Files
catena/parity/src/bin/regen.rs
T

241 lines
8.7 KiB
Rust
Raw Normal View History

//! Regenerates the golden files by running the Python oracles.
//!
//! Never run as part of a test: a golden file that regenerates itself when
//! it fails is a test that cannot fail. Run it deliberately, read the diff,
//! and commit the change with the reason.
//!
//! ```text
//! CATENA_PARITY_PYTHON=... CATENA_PARITY_PYTHONPATH=... \
//! cargo run -p parity --bin regen
//! ```
use std::process::ExitCode;
/// What one oracle run produces: the golden files it wrote, or why it could
/// not.
type Written = Result<Vec<String>, String>;
/// One oracle and the name it is reported under.
type Job = (&'static str, fn() -> Written);
fn main() -> ExitCode {
let jobs: [Job; 12] = [
("tokens", tokens),
("unescape", unescape),
("chunkmd", chunkmd),
("mdscrub", mdscrub),
("pdftriage", pdftriage),
("cuenorm", cuenorm),
("cueseg", cueseg),
2026-09-19 12:29:54 -04:00
("rrf", rrf),
("cuepack", cuepack),
("booksniff", booksniff),
("bibclean", bibclean),
("slug", slug),
];
for (name, job) in jobs {
match job() {
Ok(written) => {
for path in written {
eprintln!("wrote {path}");
}
}
Err(e) => {
eprintln!("regen {name}: {e}");
return ExitCode::FAILURE;
}
}
}
ExitCode::SUCCESS
}
fn tokens() -> Written {
let header = format!(
"# cl100k_base token counts, one per line of parity::sample::standard()\n\
# seed={:#018x} lines={}\n",
parity::sample::SEED,
parity::sample::LINES,
);
let counts = parity::run_oracle("tokens.py", &parity::sample::standard())?;
let path = parity::golden("tokens.counts");
std::fs::write(&path, format!("{header}{counts}")).map_err(|e| e.to_string())?;
Ok(vec![path.display().to_string()])
}
fn unescape() -> Written {
let dir = parity::golden("unescape");
std::fs::create_dir_all(&dir).map_err(|e| e.to_string())?;
let cases = parity::dir().join("cases/unescape/entities.txt");
let text = std::fs::read_to_string(&cases).map_err(|e| e.to_string())?;
let decoded = parity::run_oracle("unescape.py", &text)?;
let path = dir.join("entities.jsonl");
std::fs::write(&path, decoded).map_err(|e| e.to_string())?;
Ok(vec![path.display().to_string()])
}
fn slug() -> Written {
let dir = parity::golden("slug");
std::fs::create_dir_all(&dir).map_err(|e| e.to_string())?;
let cases = parity::dir().join("cases/slug/records.ndjson");
let cases = std::fs::read_to_string(&cases).map_err(|e| e.to_string())?;
let judgements = parity::run_oracle("slug.py", &cases)?;
let path = dir.join("records.ndjson");
std::fs::write(&path, judgements).map_err(|e| e.to_string())?;
Ok(vec![path.display().to_string()])
}
fn bibclean() -> Written {
let dir = parity::golden("bibclean");
std::fs::create_dir_all(&dir).map_err(|e| e.to_string())?;
let cases = parity::dir().join("cases/bibclean/records.ndjson");
let cases = std::fs::read_to_string(&cases).map_err(|e| e.to_string())?;
let judgements = parity::run_oracle("bibclean.py", &cases)?;
let path = dir.join("records.ndjson");
std::fs::write(&path, judgements).map_err(|e| e.to_string())?;
Ok(vec![path.display().to_string()])
}
fn booksniff() -> Written {
let dir = parity::golden("booksniff");
std::fs::create_dir_all(&dir).map_err(|e| e.to_string())?;
let cases = parity::dir().join("cases/booksniff/files.ndjson");
let cases = std::fs::read_to_string(&cases).map_err(|e| e.to_string())?;
let verdicts = parity::run_oracle("booksniff.py", &cases)?;
let path = dir.join("files.ndjson");
std::fs::write(&path, verdicts).map_err(|e| e.to_string())?;
Ok(vec![path.display().to_string()])
}
fn cuepack() -> Written {
let dir = parity::golden("cuepack");
std::fs::create_dir_all(&dir).map_err(|e| e.to_string())?;
let budgets = [("default", 75.0, 512), ("small", 12.0, 24)];
let mut written = Vec::new();
for case in parity::cases_with_extension("cuepack", "ndjson") {
let name = parity::case_name(&case);
let cues = std::fs::read_to_string(&case).map_err(|e| e.to_string())?;
