w3lib.utils: deprecate functions not needed for Python 3

tests/test_util.py

@@ -0,0 +1,26 @@
+from unittest import TestCase
+
+from pytest import deprecated_call
+
+from w3lib.util import str_to_unicode, to_native_str, unicode_to_str
+
+
+class StrToUnicodeTestCase(TestCase):
+
+    def test_deprecation(self):
+        with deprecated_call():
+            str_to_unicode('')
+
+
+class ToNativeStrTestCase(TestCase):
+
+    def test_deprecation(self):
+        with deprecated_call():
+            to_native_str('')
+
+
+class UnicodeToStrTestCase(TestCase):
+
+    def test_deprecation(self):
+        with deprecated_call():
+            unicode_to_str('')

w3lib/url.py

@@ -24,7 +24,7 @@
     urlunsplit,
 )
 from urllib.request import pathname2url, url2pathname
-from w3lib.util import to_bytes, to_native_str, to_unicode
+from w3lib.util import to_bytes, to_unicode
 
 
 # error handling function for bytes-to-Unicode decoding errors with URLs
@@ -85,13 +85,13 @@ def safe_url_string(url, encoding='utf8', path_encoding='utf8', quote_path=True)
     if quote_path:
         path = quote(to_bytes(parts.path, path_encoding), _path_safe_chars)
     else:
-        path = to_native_str(parts.path)
+        path = to_unicode(parts.path)
 
     # quote() in Python2 return type follows input type;
     # quote() in Python3 always returns Unicode (native str)
     return urlunsplit((
-        to_native_str(parts.scheme),
-        to_native_str(netloc).rstrip(':'),
+        to_unicode(parts.scheme),
+        to_unicode(netloc).rstrip(':'),
         path,
         # encoding of query and fragment follows page encoding
         # or form-charset (if known and passed)
@@ -415,8 +415,8 @@ def _safe_ParseResult(parts, encoding='utf8', path_encoding='utf8'):
         netloc = parts.netloc
 
     return (
-        to_native_str(parts.scheme),
-        to_native_str(netloc),
+        to_unicode(parts.scheme),
+        to_unicode(netloc),
 
         # default encoding for path component SHOULD be UTF-8
         quote(to_bytes(parts.path, path_encoding), _path_safe_chars),

w3lib/util.py

@@ -1,11 +1,26 @@
+from warnings import warn
+
+
 def str_to_unicode(text, encoding=None, errors='strict'):
+    warn(
+        "The w3lib.utils.str_to_unicode function is deprecated and "
+        "will be removed in a future release.",
+        DeprecationWarning,
+        stacklevel=2,
+    )
     if encoding is None:
         encoding = 'utf-8'
     if isinstance(text, bytes):
         return text.decode(encoding, errors)
     return text
 
 def unicode_to_str(text, encoding=None, errors='strict'):
+    warn(
+        "The w3lib.utils.unicode_to_str function is deprecated and "
+        "will be removed in a future release.",
+        DeprecationWarning,
+        stacklevel=2,
+    )
     if encoding is None:
         encoding = 'utf-8'
     if isinstance(text, str):
@@ -38,4 +53,11 @@ def to_bytes(text, encoding=None, errors='strict'):
 
 def to_native_str(text, encoding=None, errors='strict'):
     """ Return str representation of `text` """
+    warn(
+        "The w3lib.utils.to_native_str function is deprecated and "
+        "will be removed in a future release. Please use "
+        "w3lib.utils.to_unicode instead.",
+        DeprecationWarning,
+        stacklevel=2,
+    )
     return to_unicode(text, encoding, errors)