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

Work on draft Italian tokenizer

This commit is contained in:
Matthew Honnibal 2016-11-02 19:56:32 +01:00
parent 7555aa5e63
commit 19c1e83d3d
1 changed files with 20 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
spacy/it/__init__.py
View File

@ -3,7 +3,25 @@ from __future__ import unicode_literals, print_function
from os import path
from ..language import Language
from ..attrs import LANG
from . import language_data
class Italian(Language):
pass
class German(Language):
lang = 'it'
class Defaults(Language.Defaults):
tokenizer_exceptions = dict(language_data.TOKENIZER_EXCEPTIONS)
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'it'
prefixes = tuple(language_data.TOKENIZER_PREFIXES)
suffixes = tuple(language_data.TOKENIZER_SUFFIXES)
infixes = tuple(language_data.TOKENIZER_INFIXES)
tag_map = dict(language_data.TAG_MAP)
stop_words = set(language_data.STOP_WORDS)