refactor: Wave 2 god-file splits — decode/protocol/config/conditions + tdbe::time lift (refs #500)

CHANGELOG.md

@@ -5,6 +5,40 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [8.0.36] - 2026-05-07
+
+### Changed
+
+- **`crates/thetadatadx/src/decode.rs` (2177 LoC) split into 7 modules**
+  under `mdds/decode/{error,headers,transport,extract,cell,v3}`. Pure
+  structural refactor; public API unchanged via `mdds::decode::*` re-exports.
+- **Eastern-time + DST primitives lifted to `tdbe::time`.**
+  `eastern_offset_ms`, `march_second_sunday_utc`, `november_first_sunday_utc`,
+  `april_first_sunday_utc`, `october_last_sunday_utc`, `civil_to_epoch_days`,
+  `timestamp_to_ms_of_day`, `timestamp_to_date` — single canonical module
+  reused by mdds, fpss, flatfiles. tdbe 0.12.9 → 0.12.10.
+- **`crates/thetadatadx/src/fpss/protocol.rs` (1613 LoC) split into 4 modules**
+  under `fpss/protocol/`. `mod.rs` keeps constants and re-exports;
+  `contract.rs` holds `Contract` + 6 constructors + `Display` + `FromStr` +
+  OCC-21 parser; `wire.rs` holds payload builders / parsers; `subscription.rs`
+  holds `SubscriptionKind`.
+- **`crates/thetadatadx/src/config.rs` (1396 LoC, 30 flat fields) refactored
+  into 7 nested typed sub-configs.** `DirectConfig` now contains `mdds`,
+  `fpss`, `reconnect`, `retry`, `auth`, `metrics`, `runtime`. Field-read
+  accessors preserved on `DirectConfig` for back-compat (`config.mdds_host()`
+  etc still work). Field-write callers must migrate to nested form
+  (`config.fpss.queue_depth = ...`). Adds `mdds.connect_timeout_secs`
+  (default 10s, covers prior LOW finding).
+- **`crates/tdbe/src/conditions.rs` (2749 LoC) refactored to TOML-driven
+  codegen.** Source-of-truth at `crates/tdbe/data/{trade,quote}_conditions.toml`
+  (149 + 75 entries). `crates/tdbe/build.rs` reads the TOMLs and emits
+  `crates/tdbe/src/conditions/tables_generated.rs` with compile-time
+  const arrays. Public surface unchanged; new `condition_tables_pin`
+  test pins 12 known entries against the const arrays for round-trip
+  protection.
+
+  Refs #500.
+
 ## [8.0.35] - 2026-05-07
 
 ### Documentation

crates/tdbe/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "tdbe"
-version = "0.12.9"
+version = "0.12.10"
 edition.workspace = true
 rust-version.workspace = true
 authors.workspace = true
@@ -11,6 +11,14 @@ repository.workspace = true
 license.workspace = true
 keywords = ["thetadata", "encoding", "market-data", "codec", "greeks"]
 categories = ["encoding", "finance"]
+build = "build.rs"
+include = [
+    "src/**/*.rs",
+    "data/*.toml",
+    "build.rs",
+    "Cargo.toml",
+    "README.md",
+]
 
 [lints]
 workspace = true
@@ -19,6 +27,13 @@ workspace = true
 sonic-rs = "0.5.8"
 thiserror = "2.0.18"
 
+[build-dependencies]
+# Build-time only: parses `data/{trade,quote}_conditions.toml` into the
+# committed `src/conditions/tables_generated.rs`. Does not ship to
+# runtime consumers -- `tdbe`'s runtime dep graph is unchanged.
+serde = { version = "1.0", features = ["derive"] }
+toml = "1.1"
+
 [dev-dependencies]
 criterion = { version = "0.8.2", features = ["html_reports"] }
 

