FabledCurator/tests/test_sidecar_util.py

from backend.app.utils.sidecar import SidecarData, find_sidecar, parse_sidecar


def test_find_sidecar_stem_json(tmp_path):
    media = tmp_path / "photo.jpg"
    media.write_bytes(b"x")
    sc = tmp_path / "photo.json"
    sc.write_text("{}")
    assert find_sidecar(media) == sc


def test_find_sidecar_full_name_json(tmp_path):
    media = tmp_path / "photo.jpg"
    media.write_bytes(b"x")
    sc = tmp_path / "photo.jpg.json"
    sc.write_text("{}")
    assert find_sidecar(media) == sc


def test_find_sidecar_none(tmp_path):
    media = tmp_path / "photo.jpg"
    media.write_bytes(b"x")
    assert find_sidecar(media) is None


def test_find_sidecar_gallerydl_numbered_prefix(tmp_path):
    """gallery-dl prefixes media filenames with NN_ for in-post ordering
    (e.g. `01_HOLLOW-ICHIGO.png`) but writes the post-level sidecar under
    the attachment stem WITHOUT the prefix (`HOLLOW-ICHIGO.json`).
    Confirmed against real Patreon downloads 2026-05-26 — operator's deep
    scan produced 24 refresh calls but 0 Posts because the unprefixed
    sidecar was invisible to find_sidecar."""
    media = tmp_path / "01_HOLLOW-ICHIGO.png"
    media.write_bytes(b"x")
    sc = tmp_path / "HOLLOW-ICHIGO.json"
    sc.write_text("{}")
    assert find_sidecar(media) == sc


def test_find_sidecar_multidigit_prefix(tmp_path):
    """Numbering prefix can be wider than 2 digits (`001_...`); the strip
    handles any \\d+_ form."""
    media = tmp_path / "001_mirko-sketch.png"
    media.write_bytes(b"x")
    sc = tmp_path / "mirko-sketch.json"
    sc.write_text("{}")
    assert find_sidecar(media) == sc


def test_find_sidecar_prefers_attachment_level_over_post_level(tmp_path):
    """If BOTH a per-attachment sidecar and a post-level sidecar exist,
    the attachment-level one wins (it's more specific)."""
    media = tmp_path / "01_image.png"
    media.write_bytes(b"x")
    per_attachment = tmp_path / "01_image.json"
    per_attachment.write_text('{"specific": true}')
    post_level = tmp_path / "image.json"
    post_level.write_text('{"specific": false}')
    assert find_sidecar(media) == per_attachment


def test_find_sidecar_no_underscore_not_treated_as_prefix(tmp_path):
    """`01.png` (just digits, no underscore-separated stem) shouldn't
    match. The regex requires NN_<something>."""
    media = tmp_path / "01.png"
    media.write_bytes(b"x")
    (tmp_path / ".json").write_text("{}")  # would be matched only if buggy
    assert find_sidecar(media) is None


def test_parse_empty_dict_all_none():
    sd = parse_sidecar({})
    assert isinstance(sd, SidecarData)
    assert (sd.platform, sd.external_post_id, sd.post_url, sd.post_title,
            sd.description, sd.attachment_count, sd.post_date) == (
        None, None, None, None, None, None, None)
    assert sd.raw == {}


def test_parse_core_fields_and_id_priority():
    """`post_id` MUST win over `id` (SubscribeStar duplicate-post fix).
    Patreon sidecars in the wild don't expose post_id; this test uses
    `category=patreon` but synthetically sets both fields to pin the
    parser's precedence."""
    sd = parse_sidecar({
        "category": "patreon",
        "id": 12345, "post_id": 999,
        "url": "https://patreon.com/posts/12345",
        "title": "  Hello  ",
        "content": "<p>body</p>",
        "page_count": 4,
        "published_at": "2023-08-01T04:20:02Z",
    })
    assert sd.platform == "patreon"
    assert sd.external_post_id == "999"            # 'post_id' wins over 'id'
    assert sd.post_url == "https://patreon.com/posts/12345"
    assert sd.post_title == "Hello"
    assert sd.description == "<p>body</p>"
    assert sd.attachment_count == 4
    assert sd.post_date.year == 2023 and sd.post_date.tzinfo is not None


def test_parse_id_used_when_no_post_id():
    """Without post_id (Patreon/Pixiv/Discord real shape), `id` wins."""
    sd = parse_sidecar({"id": 12345, "url": "https://example.test/p/1"})
    assert sd.external_post_id == "12345"


def test_parse_description_precedence_and_images_count():
    sd = parse_sidecar({"description": "d", "caption": "c",
                         "images": [1, 2, 3]})
    assert sd.description == "d"          # content>description>caption>message
    assert sd.attachment_count == 3      # len(images) fallback


def test_parse_message_used_as_description_fallback():
    """Discord posts have `message` not `content`; FC must surface it."""
    sd = parse_sidecar({"category": "discord", "message": "hello channel"})
    assert sd.description == "hello channel"


