Retain whitespace in split for detecting urls

bookwyrm/templatetags/utilities.py

@@ -56,7 +56,7 @@ def truncatepath(value, arg):
 @register.simple_tag(takes_context=False)
 def get_book_cover_thumbnail(book, size="medium", ext="jpg"):
     """Returns a book thumbnail at the specified size and extension,
-       with fallback if needed"""
+    with fallback if needed"""
     if size == "":
         size = "medium"
     try:

bookwyrm/tests/views/test_status.py

@@ -281,7 +281,7 @@ class StatusViews(TestCase):
             ("@nutria@%s" % DOMAIN, user),
         )
 
-    def test_format_links(self, *_):
+    def test_format_links_simple_url(self, *_):
         """find and format urls into a tags"""
         url = "http://www.fish.com/"
         self.assertEqual(
@@ -291,6 +291,27 @@ class StatusViews(TestCase):
             views.status.format_links("(%s)" % url),
             '(<a href="%s">www.fish.com/</a>)' % url,
         )
+
+    def test_format_links_paragraph_break(self, *_):
+        """find and format urls into a tags"""
+        url = """okay
+
+http://www.fish.com/"""
+        self.assertEqual(
+            views.status.format_links(url),
+            'okay\n\n<a href="http://www.fish.com/">www.fish.com/</a>',
+        )
+
+    def test_format_links_parens(self, *_):
+        """find and format urls into a tags"""
+        url = "http://www.fish.com/"
+        self.assertEqual(
+            views.status.format_links("(%s)" % url),
+            '(<a href="%s">www.fish.com/</a>)' % url,
+        )
+
+    def test_format_links_special_chars(self, *_):
+        """find and format urls into a tags"""
         url = "https://archive.org/details/dli.granth.72113/page/n25/mode/2up"
         self.assertEqual(
             views.status.format_links(url),

bookwyrm/views/status.py

@@ -155,9 +155,11 @@ def format_links(content):
     """detect and format links"""
     validator = URLValidator()
     formatted_content = ""
-    split_content = content.split(" ")
+    split_content = re.split(r"(\s+)", content)
 
-    for index, potential_link in enumerate(split_content):
+    for potential_link in split_content:
+        if not potential_link:
+            continue
         wrapped = _wrapped(potential_link)
         if wrapped:
             wrapper_close = potential_link[-1]
@@ -182,8 +184,6 @@ def format_links(content):
 
         if wrapped:
             formatted_content += wrapper_close
-        if index < len(split_content) - 1:
-            formatted_content += " "
 
     return formatted_content