Brummel/Aura
1
0
Fork 0
Code Issues 30 Pull Requests Actions Packages Projects Releases Wiki Activity

test(cli): synthetic per-test M1 archive — no-window generalize tests go hostless

Browse Source 
The two generalize E2E tests whose property is no-window span
resolution (shared-window fallback, intersection semantics) no longer
stream the 6.6 GB host archive: fresh_project_with_data() generates a
deterministic two-symbol M1 archive (SYMA 2024-01..08, SYMB 2024-03..06
strictly inside it, so the intersection differs from symbols[0]'s
window on both bounds) in the exact zip/48-byte-record format
data-server reads, plus geometry sidecars, under the per-test project's
paths.data. Both tests drop their local_data_present gates — they now
run on any host, data mount or not.

~35s and ~50s become 0.74s and 1.14s; the full cli_run binary lands at
~25s (211s at the branch base). Full workspace suite: 247s -> 45.7s.

refs #250
This commit is contained in:
Claude
2026-07-13 15:24:00 +02:00
parent 25b8354959
commit c31e946bb7
4 changed files with 226 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files
crates/aura-cli/tests/common/mod.rs
+193 -18
View File
@@ -52,6 +52,40 @@ impl Drop for FreshProject {
}
}
/// Mints a unique, empty tempdir under `std::env::temp_dir()`, named
/// `aura-e2e-<pid>-<counter>` so concurrent test threads (same process) and
/// concurrent `cargo test` processes never collide.
fn mint_tempdir() -> PathBuf {
static COUNTER: AtomicUsize = AtomicUsize::new(0);
let root = std::env::temp_dir().join(format!(
"aura-e2e-{}-{}",
std::process::id(),
COUNTER.fetch_add(1, Ordering::Relaxed)
));
std::fs::create_dir_all(&root).expect("create fresh project tempdir");
root
}
/// Writes the `Aura.toml` + `demo_signal.json` common to every fresh project:
/// an absolute `[nodes]` pointer at the shared, once-built fixture crate, and
/// — when `data_dir` is `Some` — a `[paths] data` override pointing at it
/// (relative, resolved against the invocation cwd, which every test that uses
/// this always sets to `root` itself via `.current_dir`).
fn write_project_files(root: &Path, data_dir: Option<&str>) {
let fixture = built_project();
let data_line = data_dir.map(|d| format!("data = \"{d}\"\n")).unwrap_or_default();
std::fs::write(
root.join("Aura.toml"),
format!(
"[paths]\nruns = \"runs\"\n{data_line}\n[nodes]\ncrates = [\"{}\"]\n",
fixture.display()
),
)
.expect("write fresh project Aura.toml");
std::fs::copy(fixture.join("demo_signal.json"), root.join("demo_signal.json"))
.expect("copy demo_signal.json into the fresh project");
}
/// Mint a unique tempdir holding a 2-line data-level project (`Aura.toml`
/// with an absolute `[nodes]` pointer at the shared, once-built fixture
/// crate) plus a copy of `demo_signal.json`. Every test gets its own `runs/`
@@ -60,24 +94,26 @@ impl Drop for FreshProject {
/// whole test body: `let (dir, _g) = fresh_project();`.
#[allow(dead_code)]
pub fn fresh_project() -> (PathBuf, FreshProject) {
static COUNTER: AtomicUsize = AtomicUsize::new(0);
let root = std::env::temp_dir().join(format!(
"aura-e2e-{}-{}",
std::process::id(),
COUNTER.fetch_add(1, Ordering::Relaxed)
));
std::fs::create_dir_all(&root).expect("create fresh project tempdir");
let fixture = built_project();
std::fs::write(
root.join("Aura.toml"),
format!(
"[paths]\nruns = \"runs\"\n\n[nodes]\ncrates = [\"{}\"]\n",
fixture.display()
),
)
.expect("write fresh project Aura.toml");
std::fs::copy(fixture.join("demo_signal.json"), root.join("demo_signal.json"))
.expect("copy demo_signal.json into the fresh project");
let root = mint_tempdir();
write_project_files(&root, None);
(root.clone(), FreshProject { root })
}
/// Like [`fresh_project`], but additionally generates a tiny synthetic M1
/// archive under `<root>/data/` (two symbols, `SYMA` spanning 2024-01..08 and
/// `SYMB` spanning 2024-03..06 — `SYMB` lies strictly inside `SYMA`) and
/// points `[paths] data` at it. For tests whose property is archive-window
/// (span) semantics, not archive size — no host tick-data mount needed, and
/// no `--real`-symbol data refusal is ever reachable, so gates on data
/// presence are dead code once a test switches to this helper (#250).
