"""Load real production documents as test fixtures.

Real files rather than generated ones: a fixture built with the same
understanding of the format that produced the parser cannot catch a wrong
mental model -- it is wrong in the same way, so the test passes and production
breaks. Every table shape this parser handles was found by reading these
files, not by reasoning about what DOCX can contain.

The documents live outside the repository so no customer-facing file enters
git history. Point `TEST_DOCUMENTS_DIR` at the directory holding them; tests
that need one skip when it is absent.

These skips cover a missing *external input*, never a failing assertion -- but
a machine without the directory does run a smaller suite than CI should.

Filenames live in `documents.json` rather than in this module: they are mostly
Persian, and Arabic letterforms in Python source are flagged as ambiguous with
Latin lookalikes (RUF001). They are data, so they belong in a data file.
"""

import json
import os
from pathlib import Path

import pytest

DOCUMENTS_DIR = Path(
    os.environ.get("TEST_DOCUMENTS_DIR", "~/Documents/asia_data_sample")
).expanduser()

_MANIFEST = json.loads((Path(__file__).parent / "documents.json").read_text("utf-8"))

# Each entry is the only sample exercising some structure; `why` in the
# manifest records what would go untested without it.
PROSE_DOCX = _MANIFEST["prose_docx"]["filename"]
LIST_DOCX = _MANIFEST["list_docx"]["filename"]
TABLE_DOCX = _MANIFEST["table_docx"]["filename"]
MIXED_DOCX = _MANIFEST["mixed_docx"]["filename"]
LAYOUT_DOCX = _MANIFEST["layout_docx"]["filename"]
QA_XLSX = _MANIFEST["qa_xlsx"]["filename"]
BRANCHES_XLSX = _MANIFEST["branches_xlsx"]["filename"]


def load_document(filename: str) -> bytes:
    """Return a real document's bytes, skipping the test when it is unavailable."""
    path = DOCUMENTS_DIR / filename
    if not path.is_file():
        pytest.skip(
            f"{filename} not found in {DOCUMENTS_DIR}; "
            f"set TEST_DOCUMENTS_DIR to the directory holding the sample documents"
        )
    return path.read_bytes()