MultiforaDB/src/fuzz_split.zig

//! Randomised differential over Index with wildly varying key sizes.
//!
//! The tree's split logic is where record sizes and slot counts interact:
//! a page can be full of bytes or full of slots, and the record that caused
//! the split has to fit the half it lands in. Fixed-shape tests never mix
//! those, so this hammers the same index with keys from 4 bytes to past the
//! inline limit, interleaves removals (which leave dead bytes behind), and
//! checks the whole tree against a model.
//!
//! Run: zig test src/fuzz_split.zig

const std = @import("std");
const bson = @import("bson.zig");
const index = @import("index.zig");
const pgr = @import("pager.zig");

const testing = std.testing;

fn make_doc(gpa: std.mem.Allocator, i: usize, s: []const u8) ![]u8 {
    var out: std.ArrayListUnmanaged(u8) = .empty;
    defer out.deinit(gpa);
    try bson.write_doc(&.{
        .{ .key = "_id", .value = .{ .int32 = @intCast(i) } },
        .{ .key = "s", .value = .{ .string = s } },
    }, gpa, &out);
    return out.toOwnedSlice(gpa);
}

const Doc = struct {
    s: []u8,
    bytes: []u8,
    off: u64,
    live: bool,
};

/// A throwaway data file for this harness. The B+tree's pages live in the data
/// file now, so a standalone harness has to provide one.
/// The Threaded is intentionally leaked: it must outlive the pager's io, and
/// these harnesses are one-shot processes. fuzz_split runs under the testing
/// allocator, which checks for leaks, so it uses the page allocator here.
fn harness_pager(gpa: std.mem.Allocator, name: []const u8) !*pgr.Pager {
    const threaded = try std.heap.page_allocator.create(std.Io.Threaded);
    threaded.* = .init_single_threaded;
    const io = threaded.io();
    const path = try std.fmt.allocPrint(std.heap.page_allocator, ".zig-cache/{s}.data", .{name});
    std.Io.Dir.cwd().deleteFile(io, path) catch {};
    const pg = try gpa.create(pgr.Pager);
    pg.* = try pgr.Pager.open(gpa, io, path, .{});
    return pg;
}

fn run(seed: u64, ops: usize, max_len: usize) !void {
    const gpa = testing.allocator;
    var prng = std.Random.DefaultPrng.init(seed);
    const rand = prng.random();

    const pg = try harness_pager(gpa, "fuzz_split");
    defer {
        pg.deinit();
        gpa.destroy(pg);
    }
    var ix = try index.Index.init(gpa, pg, "s_1", &.{.{ .path = "s", .descending = false }}, false, false, null);
    defer ix.deinit(gpa);

    var docs: std.ArrayListUnmanaged(Doc) = .empty;
    defer {
        for (docs.items) |d| {
            gpa.free(d.s);
            gpa.free(d.bytes);
        }
        docs.deinit(gpa);
    }

    var live: usize = 0;
    for (0..ops) |op| {
        if (live > 0 and rand.uintLessThan(u32, 100) < 35) {
            // Remove a random live document.
            var pick = rand.uintLessThan(usize, live);
            for (docs.items) |*d| {
                if (!d.live) continue;
                if (pick == 0) {
                    ix.remove_doc(gpa, d.bytes, d.off);
                    d.live = false;
                    live -= 1;
                    break;
                }
                pick -= 1;
            }
        } else {
            // Insert a document whose key length is drawn from a mix of
            // tiny, around the inline limit, and past it (spilled).
            const len = switch (rand.uintLessThan(u32, 10)) {
                0...4 => rand.intRangeAtMost(usize, 1, 16),
                5...7 => rand.intRangeAtMost(usize, 900, 1100),
                else => rand.intRangeAtMost(usize, 1100, max_len),
            };
            const s = try gpa.alloc(u8, len);
            errdefer gpa.free(s);
            // A small alphabet so keys collide and share prefixes.
            for (s) |*c| c.* = 'a' + rand.uintLessThan(u8, 4);
            const id: u64 = @intCast(op + 1);
            const bytes = try make_doc(gpa, op, s);
            errdefer gpa.free(bytes);
            _ = try ix.add_doc(gpa, bytes, id, false);
            try docs.append(gpa, .{ .off = id, .s = s, .bytes = bytes, .live = true });
            live += 1;
        }

        if (op % 25 != 0 and op != ops - 1) continue;

        // The tree holds exactly the live entries, in key order.
        try testing.expectEqual(live, ix.count());
        var seen: usize = 0;
        var prev: []const u8 = "";
        var it = ix.iter();
        while (it.next()) |e| : (seen += 1) {
            try testing.expect(std.mem.order(u8, prev, e.key) != .gt);
            prev = e.key;
        }
        try testing.expectEqual(live, seen);

        // Every live document is reachable by a descent, not just by
        // walking the leaf chain: a bad separator breaks only the descent.
        var found: std.ArrayListUnmanaged(u64) = .empty;
        defer found.deinit(gpa);
        for (docs.items) |d| {
            if (!d.live) continue;
            if (rand.uintLessThan(u32, 100) >= 10) continue; // sample
            found.clearRetainingCapacity();
            try ix.lookup_eq(gpa, &.{.{ .string = d.s }}, &found);
            var hit = false;
            for (found.items) |got| {
                if (got == d.off) hit = true;
            }
            if (!hit) {
                std.debug.print("seed {d} op {d}: off {d} (key len {d}) not found by descent\n", .{
                    seed,
                    op,
                    d.off,
                    d.s.len,
                });
                return error.EntryUnreachable;
            }
        }
    }
}

test "mixed key sizes with removals" {
    for (0..6) |k| try run(@intCast(k + 1), 1500, 8000);
}

test "keys clustered around the inline limit" {
    for (0..4) |k| try run(@intCast(k + 100), 1200, 1200);
}