Files
nxdns/src/config/import.zig
T

978 lines
40 KiB
Zig

//! `nxdns import`: a ZON file becomes the whole configuration of `config.db`.
//!
//! Configuration, not content: the `hand_edited = 0` client rows the DNS path
//! materialises from live traffic are runtime state, they are absent from an
//! export, and an import carries them across rather than deleting them.
//!
//! `clients.first_seen` and `clients.last_seen` are runtime state on every client
//! row, configured ones included, and the config model carries neither. So an
//! address the database already knew keeps both across an import, and only an
//! address it has never seen takes the import's clock.
//!
//! The order is the specification. Nothing reaches the database until the file
//! has been read, parsed and validated, and every write happens inside one
//! `BEGIN IMMEDIATE` transaction, so a failed import leaves the database
//! byte-for-byte as it was.
//!
//! No filesystem write happens anywhere in this file: the input is opened
//! read-only and the database is SQLite's business.
const std = @import("std");
const Allocator = std.mem.Allocator;
const db = @import("../storage/db.zig");
const config_schema = @import("../storage/config_schema.zig");
const context = @import("../storage/repositories/context.zig");
const clients_repo = @import("../storage/repositories/clients_repo.zig");
const groups_repo = @import("../storage/repositories/groups_repo.zig");
const local_repo = @import("../storage/repositories/local_repo.zig");
const rules_repo = @import("../storage/repositories/rules_repo.zig");
const settings_repo = @import("../storage/repositories/settings_repo.zig");
const sources_repo = @import("../storage/repositories/sources_repo.zig");
const upstreams_repo = @import("../storage/repositories/upstreams_repo.zig");
const address = @import("../platform/address.zig");
const model = @import("model.zig");
const validate = @import("validate.zig");
const log = std.log.scoped(.config_import);
pub const Options = struct { force: bool = false };
pub const Error = db.Error || validate.ValidateError || std.Io.Dir.ReadFileAllocError ||
error{ DatabaseNotEmpty, ConfigTooLarge, ParseZon, PasswordAndHashBothSet };
pub const max_config_bytes = 4 * 1024 * 1024;
/// Holds any PHC-encoded argon2id string comfortably.
const hash_buf_len = 256;
/// The canonical text of an IPv6 prefix, the longest value canonicalised here.
const canonical_buf_len = 64;
// ---------------------------------------------------------------------------
// emptiness
// ---------------------------------------------------------------------------
/// A database is "never configured" when the migrations have run and the
/// operator has added nothing. The migrations themselves create
/// `schema_version` and seed `groups(1, 'default')`, so "no rows anywhere" is
/// the wrong test.
///
/// True iff no table in `config_schema.content_tables` holds a row the operator
/// put there, `groups` holds exactly one row, and that row is the seeded
/// `(1, 'default', 0)`.
///
/// `clients` is the one table a row can reach without an operator: the DNS path
/// materialises `hand_edited = 0` rows straight from live traffic (PLAN §7.2).
/// Counting those made emptiness a function of traffic — a server that had
/// answered a single query silently ignored the seed file its operator dropped
/// next to it. So only `hand_edited = 1` rows count, which is the predicate
/// `clients_repo.listClients` already exports by: this database is empty exactly
/// when its export is empty.
pub fn isEmpty(database: *db.Db) db.Error!bool {
// `inline for` over a comptime table list: every statement below is a
// compile-time string, so no table name is ever concatenated at run time.
inline for (config_schema.content_tables) |table| {
const count_sql = comptime if (std.mem.eql(u8, table, "clients"))
"SELECT count(*) FROM clients WHERE hand_edited = 1"
else
"SELECT count(*) FROM " ++ table;
if (try database.queryInt(count_sql) != 0) return false;
}
if (try database.queryInt("SELECT count(*) FROM groups") != 1) return false;
const seeded = try database.queryInt(
"SELECT count(*) FROM groups WHERE id = 1 AND name = 'default' AND safe_search = 0",
);
return seeded == 1;
}
// ---------------------------------------------------------------------------
// import
// ---------------------------------------------------------------------------
/// Reads, parses, validates, then replaces the database contents.
pub fn importFile(
io: std.Io,
gpa: Allocator,
database: *db.Db,
dir: std.Io.Dir,
path: []const u8,
options: Options,
diags: *validate.Diagnostics,
) Error!void {
// `std.zon.parse` needs a sentinel-terminated source and `readFileAlloc`
// cannot supply one.
const source = dir.readFileAllocOptions(
io,
path,
gpa,
.limited(max_config_bytes),
.of(u8),
0,
) catch |e| switch (e) {
error.StreamTooLong => return error.ConfigTooLarge,
else => |other| return other,
};
defer gpa.free(source);
return importSource(io, gpa, database, source, options, diags);
}
/// `importFile` minus the file. It exists because every step from the parse
/// onwards is testable without touching a filesystem, and `nxdns check` (S6)
/// needs the same parse-and-validate half.
