explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-12 02:06:31 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Draft a from_orth method for Doc

Browse Source
This commit is contained in:
Matthew Honnibal 2015-07-17 16:39:54 +02:00
parent a9149fdcbd
commit dfdf19f6a9
1 changed files with 14 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
spacy/tokens/doc.pyx
View File

@ -96,6 +96,20 @@ cdef class Doc:
self.is_parsed = False self.is_parsed = False
self._py_tokens = [] self._py_tokens = []
@classmethod
def from_orth(cls, Vocab vocab, attr_t[:] orths, attr_t[:] spaces):
cdef int i
cdef const LexemeC* lex
cdef Doc self = cls(vocab)
cdef unicode string
cdef UniStr new_orth_c
for i in range(len(orths)):
string = vocab.strings[orths[i]]
slice_unicode(&new_orth_c, string, 0, len(string))
lex = self.vocab.get(self.mem, &new_orth_c)
self.push_back(lex, spaces[i])
return self
def __getitem__(self, object i): def __getitem__(self, object i):
"""Get a token. """Get a token.