GallerySubscriber/backend/tests/services/test_gallery_dl_categorize.py

"""Unit tests for GalleryDLService._categorize_error.

Focus: making sure errors gallery-dl logs but recovers from (e.g., Patreon's
"Failed to extract campaign ID" that falls back to /cw/<vanity>) don't get
misclassified as real failures when the overall run was just archive skips.
"""
from unittest.mock import patch

from app.services.gallery_dl import ErrorType, GalleryDLService


def _make_service():
    """Build a service without touching the filesystem."""
    with patch.object(GalleryDLService, "_load_base_config", return_value={}):
        return GalleryDLService(rate_limit=1.0)


def test_patreon_campaign_id_error_with_skips_is_no_new_content():
    """gallery-dl logged the extractor error but recovered + skipped all → no_new_content."""
    service = _make_service()
    stderr = (
        "[patreon][error] Failed to extract campaign ID\n"
        "[patreon][info] campaign_id: 548223\n"
        "[patreon][api] HEAD https://c10.patreonusercontent.com/4/.../img.jpg\n"
    )
    stdout = (
        "# /data/downloads/ElArteDeVero/patreon/2024-01-01_1_title/01_img.jpg\n"
        "# /data/downloads/ElArteDeVero/patreon/2024-01-02_2_title/01_img.jpg\n"
    )

    error_type, _message = service._categorize_error(1, stdout, stderr)

    assert error_type == ErrorType.NO_NEW_CONTENT


def test_patreon_campaign_id_error_without_skips_still_fails():
    """Same error line but no skip activity → genuine failure, not masked."""
    service = _make_service()
    stderr = "[patreon][error] Failed to extract campaign ID\n"
    stdout = ""

    error_type, _message = service._categorize_error(1, stdout, stderr)

    assert error_type != ErrorType.NO_NEW_CONTENT


def test_patreon_campaign_id_error_alongside_real_error_still_fails():
    """Campaign-ID error + a genuine auth error → auth error wins, not masked."""
    service = _make_service()
    stderr = (
        "[patreon][error] Failed to extract campaign ID\n"
        '[patreon][error] "GET /api/posts HTTP/1.1" 401 None\n'
    )
    stdout = "# /data/downloads/Foo/patreon/post1/img.jpg\n"

    error_type, _message = service._categorize_error(1, stdout, stderr)

    assert error_type == ErrorType.AUTH_ERROR


def test_patreon_per_item_download_404_with_skips_is_no_new_content():
    """Per-item 'Failed to download' + urllib3 404 HEAD + skips → no_new_content.

    Real-world trigger: a Patreon post's media URL (e.g., /media-u/v3/<id>)
    expired or was deleted. gallery-dl logs [download][error] and moves on;
    other items skip cleanly. We shouldn't classify the whole source NOT_FOUND
    just because one attachment 404'd.
    """
    service = _make_service()
    stderr = (
        "[download][error] Failed to download 02_46004845.part\n"
        '[urllib3.connectionpool][debug] "HEAD /media-u/v3/46004845 HTTP/1.1" 404 0\n'
        "[downloader.http][warning] '404 OK' for 'https://www.patreon.com/media-u/v3/46004845'\n"
        "[download][error] Failed to download 03_46004845.part\n"
        "[patreon][debug] skipping https://c10.patreonusercontent.com/4/patreon-media/p/post/30953341/.../1.png (abc image_large)\n"
    )
    stdout = ""

    error_type, _message = service._categorize_error(1, stdout, stderr)

    assert error_type == ErrorType.NO_NEW_CONTENT


def test_patreon_per_item_download_failure_without_skips_still_fails():
    """Same 'Failed to download' error but no skip activity → real failure."""
    service = _make_service()
    stderr = (
        "[download][error] Failed to download 02_46004845.part\n"
        '[urllib3.connectionpool][debug] "HEAD /media-u/v3/46004845 HTTP/1.1" 404 0\n'
    )
    stdout = ""

    error_type, _message = service._categorize_error(1, stdout, stderr)

    assert error_type != ErrorType.NO_NEW_CONTENT


def test_patreon_tier_gated_warnings_classify_as_tier_limited():
    """Many 'Not allowed to view post N' warnings + exit 4 + no downloads →
    TIER_LIMITED. Reflects a Patreon tier downgrade where older posts are now
    paywalled but we don't want to call this a failure."""
    service = _make_service()
    stderr = "\n".join(
        f"[patreon][warning] Not allowed to view post {100000 + i}"
        for i in range(15)
    )
    stdout = ""

    error_type, message = service._categorize_error(4, stdout, stderr)

