def parse_docstring(docstring):
"""
Parse out the parts of a docstring. Return (title, body, metadata).
"""
docstring = trim_docstring(docstring)
parts = re.split(r'\n{2,}', docstring)
title = parts[0]
if len(parts) == 1:
body = ''
metadata = {}
else:
parser = HeaderParser()
try:
metadata = parser.parsestr(parts[-1])
except HeaderParseError:
metadata = {}
body = "\n\n".join(parts[1:])
else:
metadata = dict(metadata.items())
if metadata:
body = "\n\n".join(parts[1:-1])
else:
body = "\n\n".join(parts[1:])
return title, body, metadata
python类HeaderParseError()的实例源码
def test_set_boundary(self):
eq = self.assertEqual
# This one has no existing boundary parameter, but the Content-Type:
# header appears fifth.
msg = self._msgobj('msg_01.txt')
msg.set_boundary('BOUNDARY')
header, value = msg.items()[4]
eq(header.lower(), 'content-type')
eq(value, 'text/plain; charset="us-ascii"; boundary="BOUNDARY"')
# This one has a Content-Type: header, with a boundary, stuck in the
# middle of its headers. Make sure the order is preserved; it should
# be fifth.
msg = self._msgobj('msg_04.txt')
msg.set_boundary('BOUNDARY')
header, value = msg.items()[4]
eq(header.lower(), 'content-type')
eq(value, 'multipart/mixed; boundary="BOUNDARY"')
# And this one has no Content-Type: header at all.
msg = self._msgobj('msg_03.txt')
self.assertRaises(errors.HeaderParseError,
msg.set_boundary, 'BOUNDARY')
def parse_docstring(docstring):
"""
Parse out the parts of a docstring. Return (title, body, metadata).
"""
docstring = trim_docstring(docstring)
parts = re.split(r'\n{2,}', docstring)
title = parts[0]
if len(parts) == 1:
body = ''
metadata = {}
else:
parser = HeaderParser()
try:
metadata = parser.parsestr(parts[-1])
except HeaderParseError:
metadata = {}
body = "\n\n".join(parts[1:])
else:
metadata = dict(metadata.items())
if metadata:
body = "\n\n".join(parts[1:-1])
else:
body = "\n\n".join(parts[1:])
return title, body, metadata
def test_set_boundary(self):
eq = self.assertEqual
# This one has no existing boundary parameter, but the Content-Type:
# header appears fifth.
msg = self._msgobj('msg_01.txt')
msg.set_boundary('BOUNDARY')
header, value = msg.items()[4]
eq(header.lower(), 'content-type')
eq(value, 'text/plain; charset="us-ascii"; boundary="BOUNDARY"')
# This one has a Content-Type: header, with a boundary, stuck in the
# middle of its headers. Make sure the order is preserved; it should
# be fifth.
msg = self._msgobj('msg_04.txt')
msg.set_boundary('BOUNDARY')
header, value = msg.items()[4]
eq(header.lower(), 'content-type')
eq(value, 'multipart/mixed; boundary="BOUNDARY"')
# And this one has no Content-Type: header at all.
msg = self._msgobj('msg_03.txt')
self.assertRaises(errors.HeaderParseError,
msg.set_boundary, 'BOUNDARY')
def parse_docstring(docstring):
"""
Parse out the parts of a docstring. Return (title, body, metadata).
