Files
nxdns/src/web/handlers/blocklists.zig
T
mokhtar 25455e5ae2
CI / test (push) Failing after 11s
CI / cross (push) Failing after 25s
CI / docker (push) Failing after 24s
CI / test-aarch64 (push) Failing after 2m22s
CI / frontend (push) Successful in 43s
milestone 16: behavioral fixes for silent failures, locks, counters and the query log
2026-08-07 01:54:40 +02:00

422 lines
17 KiB
Zig

//! `/api/blocklists` — the blocklist sources table, and the manual refresh.
//!
//! The resource is `blocklist_sources`: its four configuration columns are what
//! an operator edits, and the counters the refresh writes ride along in the
//! read shape so the UI can show a list's size next to its url (ruling 9).
//!
//! `POST /api/blocklists/update` runs `Manager.refreshAll` and then the reload
//! seam, and answers 202 with the status of every source (ruling 12). The
//! refresh downloads and compiles before the response is written: 202 is
//! "accepted and done as far as this connection is concerned", and the status
//! table in the body is what tells the operator which sources actually landed.
//!
//! `DELETE /api/blocklists/{id}` removes the row, reloads, and then sweeps the
//! compiled files that row named, so `<data_dir>/blocklists/` follows the table
//! the operator is looking at rather than the scheduler's next pass.
const std = @import("std");
const Allocator = std.mem.Allocator;
const http_util = @import("../http_util.zig");
const manager_mod = @import("../../filter/manager.zig");
const model = @import("../../config/model.zig");
const mutations = @import("mutations.zig");
const server = @import("../server.zig");
const sources_repo = @import("../../storage/repositories/sources_repo.zig");
const Failure = mutations.Failure;
const Request = http_util.Request;
const HandlerError = http_util.HandlerError;
const log = std.log.scoped(.web_api);
const url_conflict = "a blocklist with that url already exists";
/// How many source statuses one refresh response carries. A household runs a
/// handful of lists; a table longer than this is truncated in the response
/// only, never in the refresh.
pub const max_statuses = 64;
const Body = struct {
url: []const u8,
name: []const u8,
enabled: bool = true,
is_suggested: bool = false,
};
const Created = union(enum) { id: i64, fail: Failure };
/// One source's status, in the shape the API speaks: the fixed-size text fields
/// of `manager.SourceStatus` become plain strings, and the compile counts are
/// flattened next to them.
pub const StatusView = struct {
id: i64,
state: []const u8,
loaded: bool,
last_attempt: i64,
last_success: i64,
url: []const u8,
last_error: []const u8,
domains: u32,
wildcards: u32,
skipped_regex: u32,
pub fn from(status: *const manager_mod.SourceStatus) StatusView {
return .{
.id = status.id,
.state = @tagName(status.state),
.loaded = status.loaded,
.last_attempt = status.last_attempt,
.last_success = status.last_success,
.url = status.urlText(),
.last_error = status.errorText(),
.domains = status.counts.domains,
.wildcards = status.counts.wildcards,
.skipped_regex = status.counts.skipped_regex,
};
}
};
// ---------------------------------------------------------------------------
// decisions
// ---------------------------------------------------------------------------
pub fn applyCreate(
state: *server.WebState,
io: std.Io,
arena: Allocator,
item: model.BlocklistSource,
) error{OutOfMemory}!Created {
const database = switch (mutations.configDb(state)) {
.database => |value| value,
.fail => |failure| return .{ .fail = failure },
};
if (try mutations.checkSource(arena, item)) |problem| return .{ .fail = .{ .invalid = problem } };
state.config_lock.lockUncancelable(io);
const inserted = sources_repo.insertSourceRow(database, item);
state.config_lock.unlock(io);
const id = inserted catch |err| return .{ .fail = mutations.dbFailure(err, url_conflict) };
if (mutations.reload(state, io)) |failure| return .{ .fail = failure };
return .{ .id = id };
}
pub fn applyUpdate(
state: *server.WebState,
io: std.Io,
arena: Allocator,
id: i64,
item: model.BlocklistSource,
) error{OutOfMemory}!?Failure {
const database = switch (mutations.configDb(state)) {
.database => |value| value,
.fail => |failure| return failure,
};
if (try mutations.checkSource(arena, item)) |problem| return .{ .invalid = problem };
state.config_lock.lockUncancelable(io);
const written = sources_repo.updateSource(database, id, item);
state.config_lock.unlock(io);
written catch |err| return mutations.dbFailure(err, url_conflict);
return mutations.reload(state, io);
}
pub fn applyDelete(state: *server.WebState, io: std.Io, id: i64) ?Failure {
const database = switch (mutations.configDb(state)) {
.database => |value| value,
.fail => |failure| return failure,
};
state.config_lock.lockUncancelable(io);
const written = sources_repo.deleteSource(database, id);
state.config_lock.unlock(io);
written catch |err| return mutations.dbFailure(err, url_conflict);
const failure = mutations.reload(state, io);
pruneFiles(state, io);
return failure;
}
/// Removes the compiled files the deleted row leaves behind.
