//! The `querylog.db` schema and its open-or-recreate policy.
//!
//! `querylog.db` is never migrated (PLAN §3.7). It holds expendable log rows,
//! so a schema change replaces the file instead of upgrading it. The
//! replacement trigger is a fingerprint derived from the DDL text itself, so
//! editing the schema below automatically invalidates every existing file — the
//! policy cannot drift out of sync with the SQL.
//!
//! **Recreating is destructive, so the predicate is a positive whitelist.** Only
//! a missing file, `error.Corrupt`, `error.NotADb`, a failed `PRAGMA
//! quick_check` and a fingerprint mismatch recreate. Every other error
//! propagates and the file on disk is not touched. `error.Busy` / `error.Locked`
//! mean another process holds the write lock — waiting is right, deleting is
//! catastrophic. `error.OutOfMemory` is this process's problem. `error.CantOpen`
//! is usually a permission or missing-directory problem that recreating would
//! mask rather than fix. Same for `error.ReadOnly`, `error.IoErr`, `error.Full`,
//! `error.Perm`, `error.Auth` and `error.Canceled`.

const std = @import("std");

const db = @import("db.zig");

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

/// Verbatim from PLAN §11.3. Multi-statement text — it goes through
/// `db.Db.exec`, never through `prepare`.
pub const ddl: [:0]const u8 =
    \\CREATE TABLE domains (
    \\    id INTEGER PRIMARY KEY,
    \\    domain TEXT NOT NULL UNIQUE
    \\);
    \\
    \\CREATE TABLE query_log (
    \\    id INTEGER PRIMARY KEY,
    \\    timestamp INTEGER NOT NULL,
    \\    domain_id INTEGER NOT NULL REFERENCES domains(id),
    \\    client_ip TEXT NOT NULL,            -- text, not a FK: log rows are immutable facts
    \\    qtype INTEGER,
    \\    blocked INTEGER NOT NULL,
    \\    block_reason TEXT,
    \\    response_time_us INTEGER,
    \\    cache_hit INTEGER,
    \\    upstream TEXT
    \\);
    \\CREATE INDEX idx_query_log_ts ON query_log(timestamp);
    \\CREATE INDEX idx_query_log_client ON query_log(client_ip);
    \\CREATE INDEX idx_query_log_domain ON query_log(domain_id);
    \\
    \\CREATE TABLE upstream_targets (
    \\    id INTEGER PRIMARY KEY,
    \\    url TEXT NOT NULL UNIQUE   -- the historical identity: config.db ids cannot cross database files
    \\);
    \\
    \\CREATE TABLE upstream_minute (
    \\    upstream_id INTEGER NOT NULL REFERENCES upstream_targets(id),
    \\    minute_ts INTEGER NOT NULL,
    \\    successes INTEGER NOT NULL,
    \\    failures INTEGER NOT NULL,
    \\    last_failure_ts INTEGER,
    \\    last_error TEXT,
    \\    PRIMARY KEY (upstream_id, minute_ts),
    \\    CHECK (successes >= 0),
    \\    CHECK (failures >= 0)
    \\) WITHOUT ROWID;
    \\CREATE INDEX idx_upstream_minute_ts ON upstream_minute(minute_ts);
;

/// `PRAGMA user_version` is a signed 32-bit field. Deriving the fingerprint from
/// the DDL means editing the schema automatically invalidates every existing
/// file — which is exactly the policy.
pub const fingerprint: i32 = blk: {
    // Covers the CRC lookup-table generation in std.hash.crc, which evaluates
    // under this scope's quota and overflows the 1000 default (and 100k).
    @setEvalBranchQuota(2_000_000);
    break :blk @bitCast(std.hash.Crc32.hash(ddl));
};

const set_user_version = std.fmt.comptimePrint("PRAGMA user_version = {d};", .{fingerprint});

/// Long enough for any path this program will be handed, plus the aside suffix.
/// A longer path is `error.NameTooLong`, which is what the filesystem calls
/// would have returned anyway.
const path_buf_len = 4096 + 64;

pub const RecreateReason = enum { missing, corrupt, not_a_database, quick_check_failed, fingerprint_mismatch };

pub const OpenResult = struct {
    database: db.Db,
    /// Non-null feeds a counter and the `/api/health` rollup.
    recreated: ?RecreateReason,
};

pub const Error = db.Error || error{AsideNameCollision} ||
    std.Io.Dir.RenamePreserveError || std.Io.Dir.DeleteFileError || std.Io.Dir.AccessError;