"""
docstring = trim_docstring(docstring)
parts = re.split(r'\n{2,}', docstring)
title = parts[0]
if len(parts) == 1:
body = ''
metadata = {}
else:
parser = HeaderParser()
try:
metadata = parser.parsestr(parts[-1])
except HeaderParseError:
metadata = {}
body = "\n\n".join(parts[1:])
else:
metadata = dict(metadata.items())
if metadata:
body = "\n\n".join(parts[1:-1])
else:
body = "\n\n".join(parts[1:])
return title, body, metadata
def get_subject_from_headers(headers):
"""
Get the subject of an email
:param `Message` headers: The SMTP headers of the email
:rtype: str
:return: The subject of the email
"""
subject = ''
subject_part = []
if 'Subject' in headers and headers['Subject'] is not None:
try:
decodefrag = decode_header(headers['Subject'])
except HeaderParseError:
return subject
for line, encoding in decodefrag:
enc = 'utf-8' if encoding is None or encoding == 'unknown' else encoding
subject_part.append(utils.decode_every_charset_in_the_world(line, enc))
subject = ''.join(subject_part)[:1023]
return subject
def parse_docstring(docstring):
"""
Parse out the parts of a docstring. Return (title, body, metadata).
"""
docstring = trim_docstring(docstring)
parts = re.split(r'\n{2,}', docstring)
title = parts[0]
if len(parts) == 1:
body = ''
metadata = {}
else:
parser = HeaderParser()
try:
metadata = parser.parsestr(parts[-1])
except HeaderParseError:
metadata = {}
body = "\n\n".join(parts[1:])
else:
metadata = dict(metadata.items())
if metadata:
body = "\n\n".join(parts[1:-1])
else:
body = "\n\n".join(parts[1:])
return title, body, metadata
def test_set_boundary(self):
eq = self.assertEqual
# This one has no existing boundary parameter, but the Content-Type:
# header appears fifth.
msg = self._msgobj('msg_01.txt')
msg.set_boundary('BOUNDARY')
header, value = msg.items()[4]
eq(header.lower(), 'content-type')
eq(value, 'text/plain; charset="us-ascii"; boundary="BOUNDARY"')
# This one has a Content-Type: header, with a boundary, stuck in the
# middle of its headers. Make sure the order is preserved; it should
# be fifth.
msg = self._msgobj('msg_04.txt')
msg.set_boundary('BOUNDARY')
header, value = msg.items()[4]
eq(header.lower(), 'content-type')
eq(value, 'multipart/mixed; boundary="BOUNDARY"')
# And this one has no Content-Type: header at all.
msg = self._msgobj('msg_03.txt')
self.assertRaises(errors.HeaderParseError,
msg.set_boundary, 'BOUNDARY')
def test_set_boundary(self):
eq = self.assertEqual
# This one has no existing boundary parameter, but the Content-Type:
# header appears fifth.
msg = self._msgobj('msg_01.txt')
msg.set_boundary('BOUNDARY')
header, value = msg.items()[4]
eq(header.lower(), 'content-type')
eq(value, 'text/plain; charset="us-ascii"; boundary="BOUNDARY"')
# This one has a Content-Type: header, with a boundary, stuck in the
# middle of its headers. Make sure the order is preserved; it should
# be fifth.
msg = self._msgobj('msg_04.txt')
msg.set_boundary('BOUNDARY')
header, value = msg.items()[4]
eq(header.lower(), 'content-type')
eq(value, 'multipart/mixed; boundary="BOUNDARY"')
# And this one has no Content-Type: header at all.
msg = self._msgobj('msg_03.txt')
self.assertRaises(errors.HeaderParseError,
msg.set_boundary, 'BOUNDARY')
def test_set_boundary(self):
eq = self.assertEqual
# This one has no existing boundary parameter, but the Content-Type:
# header appears fifth.
msg = self._msgobj('msg_01.txt')
msg.set_boundary('BOUNDARY')
header, value = msg.items()[4]
eq(header.lower(), 'content-type')
eq(value, 'text/plain; charset="us-ascii"; boundary="BOUNDARY"')
# This one has a Content-Type: header, with a boundary, stuck in the
# middle of its headers. Make sure the order is preserved; it should
# be fifth.
msg = self._msgobj('msg_04.txt')
msg.set_boundary('BOUNDARY')
header, value = msg.items()[4]
eq(header.lower(), 'content-type')
eq(value, 'multipart/mixed; boundary="BOUNDARY"')
# And this one has no Content-Type: header at all.
msg = self._msgobj('msg_03.txt')
self.assertRaises(errors.HeaderParseError,
msg.set_boundary, 'BOUNDARY')
def parse_docstring(docstring):
"""
Parse out the parts of a docstring. Return (title, body, metadata).
