Classroom_Desktop/scripts/classroom-presentation-import

#!/usr/bin/env python3

"""Watch the teacher's downloads, and keep the library tidy.

A teacher downloads a session in ordinary Chrome and then looks for it in
Presentations. Nothing in between is their job: no file manager, no
import button, no "where did you save it". This is the in between.

    classroom-presentation-import            run as a service, forever
    classroom-presentation-import --once     one pass, for a technician
    classroom-presentation-import --status   what the library holds

WHAT IT WILL NOT DO.

    It never touches the teacher's download. The file Chrome wrote stays
    where Chrome wrote it, with the name Chrome gave it, for as long as
    the teacher leaves it there. Everything the library does is done to
    its own copy.

    It never imports a Wonder Ink worksheet. Wonder Ink downloads into a
    directory of its own inside Downloads and those are worksheets, not
    sessions; the cleanup will not remove one either.

    It never imports a file that is still arriving. Chrome writes
    `Session 7.pptx.crdownload` and renames it when the transfer is
    done, so a finished name with that sibling beside it is a download in
    progress, not a presentation.

    It never overwrites a presentation with a later one of the same
    name. Two downloads called "Bible Study.pdf" are two presentations.
"""

import argparse
import os
import shutil
import sys
import time
import uuid

sys.path.insert(0, "/usr/local/lib/ekklesia-classroom")
sys.path.insert(
    0,
    os.path.join(os.path.dirname(os.path.abspath(__file__)), "..", "lib"),
)

import classroom_presentations as library  # noqa: E402
from classroom_config import feature, read_device_config  # noqa: E402

# How often the downloads directory is looked at.
#
# Polling rather than inotify, deliberately. A teacher waits a few
# seconds either way, this cannot leak a watch descriptor or miss an
# event across a restart, and it is the kind of code somebody can still
# read in two years.
SCAN_SECONDS = 4

# How often expired presentations are cleared out.
CLEANUP_SECONDS = 3600


def say(message):
    print(f"classroom-presentation-import: {message}", flush=True)


def new_directory(root):
    root.mkdir(parents=True, exist_ok=True)
    directory = root / uuid.uuid4().hex

    directory.mkdir()

    return directory


def import_one(source, root=None):
    """Take one finished download into the library.

    Ordered so that an interruption is always recoverable. The metadata
    is written first, saying "importing"; the sweep at startup throws
    away anything still saying that and lets it be imported again. A
    presentation only becomes visible to a teacher once every file it
    needs is on disk.
    """
    root = root if root is not None else library.library_root()
    mark = library.fingerprint(source)

    if mark is None:
        return None

    directory = new_directory(root)
    managed = directory / source.name

    data = {
        "id": directory.name,
        "state": "importing",
        "title": library.readable_title(source.name),
        "original_name": source.name,
        "source_path": str(source),
        "managed_copy": source.name,
        "format": library.SUPPORTED.get(source.suffix.lower(), ""),
        "imported_at": library.stamp(),
        "last_presented_at": None,
        "times_presented": 0,
        "thumbnail_page": 1,
        "pages": 0,
        "error": None,
    }

    presentation = library.Presentation(directory, data)
    presentation.save()

    # Recorded before the work, so that a file which crashes the
    # conversion every time cannot be retried in a loop forever. The
    # startup sweep is what un-records an import interrupted part way.
    library.remember(mark, directory.name, root)

    say(f"importing {source.name}")

    try:
        # THE TEACHER'S OWN DOWNLOAD IS COPIED, NEVER MOVED.
        shutil.copy2(source, managed)

        if data["format"] == "pdf":
            # Already the thing everything else is converted into. A
            # session exported from Google Slides as a PDF keeps exactly
            # the appearance Google gave it, with no conversion at all.
            shutil.copy2(managed, presentation.slides)
        else:
            converted, error = library.convert_to_pdf(
                managed, presentation.slides)

            if not converted:
                raise RuntimeError(error or "the file could not be converted")

        pages, error = library.render_pages(
            presentation.slides, presentation.pages_directory)

        if not pages:
            raise RuntimeError(error or "the slides could not be rendered")

        data["pages"] = pages
        data["title"] = library.unique_title(
            library.readable_title(
                source.name, library.first_text(presentation.slides)),
            library.titles_in_use(root, exclude=presentation.id),
        )

        library.render_thumbnail(presentation.page_image(1),
                                 presentation.thumbnail)

        data["state"] = "ready"
        presentation.save()

        say(f"imported {data['title']!r} ({pages} slides)")

        return presentation
    except Exception as error:  # noqa: BLE001
        # A card that says it could not be opened, rather than a card
        # that opens onto nothing. The teacher's download is untouched
        # either way, which is what the message says.
        data["state"] = "failed"
        data["error"] = str(error)[:300]
        presentation.save()

        say(f"could not import {source.name}: {error}")

        return presentation


def sweep(root=None):
    """Throw away imports that were interrupted, so they can happen again.

