from __future__ import annotations

import re
from abc import ABC, abstractmethod
from pathlib import Path

from app.parsers.models import ParsedReport

# Fuzzy column-name patterns → canonical field name
COLUMN_PATTERNS: dict[str, list[re.Pattern[str]]] = {
    "feature_name": [
        re.compile(r"feat|char|dimen|label|id|name|item", re.I),
    ],
    "nominal": [
        re.compile(r"nom|target|blueprint|print", re.I),
    ],
    "tolerance_plus": [
        re.compile(r"tol.*\+|upper.*tol|\+.*tol|usl|dev.*\+|pos.*tol", re.I),
    ],
    "tolerance_minus": [
        re.compile(r"tol.*-|lower.*tol|-.*tol|lsl|dev.*-|neg.*tol", re.I),
    ],
    "actual": [
        re.compile(r"actual|meas|value|result|reading", re.I),
    ],
    "deviation": [
        re.compile(r"dev(?!.*tol)|diff|error|delta", re.I),
    ],
}


def match_column(header: str) -> str | None:
    """Return the canonical field name for a header string, or None."""
    header = header.strip()
    for field_name, patterns in COLUMN_PATTERNS.items():
        for pat in patterns:
            if pat.search(header):
                return field_name
    return None


class CMMParser(ABC):
    @abstractmethod
    def parse(self, path: Path) -> ParsedReport: ...


def get_parser(filename: str) -> CMMParser:
    suffix = Path(filename).suffix.lower()
    if suffix == ".pdf":
        from app.parsers.pdf_parser import PDFParser
        return PDFParser()
    if suffix in (".xlsx", ".xls", ".csv"):
        from app.parsers.excel_parser import ExcelParser
        return ExcelParser()
    raise ValueError(f"Unsupported file type: {suffix}")