def apply(self):
if not len(self.document):
# @@@ replace these DataErrors with proper system messages
raise DataError('Document tree is empty.')
header = self.document[0]
if not isinstance(header, nodes.field_list) or \
'rfc2822' not in header['classes']:
raise DataError('Document does not begin with an RFC-2822 '
'header; it is not a PEP.')
pep = None
for field in header:
if field[0].astext().lower() == 'pep': # should be the first field
value = field[1].astext()
try:
pep = int(value)
cvs_url = self.pep_cvs_url % pep
except ValueError:
pep = value
cvs_url = None
msg = self.document.reporter.warning(
'"PEP" header must contain an integer; "%s" is an '
'invalid value.' % pep, base_node=field)
msgid = self.document.set_id(msg)
prb = nodes.problematic(value, value or '(none)',
refid=msgid)
prbid = self.document.set_id(prb)
msg.add_backref(prbid)
if len(field[1]):
field[1][0][:] = [prb]
else:
field[1] += nodes.paragraph('', '', prb)
break
if pep is None:
raise DataError('Document does not contain an RFC-2822 "PEP" '
'header.')
if pep == 0:
# Special processing for PEP 0.
pending = nodes.pending(peps.PEPZero)
self.document.insert(1, pending)
self.document.note_pending(pending)
if len(header) < 2 or header[1][0].astext().lower() != 'title':
raise DataError('No title!')
for field in header:
name = field[0].astext().lower()
body = field[1]
if len(body) > 1:
raise DataError('PEP header field body contains multiple '
'elements:\n%s' % field.pformat(level=1))
elif len(body) == 1:
if not isinstance(body[0], nodes.paragraph):
raise DataError('PEP header field body may only contain '
'a single paragraph:\n%s'
% field.pformat(level=1))
elif name == 'last-modified':
date = time.strftime(
'%d-%b-%Y',
time.localtime(os.stat(self.document['source'])[8]))
if cvs_url:
body += nodes.paragraph(
'', '', nodes.reference('', date, refuri=cvs_url))
else:
# empty
continue
para = body[0]
if name in ('author', 'bdfl-delegate', 'sponsor'):
for node in para:
if isinstance(node, nodes.reference):
node.replace_self(peps.mask_email(node))
elif name == 'discussions-to':
for node in para:
if isinstance(node, nodes.reference):
node.replace_self(peps.mask_email(node, pep))
elif name in ('replaces', 'superseded-by', 'requires'):
newbody = []
space = nodes.Text(' ')
for refpep in re.split(r',?\s+', body.astext()):
pepno = int(refpep)
newbody.append(nodes.reference(
refpep, refpep,
refuri=(self.document.settings.pep_base_url
+ self.pep_url % pepno)))
newbody.append(space)
para[:] = newbody[:-1] # drop trailing space
elif name == 'last-modified':
utils.clean_rcs_keywords(para, self.rcs_keyword_substitutions)
if cvs_url:
date = para.astext()
para[:] = [nodes.reference('', date, refuri=cvs_url)]
elif name == 'content-type':
pep_type = para.astext()
uri = self.document.settings.pep_base_url + self.pep_url % 12
para[:] = [nodes.reference('', pep_type, refuri=uri)]
elif name == 'version' and len(body):
utils.clean_rcs_keywords(para, self.rcs_keyword_substitutions)
def visit_reference(node: nodes.reference) -> None:
"""Mask email addresses if present."""
node.replace_self(peps.mask_email(node))
def apply(self):
if not len(self.document):
# @@@ replace these DataErrors with proper system messages
raise DataError('Document tree is empty.')
header = self.document[0]
if not isinstance(header, nodes.field_list) or \
'rfc2822' not in header['classes']:
raise DataError('Document does not begin with an RFC-2822 '
'header; it is not a PEP.')
pep = None
for field in header:
if field[0].astext().lower() == 'pep': # should be the first field
value = field[1].astext()
try:
pep = int(value)
cvs_url = self.pep_cvs_url % pep
except ValueError:
pep = value
cvs_url = None
msg = self.document.reporter.warning(
'"PEP" header must contain an integer; "%s" is an '
'invalid value.' % pep, base_node=field)
msgid = self.document.set_id(msg)
prb = nodes.problematic(value, value or '(none)',
refid=msgid)
prbid = self.document.set_id(prb)
msg.add_backref(prbid)
if len(field[1]):
field[1][0][:] = [prb]
else:
field[1] += nodes.paragraph('', '', prb)
break
if pep is None:
raise DataError('Document does not contain an RFC-2822 "PEP" '
'header.')
