3fac029a71
Each *-conformance/README.md now has a line that begins **Provenance.**: the generator that writes the corpus and its input, and for an input not generated here its source and licence. OER/2's corpus is settled and left as it is. byte-exact-conformance and quantum-ops-conformance get a README. wai-rs/tests/vectors/README.md gives a row per vector directory. Where the staged-delivery, staged-measurement and telemetry READMEs called their content "synthetic", that sentence is now their provenance line. Two vectors are recorded as not generated, from the provenance audit: int_video's video_real (a pan over a third-party picture) and neural-conformance's photo (a third-party picture, with a decoder trained on unrecorded images). Their lines say so and that they are to be replaced; the photo bullet no longer names the picture's source product. tests/corpus_provenance.rs requires the line in every corpus and a row for every vector directory; CI runs it with the carriage tests. CONTRIBUTING states the rule: corpus content is generated here, or recorded with a licence that permits redistribution, and a word like "synthetic" is not a provenance line. Co-Authored-By: Claude Opus 5.5 <[email protected]>
73 lines
2.9 KiB
Rust
73 lines
2.9 KiB
Rust
//! Every corpus states where its content comes from (CONTRIBUTING, *Corpus content*).
|
|
//!
|
|
//! Each `wai/*-conformance/` directory has a `README.md` with a line that begins
|
|
//! `**Provenance.**`, and `tests/vectors/README.md` has a row for every directory under
|
|
//! `tests/vectors/` whose provenance cell is not empty. A provenance line names the
|
|
//! generator that writes the content and the generator's input; an input not generated
|
|
//! in this repository is named with its source and its licence. The test holds the
|
|
//! line's presence, not its truth: that is a reviewer's, and for audio also
|
|
//! `tools/wai_audio_provenance_check.py`'s.
|
|
|
|
use std::path::PathBuf;
|
|
|
|
fn wai() -> PathBuf {
|
|
PathBuf::from(env!("CARGO_MANIFEST_DIR")).join("..")
|
|
}
|
|
|
|
/// The line a README states its provenance in, if it has one with text after the label.
|
|
fn provenance_line(readme: &str) -> Option<&str> {
|
|
readme
|
|
.lines()
|
|
.map(str::trim_start)
|
|
.find(|l| l.starts_with("**Provenance.**") && l.len() > "**Provenance.**".len() + 1)
|
|
}
|
|
|
|
#[test]
|
|
fn every_conformance_corpus_states_its_provenance() {
|
|
// OER/2 is settled: no change edits its documents or its corpus.
|
|
let settled = ["oer-conformance"];
|
|
let mut dirs: Vec<String> = std::fs::read_dir(wai())
|
|
.unwrap()
|
|
.flatten()
|
|
.filter(|e| e.path().is_dir())
|
|
.map(|e| e.file_name().to_string_lossy().into_owned())
|
|
.filter(|n| n.ends_with("-conformance"))
|
|
.collect();
|
|
dirs.sort();
|
|
assert!(dirs.len() > 10, "found {} corpora", dirs.len());
|
|
let mut missing = Vec::new();
|
|
for d in &dirs {
|
|
if settled.contains(&d.as_str()) {
|
|
continue;
|
|
}
|
|
match std::fs::read_to_string(wai().join(d).join("README.md")) {
|
|
Ok(text) if provenance_line(&text).is_some() => {}
|
|
Ok(_) => missing.push(format!("{d}/README.md has no `**Provenance.**` line")),
|
|
Err(_) => missing.push(format!("{d} has no README.md")),
|
|
}
|
|
}
|
|
assert!(missing.is_empty(), "corpora without a provenance line:\n {}", missing.join("\n "));
|
|
}
|
|
|
|
#[test]
|
|
fn every_vector_directory_states_its_provenance() {
|
|
let root = wai().join("wai-rs/tests/vectors");
|
|
let index = std::fs::read_to_string(root.join("README.md")).expect("tests/vectors/README.md");
|
|
let mut dirs: Vec<String> = std::fs::read_dir(&root)
|
|
.unwrap()
|
|
.flatten()
|
|
.filter(|e| e.path().is_dir())
|
|
.map(|e| e.file_name().to_string_lossy().into_owned())
|
|
.collect();
|
|
dirs.sort();
|
|
let mut missing = Vec::new();
|
|
for d in &dirs {
|
|
// A row: | `<dir>/` | <provenance> | …
|
|
let row = index.lines().find(|l| l.trim_start().starts_with(&format!("| `{d}/` |")));
|
|
let cell = row.and_then(|r| r.split('|').nth(2)).map(str::trim).unwrap_or("");
|
|
if cell.is_empty() {
|
|
missing.push(d.clone());
|
|
}
|
|
}
|
|
assert!(missing.is_empty(), "tests/vectors/README.md states no provenance for: {missing:?}");
|
|
}
|