crates/tdbe/build.rs

@@ -0,0 +1,186 @@
+//! Build-time codegen for trade and quote condition tables.
+//!
+//! Reads `data/trade_conditions.toml` (149 entries) and
+//! `data/quote_conditions.toml` (75 entries) and emits
+//! `src/conditions/tables_generated.rs` containing the
+//! `TRADE_CONDITIONS` and `QUOTE_CONDITIONS` const arrays.
+//!
+//! The generated file is committed so downstream consumers building
+//! `tdbe` from crates.io don't have to re-run codegen unless they edit
+//! the TOML source-of-truth files locally.
+
+use std::env;
+use std::fs;
+use std::path::PathBuf;
+
+use serde::Deserialize;
+use toml::Value;
+
+#[derive(Deserialize)]
+struct TradeFile {
+    trade: Vec<TradeRow>,
+}
+
+#[derive(Deserialize)]
+struct QuoteFile {
+    quote: Vec<QuoteRow>,
+}
+
+#[derive(Deserialize)]
+struct TradeRow {
+    code: i32,
+    name: String,
+    description: String,
+    cancel: bool,
+    late_report: bool,
+    auto_executed: bool,
+    open_report: bool,
+    volume: bool,
+    high: bool,
+    low: bool,
+    last: bool,
+}
+
+#[derive(Deserialize)]
+struct QuoteRow {
+    code: i32,
+    name: String,
+    description: String,
+    firm: bool,
+    halted: bool,
+}
+
+fn rust_string_literal(s: &str) -> String {
+    let mut out = String::with_capacity(s.len() + 2);
+    out.push('"');
+    for ch in s.chars() {
+        match ch {
+            '\\' => out.push_str("\\\\"),
+            '"' => out.push_str("\\\""),
+            '\n' => out.push_str("\\n"),
+            '\r' => out.push_str("\\r"),
+            '\t' => out.push_str("\\t"),
+            c if (c as u32) < 0x20 => {
+                use std::fmt::Write;
+                let _ = write!(out, "\\u{{{:x}}}", c as u32);
+            }
+            c => out.push(c),
+        }
+    }
+    out.push('"');
+    out
+}
+
+fn main() {
+    let manifest_dir = PathBuf::from(env::var("CARGO_MANIFEST_DIR").unwrap());
+    let trade_toml = manifest_dir.join("data/trade_conditions.toml");
+    let quote_toml = manifest_dir.join("data/quote_conditions.toml");
+    let out = manifest_dir.join("src/conditions/tables_generated.rs");
+
+    println!("cargo:rerun-if-changed=data/trade_conditions.toml");
+    println!("cargo:rerun-if-changed=data/quote_conditions.toml");
+    println!("cargo:rerun-if-changed=build.rs");
+
+    let trade_src = fs::read_to_string(&trade_toml)
+        .unwrap_or_else(|e| panic!("read {}: {e}", trade_toml.display()));
+    let quote_src = fs::read_to_string(&quote_toml)
+        .unwrap_or_else(|e| panic!("read {}: {e}", quote_toml.display()));
+
+    // Parse via `toml::Value` first to give precise spec errors, then re-deserialize
+    // into typed rows.
+    let _: Value = toml::from_str(&trade_src).expect("trade_conditions.toml: invalid TOML");
+    let _: Value = toml::from_str(&quote_src).expect("quote_conditions.toml: invalid TOML");
+
+    let trades: TradeFile =
+        toml::from_str(&trade_src).expect("trade_conditions.toml: schema mismatch");
+    let quotes: QuoteFile =
+        toml::from_str(&quote_src).expect("quote_conditions.toml: schema mismatch");
+
+    assert_eq!(
+        trades.trade.len(),
+        149,
+        "trade_conditions.toml must have exactly 149 entries"
+    );
+    assert_eq!(
+        quotes.quote.len(),
+        75,
+        "quote_conditions.toml must have exactly 75 entries"
+    );
+    for (i, t) in trades.trade.iter().enumerate() {
+        assert_eq!(
+            t.code as usize, i,
+            "trade_conditions.toml[{i}] has code {} (must equal index)",
+            t.code
+        );
+    }
+    for (i, q) in quotes.quote.iter().enumerate() {
+        assert_eq!(
+            q.code as usize, i,
+            "quote_conditions.toml[{i}] has code {} (must equal index)",
+            q.code
+        );
+    }
+
+    let mut s = String::new();
+    s.push_str("// @generated DO NOT EDIT — regenerated by build.rs from data/*.toml\n");
+    s.push_str("//\n");
+    s.push_str("// Source-of-truth: crates/tdbe/data/trade_conditions.toml\n");
+    s.push_str("//                  crates/tdbe/data/quote_conditions.toml\n\n");
+    s.push_str("use super::{QuoteCondition, TradeCondition};\n\n");
+
+    s.push_str("/// All 149 trade condition codes (0..148).\n");
+    s.push_str("pub const TRADE_CONDITIONS: [TradeCondition; 149] = [\n");
+    for t in &trades.trade {
+        s.push_str("    TradeCondition {\n");
+        s.push_str(&format!("        code: {},\n", t.code));
+        s.push_str(&format!(
+            "        name: {},\n",
+            rust_string_literal(&t.name)
+        ));
+        s.push_str(&format!(
+            "        description: {},\n",
+            rust_string_literal(&t.description)
+        ));
+        s.push_str(&format!("        cancel: {},\n", t.cancel));
+        s.push_str(&format!("        late_report: {},\n", t.late_report));
+        s.push_str(&format!("        auto_executed: {},\n", t.auto_executed));
+        s.push_str(&format!("        open_report: {},\n", t.open_report));
+        s.push_str(&format!("        volume: {},\n", t.volume));
+        s.push_str(&format!("        high: {},\n", t.high));
+        s.push_str(&format!("        low: {},\n", t.low));
+        s.push_str(&format!("        last: {},\n", t.last));
+        s.push_str("    },\n");
+    }
+    s.push_str("];\n\n");
+
+    s.push_str("/// All 75 quote condition codes (0..74).\n");
+    s.push_str("pub const QUOTE_CONDITIONS: [QuoteCondition; 75] = [\n");
+    for q in &quotes.quote {
+        s.push_str("    QuoteCondition {\n");
+        s.push_str(&format!("        code: {},\n", q.code));
+        s.push_str(&format!(
+            "        name: {},\n",
+            rust_string_literal(&q.name)
+        ));
+        s.push_str(&format!(
+            "        description: {},\n",
+            rust_string_literal(&q.description)
+        ));
+        s.push_str(&format!("        firm: {},\n", q.firm));
+        s.push_str(&format!("        halted: {},\n", q.halted));
+        s.push_str("    },\n");
+    }
+    s.push_str("];\n");
+
+    // Write only if changed, to avoid touching mtime and triggering downstream rebuilds.
+    let needs_write = match fs::read_to_string(&out) {
+        Ok(existing) => existing != s,
+        Err(_) => true,
+    };
+    if needs_write {
+        if let Some(parent) = out.parent() {
+            fs::create_dir_all(parent).expect("create conditions dir");
+        }
+        fs::write(&out, s).expect("write tables_generated.rs");
+    }
+}