modernized tests

tests/conftest.py

@@ -16,8 +16,8 @@
 
 
 @pytest.fixture
-def git_repo(tmpdir):
-    return get_test_repo(str(tmpdir), remote_url='https://github.com/lexibank/dataset.git')
+def git_repo(tmp_path):
+    return get_test_repo(tmp_path, remote_url='https://github.com/lexibank/dataset.git')
 
 
 @pytest.fixture

tests/test_commands.py

@@ -1,6 +1,5 @@
 import shlex
 import logging
-import pathlib
 import argparse
 
 import pytest
@@ -24,12 +23,10 @@ def _main(cmd, **kw):
     main(['--no-config'] + shlex.split(cmd), **kw)
 
 
-def test_makecldf_concepticon_concepts(repos, tmpdir):
+def test_makecldf_concepticon_concepts(repos):
     d = repos / 'datasets' / 'test_dataset_concepticon_concepts'
     _main('lexibank.makecldf {0} --glottolog {1} --concepticon {1} --clts {1}'.format(
-        str(d / 'tdcc.py'),
-        str(repos),
-    ))
+        d / 'tdcc.py', repos))
     assert d.joinpath('cldf', 'parameters.csv').read_text(encoding='utf8').splitlines()[0] == \
         'ID,Name,Concepticon_ID,Concepticon_Gloss,NUMBER,ENGLISH,CHINESE,PAGE'
 
@@ -50,7 +47,7 @@ def test_makecldf_multi_profiles(repos):
     assert 'FREQUENCY' in (d / 'etc' / 'orthography' / 'p1.tsv').read_text(encoding='utf8')
 
 
-def test_makecldf(repos, dataset, dataset_cldf, dataset_no_cognates, sndcmp, tmpdir, capsys):
+def test_makecldf(repos, dataset, dataset_cldf, dataset_no_cognates, sndcmp, capsys, tmp_path):
     _main('lexibank.makecldf {0} --glottolog {1} --concepticon {1} --clts {1}'.format(
         str(dataset.dir / 'td.py'),
         str(repos),
@@ -89,7 +86,7 @@ def test_makecldf(repos, dataset, dataset_cldf, dataset_no_cognates, sndcmp, tmp
         str(dataset_no_cognates.dir / 'tdn.py'),
         str(repos),
         str(repos),
-        str(tmpdir.join('db')),
+        str(tmp_path / 'db'),
     ))
 
 
@@ -108,25 +105,16 @@ def test_check_lexibank(dataset_cldf, caplog):
     assert any('Cross-concept' in w for w in warnings)
 
 
-def test_ls(repos, tmpdir, dataset):
+def test_ls(repos, tmp_path, dataset):
     _main('lexibank.load --db {3} {0} --glottolog {1} --concepticon {2}'.format(
-        str(dataset.dir / 'td.py'),
-        str(repos),
-        str(repos),
-        str(tmpdir.join('db')),
-    ))
-    _main('lexibank.ls {0} --all --db {1}'.format(
-        str(dataset.dir / 'td.py'),
-        str(tmpdir.join('db'))))
-    _main('lexibank.unload --db {1} {0}'.format(
-        str(dataset.dir / 'td.py'),
-        str(tmpdir.join('db')),
-    ))
+        dataset.dir / 'td.py', repos, repos, tmp_path / 'db'))
+    _main('lexibank.ls {0} --all --db {1}'.format(dataset.dir / 'td.py', tmp_path / 'db'))
+    _main('lexibank.unload --db {1} {0}'.format(dataset.dir / 'td.py', tmp_path / 'db'))
 
 
-def test_db(tmpdir, mocker):
+def test_db(tmp_path, mocker):
     mocker.patch('pylexibank.commands.db.subprocess', mocker.Mock(return_value=0))
-    _main('lexibank.db --db {0}'.format(str(tmpdir.join('db'))))
+    _main('lexibank.db --db {0}'.format(tmp_path / 'db'))
 
 
 def test_check_phonotactics(dataset):
@@ -151,13 +139,12 @@ def test_readme(dataset, repos):
     assert '# Contributors' in dataset.dir.joinpath('README.md').read_text(encoding='utf8')
 
 
-def test_new(tmpdir, mocker):
+def test_new(tmp_path, mocker):
     mocker.patch('cldfbench.metadata.input', mocker.Mock(return_value='abc'))
-    _main('new --template lexibank_simple --out ' + str(tmpdir))
-    assert pathlib.Path(str(tmpdir)).joinpath('abc', 'CONTRIBUTORS.md').exists()
+    _main('new --template lexibank_simple --out ' + str(tmp_path))
+    assert tmp_path.joinpath('abc', 'CONTRIBUTORS.md').exists()
 
     mocker.patch('cldfbench.metadata.input', mocker.Mock(return_value='cde'))
-    _main('new --template lexibank_combined --out ' + str(tmpdir))
-    assert '{{' not in pathlib.Path(str(tmpdir)).joinpath(
-        'cde', 'lexibank_cde.py').read_text(encoding='utf8')
+    _main('new --template lexibank_combined --out ' + str(tmp_path))
+    assert '{{' not in tmp_path.joinpath('cde', 'lexibank_cde.py').read_text(encoding='utf8')
 

tests/test_dataset.py

@@ -1,7 +1,6 @@
 import sys
 import json
 import importlib
-import pathlib
 
 import pytest
 from clldutils.path import sys_path
@@ -43,8 +42,8 @@ class Test(Dataset):
         Test()
 