/// Opens `path`, recreating it if and only if it is genuinely unusable.
///
/// `path` is resolved twice by two different mechanisms: `dir`-relative for the
/// filesystem calls, and process-cwd-relative by SQLite's VFS, which knows
/// nothing about `dir`. The caller must therefore pass either an absolute path
/// with `dir` open on its parent, or `std.Io.Dir.cwd()` with a cwd-relative
/// path.
pub fn open(io: std.Io, dir: std.Io.Dir, path: [:0]const u8) Error!OpenResult {
    var handle: ?db.Db = null;
    errdefer if (handle) |*h| h.close();

    const reason: ?RecreateReason = probe: {
        dir.access(io, path, .{}) catch |e| switch (e) {
            error.FileNotFound => break :probe .missing,
            else => |other| return other,
        };

        handle = db.Db.open(path, .{ .mode = .read_write_existing }) catch |e|
            break :probe recreatable(e) orelse return e;
        const opened = &handle.?;

        db.applyPragmas(opened, .{}) catch |e|
            break :probe recreatable(e) orelse return e;

        const healthy = quickCheck(opened) catch |e|
            break :probe recreatable(e) orelse return e;
        if (!healthy) break :probe .quick_check_failed;

        const stamped = opened.queryInt("PRAGMA user_version") catch |e|
            break :probe recreatable(e) orelse return e;
        if (stamped != fingerprint) break :probe .fingerprint_mismatch;

        break :probe null;
    };

    const cause = reason orelse return .{ .database = handle.?, .recreated = null };

    // Close first, so SQLite checkpoints and drops `-wal`/`-shm` where it can.
    if (handle) |*h| h.close();
    handle = null;

    var aside_buf: [path_buf_len]u8 = undefined;
    const aside: ?[]const u8 = if (cause == .missing)
        null
    else
        try renameAside(io, dir, path, &aside_buf);

    // Not optional: a stale WAL left beside the renamed database would be
    // replayed into the freshly created file and corrupt it immediately. Any
    // failure other than "already gone" propagates rather than building the new
    // database on a half-cleaned state.
    try deleteSidecars(io, dir, path);

    const fresh = try createFresh(path);
    if (cause == .missing) {
        log.info("created querylog database '{s}'", .{path});
    } else {
        log.warn("recreated querylog database '{s}': {s}; previous file kept as '{s}'", .{
            path,
            @tagName(cause),
            aside.?,
        });
    }
    return .{ .database = fresh, .recreated = cause };
}

/// The whitelist. `null` means "propagate, do not touch the file".
fn recreatable(e: db.Error) ?RecreateReason {
    return switch (e) {
        error.Corrupt => .corrupt,
        error.NotADb => .not_a_database,
        else => null,
    };
}

/// `PRAGMA quick_check` rather than `integrity_check`: it skips the expensive
/// index-vs-table cross-check while still catching structural damage, and a
/// damaged index on an expendable log is not worth a multi-second startup scan.
fn quickCheck(database: *db.Db) db.Error!bool {
    var stmt = try database.prepare("PRAGMA quick_check");
    defer stmt.deinit();
    if (!try stmt.step()) return false;
    return std.ascii.eqlIgnoreCase(stmt.columnText(0), "ok");
}

/// Renames the unusable file out of the way and returns the name it now has.
///
/// `renamePreserve` is `RENAME_NOREPLACE`: it returns `error.PathAlreadyExists`
/// instead of overwriting. A previously saved corrupt file must never be
/// destroyed by the next recreate, and two recreates in the same second are not
/// hypothetical on a boot loop — hence the uniquifying retries.
fn renameAside(io: std.Io, dir: std.Io.Dir, path: []const u8, buf: []u8) Error![]const u8 {
    const seconds = std.Io.Clock.real.now(io).toSeconds();
    var attempt: u32 = 0;
    while (attempt < 100) : (attempt += 1) {
        const aside = if (attempt == 0)
            std.fmt.bufPrint(buf, "{s}.corrupt-{d}", .{ path, seconds }) catch return error.NameTooLong
        else
            std.fmt.bufPrint(buf, "{s}.corrupt-{d}-{d}", .{ path, seconds, attempt }) catch return error.NameTooLong;

