diff --git a/crates/weksa/src/context.rs b/crates/weksa/src/context.rs index 0ecd067..5b64758 100644 --- a/crates/weksa/src/context.rs +++ b/crates/weksa/src/context.rs @@ -759,6 +759,9 @@ impl Prompt { } } +#[cfg(test)] +mod mutants; + #[cfg(test)] mod tests { use super::*; diff --git a/crates/weksa/src/context/mutants.rs b/crates/weksa/src/context/mutants.rs new file mode 100644 index 0000000..876816f --- /dev/null +++ b/crates/weksa/src/context/mutants.rs @@ -0,0 +1,14 @@ +//! Pins for private reach of `context.rs` that no run can produce. + +use super::*; + +/// A corpus with no live Train item of the panel's languages holds an empty +/// train. (A run refuses a panel without Train items at open, so only the +/// builder shows it.) +#[test] +fn no_train_item_of_the_panel_is_an_empty_train() { + let dir = tempfile::tempdir().unwrap(); + let corpus = CorpusStore::open(&dir.path().join("c.cc")).unwrap(); + let train = TrainItems::from_corpus(&corpus, &["en-US".to_string()]).unwrap(); + assert_eq!((train.len(), train.is_empty()), (0, true)); +} diff --git a/crates/weksa/src/encode.rs b/crates/weksa/src/encode.rs index ed3f496..500d575 100644 --- a/crates/weksa/src/encode.rs +++ b/crates/weksa/src/encode.rs @@ -566,6 +566,9 @@ pub fn packet_id(item: &CorpusItemId, rev: u32, encoder: &EncoderId) -> PacketId PacketId::parse(&format!("packet:{}", hex16(digest))).expect("a packet id is well formed") } +#[cfg(test)] +mod mutants; + #[cfg(test)] mod tests { use super::*; diff --git a/crates/weksa/src/encode/mutants.rs b/crates/weksa/src/encode/mutants.rs new file mode 100644 index 0000000..344c2a9 --- /dev/null +++ b/crates/weksa/src/encode/mutants.rs @@ -0,0 +1,13 @@ +//! Pins for `unmark` that the import door only reaches through a whole work. + +use super::*; + +/// A form that opens another markup is malformed, though its entity id is +/// sound: the model wrote a nested or unclosed mark, not a name. +#[test] +fn a_form_that_opens_a_mark_is_malformed() { + assert_eq!(unmark("[[entity:orsa|Or[[sa]] came"), None); + // The same line without the nested opener unmarks. + let (plain, names) = unmark("[[entity:orsa|Orsa]] came").unwrap(); + assert_eq!((plain.as_str(), names.len()), ("Orsa came", 1)); +} diff --git a/crates/weksa/src/run.rs b/crates/weksa/src/run.rs index 7339a6e..15216d6 100644 --- a/crates/weksa/src/run.rs +++ b/crates/weksa/src/run.rs @@ -3112,6 +3112,9 @@ fn discard_inventory(dir: &Path) { } } +#[cfg(test)] +mod mutants; + #[cfg(test)] mod tests { use super::*; diff --git a/crates/weksa/src/run/mutants.rs b/crates/weksa/src/run/mutants.rs new file mode 100644 index 0000000..75b1e63 --- /dev/null +++ b/crates/weksa/src/run/mutants.rs @@ -0,0 +1,21 @@ +//! Pins for private functions of `run.rs` that the doors reach only through a +//! whole run. + +use super::*; + +/// A line is probed only when it has at least four words, and then it is +/// split in two near its byte middle, the pieces trimmed. +#[test] +fn a_recall_line_splits_from_four_words_and_not_before() { + assert_eq!(recall_split("one two three"), None); + assert_eq!(recall_split(""), None); + assert_eq!( + recall_split("one two three four"), + Some(("one two".to_string(), "three four".to_string())) + ); + // No spaces: each ideograph is a word, the split falls at the middle. + assert_eq!( + recall_split("天地不仁以万物为刍狗"), + Some(("天地不仁以".to_string(), "万物为刍狗".to_string())) + ); +} diff --git a/crates/weksa/tests/mutants_c.rs b/crates/weksa/tests/mutants_c.rs new file mode 100644 index 0000000..70c499d --- /dev/null +++ b/crates/weksa/tests/mutants_c.rs @@ -0,0 +1,136 @@ +//! Pins for behaviour of `context.rs`, `encode.rs` and `run.rs` found unpinned +//! by mutation testing. Each test states what the code does in domain terms. + +mod common; + +use std::path::{Path, PathBuf}; + +use weksa::context::Prompt; +use weksa::entity::{Entity, EntityOrigin, LanguageForms}; +use weksa::packet::{EntityId, proof_packet}; +use weksa::{CorpusItemId, CorpusStore, EntityForms, EntityStore, InventoryStore, PacketStore}; + +fn data(sub: &str) -> PathBuf { + Path::new(env!