AirlockTools/utils/hashfunctions.py

#    Copyright (C) 2025 James Brotosky, Brandon Wickline
#
#    This program is free software: you can redistribute it and/or modify
#    it under the terms of the GNU Affero General Public License as published
#    by the Free Software Foundation, either version 3 of the License, or
#    (at your option) any later version.
#
#    This program is distributed in the hope that it will be useful,
#    but WITHOUT ANY WARRANTY; without even the implied warranty of
#    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
#    GNU Affero General Public License for more details.
#
#    You should have received a copy of the GNU Affero General Public License
#    along with this program.  If not, see <https://www.gnu.org/licenses/>.

import pandas as pd
import requests
import os
import json
import utils.pathfunctions as pathf
import utils.pretty as ct


def aggregateHashes(executions_json) -> pd.DataFrame:
    """
    Takes the executions,  aggregates all the data with sha256 as primary, then returns aggregated dataframe
    """
    data = json.loads(executions_json)
    df = pd.DataFrame(data["response"]["exechistories"])

    if df.empty:
         return df
    print(df)
    # Aggregate by sha256, deduplicate lists, and preserve order
    agg_df = df.groupby("sha256").agg(lambda x: list(dict.fromkeys(x))).reset_index()

    # Add a column for the number of unique hostnames
    agg_df["num_devices"] = agg_df["hostname"].apply(len)

    # Sort by num_devices in descending order
    agg_df = agg_df.sort_values("num_devices", ascending=False)

    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 
    """
    if 'sha256' not in agg_df.columns or agg_df.empty:
        print("⚠️ 'sha256' column missing or DataFrame is empty. Skipping API query.")
        return agg_df.copy()  # Return as-is to avoid breaking downstream logic

    endpoint = url + '/v1/hash/query'
    payload = {
        "hashes": agg_df['sha256'].tolist()
    }

    headers = {"X-APIKey": os.getenv('APIKEY')}
    payload = json.dumps(payload)

    response = requests.post(endpoint, headers=headers, data=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)

    if 'sha256' not in df_api.columns:
        print("⚠️ API response missing 'sha256'. Skipping merge.")
        return agg_df.copy()

    df = agg_df.merge(df_api, on="sha256", how="left")

    # Only include columns that exist to avoid KeyErrors
    expected_columns = ['sha256', 'filename_x', 'description', 'productname', 'productversion',
                        'publisher_y', 'publisher_x', 'netdomain', 'hostname', 'username',
                        'reputation_lastseen', 'reputation_scannermatch', 'reputation_scannercount',
                        'reputation_status', 'reputation_threatlevel', 'reputation_threatname',
                        'reputation_timestamp', 'pprocess', 'gprocess', 'commandline']

    available_columns = [col for col in expected_columns if col in df.columns]
    aug_df = df[available_columns]

    return aug_df

def categorizeHashes(df: pd.DataFrame, threat_tolerance: int, untrusted_publishers: list, pups: list):
    if untrusted_publishers is None: untrusted_publishers = []
    if pups is None: pups = []

    def reputationtool(row):
        val = row["reputation_scannermatch"]
        if pd.isna(val) or val == "N/A":
            return row["publisher"] == "Not Signed"
        try:
            return int(val) > threat_tolerance
        except (ValueError, TypeError):
            return row["publisher"] == "Not Signed"

    df["reputation_flag"] = df.apply(reputationtool, axis=1)

    mask_needsreview = (
        ((df["publisher"] == "Not Signed") & df["reputation_flag"]) |
        (df["reputation_status"] == "UNKNOWN")
    )

    mask_approved = (
        (
            (df["publisher"] != "Not Signed") &
            ~df["publisher"].isin(untrusted_publishers) &
            ~df["reputation_status"].isna() &
            ~df["description"].str.contains(pathf.regulator(pups), case=False, na=False)
        ) |
        (
            (df["publisher"] == "Not Signed") &
            ~df["reputation_flag"] &
            ~df["publisher"].isin(untrusted_publishers) &
            ~df["reputation_status"].isna() &
            ~df["description"].str.contains(pathf.regulator(pups), case=False, na=False)
        )
    )

    needsreview_df = df[mask_needsreview]
    approved_df = df[mask_approved]
    unapproved_df = df[~(mask_needsreview | mask_approved)]

    return needsreview_df, approved_df, unapproved_df



def explode_and_deduplicate(df):
    df['sha256'] = df['sha256'].str.split(',')
    df = df.explode('sha256')
    return df.drop_duplicates().reset_index(drop=True)

def clean_sha256(df, column='sha256'):
    """Discard quotes, brackets, and whitespace from sha256 values."""
    df[column] = df[column].astype(str).str.strip("'[]\" ")
    return df

def destinationHashes(
    df_approved_paths: pd.DataFrame,
    df_approved_hashes: pd.DataFrame,
    df_hashes_auto_approved: pd.DataFrame,
    df_hashes_manually_approved: pd.DataFrame,
):
    # Deduplicate and explode all input DataFrames
    df_approved_paths = explode_and_deduplicate(df_approved_paths)
    df_approved_hashes = explode_and_deduplicate(df_approved_hashes)
    df_hashes_auto_approved = explode_and_deduplicate(df_hashes_auto_approved)
    df_hashes_manually_approved = explode_and_deduplicate(df_hashes_manually_approved)

    # Clean sha256 values in all relevant DataFrames
    df_approved_hashes = clean_sha256(df_approved_hashes)
    df_hashes_auto_approved = clean_sha256(df_hashes_auto_approved)
    df_hashes_manually_approved = clean_sha256(df_hashes_manually_approved)

    # Create sets for faster lookup
    auto_approved_sha256 = set(df_hashes_auto_approved['sha256'].values)
    manually_approved_sha256 = set(df_hashes_manually_approved['sha256'].values)

    # Debug: Print unmatched hashes
    unmatched = set(df_approved_hashes['sha256']) - (auto_approved_sha256 | manually_approved_sha256)
    print(f"Unmatched hashes: {unmatched}")

    # Process df_approved_paths
    df_paths = df_approved_paths.assign(destination='Path Exclusion')
    df_paths = df_paths[['sha256', 'description', 'destination', 'grouped_directory', 'filename']]

    # Process df_approved_hashes
    df_hashes = df_approved_hashes.copy()
    df_hashes['destination'] = df_hashes['sha256'].apply(
        lambda x: 'Parent Policy Baseline' if x in auto_approved_sha256
                  else ('Child Policy Allowlist' if x in manually_approved_sha256 else None)
    )
    df_hashes = df_hashes.dropna(subset=['destination'])
    df_hashes = df_hashes.assign(grouped_directory=None)

    # Use 'filename_x' only if it exists, otherwise fallback to 'filename'
    filename_col = 'filename_x' if 'filename_x' in df_hashes.columns else 'filename'
    selected_cols = ['sha256', 'description', 'destination', 'grouped_directory', filename_col]
    df_hashes = df_hashes[selected_cols]

    # Concatenate results
    df_hashdestination = pd.concat([df_paths, df_hashes], ignore_index=True)
    return df_hashdestination