mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-24 17:06:29 +03:00
df19e2bff6
<!--- Provide a general summary of your changes in the title. -->
## Description
This PR adds the abilility to override custom extension attributes during merging. This will only work for attributes that are writable, i.e. attributes registered with a default value like `default=False` or attribute that have both a getter *and* a setter implemented.
```python
Token.set_extension('is_musician', default=False)
doc = nlp("I like David Bowie.")
with doc.retokenize() as retokenizer:
attrs = {"LEMMA": "David Bowie", "_": {"is_musician": True}}
retokenizer.merge(doc[2:4], attrs=attrs)
assert doc[2].text == "David Bowie"
assert doc[2].lemma_ == "David Bowie"
assert doc[2]._.is_musician
```
### Types of change
enhancement
## Checklist
<!--- Before you submit the PR, go over this checklist and make sure you can
tick off all the boxes. [] -> [x] -->
- [x] I have submitted the spaCy Contributor Agreement.
- [x] I ran the tests, and all new and existing tests passed.
- [x] My changes don't require a change to the documentation, or if they do, I've added all required information.
93 lines
3.5 KiB
Python
93 lines
3.5 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
import functools
|
|
|
|
from ..errors import Errors
|
|
|
|
|
|
class Underscore(object):
|
|
doc_extensions = {}
|
|
span_extensions = {}
|
|
token_extensions = {}
|
|
|
|
def __init__(self, extensions, obj, start=None, end=None):
|
|
object.__setattr__(self, "_extensions", extensions)
|
|
object.__setattr__(self, "_obj", obj)
|
|
# Assumption is that for doc values, _start and _end will both be None
|
|
# Span will set non-None values for _start and _end
|
|
# Token will have _start be non-None, _end be None
|
|
# This lets us key everything into the doc.user_data dictionary,
|
|
# (see _get_key), and lets us use a single Underscore class.
|
|
object.__setattr__(self, "_doc", obj.doc)
|
|
object.__setattr__(self, "_start", start)
|
|
object.__setattr__(self, "_end", end)
|
|
|
|
def __getattr__(self, name):
|
|
if name not in self._extensions:
|
|
raise AttributeError(Errors.E046.format(name=name))
|
|
default, method, getter, setter = self._extensions[name]
|
|
if getter is not None:
|
|
return getter(self._obj)
|
|
elif method is not None:
|
|
return functools.partial(method, self._obj)
|
|
else:
|
|
return self._doc.user_data.get(self._get_key(name), default)
|
|
|
|
def __setattr__(self, name, value):
|
|
if name not in self._extensions:
|
|
raise AttributeError(Errors.E047.format(name=name))
|
|
default, method, getter, setter = self._extensions[name]
|
|
if setter is not None:
|
|
return setter(self._obj, value)
|
|
else:
|
|
self._doc.user_data[self._get_key(name)] = value
|
|
|
|
def set(self, name, value):
|
|
return self.__setattr__(name, value)
|
|
|
|
def get(self, name):
|
|
return self.__getattr__(name)
|
|
|
|
def has(self, name):
|
|
return name in self._extensions
|
|
|
|
def _get_key(self, name):
|
|
return ("._.", name, self._start, self._end)
|
|
|
|
|
|
def get_ext_args(**kwargs):
|
|
"""Validate and convert arguments. Reused in Doc, Token and Span."""
|
|
default = kwargs.get("default")
|
|
getter = kwargs.get("getter")
|
|
setter = kwargs.get("setter")
|
|
method = kwargs.get("method")
|
|
if getter is None and setter is not None:
|
|
raise ValueError(Errors.E089)
|
|
valid_opts = ("default" in kwargs, method is not None, getter is not None)
|
|
nr_defined = sum(t is True for t in valid_opts)
|
|
if nr_defined != 1:
|
|
raise ValueError(Errors.E083.format(nr_defined=nr_defined))
|
|
if setter is not None and not hasattr(setter, "__call__"):
|
|
raise ValueError(Errors.E091.format(name="setter", value=repr(setter)))
|
|
if getter is not None and not hasattr(getter, "__call__"):
|
|
raise ValueError(Errors.E091.format(name="getter", value=repr(getter)))
|
|
if method is not None and not hasattr(method, "__call__"):
|
|
raise ValueError(Errors.E091.format(name="method", value=repr(method)))
|
|
return (default, method, getter, setter)
|
|
|
|
|
|
def is_writable_attr(ext):
|
|
"""Check if an extension attribute is writable.
|
|
ext (tuple): The (default, getter, setter, method) tuple available via
|
|
{Doc,Span,Token}.get_extension.
|
|
RETURNS (bool): Whether the attribute is writable.
|
|
"""
|
|
default, method, getter, setter = ext
|
|
# Extension is writable if it has a setter (getter + setter), if it has a
|
|
# default value (or, if its default value is none, none of the other values
|
|
# should be set).
|
|
if setter is not None or default is not None or all(e is None for e in ext):
|
|
return True
|
|
return False
|