Create indexing.py

indexing.py

@@ -0,0 +1,30 @@
+import re
+
+import re
+
+def word_index_multiple_mmr(text):
+    words = ["no", "not", "normal", "intact", "deficient", "mmr", "mismatch"]
+    word_indices = {word: [] for word in words}
+    current_index = 0
+
+    for word in text.split():
+        word_lower = word.lower()
+        if word_lower in words:
+            word_indices[word_lower].append(current_index)
+        current_index += 1
+        
+    mmr_indices = word_indices["mmr"]
+    for word, indices in word_indices.items():
+        if word != "mmr":
+            for i, index in enumerate(indices):
+                if i < len(mmr_indices) and index < mmr_indices[i]:
+                    indices[i] = -index
+
+    return word_indices
+
+
+# Example usage
+text = """PMS-2 Positive Tumors displaying loss of any MMR protein are mismatch repair deficient and considered to be MSI-High (MSI-H), whereas those with intact MMR proteins are expected to be microsatellite stable (MSS) or MSI-low (MSI-L). $$ IHC shows normal expression of MLH-1, MSH-2, MSH-6, and PMS-2. $$ The results of the IC analysis suggest the presence of normal DNA mismatch $$ Positive MSH-6. Another MMR protein is also involved."""
+
+result = word_index_multiple_mmr(text)
+print(result)