pub fn importSource(
io: std.Io,
gpa: Allocator,
database: *db.Db,
source: [:0]const u8,
options: Options,
diags: *validate.Diagnostics,
) Error!void {
// The parsed `Config` is arena-owned and `std.zon.parse.free` is NEVER
// called on it. `Parser.parseStruct` fills an absent field by copying the
// struct's default straight through (parse.zig:874), so a defaulted
// `[]const u8` — and this model has many non-empty string defaults — points
// into the binary's read-only data. `parse.free` keeps no record of which
// fields were parsed and which were defaulted, so it would `@memset` and
// free rodata. Freeing the arena is the only correct release.
var arena_state: std.heap.ArenaAllocator = .init(gpa);
defer arena_state.deinit();
const arena = arena_state.allocator();
var zon_diag: std.zon.parse.Diagnostics = .{};
const cfg = std.zon.parse.fromSliceAlloc(model.Config, arena, source, &zon_diag, .{}) catch |e| switch (e) {
error.OutOfMemory => return error.OutOfMemory,
error.ParseZon => {
try reportParseFailure(diags, &zon_diag);
return error.ParseZon;
},
};
try validate.validate(cfg, diags);
const now = std.Io.Clock.real.now(io).toSeconds();
return applyToDb(io, gpa, database, cfg, now, options);
}
/// The line and column of a ZON syntax error are the only thing the operator can
/// act on, so they travel the same channel as every other config problem: the
/// caller's `Diagnostics`, which `nxdns import` already renders to stderr. The
/// global log is not that channel — an operator reading command output would see
/// a bare `ParseZon` and nothing else.
///
/// `std.zon.parse.Diagnostics` renders one "line:column: error: text" line per
/// problem, plus a "note:" line each, so each rendered line becomes one
/// `Problem` and the list keeps the parser's order.
fn reportParseFailure(
diags: *validate.Diagnostics,
zon_diag: *const std.zon.parse.Diagnostics,
) error{OutOfMemory}!void {
const rendered = try std.fmt.allocPrint(diags.gpa, "{f}", .{zon_diag});
defer diags.gpa.free(rendered);
var lines = std.mem.splitScalar(u8, rendered, '\n');
while (lines.next()) |line| {
if (line.len == 0) continue;
try diags.add(error.ParseZon, "config", .{}, "{s}", .{line});
}
}
/// The half `bootstrap` reuses: an already-parsed, already-validated config into
/// the database, all or nothing. `now` is the caller's timestamp for the runtime
/// columns the model omits.
pub fn applyToDb(
io: std.Io,
gpa: Allocator,
database: *db.Db,
cfg: model.Config,
now: i64,
options: Options,
) Error!void {
var tx = try db.Tx.begin(database);
errdefer tx.rollback();
// Inside the transaction on purpose. Checking before `BEGIN IMMEDIATE`
// would leave a TOCTOU window against a concurrently starting process;
// `BEGIN IMMEDIATE` already holds the write lock, so the check and the
// writes are one atomic unit.
if (!options.force and !try isEmpty(database)) return error.DatabaseNotEmpty;
try liftSavedClients(database);
inline for (config_schema.delete_order) |table| {
try database.exec("DELETE FROM " ++ table ++ ";");
}
var group_ids: context.IdMap = .empty;
defer group_ids.deinit(gpa);
var source_ids: context.IdMap = .empty;
defer source_ids.deinit(gpa);
try insertGroups(database, gpa, cfg, &group_ids);
try insertSources(database, gpa, cfg, &source_ids);
const ctx: context.InsertContext = .{
.now = now,
.group_ids = &group_ids,
.source_ids = &source_ids,
};
for (cfg.clients) |client| {
var buf: [canonical_buf_len]u8 = undefined;
var canonical = client;
canonical.ip = try canonicalIp(client.ip, &buf);
try clients_repo.insertClient(database, canonical, ctx);
}
try restoreSavedClients(database, group_ids.get("default").?);
for (cfg.client_prefixes) |entry| {
var buf: [canonical_buf_len]u8 = undefined;
var canonical = entry;
canonical.prefix = try canonicalPrefix(entry.prefix, &buf);
try clients_repo.insertClientPrefix(database, canonical, ctx);
}
for (cfg.upstreams) |item| try upstreams_repo.insertUpstream(database, item, ctx);
for (cfg.group_sources) |item| try groups_repo.insertGroupSource(database, item, ctx);
for (cfg.rules) |item| try rules_repo.insertRule(database, item, ctx);
for (cfg.local_records) |item| try local_repo.insertLocalRecord(database, item, ctx);
for (cfg.forward_zones) |item| try local_repo.insertForwardZone(database, item, ctx);
// The buffer must outlive `toSettings`: `effective.web.password_hash` points
// into it.
var hash_buf: [hash_buf_len]u8 = undefined;
var effective = cfg;
if (cfg.web.password.len != 0) {
if (cfg.web.password_hash.len != 0) return error.PasswordAndHashBothSet;
effective.web.password_hash = try hashPassword(io, gpa, cfg.web.password, &hash_buf);
}
// Operator input, never stored. `toSettings` skips the field in both
// directions; clearing it here keeps the in-memory value honest too.
