//! Query-log retention (PLAN §11.5): a daily pass over `querylog.db` that
//! deletes rows older than `logging.retention_days`, truncates the WAL, and
//! rewrites the file on every seventh pass.
//!
//! The pass touches `querylog.db` only. §3.6 walls `config.db` off from
//! retention churn, and the `hand_edited=0` client rows of §7.2 are pruned by
//! whatever creates them, which is the client tracker (`server/clients.zig`).
//!
//! Nothing here retries within a pass. A failed step logs at `warn` and the
//! next pass, a day later, does the same work again against the same data.

const std = @import("std");

const db = @import("db.zig");
const disk_monitor = @import("disk_monitor.zig");
const events = @import("events.zig");
const queries_repo = @import("repositories/queries_repo.zig");

const log = std.log.scoped(.retention);

/// A full `VACUUM` rewrites the whole database file. On the SD card of a
/// household box that is the most expensive write this program makes, so it
/// runs on every seventh pass rather than every night.
pub const vacuum_every_passes = 7;

/// One day. `retention_days` is the finest granularity the configuration
/// expresses, so a finer schedule would prune nothing new.
pub const pass_interval_s = 86_400;

/// A consistent copy of the counters, for `/metrics` and the health rollup.
pub const Stats = struct {
    passes: u64 = 0,
    rows_pruned: u64 = 0,
    checkpoints: u64 = 0,
    vacuums: u64 = 0,
    /// Vacuums the disk monitor refused. The pass still pruned and
    /// checkpointed, and the vacuum is due again on the next pass.
    vacuums_gated: u64 = 0,
};

/// The live counters. Atomic because the retention task writes them and the web
/// task reads them, on different threads, with no lock between the two — the
/// same shape the query logger uses for its own counters.
const Counters = struct {
    passes: std.atomic.Value(u64) = .init(0),
    rows_pruned: std.atomic.Value(u64) = .init(0),
    checkpoints: std.atomic.Value(u64) = .init(0),
    vacuums: std.atomic.Value(u64) = .init(0),
    vacuums_gated: std.atomic.Value(u64) = .init(0),
};

/// `logging.retention_days`, shared by its two consumers — this pass and
/// `server/clients.zig`'s stale-client prune. One cell rather than a copy in
/// each: the two must never prune to different cutoffs, and a settings apply
/// stores once. Owned by app-level state and outlives both readers.
///
/// `.monotonic` is enough: the value stands alone and orders nothing else, and
/// each consumer reads it once per pass.
pub const RetentionDays = struct {
    value: std.atomic.Value(u32),

    pub fn init(days: u16) RetentionDays {
        return .{ .value = .init(days) };
    }

    pub fn get(self: *const RetentionDays) u32 {
        return self.value.load(.monotonic);
    }

    pub fn setRetentionDays(self: *RetentionDays, days: u16) void {
        self.value.store(days, .monotonic);
    }

    pub fn seconds(self: *const RetentionDays) i64 {
        return @as(i64, self.get()) * std.time.s_per_day;
    }
};

pub const Retention = struct {
    days: *const RetentionDays,
    counters: Counters,
    /// Passes since the last vacuum that succeeded. Plain rather than atomic:
    /// only the retention task reads or writes it, and no consumer reports it.
    passes_since_vacuum: u32,

    pub fn init(days: *const RetentionDays) Retention {
        return .{ .days = days, .counters = .{}, .passes_since_vacuum = 0 };
    }

    /// The counters, read one at a time. A scrape that lands mid-pass can see a
    /// pass counted before the rows it pruned are; the alternative is a lock on
    /// the pass itself, which buys a consistency no consumer needs.
    pub fn snapshotStats(self: *const Retention) Stats {
        return .{
            .passes = self.counters.passes.load(.monotonic),
            .rows_pruned = self.counters.rows_pruned.load(.monotonic),
            .checkpoints = self.counters.checkpoints.load(.monotonic),
            .vacuums = self.counters.vacuums.load(.monotonic),
            .vacuums_gated = self.counters.vacuums_gated.load(.monotonic),
        };
    }

