import ast
import csv
import functools
import os
import re
from datetime import datetime, timedelta, timezone
from io import BytesIO
from urllib.parse import urlparse

import boto3
import pandas as pd
import requests
from google.cloud import bigquery


@functools.lru_cache
def gw_access(begin, epoch=None):
    if epoch is None:
        S3_BUCKET = os.getenv("S3_BUCKET")
        s3 = boto3.client("s3")

        gw_access_df = pd.DataFrame()

        d = begin
        while d < datetime.now(timezone.utc):
            try:
                df = pd.read_csv(
                    s3.get_object(
                        Bucket=S3_BUCKET,
                        Key=f"data/gw_access_log/{d.date()}.sample.csv",
                    )["Body"],
                    low_memory=False,
                )
                gw_access_df = pd.concat([gw_access_df, df])
            except:
                pass

            d += timedelta(days=1)
        return gw_access_df

    gw_access_df = gw_access(begin, epoch=None)
    gw_access_df = gw_access_df[gw_access_df.time < epoch]
    return gw_access_df


@functools.lru_cache
def dbaas_clusters(epoch=None):
    if epoch is None:
        client = bigquery.Client()
        r = client.query("SELECT * FROM `gcp-digital-bi.metadb.dbaas_clusters`")
        return pd.DataFrame.from_records([dict(row) for row in r])
    df = dbaas_clusters(epoch=None)
    return df[df.created_at < epoch]