explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-10-31 16:07:41 +03:00
Code Issues Packages Projects Releases Wiki Activity

Implement Doc.copy

Browse Source
This commit is contained in:
Matthew Honnibal 2020-06-25 21:18:37 +02:00
parent ae58d00327
commit c2fff89b1d
1 changed files with 23 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
spacy/tokens/doc.pyx
View File

@ -13,6 +13,7 @@ import srsly
from thinc.api import get_array_module from thinc.api import get_array_module
from thinc.util import copy_array from thinc.util import copy_array
import warnings import warnings
import copy
from .span cimport Span from .span cimport Span
from .token cimport Token from .token cimport Token
@ -890,6 +891,28 @@ cdef class Doc:
""" """
return numpy.asarray(_get_lca_matrix(self, 0, len(self))) return numpy.asarray(_get_lca_matrix(self, 0, len(self)))
def copy(self):
cdef Doc other = Doc(self.vocab)
other._vector = copy.deepcopy(self._vector)
other._vector_norm = copy.deepcopy(self._vector_norm)
other.tensor = copy.deepcopy(self.tensor)
other.cats = copy.deepcopy(self.cats)
other.user_data = copy.deepcopy(self.user_data)
other.is_tagged = self.is_tagged
other.is_parsed = self.is_parsed
other.is_morphed = self.is_morphed
other.sentiment = self.sentiment
other.user_hooks = dict(self.user_hooks)
other.user_token_hooks = dict(self.user_token_hooks)
other.user_span_hooks = dict(self.user_span_hooks)
other.length = self.length
other.max_length = self.max_length
buff_size = other.max_length + (PADDING*2)
tokens = <TokenC*>other.mem.alloc(buff_size, sizeof(TokenC))
memcpy(tokens, self.c - PADDING, buff_size * sizeof(TokenC))
other.c = &tokens[PADDING]
return other
def to_disk(self, path, **kwargs): def to_disk(self, path, **kwargs):
"""Save the current state to a directory. """Save the current state to a directory.