    /// One pass: prune, checkpoint, and on every seventh pass vacuum.
    ///
    /// The three steps are independent. A failed prune does not skip the
    /// checkpoint, because the WAL that the checkpoint truncates was filled by
    /// the query logger rather than by this pass.
    ///
    /// Every failure is a database error, and every database error logs at
    /// `warn` and leaves the pass counted as done: a pass that returned early
    /// on the first failure would still be a day away from its retry.
    ///
    /// `database` must be a connection no other task uses; see `run`.
    ///
    /// `monitor` gates the vacuum only. Prune and checkpoint free space, so a
    /// full disk is a reason to run them rather than a reason to skip them,
    /// while a `VACUUM` rewrites the whole file on the very filesystem the
    /// monitor watches and fails `SQLITE_FULL` there. A null monitor means no
    /// gate, which is the shape the logger's writer takes.
    pub fn runOnce(
        self: *Retention,
        io: std.Io,
        database: *db.Db,
        monitor: ?*disk_monitor.Monitor,
        store: ?*events.Store,
    ) void {
        add(&self.counters.passes, 1);
        const now = std.Io.Clock.real.now(io).toSeconds();
        const cutoff = now - self.days.seconds();

        // Diagnostics retention rides this pass rather than a schedule of its
        // own: one daily housekeeping task, and a box restarted every night
        // still prunes through `Store.init`.
        if (store) |s| s.prune(io, now);

        // One operation, not two: the delete and the coverage watermark it
        // advances commit together or not at all (`queries_repo`).
        if (queries_repo.pruneOlderThan(database, cutoff)) |pruned| {
            add(&self.counters.rows_pruned, @intCast(pruned.deleted));
            maintenance(store, io, now, "prune", null);
        } else |err| {
            log.warn("retention prune before {d} failed: {s}", .{ cutoff, @errorName(err) });
            maintenance(store, io, now, "prune", @errorName(err));
        }

        if (queries_repo.checkpointTruncate(database)) {
            add(&self.counters.checkpoints, 1);
            maintenance(store, io, now, "checkpoint", null);
        } else |err| {
            log.warn("retention checkpoint failed: {s}", .{@errorName(err)});
            maintenance(store, io, now, "checkpoint", @errorName(err));
        }

        self.passes_since_vacuum += 1;
        if (self.passes_since_vacuum < vacuum_every_passes) return;

        // The counter is not reset here, so a vacuum the monitor refused is due
        // again on the very next pass rather than seven passes later.
        if (monitor) |m| if (!m.writesAllowed()) {
            add(&self.counters.vacuums_gated, 1);
            log.warn("retention vacuum skipped: the disk monitor refuses writes", .{});
            maintenance(store, io, now, "vacuum", "the disk monitor refuses writes");
            return;
        };

        if (queries_repo.vacuum(database)) {
            add(&self.counters.vacuums, 1);
            self.passes_since_vacuum = 0;
            maintenance(store, io, now, "vacuum", null);
        } else |err| {
            log.warn("retention vacuum failed: {s}", .{@errorName(err)});
            maintenance(store, io, now, "vacuum", @errorName(err));
        }
    }

    /// One step's outcome. `reason` null is the success branch of that same
    /// step in that same pass, which is what closes its episode; a gated vacuum
    /// is a failure of the step, because the work it owes is still owed.
    fn maintenance(
        store: ?*events.Store,
        io: std.Io,
        now_s: i64,
        operation: []const u8,
        reason: ?[]const u8,
    ) void {
        const s = store orelse return;
        const text = reason orelse return s.resolve(io, now_s, .query_log_maintenance, operation);
        var buf: [events.Store.max_detail_len]u8 = undefined;
        const detail = std.fmt.bufPrint(&buf, "retention {s} failed: {s}", .{ operation, text }) catch buf[0..];
        s.report(io, now_s, .query_log_maintenance, operation, operation, .warning, detail);
    }

    fn add(counter: *std.atomic.Value(u64), delta: u64) void {
        _ = counter.fetchAdd(delta, .monotonic);
    }

