First Draft

utils/hashfunctions.py

@@ -0,0 +1,84 @@
+import pandas as pd
+import requests
+import os
+
+def aggregateHashes(executions_json: dict) -> pd.DataFrame:
+    """
+    Takes the executions,  aggregates all the data with sha256 as primary, then returns aggregated dataframe
+    """
+
+    exechistories = executions_json.get("response", {}).get("exechistories", [])
+    df = pd.DataFrame(exechistories)
+    
+    if df.empty:
+        return df 
+    
+    # Aggregate by sha256 - keep all entries in lists
+    agg_df = df.groupby("sha256").agg(lambda x: list(x)).reset_index()
+    
+    return agg_df
+
+def augmentAggregatedHashes(url, agg_df: pd.DataFrame) -> pd.DataFrame:
+    """
+    Takes output of aggregatedHashes, queries API for those hashes, flattens response while keeping one row per hash,
+    aggregate applications and baselines into lists, then merges results back into agg_df to create a 
+    """
+    endpoint = url + 'v1/hash/query'
+    payload = agg_df['sha256'].tolist()
+    headers = {"X-APIKey": os.getenv('APIKEY')}
+
+    response = requests.post(endpoint, headers=headers, json=payload, verify=False)
+    data = response.json()  
+    results = data.get("response", {}).get("results", [])
+
+    rows = []
+    for res in results:
+        row = {"sha256": res.get("sha256"), "result": res.get("result")}
+
+        if "data" in res:
+            d = res["data"]
+            for key in ["filename", "filepath", "description", "filesize", "md5",
+                        "productname", "productversion", "publisher", "createtime", "modtime",
+                        "sha128", "sha384", "sha512", "datetime"]:
+                row[key] = d.get(key)
+
+            row["applications"] = d.get("applications", [])
+            row["baselines"] = d.get("baselines", [])
+
+            reputation = d.get("reputation", {})
+            for k, v in reputation.items():
+                row[f"reputation_{k}"] = v
+
+        rows.append(row)
+
+    df_api = pd.DataFrame(rows)
+
+    aug_df = agg_df.merge(df_api, on="sha256", how="left")
+
+    return aug_df
+
+def categorize_hashes(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 = df.copy()  
+    df["threatlevel"] = df["reputation"].apply(lambda x: x.get("threatlevel") if pd.notnull(x) else None)
+
+    # Masks for each category
+    mask_needsreview = (df["publisher"] == "Not Signed") & (df["threatlevel"] > threat_tolerance)
+    mask_approved = (df["publisher"] != "Not Signed") & (~df["publisher"].isin(untrusted_publishers))
+
+    # Create DataFrames for each category
+    needsreview_df = df[mask_needsreview].drop(columns=["threatlevel"])
+    approved_df = df[mask_approved].drop(columns=["threatlevel"])
+    remaining_df = df[~(mask_needsreview | mask_approved)].drop(columns=["threatlevel"])
+
+    return needsreview_df, approved_df, remaining_df
+
+def approve_hashes(approved_df: pd.DataFrame):
+    pass