This is an archive of the discontinued Mercurial Phabricator instance.

Differential D3954

mail: cope with Py3 unicode antics on email addresses
ClosedPublic

Authored by durin42 on Jul 16 2018, 7:16 PM.

Details

Reviewers
None
Group Reviewers
hg-reviewers
Commits
rHGeabdf3c25b8b: mail: cope with Py3 unicode antics on email addresses
Summary

Diff Detail

Repository
rHG Mercurial
Lint
Lint Skipped
Unit
Unit Tests Skipped

Event Timeline

durin42 created this revision.Jul 16 2018, 7:16 PM
yuja added a subscriber: yuja.Jul 17 2018, 9:25 AM
  • return email.utils.formataddr((name, addr))

+ return pycompat.bytesurl(
+ email.utils.formataddr((name, addr.decode('ascii'))))

Maybe this would bring unicode to Python 2.

def addressencode(ui, address, charsets=None, display=False):

'''Turns address into RFC-2047 compliant header.'''
if display or not address:
    return address or ''
  • name, addr = email.utils.parseaddr(address)

+ name, addr = email.utils.parseaddr(pycompat.strurl(address))

strurl() is too strict to convert a user input. encoding.strfromlocal()
can be used instead.

result = []
  • for name, addr in email.utils.getaddresses(addrs):

+ for name, addr in email.utils.getaddresses(
+ [pycompat.strurl(a) for a in addrs]):

Same here.

durin42 updated this revision to Diff 10190.Aug 9 2018, 4:43 PM
durin42 updated this revision to Diff 10194.Aug 9 2018, 4:48 PM
Closed by commit rHGeabdf3c25b8b: mail: cope with Py3 unicode antics on email addresses (authored by durin42). · Explain WhyAug 9 2018, 11:00 PM
This revision was automatically updated to reflect the committed changes.
yuja added a comment.Aug 11 2018, 10:17 PM

def _addressencode(ui, name, addr, charsets=None):

name = headencode(ui, name, charsets)
try:
  • acc, dom = addr.split('@')

+ acc, dom = addr.split(r'@')

I think addr here should be a byte string since dom is decoded to unicode,
and addr is embedded in abort message.

acc = acc.encode('ascii')
dom = dom.decode(encoding.encoding).encode('idna')
addr = '%s@%s' % (acc, dom)

@@ -311,27 +311,31 @@

    addr = addr.encode('ascii')
except UnicodeDecodeError:
    raise error.Abort(_('invalid local address: %s') % addr)
  • return email.utils.formataddr((name, addr))

+ return pycompat.bytesurl(
+ email.utils.formataddr((name, encoding.strfromlocal(addr))))

result = []
  • for name, addr in email.utils.getaddresses(addrs):

+ for name, addr in email.utils.getaddresses(
+ [encoding.strfromlocal(a) for a in addrs]):

if name or addr:
    result.append(_addressencode(ui, name, addr, charsets))
  • return result

+ return [pycompat.bytesurl(r) for r in result]

_addressencode() retunrs bytes.

Revision Contents
Changeset List

PathPackages
Mmercurial/mail.py (14 lines)

Diff 10194

mercurial/mail.py

# split into words? # split into words?
s, cs = _encode(ui, s, charsets) s, cs = _encode(ui, s, charsets)
return str(email.header.Header(s, cs)) return str(email.header.Header(s, cs))
return s return s
def _addressencode(ui, name, addr, charsets=None): def _addressencode(ui, name, addr, charsets=None):
name = headencode(ui, name, charsets) name = headencode(ui, name, charsets)
try: try:
acc, dom = addr.split('@') acc, dom = addr.split(r'@')
acc = acc.encode('ascii') acc = acc.encode('ascii')
dom = dom.decode(encoding.encoding).encode('idna') dom = dom.decode(encoding.encoding).encode('idna')
addr = '%s@%s' % (acc, dom) addr = '%s@%s' % (acc, dom)
except UnicodeDecodeError: except UnicodeDecodeError:
raise error.Abort(_('invalid email address: %s') % addr) raise error.Abort(_('invalid email address: %s') % addr)
except ValueError: except ValueError:
try: try:
# too strict? # too strict?
addr = addr.encode('ascii') addr = addr.encode('ascii')
except UnicodeDecodeError: except UnicodeDecodeError:
raise error.Abort(_('invalid local address: %s') % addr) raise error.Abort(_('invalid local address: %s') % addr)
return email.utils.formataddr((name, addr)) return pycompat.bytesurl(
email.utils.formataddr((name, encoding.strfromlocal(addr))))
def addressencode(ui, address, charsets=None, display=False): def addressencode(ui, address, charsets=None, display=False):
'''Turns address into RFC-2047 compliant header.''' '''Turns address into RFC-2047 compliant header.'''
if display or not address: if display or not address:
return address or '' return address or ''
name, addr = email.utils.parseaddr(address) name, addr = email.utils.parseaddr(encoding.strfromlocal(address))
return _addressencode(ui, name, addr, charsets) return _addressencode(ui, name, addr, charsets)
def addrlistencode(ui, addrs, charsets=None, display=False): def addrlistencode(ui, addrs, charsets=None, display=False):
'''Turns a list of addresses into a list of RFC-2047 compliant headers. '''Turns a list of addresses into a list of RFC-2047 compliant headers.
A single element of input list may contain multiple addresses, but output A single element of input list may contain multiple addresses, but output
always has one address per item''' always has one address per item'''
for a in addrs:
assert isinstance(a, bytes), (r'%r unexpectedly not a bytestr' % a)
if display: if display:
return [a.strip() for a in addrs if a.strip()] return [a.strip() for a in addrs if a.strip()]
result = [] result = []
for name, addr in email.utils.getaddresses(addrs): for name, addr in email.utils.getaddresses(
[encoding.strfromlocal(a) for a in addrs]):
if name or addr: if name or addr:
result.append(_addressencode(ui, name, addr, charsets)) result.append(_addressencode(ui, name, addr, charsets))
return result return [pycompat.bytesurl(r) for r in result]
def mimeencode(ui, s, charsets=None, display=False): def mimeencode(ui, s, charsets=None, display=False):
'''creates mime text object, encodes it if needed, and sets '''creates mime text object, encodes it if needed, and sets
charset and transfer-encoding accordingly.''' charset and transfer-encoding accordingly.'''
cs = 'us-ascii' cs = 'us-ascii'
if not display: if not display:
s, cs = _encode(ui, s, charsets) s, cs = _encode(ui, s, charsets)
return mimetextqp(s, 'plain', cs) return mimetextqp(s, 'plain', cs)