WealthySmart/backend/app/api/v1/endpoints/import_transactions.py

import hashlib
import re
from datetime import datetime
from typing import Optional

from fastapi import APIRouter, Depends
from pydantic import BaseModel, Field
from sqlmodel import Session, select

from app.auth import get_current_user
from app.db import get_session
from app.models.models import (
    Bank,
    Currency,
    Transaction,
    TransactionSource,
    TransactionType,
)
from app.api.v1.endpoints.transactions import auto_categorize

router = APIRouter(prefix="/import", tags=["import"])


class PasteImportRequest(BaseModel):
    # ~1 MB cap: a full statement paste is a few KB; anything larger is abuse.
    text: str = Field(max_length=1_000_000)
    bank: Bank = Bank.BAC
    source: TransactionSource = TransactionSource.CREDIT_CARD
    # Override for false-positive dedup (legitimate same-day, same-amount
    # repeat purchases hash identically) — review UX-20/BE-08.
    allow_duplicates: bool = False


class SkippedDuplicate(BaseModel):
    line: int
    merchant: str
    date: str
    amount: float
    currency: str
    existing_id: int
    existing_merchant: str
    existing_date: str
    existing_amount: float
    existing_source: str


class PasteImportResult(BaseModel):
    imported: int
    duplicates: int
    errors: list[str]
    skipped: list[SkippedDuplicate] = []


def make_reference_hash(date: datetime, merchant: str, amount: float, currency: str) -> str:
    raw = f"{date.isoformat()}|{merchant.strip().upper()}|{amount}|{currency}"
    return hashlib.sha256(raw.encode()).hexdigest()[:16]


def parse_bac_line(line: str) -> Optional[dict]:
    """Parse a single BAC statement line.

    Format: DD/MM/YYYY\tMERCHANT\\CITY\\COUNTRY\tAMOUNT CURRENCY
    """
    line = line.strip()
    if not line:
        return None

    parts = re.split(r"\t+", line)
    if len(parts) < 3:
        # Try multiple spaces as delimiter
        parts = re.split(r"\s{2,}", line)
    if len(parts) < 3:
        return None

    # Parse date
    date_str = parts[0].strip()
    try:
        date = datetime.strptime(date_str, "%d/%m/%Y")
    except ValueError:
        return None

    # Parse merchant\city\country
    merchant_raw = parts[1].strip()
    merchant_parts = merchant_raw.split("\\")
    merchant = merchant_parts[0].strip()
    city = merchant_parts[1].strip() if len(merchant_parts) > 1 else None

    # Parse amount + currency
    amount_str = parts[2].strip()
    # Extract currency (last 3 chars)
    match = re.match(r"^([\d,.-]+)\s*(CRC|USD)$", amount_str, re.IGNORECASE)
    if not match:
        return None

    amount_raw = match.group(1).replace(",", "")
    currency = match.group(2).upper()
    amount = float(amount_raw)

    # Determine transaction type
    is_refund = amount < 0 or "PAGO RECIBIDO" in merchant.upper()
    tx_type = TransactionType.DEVOLUCION if is_refund else TransactionType.COMPRA
    amount = abs(amount)

    return {
        "date": date,
        "merchant": merchant,
        "city": city,
        "amount": amount,
        "currency": currency,
        "transaction_type": tx_type,
    }


@router.post("/paste", response_model=PasteImportResult)
def paste_import(
    req: PasteImportRequest,
    session: Session = Depends(get_session),
    _user: str = Depends(get_current_user),
):
    imported = 0
    duplicates = 0
    errors: list[str] = []
    skipped: list[SkippedDuplicate] = []

    lines = req.text.strip().splitlines()

    for i, line in enumerate(lines, 1):
        if not line.strip():
            continue

        parsed = parse_bac_line(line)
        if parsed is None:
            errors.append(f"Line {i}: could not parse")
            continue

        # Generate reference hash for duplicate detection
        ref_hash = make_reference_hash(
            parsed["date"], parsed["merchant"], parsed["amount"], parsed["currency"]
        )

        # Check for duplicates — and SHOW the user what matched instead of
        # silently dropping the line (UX-20).
        if not req.allow_duplicates:
            existing = session.exec(
                select(Transaction).where(Transaction.reference == ref_hash)
            ).first()
            if existing:
                duplicates += 1
                skipped.append(
                    SkippedDuplicate(
                        line=i,
                        merchant=parsed["merchant"],
                        date=parsed["date"].isoformat(),
                        amount=parsed["amount"],
                        currency=parsed["currency"],
                        existing_id=existing.id or 0,
                        existing_merchant=existing.merchant,
                        existing_date=existing.date.isoformat(),
                        existing_amount=float(existing.amount),
                        existing_source=existing.source.value,
                    )
                )
                continue

        tx = Transaction(
            amount=parsed["amount"],
            currency=Currency(parsed["currency"]),
            merchant=parsed["merchant"],
            city=parsed["city"],
            date=parsed["date"],
            transaction_type=parsed["transaction_type"],
            source=req.source,
            bank=req.bank,
            reference=ref_hash,
        )
        tx.category_id = auto_categorize(tx.merchant, session)

        session.add(tx)
        imported += 1

    if imported > 0:
        session.commit()

    return PasteImportResult(
        imported=imported, duplicates=duplicates, errors=errors, skipped=skipped
    )