("CARGO_MANIFEST_DIR")) + .join("../../data") + .join(sub) +} + +struct Held(Vec); + +impl EntityForms for Held { + fn entity(&self, id: &EntityId) -> anyhow::Result> { + Ok(self.0.iter().find(|e| &e.id == id).cloned()) + } +} + +fn spoken(slug: &str, form: &str) -> Entity { + Entity { + id: EntityId::parse(&format!("entity:{slug}")).unwrap(), + forms: vec![LanguageForms { + language: "en-US".into(), + forms: vec![form.into()], + pronunciation: None, + }], + origin: EntityOrigin::Cast { + persona: slug.into(), + fixture: "f.yaml".into(), + }, + } +} + +/// A speaker whom no referent cites contributes no entry to the lowering +/// prompt, even when another entity is cited: only the cited entity is listed. +#[test] +fn an_uncited_speaker_is_absent_from_the_lowering_prompt() { + let cast_inv = InventoryStore::open(&data("interlingua/inventory.cc")).unwrap(); + let entities = EntityStore::open(&data("entity/entity.cc")).unwrap(); + let corpus = CorpusStore::open(&data("corpus/corpus.cc")).unwrap(); + let dir = tempfile::tempdir().unwrap(); + let view = PacketStore::open(&dir.path().join("p.cc")) + .unwrap() + .admit(proof_packet(), &cast_inv, &corpus, &entities) + .unwrap(); + let state = weksa::SpeakerStateStore::open(&dir.path().join("s.cc")).unwrap(); + let view = view + .with_scene(&cast_inv.inventory().unwrap(), &state, &corpus) + .unwrap(); + let held = Held(vec![ + spoken("nibu", "Nibu"), + spoken("other", "SPEAKERCANARY"), + ]); + let item = CorpusItemId::parse("item:nibu:1").unwrap(); + let speaker = EntityId::parse("entity:other").unwrap(); + let prompt = Prompt::lower( + &view, + &item, + &speaker, + "en-US", + &cast_inv.inventory().unwrap(), + &held, + &weksa::Ontology::empty(), + ) + .unwrap(); + let text = prompt.text(); + assert!( + text.contains("\n\nentities: {\"entity:nibu\":[\"Nibu\"]}\n\n"), + "{text}" + ); + assert!(!text.contains("SPEAKERCANARY"), "{text}"); +} + +/// A run refuses a panel language that lacks a live Train or a live Validation +/// item: one no item carries, one with only a Test item, one with only Train. +#[test] +fn a_panel_language_no_item_carries_is_refused_at_open() { + let dir = tempfile::tempdir().unwrap(); + let d = dir.path(); + // Builds the corpus, entity and ontology stores the run reads. + drop(common::run_over(d)); + let entities = common::entities_in(d); + let mut corpus = CorpusStore::open(&d.join("c.cc")).unwrap(); + for (key, language, bucket) in [("item:jp:1", "ja-JP", 90), ("item:pt:1", "pt-BR", 10)] { + let mut item = common::item_in( + key, + &format!("line of {key}"), + &common::group_in_bucket(bucket), + common::cast(), + ); + item.language = language.into(); + corpus.add(item, &entities).unwrap(); + } + drop(corpus); + let create = |panel: &[&str]| { + weksa::run::RunStores::create( + &d.join(format!("run-{}", panel.join("-"))), + "t", + weksa::run::RunPaths { + corpus: &d.join("c.cc"), + inventory: &d.join("i.cc"), + entities: &d.join("entities.cc"), + ontology: &d.join("ontology.cc"), + speaker_state: &common::speaker_state_beside(&d.join("ontology.cc")), + }, + "fake-model", + "bag", + weksa::run::LowererReach::ToolLessRelay, + weksa::corpus::ModelFamily::Unrecorded, + &panel.iter().map(|t| (*t).to_string()).collect::>(), + ) + }; + assert!(create(&["en-US"]).is_ok()); + for panel in [&["ja-JP"][..], &["pt-BR"], &["xx-XX"], &["en-US", "ja-JP"]] { + assert!( + matches!(create(panel), Err(weksa::run::RunError::Panel)), + "{panel:?}" + ); + } +} + +/// A run keeps its recall probes in `recall` under its own root. +#[test] +fn a_run_keeps_its_recall_under_its_root() { + let dir = tempfile::tempdir().unwrap(); + let run = common::run_over(dir.path()); + assert_eq!(run.recall_dir(), dir.path().join("run").join("recall")); +}