Merge pull request #5412 from VesnaT/url_reader_special_chars

[FIX] UrlReader: Support urls with special characters

Author: PrimozGodec

Orange/data/io.py

@@ -13,7 +13,8 @@
 
 from os import path, remove
 from tempfile import NamedTemporaryFile
-from urllib.parse import urlparse, urlsplit, urlunsplit, unquote as urlunquote
+from urllib.parse import urlparse, urlsplit, urlunsplit, \
+    unquote as urlunquote, quote
 from urllib.request import urlopen, Request
 from pathlib import Path
 
@@ -405,6 +406,7 @@ def __init__(self, filename):
         filename = filename.strip()
         if not urlparse(filename).scheme:
             filename = 'http://' + filename
+        filename = quote(filename, safe="/:")
         super().__init__(filename)
 
     @staticmethod

Orange/tests/test_url_reader.py

@@ -17,3 +17,14 @@ def test_zipped(self):
             "http://datasets.biolab.si/core/philadelphia-crime.csv.xz"
         ).read()
         self.assertEqual(9666, len(data))
+
+    def test_special_characters(self):
+        # TO-DO - replace this file with a more appropriate one (e.g. .csv)
+        #  and change the assertion accordingly
+        path = "http://file.biolab.si/text-semantics/data/elektrotehniski-" \
+               "vestnik-clanki/detektiranje-utrdb-v-šahu-.txt"
+        self.assertRaises(OSError, UrlReader(path).read)
+
+
+if __name__ == "__main__":
+    unittest.main()