mirror of https://github.com/explosion/spaCy.git
72 lines
2.0 KiB
Plaintext
72 lines
2.0 KiB
Plaintext
|
//- 💫 DOCS > API > CYTHON > CLASSES > DOC
|
||
|
|
|
||
|
|
p
|
||
|
|
| The #[code Doc] object holds an array of
|
||
|
|
| #[+api("cython-structs#tokenc") #[code TokenC]] structs.
|
||
|
|
|
||
|
|
+infobox
|
||
|
|
| This section documents the extra C-level attributes and methods that
|
||
|
|
| can't be accessed from Python. For the Python documentation, see
|
||
|
|
| #[+api("doc") #[code Doc]].
|
||
|
|
|
||
|
|
+h(3, "doc_attributes") Attributes
|
||
|
|
|
||
|
|
+table(["Name", "Type", "Description"])
|
||
|
|
+row
|
||
|
|
+cell #[code mem]
|
||
|
|
+cell #[code cymem.Pool]
|
||
|
|
+cell
|
||
|
|
| A memory pool. Allocated memory will be freed once the
|
||
|
|
| #[code Doc] object is garbage collected.
|
||
|
|
|
||
|
|
+row
|
||
|
|
+cell #[code vocab]
|
||
|
|
+cell #[code Vocab]
|
||
|
|
+cell A reference to the shared #[code Vocab] object.
|
||
|
|
|
||
|
|
+row
|
||
|
|
+cell #[code c]
|
||
|
|
+cell #[code TokenC*]
|
||
|
|
+cell
|
||
|
|
| A pointer to a #[+api("cython-structs#tokenc") #[code TokenC]]
|
||
|
|
| struct.
|
||
|
|
|
||
|
|
+row
|
||
|
|
+cell #[code length]
|
||
|
|
+cell #[code int]
|
||
|
|
+cell The number of tokens in the document.
|
||
|
|
|
||
|
|
+row
|
||
|
|
+cell #[code max_length]
|
||
|
|
+cell #[code int]
|
||
|
|
+cell The underlying size of the #[code Doc.c] array.
|
||
|
|
|
||
|
|
+h(3, "doc_push_back") Doc.push_back
|
||
|
|
+tag method
|
||
|
|
|
||
|
|
p
|
||
|
|
| Append a token to the #[code Doc]. The token can be provided as a
|
||
|
|
| #[+api("cython-structs#lexemec") #[code LexemeC]] or
|
||
|
|
| #[+api("cython-structs#tokenc") #[code TokenC]] pointer, using Cython's
|
||
|
|
| #[+a("http://cython.readthedocs.io/en/latest/src/userguide/fusedtypes.html") fused types].
|
||
|
|
|
||
|
|
+aside-code("Example").
|
||
|
|
from spacy.tokens cimport Doc
|
||
|
|
from spacy.vocab cimport Vocab
|
||
|
|
|
||
|
|
doc = Doc(Vocab())
|
||
|
|
lexeme = doc.vocab.get(u'hello')
|
||
|
|
doc.push_back(lexeme, True)
|
||
|
|
assert doc.text == u'hello '
|
||
|
|
|
||
|
|
+table(["Name", "Type", "Description"])
|
||
|
|
+row
|
||
|
|
+cell #[code lex_or_tok]
|
||
|
|
+cell #[code LexemeOrToken]
|
||
|
|
+cell The word to append to the #[code Doc].
|
||
|
|
|
||
|
|
+row
|
||
|
|
+cell #[code has_space]
|
||
|
|
+cell #[code bint]
|
||
|
|
+cell Whether the word has trailing whitespace.
|