Add Doc.to_disk() and Doc.from_disk() methods

This commit is contained in:
ines 2017-05-24 11:58:17 +02:00
parent 10afb3c796
commit 66088851dc
2 changed files with 56 additions and 0 deletions

View File

@ -598,6 +598,24 @@ cdef class Doc:
self.is_tagged = bool(TAG in attrs or POS in attrs) self.is_tagged = bool(TAG in attrs or POS in attrs)
return self return self
def to_disk(self, path):
"""Save the current state to a directory.
path (unicode or Path): A path to a directory, which will be created if
it doesn't exist. Paths may be either strings or `Path`-like objects.
"""
raise NotImplementedError()
def from_disk(self, path):
"""Loads state from a directory. Modifies the object in place and
returns it.
path (unicode or Path): A path to a directory. Paths may be either
strings or `Path`-like objects.
RETURNS (Doc): The modified `Doc` object.
"""
raise NotImplementedError()
def to_bytes(self): def to_bytes(self):
"""Serialize, i.e. export the document contents to a binary string. """Serialize, i.e. export the document contents to a binary string.

View File

@ -253,6 +253,44 @@ p
+cell #[code Doc] +cell #[code Doc]
+cell Itself. +cell Itself.
+h(2, "to_disk") Doc.to_disk
+tag method
p Save the current state to a directory.
+aside-code("Example").
doc.to_disk('/path/to/doc')
+table(["Name", "Type", "Description"])
+row
+cell #[code path]
+cell unicode or #[code Path]
+cell
| A path to a directory, which will be created if it doesn't exist.
| Paths may be either strings or #[code Path]-like objects.
+h(2, "from_disk") Doc.from_disk
+tag method
p Loads state from a directory. Modifies the object in place and returns it.
+aside-code("Example").
from spacy.tokens import Doc
doc = Doc().from_disk('/path/to/doc')
+table(["Name", "Type", "Description"])
+row
+cell #[code path]
+cell unicode or #[code Path]
+cell
| A path to a directory. Paths may be either strings or
| #[code Path]-like objects.
+footrow
+cell returns
+cell #[code Doc]
+cell The modified #[code Doc] object.
+h(2, "to_bytes") Doc.to_bytes +h(2, "to_bytes") Doc.to_bytes
+tag method +tag method