//! 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:?}");
}