"""
docstring = trim_docstring(docstring)
parts = re.split(r'\n{2,}', docstring)
title = parts[0]
if len(parts) == 1:
body = ''
metadata = {}
else:
parser = HeaderParser()
try:
metadata = parser.parsestr(parts[-1])
except HeaderParseError:
metadata = {}
body = "\n\n".join(parts[1:])
else:
metadata = dict(metadata.items())
if metadata:
body = "\n\n".join(parts[1:-1])
else:
body = "\n\n".join(parts[1:])
return title, body, metadata
def parse_docstring(docstring):
"""
Parse out the parts of a docstring. Return (title, body, metadata).
"""
docstring = trim_docstring(docstring)
parts = re.split(r'\n{2,}', docstring)
title = parts[0]
if len(parts) == 1:
body = ''
metadata = {}
else:
parser = HeaderParser()
try:
metadata = parser.parsestr(parts[-1])
except HeaderParseError:
metadata = {}
body = "\n\n".join(parts[1:])
else:
metadata = dict(metadata.items())
if metadata:
body = "\n\n".join(parts[1:-1])
else:
body = "\n\n".join(parts[1:])
return title, body, metadata
def test_set_boundary(self):
eq = self.assertEqual
# This one has no existing boundary parameter, but the Content-Type:
# header appears fifth.
msg = self._msgobj('msg_01.txt')
msg.set_boundary('BOUNDARY')
header, value = msg.items()[4]
eq(header.lower(), 'content-type')
eq(value, 'text/plain; charset="us-ascii"; boundary="BOUNDARY"')
# This one has a Content-Type: header, with a boundary, stuck in the
# middle of its headers. Make sure the order is preserved; it should
# be fifth.
msg = self._msgobj('msg_04.txt')
msg.set_boundary('BOUNDARY')
header, value = msg.items()[4]
eq(header.lower(), 'content-type')
eq(value, 'multipart/mixed; boundary="BOUNDARY"')
# And this one has no Content-Type: header at all.
msg = self._msgobj('msg_03.txt')
self.assertRaises(errors.HeaderParseError,
msg.set_boundary, 'BOUNDARY')
def test_set_boundary(self):
eq = self.assertEqual
# This one has no existing boundary parameter, but the Content-Type:
# header appears fifth.
msg = self._msgobj('msg_01.txt')
msg.set_boundary('BOUNDARY')
header, value = msg.items()[4]
eq(header.lower(), 'content-type')
eq(value, 'text/plain; charset="us-ascii"; boundary="BOUNDARY"')
# This one has a Content-Type: header, with a boundary, stuck in the
# middle of its headers. Make sure the order is preserved; it should
# be fifth.
msg = self._msgobj('msg_04.txt')
msg.set_boundary('BOUNDARY')
header, value = msg.items()[4]
eq(header.lower(), 'content-type')
eq(value, 'multipart/mixed; boundary="BOUNDARY"')
# And this one has no Content-Type: header at all.
msg = self._msgobj('msg_03.txt')
self.assertRaises(errors.HeaderParseError,
msg.set_boundary, 'BOUNDARY')
def parse_docstring(docstring):
"""
Parse out the parts of a docstring. Return (title, body, metadata).
"""
docstring = trim_docstring(docstring)
parts = re.split(r'\n{2,}', docstring)
title = parts[0]
if len(parts) == 1:
body = ''
metadata = {}
else:
parser = HeaderParser()
try:
metadata = parser.parsestr(parts[-1])
except HeaderParseError:
metadata = {}
body = "\n\n".join(parts[1:])
else:
metadata = dict(metadata.items())
if metadata:
body = "\n\n".join(parts[1:-1])
else:
body = "\n\n".join(parts[1:])
return title, body, metadata
def parse_docstring(docstring):
"""
Parse out the parts of a docstring. Return (title, body, metadata).
