
text_content = text_content.decode(encoding).encode('utf-8')
else:
text_content = text_content.decode().encode('utf-8')
except (UnicodeDecodeError, LookupError), error_message:
encoding = guessEncodingFromText(text_content, content_type)
if encoding is not None:
try:
text_content = text_content.decode(encoding).encode('utf-8')
except (UnicodeDecodeError, LookupError):
text_content = repr(text_content)[1:-1]
else:
text_content = repr(text_content)[1:-1]
return text_content, encoding
class MailMessageMixin:
"""
Contains methods to read email's content or metadata for the data property
of the self object.
Sub-classes should implement a self._getMessage function returning a python
instance of email.message.Message.
The methods of this Mixin were originally in the Product.ERP5.Document.EmailDocument
class, but have been moved in a mixin to be shared with InternetMessagePost.
"""
# Declarative security
security = ClassSecurityInfo()
security.declareObjectProtected(Permissions.AccessContentsInformation)
def _getMessage(self):
"""
Method to overwrite in children classes, as it is the base of all
other methods of the mixin.
It should return an instance of email.message.Message
"""
raise NotImplementedError
def _getMessageTextPart(self):
"""
Return the main text part of the message data
Based on rfc: http://tools.ietf.org/html/rfc2046#section-5.1.4)
"""
# Default value if no text is found
found_part = None
part_list = [self._getMessage()]
while part_list:
part = part_list.pop(0)
if part.is_multipart():
if part.get_content_subtype() == 'alternative':
# Try to get the favourite text format defined on preference
preferred_content_type = self.getPortalObject().portal_preferences.\
getPreferredTextFormat('text/html')
favourite_part = None
for subpart in part.get_payload():
if subpart.get_content_type() == preferred_content_type:
part_list.insert(0, subpart)
else:
part_list.append(subpart)
else:
part_list.extend(part.get_payload())
elif part.get_content_maintype() == 'text':
found_part = part
break
return found_part
security.declareProtected(Permissions.AccessContentsInformation, 'getContentInformation')
def getContentInformation(self):
"""
Returns the content information from the header information.
This is used by the metadata discovery system.
Header information is converted in UTF-8 since this is the standard
way of representing strings in ERP5.
"""
result = {}
for (name, value) in self._getMessage().items():
try:
decoded_header = decode_header(value)
except HeaderParseError, error_message:
decoded_header = ()
LOG('MailMessageMixin.getContentInformation', INFO,
'Failed to decode %s header of %s with error: %s' %
(name, self.getPath(), error_message))
for text, encoding in decoded_header:
text, encoding = testCharsetAndConvert(text, 'text/plain', encoding)
if name in result:
result[name] = '%s %s' % (result[name], text)
else:
result[name] = text
return result
security.declareProtected(Permissions.AccessContentsInformation, 'getAttachmentInformationList')
def getAttachmentInformationList(self, **kw):
"""
Returns a list of dictionnaries for every attachment. Each dictionnary
represents the metadata of the attachment.
**kw - support for listbox (TODO: improve it)
"""
result = []
for i, part in enumerate(self._getMessage().walk()):
if not part.is_multipart():
kw = dict(part.items())
kw['uid'] = 'part_%s' % i
kw['index'] = i
filename = part.get_filename()
if not filename:
# get_filename return name only from Content-Disposition header
# of the message but sometimes this value is stored in
# Content-Type header
content_type_header = kw.get('Content-Type',
kw.get('Content-type', ''))
filename_list = re.findall(filename_regexp,
content_type_header,
re.MULTILINE)
if filename_list:
filename = filename_list[0]
if filename:
kw['filename'] = filename
else:
content_disposition = kw.get('Content-Disposition',
kw.get('Content-disposition', None))
prefix = 'part_'
if content_disposition:
if content_disposition.split(';')[0] == 'attachment':
prefix = 'attachment_'
elif content_disposition.split(';')[0] == 'inline':
prefix = 'inline_'
kw['filename'] = '%s%s' % (prefix, i)
kw['content_type'] = part.get_content_type()
result.append(kw)
return result
security.declareProtected(Permissions.AccessContentsInformation, 'getAttachmentData')
def getAttachmentData(self, index, REQUEST=None):
"""
Returns the decoded data of an attachment.
