first draft of pathfunctions

utils/pathfunctions.py

@@ -0,0 +1,39 @@
+import pandas as pd
+import os
+
+
+def filepathInitalGroup(df: pd.DataFrame) -> pd.DataFrame:
+    import os
+    import pandas as pd
+    from itertools import chain
+
+    # 1. Split comma-separated filenames into lists
+    df["filename_x"] = df["filename_x"].str.split(",")
+
+    # 2. Explode so each filename has its own row
+    df = df.explode("filename_x", ignore_index=True)
+
+    # 3. Strip whitespace from filenames
+    df["filename_x"] = df["filename_x"].str.strip()
+
+    # 4. Split into directory and filename
+    df["directory"] = df["filename_x"].apply(lambda x: os.path.dirname(x) if pd.notna(x) else "")
+    df["filename"] = df["filename_x"].apply(lambda x: os.path.basename(x) if pd.notna(x) else "")
+
+    # 5. Drop the original column
+    df = df.drop(columns=["filename_x"])
+
+    # 6. Ensure all columns are lists (except directory, which is the key)
+    for col in df.columns:
+        if col != "directory":
+            df[col] = df[col].apply(lambda x: x if isinstance(x, list) else [x])
+
+    # 7. Combine rows with the same directory, flatten lists, deduplicate
+    def combine_lists(series):
+        flat = list(chain.from_iterable(series))
+        # deduplicate while preserving order
+        return list(dict.fromkeys(flat))
+
+    df = df.groupby("directory", as_index=False).agg(combine_lists)
+
+    return df