"""
docstring = trim_docstring(docstring)
parts = re.split(r'\n{2,}', docstring)
title = parts[0]
if len(parts) == 1:
body = ''
metadata = {}
else:
parser = HeaderParser()
try:
metadata = parser.parsestr(parts[-1])
except HeaderParseError:
metadata = {}
body = "\n\n".join(parts[1:])
else:
metadata = dict(metadata.items())
if metadata:
body = "\n\n".join(parts[1:-1])
else:
body = "\n\n".join(parts[1:])
return title, body, metadata
def test_set_boundary(self):
eq = self.assertEqual
# This one has no existing boundary parameter, but the Content-Type:
# header appears fifth.
msg = self._msgobj('msg_01.txt')
msg.set_boundary('BOUNDARY')
header, value = msg.items()[4]
eq(header.lower(), 'content-type')
eq(value, 'text/plain; charset="us-ascii"; boundary="BOUNDARY"')
# This one has a Content-Type: header, with a boundary, stuck in the
# middle of its headers. Make sure the order is preserved; it should
# be fifth.
msg = self._msgobj('msg_04.txt')
msg.set_boundary('BOUNDARY')
header, value = msg.items()[4]
eq(header.lower(), 'content-type')
eq(value, 'multipart/mixed; boundary="BOUNDARY"')
# And this one has no Content-Type: header at all.
msg = self._msgobj('msg_03.txt')
self.assertRaises(errors.HeaderParseError,
msg.set_boundary, 'BOUNDARY')
def parse_docstring(docstring):
"""
Parse out the parts of a docstring. Return (title, body, metadata).
"""
docstring = trim_docstring(docstring)
parts = re.split(r'\n{2,}', docstring)
title = parts[0]
if len(parts) == 1:
body = ''
metadata = {}
else:
parser = HeaderParser()
try:
metadata = parser.parsestr(parts[-1])
except HeaderParseError:
metadata = {}
body = "\n\n".join(parts[1:])
else:
metadata = dict(metadata.items())
if metadata:
body = "\n\n".join(parts[1:-1])
else:
body = "\n\n".join(parts[1:])
return title, body, metadata
def parse_docstring(docstring):
"""
Parse out the parts of a docstring. Return (title, body, metadata).
"""
docstring = trim_docstring(docstring)
parts = re.split(r'\n{2,}', docstring)
title = parts[0]
if len(parts) == 1:
body = ''
metadata = {}
else:
parser = HeaderParser()
try:
metadata = parser.parsestr(parts[-1])
except HeaderParseError:
metadata = {}
body = "\n\n".join(parts[1:])
else:
metadata = dict(metadata.items())
if metadata:
body = "\n\n".join(parts[1:-1])
else:
body = "\n\n".join(parts[1:])
return title, body, metadata
def test_set_boundary(self):
eq = self.assertEqual
# This one has no existing boundary parameter, but the Content-Type:
# header appears fifth.
msg = self._msgobj('msg_01.txt')
msg.set_boundary('BOUNDARY')
header, value = msg.items()[4]
eq(header.lower(), 'content-type')
eq(value, 'text/plain; charset="us-ascii"; boundary="BOUNDARY"')
# This one has a Content-Type: header, with a boundary, stuck in the
# middle of its headers. Make sure the order is preserved; it should
# be fifth.
msg = self._msgobj('msg_04.txt')
msg.set_boundary('BOUNDARY')
header, value = msg.items()[4]
eq(header.lower(), 'content-type')
eq(value, 'multipart/mixed; boundary="BOUNDARY"')
# And this one has no Content-Type: header at all.
msg = self._msgobj('msg_03.txt')
self.assertRaises(errors.HeaderParseError,
msg.set_boundary, 'BOUNDARY')
def parse_docstring(docstring):
"""
Parse out the parts of a docstring. Return (title, body, metadata).