effective.web.password = "";
var pairs: std.ArrayList(model.SettingPair) = .empty;
defer {
model.freeSettings(gpa, pairs.items);
pairs.deinit(gpa);
}
try model.toSettings(effective, gpa, &pairs);
for (pairs.items) |pair| try settings_repo.insertSetting(database, pair, ctx);
try tx.commit();
}
const lift_saved_clients_sql: [:0]const u8 =
\\DROP TABLE IF EXISTS temp.saved_clients;
\\CREATE TEMP TABLE saved_clients AS
\\ SELECT ip, name, hand_edited, first_seen, last_seen FROM clients;
;
/// Carries what the wipe must not destroy over the wipe that follows: the
/// auto-materialised client rows themselves, and the observed timestamps of
/// every client row whatever its flag.
///
/// A `hand_edited = 0` row is runtime state, not configuration: the DNS path
/// wrote it from live traffic and `clients_repo.listClients` already keeps it out
/// of an export. Replacing the *configuration* must therefore not delete it —
/// but it cannot survive in place either, because `clients.group_id` references
/// `groups(id)` with no cascade, and the wipe empties `groups`. So the rows step
/// aside into the temp database and come back once `groups` holds `default`
/// again.
///
/// The table takes every row, not only the `hand_edited = 0` ones, because
/// `first_seen` and `last_seen` are runtime state on a configured row too — the
/// tracker keeps writing `last_seen` on the clients the operator named. Saving
/// only the materialised rows would keep the observation history of the devices
/// nobody named and destroy it for the devices somebody did. `hand_edited` rides
/// along so the restore can tell the two apart.
///
/// `IF EXISTS` because a rolled-back import must not poison the next one.
fn liftSavedClients(database: *db.Db) Error!void {
return database.exec(lift_saved_clients_sql);
}
const merge_observed_timestamps_sql: [:0]const u8 =
\\UPDATE clients AS c
\\ SET first_seen = m.first_seen, last_seen = m.last_seen
\\ FROM temp.saved_clients m
\\ WHERE m.ip = c.ip
;
const restore_materialised_clients_sql =
\\INSERT INTO clients (ip, name, group_id, hand_edited, first_seen, last_seen)
\\SELECT m.ip, m.name, ?1, 0, m.first_seen, m.last_seen
\\ FROM temp.saved_clients m
\\ WHERE m.hand_edited = 0
\\ AND NOT EXISTS (SELECT 1 FROM clients c WHERE c.ip = m.ip)
;
/// Puts back what `liftSavedClients` set aside, in two steps that must stay in
/// this order: the restore drops the temp table on its way out, so the merge
/// cannot follow it.
///
/// **The merge.** An address the config declares belongs to the config — but
/// `first_seen` and `last_seen` are not the config's to state. The model carries
/// neither field, so `insertClient` writes `now` into both as a placeholder for a
/// device it knows nothing about. When the database already held that address, the
/// placeholder is the worse of the two values and both columns come from the saved
/// row instead. Everything else on the row stays the config's: the name, the
/// group, and `hand_edited = 1`.
///
/// Not "the earlier `first_seen` and the later `last_seen`": the placeholder is
/// the wall clock at import time and every real observation predates it, so
/// "later" would resolve to the placeholder every time and stamp each named
/// device as seen at the moment of the import. An operator restoring a backup
/// would read that as liveness. `first_seen` and `last_seen` mean "when a query
/// from this address arrived", `pruneStale` and the API both read them that way,
/// and an import is not a query. Taking both from the saved row also keeps
/// `first_seen <= last_seen`, which `upsertSeen` guarantees pairwise.
///
/// Only the config's own clients are in the table at this point, so the update
/// needs no filter of its own, and the saved row's flag does not enter into it: a
/// device keeps its history whether the previous row was materialised or
/// configured. A `--force` re-import of the same file is the case that matters —
/// it deletes and rewrites every configured client, and without the merge each
/// one would come back claiming it was first seen at the moment of the import.
///
/// **The restore.** Only `hand_edited = 0` rows come back. A configured client is
/// configuration, so a file that leaves its address out has removed that client
/// and the row must stay gone; its history was saved for the merge, not for a
/// resurrection. `WHERE NOT EXISTS` rather than `INSERT OR IGNORE`: the only
/// materialised row worth skipping is one whose address the config claims — the
/// operator naming a device the server had already discovered, handled by the
/// merge above — and every other constraint failure stays loud.
///
/// The rows return to `default`, the group `upsertSeen` materialises into.
