def get_entries(
self,
entry_type: Type[EntryType],
range_annotation: Optional[Annotation] = None,
components: Optional[Union[str,
List[str]]] = None) -> Iterable[EntryType]:
"""
Get ``entry_type`` entries from the span of ``range_annotation`` in a
DataPack.
Args:
entry_type (type): The type of entries requested.
range_annotation (Annotation, optional): The range of entries
requested. If `None`, will return valid entries in the range of
whole data_pack.
components (str or list, optional): The component generating the
entries requested. If `None`, will return valid entries
generated by any component.
"""
range_begin = range_annotation.span.begin if range_annotation else 0
range_end = (range_annotation.span.end
if range_annotation else self.annotations[-1].span.end)
# valid type
valid_id = self.get_ids_by_type(entry_type)
# valid component
if components is not None:
if isinstance(components, str):
components = [components]
valid_component_id: Set[int] = set()
for component in components:
valid_component_id |= self.get_ids_by_component(component)
valid_id &= valid_component_id
# valid span
if range_annotation is not None:
coverage_index = self.index.coverage_index(type(range_annotation),
entry_type)
if coverage_index is not None:
valid_id &= coverage_index[range_annotation.tid]
if issubclass(entry_type, Annotation):
begin_index = self.annotations.bisect(
Annotation(self, range_begin, range_begin))
end_index = self.annotations.bisect(
Annotation(self, range_end, range_end))
for annotation in self.annotations[begin_index:end_index]:
if annotation.tid not in valid_id:
continue
if (range_annotation is None or self.index.in_span(
annotation, range_annotation.span)):
yield annotation
elif issubclass(entry_type, (Link, Group)):
for entry_id in valid_id:
entry: EntryType = self.get_entry(entry_id) # type: ignore
if (range_annotation is None
or self.index.in_span(entry, range_annotation.span)):
yield entry
def iter_in_range(self, entry_type: Type[EntryType],
range_annotation: Annotation) -> Iterator[EntryType]:
"""
Iterate the entries of the provided type within or fulfill the
constraints of the `range_annotation`. The constraint is True if
an entry is `in_span` of the provided `range_annotation`.
Internally, if the coverage index between the entry type and the
type of the `range_annotation` is built, then this will create the
iterator from the index. Otherwise, the function will iterate them
from scratch (which is slower). If there are frequent usage of this
function, it is suggested to build the coverage index.
Args:
entry_type: The type of entry to iterate over.
range_annotation: The range annotation that serve as the constraint.
Returns:
An iterator of the entries with in the `range_annotation`.
"""
use_coverage = self._index.coverage_index_is_valid
coverage_index: Optional[Dict[int, Set[int]]] = {}
if use_coverage:
coverage_index = self._index.coverage_index(
type(range_annotation), entry_type)
if coverage_index is None:
use_coverage = False
if use_coverage and coverage_index is not None:
for tid in coverage_index[range_annotation.tid]:
yield self.get_entry(tid) # type: ignore
else:
if issubclass(entry_type, Annotation):
range_begin = (range_annotation.span.begin
if range_annotation else 0)
range_end = (range_annotation.span.end if range_annotation else
self.annotations[-1].span.end)
if issubclass(entry_type, Annotation):
temp_begin = Annotation(self, range_begin, range_begin)
begin_index = self.annotations.bisect(temp_begin)
temp_end = Annotation(self, range_end, range_end)
end_index = self.annotations.bisect(temp_end)
# Make sure these temporary annotations are not part of the
# actual data.
temp_begin.regret_creation()
temp_end.regret_creation()
yield from self.annotations[begin_index:end_index]
elif issubclass(entry_type, Link):
for link in self.links:
if self._index.in_span(link, range_annotation.span):
yield link
elif issubclass(entry_type, Group):
for group in self.groups:
if self._index.in_span(group, range_annotation.span):
yield group
def get_entries(
self,
entry_type: Type[EntryType],
range_annotation: Optional[Annotation] = None,
components: Optional[Union[str,
List[str]]] = None) -> Iterable[EntryType]:
r"""Get ``entry_type`` entries from the span of ``range_annotation`` in
a DataPack.
Example:
.. code-block:: python
for sentence in input_pack.get_entries(Sentence):
token_entries = input_pack.get_entries(
entry_type=Token,range_annotation=sentence,
component=token_component)
...
In the above code snippet, we get entries of type ``Token`` within
each ``sentence`` which were generated by ``token_component``
Args:
entry_type (type): The type of entries requested.
range_annotation (Annotation, optional): The range of entries
requested. If `None`, will return valid entries in the range of
whole data_pack.
components (str or list, optional): The component generating the
entries requested. If `None`, will return valid entries
generated by any component.
"""
if range_annotation is not None and len(self.annotations) == 0:
yield from []
# After yield, don't do real queries.
return
range_begin = range_annotation.span.begin if range_annotation else 0
range_end = (range_annotation.span.end
if range_annotation else self.annotations[-1].span.end)
# valid type
valid_id = self.get_ids_by_type(entry_type)
# valid component
if components is not None:
if isinstance(components, str):
components = [components]
valid_id &= self.get_ids_by_components(components)
# Generics do not work with range_annotation.
if issubclass(entry_type, Generics):
for entry_id in valid_id:
entry: EntryType = self.get_entry(entry_id) # type: ignore
yield entry
return
# valid span
if range_annotation is not None:
coverage_index = self.index.coverage_index(type(range_annotation),
entry_type)
if coverage_index is not None:
valid_id &= coverage_index[range_annotation.tid]
if issubclass(entry_type, Annotation):
temp_begin = Annotation(self, range_begin, range_begin)
begin_index = self.annotations.bisect(temp_begin)
temp_end = Annotation(self, range_end, range_end)
end_index = self.annotations.bisect(temp_end)
# Make sure these temporary annotations are not part of the
# actual data.
temp_begin.regret_creation()
temp_end.regret_creation()
for annotation in self.annotations[begin_index:end_index]:
if annotation.tid not in valid_id:
continue
if (range_annotation is None or self.index.in_span(
annotation, range_annotation.span)):
yield annotation
elif issubclass(entry_type, (Link, Group)):
for entry_id in valid_id:
entry: EntryType = self.get_entry(entry_id) # type: ignore
if (range_annotation is None
or self.index.in_span(entry, range_annotation.span)):
yield entry