"""
docstring = trim_docstring(docstring)
parts = re.split(r'\n{2,}', docstring)
title = parts[0]
if len(parts) == 1:
body = ''
metadata = {}
else:
parser = HeaderParser()
try:
metadata = parser.parsestr(parts[-1])
except HeaderParseError:
metadata = {}
body = "\n\n".join(parts[1:])
else:
metadata = dict(metadata.items())
if metadata:
body = "\n\n".join(parts[1:-1])
else:
body = "\n\n".join(parts[1:])
return title, body, metadata
def parse_docstring(docstring):
"""
Parse out the parts of a docstring. Return (title, body, metadata).
"""
docstring = trim_docstring(docstring)
parts = re.split(r'\n{2,}', docstring)
title = parts[0]
if len(parts) == 1:
body = ''
metadata = {}
else:
parser = HeaderParser()
try:
metadata = parser.parsestr(parts[-1])
except HeaderParseError:
metadata = {}
body = "\n\n".join(parts[1:])
else:
metadata = dict(metadata.items())
if metadata:
body = "\n\n".join(parts[1:-1])
else:
body = "\n\n".join(parts[1:])
return title, body, metadata
def parse_docstring(docstring):
"""
Parse out the parts of a docstring. Return (title, body, metadata).
"""
docstring = trim_docstring(docstring)
parts = re.split(r'\n{2,}', docstring)
title = parts[0]
if len(parts) == 1:
body = ''
metadata = {}
else:
parser = HeaderParser()
try:
metadata = parser.parsestr(parts[-1])
except HeaderParseError:
metadata = {}
body = "\n\n".join(parts[1:])
else:
metadata = dict(metadata.items())
if metadata:
body = "\n\n".join(parts[1:-1])
else:
body = "\n\n".join(parts[1:])
return title, body, metadata
def test_set_boundary(self):
eq = self.assertEqual
# This one has no existing boundary parameter, but the Content-Type:
# header appears fifth.
msg = self._msgobj('msg_01.txt')
msg.set_boundary('BOUNDARY')
header, value = msg.items()[4]
eq(header.lower(), 'content-type')
eq(value, 'text/plain; charset="us-ascii"; boundary="BOUNDARY"')
# This one has a Content-Type: header, with a boundary, stuck in the
# middle of its headers. Make sure the order is preserved; it should
# be fifth.
msg = self._msgobj('msg_04.txt')
msg.set_boundary('BOUNDARY')
header, value = msg.items()[4]
eq(header.lower(), 'content-type')
eq(value, 'multipart/mixed; boundary="BOUNDARY"')
# And this one has no Content-Type: header at all.
msg = self._msgobj('msg_03.txt')
self.assertRaises(errors.HeaderParseError,
msg.set_boundary, 'BOUNDARY')
def parse_docstring(docstring):
"""
Parse out the parts of a docstring. Return (title, body, metadata).
"""
docstring = trim_docstring(docstring)
parts = re.split(r'\n{2,}', docstring)
title = parts[0]
if len(parts) == 1:
body = ''
metadata = {}
else:
parser = HeaderParser()
try:
metadata = parser.parsestr(parts[-1])
except HeaderParseError:
metadata = {}
body = "\n\n".join(parts[1:])
else:
metadata = dict(metadata.items())
if metadata:
body = "\n\n".join(parts[1:-1])
else:
body = "\n\n".join(parts[1:])
return title, body, metadata
def test_set_boundary(self):