 
-def test_Dataset_tokenizer(tmpdir):
-    etc = pathlib.Path(str(tmpdir)).joinpath('etc')
+def test_Dataset_tokenizer(tmp_path):
+    etc = tmp_path / 'etc'
     etc.mkdir()
     orth_dir = etc.joinpath('orthography')
     orth_dir.mkdir()

tests/test_db.py

@@ -4,6 +4,11 @@
 from pylexibank.db import Database, ColSpec, schema
 
 
+@pytest.fixture
+def db(tmp_path):
+    return Database(tmp_path / 'lexibank.sqlite')
+
+
 def test_ColSpec():
     col = ColSpec(name='c', csvw_type='float')
     assert col.convert(5) == '5'
@@ -24,8 +29,7 @@ def test_schema(cldf_dataset):
         assert False
 
 
-def test_db(tmpdir, dataset, mocker, capsys):
-    db = Database(str(tmpdir.join('lexibank.sqlite')))
+def test_db(dataset, mocker, capsys, db):
     db.load(dataset)
     db.create(exists_ok=True)
     with pytest.raises(ValueError):
@@ -58,8 +62,7 @@ def test_db(tmpdir, dataset, mocker, capsys):
     db.load(dataset)
 
 
-def test_db_multiple_datasets(tmpdir, dataset, dataset_cldf, dataset_cldf_capitalisation, capsys):
-    db = Database(str(tmpdir.join('lexibank.sqlite')))
+def test_db_multiple_datasets(dataset, dataset_cldf, dataset_cldf_capitalisation, capsys, db):
     db.load(dataset)
     db.load(dataset_cldf, verbose=True)
     db.load(dataset_cldf_capitalisation, verbose=True)
@@ -71,11 +74,10 @@ def test_db_multiple_datasets(tmpdir, dataset, dataset_cldf, dataset_cldf_capita
         assert ('1', 'abc') in [(r[0], r[1]) for r in res]
 
 
-def test_db_multiple_datasets_error(tmpdir, dataset, dataset_factory):
+def test_db_multiple_datasets_error(dataset, dataset_factory, db):
     import shutil
     from clldutils.jsonlib import load, dump
 
-    db = Database(str(tmpdir.join('lexibank.sqlite')))
     assert not db.fname.exists()
     db.load(dataset)
 

tests/test_profile.py

@@ -44,8 +44,8 @@ def test_augment(clts):
     assert prf.graphemes['^a']['SCA'] == 'S'
 
 
-def test_write(tmpdir):
-    fname = pathlib.Path(str(tmpdir)) / 'profile.tsv'
+def test_write(tmp_path):
+    fname = tmp_path / 'profile.tsv'
     prf = Profile({'Grapheme': 'ab', 'IPA': 'z'}, {'Grapheme': 'x', 'IPA': 'y'})
     prf.write(fname)
     assert Profile.from_file(fname).graphemes == prf.graphemes
@@ -62,8 +62,8 @@ def test_clean(clts):
     assert prf.graphemes['b']['IPA'] == 'b/tɬ'
 
 
-def test_check(caplog, tmpdir, clts):
-    prf_path = pathlib.Path(str(tmpdir)) / 'profile.tsv'
+def test_check(caplog, tmp_path, clts):
+    prf_path = tmp_path / 'profile.tsv'
 
     prf_path.write_text('Grapheme\tIPA\na\tx\na\tx\n')
     prf = Profile.from_file(prf_path)

tests/test_providers_abvd.py

@@ -1,20 +1,18 @@
 import pytest
-from pathlib import Path
 
 from clldutils.path import copytree
-from pycldf.sources import Source
 
 from pylexibank.providers import abvd
 
 
 @pytest.fixture
-def abvd_dataset(repos, tmpdir, glottolog, concepticon):
-    copytree(repos / 'datasets' / 'abvd', str(tmpdir.join('abvd')))
+def abvd_dataset(repos, tmp_path, glottolog, concepticon):
+    copytree(repos / 'datasets' / 'abvd', tmp_path / 'abvd')
 
     class Dataset(abvd.BVD):
         id = 'x'
         SECTION = 'y'
-        dir = Path(str(tmpdir.join('abvd')))
+        dir = tmp_path / 'abvd'
 
     return Dataset(glottolog=glottolog, concepticon=concepticon)
 

tests/test_providers_clld.py

@@ -1,9 +1,7 @@
-import pathlib
-
 from pylexibank.providers.clld import CLLD
 
 
-def test_CLLD(mocker, repos, tmpdir):
+def test_CLLD(mocker, repos, tmp_path):
     class Response(mocker.Mock):
         def iter_content(self, *args, **kw):
             print(repos.joinpath('wold_dataset.cldf.zip'))
@@ -12,7 +10,7 @@ def iter_content(self, *args, **kw):
 
