edge case fix

new_dale_chall_readability/utils.py

@@ -10,28 +10,67 @@
 
 
 def pct_unfamiliar_words(text: str) -> float:
+    """
+    Calculates the percentage of unfamiliar words in a string.
+
+    step1: calls all words in a tuple from _words.
+    step2: removes the possesives from any words in said tuple.
+    step3: counts the number of unfamiliar words from cleaned tuple using _is_unfamiliar.
+    step3: returns the percentage by dividing the length of unfamiliar words by words.
+    """
     words = _words(text)
+    if not words:
+        return 0.0
     no_possesives = (w.replace("'s", "").replace("s'", "") for w in words)
     unfamiliar_words = [w for w in no_possesives if _is_unfamiliar(w)]
 
     return len(unfamiliar_words) / len(words)
 
 
 def avg_sentence_length(text: str) -> float:
+    """
+    Calculates average number of words per sentence in text.
+
+    step1: remove newlines and trailing white space from text.
+    step2: seperates text into sentances based on non-punctuation characters
+    followed by an optional punctuation
+    step3: calls _words to return all words in a tuple
+    step4: returns the average length by dividing the length of words to the length
+    of sentences.
+    """
     cleaned_up_text = text.replace("\n", " ").strip()
     sentences = re.findall(r"\b[^.!?]+[.!?]*", cleaned_up_text, re.UNICODE)
+    #prevents division of zero error
+    if not sentences:
+        return 0.0
     words = _words(text)
 
     return len(words) / len(sentences)
 
 
 def _words(in_text: str) -> tuple[str, ...]:
+    """
+    Takes the plain text that is entered and returns a tuple of words.
+
+    Args:
+        in_text: an string of words that includes HTML tags, punctuation marks, and capital words.
+        otherwise known as plain_text.
+    Returns:
+        tuple: a tuple of individual words that are stripped of HTML tags, punctuation marks, 
+        and turns Capital letters into lower case.
+
+    Example:
+        text = <p>The excited child ran to the park, yelling, 'Look, a big red ball!'
+        as she chased after it, laughing with glee.</p>
+        words = _words(text) # ("the", "excited", "child", etc...)
+    """
     plain_text = BeautifulSoup(in_text, "html.parser").text
 
     return tuple(w.lower().strip('.(),"') for w in plain_text.split())
 
 
 def _is_unfamiliar(word: str) -> bool:
+
     """
     Determine if a word is considered unfamiliar according to the Dale-Chall formula.
 

tests/utils_test.py

@@ -1,4 +1,4 @@
-from new_dale_chall_readability.utils import pct_unfamiliar_words
+from new_dale_chall_readability.utils import pct_unfamiliar_words, avg_sentence_length
 
 
 class TestPctUnfamiliarWords:
@@ -46,3 +46,14 @@ def test_embedded_ages(self):
         input = "A boy or girl aged 14, 15 or 16."
 
         assert pct_unfamiliar_words(input) == 0.0
+
+    def test_divide_0_words(self):
+        input = " "
+
+        assert pct_unfamiliar_words(input) == 0.0
+
+class TestAvgSentenceLength:
+    def test_divide_0_sentences(self):
+        input = " "
+
+        assert avg_sentence_length(input) == 0.0