From 5e4f5ebfc881051cf44f5ee19c1c51020c340d84 Mon Sep 17 00:00:00 2001 From: Ines Montani Date: Thu, 12 Jan 2017 23:39:18 +0100 Subject: [PATCH] Modernise BILUO tests --- spacy/tests/gold/test_biluo.py | 27 +++++++++++---------------- 1 file changed, 11 insertions(+), 16 deletions(-) diff --git a/spacy/tests/gold/test_biluo.py b/spacy/tests/gold/test_biluo.py index 804739ae6..a1aa91cf0 100644 --- a/spacy/tests/gold/test_biluo.py +++ b/spacy/tests/gold/test_biluo.py @@ -1,48 +1,43 @@ +# coding: utf-8 from __future__ import unicode_literals from ...gold import biluo_tags_from_offsets -from ...vocab import Vocab from ...tokens.doc import Doc import pytest -@pytest.fixture -def vocab(): - return Vocab() - - -def test_U(vocab): - orths_and_spaces = [('I', True), ('flew', True), ('to', True), ('London', False), - ('.', True)] - doc = Doc(vocab, orths_and_spaces=orths_and_spaces) +def test_gold_biluo_U(en_vocab): + orths_and_spaces = [('I', True), ('flew', True), ('to', True), + ('London', False), ('.', True)] + doc = Doc(en_vocab, orths_and_spaces=orths_and_spaces) entities = [(len("I flew to "), len("I flew to London"), 'LOC')] tags = biluo_tags_from_offsets(doc, entities) assert tags == ['O', 'O', 'O', 'U-LOC', 'O'] -def test_BL(vocab): +def test_gold_biluo_BL(en_vocab): orths_and_spaces = [('I', True), ('flew', True), ('to', True), ('San', True), ('Francisco', False), ('.', True)] - doc = Doc(vocab, orths_and_spaces=orths_and_spaces) + doc = Doc(en_vocab, orths_and_spaces=orths_and_spaces) entities = [(len("I flew to "), len("I flew to San Francisco"), 'LOC')] tags = biluo_tags_from_offsets(doc, entities) assert tags == ['O', 'O', 'O', 'B-LOC', 'L-LOC', 'O'] -def test_BIL(vocab): +def test_gold_biluo_BIL(en_vocab): orths_and_spaces = [('I', True), ('flew', True), ('to', True), ('San', True), ('Francisco', True), ('Valley', False), ('.', True)] - doc = Doc(vocab, orths_and_spaces=orths_and_spaces) + doc = Doc(en_vocab, orths_and_spaces=orths_and_spaces) entities = [(len("I flew to "), len("I flew to San Francisco Valley"), 'LOC')] tags = biluo_tags_from_offsets(doc, entities) assert tags == ['O', 'O', 'O', 'B-LOC', 'I-LOC', 'L-LOC', 'O'] -def test_misalign(vocab): +def test_gold_biluo_misalign(en_vocab): orths_and_spaces = [('I', True), ('flew', True), ('to', True), ('San', True), ('Francisco', True), ('Valley.', False)] - doc = Doc(vocab, orths_and_spaces=orths_and_spaces) + doc = Doc(en_vocab, orths_and_spaces=orths_and_spaces) entities = [(len("I flew to "), len("I flew to San Francisco Valley"), 'LOC')] tags = biluo_tags_from_offsets(doc, entities) assert tags == ['O', 'O', 'O', '-', '-', '-']