#[allow(dead_code)]
pub fn fresh_project_with_data() -> (PathBuf, FreshProject) {
let root = mint_tempdir();
write_project_files(&root, Some("data"));
let data_dir = root.join("data");
std::fs::create_dir_all(&data_dir).expect("create synthetic archive dir");
synthetic_data::write_symbol_archive(&data_dir, "SYMA", (2024, 1), (2024, 8));
synthetic_data::write_symbol_archive(&data_dir, "SYMB", (2024, 3), (2024, 6));
(root.clone(), FreshProject { root })
}
@@ -108,3 +144,142 @@ impl Drop for ScratchGuard {
}
}
}
/// A tiny, deterministic synthetic M1 archive generator: hand-packs the exact
/// on-disk format `data-server` reads (its `loader.rs` and `records.rs`) —
/// one zip per `SYMBOL_YYYY_MM.m1` holding a single `.bin` entry of packed
/// 48-byte `RawM1Record`s, plus a `SYMBOL.meta.json` geometry sidecar — so
/// the two no-window `generalize` E2E tests get a real, tiny, hostless
/// archive instead of streaming the 6.6 GB host archive (#250).
#[allow(dead_code)]
mod synthetic_data {
use std::io::Write;
use std::path::Path;
/// Days since the Unix epoch for a proleptic-Gregorian civil date.
/// Howard Hinnant's `days_from_civil` — dependency-free calendar math so
/// this module needs no `chrono` (data-server's own dependency, not
/// aura-cli's).
fn days_from_civil(y: i32, m: u32, d: u32) -> i64 {
let y = i64::from(if m <= 2 { y - 1 } else { y });
let era = if y >= 0 { y } else { y - 399 } / 400;
let yoe = y - era * 400; // [0, 399]
let mp = (i64::from(m) + 9) % 12; // [0, 11], Mar=0 .. Feb=11
let doy = (153 * mp + 2) / 5 + i64::from(d) - 1; // [0, 365]
let doe = yoe * 365 + yoe / 4 - yoe / 100 + doy; // [0, 146096]
era * 146_097 + doe - 719_468
}
/// Unix milliseconds at `y-m-d hh:mm:00` UTC.
fn unix_ms(y: i32, m: u32, d: u32, hh: u32, mm: u32) -> i64 {
days_from_civil(y, m, d) * 86_400_000 + (i64::from(hh) * 3600 + i64::from(mm) * 60) * 1000
}
/// 0 = Sunday .. 6 = Saturday (1970-01-01 was a Thursday, day 0).
fn weekday(y: i32, m: u32, d: u32) -> i64 {
(days_from_civil(y, m, d) % 7 + 4 + 7) % 7
}
fn days_in_month(y: i32, m: u32) -> u32 {
match m {
1 | 3 | 5 | 7 | 8 | 10 | 12 => 31,
4 | 6 | 9 | 11 => 30,
2 if (y % 4 == 0 && y % 100 != 0) || y % 400 == 0 => 29,
2 => 28,
_ => unreachable!("month out of range: {m}"),
}
}
/// A deterministic price at continuous minute offset `t` (minutes since
/// 2024-01-01T00:00 UTC, shared across both symbols so their overlapping
/// span carries the same underlying curve): a gentle upward trend plus a
/// 180-minute sine — short enough against a day's 480 tradeable minutes to
/// produce several SMA(3)/SMA(12) crossovers per day.
