import pandas as pd
import requests
import os
import json


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 
    """
    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)

    df = agg_df.merge(df_api, on="sha256", how="left")
    aug_df = df[['sha256', 'filename_x', 'description', 'productname', 'productversion', 'publisher_y', 'publisher_x', 'netdomain', 'hostname', 'username', 'pprocess', 'gprocess', 'commandline', 'reputation_lastseen', 'reputation_scannercount', 'reputation_scannermatch', 'reputation_status', 'reputation_threatlevel', 'reputation_threatname', 'reputation_timestamp']]
    return aug_df
 
def categorizeHashes(aug_df: pd.DataFrame, threat_tolerance: int, untrusted_publishers: list):
    if untrusted_publishers is None:
        untrusted_publishers = []

    df = aug_df.copy()

    def reputationtool(row, threat_tolerance):
        if row["reputation_scannermatch"] == "N/A":
            return True
        try:
            if int(row["reputation_scannermatch"]) > threat_tolerance:
                return True
        except (ValueError, TypeError):
            pass
        return False

    mask_needsreview = (df["publisher_y"] == "Not Signed") & df.apply(lambda row: reputationtool(row, threat_tolerance), axis=1)

    mask_approved = (
    ((df["publisher_y"] != "Not Signed") & (~df["publisher_y"].isin(untrusted_publishers))) &
    (df["publisher_y"] != "Not Signed")  # explicitly signed
    ) | (
    (df["publisher_y"] == "Not Signed") &
    (~df.apply(lambda row: reputationtool(row, threat_tolerance), axis=1)) &
    (~df["publisher_y"].isin(untrusted_publishers))  # exclude untrusted even if unsigned
    )


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

    return needsreview_df, approved_df, remaining_df