import re
import pandas as pd

for input in ["ASSET", "CUST", "DOB"]:
    with open(f"Inputs/{input}", errors="replace") as reportFile:
        report: str = reportFile.read()
        # Removes characters that cause errors
        report: str = report.replace("^"," ")
        colDict = {"ColName": [], "start": [], "end": []}
        for line in report.splitlines():
            print(line.strip())
            if len(line.strip()) > 50:
                matches = re.finditer('(\w|\.|/|#)+\s', line)
                for match in matches:
                    print(match)
                    colDict["ColName"].append(match.group())
                    colDict["start"].append(match.start())
                    colDict["end"].append(match.end())
                break
    pd.DataFrame(colDict).to_csv(f"Outputs/{input}.csv")