/// `first_seen` and `last_seen` cross unchanged; the row id does not, because the
/// config's clients went in first and hold the low ids now. Nothing references
/// `clients.id` inside `config.db`, and §3.6 keeps the query log out of it.
fn restoreSavedClients(database: *db.Db, default_group_id: i64) Error!void {
try database.exec(merge_observed_timestamps_sql);
{
var stmt = try database.prepare(restore_materialised_clients_sql);
defer stmt.deinit();
try stmt.bindInt(1, default_group_id);
try stmt.exec();
}
return database.exec("DROP TABLE temp.saved_clients;");
}
/// `default` goes in first and takes rowid 1. §11.2 seeds group 1 as `default`
/// and §7.2's fallback assignment depends on it; letting an import renumber it
/// would silently move every unassigned client.
///
/// The repositories expose no insert-with-id, so the id is taken rather than
/// given: SQLite assigns rowid 1 to the first row of an empty table, and the
/// table was emptied a few statements ago. The result is checked, not assumed.
fn insertGroups(database: *db.Db, gpa: Allocator, cfg: model.Config, ids: *context.IdMap) Error!void {
const default_index = indexOfGroup(cfg.groups, "default") orelse {
log.warn("the config declares no group named 'default'", .{});
return error.MissingDefaultGroup;
};
try insertGroup(database, gpa, cfg.groups[default_index], ids);
const default_id = ids.get("default").?;
if (default_id != 1) {
log.warn("group 'default' took id {d}, not 1", .{default_id});
return error.Unexpected;
}
for (cfg.groups, 0..) |group, i| {
if (i == default_index) continue;
try insertGroup(database, gpa, group, ids);
}
}
fn insertGroup(database: *db.Db, gpa: Allocator, group: model.Group, ids: *context.IdMap) Error!void {
try groups_repo.insertGroup(database, group, .{});
// The key borrows from `cfg`, which outlives the transaction.
try ids.put(gpa, group.name, database.lastInsertRowid());
}
fn insertSources(database: *db.Db, gpa: Allocator, cfg: model.Config, ids: *context.IdMap) Error!void {
for (cfg.blocklist_sources) |item| {
try sources_repo.insertBlocklistSource(database, item, .{});
try ids.put(gpa, item.url, database.lastInsertRowid());
}
}
fn indexOfGroup(groups: []const model.Group, name: []const u8) ?usize {
for (groups, 0..) |group, i| {
if (std.mem.eql(u8, group.name, name)) return i;
}
return null;
}
/// The validator compares client addresses after canonicalisation, so the row
/// this writes must be canonical too — otherwise `fd00::1` and
/// `FD00:0:0:0:0:0:0:1` pass validation as a duplicate pair and then collide on
/// the column's `UNIQUE`.
fn canonicalIp(text: []const u8, buf: []u8) error{BadClientIp}![]const u8 {
const addr = address.NetAddress.parse(text) catch return error.BadClientIp;
var w: std.Io.Writer = .fixed(buf);
addr.format(&w) catch return error.BadClientIp;
return w.buffered();
}
fn canonicalPrefix(text: []const u8, buf: []u8) error{BadClientPrefix}![]const u8 {
const prefix = address.Prefix.parse(text) catch return error.BadClientPrefix;
var w: std.Io.Writer = .fixed(buf);
prefix.format(&w) catch return error.BadClientPrefix;
return w.buffered();
}
/// argon2id with the OWASP parameters (t=2, m=19 MiB, p=1) rather than the
/// 64 MiB `interactive_2id`, because PLAN §18 budgets under 100 MiB total on a
/// Pi 5.
///
/// `strHash`'s error set reaches beyond this module's (it carries
/// `std.Thread.SpawnError` and the PHC encoding errors), so anything that is
/// neither out of memory nor a cancellation is reported as `error.Unexpected`
/// with the real cause logged.
fn hashPassword(io: std.Io, gpa: Allocator, password: []const u8, buf: []u8) Error![]const u8 {
return std.crypto.pwhash.argon2.strHash(password, .{
.allocator = gpa,
.params = .owasp_2id,
.mode = .argon2id,
.encoding = .phc,
}, buf, io) catch |e| switch (e) {
error.OutOfMemory => error.OutOfMemory,
error.Canceled => error.Canceled,
else => {
log.warn("hashing web.password failed: {s}", .{@errorName(e)});
return error.Unexpected;
},
};
}
// ---------------------------------------------------------------------------
// tests
// ---------------------------------------------------------------------------
const testing = std.testing;
const migrations = @import("../storage/migrations.zig");
fn openMigrated() !db.Db {
var database = try db.Db.open(":memory:", .{ .mode = .memory });
errdefer database.close();
try db.applyPragmas(&database, .{});
_ = try migrations.migrate(&database);
return database;
}
/// Every row of every config table, rendered in a stable order. Two dumps are
/// equal exactly when the database content is.