for (set, seconds, max_tokens) in budgets {
let packed = parity::run_oracle_with(
"cuepack.py",
&[seconds.to_string(), max_tokens.to_string()],
&cues,
)?;
let path = dir.join(format!("{name}.{set}.ndjson"));
std::fs::write(&path, packed).map_err(|e| e.to_string())?;
written.push(path.display().to_string());
}
}
Ok(written)
}
2026-09-19 12:29:54 -04:00
fn rrf() -> Written {
let dir = parity::golden("rrf");
std::fs::create_dir_all(&dir).map_err(|e| e.to_string())?;
let mut written = Vec::new();
for case in parity::cases_with_extension("rrf", "ndjson") {
let hits = std::fs::read_to_string(&case).map_err(|e| e.to_string())?;
let fused = parity::run_oracle("rrf.py", &hits)?;
let path = dir.join(format!("{}.ndjson", parity::case_name(&case)));
std::fs::write(&path, fused).map_err(|e| e.to_string())?;
written.push(path.display().to_string());
}
Ok(written)
}
fn cueseg() -> Written {
let dir = parity::golden("cueseg");
std::fs::create_dir_all(&dir).map_err(|e| e.to_string())?;
let table = parity::dir().join("cases/cueseg/durations.json");
let table = std::fs::read_to_string(&table).map_err(|e| e.to_string())?;
let durations: std::collections::BTreeMap<String, std::collections::BTreeMap<String, f64>> =
serde_json::from_str(&table).map_err(|e| e.to_string())?;
let mut written = Vec::new();
for case in parity::cases_with_extension("cueseg", "ndjson") {
let name = parity::case_name(&case);
let Some(spans) = durations.get(&name) else {
continue;
};
let cues = std::fs::read_to_string(&case).map_err(|e| e.to_string())?;
for (span, duration) in spans {
let chapters = parity::run_oracle_with("cueseg.py", &[format!("{duration}")], &cues)?;
let path = dir.join(format!("{name}.{span}.ndjson"));
std::fs::write(&path, chapters).map_err(|e| e.to_string())?;
written.push(path.display().to_string());
}
}
Ok(written)
}
fn cuenorm() -> Written {
let dir = parity::golden("cuenorm");
std::fs::create_dir_all(&dir).map_err(|e| e.to_string())?;
let mut written = Vec::new();
for case in parity::cases_with_extension("cuenorm", "srt") {
let content = std::fs::read_to_string(&case).map_err(|e| e.to_string())?;
let cues = parity::run_node_oracle("cuenorm.mjs", &content)?;
let path = dir.join(format!("{}.ndjson", parity::case_name(&case)));
std::fs::write(&path, cues).map_err(|e| e.to_string())?;
written.push(path.display().to_string());
}
Ok(written)
}
fn pdftriage() -> Written {
let dir = parity::golden("pdftriage");
std::fs::create_dir_all(&dir).map_err(|e| e.to_string())?;
let cases = parity::dir().join("cases/pdftriage/samples.ndjson");
let text = std::fs::read_to_string(&cases).map_err(|e| e.to_string())?;
let measured = parity::run_oracle("pdftriage.py", &text)?;
let path = dir.join("samples.ndjson");
std::fs::write(&path, measured).map_err(|e| e.to_string())?;
Ok(vec![path.display().to_string()])
}
fn mdscrub() -> Written {
let dir = parity::golden("mdscrub");
std::fs::create_dir_all(&dir).map_err(|e| e.to_string())?;
let mut written = Vec::new();
for case in parity::cases("mdscrub") {
let markdown = std::fs::read_to_string(&case).map_err(|e| e.to_string())?;
let name = parity::case_name(&case);
let cleaned = parity::run_oracle("mdscrub.py", &markdown)?;
let path = dir.join(format!("{name}.md"));
std::fs::write(&path, cleaned).map_err(|e| e.to_string())?;
written.push(path.display().to_string());
}
Ok(written)
}
fn chunkmd() -> Written {
let dir = parity::golden("chunkmd");
std::fs::create_dir_all(&dir).map_err(|e| e.to_string())?;
let mut written = Vec::new();
for case in parity::cases("chunkmd") {
let markdown = std::fs::read_to_string(&case).map_err(|e| e.to_string())?;
for (set, budgets) in parity::budgets::SETS {
let records = parity::run_oracle_with(
"chunkmd.py",
&parity::budgets::as_args(budgets),
&markdown,
)?;
let path = dir.join(format!("{}.{set}.ndjson", parity::case_name(&case)));
std::fs::write(&path, records).map_err(|e| e.to_string())?;
written.push(path.display().to_string());
}
}
Ok(written)
}