     class WOLD(CLLD):
         id = 'wold'
-        dir = pathlib.Path(str(tmpdir))
+        dir = tmp_path
 
     ds = WOLD()
     assert ds.url()

tests/test_providers_sndcmp.py

@@ -15,15 +15,18 @@
 
 
 @pytest.fixture
-def sndcmp_dataset(repos, tmpdir, glottolog, concepticon):
+def sndcmp_dir(tmp_path, repos):
+    copytree(repos / 'datasets' / 'sndcmp', tmp_path / 'sndcmp')
+    return tmp_path / 'sndcmp'
 
-    copytree(repos / 'datasets' / 'sndcmp', str(tmpdir.join('sndcmp')))
 
+@pytest.fixture
+def sndcmp_dataset(repos, glottolog, concepticon, sndcmp_dir):
     class CustomConcept(SNDCMPConcept):
         Bislama_Gloss = attr.ib(default=None)
 
     class Dataset(SNDCMP):
-        dir = str(tmpdir.join('sndcmp'))
+        dir = sndcmp_dir
         id = "sndcmpvanuatu"
         study_name = "Vanuatu"
         second_gloss_lang = "Bislama"
@@ -40,12 +43,9 @@ def get_source_id_array(self, lexeme):
 
 
 @pytest.fixture
-def sndcmp2_dataset(repos, tmpdir, glottolog, concepticon):
-
-    copytree(repos / 'datasets' / 'sndcmp', str(tmpdir.join('sndcmp')))
-
+def sndcmp2_dataset(repos, glottolog, concepticon, sndcmp_dir):
     class Dataset(SNDCMP):
-        dir = str(tmpdir.join('sndcmp'))
+        dir = sndcmp_dir
         id = "sndcmpvanuatu"
         study_name = "Vanuatu"
         source_id_array = ["Shimelman2019"]
@@ -55,12 +55,9 @@ class Dataset(SNDCMP):
 
 
 @pytest.fixture
-def sndcmp_dl_dataset(repos, tmpdir, glottolog, concepticon):
-
-    copytree(repos / 'datasets' / 'sndcmp', str(tmpdir.join('sndcmp')))
-
+def sndcmp_dl_dataset(repos, glottolog, concepticon, sndcmp_dir):
     class Dataset(SNDCMP):
-        dir = str(tmpdir.join('sndcmp'))
+        dir = sndcmp_dir
         id = "sndcmpbrazil"
         study_name = "Brazil"
         second_gloss_lang = None
@@ -71,7 +68,6 @@ class Dataset(SNDCMP):
 
 
 def test_sndcmp(sndcmp_dataset, mocker):
-
     sndcmp_dataset.cmd_create_ref_etc_files(mocker.MagicMock())
     assert (sndcmp_dataset.raw_dir / 'languages.csv').exists()
     assert (sndcmp_dataset.raw_dir / 'concepts.csv').exists()
@@ -83,7 +79,6 @@ def test_sndcmp(sndcmp_dataset, mocker):
 
 
 def test_sndcmp2(sndcmp2_dataset, mocker):
-
     sndcmp2_dataset.cmd_create_ref_etc_files(mocker.MagicMock())
     csv = sndcmp2_dataset.raw_dir / 'concepts.csv'
     res = list(reader(csv, dicts=True))
@@ -96,7 +91,6 @@ def test_sndcmp_cldf(sndcmp_dataset, mocker):
 
 
 def test_sndcmp_dl(sndcmp_dl_dataset, mocker):
-
     class Requests(mocker.Mock):
         def get(self, *args, **kw):
             if 'zip' in args[0]:

tests/test_providers_tob.py

@@ -16,14 +16,14 @@
        '</div>'
 
 
-def test_TOB(tmpdir, mocker, concepticon, glottolog):
+def test_TOB(tmp_path, mocker, concepticon, glottolog):
     class DS(TOB):
-        dir = Path(str(tmpdir))
+        dir = tmp_path
         id = 'test'
         name = 'name'
         dset = 'dset'
 
-    tmpdir.join('metadata.json').write_text('{"conceptlist": "Wang-2004-471"}', encoding='utf8')
+    tmp_path.joinpath('metadata.json').write_text('{"conceptlist": "Wang-2004-471"}', encoding='utf8')
 
     class Requests(mocker.Mock):
         def get(self, *args, **kw):

tests/test_util.py

@@ -18,8 +18,8 @@ def test_iter_repl(seq, subseq, repl, out):
     assert list(util.iter_repl(seq, subseq, repl)) == out
 
 
-def test_jsondump(tmpdir):
-    fname = str(tmpdir.join('dump.json'))
+def test_jsondump(tmp_path):
+    fname = tmp_path / 'dump.json'
     res = util.jsondump({'a': 2}, fname)
     assert 'a' in res
     res = util.jsondump({'b': 3}, fname)