def test_parse_source_url_present_and_absent():
    """The per-media sidecar carries a `source_url` (#830 Phase 2); a post-only
    sidecar (no media file) omits it → None."""
    sd = parse_sidecar({"category": "patreon", "id": "1",
                        "source_url": "https://cdn.test/abc.png"})
    assert sd.source_url == "https://cdn.test/abc.png"
    assert parse_sidecar({"category": "patreon", "id": "1"}).source_url is None


def test_parse_date_epoch_and_unparseable_and_naive():
    assert parse_sidecar({"timestamp": 1690857602}).post_date.tzinfo is not None
    assert parse_sidecar({"date": "not-a-date"}).post_date is None
    naive = parse_sidecar({"date": "2023-08-01T00:00:00"}).post_date
    assert naive is not None and naive.utcoffset().total_seconds() == 0


def test_parse_title_derived_from_content_when_empty():
    """SubscribeStar gallery-dl writes `title: ""` and puts the leading
    sentence in `content` HTML. When `title` is empty, synthesize the
    post title from the content body's first non-empty text line."""
    sd = parse_sidecar({
        "title": "",
        "content": "\n<div>Lets say hello to you guys with my Belle <br><br><br>\n</div>\n",
    })
    assert sd.post_title == "Lets say hello to you guys with my Belle"
    assert sd.description == (
        "<div>Lets say hello to you guys with my Belle <br><br><br>\n</div>"
    )


def test_parse_title_derived_truncates_long_content():
    long = "x" * 200
    sd = parse_sidecar({"title": "", "content": long})
    assert sd.post_title is not None
    assert len(sd.post_title) <= 120
    assert sd.post_title.endswith("…")


def test_parse_title_explicit_wins_over_content_fallback():
    """If `title` is non-empty, the fallback never runs."""
    sd = parse_sidecar({"title": "Real Title", "content": "<p>body line</p>"})
    assert sd.post_title == "Real Title"


def test_parse_title_no_fallback_when_no_content():
    sd = parse_sidecar({"title": ""})
    assert sd.post_title is None


def test_parse_subscribestar_post_url_derived_and_post_id_wins():
    """SubscribeStar gallery-dl puts the per-attachment id in `id` and
    the actual post id in `post_id`. The bare `url` is the file URL —
    must be ignored and a derived permalink used instead."""
    sd = parse_sidecar({
        "category": "subscribestar",
        "id": 711509, "post_id": 360360,
        "url": "/post_uploads?payload=opaque",
        "title": "",
        "content": "<div>hello</div>",
    })
    assert sd.external_post_id == "360360"
    assert sd.post_url == "https://www.subscribestar.com/posts/360360"


def test_parse_hentaifoundry_post_url_derived():
    """HF sidecars omit `url` entirely and use `index`+`user` for the
    post's natural key. Synthesize the canonical /pictures/user/<u>/<i>
    permalink."""
    sd = parse_sidecar({
        "category": "hentaifoundry",
        "index": 1182595,
        "user": "HolyMeh",
        "title": "Annigosa",
    })
    assert sd.external_post_id == "1182595"
    assert sd.post_url == "https://www.hentai-foundry.com/pictures/user/HolyMeh/1182595"


def test_parse_discord_post_url_derived_and_message_id_wins():
    """Discord posts use `message_id` for the post key and the
    server/channel/message triple for the permalink."""
    sd = parse_sidecar({
        "category": "discord",
        "message_id": "1195924119762505818",
        "channel_id": "968315530597498880",
        "server_id": "771088957849075793",
        "message": "channel body text",
        "url": "https://cdn.discordapp.com/attachments/file.png",
    })
    assert sd.external_post_id == "1195924119762505818"
    assert sd.post_url == (
        "https://discord.com/channels/771088957849075793/"
        "968315530597498880/1195924119762505818"
    )
    assert sd.description == "channel body text"


def test_parse_patreon_post_url_kept_as_is():
    """Patreon's bare `url` IS a real permalink — must not be replaced."""
    sd = parse_sidecar({
        "category": "patreon",
        "id": 47074733,
        "url": "https://www.patreon.com/posts/barbara-genshin-47074733",
    })
    assert sd.post_url == "https://www.patreon.com/posts/barbara-genshin-47074733"


def test_parse_derived_url_returns_none_when_fields_missing():
    """If the per-platform fields needed to derive the URL are missing,
    return None rather than fall back to the file `url`."""
    sd = parse_sidecar({
        "category": "subscribestar",
        "url": "/post_uploads?payload=opaque",
        # no post_id
    })
    assert sd.post_url is None


def test_parse_ignores_non_str_junk():
    sd = parse_sidecar({"category": 5, "title": 7, "page_count": "x",
                        "id": True})
    assert sd.platform is None and sd.post_title is None
    assert sd.attachment_count is None
    assert sd.external_post_id is None   # bool is not a valid id
    assert sd.raw == {"category": 5, "title": 7, "page_count": "x",
                      "id": True}