///
/// This is the moment an orphan is made during normal operation, and the only
/// other sweep is the scheduler's — up to `blocklist_update.interval_hours`
/// away. Without this call a deleted list keeps its megabytes on disk for a day.
///
/// After the reload and never part of the response: the row is gone and the
/// snapshot has stopped enforcing the list, so bytes still on disk are not a
/// failed delete. `Manager.pruneOrphans` takes the manager's refresh lock and
/// then its writer lock; the reload above has already taken and released the
/// writer lock — nothing here holds either, and `state.config_lock` was
/// released before both.
fn pruneFiles(state: *server.WebState, io: std.Io) void {
const manager = state.manager orelse return;
manager.pruneOrphans(io) catch |err| {
log.warn("pruning the deleted blocklist's files failed: {s}", .{@errorName(err)});
};
}
/// Refreshes every enabled source, then applies the result (ruling 12).
///
/// `refreshAll` already ends in the manager's own reload; the seam is called
/// too, because it is how the composition root learns that a change landed and
/// the only reload a test can observe.
pub fn applyRefresh(state: *server.WebState, io: std.Io, out: []manager_mod.SourceStatus) union(enum) {
statuses: usize,
fail: Failure,
} {
const manager = state.manager orelse return .{ .fail = .{ .unavailable = "no blocklist manager" } };
manager.refreshAll(io) catch |err| switch (err) {
error.Canceled => return .{ .fail = .{ .unavailable = "shutting down" } },
error.OutOfMemory => return .{ .fail = .{ .internal = error.OutOfMemory } },
// A source that fails to fetch or compile records that in the status
// table and returns cleanly, so reaching here means the pass itself
// broke. `Manager.Error` is wider than `db.Error`, so the cause is
// logged here and the client is told only that it was internal.
else => {
log.warn("refreshing the blocklists failed: {s}", .{@errorName(err)});
return .{ .fail = .{ .internal = error.Unexpected } };
},
};
if (mutations.reload(state, io)) |failure| return .{ .fail = failure };
return .{ .statuses = manager.statusSnapshot(io, out) };
}
// ---------------------------------------------------------------------------
// routes
// ---------------------------------------------------------------------------
pub fn list(state: *server.WebState, io: std.Io, request: *Request) HandlerError!void {
_ = io;
const database = switch (mutations.configDb(state)) {
.database => |value| value,
.fail => |failure| return mutations.respondFailure(request, failure, "listing blocklists"),
};
const rows = sources_repo.listSourceRows(database, request.arena) catch |err|
return mutations.respondFailure(request, .{ .internal = err }, "listing blocklists");
return http_util.respondJson(request, .ok, .{ .blocklists = rows.items }, &.{});
}
pub fn get(state: *server.WebState, io: std.Io, request: *Request) HandlerError!void {
_ = io;
const database = switch (mutations.configDb(state)) {
.database => |value| value,
.fail => |failure| return mutations.respondFailure(request, failure, "reading a blocklist"),
};
const row = sources_repo.getSource(database, request.arena, request.id.?) catch |err|
return mutations.respondFailure(request, .{ .internal = err }, "reading a blocklist");
const found = row orelse return mutations.respondFailure(request, .not_found, "");
return http_util.respondJson(request, .ok, found, &.{});
}
pub fn create(state: *server.WebState, io: std.Io, request: *Request) HandlerError!void {
const parsed = http_util.parseBody(Body, request) catch |err|
return mutations.respondBadBody(request, err);