fn dump(database: *db.Db, gpa: Allocator) ![]u8 {
var out: std.Io.Writer.Allocating = .init(gpa);
errdefer out.deinit();
const w = &out.writer;
try w.writeAll("groups\n");
var stmt = try database.prepare("SELECT id, name, safe_search FROM groups ORDER BY id");
defer stmt.deinit();
while (try stmt.step()) {
try w.print(" {d} {s} {d}\n", .{ stmt.columnInt(0), stmt.columnText(1), stmt.columnInt(2) });
}
inline for (config_schema.content_tables) |table| {
try w.print("{s}\n", .{table});
var rows = try database.prepare("SELECT * FROM " ++ table ++ " ORDER BY 1, 2");
defer rows.deinit();
const columns = db.c.sqlite3_column_count(rows.handle);
while (try rows.step()) {
var col: c_int = 0;
while (col < columns) : (col += 1) {
try w.print(" {s}", .{rows.columnText(col)});
}
try w.writeAll("\n");
}
}
return out.toOwnedSlice();
}
/// The smallest config that validates: one enabled upstream and the `default`
/// group.
const minimal_source: [:0]const u8 =
\\.{
\\ .groups = .{ .{ .name = "default" } },
\\ .upstreams = .{ .{ .url = "https://dns.example/dns-query" } },
\\}
;
/// Exercises every collection and a few non-default scalars.
const full_source: [:0]const u8 =
\\.{
\\ .dns = .{ .port = 5353 },
\\ .logging = .{ .level = .err, .retention_days = 7 },
\\ .groups = .{ .{ .name = "default" }, .{ .name = "kids", .safe_search = true } },
\\ .upstreams = .{
\\ .{ .url = "https://dns.example/dns-query", .priority = 10 },
\\ .{ .url = "tls://dot.example:853", .priority = 20, .enabled = false, .tls_name = "dot.example" },
\\ },
\\ .clients = .{ .{ .ip = "FD00:0:0:0:0:0:0:1", .name = "tablet", .group = "kids" } },
\\ .client_prefixes = .{ .{ .prefix = "192.168.1.0/24", .group = "kids", .priority = 50 } },
\\ .blocklist_sources = .{ .{ .url = "https://lists.example/ads.txt", .name = "ads" } },
\\ .group_sources = .{ .{ .group = "kids", .source_url = "https://lists.example/ads.txt" } },
\\ .rules = .{ .{ .group = "kids", .pattern = "*.tracker.example", .kind = .wildcard, .action = .block } },
\\ .local_records = .{ .{ .name = "nas.lan", .rtype = .a, .value = "192.168.1.10", .ttl = 600 } },
\\ .forward_zones = .{ .{ .zone = "lan", .resolver = "udp://192.168.1.1:53" } },
\\}
;
fn importText(io: std.Io, database: *db.Db, source: [:0]const u8, options: Options) !void {
var diags: validate.Diagnostics = .init(testing.allocator);
defer diags.deinit();
return importSource(io, testing.allocator, database, source, options, &diags);
}
test "isEmpty is true on a freshly migrated database" {
var database = try openMigrated();
defer database.close();
try testing.expect(try isEmpty(&database));
}
test "isEmpty is false once a settings row exists" {
var database = try openMigrated();
defer database.close();
try database.exec("INSERT INTO settings (key, value) VALUES ('dns.port', '53');");
try testing.expect(!try isEmpty(&database));
}
test "isEmpty ignores the client rows live traffic materialises" {
var database = try openMigrated();
defer database.close();
// The real §7.2 write path, not hand-written SQL: what makes these rows
// ignorable is that `upsertSeen` is the thing that wrote them.
try clients_repo.upsertSeen(&database, "192.168.1.5", 1700000000);
try clients_repo.upsertSeen(&database, "192.168.1.6", 1700000100);
try testing.expectEqual(@as(i64, 2), try clients_repo.countClients(&database));
try testing.expect(try isEmpty(&database));
}
test "isEmpty is false once a client carries operator intent" {
var database = try openMigrated();
defer database.close();
_ = try clients_repo.insertClientRow(
&database,
.{ .ip = "192.168.1.7", .name = "printer", .group_id = 1 },
1700000000,
);
try testing.expect(!try isEmpty(&database));
}
test "isEmpty is false once an operator edits a materialised client" {
var database = try openMigrated();
defer database.close();
try clients_repo.upsertSeen(&database, "192.168.1.5", 1700000000);
try testing.expect(try isEmpty(&database));
// A PUT through the API is what turns a discovered device into policy, and
// that policy is exactly what a seed would replace.
const id = try database.queryInt("SELECT id FROM clients WHERE ip = '192.168.1.5'");
try clients_repo.updateClient(&database, id, .{ .name = "tv", .group_id = 1 });
try testing.expect(!try isEmpty(&database));
}
test "isEmpty is false once the seeded group is changed" {
var database = try openMigrated();
defer database.close();
try database.exec("UPDATE groups SET name = 'renamed' WHERE id = 1;");
try testing.expect(!try isEmpty(&database));
}
test "importSource seeds a migrated database and group 'default' keeps id 1" {
var threaded: std.Io.Threaded = .init(testing.allocator, .{});
defer threaded.deinit();
const io = threaded.io();
var database = try openMigrated();
defer database.close();
try importText(io, &database, full_source, .{});
try testing.expectEqual(@as(i64, 1), try database.queryInt("SELECT id FROM groups WHERE name = 'default'"));
try testing.expectEqual(@as(i64, 2), try database.queryInt("SELECT count(*) FROM upstreams"));
// The v6 client address was written in canonical form, not as typed.
