first draft of pathfunctions

AirlockTools.py

@@ -3,6 +3,7 @@ import os
 import utils.getdeviceevents
 import utils.allowlist
 import utils.hashfunctions
+import utils.pathfunctions
 import urllib3
 import pandas as pd
 
@@ -46,6 +47,15 @@ def menu():
 			categorized[0].to_html("needsreview.html", index=False)
 			categorized[1].to_html("approved.html", index=False)
 			categorized[2].to_html("remaining.html", index=False)
+		if choice == '4':
+			html_file = "augmentedlist.html"
+			augmented_df = pd.read_html(html_file)
+			print(augmented_df)
+
+			combined_df = pd.concat(augmented_df, ignore_index=True)
+			test = utils.pathfunctions.filepathInitalGroup(combined_df)
+			test.to_html("testgroup2.html", index=False)
+			
 
 
 if __name__ == "__main__":

utils/hashfunctions.py

@@ -91,43 +91,3 @@ def categorizeHashes(aug_df: pd.DataFrame, threat_tolerance: int, untrusted_publ
    remaining_df = df[~(mask_needsreview | mask_approved)]
 
    return needsreview_df, approved_df, remaining_df
-
- 
-"""
-def categorizeHashes(aug_df: pd.DataFrame, threat_tolerance: int, untrusted_publishers: list):
-    
-    Categorize hashes into needsreview, approved, and remaining based on publisher and threat level.
-    
-    
-    if untrusted_publishers is None:
-        untrusted_publishers = []
-
-    # Flatten threatlevel from nested reputation dict
-    df = aug_df.copy()  
-
-    # Masks for each category
-    mask_needsreview = ((df["publisher_y"] == "Not Signed") & reputationtool(df)) 
-
-    print(mask_needsreview)
-
-    mask_approved = (df["publisher_y"] != "Not Signed") & (~df["publisher_y"].isin(untrusted_publishers))
-
-    print(mask_approved)
-
-    # Create DataFrames for each category
-    needsreview_df = df[mask_needsreview]
-    approved_df = df[mask_approved]
-    remaining_df = df[~(mask_needsreview | mask_approved)]
-
-    return needsreview_df, approved_df, remaining_df
-
-def approvehashes(approved_df: pd.DataFrame):
-    pass
-
-def reputationtool(df):
-    if df["reputation_scannermatch"] == "N/A":
-        return True
-    if df["reputation_scannermatch"].astype(int) > 3:
-        return True
-    return False
-    """

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