fix(strings): use frequency-based signature for anagrams

Replaced the sorting-based signature implementation with a frequency-based
approach using `collections.Counter`. This ensures that the signature
represents both characters and their counts, preventing collisions and
better grouping of true anagrams.

Examples:
- "test" → "e1s1t2"
- "finaltest" → "a1e1f1i1l1n1s1t2"
- "this is a test" → " 3a1e1h1i2s3t3"

Also updated the anagram lookup to use the new frequency-based signatures, making results more accurate and avoiding false positives.

Author: sowndappan5

strings/anagrams.py

@@ -3,42 +3,50 @@
 import collections
 import pprint
 from pathlib import Path
+from typing import List
 
 
 def signature(word: str) -> str:
-    """Return a word sorted
+    """
+    Return a frequency-based signature for a word.
+
     >>> signature("test")
-    'estt'
+    'e1s1t2'
     >>> signature("this is a test")
-    '   aehiisssttt'
+    ' 3a1e1h1i2s3t3'
     >>> signature("finaltest")
-    'aefilnstt'
+    'a1e1f1i1l1n1s1t2'
     """
-    return "".join(sorted(word))
+    freq = collections.Counter(word)
+    return "".join(f"{ch}{freq[ch]}" for ch in sorted(freq))
 
 
-def anagram(my_word: str) -> list[str]:
-    """Return every anagram of the given word
+def anagram(my_word: str) -> List[str]:
+    """
+    Return every anagram of the given word from the dictionary.
+
     >>> anagram('test')
     ['sett', 'stet', 'test']
     >>> anagram('this is a test')
     []
     >>> anagram('final')
     ['final']
     """
-    return word_by_signature[signature(my_word)]
+    return word_by_signature.get(signature(my_word), [])
 
 
+# Load word list
 data: str = Path(__file__).parent.joinpath("words.txt").read_text(encoding="utf-8")
 word_list = sorted({word.strip().lower() for word in data.splitlines()})
 
+# Map signatures to word list
 word_by_signature = collections.defaultdict(list)
 for word in word_list:
     word_by_signature[signature(word)].append(word)
 
 if __name__ == "__main__":
     all_anagrams = {word: anagram(word) for word in word_list if len(anagram(word)) > 1}
 
-    with open("anagrams.txt", "w") as file:
-        file.write("all_anagrams = \n ")
+    with open("anagrams.txt", "w", encoding="utf-8") as file:
+        file.write("all_anagrams = \n")
         file.write(pprint.pformat(all_anagrams))