from __future__ import annotations

import csv

import io

from app.services.normalize import RawRead

from app.services.parsers.base import BaseParser, ParseResult

class CsvFlockParser(BaseParser):

    name = "csv_flock"

    def parse(self, data: bytes) -> ParseResult:

        text = data.decode("utf-8-sig", errors="replace")

        sample = text[:4096]

        try:

            dialect = csv.Sniffer().sniff(sample, delimiters=",;\t|")

        except csv.Error:

            dialect = csv.excel

        reader = csv.DictReader(io.StringIO(text), dialect=dialect)

        headers = reader.fieldnames or []

        rows: list[RawRead] = []

        errors: list[str] = []

        for i, row in enumerate(reader, start=1):

            clean = {k: v for k, v in row.items() if k is not None}

            if not any((v or "").strip() for v in clean.values()):

                continue

            rows.append(RawRead(fields=clean, source_row=i))

        return ParseResult(headers=list(headers), rows=rows, errors=errors)