try testing.expectEqual(@as(i64, 1), try database.queryInt("SELECT count(*) FROM clients WHERE ip = 'fd00::1'"));
try testing.expectEqual(
@as(i64, 1),
try database.queryInt("SELECT count(*) FROM upstreams WHERE tls_name = 'dot.example'"),
);
try testing.expectEqual(
@as(i64, 1),
try database.queryInt("SELECT count(*) FROM upstreams WHERE tls_name = ''"),
);
}
test "an import keeps the materialised clients it found and lets the config claim an address" {
var threaded: std.Io.Threaded = .init(testing.allocator, .{});
defer threaded.deinit();
const io = threaded.io();
var database = try openMigrated();
defer database.close();
// Two devices the server discovered. `full_source` names the second one.
// The first is seen twice, so `first_seen` and `last_seen` differ and the
// assertions below cannot pass by carrying one column into both.
try clients_repo.upsertSeen(&database, "192.168.1.5", 1700000000);
try clients_repo.upsertSeen(&database, "192.168.1.5", 1700000100);
try clients_repo.upsertSeen(&database, "fd00::1", 1700000200);
try importText(io, &database, full_source, .{});
try testing.expectEqual(@as(i64, 2), try clients_repo.countClients(&database));
// The device the config says nothing about keeps its flag, its group and
// both timestamps: a seed is not a reason to forget when a device appeared.
var stmt = try database.prepare(
"SELECT hand_edited, group_id, first_seen, last_seen FROM clients WHERE ip = '192.168.1.5'",
);
defer stmt.deinit();
try testing.expect(try stmt.step());
try testing.expectEqual(@as(i64, 0), stmt.columnInt(0));
try testing.expectEqual(@as(i64, 1), stmt.columnInt(1));
try testing.expectEqual(@as(i64, 1700000000), stmt.columnInt(2));
try testing.expectEqual(@as(i64, 1700000100), stmt.columnInt(3));
// The one the config names belongs to the config: named, in `kids`, and
// hand-edited, so a later prune leaves it alone.
try testing.expectEqual(@as(i64, 1), try database.queryInt(
\\SELECT count(*) FROM clients c JOIN groups g ON g.id = c.group_id
\\ WHERE c.ip = 'fd00::1' AND c.hand_edited = 1 AND c.name = 'tablet' AND g.name = 'kids'
));
}
test "the config claiming a discovered address keeps that device's observed timestamps" {
var threaded: std.Io.Threaded = .init(testing.allocator, .{});
defer threaded.deinit();
const io = threaded.io();
var database = try openMigrated();
defer database.close();
// The device is seen twice, so the two timestamps differ and neither
// assertion below can pass by carrying one column into the other.
// `full_source` names this address.
try clients_repo.upsertSeen(&database, "fd00::1", 1700000200);
try clients_repo.upsertSeen(&database, "fd00::1", 1700000900);
try importText(io, &database, full_source, .{});
var stmt = try database.prepare(
"SELECT hand_edited, name, first_seen, last_seen FROM clients WHERE ip = 'fd00::1'",
);
defer stmt.deinit();
try testing.expect(try stmt.step());
// The row is the config's: named, hand-edited.
try testing.expectEqual(@as(i64, 1), stmt.columnInt(0));
try testing.expectEqualStrings("tablet", stmt.columnText(1));
// The observation history is the tracker's. The import clock is `now`, so
// both columns would hold a value far above these if the import had written
// its own.
try testing.expectEqual(@as(i64, 1700000200), stmt.columnInt(2));
try testing.expectEqual(@as(i64, 1700000900), stmt.columnInt(3));
}
test "a failed import leaves the observed timestamps exactly as they were" {
var threaded: std.Io.Threaded = .init(testing.allocator, .{});
defer threaded.deinit();
const io = threaded.io();
const gpa = testing.allocator;
var database = try openMigrated();
defer database.close();
// One address the config below claims, one it says nothing about.
try clients_repo.upsertSeen(&database, "fd00::1", 1700000200);
try clients_repo.upsertSeen(&database, "fd00::1", 1700000900);
try clients_repo.upsertSeen(&database, "192.168.1.5", 1700000000);
const before = try dump(&database, gpa);
defer gpa.free(before);
// The clients go in, the timestamps merge, and then two identical local
// records violate `UNIQUE(name, rtype, value)`. Everything the import wrote
// must go with the transaction.