        dir.renamePreserve(path, dir, aside, io) catch |e| switch (e) {
            error.PathAlreadyExists => continue,
            else => |other| return other,
        };
        return aside;
    }
    return error.AsideNameCollision;
}

fn deleteSidecars(io: std.Io, dir: std.Io.Dir, path: []const u8) Error!void {
    var buf: [path_buf_len]u8 = undefined;
    for ([_][]const u8{ "-wal", "-shm" }) |suffix| {
        const sidecar = std.fmt.bufPrint(&buf, "{s}{s}", .{ path, suffix }) catch return error.NameTooLong;
        dir.deleteFile(io, sidecar) catch |e| switch (e) {
            error.FileNotFound => {},
            else => |other| return other,
        };
    }
}

fn createFresh(path: [:0]const u8) db.Error!db.Db {
    var database = try db.Db.open(path, .{ .mode = .read_write_create });
    errdefer database.close();
    try db.applyPragmas(&database, .{});

    var tx = try db.Tx.begin(&database);
    errdefer tx.rollback();
    try database.exec(ddl);
    try database.exec(set_user_version);
    try tx.commit();

    return database;
}

const testing = std.testing;

test "fingerprint matches a fresh hash of the DDL" {
    try testing.expectEqual(fingerprint, @as(i32, @bitCast(std.hash.Crc32.hash(ddl))));
}

test "ddl creates the query-log tables, the upstream-history tables and every index" {
    var database = try db.Db.open(":memory:", .{ .mode = .memory });
    defer database.close();
    try db.applyPragmas(&database, .{});
    try database.exec(ddl);

    try testing.expectEqual(
        @as(i64, 4),
        try database.queryInt("SELECT count(*) FROM sqlite_schema WHERE type='table'"),
    );
    const objects = [_][]const u8{
        "domains",              "query_log",
        "idx_query_log_ts",     "idx_query_log_client",
        "idx_query_log_domain", "upstream_targets",
        "upstream_minute",      "idx_upstream_minute_ts",
    };
    for (objects) |name| {
        var stmt = try database.prepare("SELECT count(*) FROM sqlite_schema WHERE name = ?1");
        defer stmt.deinit();
        try stmt.bindText(1, name);
        try testing.expect(try stmt.step());
        try testing.expectEqual(@as(i64, 1), stmt.columnInt(0));
    }
}

test "the user_version statement stamps the fingerprint" {
    var database = try db.Db.open(":memory:", .{ .mode = .memory });
    defer database.close();
    try database.exec(set_user_version);
    try testing.expectEqual(@as(i64, fingerprint), try database.queryInt("PRAGMA user_version"));
}

// The behaviour these two cases describe — a resource error leaves the file on
// disk alone — is proven against a real file by "S7 case 23" in
// `storage_integration_test.zig`, which locks a healthy `querylog.db` from a
// second connection and asserts `open` returns `error.Busy` with the bytes, the
// file and the absence of an aside all intact. `error.OutOfMemory` has no such
// case: `open` takes no allocator, and SQLite allocates through its own global
// allocator, so there is no seam to inject a failure through. The two tests
// below are what covers it.
test "recreatable is a whitelist and never selects a resource error" {
    try testing.expectEqual(RecreateReason.corrupt, recreatable(error.Corrupt).?);
    try testing.expectEqual(RecreateReason.not_a_database, recreatable(error.NotADb).?);
    const propagating = [_]db.Error{
        error.Busy,       error.Locked, error.OutOfMemory, error.CantOpen,
        error.ReadOnly,   error.IoErr,  error.Full,        error.Perm,
        error.Auth,       error.Misuse, error.Constraint,  error.SqliteError,
        error.Unexpected,
    };
    for (propagating) |e| {
        try testing.expect(recreatable(e) == null);
    }
}

test "recreatable selects exactly two of db.Error's members" {
    // Exhaustive over the whole set, so a variant added to `db.Error` later
    // defaults to propagate. The list above only proves the named errors are
    // safe today; this proves nothing else can join the whitelist unnoticed.
    var whitelisted: usize = 0;
    inline for (@typeInfo(db.Error).error_set.?) |member| {
        if (recreatable(@field(db.Error, member.name)) != null) whitelisted += 1;
    }
    try testing.expectEqual(@as(usize, 2), whitelisted);
}