From 22375eafb08fe768bea972ecab6c3ec911554e51 Mon Sep 17 00:00:00 2001 From: ines Date: Tue, 9 May 2017 11:06:25 +0200 Subject: [PATCH] Fix and merge attrs and lex_attrs tests --- spacy/tests/lang/test_attrs.py | 52 +++++++++++++++++++++++ spacy/tests/test_attrs.py | 27 ------------ spacy/tests/test_orth.py | 77 ---------------------------------- 3 files changed, 52 insertions(+), 104 deletions(-) create mode 100644 spacy/tests/lang/test_attrs.py delete mode 100644 spacy/tests/test_attrs.py delete mode 100644 spacy/tests/test_orth.py diff --git a/spacy/tests/lang/test_attrs.py b/spacy/tests/lang/test_attrs.py new file mode 100644 index 000000000..92ee04737 --- /dev/null +++ b/spacy/tests/lang/test_attrs.py @@ -0,0 +1,52 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from ...attrs import intify_attrs, ORTH, NORM, LEMMA, IS_ALPHA +from ...lang.lex_attrs import is_punct, is_ascii, like_url, word_shape + +import pytest + + +@pytest.mark.parametrize('text', ["dog"]) +def test_attrs_key(text): + assert intify_attrs({"ORTH": text}) == {ORTH: text} + assert intify_attrs({"NORM": text}) == {NORM: text} + assert intify_attrs({"lemma": text}, strings_map={text: 10}) == {LEMMA: 10} + + +@pytest.mark.parametrize('text', ["dog"]) +def test_attrs_idempotence(text): + int_attrs = intify_attrs({"lemma": text, 'is_alpha': True}, strings_map={text: 10}) + assert intify_attrs(int_attrs) == {LEMMA: 10, IS_ALPHA: True} + + +@pytest.mark.parametrize('text', ["dog"]) +def test_attrs_do_deprecated(text): + int_attrs = intify_attrs({"F": text, 'is_alpha': True}, strings_map={text: 10}, + _do_deprecated=True) + assert int_attrs == {ORTH: 10, IS_ALPHA: True} + + +@pytest.mark.parametrize('text,match', [(',', True), (' ', False), ('a', False)]) +def test_lex_attrs_is_punct(text, match): + assert is_punct(text) == match + + +@pytest.mark.parametrize('text,match', [(',', True), ('£', False), ('♥', False)]) +def test_lex_attrs_is_ascii(text, match): + assert is_ascii(text) == match + + +@pytest.mark.parametrize('text,match', [ + ('www.google.com', True), ('google.com', True), ('sydney.com', True), + ('2girls1cup.org', True), ('http://stupid', True), ('www.hi', True), + ('dog', False), ('1.2', False), ('1.a', False), ('hello.There', False)]) +def test_lex_attrs_like_url(text, match): + assert like_url(text) == match + + +@pytest.mark.parametrize('text,shape', [ + ('Nasa', 'Xxxx'), ('capitalized', 'xxxx'), ('999999999', 'dddd'), + ('C3P0', 'XdXd'), (',', ','), ('\n', '\n'), ('``,-', '``,-')]) +def test_lex_attrs_word_shape(text, shape): + assert word_shape(text) == shape diff --git a/spacy/tests/test_attrs.py b/spacy/tests/test_attrs.py deleted file mode 100644 index 9a3af9d82..000000000 --- a/spacy/tests/test_attrs.py +++ /dev/null @@ -1,27 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from ..attrs import intify_attrs, ORTH, NORM, LEMMA, IS_ALPHA - -import pytest - - -@pytest.mark.parametrize('text', ["dog"]) -def test_attrs_key(text): - assert intify_attrs({"ORTH": text}) == {ORTH: text} - assert intify_attrs({"NORM": text}) == {NORM: text} - assert intify_attrs({"lemma": text}, strings_map={text: 10}) == {LEMMA: 10} - - -@pytest.mark.parametrize('text', ["dog"]) -def test_attrs_idempotence(text): - int_attrs = intify_attrs({"lemma": text, 'is_alpha': True}, strings_map={text: 10}) - assert intify_attrs(int_attrs) == {LEMMA: 10, IS_ALPHA: True} - - -@pytest.mark.parametrize('text', ["dog"]) -def test_attrs_do_deprecated(text): - int_attrs = intify_attrs({"F": text, 'is_alpha': True}, - strings_map={text: 10}, - _do_deprecated=True) - assert int_attrs == {ORTH: 10, IS_ALPHA: True} diff --git a/spacy/tests/test_orth.py b/spacy/tests/test_orth.py deleted file mode 100644 index c8dcbf209..000000000 --- a/spacy/tests/test_orth.py +++ /dev/null @@ -1,77 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from ..orth import is_alpha, is_digit, is_punct, is_space, is_ascii, is_upper -from ..orth import is_lower, is_title, like_url, like_number, word_shape - -import pytest - - -# TODO: brackets, is_ascii, is_upper, is_lower, is_title - - -@pytest.mark.parametrize('text,match', [ - ('1997', False), ('19.97', False), ('hello9', False), ('Hello', True), - ('HELLO', True), ('Hello9', False), ('\n', False), ('!', False), - ('!d', False), ('\nd', False)]) -def test_orth_is_alpha(text, match): - if match: - assert is_alpha(text) - else: - assert not is_alpha(text) - - -@pytest.mark.parametrize('text,match', [ - ('1997', True), ('0000000', True), ('19.97', False), ('hello9', False), ('Hello', False), ('\n', False), ('!', False), ('!0', False), - ('\n5', False)]) -def test_orth_is_digit(text, match): - if match: - assert is_digit(text) - else: - assert not is_digit(text) - - -@pytest.mark.parametrize('text,match', [(',', True), (' ', False), ('a', False)]) -def test_orth_is_punct(text,match): - if match: - assert is_punct(text) - else: - assert not is_punct(text) - - -@pytest.mark.parametrize('text,match', [(',', False), (' ', True), ('a', False)]) -def test_orth_is_space(text,match): - if match: - assert is_space(text) - else: - assert not is_space(text) - - -@pytest.mark.parametrize('text,match', [ - ('www.google.com', True), ('google.com', True), ('sydney.com', True), - ('2girls1cup.org', True), ('http://stupid', True), ('www.hi', True), - ('dog', False), ('1.2', False), ('1.a', False), ('hello.There', False)]) -def test_orth_like_url(text, match): - if match: - assert like_url(text) - else: - assert not like_url(text) - - -@pytest.mark.parametrize('text,match', [ - ('10', True), ('1', True), ('10,000', True), ('10,00', True), - (',10', True), ('999.0', True), ('one', True), ('two', True), - ('billion', True), ('dog', False), (',', False), ('1/2', True), - ('1/2/3', False)]) -def test_orth_like_number(text, match): - if match: - assert like_number(text) - else: - assert not like_number(text) - - -@pytest.mark.parametrize('text,shape', [ - ('Nasa', 'Xxxx'), ('capitalized', 'xxxx'), ('999999999', 'dddd'), - ('C3P0', 'XdXd'), (',', ','), ('\n', '\n'), ('``,-', '``,-')]) -def test_orth_word_shape(text, shape): - assert word_shape(text) == shape