"""Read the supplied XLSX matrix using the standard OOXML structures."""

from __future__ import annotations

import re
import zipfile
from pathlib import Path
from typing import Any
from xml.etree import ElementTree


MAIN_NS = "http://schemas.openxmlformats.org/spreadsheetml/2006/main"
CELL_REFERENCE = re.compile(r"([A-Z]+)([0-9]+)")


def _column_index(reference: str) -> int:
    match = CELL_REFERENCE.fullmatch(reference)
    if not match:
        raise ValueError(f"Invalid XLSX cell reference: {reference}")
    result = 0
    for character in match.group(1):
        result = result * 26 + ord(character) - ord("A") + 1
    return result - 1


def _shared_strings(archive: zipfile.ZipFile) -> list[str]:
    root = ElementTree.fromstring(archive.read("xl/sharedStrings.xml"))
    return [
        "".join(node.text or "" for node in item.iter(f"{{{MAIN_NS}}}t"))
        for item in root.findall(f"{{{MAIN_NS}}}si")
    ]


def read_source_signals(path: Path) -> list[dict[str, Any]]:
    """Return the 23 signal rows needed for source-to-normalized contract checks."""

    with zipfile.ZipFile(path) as archive:
        strings = _shared_strings(archive)
        worksheet = ElementTree.fromstring(archive.read("xl/worksheets/sheet1.xml"))

    rows: list[list[str]] = []
    for row_node in worksheet.iter(f"{{{MAIN_NS}}}row"):
        values: dict[int, str] = {}
        for cell in row_node.findall(f"{{{MAIN_NS}}}c"):
            value_node = cell.find(f"{{{MAIN_NS}}}v")
            if value_node is None or value_node.text is None:
                continue
            value = value_node.text
            if cell.get("t") == "s":
                value = strings[int(value)]
            values[_column_index(str(cell.get("r")))] = value
        if values:
            width = max(values) + 1
            rows.append([values.get(index, "") for index in range(width)])

    records = []
    for row in rows[1:]:
        if len(row) < 6 or not row[0]:
            continue
        records.append(
            {
                "name": row[0],
                "description": row[1],
                "frame_id": int(row[2], 16),
                "sub_id": None if row[3] in {"", "null"} else int(row[3], 16),
                "start_bit": int(float(row[4])),
                "bit_length": int(float(row[5])),
            }
        )
    return records