test_core.py

"""
Tests for Aadhaar Masking API.
Run: pytest tests/ -v
"""

import io
import re

import numpy as np
import pytest

# ── Verhoeff tests ─────────────────────────────────────────────────────────────

from app.utils.verhoeff import validate


def test_verhoeff_valid_known():
    # Known valid Aadhaar-format numbers (public test vectors)
    assert validate("234123412346") is True  # example that passes Verhoeff


def test_verhoeff_invalid():
    assert validate("123456789012") is False


def test_verhoeff_length_guard():
    # Verhoeff works on any digit string; 12-digit gate is at detection layer
    assert isinstance(validate("0"), bool)


# ── Regex pattern tests ────────────────────────────────────────────────────────

import re

AADHAAR_RE = re.compile(
    r"(?<!\d)([2-9]\d{3})[\s\-]?(\d{4})[\s\-]?(\d{4})(?!\d)"
)


def test_aadhaar_regex_matches_spaced():
    text = "Your Aadhaar: 2341 2341 2346"
    m = AADHAAR_RE.search(text)
    assert m is not None


def test_aadhaar_regex_no_match_phone():
    # 10-digit phone starting with 9 — should NOT match 12-digit pattern
    text = "Call us at 9876543210"
    raw = text.replace(" ", "")
    # Phone is 10 digits; our regex needs 12, so no full match expected
    matches = [
        m.group(0).replace(" ", "").replace("-", "")
        for m in AADHAAR_RE.finditer(text)
        if len(m.group(0).replace(" ", "").replace("-", "")) == 12
    ]
    assert matches == []


VID_RE = re.compile(
    r"(?<!\d)(9\d{3})[\s\-]?(\d{4})[\s\-]?(\d{4})[\s\-]?(\d{4})(?!\d)"
)


def test_vid_regex_matches():
    text = "VID: 9876 5432 1098 7654"
    assert VID_RE.search(text) is not None


def test_vid_regex_no_match_short():
    text = "9876 5432 1098"  # only 12 digits
    assert VID_RE.search(text) is None


# ── Masking text tests ─────────────────────────────────────────────────────────

from app.models.schemas import MaskType
from app.services.masking_service import _mask_aadhaar_text, _mask_vid_text


def test_mask_aadhaar_partial():
    assert _mask_aadhaar_text("2341 2341 2346", MaskType.partial) == "XXXX XXXX 2346"


def test_mask_aadhaar_full():
    assert _mask_aadhaar_text("2341 2341 2346", MaskType.full) == "XXXX XXXX XXXX"


def test_mask_vid_partial():
    result = _mask_vid_text("9876 5432 1098 7654", MaskType.partial)
    assert result == "XXXX XXXX XXXX 7654"


def test_mask_vid_full():
    result = _mask_vid_text("9876 5432 1098 7654", MaskType.full)
    assert result == "XXXX XXXX XXXX XXXX"


# ── File service tests ─────────────────────────────────────────────────────────

from app.services.file_service import decode_image
import cv2


def test_decode_png_bytes():
    img = np.zeros((100, 100, 3), dtype=np.uint8)
    _, buf = cv2.imencode(".png", img)
    decoded = decode_image(bytes(buf), "png")
    assert decoded.shape == (100, 100, 3)


def test_decode_bad_bytes():
    with pytest.raises(ValueError):
        decode_image(b"not an image", "jpg")


# ── Cleanup / storage tests ────────────────────────────────────────────────────

from app.utils.cleanup import save_file, get_file_path, delete_file


def test_save_and_retrieve():
    fid = save_file(b"hello", "txt")
    path = get_file_path(fid)
    assert path is not None
    assert path.read_bytes() == b"hello"


def test_delete_file():
    fid = save_file(b"bye", "txt")
    delete_file(fid)
    assert get_file_path(fid) is None