#!/usr/bin/env python3

import argparse
from pathlib import Path
import pandas as pd
import csv
from Levenshtein import distance as levendist


argparser = argparse.ArgumentParser(
    description="Distance evaluation"
)
argparser.add_argument(
    "vp_dir", help="Directory containing merged.csv"
)

args = argparser.parse_args()

vp_path = Path(args.vp_dir)

df = pd.read_csv(vp_path / "merged.csv")

df["levenshtein-distance"] = df.apply(
    lambda row: levendist(str(row.url), str(row.log_url)), axis=1
)



df.to_csv(vp_path / "metrics.csv", quoting=csv.QUOTE_NONNUMERIC)