    /// Daily loop, first pass immediately. The composition root starts it as a
    /// concurrent task (`app.zig`).
    ///
    /// `boot` rather than `awake`: a box that suspends overnight must still see
    /// its day elapse.
    ///
    /// `database` must be a connection dedicated to retention: no other task
    /// may use the same handle while this loop runs. `FULLMUTEX` (`db.zig:218`)
    /// serializes one SQLite call against another, but a transaction is
    /// connection state, not call state. On a handle shared with the query
    /// logger's writer, a prune that lands between that writer's BEGIN and
    /// COMMIT runs inside the writer's transaction and commits or rolls back
    /// with the batch, and a checkpoint or a `VACUUM` can land inside a
    /// transaction that is still open.
    ///
    /// Retention takes `database` per call and opens nothing itself; the
    /// composition root opens the second connection with
    /// `cli.DataDir.reopenQuerylogDb`. Isolation across the two connections is
    /// SQLite's own — WAL plus the `busy_timeout` of `db.zig`'s open options —
    /// so a pass that still loses a race sees `error.Busy` or `error.Locked`,
    /// logs at `warn`, and repeats the work on the next interval.
    pub fn run(
        self: *Retention,
        io: std.Io,
        database: *db.Db,
        monitor: ?*disk_monitor.Monitor,
        store: ?*events.Store,
    ) std.Io.Cancelable!void {
        const interval: std.Io.Clock.Duration = .{
            .raw = .fromSeconds(pass_interval_s),
            .clock = .boot,
        };
        while (true) {
            self.runOnce(io, database, monitor, store);
            try interval.sleep(io);
        }
    }
};

// ---------------------------------------------------------------------------
// tests
// ---------------------------------------------------------------------------

const events_fixture = @import("events_fixture.zig");
const querylog_schema = @import("querylog_schema.zig");

const testing = std.testing;

fn openLog() !db.Db {
    var database = try db.Db.open(":memory:", .{ .mode = .memory });
    errdefer database.close();
    try db.applyPragmas(&database, .{});
    try database.exec(querylog_schema.ddl);
    return database;
}

fn writeRows(database: *db.Db, timestamps: []const i64) !void {
    var writer = try queries_repo.BatchWriter.init(database);
    defer writer.deinit();
    var rows: [8]queries_repo.Row = undefined;
    for (timestamps, rows[0..timestamps.len]) |timestamp, *row| {
        row.* = .{
            .timestamp = timestamp,
            .domain = "example.com",
            .client_ip = "192.0.2.10",
            .qtype = 1,
            .qclass = 1,
            .rcode = 0,
            .blocked = false,
            .response_time_us = null,
            .cache_hit = null,
            .upstream = null,
            .group_id = 1,
            .group_name = "default",
            .policy_action = .allow,
            .policy_reason = .no_match,
            .matched = null,
            .source_id = null,
            .source_name = null,
            .cname_target = null,
            .safe_search_target = null,
            .route_kind = .upstream,
            .forward_zone = null,
        };
    }
    try writer.writeBatch(rows[0..timestamps.len]);
}

test "a pass prunes the rows past the retention window and keeps the rest" {
    var threaded: std.Io.Threaded = .init(testing.allocator, .{});
    defer threaded.deinit();
    const io = threaded.io();

    var database = try openLog();
    defer database.close();

    const now = std.Io.Clock.real.now(io).toSeconds();
    const day = 86_400;
    try writeRows(&database, &.{ now - 40 * day, now - 31 * day, now - 29 * day, now - 60 });

    var retention_days: RetentionDays = .init(30);
    var retention: Retention = .init(&retention_days);
    retention.runOnce(io, &database, null, null);

    try testing.expectEqual(@as(i64, 2), try queries_repo.countRows(&database));
    try testing.expectEqual(@as(u64, 1), retention.snapshotStats().passes);
    try testing.expectEqual(@as(u64, 2), retention.snapshotStats().rows_pruned);
    try testing.expectEqual(@as(u64, 1), retention.snapshotStats().checkpoints);
    try testing.expectEqual(@as(u64, 0), retention.snapshotStats().vacuums);
}

test "the cutoff follows retention_days" {
    var threaded: std.Io.Threaded = .init(testing.allocator, .{});
    defer threaded.deinit();
    const io = threaded.io();

    var database = try openLog();
    defer database.close();

    const now = std.Io.Clock.real.now(io).toSeconds();
    const day = 86_400;
    // The same row is inside the window of one configuration and outside the
    // window of the other.
    try writeRows(&database, &.{now - 3 * day});