    assert error_type == ErrorType.TIER_LIMITED
    assert "15" in message


def test_tier_limited_with_exit_code_1_also_classifies():
    """Mixed run: exit 1 with tier-gated warnings and no real errors."""
    service = _make_service()
    stderr = "[patreon][warning] Not allowed to view post 999\n"
    stdout = ""

    error_type, _message = service._categorize_error(1, stdout, stderr)

    assert error_type == ErrorType.TIER_LIMITED


def test_tier_limited_not_applied_when_real_error_present():
    """Tier warnings + a real auth error → auth error wins (TIER_LIMITED is
    only for 'everything else was fine' runs)."""
    service = _make_service()
    stderr = (
        "[patreon][warning] Not allowed to view post 999\n"
        '[patreon][error] "GET /api/posts HTTP/1.1" 401 None\n'
    )
    stdout = ""

    error_type, _message = service._categorize_error(1, stdout, stderr)

    assert error_type == ErrorType.AUTH_ERROR


def test_tier_limited_does_not_fire_on_exit_0():
    """Successful run with some paywalled posts as warnings isn't an error at
    all — don't reach the TIER_LIMITED branch (exit 0 → success path earlier)."""
    service = _make_service()
    stderr = "[patreon][warning] Not allowed to view post 999\n"
    stdout = "/data/downloads/Artist/patreon/post1/img.jpg\n"

    error_type, _message = service._categorize_error(0, stdout, stderr)

    # Exit 0 + stdout activity should not hit the TIER_LIMITED branch
    assert error_type != ErrorType.TIER_LIMITED


def test_skip_activity_takes_precedence_over_tier_limited():
    """If there's also skip activity, NO_NEW_CONTENT wins — precedence matters
    because the tier_limited branch is the last informational fallback."""
    service = _make_service()
    stderr = "[patreon][warning] Not allowed to view post 999\n"
    stdout = "# /data/downloads/Artist/patreon/post1/img.jpg\n"

    error_type, _message = service._categorize_error(1, stdout, stderr)

    assert error_type == ErrorType.NO_NEW_CONTENT


def test_tier_limited_with_ytdl_403s_not_access_denied():
    """Real-world Patreon scenario: account lost tier access. Posts show up as
    '[patreon][warning] Not allowed to view post N' (no downloads attempted)
    AND yt-dlp tries to fetch video HLS manifests that are also tier-gated,
    producing '[downloader.ytdl][error] HTTP Error 403: Forbidden' per item.

    Before the fix, the 'Forbidden' text in per-item ytdl errors latched onto
    ACCESS_DENIED_PATTERNS and misclassified the whole source as ACCESS_DENIED.
    Correct behavior: TIER_LIMITED (the warnings are the dominant signal; the
    per-item 403s are just tier gating manifesting at the HLS layer)."""
    service = _make_service()
    tier_warnings = "\n".join(
        f"[patreon][warning] Not allowed to view post {100000 + i}"
        for i in range(20)
    )
    ytdl_errors = "\n".join(
        "[downloader.ytdl][error] ExtractorError: Failed to download m3u8 "
        "information: HTTP Error 403: Forbidden "
        f"(caused by <HTTPError 403: Forbidden>) ({i}/4)"
        for i in range(1, 5)
    ) + "\n[download][error] Failed to download 02_video.mp4\n"
    stderr = tier_warnings + "\n" + ytdl_errors
    stdout = ""

    error_type, message = service._categorize_error(1, stdout, stderr)

    assert error_type == ErrorType.TIER_LIMITED, f"got {error_type}: {message}"
    assert "20" in message


def test_ytdl_missing_with_skips_classifies_as_no_new_content():
    """Real-world scenario from a Patreon source: container is missing yt-dlp
    so every video logs '[downloader.ytdl][error] Cannot import yt-dlp' plus
    one [download][error] per video. With overwhelming skip activity, this
    should classify as NO_NEW_CONTENT (the setup gap is per-item — it
    shouldn't mask the dominant signal that the archive is up-to-date).

    Regression: previously the yt-dlp import error didn't match any per-item
    pattern, so has_actual_error stayed True and the run was misclassified as
    UNKNOWN_ERROR even though 1300+ files were skipped."""
    service = _make_service()
    stderr = (
        "[downloader.ytdl][error] Cannot import yt-dlp or youtube-dl\n"
        "[download][error] Failed to download 02_video.mp4\n"
        "[download][error] Failed to download 02_video.mp4\n"
    )
    stdout = "# /data/downloads/Artist/patreon/post/01_img.jpg\n" * 100

    error_type, _message = service._categorize_error(4, stdout, stderr)

    assert error_type == ErrorType.NO_NEW_CONTENT