planner/webservice/planner_split_files.py

import hashlib
from plan_values2 import VALUES2_HEADER

import json
import csv
from pathlib import Path


def split_file(filename, username):
    with open(filename, "r") as frh:
        structure = json.load(frh)

    input_file = Path(filename)
    export_values2(input_file, structure)
    export_user_config(input_file, structure, username)
    export_options(input_file, structure)
    export_scaffold(input_file, structure)


def export_values2(input_file, structure):
    result = []

    values2 = dict([(s["id"], s["values2"]) for s in structure])
    for id, s_entry in values2.items():
        for department, v2 in s_entry.items():
            result.append([id, department, *v2])

    output_filename = f"data_{input_file.name[:-5]}.csv"
    output_file = input_file.parent / output_filename

    with open(output_file, "w") as fwh:
        csv_writer = csv.writer(fwh, delimiter="\t")
        csv_writer.writerow(VALUES2_HEADER)
        csv_writer.writerows(result)


def export_user_config(input_file, structure, username):
    res = {}
    res["drilldown"] = dict([(s["id"], s["drilldown"]) for s in structure])

    timestamp = input_file.name.split("_")[2][:-5]
    output_filename = f"user_{username}_{timestamp}.json"
    output_file = input_file.parent / output_filename

    with open(output_file, "w") as fwh:
        json.dump(res, fwh, indent=2)


def export_options(input_file, structure):
    res = dict([(s["id"], s["options"]) for s in structure])

    output_filename = f"options_{input_file.name}"
    output_file = input_file.parent / output_filename

    with open(output_file, "w") as fwh:
        json.dump(res, fwh, indent=2)


def export_scaffold(input_file, structure):
    res = []
    for s in structure:
        res.append(
            {
                "id": s["id"],
                "text": s["text"],
                "children": s["children"],
                "children2": s["children2"],
                "parents": s["parents"],
                "accounts": s["accounts"],
                "costcenter": s["costcenter"],
                "level": s["level"],
                "form": s["form"],
                "planlevel": s.get("planlevel", False),
            }
        )

    output_filename = f"struct_{input_file.name}"
    output_file = input_file.parent / output_filename

    with open(output_file, "w") as fwh:
        json.dump(res, fwh, indent=2)


def convert_folder(base_dir):
    for filename in Path(base_dir).glob("20*.json"):
        split_file(filename, "global")


def hash_folder(base_dir):
    res = []

    for filename in Path(base_dir).glob("*.*"):
        if not filename.is_file():
            continue
        with filename.open("rb") as frh:
            digest = sha256_file_digest(frh.read())
            res.append([filename.name, digest])

    res.sort()
    most_recent = dict([(e[1], e[0]) for e in res])
    for e in res:
        e.append(e[0] == most_recent.get(e[1], None))

    with open(base_dir + "/_hash.csv", "w") as fwh:
        csv_writer = csv.writer(fwh, delimiter="\t")
        csv_writer.writerow(["Datei", "Hashwert", "Original"])
        csv_writer.writerows(res)


def sha256_file_digest(text):
    m = hashlib.new("sha256")
    m.update(text)
    return m.hexdigest()


if __name__ == "__main__":
    # split_file("save/2024_V1_20231114102855.json", "global")
    # convert_folder("save/")
    hash_folder("save/")