diff --git a/crates/sqllogictest/test_files/README.md b/crates/sqllogictest/test_files/README.md index 980b300..a66ac51 100644 --- a/crates/sqllogictest/test_files/README.md +++ b/crates/sqllogictest/test_files/README.md @@ -94,6 +94,20 @@ for example `cargo test -p datafusion-spark-sqllogictest -- math/expm1 --mode=ev A record that cannot run in `evaluate` mode yet is marked `skipif evaluate`, with a comment that links the issue. Remove the marks when the issue is fixed. +## Filling in expected results + +Pass `--complete` to rewrite the expected output of the matching files with the +results of running them: + +```shell +cargo test -p datafusion-spark-sqllogictest -- math/expm1 --complete +``` + +Write the queries with an empty result after `----`, run with `--complete`, then +review the diff. It records whatever the functions return, so check the results against +Spark (see below) before committing them. Completion runs in `simplify` mode unless +`--mode` says otherwise. A normal run afterwards checks that both modes agree. + ## Checking the expected results against Spark The expected results in these files come from DataFusion. To compare them with diff --git a/crates/sqllogictest/tests/sqllogictests.rs b/crates/sqllogictest/tests/sqllogictests.rs index 0c2d9db..11d7e07 100644 --- a/crates/sqllogictest/tests/sqllogictests.rs +++ b/crates/sqllogictest/tests/sqllogictests.rs @@ -21,11 +21,13 @@ //! that links the issue. Prefer it over `onlyif simplify`, because the PySpark runner //! skips every `onlyif` record that is not for `spark`. //! -//! Usage: `cargo test -p datafusion-spark-sqllogictest -- [FILTER]... [--mode=MODE]`, where -//! each `FILTER` is a substring of the test file path and `MODE` is `simplify` or -//! `evaluate` (both by default). Pass `--complete` to rewrite the expected results in the -//! matching files with the actual results instead of checking them. It runs only in -//! `simplify` mode, so each file is rewritten once. +//! Usage: `cargo test -p datafusion-spark-sqllogictest -- [FILTER]... [--mode=MODE] +//! [--complete]`, where each `FILTER` is a substring of the test file path and `MODE` is +//! `simplify` or `evaluate` (both by default). +//! +//! `--complete` rewrites the expected output of each matching file with the results of +//! running it, in `simplify` mode unless `--mode` says otherwise. Review the diff before +//! committing it, since it records whatever the functions return. mod engine; @@ -174,12 +176,15 @@ fn new_context(mode: Mode) -> SessionContext { SessionContext::new_with_state(builder.build()) } +/// Runs the file at `path`, or with `complete`, rewrites its expected output with the +/// results of this run. async fn run_file(path: PathBuf, mode: Mode, complete: bool) -> Result<(), String> { let mut runner = sqllogictest::Runner::new(|| async { Ok(SparkDataFusion::new(new_context(mode))) }); runner.add_label(mode.label()); if complete { + // Records skipped for this mode's label are written back unchanged. return runner .update_test_file( &path, @@ -205,6 +210,8 @@ async fn main() -> ExitCode { let args: Vec = std::env::args().skip(1).collect(); let complete = args.iter().any(|arg| arg == "--complete"); let modes: Vec = match args.iter().find_map(|arg| arg.strip_prefix("--mode=")) { + // Completion writes one set of results, so it runs one mode. Both modes must + // produce the same results, which a normal run then checks. None if complete => vec![Mode::Simplify], None => Mode::ALL.to_vec(), Some(name) => match Mode::ALL.into_iter().find(|m| m.label() == name) { @@ -248,6 +255,7 @@ async fn main() -> ExitCode { // A panic in one file (for example a function indexing past the end of an // array) is reported as that file failing, so the other results still print. match handle.await.map_err(|e| e.to_string()).and_then(|r| r) { + Ok(()) if complete => println!("COMPLETED {name}"), Ok(()) => println!("PASS {name}"), Err(e) => { failed += 1;