Converted basic tests to pytest

requirements-dev.txt

@@ -1,6 +1,6 @@
 -r requirements.txt
-nose
-nosexcover
+pytest
+pytest-cov
 jupyter
 sphinx
 git+https://github.com/spatialaudio/nbsphinx#egg=nbsphinx

test/doclist_tests.py

@@ -3,7 +3,6 @@
 
 from dariah_topics.doclist import PathDocList
 from pathlib import Path
-from nose.tools import eq_
 
 project_path = Path(__file__).absolute().parent.parent
 
@@ -24,7 +23,7 @@ def setup():
 
 def test_pdl_glob():
     """The glob created list should contain the 30 files from grenzboten_sample"""
-    eq_(len(grenzboten_sample), 30, msg="Not 30 texts: " + str(docs))
+    assert len(grenzboten_sample) == 30
 
 
 def test_pdl_list():

test/integration_test.py

@@ -2,8 +2,8 @@
 # -*- coding: utf-8 -*-
 
 from subprocess import check_output, STDOUT, CalledProcessError
-from nose.plugins.skip import SkipTest
 from pathlib import Path
+import pytest
 import logging
 import re
 
@@ -28,7 +28,7 @@ def run_notebook(notebook_name):
             message = cellinfo.group(1)
         logging.error(message)
 
-@SkipTest
+@pytest.mark.skip
 def jupyter_lda_test():
     run_notebook("IntroducingLda.ipynb")
 

test/mallet_test.py

@@ -1,7 +1,7 @@
-from nose.tools import raises
+from pytest import raises
 from dariah_topics.mallet import Mallet
 
-@raises(FileNotFoundError)
 def command_not_found_test():
     """When the mallet executable was not found, raise an exception."""
-    Mallet(executable="i_am_an_executable_that_does_not_exist")
+    with raises(FileNotFoundError):
+        Mallet(executable="i_am_an_executable_that_does_not_exist")

test/test_fuzzy_segmenting.py

@@ -4,7 +4,6 @@
 from dariah_topics.preprocessing import segment_fuzzy, split_paragraphs, \
     segment, tokenize
 from functools import partial
-from nose.tools import eq_
 from itertools import chain
 from pathlib import Path
 import re
@@ -33,59 +32,58 @@
 
 def test_split_paragraphs_spar():
     chunked = split_paragraphs(_DEMO_SPAR)
-    eq_(len(chunked), 4, msg='not 4 chunks: ' + str(chunked))
+    assert len(chunked) == 4
 
 
 def test_split_paragraphs_dpar():
     chunked = split_paragraphs(_DEMO_DPAR, sep=r'\n\n')
-    eq_(len(chunked), 4, msg='not 4 chunks: ' + str(chunked))
+    assert len(chunked) == 4
 
 
 def test_split_paragraphs_dpar_re():
     chunked = split_paragraphs(_DEMO_DPAR, sep=re.compile(r'\n\n'))
-    eq_(len(chunked), 4, msg='not 4 chunks: ' + str(chunked))
-
+    assert len(chunked) == 4
 
 
 def test_plain_segments():
     """segment_size chunks, zero tolerance"""
     document = ("01234 "*4).split()
     segments = list(segment_fuzzy(document, segment_size=5))
-    eq_(segments, [[['0', '1', '2', '3', '4']],
-                   [['0', '1', '2', '3', '4']],
-                   [['0', '1', '2', '3', '4']],
-                   [['0', '1', '2', '3', '4']]])
+    assert segments ==[[['0', '1', '2', '3', '4']],
+                       [['0', '1', '2', '3', '4']],
+                       [['0', '1', '2', '3', '4']],
+                       [['0', '1', '2', '3', '4']]]
 
 
 def test_shorter_segments():
     """shorter segments than chunks, no tolerance"""
     document = ("01234 "*4).split()
     segments = list(segment_fuzzy(document, segment_size=4))
-    eq_(segments, [[['0', '1', '2', '3']],
-                   [['4'], ['0', '1', '2']],
-                   [['3', '4'], ['0', '1']],
-                   [['2', '3', '4'], ['0']],
-                   [['1', '2', '3', '4']]])
+    assert segments == [[['0', '1', '2', '3']],
+                        [['4'], ['0', '1', '2']],
+                        [['3', '4'], ['0', '1']],
+                        [['2', '3', '4'], ['0']],
+                        [['1', '2', '3', '4']]]
 
 
 def test_tolerance():
     """chunk size within tolerance"""
     document = ("01234 "*4).split()
     segments = list(segment_fuzzy(document, segment_size=4, tolerance=1))
-    eq_(segments, [[['0', '1', '2', '3', '4']],
-                   [['0', '1', '2', '3', '4']],
-                   [['0', '1', '2', '3', '4']],
-                   [['0', '1', '2', '3', '4']]])
+    assert segments == [[['0', '1', '2', '3', '4']],
+                        [['0', '1', '2', '3', '4']],
+                        [['0', '1', '2', '3', '4']],
+                        [['0', '1', '2', '3', '4']]]
 
 
 def test_tolerance_2():
     """segment size ~ 2*chunk_size"""
     document = ("01234 "*4).split()
     segments = list(segment_fuzzy(document, segment_size=8, tolerance=2))
-    eq_(segments, [[['0', '1', '2', '3', '4'],
-                    ['0', '1', '2', '3', '4']],
-                   [['0', '1', '2', '3', '4'],
-                    ['0', '1', '2', '3', '4']]])
+    assert segments ==  [[['0', '1', '2', '3', '4'],
+                          ['0', '1', '2', '3', '4']],
+                         [['0', '1', '2', '3', '4'],
+                          ['0', '1', '2', '3', '4']]]
 
 
 def test_overlong_chunk():