siftlode/backend/app/downloads/storage.py

"""On-disk layout for downloaded media — Plex-friendly tree + .nfo/poster sidecars.

The physical filename is system-decided and bound to the source id (never renamed; the user's
custom name is display-only, applied at local-download time). Layout is admin-configurable:

  plex:  {Channel}/Season {Year}/{Channel} - {YYYY-MM-DD} - {title} [{id}].{ext}
  flat:  {title} [{id}].{ext}

Plus a Kodi/Plex-readable `<basename>.nfo` (episodedetails) and `<basename>.jpg` thumbnail, so
a Plex library using a metadata agent picks up rich info. Channel = "show", video = episode,
date-based — the community-standard mapping for YouTube-in-Plex.
"""
import re
import shutil
import unicodedata
from dataclasses import dataclass
from datetime import date
from pathlib import Path
from xml.sax.saxutils import escape

# Reserve room for the " [id].ext" suffix + parent dirs within the 255-byte component limit.
_MAX_TITLE = 120
# Filesystem-illegal on Windows/Plex + control chars.
_ILLEGAL = re.compile(r'[<>:"/\\|?*\x00-\x1f]')
# Unicode categories we drop entirely: emoji/pictographs (So), modifier symbols/skin-tones
# (Sk), and every control/format/private/surrogate/unassigned char (C*). Letters (incl.
# accented á/ö/ü/ß), digits, and ordinary punctuation are KEPT — Siftlode is trilingual, so
# ASCII-folding would mangle Hungarian/German titles.
_DROP_CATEGORIES = {"So", "Sk", "Cc", "Cf", "Cs", "Co", "Cn"}


@dataclass
class MediaMeta:
    video_id: str
    title: str
    uploader: str
    upload_date: date | None
    duration_s: int | None = None
    description: str | None = None
    thumbnail_url: str | None = None


def sanitize(name: str, limit: int = _MAX_TITLE) -> str:
    """Turn an arbitrary (emoji-laden, clickbait) title into a clean, space-free path token.

    Steps: NFKC-normalize (fold fancy width/compat forms) → drop emoji/symbols/control chars →
    strip filesystem-illegal chars → collapse whitespace and runs of the same punctuation →
    join words with underscores → trim junk punctuation from the ends → length-cap. Accented
    letters and digits survive; the result never contains spaces or path separators."""
    text = unicodedata.normalize("NFKC", name or "")
    text = "".join(
        ch for ch in text if unicodedata.category(ch) not in _DROP_CATEGORIES
    )
    text = _ILLEGAL.sub("", text)
    # Collapse repeated punctuation ("!!!", "???", "-----") to a single mark.
    text = re.sub(r"([^\w\s])\1{1,}", r"\1", text)
    # Whitespace → single underscore (no spaces in generated names).
    text = re.sub(r"\s+", "_", text.strip())
    # Tidy separator pile-ups and trim junk from the ends.
    text = re.sub(r"_{2,}", "_", text).strip("_.-·—–|,;:!?ّ ")
    if len(text) > limit:
        text = text[:limit].rstrip("_.-")
    return text or "untitled"


def rel_path(meta: MediaMeta, ext: str, layout: str = "plex") -> str:
    """Path of the media file relative to DOWNLOAD_ROOT (forward slashes)."""
    title = sanitize(meta.title)
    vid = meta.video_id
    if layout == "flat":
        return f"{title}_[{vid}].{ext}"
    channel = sanitize(meta.uploader or "Unknown_Channel", 80)
    year = meta.upload_date.year if meta.upload_date else 0
    d = meta.upload_date.isoformat() if meta.upload_date else "0000-00-00"
    epname = f"{channel}_-_{d}_-_{title}_[{vid}].{ext}"
    return f"{channel}/Season_{year}/{epname}"


def abs_path(download_root: str, rel: str) -> Path:
    return Path(download_root) / rel


def place_file(staging_file: Path, download_root: str, rel: str) -> None:
    """Move a completed staging file into its final location under DOWNLOAD_ROOT."""
    dest = abs_path(download_root, rel)
    dest.parent.mkdir(parents=True, exist_ok=True)
    shutil.move(str(staging_file), str(dest))


def _nfo_xml(meta: MediaMeta) -> str:
    aired = meta.upload_date.isoformat() if meta.upload_date else ""
    year = meta.upload_date.year if meta.upload_date else ""
    parts = [
        '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>',
        "<episodedetails>",
        f"  <title>{escape(meta.title or '')}</title>",
        f"  <showtitle>{escape(meta.uploader or '')}</showtitle>",
        f"  <studio>{escape(meta.uploader or '')}</studio>",
        f"  <aired>{aired}</aired>",
        f"  <premiered>{aired}</premiered>",
        f"  <year>{year}</year>",
        f"  <plot>{escape(meta.description or '')}</plot>",
        f"  <uniqueid type=\"youtube\" default=\"true\">{escape(meta.video_id)}</uniqueid>",
    ]
    if meta.duration_s:
        parts.append(f"  <runtime>{round(meta.duration_s / 60)}</runtime>")
    parts.append("</episodedetails>")
    return "\n".join(parts)


def write_sidecars(
    download_root: str, rel: str, meta: MediaMeta, thumb_src: Path | None
) -> bool:
    """Write `<basename>.nfo` + `<basename>.jpg` next to the media file. Returns True if written."""
    media = abs_path(download_root, rel)
    base = media.with_suffix("")
    try:
        base.with_suffix(".nfo").write_text(_nfo_xml(meta), encoding="utf-8")
        if thumb_src and thumb_src.exists():
            shutil.copyfile(str(thumb_src), str(base.with_suffix(".jpg")))
        return True
    except OSError:
        return False


def delete_asset_files(download_root: str, rel: str) -> None:
    """Remove the media file and its sidecars; prune now-empty parent dirs (best effort)."""
    media = abs_path(download_root, rel)
    base = media.with_suffix("")
    for p in (media, base.with_suffix(".nfo"), base.with_suffix(".jpg")):
        try:
            p.unlink()
        except OSError:
            pass
    # Prune empty Season/Channel dirs up to (but not including) the root.
    root = Path(download_root).resolve()
    parent = media.parent
    while parent != root and root in parent.parents:
        try:
            parent.rmdir()  # only succeeds if empty
        except OSError:
            break
        parent = parent.parent