"""
for i, part in enumerate(self._getMessage().walk()):
if index == i:
# This part should be handled in skin script
# but it was a bit easier to access items here
kw = dict(part.items())
content_type = part.get_content_type()
if REQUEST is not None:
filename = part.get_filename()
if not filename:
# get_filename return name only from Content-Disposition header
# of the message but sometimes this value is stored in
# Content-Type header
content_type_header = kw.get('Content-Type',
kw.get('Content-type', ''))
filename_list = re.findall(filename_regexp,
content_type_header,
re.MULTILINE)
if filename_list:
filename = filename_list[0]
RESPONSE = REQUEST.RESPONSE
RESPONSE.setHeader('Accept-Ranges', 'bytes')
if content_type and filename:
RESPONSE.setHeader('Content-Type', content_type)
RESPONSE.setHeader('Content-disposition',
'attachment; filename="%s"' % filename)
if 'text/html' in content_type:
part_encoding = part.get_content_charset()
message_text = part.get_payload(decode=1)
text_result, encoding = testCharsetAndConvert(message_text,
content_type,
part_encoding)
# Strip out html content in safe mode.
mime, content = self.convert(format='html',
text_content=text_result,
encoding=part_encoding,
index=index) # add index to generate
# a unique cache key per attachment
else:
content = part.get_payload(decode=1)
return content
return KeyError, "No attachment with index %s" % index
# Helper methods which override header property sheet
security.declareProtected(Permissions.AccessContentsInformation, 'getSender')
def getSender(self, *args):
"""
"""
if not self.hasData():
return self._baseGetSender(*args)
return self.getContentInformation().get('From', *args)
security.declareProtected(Permissions.AccessContentsInformation, 'getRecipient')
def getRecipient(self, *args):
"""
"""
if not self.hasData():
return self._baseGetRecipient(*args)
return self.getContentInformation().get('To', *args)
security.declareProtected(Permissions.AccessContentsInformation, 'getCcRecipient')
def getCcRecipient(self, *args):
"""
"""
if not self.hasData():
return self._baseGetCcRecipient(*args)
return self.getContentInformation().get('Cc', *args)
security.declareProtected(Permissions.AccessContentsInformation, 'getGroupingReference')
def getGroupingReference(self, *args):
"""
The reference refers here to the Thread of messages.
"""
if not self.hasData():
result = self._baseGetGroupingReference(*args)
else:
if not len(args):
args = (self._baseGetGroupingReference(),)
result = self.getContentInformation().get('References', *args)
if result:
result = result.split() # Only take the first reference
if result:
result = result[0]
if result:
return result
return self.getFilename(*args)
security.declareProtected(Permissions.AccessContentsInformation,
'getSourceReference')
def getSourceReference(self, *args):
"""
The Message-ID is considered here as the source reference
of the message on the sender side (source)
"""
if not self.hasData():
return self._baseGetSourceReference(*args)
if not len(args):
args = (self._baseGetSourceReference(),)
content_information = self.getContentInformation()
return content_information.get('Message-ID') or content_information.get('Message-Id', *args)
security.declareProtected(Permissions.AccessContentsInformation, 'getDestinationReference')
def getDestinationReference(self, *args):
"""
The In-Reply-To is considered here as the reference
of the thread on the side of a former sender (destination)
This is a hack which can be acceptable since
the reference of an email is shared.
"""
if not self.hasData():
return self._baseGetDestinationReference(*args)
if not len(args):
args = (self._baseGetDestinationReference(),)
return self.getContentInformation().get('In-Reply-To', *args)
InitializeClass(MailMessageMixin)
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7