const item = toModel(parsed.value);
return switch (try applyCreate(state, io, request.arena, item)) {
.fail => |failure| mutations.respondFailure(request, failure, "creating a blocklist"),
.id => |id| http_util.respondJson(request, .created, .{
.id = id,
.url = item.url,
.name = item.name,
.enabled = item.enabled,
.is_suggested = item.is_suggested,
}, &.{}),
};
}
pub fn update(state: *server.WebState, io: std.Io, request: *Request) HandlerError!void {
const parsed = http_util.parseBody(Body, request) catch |err|
return mutations.respondBadBody(request, err);
const item = toModel(parsed.value);
const id = request.id.?;
if (try applyUpdate(state, io, request.arena, id, item)) |failure| {
return mutations.respondFailure(request, failure, "updating a blocklist");
}
return http_util.respondJson(request, .ok, .{
.id = id,
.url = item.url,
.name = item.name,
.enabled = item.enabled,
.is_suggested = item.is_suggested,
}, &.{});
}
pub fn remove(state: *server.WebState, io: std.Io, request: *Request) HandlerError!void {
if (applyDelete(state, io, request.id.?)) |failure| {
return mutations.respondFailure(request, failure, "deleting a blocklist");
}
return http_util.respondEmpty(request, .no_content);
}
/// `POST /api/blocklists/update`.
pub fn refresh(state: *server.WebState, io: std.Io, request: *Request) HandlerError!void {
const statuses = try request.arena.alloc(manager_mod.SourceStatus, max_statuses);
return switch (applyRefresh(state, io, statuses)) {
.fail => |failure| mutations.respondFailure(request, failure, "refreshing the blocklists"),
.statuses => |count| respondStatuses(request, statuses[0..count]),
};
}
fn respondStatuses(request: *Request, statuses: []const manager_mod.SourceStatus) HandlerError!void {
const views = try request.arena.alloc(StatusView, statuses.len);
for (views, statuses) |*view, *status| view.* = .from(status);
return http_util.respondJson(request, .accepted, .{ .sources = views }, &.{});
}
fn toModel(body: Body) model.BlocklistSource {
return .{
.url = body.url,
.name = body.name,
.enabled = body.enabled,
.is_suggested = body.is_suggested,
};
}
// ---------------------------------------------------------------------------
// tests
// ---------------------------------------------------------------------------
const testing = std.testing;
const valid: model.BlocklistSource = .{ .url = "https://a.test/list.txt", .name = "a" };
test "a created blocklist is stored with its runtime columns at their defaults" {
var bench: mutations.Bench = undefined;
try bench.init(testing.allocator);
defer bench.deinit(testing.allocator);
const created = try applyCreate(&bench.state, bench.io(), bench.arena(), valid);
try testing.expectEqual(@as(usize, 1), bench.reloads);
const row = (try sources_repo.getSource(&bench.database, bench.arena(), created.id)).?;
try testing.expectEqualStrings("https://a.test/list.txt", row.url);
try testing.expect(row.enabled);
try testing.expectEqual(@as(?i64, null), row.last_updated);
try testing.expectEqual(@as(i64, 0), row.domain_count);
}
test "a url the validator refuses never reaches the database" {
var bench: mutations.Bench = undefined;
try bench.init(testing.allocator);
defer bench.deinit(testing.allocator);
const created = try applyCreate(&bench.state, bench.io(), bench.arena(), .{
.url = "ftp://a.test/list.txt",
.name = "a",
});
try testing.expect(created.fail == .invalid);
try testing.expectEqual(@as(i64, 0), try bench.queryInt("SELECT count(*) FROM blocklist_sources"));
const unnamed = try applyCreate(&bench.state, bench.io(), bench.arena(), .{
.url = "https://a.test/list.txt",
.name = "",
});
try testing.expect(unnamed.fail == .invalid);
