Added an optional param default_scheme to the url_normalize so that u…

…ser may provide default scheme (e.g., 'http') instead of 'https'.

README.md

@@ -37,6 +37,7 @@ Type "help", "copyright", "credits" or "license" for more information.
 
 History:
 
+* 1.4.1: Added an optional param default_scheme to the url_normalize
 * 1.4.0: A bit of code refactoring and cleanup
 * 1.3.3: Support empty string and double slash urls (//domain.tld)
 * 1.3.2: Same code support both Python 3 and Python 2.
@@ -45,7 +46,7 @@ History:
 * 1.1.2: support for shebang (#!) urls
 * 1.1.1: using 'http' schema by default when appropriate
 * 1.1.0: added handling of IDN domains
-* 1.0.0: code pep8-zation
+* 1.0.0: code pep8
 * 0.1.0: forked from Sam Ruby's urlnorm.py
 
 License: "Python" (PSF) License

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "url-normalize"
-version = "1.4.0"
+version = "1.4.1"
 description = "URL normalization for Python"
 authors = ["Nikolay Panov <[email protected]>"]
 license = "PSF"

tests/test_provide_url_scheme.py

@@ -18,3 +18,13 @@ def test_provide_url_scheme_result_is_expected():
         result = provide_url_scheme(url)
 
         assert result == expected, url
+
+
+def test_provide_url_scheme_accept_default_scheme_param():
+    """Assert we could provide default_scheme param other than https."""
+    url = "//site/path"
+    expected = "http://site/path"
+
+    actual = provide_url_scheme(url, default_scheme="http")
+
+    assert actual == expected

tests/test_url_normalize.py

@@ -92,3 +92,13 @@ def test_url_normalize_results():
     """Assert url_normalize return expected results."""
     for value, expected in EXPECTED_RESULTS.items():
         assert expected == url_normalize(value), value
+
+
+def test_url_normalize_with_http_scheme():
+    """Assert we could use http scheme as default."""
+    url = "//www.foo.com/"
+    expected = "http://www.foo.com/"
+
+    actual = url_normalize(url, default_scheme='http')
+
+    assert actual == expected

url_normalize/__init__.py

@@ -20,24 +20,13 @@
     http://intertwingly.net/blog/2004/08/04/Urlnorm
 This fork author: Nikolay Panov (<[email protected]>)
 
-History:
-* 1.4.0: A bit of code refactoring and cleanup
-* 1.3.3: Support empty string and double slash urls (//domain.tld)
-* 1.3.2: Same code support both Python 3 and Python 2.
-* 1.3.1: Python 3 compatibility
-* 1.2.1: PEP8, setup.py
-* 1.1.2: support for shebang (#!) urls
-* 1.1.1: using 'http' schema by default when appropriate
-* 1.1.0: added handling of IDN domains
-* 1.0.0: code pep8-zation
-* 0.1.0: forked from Sam Ruby's urlnorm.py
 """
 
 from __future__ import absolute_import
 
 from .url_normalize import url_normalize
 
 __license__ = "Python"
-__version__ = "1.4.0"
+__version__ = "1.4.1"
 
 __all__ = ["url_normalize"]

url_normalize/url_normalize.py

@@ -17,27 +17,29 @@
     "ws": "80",
     "wss": "443",
 }
+DEFAULT_CHARSET = "utf-8"
 DEFAULT_SCHEME = "https"
 
 
-def provide_url_scheme(url):
+def provide_url_scheme(url, default_scheme=DEFAULT_SCHEME):
     """Make sure we have valid url scheme.
 
     Params:
         url : string : the URL
+        default_scheme : string : default scheme to use, e.g. 'https'
 
     Returns:
         string : updated url with validated/attached scheme
 
     """
     has_scheme = ":" in url[:7]
-    is_default_scheme = url.startswith("//")
-    is_file_path = url == "-" or (url.startswith("/") and not is_default_scheme)
+    is_universal_scheme = url.startswith("//")
+    is_file_path = url == "-" or (url.startswith("/") and not is_universal_scheme)
     if not url or has_scheme or is_file_path:
         return url
-    if is_default_scheme:
-        return DEFAULT_SCHEME + ":" + url
-    return DEFAULT_SCHEME + "://" + url
+    if is_universal_scheme:
+        return default_scheme + ":" + url
+    return default_scheme + "://" + url
 
 
 def generic_url_cleanup(url):
@@ -86,7 +88,7 @@ def normalize_userinfo(userinfo):
     return userinfo
 
 
-def normalize_host(host, charset="utf-8"):
+def normalize_host(host, charset=DEFAULT_CHARSET):
     """Normalize host part of the url.
 
     Lowercase and strip of final dot.
@@ -204,7 +206,7 @@ def normalize_query(query):
     return query
 
 
-def url_normalize(url, charset="utf-8"):
+def url_normalize(url, charset=DEFAULT_CHARSET, default_scheme=DEFAULT_SCHEME):
     """URI normalization routine.
 
     Sometimes you get an URL by a user that just isn't a real
@@ -218,10 +220,14 @@ def url_normalize(url, charset="utf-8"):
     Params:
         charset : string : optional
             The target charset for the URL if the url was given as unicode string.
+
+    Returns:
+        string : a normalized url
+
     """
     if not url:
         return url
-    url = provide_url_scheme(url)
+    url = provide_url_scheme(url, default_scheme)
     url = generic_url_cleanup(url)
     url_elements = deconstruct_url(url)
     url_elements = url_elements._replace(