Tests

MANIFEST.in

@@ -4,6 +4,7 @@ recursive-include orangecontrib/text/tests *.txt *.json
 recursive-include orangecontrib/text/tutorials *.ows
 recursive-include orangecontrib/text/widgets/icons *.svg *.png *.ai
 recursive-include orangecontrib/text/widgets/resources *.js *.css *.html
+recursive-include orangecontrib/text/widgets/tests/data
 include orangecontrib/text/widgets/tests/bow-test
 recursive-include scripts *.sh *.py
 

orangecontrib/text/widgets/tests/data/documents/good/sample_txt_ž.txt

@@ -0,0 +1 @@
+This is a test txt_ž file

orangecontrib/text/widgets/tests/data/sentiment/neg.txt

@@ -0,0 +1,5 @@
+bad
+ugly
+sad
+random
+quasi

orangecontrib/text/widgets/tests/data/sentiment/pos.txt

@@ -0,0 +1,5 @@
+good
+nice
+great
+human
+user

orangecontrib/text/widgets/tests/test_owimportdocuments.py

@@ -8,17 +8,17 @@
 class TestOWImportDocuments(WidgetTest):
     def setUp(self) -> None:
         self.widget: OWImportDocuments = self.create_widget(OWImportDocuments)
-        path = os.path.join(os.path.dirname(__file__), "data")
+        path = os.path.join(os.path.dirname(__file__), "data/documents")
         self.widget.setCurrentPath(path)
         self.widget.reload()
         self.wait_until_finished()
 
     def test_current_path(self):
-        path = os.path.join(os.path.dirname(__file__), "data")
+        path = os.path.join(os.path.dirname(__file__), "data/documents")
         self.assertEqual(path, self.widget.currentPath)
 
     def test_no_skipped(self):
-        path = os.path.join(os.path.dirname(__file__), "data", "good")
+        path = os.path.join(os.path.dirname(__file__), "data/documents", "good")
         self.widget.setCurrentPath(path)
         self.widget.reload()
         self.wait_until_finished()
@@ -30,14 +30,18 @@ def test_output(self):
         self.assertEqual(3, len(output.domain.metas))
         names = output.get_column_view("name")[0]
         self.assertListEqual(
-            ["sample_docx", "sample_odt", "sample_pdf", "sample_txt"],
+            # ž in sample_text_ž must be unicode char 0x17E not decomposed
+            # 0x7A + 0x30C as it is in file name
+            ["sample_docx", "sample_odt", "sample_pdf", "sample_txt_ž"],
             sorted(names.tolist()),
         )
         texts = output.get_column_view("content")[0]
         self.assertListEqual(
+            # ž in sample_text_ž must be unicode char 0x17E not decomposed
+            # 0x7A + 0x30C as it is in file name
             [
                 f"This is a test {x} file"
-                for x in ["docx", "odt", "pdf", "txt"]
+                for x in ["docx", "odt", "pdf", "txt_ž"]
             ],
             sorted([x.strip() for x in texts.tolist()]),
         )

orangecontrib/text/widgets/tests/test_owsentimentanalysis.py

@@ -1,3 +1,6 @@
+import os
+import numpy as np
+
 from unittest import mock, skip
 from unittest.mock import patch
 
@@ -39,6 +42,18 @@ def test_output(self):
         out_corpus = self.get_output(self.widget.Outputs.corpus)
         self.assertEqual(len(out_corpus.domain), len(self.corpus.domain) + 1)
 
+        # test custom files
+        self.widget.pos_file = os.path.join(os.path.dirname(__file__),
+                                            "data/sentiment/pos.txt")
+        self.widget.neg_file = os.path.join(os.path.dirname(__file__),
+                                            "data/sentiment/neg.txt")
+        self.widget.custom_list.click()
+        out_corpus = self.get_output(self.widget.Outputs.corpus)
+        self.assertEqual(len(out_corpus.domain), len(self.corpus.domain) + 1)
+        res = np.array([[0], [10], [16.66666667], [12.5], [11.11111111],
+                        [-14.28571429], [0], [-10], [0]])
+        np.testing.assert_array_almost_equal(out_corpus.X, res, decimal=8)
+
     def test_language_changed(self):
         """Test if output changes on language change"""
         self.send_signal(self.widget.Inputs.corpus, self.corpus)