From 753068f1d533076da72b9b52c8b65d2883eccd3c Mon Sep 17 00:00:00 2001 From: Ines Montani Date: Sun, 18 Dec 2016 16:55:25 +0100 Subject: [PATCH] Use base language data as default --- spacy/language.py | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/spacy/language.py b/spacy/language.py index a95146eb2..222aadf16 100644 --- a/spacy/language.py +++ b/spacy/language.py @@ -21,6 +21,7 @@ from .matcher import Matcher from . import attrs from . import orth from . import util +from . import language_data from .lemmatizer import Lemmatizer from .train import Trainer @@ -140,14 +141,14 @@ class BaseDefaults(object): if nlp.entity: pipeline.append(nlp.entity) return pipeline - - prefixes = tuple() - suffixes = tuple() + prefixes = tuple(language_data.TOKENIZER_PREFIXES) - infixes = tuple() - - tag_map = {} + suffixes = tuple(language_data.TOKENIZER_SUFFIXES) + + infixes = tuple(language_data.TOKENIZER_INFIXES) + + tag_map = dict(language_data.TAG_MAP) tokenizer_exceptions = {}