eq = self.assertEqual
# This one has no existing boundary parameter, but the Content-Type:
# header appears fifth.
msg = self._msgobj('msg_01.txt')
msg.set_boundary('BOUNDARY')
header, value = msg.items()[4]
eq(header.lower(), 'content-type')
eq(value, 'text/plain; charset="us-ascii"; boundary="BOUNDARY"')
# This one has a Content-Type: header, with a boundary, stuck in the
# middle of its headers. Make sure the order is preserved; it should
# be fifth.
msg = self._msgobj('msg_04.txt')
msg.set_boundary('BOUNDARY')
header, value = msg.items()[4]
eq(header.lower(), 'content-type')
eq(value, 'multipart/mixed; boundary="BOUNDARY"')
# And this one has no Content-Type: header at all.
msg = self._msgobj('msg_03.txt')
self.assertRaises(errors.HeaderParseError,
msg.set_boundary, 'BOUNDARY')
def test_set_boundary(self):
eq = self.assertEqual
# This one has no existing boundary parameter, but the Content-Type:
# header appears fifth.
msg = self._msgobj('msg_01.txt')
msg.set_boundary('BOUNDARY')
header, value = msg.items()[4]
eq(header.lower(), 'content-type')
eq(value, 'text/plain; charset="us-ascii"; boundary="BOUNDARY"')
# This one has a Content-Type: header, with a boundary, stuck in the
# middle of its headers. Make sure the order is preserved; it should
# be fifth.
msg = self._msgobj('msg_04.txt')
msg.set_boundary('BOUNDARY')
header, value = msg.items()[4]
eq(header.lower(), 'content-type')
eq(value, 'multipart/mixed; boundary="BOUNDARY"')
# And this one has no Content-Type: header at all.
msg = self._msgobj('msg_03.txt')
self.assertRaises(errors.HeaderParseError,
msg.set_boundary, 'BOUNDARY')
def get_comment(value):
"""comment = "(" *([FWS] ccontent) [FWS] ")"
ccontent = ctext / quoted-pair / comment
We handle nested comments here, and quoted-pair in our qp-ctext routine.
"""
if value and value[0] != '(':
raise errors.HeaderParseError(
"expected '(' but found '{}'".format(value))
comment = Comment()
value = value[1:]
while value and value[0] != ")":
if value[0] in WSP:
token, value = get_fws(value)
elif value[0] == '(':
token, value = get_comment(value)
else:
token, value = get_qp_ctext(value)
comment.append(token)
if not value:
comment.defects.append(errors.InvalidHeaderDefect(
"end of header inside comment"))
return comment, value
return comment, value[1:]
def get_dot_atom_text(value):
""" dot-text = 1*atext *("." 1*atext)
"""
dot_atom_text = DotAtomText()
if not value or value[0] in ATOM_ENDS:
raise errors.HeaderParseError("expected atom at a start of "
"dot-atom-text but found '{}'".format(value))
while value and value[0] not in ATOM_ENDS:
token, value = get_atext(value)
dot_atom_text.append(token)
if value and value[0] == '.':
dot_atom_text.append(DOT)
value = value[1:]
if dot_atom_text[-1] is DOT:
raise errors.HeaderParseError("expected atom at end of dot-atom-text "
"but found '{}'".format('.'+value))
return dot_atom_text, value
def get_dot_atom(value):
""" dot-atom = [CFWS] dot-atom-text [CFWS]
Any place we can have a dot atom, we could instead have an rfc2047 encoded
word.
"""
dot_atom = DotAtom()
if value[0] in CFWS_LEADER:
token, value = get_cfws(value)
dot_atom.append(token)
if value.startswith('=?'):
try:
token, value = get_encoded_word(value)
except errors.HeaderParseError:
# XXX: need to figure out how to register defects when
# appropriate here.
token, value = get_dot_atom_text(value)
else:
token, value = get_dot_atom_text(value)
dot_atom.append(token)
if value and value[0] in CFWS_LEADER:
token, value = get_cfws(value)
dot_atom.append(token)
return dot_atom, value
