"""File readers — iterate raw rows from various file formats.

Each reader yields rows as list[str]. The first row is typically
headers, but that interpretation is left to the consumer
(DictRowIterator).
"""

import csv
import json
from collections.abc import Iterator
from typing import Protocol, runtime_checkable

from openpyxl import load_workbook


@runtime_checkable
class FileReader(Protocol):
    """Protocol for reading raw rows from a file."""

    def read(self, file_path: str) -> Iterator[list[str]]: ...


class CsvFileReader:
    """Reads a CSV file, yielding each row as a list of strings."""

    def read(self, file_path: str) -> Iterator[list[str]]:
        with open(file_path, 'r', encoding='utf-8') as f:
            reader = csv.reader(f)
            yield from reader


class JsonFileReader:
    """Reads a JSON file containing a list of objects.

    Uses incremental parsing (ijson) when available, falling back to
    ``json.load`` for small files. The first yielded row is the header
    (keys of the first object). Subsequent rows are values in header order.
    """

    def read(self, file_path: str) -> Iterator[list[str]]:
        try:
            import ijson

            yield from self._read_streaming(file_path, ijson)
        except ImportError:
            yield from self._read_eager(file_path)

    @staticmethod
    def _read_eager(file_path: str) -> Iterator[list[str]]:
        with open(file_path, 'r', encoding='utf-8') as f:
            data = json.load(f)

        if not isinstance(data, list) or not data:
            return

        headers = list(data[0].keys())
        yield headers

        for obj in data:
            yield [str(obj.get(h, '')) for h in headers]

    @staticmethod
    def _read_streaming(file_path: str, ijson) -> Iterator[list[str]]:
        headers: list[str] | None = None

        with open(file_path, 'rb') as f:
            for obj in ijson.items(f, 'item'):
                if headers is None:
                    headers = list(obj.keys())
                    yield headers
                yield [str(obj.get(h, '')) for h in headers]


class XlsxFileReader:
    """Reads an XLSX file, yielding each row as a list of strings.

    Requires openpyxl to be installed.
    """

    def read(self, file_path: str) -> Iterator[list[str]]:
        wb = load_workbook(file_path, read_only=True, data_only=True)
        ws = wb.active

        for row in ws.iter_rows(values_only=True):
            yield [str(cell) if cell is not None else '' for cell in row]

        wb.close()