explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 09:26:27 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add getters_for_spans and getters_for_tokens attributes to Doc. Fix docstring

Browse Source
This commit is contained in:
Matthew Honnibal 2016-10-17 02:42:51 +02:00
parent ae11ea8240
commit 62230dd13a
1 changed files with 10 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
spacy/tokens/doc.pyx
View File

@ -89,11 +89,14 @@ cdef class Doc:
A Vocabulary object, which must match any models you want to A Vocabulary object, which must match any models you want to
use (e.g. tokenizer, parser, entity recognizer). use (e.g. tokenizer, parser, entity recognizer).
orths_and_spaces: words:
A list of tokens in the document as a sequence of A list of unicode strings to add to the document as words. If None,
`(orth_id, has_space)` tuples, where `orth_id` is an defaults to empty list.
integer and `has_space` is a boolean, indicating whether the
token has a trailing space. spaces:
A list of boolean values, of the same length as words. True
means that the word is followed by a space, False means it is not.
If None, defaults to [True]*len(words)
''' '''
self.vocab = vocab self.vocab = vocab
size = 20 size = 20
@ -112,6 +115,8 @@ cdef class Doc:
self.length = 0 self.length = 0
self.is_tagged = False self.is_tagged = False
self.is_parsed = False self.is_parsed = False
self.getters_for_tokens = {}
self.getters_for_spans = {}
self._py_tokens = [] self._py_tokens = []
self._vector = None self._vector = None
self.noun_chunks_iterator = CHUNKERS.get(self.vocab.lang) self.noun_chunks_iterator = CHUNKERS.get(self.vocab.lang)