explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-24 17:06:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Rename ATTR_IDS to attrs.IDS. Rename ATTR_NAMES to attrs.NAMES. Rename UNIV_POS_IDS to parts_of_speech.IDS

Browse Source
This commit is contained in:
Matthew Honnibal 2015-10-10 17:55:55 +11:00
parent 3cea417852
commit 94bafc1417
5 changed files with 10 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/attrs.pyx
View File

@ -1,4 +1,4 @@
ATTR_IDS = {
IDS = {
"NULL_ATTR": NULL_ATTR,
"IS_ALPHA": IS_ALPHA,
"IS_ASCII": IS_ASCII,
@ -87,4 +87,4 @@ ATTR_IDS = {
}
# ATTR IDs, in order of the symbol
ATTR_NAMES = [key for key, value in sorted(ATTR_IDS.items(), key=lambda item: item[1])]
NAMES = [key for key, value in sorted(IDS.items(), key=lambda item: item[1])]

4
spacy/morphology.pyx
View File

@ -6,7 +6,7 @@ try:
except ImportError:
import json
from .parts_of_speech import UNIV_POS_NAMES
from .parts_of_speech import IDS as POS_IDS
from .parts_of_speech cimport ADJ, VERB, NOUN, PUNCT
@ -24,7 +24,7 @@ cdef class Morphology:
self.rich_tags[i].id = i
self.rich_tags[i].name = self.strings[tag_str]
self.rich_tags[i].morph = 0
self.rich_tags[i].pos = UNIV_POS_NAMES[props['pos'].upper()]
self.rich_tags[i].pos = POS_IDS[props['pos'].upper()]
self.reverse_index[self.rich_tags[i].name] = i
self._cache = PreshMapArray(self.n_tags)

5
spacy/parts_of_speech.pyx
View File

@ -1,7 +1,7 @@
from __future__ import unicode_literals
UNIV_POS_NAMES = {
IDS = {
"NO_TAG": NO_TAG,
"ADJ": ADJ,
"ADP": ADP,
@ -23,3 +23,6 @@ UNIV_POS_NAMES = {
"EOL": EOL,
"SPACE": SPACE
}
NAMES = [key for key, value in sorted(IDS.items(), key=lambda item: item[1])]

1
spacy/tokens/doc.pyx
View File

@ -14,7 +14,6 @@ from ..typedefs cimport attr_t, flags_t
from ..attrs cimport attr_id_t
from ..attrs cimport ID, ORTH, NORM, LOWER, SHAPE, PREFIX, SUFFIX, LENGTH, CLUSTER
from ..attrs cimport POS, LEMMA, TAG, DEP, HEAD, SPACY, ENT_IOB, ENT_TYPE
from ..parts_of_speech import UNIV_POS_NAMES
from ..parts_of_speech cimport CONJ, PUNCT, NOUN
from ..parts_of_speech cimport univ_pos_t
from ..lexeme cimport Lexeme

7
spacy/tokens/token.pyx
View File

@ -9,7 +9,7 @@ import numpy
from ..lexeme cimport Lexeme
from ..parts_of_speech import UNIV_POS_NAMES
from .. import parts_of_speech
from ..attrs cimport LEMMA
from ..attrs cimport ID, ORTH, NORM, LOWER, SHAPE, PREFIX, SUFFIX, LENGTH, CLUSTER
@ -318,7 +318,7 @@ cdef class Token:
property pos_:
def __get__(self):
return _pos_id_to_string[self.c.pos]
return parts_of_speech.NAMES[self.c.pos]
property tag_:
def __get__(self):
@ -363,6 +363,3 @@ cdef class Token:
property like_email:
def __get__(self): return Lexeme.c_check_flag(self.c.lex, LIKE_EMAIL)
_pos_id_to_string = {id_: string for string, id_ in UNIV_POS_NAMES.items()}