From 80fdf0a6e6bcfd833f578e8a3a449f4d427154db Mon Sep 17 00:00:00 2001
From: Adrien Barbaresi <adbar@users.noreply.github.com>
Date: Thu, 11 Jan 2024 18:02:31 +0100
Subject: [PATCH] fix in clean_url(): remove whitespace (#77)

---
 courlan/clean.py    | 4 ++--
 tests/unit_tests.py | 1 +
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/courlan/clean.py b/courlan/clean.py
index fc68527..196ffab 100644
--- a/courlan/clean.py
+++ b/courlan/clean.py
@@ -64,8 +64,8 @@ def scrub_url(url: str) -> str:
         "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
         "\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f \r\n"
     )
-    # clean the input string
-    url = url.replace("[ \t]+", "")
+    # strip space in input string
+    url = "".join(url.split())
     # <![CDATA[http://www.urbanlife.de/item/260-bmw-i8-hybrid-revolution-unter-den-sportwagen.html]]>
     if url.startswith("<![CDATA["):
         url = url.replace("<![CDATA[", "")  # url = re.sub(r'^<!\[CDATA\[', '', url)
diff --git a/tests/unit_tests.py b/tests/unit_tests.py
index 42f8860..6fd78aa 100644
--- a/tests/unit_tests.py
+++ b/tests/unit_tests.py
@@ -150,6 +150,7 @@ def test_scrub():
     assert clean_url(5) is None
     assert clean_url("ø\xaa") == "%C3%B8%C2%AA"
     assert clean_url("https://example.org/?p=100") == "https://example.org/?p=100"
+    assert clean_url("https://example.org/\t?p=100") == "https://example.org/?p=100"
     assert (
         clean_url("https://example.org:443/file.html?p=100&abc=1#frag")
         == "https://example.org/file.html?abc=1&p=100#frag"