try testing.expectEqual(@as(usize, 0), bench.reloads);
}
test "a duplicate url is a conflict" {
var bench: mutations.Bench = undefined;
try bench.init(testing.allocator);
defer bench.deinit(testing.allocator);
_ = try applyCreate(&bench.state, bench.io(), bench.arena(), valid);
const again = try applyCreate(&bench.state, bench.io(), bench.arena(), valid);
try testing.expectEqualStrings(url_conflict, again.fail.conflict);
}
test "editing a blocklist keeps the counters the refresh wrote" {
var bench: mutations.Bench = undefined;
try bench.init(testing.allocator);
defer bench.deinit(testing.allocator);
const created = try applyCreate(&bench.state, bench.io(), bench.arena(), valid);
try sources_repo.updateSourceStats(&bench.database, created.id, .{
.last_updated = 1700,
.domain_count = 42,
.wildcard_count = 3,
.skipped_regex_count = 1,
.checksum = "abc",
});
const failure = try applyUpdate(&bench.state, bench.io(), bench.arena(), created.id, .{
.url = "https://a.test/list.txt",
.name = "renamed",
.enabled = false,
});
try testing.expectEqual(@as(?Failure, null), failure);
const row = (try sources_repo.getSource(&bench.database, bench.arena(), created.id)).?;
try testing.expectEqualStrings("renamed", row.name);
try testing.expect(!row.enabled);
try testing.expectEqual(@as(i64, 42), row.domain_count);
try testing.expectEqual(@as(usize, 2), bench.reloads);
}
test "updating and deleting an id no row holds is a 404" {
var bench: mutations.Bench = undefined;
try bench.init(testing.allocator);
defer bench.deinit(testing.allocator);
try testing.expectEqual(
Failure.not_found,
(try applyUpdate(&bench.state, bench.io(), bench.arena(), 999, valid)).?,
);
try testing.expectEqual(Failure.not_found, applyDelete(&bench.state, bench.io(), 999).?);
try testing.expectEqual(@as(usize, 0), bench.reloads);
}
test "deleting a blocklist takes its group assignments with it" {
var bench: mutations.Bench = undefined;
try bench.init(testing.allocator);
defer bench.deinit(testing.allocator);
const created = try applyCreate(&bench.state, bench.io(), bench.arena(), valid);
try bench.exec("INSERT INTO group_sources (group_id, source_id) VALUES (1, 1);");
try testing.expectEqual(@as(?Failure, null), applyDelete(&bench.state, bench.io(), created.id));
try testing.expectEqual(@as(i64, 0), try bench.queryInt("SELECT count(*) FROM group_sources"));
try testing.expectEqual(@as(usize, 2), bench.reloads);
}
test "a refresh with no manager is unavailable rather than a silent success" {
var bench: mutations.Bench = undefined;
try bench.init(testing.allocator);
defer bench.deinit(testing.allocator);
var statuses: [4]manager_mod.SourceStatus = undefined;
const outcome = applyRefresh(&bench.state, bench.io(), &statuses);
try testing.expect(outcome.fail == .unavailable);
try testing.expectEqual(@as(usize, 0), bench.reloads);
}
test "a status becomes the flat shape the API answers with" {
var status: manager_mod.SourceStatus = .{ .id = 7, .state = .fetch_failed, .loaded = true };
const url = "https://a.test/list.txt";
@memcpy(status.url[0..url.len], url);
status.url_len = url.len;
const message = "connection refused";
@memcpy(status.last_error[0..message.len], message);
status.last_error_len = message.len;
status.counts = .{ .domains = 10, .wildcards = 2, .skipped_regex = 1 };
const view: StatusView = .from(&status);
try testing.expectEqual(@as(i64, 7), view.id);
try testing.expectEqualStrings("fetch_failed", view.state);
try testing.expect(view.loaded);
try testing.expectEqualStrings(url, view.url);
try testing.expectEqualStrings(message, view.last_error);
try testing.expectEqual(@as(u32, 10), view.domains);
}