Add support for expiring files

SUPPLEMENTALLY:
- Add an `expiration` field to the `file` table of the database
- Produce a migration for the above change
- Overhaul the cleanup script, and integrate into fhost.py
  (now run using FLASK_APP=fhost flask prune)
- Replace the old cleanup script with a deprecation notice
- Add information about how to expire files to the index
- Update the README with information about the new script

Squashed commits:

Add a note explaining that expired files aren't immediately removed

Show correct times on the index page graph

Improve the migration script, removing the need for --legacy

Use automap in place of an explicit file map in migration

Remove vestigial `touch()`

Don't crash when upgrading a fresh database

Remove vestigial warning about legacy files

More efficiently filter to unexpired files when migrating

https://git.0x0.st/mia/0x0/pulls/72#issuecomment-224

Coalesce updates to the database during migration

https://git.0x0.st/mia/0x0/pulls/72#issuecomment-226

Remove vestigial database model

https://git.0x0.st/mia/0x0/pulls/72#issuecomment-261

prune:  Stream expired files from the database

(as opposed to collecting them all first)

config.example.py:  Add min & max expiration + description

1 files changed, 81 insertions, 0 deletions

diff --git a/migrations/versions/939a08e1d6e5_.py b/migrations/versions/939a08e1d6e5_.py
new file mode 100644
index 0000000..f86dcb3
--- /dev/null
+++ b/migrations/versions/939a08e1d6e5_.py
@@ -0,0 +1,81 @@
+"""add file expirations
+
+Revision ID: 939a08e1d6e5
+Revises: 7e246705da6a
+Create Date: 2022-11-22 12:16:32.517184
+
+"""
+
+# revision identifiers, used by Alembic.
+revision = '939a08e1d6e5'
+down_revision = '7e246705da6a'
+
+from alembic import op
+from flask import current_app
+from flask_sqlalchemy import SQLAlchemy
+from pathlib import Path
+import sqlalchemy as sa
+from sqlalchemy.ext.automap import automap_base
+from sqlalchemy.orm import Session
+
+import os
+import time
+
+""" For a file of a given size, determine the largest allowed lifespan of that file
+
+Based on the current app's configuration:  Specifically, the MAX_CONTENT_LENGTH, as well
+as FHOST_{MIN,MAX}_EXPIRATION.
+
+This lifespan may be shortened by a user's request, but no files should be allowed to
+expire at a point after this number.
+
+Value returned is a duration in milliseconds.
+"""
+def get_max_lifespan(filesize: int) -> int:
+    min_exp = current_app.config.get("FHOST_MIN_EXPIRATION", 30 * 24 * 60 * 60 * 1000)
+    max_exp = current_app.config.get("FHOST_MAX_EXPIRATION", 365 * 24 * 60 * 60 * 1000)
+    max_size = current_app.config.get("MAX_CONTENT_LENGTH", 256 * 1024 * 1024)
+    return min_exp + int((-max_exp + min_exp) * (filesize / max_size - 1) ** 3)
+
+Base = automap_base()
+
+def upgrade():
+    op.add_column('file', sa.Column('expiration', sa.BigInteger()))
+
+    bind = op.get_bind()
+    Base.prepare(autoload_with=bind)
+    File = Base.classes.file
+    session = Session(bind=bind)
+
+    storage = Path(current_app.config["FHOST_STORAGE_PATH"])
+    current_time = time.time() * 1000;
+
+    # List of file hashes which have not expired yet
+    # This could get really big for some servers
+    try:
+        unexpired_files = os.listdir(storage)
+    except FileNotFoundError:
+        return # There are no currently unexpired files
+
+    # Calculate an expiration date for all existing files
+    files = session.scalars(
+            sa.select(File)
+            .where(
+                sa.not_(File.removed),
+                File.sha256.in_(unexpired_files)
+            )
+        )
+    updates = [] # We coalesce updates to the database here
+    for file in files:
+        file_path = storage / file.sha256
+        stat = os.stat(file_path)
+        max_age = get_max_lifespan(stat.st_size) # How long the file is allowed to live, in ms
+        file_birth = stat.st_mtime * 1000 # When the file was created, in ms
+        updates.append({'id': file.id, 'expiration': int(file_birth + max_age)})
+
+    # Apply coalesced updates
+    session.bulk_update_mappings(File, updates)
+    session.commit()
+
+def downgrade():
+    op.drop_column('file', 'expiration')