Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Turkish tag map and morph rules addition (#6141) 

* feat: added turkish tag map

* feat: morph rules cconj and sconj

* feat: more conjuncts

* feat: added popular postpositions

* feat: added adverbs

* feat: added personal pronouns

* feat: added reflexive pronouns

* minor: corrected case capital

* minor: fixed comma typo

* feat: added indef pronouns

* feat: added dict iter

* fixed comma typo

* updated language class with tag map and morph

* use default tag map instead

* removed tag map
This commit is contained in:
Duygu Altinok 2020-10-07 10:27:36 +02:00 committed by GitHub
parent b95a11dd95
commit 2ce6fc2611
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 3909 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/lang/tr/__init__.py
View File

@ -3,6 +3,8 @@ from __future__ import unicode_literals
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .stop_words import STOP_WORDS from .stop_words import STOP_WORDS
from .lex_attrs import LEX_ATTRS
from .morph_rules import MORPH_RULES
from ..tokenizer_exceptions import BASE_EXCEPTIONS from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ..norm_exceptions import BASE_NORMS from ..norm_exceptions import BASE_NORMS
@ -13,12 +15,14 @@ from ...util import update_exc, add_lookups
class TurkishDefaults(Language.Defaults): class TurkishDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters) lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters.update(LEX_ATTRS)
lex_attr_getters[LANG] = lambda text: "tr" lex_attr_getters[LANG] = lambda text: "tr"
lex_attr_getters[NORM] = add_lookups( lex_attr_getters[NORM] = add_lookups(
Language.Defaults.lex_attr_getters[NORM], BASE_NORMS Language.Defaults.lex_attr_getters[NORM], BASE_NORMS
) )
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS) tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = STOP_WORDS stop_words = STOP_WORDS
morph_rules = MORPH_RULES
class Turkish(Language): class Turkish(Language):

3905
spacy/lang/tr/morph_rules.py Normal file
View File

File diff suppressed because it is too large Load Diff