    var keeps_days: RetentionDays = .init(7);
    var keeps: Retention = .init(&keeps_days);
    keeps.runOnce(io, &database, null, null);
    try testing.expectEqual(@as(i64, 1), try queries_repo.countRows(&database));
    try testing.expectEqual(@as(u64, 0), keeps.snapshotStats().rows_pruned);

    var prunes_days: RetentionDays = .init(1);
    var prunes: Retention = .init(&prunes_days);
    prunes.runOnce(io, &database, null, null);
    try testing.expectEqual(@as(i64, 0), try queries_repo.countRows(&database));
    try testing.expectEqual(@as(u64, 1), prunes.snapshotStats().rows_pruned);
}

test "setRetentionDays changes the cutoff the next pass prunes by" {
    var threaded: std.Io.Threaded = .init(testing.allocator, .{});
    defer threaded.deinit();
    const io = threaded.io();

    var database = try openLog();
    defer database.close();

    const now = std.Io.Clock.real.now(io).toSeconds();
    try writeRows(&database, &.{now - 3 * 86_400});

    var days: RetentionDays = .init(7);
    var pass: Retention = .init(&days);
    pass.runOnce(io, &database, null, null);
    try testing.expectEqual(@as(i64, 1), try queries_repo.countRows(&database));

    days.setRetentionDays(1);
    pass.runOnce(io, &database, null, null);
    try testing.expectEqual(@as(i64, 0), try queries_repo.countRows(&database));
    try testing.expectEqual(@as(u64, 1), pass.snapshotStats().rows_pruned);
}

test "the seventh pass vacuums and the six before it do not" {
    var threaded: std.Io.Threaded = .init(testing.allocator, .{});
    defer threaded.deinit();
    const io = threaded.io();

    var database = try openLog();
    defer database.close();

    var retention_days: RetentionDays = .init(30);
    var retention: Retention = .init(&retention_days);
    for (0..6) |_| {
        retention.runOnce(io, &database, null, null);
        try testing.expectEqual(@as(u64, 0), retention.snapshotStats().vacuums);
    }
    retention.runOnce(io, &database, null, null);

    try testing.expectEqual(@as(u64, 7), retention.snapshotStats().passes);
    try testing.expectEqual(@as(u64, 1), retention.snapshotStats().vacuums);
    try testing.expectEqual(@as(u64, 7), retention.snapshotStats().checkpoints);

    for (0..7) |_| retention.runOnce(io, &database, null, null);
    try testing.expectEqual(@as(u64, 14), retention.snapshotStats().passes);
    try testing.expectEqual(@as(u64, 2), retention.snapshotStats().vacuums);
}

test "a gated pass skips the vacuum, counts it, and vacuums on the next pass" {
    var threaded: std.Io.Threaded = .init(testing.allocator, .{});
    defer threaded.deinit();
    const io = threaded.io();

    var database = try openLog();
    defer database.close();

    // `.critical` is the one state `writesAllowed` refuses on, and it is
    // published here directly: no real filesystem has to fill up for it.
    var monitor: disk_monitor.Monitor = .init(.{}, std.Io.Dir.cwd(), ".", null);
    monitor.state_raw.store(@intFromEnum(disk_monitor.State.critical), .monotonic);

    var gated_days: RetentionDays = .init(30);
    var gated: Retention = .init(&gated_days);
    for (0..vacuum_every_passes) |_| gated.runOnce(io, &database, &monitor, null);

    // Prune and checkpoint ran on every pass; only the vacuum was refused.
    try testing.expectEqual(@as(u64, vacuum_every_passes), gated.snapshotStats().passes);
    try testing.expectEqual(@as(u64, vacuum_every_passes), gated.snapshotStats().checkpoints);
    try testing.expectEqual(@as(u64, 0), gated.snapshotStats().vacuums);
    try testing.expectEqual(@as(u64, 1), gated.snapshotStats().vacuums_gated);

    // The vacuum is due again immediately, not seven passes later.
    monitor.state_raw.store(@intFromEnum(disk_monitor.State.ok), .monotonic);
    gated.runOnce(io, &database, &monitor, null);
    try testing.expectEqual(@as(u64, 1), gated.snapshotStats().vacuums);
    try testing.expectEqual(@as(u64, 1), gated.snapshotStats().vacuums_gated);