const broken: model.Config = .{
.groups = &.{.{ .name = "default" }},
.upstreams = &.{.{ .url = "https://dns.example/dns-query" }},
.clients = &.{.{ .ip = "fd00::1", .name = "tablet" }},
.local_records = &.{
.{ .name = "dup.lan", .rtype = .a, .value = "10.0.0.1" },
.{ .name = "dup.lan", .rtype = .a, .value = "10.0.0.1" },
},
};
try testing.expectError(error.Constraint, applyToDb(io, gpa, &database, broken, 42, .{}));
const after = try dump(&database, gpa);
defer gpa.free(after);
try testing.expectEqualStrings(before, after);
}
test "a forced re-import replaces the configured clients and keeps the materialised ones" {
var threaded: std.Io.Threaded = .init(testing.allocator, .{});
defer threaded.deinit();
const io = threaded.io();
var database = try openMigrated();
defer database.close();
try importText(io, &database, full_source, .{});
try clients_repo.upsertSeen(&database, "10.0.0.9", 1700000200);
// The device the old file named keeps querying, so its row carries real
// observation history when the wipe reaches it.
try clients_repo.upsertSeen(&database, "fd00::1", 1700003000);
try importText(io, &database, minimal_source, .{ .force = true });
// `full_source`'s hand-edited client went with the rest of the old
// configuration; the discovered one did not.
try testing.expectEqual(@as(i64, 1), try clients_repo.countClients(&database));
try testing.expectEqual(@as(i64, 1700000200), try database.queryInt(
"SELECT first_seen FROM clients WHERE ip = '10.0.0.9' AND hand_edited = 0",
));
// The lift saves a configured client's history so the merge can hand it back
// to the same address. It must never become a reason to resurrect a client
// the new file leaves out: dropping a client from the file removes it.
try testing.expectEqual(@as(i64, 0), try database.queryInt(
"SELECT count(*) FROM clients WHERE ip = 'fd00::1'",
));
try testing.expectEqual(@as(i64, 1), try database.queryInt("SELECT count(*) FROM upstreams"));
}
test "a forced re-import keeps the observed timestamps of a client the config names" {
var threaded: std.Io.Threaded = .init(testing.allocator, .{});
defer threaded.deinit();
const io = threaded.io();
var database = try openMigrated();
defer database.close();
// The device appears in traffic, the operator's file names it, and it keeps
// querying afterwards. The row is now `hand_edited = 1` and carries a real
// `first_seen` and a later `last_seen`.
try clients_repo.upsertSeen(&database, "fd00::1", 1700000200);
try importText(io, &database, full_source, .{});
try clients_repo.upsertSeen(&database, "fd00::1", 1700005000);
try importText(io, &database, full_source, .{ .force = true });
var stmt = try database.prepare(
"SELECT hand_edited, first_seen, last_seen FROM clients WHERE ip = 'fd00::1'",
);
defer stmt.deinit();
try testing.expect(try stmt.step());
try testing.expectEqual(@as(i64, 1), stmt.columnInt(0));
// Re-importing the same file is not an observation of the device.
try testing.expectEqual(@as(i64, 1700000200), stmt.columnInt(1));
try testing.expectEqual(@as(i64, 1700005000), stmt.columnInt(2));
}
test "a failed forced import leaves every client timestamp exactly as it was" {
var threaded: std.Io.Threaded = .init(testing.allocator, .{});
defer threaded.deinit();
const io = threaded.io();
const gpa = testing.allocator;
var database = try openMigrated();
defer database.close();
// A configured client with observation history, and a materialised one.
try importText(io, &database, full_source, .{});
try clients_repo.upsertSeen(&database, "fd00::1", 1700005000);
try clients_repo.upsertSeen(&database, "10.0.0.9", 1700000200);
const before = try dump(&database, gpa);
defer gpa.free(before);
const broken: model.Config = .{
.groups = &.{.{ .name = "default" }},
.upstreams = &.{.{ .url = "https://dns.example/dns-query" }},
.clients = &.{.{ .ip = "fd00::1", .name = "tablet" }},
.local_records = &.{
.{ .name = "dup.lan", .rtype = .a, .value = "10.0.0.1" },
.{ .name = "dup.lan", .rtype = .a, .value = "10.0.0.1" },
},
};
try testing.expectError(
error.Constraint,
applyToDb(io, gpa, &database, broken, 42, .{ .force = true }),
);
const after = try dump(&database, gpa);
defer gpa.free(after);
try testing.expectEqualStrings(before, after);
}
test "applyToDb without force refuses a configured database and changes nothing" {
var threaded: std.Io.Threaded = .init(testing.allocator, .{});
defer threaded.deinit();
const io = threaded.io();
const gpa = testing.allocator;
var database = try openMigrated();
defer database.close();
try importText(io, &database, full_source, .{});
const before = try dump(&database, gpa);
defer gpa.free(before);
const second: model.Config = .{
.groups = &.{.{ .name = "default" }},
.upstreams = &.{.{ .url = "https://other.example/dns-query" }},
};
try testing.expectError(error.DatabaseNotEmpty, applyToDb(io, gpa, &database, second, 42, .{}));
const after = try dump(&database, gpa);
defer gpa.free(after);
try testing.expectEqualStrings(before, after);
}
test "applyToDb rolls back completely when an insert fails mid-way" {
var threaded: std.Io.Threaded = .init(testing.allocator, .{});
defer threaded.deinit();
const io = threaded.io();
const gpa = testing.allocator;
var database = try openMigrated();
defer database.close();
try importText(io, &database, full_source, .{});
const before = try dump(&database, gpa);
defer gpa.free(before);
// Two identical local records violate `UNIQUE(name, rtype, value)`. The
// validator would catch this, which is exactly why the test calls
// `applyToDb` directly: the all-or-nothing guarantee has to hold on its own.
