Merge d99b82134c into 95a364c43b

breadability/scoring.py

@@ -85,7 +85,7 @@ def get_link_density(node, node_text=None):
     """
     if node_text is None:
         node_text = node.text_content()
-    node_text = normalize_whitespace(node_text.strip())
+    node_text = normalize_whitespace(node_text)
 
     text_length = len(node_text)
     if text_length == 0:
@@ -101,7 +101,7 @@ def get_link_density(node, node_text=None):
 
 
 def _get_normalized_text_length(node):
-    return len(normalize_whitespace(node.text_content().strip()))
+    return len(normalize_whitespace(node.text_content()))
 
 
 def get_class_weight(node):

breadability/utils.py

@@ -18,9 +18,6 @@ except ImportError:
             pass
 
 
-MULTIPLE_WHITESPACE_PATTERN = re.compile(r"\s+", re.UNICODE)
-
-
 def is_blank(text):
     """
     Returns ``True`` if string contains only whitespace characters
@@ -29,26 +26,14 @@ def is_blank(text):
     return not text or text.isspace()
 
 
-def shrink_text(text):
-    return normalize_whitespace(text.strip())
-
-
 def normalize_whitespace(text):
     """
     Translates multiple whitespace into single space character.
-    If there is at least one new line character chunk is replaced
-    by single LF (Unix new line) character.
     """
-    return MULTIPLE_WHITESPACE_PATTERN.sub(_replace_whitespace, text)
-
+    return ' '.join(text.split())
 
-def _replace_whitespace(match):
-    text = match.group()
 
-    if "\n" in text or "\r" in text:
-        return "\n"
-    else:
-        return " "
+shrink_text = normalize_whitespace
 
 
 def cached_property(getter):