    // And the counter reset, so the next six passes vacuum nothing.
    for (0..vacuum_every_passes - 1) |_| gated.runOnce(io, &database, &monitor, null);
    try testing.expectEqual(@as(u64, 1), gated.snapshotStats().vacuums);
}

test "a warn state still allows the vacuum" {
    var threaded: std.Io.Threaded = .init(testing.allocator, .{});
    defer threaded.deinit();
    const io = threaded.io();

    var database = try openLog();
    defer database.close();

    var monitor: disk_monitor.Monitor = .init(.{}, std.Io.Dir.cwd(), ".", null);
    monitor.state_raw.store(@intFromEnum(disk_monitor.State.warn), .monotonic);

    var retention_days: RetentionDays = .init(30);
    var retention: Retention = .init(&retention_days);
    for (0..vacuum_every_passes) |_| retention.runOnce(io, &database, &monitor, null);

    try testing.expectEqual(@as(u64, 1), retention.snapshotStats().vacuums);
    try testing.expectEqual(@as(u64, 0), retention.snapshotStats().vacuums_gated);
}

test "a pass over an empty database still counts" {
    var threaded: std.Io.Threaded = .init(testing.allocator, .{});
    defer threaded.deinit();
    const io = threaded.io();

    var database = try openLog();
    defer database.close();

    var retention_days: RetentionDays = .init(30);
    var retention: Retention = .init(&retention_days);
    retention.runOnce(io, &database, null, null);

    try testing.expectEqual(@as(u64, 1), retention.snapshotStats().passes);
    try testing.expectEqual(@as(u64, 0), retention.snapshotStats().rows_pruned);
    try testing.expectEqual(@as(u64, 1), retention.snapshotStats().checkpoints);
    try testing.expectEqual(@as(i64, 0), try queries_repo.countRows(&database));
}

test "a failing prune counts the pass and leaves the rows alone" {
    var threaded: std.Io.Threaded = .init(testing.allocator, .{});
    defer threaded.deinit();
    const io = threaded.io();

    var database = try openLog();
    defer database.close();

    const now = std.Io.Clock.real.now(io).toSeconds();
    try writeRows(&database, &.{now - 40 * 86_400});
    try database.exec(
        \\CREATE TRIGGER refuse_delete BEFORE DELETE ON query_log
        \\BEGIN SELECT RAISE(ABORT, 'refused'); END;
    );

    var retention_days: RetentionDays = .init(30);
    var retention: Retention = .init(&retention_days);
    retention.runOnce(io, &database, null, null);

    try testing.expectEqual(@as(i64, 1), try queries_repo.countRows(&database));
    try testing.expectEqual(@as(u64, 1), retention.snapshotStats().passes);
    try testing.expectEqual(@as(u64, 0), retention.snapshotStats().rows_pruned);
    // The checkpoint runs whether or not the prune did.
    try testing.expectEqual(@as(u64, 1), retention.snapshotStats().checkpoints);
}

test "the next pass retries what the failed one could not do" {
    var threaded: std.Io.Threaded = .init(testing.allocator, .{});
    defer threaded.deinit();
    const io = threaded.io();

    var database = try openLog();
    defer database.close();

    const now = std.Io.Clock.real.now(io).toSeconds();
    try writeRows(&database, &.{ now - 40 * 86_400, now - 39 * 86_400 });
    try database.exec(
        \\CREATE TRIGGER refuse_delete BEFORE DELETE ON query_log
        \\BEGIN SELECT RAISE(ABORT, 'refused'); END;
    );

    var retention_days: RetentionDays = .init(30);
    var retention: Retention = .init(&retention_days);
    retention.runOnce(io, &database, null, null);
    try testing.expectEqual(@as(i64, 2), try queries_repo.countRows(&database));

    try database.exec("DROP TRIGGER refuse_delete;");
    retention.runOnce(io, &database, null, null);

    try testing.expectEqual(@as(i64, 0), try queries_repo.countRows(&database));
    try testing.expectEqual(@as(u64, 2), retention.snapshotStats().passes);
    try testing.expectEqual(@as(u64, 2), retention.snapshotStats().rows_pruned);
}