    A reboot in the middle of a conversion leaves a directory that says
    "importing" and a ledger entry claiming the download is dealt with.
    Both go, and the next scan imports it properly.
    """
    root = root if root is not None else library.library_root()

    if not root.is_dir():
        return 0

    ledger = library.ledger(root)
    stale = 0

    for presentation in library.library(root):
        if presentation.state != "importing":
            continue

        say(f"clearing an import that did not finish: {presentation.title!r}")

        for mark, value in list(ledger.items()):
            if value == presentation.id:
                ledger.pop(mark, None)

        shutil.rmtree(presentation.directory, ignore_errors=True)
        stale += 1

    if stale:
        library.write_json(library.ledger_path(root), ledger)

    return stale


def scan(root=None, downloads=None):
    """One look at the downloads directory."""
    root = root if root is not None else library.library_root()
    known = library.ledger(root)
    imported = 0

    for candidate in library.candidates(downloads):
        mark = library.fingerprint(candidate)

        if mark is None or mark in known:
            continue

        if import_one(candidate, root) is not None:
            imported += 1
            known = library.ledger(root)

    return imported


def cleanup(root=None, moment=None):
    """Remove presentations whose time is up.

    Only ever the library's own directory, and never the presentation on
    the screen. The teacher's download is not part of this and is not
    looked at.
    """
    root = root if root is not None else library.library_root()
    lock = library.presenting_lock()
    showing = ""

    try:
        showing = lock.read_text().strip()
    except OSError:
        showing = ""

    removed = 0

    for presentation in library.library(root):
        if not presentation.expired(moment):
            continue

        if presentation.id == showing:
            # A retention timer must never interrupt a room. It will
            # still be expired in an hour.
            say(f"{presentation.title!r} is expired but is being presented")
            continue

        if presentation.last_presented_at is None:
            why = f"never presented, imported {presentation.data['imported_at']}"
        else:
            why = f"last presented {presentation.data['last_presented_at']}"

        say(f"removing {presentation.title!r} — {why}")

        shutil.rmtree(presentation.directory, ignore_errors=True)
        removed += 1

    return removed


def status(root=None):
    presentations = library.library(root)

    if not presentations:
        print("the library is empty")
        return 0

    for presentation in presentations:
        expires = presentation.expires_at()
        print(f"{presentation.title}")
        print(f"  state      {presentation.state}"
              f"{' — ' + presentation.error if presentation.error else ''}")
        print(f"  slides     {presentation.pages}"
              f" (card shows slide {presentation.thumbnail_page})")
        print(f"  imported   {presentation.data.get('imported_at')}")
        presented = presentation.data.get("last_presented_at") or "never"
        print(f"  presented  {presented} "
              f"({presentation.times_presented} times)")
        print(f"  expires    {library.stamp(expires) if expires else 'unknown'}")

    return 0


def main():
    parser = argparse.ArgumentParser(
        description="Bring finished downloads into the Presentations library.")
    parser.add_argument("--once", action="store_true",
                        help="one pass, then stop")
    parser.add_argument("--status", action="store_true",
                        help="what the library holds; changes nothing")
    parser.add_argument("--cleanup", action="store_true",
                        help="apply the retention rules now")
    arguments = parser.parse_args()

    if arguments.status:
        return status()

    # A device that does not offer Presentations does not run an importer
    # for them. Said out loud for the technician who started it by hand.
    if not feature(read_device_config(), "PRESENTATIONS_ENABLED"):
        say("PRESENTATIONS_ENABLED is false on this device; not starting")
        return 0

    if arguments.cleanup:
        removed = cleanup()
        say(f"removed {removed} expired presentation(s)")
        return 0

    sweep()

    if arguments.once:
        imported = scan()
        cleanup()
        say(f"imported {imported} presentation(s)")
        return 0

    say(f"watching {library.downloads_root()}")

    last_cleanup = 0.0

    while True:
        try:
            scan()

            if time.monotonic() - last_cleanup > CLEANUP_SECONDS:
                cleanup()
                last_cleanup = time.monotonic()
        except Exception as error:  # noqa: BLE001
            # One bad file must not stop the watcher. A teacher whose
            # next download never appears has no way to find out why.
            say(f"scan failed: {error}")

        time.sleep(SCAN_SECONDS)


if __name__ == "__main__":
    sys.exit(main())