const broken: model.Config = .{
.groups = &.{.{ .name = "default" }},
.upstreams = &.{.{ .url = "https://other.example/dns-query" }},
.local_records = &.{
.{ .name = "dup.lan", .rtype = .a, .value = "10.0.0.1" },
.{ .name = "dup.lan", .rtype = .a, .value = "10.0.0.1" },
},
};
try testing.expectError(error.Constraint, applyToDb(io, gpa, &database, broken, 42, .{ .force = true }));
const after = try dump(&database, gpa);
defer gpa.free(after);
try testing.expectEqualStrings(before, after);
}
test "importSource writes nothing when validation fails" {
var threaded: std.Io.Threaded = .init(testing.allocator, .{});
defer threaded.deinit();
const io = threaded.io();
var database = try openMigrated();
defer database.close();
// No `default` group and no enabled upstream.
const bad: [:0]const u8 =
\\.{ .groups = .{ .{ .name = "kids" } } }
;
var diags: validate.Diagnostics = .init(testing.allocator);
defer diags.deinit();
try testing.expectError(
error.MissingDefaultGroup,
importSource(io, testing.allocator, &database, bad, .{}, &diags),
);
try testing.expect(diags.problems.items.len >= 2);
try testing.expect(try isEmpty(&database));
}
test "importSource reports a ZON syntax error and writes nothing" {
var threaded: std.Io.Threaded = .init(testing.allocator, .{});
defer threaded.deinit();
const io = threaded.io();
var database = try openMigrated();
defer database.close();
var diags: validate.Diagnostics = .init(testing.allocator);
defer diags.deinit();
try testing.expectError(
error.ParseZon,
importSource(io, testing.allocator, &database, ".{ .groups = ", .{}, &diags),
);
try testing.expect(try isEmpty(&database));
// The point of the diagnostic: what the CLI prints must name the line and the
// column, not just `ParseZon`.
try testing.expect(diags.problems.items.len >= 1);
var rendered: std.Io.Writer.Allocating = .init(testing.allocator);
defer rendered.deinit();
try diags.writeAll(&rendered.writer);
const text = rendered.written();
try testing.expect(std.mem.indexOf(u8, text, "1:14: error: ") != null);
}
test "a config omitting every optional field parses into an arena and leaks nothing" {
// The S5.1 rule as a test: `std.zon.parse.free` is never called, the arena
// is the only release, and `std.testing.allocator` fails the test if a
// defaulted rodata string were ever handed to the allocator.
var arena_state: std.heap.ArenaAllocator = .init(testing.allocator);
defer arena_state.deinit();
const cfg = try std.zon.parse.fromSliceAlloc(
model.Config,
arena_state.allocator(),
minimal_source,
null,
.{},
);
try testing.expectEqualStrings("0.0.0.0", cfg.dns.bind_ipv4);
try testing.expectEqual(@as(u16, 53), cfg.dns.port);
try testing.expectEqual(@as(usize, 1), cfg.groups.len);
}
test "a password is hashed into web.password_hash and never stored verbatim" {
var threaded: std.Io.Threaded = .init(testing.allocator, .{});
defer threaded.deinit();
const io = threaded.io();
const gpa = testing.allocator;
var database = try openMigrated();
defer database.close();
const cfg: model.Config = .{
.groups = &.{.{ .name = "default" }},
.upstreams = &.{.{ .url = "https://dns.example/dns-query" }},
.web = .{ .password = "correct horse battery staple" },
};
try applyToDb(io, gpa, &database, cfg, 42, .{});
var stmt = try database.prepare("SELECT value FROM settings WHERE key = 'web.password_hash'");
defer stmt.deinit();
try testing.expect(try stmt.step());
try testing.expect(std.mem.startsWith(u8, stmt.columnText(0), "$argon2id$"));
try testing.expectEqual(
@as(i64, 0),
try database.queryInt("SELECT count(*) FROM settings WHERE key = 'web.password'"),
);
}
test "a password and a password_hash together are refused" {
var threaded: std.Io.Threaded = .init(testing.allocator, .{});
defer threaded.deinit();
const io = threaded.io();
var database = try openMigrated();
defer database.close();
const cfg: model.Config = .{
.groups = &.{.{ .name = "default" }},
.upstreams = &.{.{ .url = "https://dns.example/dns-query" }},
.web = .{ .password = "plaintext", .password_hash = "$argon2id$v=19$m=19456,t=2,p=1$abc$def" },
};
try testing.expectError(
error.PasswordAndHashBothSet,
applyToDb(io, testing.allocator, &database, cfg, 42, .{}),
);
try testing.expect(try isEmpty(&database));
}