Collapsing excess whitespace after OCR

src/documents/tests/test_consumer.py

@@ -1,5 +1,6 @@
 from django.test import TestCase
 
+from ..consumer import strip_excess_whitespace
 from ..models import FileInfo
 
 
@@ -301,3 +302,16 @@ class Permutations(TestCase):
                         }
                         self._test_guessed_attributes(
                             template.format(**spec), **spec)
+
+
+class TestOCR(TestCase):
+    text_cases = [
+        ("simple     string", "simple string"),
+        ("simple    newline\n   testing string", "simple newline\ntesting string"),
+        ("utf-8   строка с пробелами в конце  ", "utf-8 строка с пробелами в конце")
+    ]
+
+    def test_strip_excess_whitespace(self):
+        for source, result in self.text_cases:
+            actual_result = strip_excess_whitespace(source)
+            assert result == actual_result, "strip_exceess_whitespace(%s) != '%s', but '%s'" % (source, result, actual_result)