test "a failing prune opens a maintenance episode the next clean pass closes" {
    var threaded: std.Io.Threaded = .init(testing.allocator, .{});
    defer threaded.deinit();
    const io = threaded.io();

    var database = try openLog();
    defer database.close();

    var fx: events_fixture.Fixture = .{};
    try fx.init(io, 1000);
    defer fx.deinit();

    const now = std.Io.Clock.real.now(io).toSeconds();
    try writeRows(&database, &.{now - 40 * 86_400});
    try database.exec(
        \\CREATE TRIGGER refuse_delete BEFORE DELETE ON query_log
        \\BEGIN SELECT RAISE(ABORT, 'refused'); END;
    );

    var retention_days: RetentionDays = .init(30);
    var retention: Retention = .init(&retention_days);
    retention.runOnce(io, &database, null, &fx.store);

    // Only the prune failed; the checkpoint succeeded, and a success writes no
    // row of its own.
    try testing.expectEqual(@as(i64, 1), try fx.count("SELECT count(*) FROM operational_events"));
    try testing.expectEqualStrings("query_log.maintenance", try fx.text("SELECT code FROM operational_events"));
    try testing.expectEqualStrings("prune", try fx.text("SELECT subject_key FROM operational_events"));
    try testing.expectEqualStrings("warning", try fx.text("SELECT severity FROM operational_events"));

    try database.exec("DROP TRIGGER refuse_delete;");
    retention.runOnce(io, &database, null, &fx.store);

    try testing.expectEqual(@as(i64, 1), try fx.count("SELECT count(*) FROM operational_events"));
    try testing.expectEqual(
        @as(i64, 0),
        try fx.count("SELECT count(*) FROM operational_events WHERE resolved_at IS NULL"),
    );
}

test "a gated vacuum is a maintenance failure the next ungated pass closes" {
    var threaded: std.Io.Threaded = .init(testing.allocator, .{});
    defer threaded.deinit();
    const io = threaded.io();

    var database = try openLog();
    defer database.close();

    var fx: events_fixture.Fixture = .{};
    try fx.init(io, 1000);
    defer fx.deinit();

    var monitor: disk_monitor.Monitor = .init(.{}, std.Io.Dir.cwd(), ".", null);
    monitor.state_raw.store(@intFromEnum(disk_monitor.State.critical), .monotonic);

    var retention_days: RetentionDays = .init(30);
    var retention: Retention = .init(&retention_days);
    for (0..vacuum_every_passes) |_| retention.runOnce(io, &database, &monitor, &fx.store);

    try testing.expectEqualStrings("vacuum", try fx.text(
        "SELECT subject_key FROM operational_events WHERE resolved_at IS NULL",
    ));

    monitor.state_raw.store(@intFromEnum(disk_monitor.State.ok), .monotonic);
    retention.runOnce(io, &database, &monitor, &fx.store);

    try testing.expectEqual(@as(u64, 1), retention.snapshotStats().vacuums);
    try testing.expectEqual(
        @as(i64, 0),
        try fx.count("SELECT count(*) FROM operational_events WHERE resolved_at IS NULL"),
    );
}

test "a pass prunes the diagnostics store once" {
    var threaded: std.Io.Threaded = .init(testing.allocator, .{});
    defer threaded.deinit();
    const io = threaded.io();

    var database = try openLog();
    defer database.close();

    var fx: events_fixture.Fixture = .{};
    try fx.init(io, 1000);
    defer fx.deinit();

    // Resolved further back than the retention window, so the pass must drop it.
    const now = std.Io.Clock.real.now(io).toSeconds();
    const stale = now - events.Store.resolved_retention_s - 86_400;
    fx.store.reportResolved(io, stale, .query_log_recreated, "one-shot", "one-shot", .warning, "aside kept");
    try testing.expectEqual(@as(i64, 1), try fx.count("SELECT count(*) FROM operational_events"));

    var retention_days: RetentionDays = .init(30);
    var retention: Retention = .init(&retention_days);
    retention.runOnce(io, &database, null, &fx.store);

    try testing.expectEqual(@as(i64, 0), try fx.count("SELECT count(*) FROM operational_events"));
}