if pep == 0:
# Special processing for PEP 0.
pending = nodes.pending(peps.PEPZero)
self.document.insert(1, pending)
self.document.note_pending(pending)
if len(header) < 2 or header[1][0].astext().lower() != 'title':
raise DataError('No title!')
for field in header:
name = field[0].astext().lower()
body = field[1]
if len(body) > 1:
raise DataError('PEP header field body contains multiple '
'elements:\n%s' % field.pformat(level=1))
elif len(body) == 1:
if not isinstance(body[0], nodes.paragraph):
raise DataError('PEP header field body may only contain '
'a single paragraph:\n%s'
% field.pformat(level=1))
elif name == 'last-modified':
date = time.strftime(
'%d-%b-%Y',
time.localtime(os.stat(self.document['source'])[8]))
if cvs_url:
body += nodes.paragraph(
'', '', nodes.reference('', date, refuri=cvs_url))
else:
# empty
continue
para = body[0]
if name in ('author', 'bdfl-delegate', 'pep-delegate', 'sponsor'):
for node in para:
if isinstance(node, nodes.reference):
node.replace_self(peps.mask_email(node))
elif name == 'discussions-to':
for node in para:
if isinstance(node, nodes.reference):
node.replace_self(peps.mask_email(node, pep))
elif name in ('replaces', 'superseded-by', 'requires'):
newbody = []
space = nodes.Text(' ')
for refpep in re.split(r',?\s+', body.astext()):
pepno = int(refpep)
newbody.append(nodes.reference(
refpep, refpep,
refuri=(self.document.settings.pep_base_url
+ self.pep_url % pepno)))
newbody.append(space)
para[:] = newbody[:-1] # drop trailing space
elif name == 'last-modified':
utils.clean_rcs_keywords(para, self.rcs_keyword_substitutions)
if cvs_url:
date = para.astext()
para[:] = [nodes.reference('', date, refuri=cvs_url)]
elif name == 'content-type':
pep_type = para.astext()
uri = self.document.settings.pep_base_url + self.pep_url % 12
para[:] = [nodes.reference('', pep_type, refuri=uri)]
elif name == 'version' and len(body):
utils.clean_rcs_keywords(para, self.rcs_keyword_substitutions)
def apply(self) -> None:
if not Path(self.document["source"]).match("pep-*"):
return # not a PEP file, exit early
if not len(self.document):
raise PEPParsingError("Document tree is empty.")
header = self.document[0]
if not isinstance(
header,
nodes.field_list) or "rfc2822" not in header["classes"]:
raise PEPParsingError(
"Document does not begin with an RFC-2822 header; it is not a PEP."
)
# PEP number should be the first field
pep_field = header[0]
if pep_field[0].astext().lower() != "pep":
raise PEPParsingError(
"Document does not contain an RFC-2822 'PEP' header!")
# Extract PEP number
value = pep_field[1].astext()
try:
pep = int(value)
except ValueError:
raise PEPParsingError(
f"'PEP' header must contain an integer. '{value}' is invalid!")
# Special processing for PEP 0.
if pep == 0:
pending = nodes.pending(pep_zero.PEPZero)
self.document.insert(1, pending)
self.document.note_pending(pending)
# If there are less than two headers in the preamble, or if Title is absent
if len(header) < 2 or header[1][0].astext().lower() != "title":
raise PEPParsingError("No title!")
fields_to_remove = []
for field in header:
name = field[0].astext().lower()
body = field[1]
if len(body) == 0:
# body is empty
continue
elif len(body) > 1:
msg = f"PEP header field body contains multiple elements:\n{field.pformat(level=1)}"
raise PEPParsingError(msg)
elif not isinstance(body[0], nodes.paragraph): # len(body) == 1
msg = f"PEP header field body may only contain a single paragraph:\n{field.pformat(level=1)}"
raise PEPParsingError(msg)
para = body[0]
if name in {"author", "bdfl-delegate", "pep-delegate", "sponsor"}:
# mask emails
for node in para:
if isinstance(node, nodes.reference):
pep_num = pep if name == "discussions-to" else -1
node.replace_self(peps.mask_email(node, pep_num))
elif name in {"replaces", "superseded-by", "requires"}:
# replace PEP numbers with normalised list of links to PEPs
new_body = []
space = nodes.Text(" ")
for ref_pep in re.split(r",?\s+", body.astext()):
new_body.append(
nodes.reference(
ref_pep,
ref_pep,
refuri=(self.document.settings.pep_base_url +
pep_url.format(int(ref_pep)))))
new_body.append(space)
para[:] = new_body[:-1] # drop trailing space
elif name in {"last-modified", "content-type", "version"}:
# Mark unneeded fields
fields_to_remove.append(field)
# Remove unneeded fields
for field in fields_to_remove:
field.parent.remove(field)