fn price_at(t_minutes: f64) -> f64 {
let hours = t_minutes / 60.0;
100.0 + 0.01 * hours + 5.0 * (2.0 * std::f64::consts::PI * t_minutes / 180.0).sin()
}
/// Packs one `RawM1Record`-shaped 48-byte little-endian record: `time`
/// (Delphi `TDateTime`, days since 1899-12-30 — the inverse of
/// `data_server::records::delphi_to_unix_ms`), `open/high/low/close`,
/// `spread` (f32), `volume` (i32).
fn pack_record(unix_ms_time: i64, open: f64, high: f64, low: f64, close: f64) -> [u8; 48] {
const DELPHI_EPOCH_OFFSET_DAYS: f64 = 25569.0;
const MS_PER_DAY: f64 = 86_400_000.0;
let dt = unix_ms_time as f64 / MS_PER_DAY + DELPHI_EPOCH_OFFSET_DAYS;
let mut rec = [0u8; 48];
rec[0..8].copy_from_slice(&dt.to_le_bytes());
rec[8..16].copy_from_slice(&open.to_le_bytes());
rec[16..24].copy_from_slice(&high.to_le_bytes());
rec[24..32].copy_from_slice(&low.to_le_bytes());
rec[32..40].copy_from_slice(&close.to_le_bytes());
rec[40..44].copy_from_slice(&0.5_f32.to_le_bytes());
rec[44..48].copy_from_slice(&100_i32.to_le_bytes());
rec
}
/// One month's worth of weekday, 08:00-16:00 UTC, 1-minute bars (~10k).
fn month_records(year: i32, month: u32) -> Vec<[u8; 48]> {
let epoch_ms = unix_ms(2024, 1, 1, 0, 0);
let mut records = Vec::new();
for day in 1..=days_in_month(year, month) {
if !(1..=5).contains(&weekday(year, month, day)) {
continue; // weekend
}
for hh in 8..16 {
for mm in 0..60 {
let ms = unix_ms(year, month, day, hh, mm);
let t = (ms - epoch_ms) as f64 / 60_000.0;
let (open, close) = (price_at(t), price_at(t + 1.0));
let high = open.max(close) + 0.2;
let low = open.min(close) - 0.2;
records.push(pack_record(ms, open, high, low, close));
}
}
}
records
}
/// Writes one `SYMBOL_YYYY_MM.m1` zip (a single `<SYMBOL>.bin` entry of
/// packed records — mirrors `data-server`'s own `create_test_m1_zip` test
/// helper) under `data_dir`.
fn write_month_zip(data_dir: &Path, symbol: &str, year: i32, month: u32) {
let path = data_dir.join(format!("{symbol}_{year:04}_{month:02}.m1"));
let file = std::fs::File::create(&path).expect("create synthetic m1 zip");
let mut zip = zip::ZipWriter::new(file);
zip.start_file::<String, ()>(format!("{symbol}.bin"), Default::default())
.expect("start synthetic m1 zip entry");
for rec in month_records(year, month) {
zip.write_all(&rec).expect("write synthetic m1 record");
}
zip.finish().expect("finish synthetic m1 zip");
}
/// Writes every month in `[from, to]` (inclusive, `(year, month)` pairs)
/// for `symbol`, plus its `<SYMBOL>.meta.json` geometry sidecar —
/// GER40-shaped (digits 1, pip/tick/lot sized like an index CFD) so the
/// R/stop machinery never hits "no recorded geometry".
pub fn write_symbol_archive(data_dir: &Path, symbol: &str, from: (i32, u32), to: (i32, u32)) {
let (mut y, mut m) = from;
loop {
write_month_zip(data_dir, symbol, y, m);
if (y, m) == to {
break;
}
m += 1;
if m > 12 {
m = 1;
y += 1;
}
}
std::fs::write(
data_dir.join(format!("{symbol}.meta.json")),
format!(
"{{\"schemaVersion\":2,\"symbol\":\"{symbol}\",\"digits\":1,\"pipSize\":1,\
\"tickSize\":0.1,\"lotSize\":1,\"baseAsset\":\"{symbol}\",\"quoteAsset\":\"EUR\"}}"
),
)
.expect("write synthetic geometry sidecar");
}
}