def from_org(cls: Type[B], node: OrgNode) -> B:
annotations: List[Annotation] = [
Annotation.from_org(anode) for anode in node.children
]
author: AuthorName = node.get_property("AUTHOR")
series: Optional[Series] = node.get_property("SERIES")
body: str = node.body.strip() if node.body.strip() else None
for p in ["AUTHOR", "SERIES"]:
try:
del node.properties[p]
except KeyError:
pass
status, heading = super().parse_heading(node)
book: B = cls(
title=heading,
author=author,
series=series,
creation_date=cls._get_creation_date(annotations),
body=body,
status=status,
properties={
key.lower(): value
for key, value in node.properties.items()
},
annotations=annotations,
)
return book
def get_body_compat(node: OrgNode) -> str:
try:
return node.get_body(format='raw')
except Exception as e:
if node.is_root():
# get_body was only added to root in 0.2.0
for x in warn_old_orgparse_once():
# ugh. really crap, but it will at least only warn once... (becaue it caches)
raise x
return UPDATE_ORGPARSE_WARNING
else:
raise e
def _parse_node(n: OrgNode) -> Parsed:
if n.is_root():
return Parsed(dt=None, heading='')
heading = n.get_heading('raw')
pp = n.properties or {}
createds = pp.get('CREATED', None)
if createds is None:
# TODO replace with 'match', but need to strip off priority etc first?
# see _parse_heading in orgparse
m = rgx.search(heading)
if m is not None:
createds = m.group(0) # could be None
# TODO a bit hacky..
heading = heading.replace(createds + ' ', '')
if createds is not None:
[odt] = OrgDate.list_from_str(createds)
dt = odt.start
else:
dt = None
return Parsed(dt=dt, heading=heading)
def _parse_node(n: OrgNode) -> Parsed:
if n.is_root():
return Parsed(dt=None, heading='')
heading = n.get_heading('raw')
pp = n.properties
createds = cast(Optional[str], pp.get('CREATED', None))
if createds is None:
# TODO replace with 'match', but need to strip off priority etc first?
# see _parse_heading in orgparse
# todo maybe use n.get_timestamps(inactive=True, point=True)? only concern is that it's searching in the body as well?
m = CREATED_RGX.search(heading)
if m is not None:
createds = m.group(0) # could be None
# todo a bit hacky..
heading = heading.replace(createds + ' ', '')
if createds is not None:
[odt] = OrgDate.list_from_str(createds)
dt = odt.start
else:
dt = None
return Parsed(dt=dt, heading=heading)
def iter_org_urls(n: OrgNode) -> Iterator[Res[Url]]:
logger = get_logger()
# todo not sure if it can fail? but for now, paranoid just in case
try:
heading = _get_heading(n)
except Exception as e:
logger.exception(e)
yield e
else:
yield from iter_urls(heading, syntax='org')
try:
content = n.get_body(format='raw')
except Exception as e:
logger.exception(e)
yield e
else:
yield from iter_urls(content, syntax='org')
def _get_heading(n: OrgNode):
# todo not sure if it's really that useful to distinguish root and non-root...
# maybe have a mode that returns uniform entries, and just relies on the convention
return '' if n.is_root() else n.get_heading(format='raw')
def _get_body(n: OrgNode):
if n.is_root():
return '\n'.join(n._lines)
else:
return n.get_body(format='raw')
def _get_heading(n: OrgNode):
return '' if n.is_root() else n.get_heading(
format='raw') # TODO convert links to html?