"""LLM-fallback CSV parser.

When the deterministic Trading 212 parser (``csv_import.parse_t212_csv``)
raises ``CSVImportError`` on an unrecognised format, this service kicks
in:

1. Detect the CSV dialect (delimiter, preamble offset).
2. Compute a fingerprint of the normalised header row.
3. Look up ``CsvFormatTemplate`` by fingerprint. On hit, replay the
   cached column-mapping deterministically. On miss, ask the LLM for a
   mapping, validate it, persist a new template, and apply it.

The LLM sees only headers + the first 3-5 sample rows. It returns a
column-mapping JSON, never transcribed numbers. The system never
auto-promotes a learned format to a hand-written parser — the operator
does that by inspecting collected ``sample_row`` values.
"""
from __future__ import annotations

import hashlib

from app.services.csv_import import CSVImportError


class LLMParseError(CSVImportError):
    """Raised when the LLM call fails or returns an unusable mapping.

    Inherits from ``CSVImportError`` so route-level error handling can
    treat both deterministic and LLM-path failures uniformly when
    desired."""


def _fingerprint(headers: list[str]) -> str:
    """Stable hash of the header row.

    Lowercases each header, strips surrounding whitespace, joins with
    ``|`` (a character extremely unlikely to appear inside a real
    header), and returns the sha256 hex digest. Whitespace/case drift
    in the same broker's export does not change the fingerprint;
    adding or removing a column does."""
    normalised = "|".join(h.strip().lower() for h in headers)
    return hashlib.sha256(normalised.encode("utf-8")).hexdigest()