Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
aef53a4c48 |
55 changed files with 1944 additions and 5890 deletions
1
.gitignore
vendored
1
.gitignore
vendored
|
|
@ -22,3 +22,4 @@ build/
|
|||
.venv/
|
||||
venv/
|
||||
target/
|
||||
tools/show-working/out/
|
||||
|
|
|
|||
|
|
@ -60,4 +60,4 @@ language-project truth.
|
|||
`CARGO_HOME=/var/lib/mind-weksa-self/cargo-home cargo test --workspace`.
|
||||
- `weksa packet proof <store>` admits the nibu proof packet under the key
|
||||
`packet:6e6962752d303031` (hex of `nibu-001`), not `nibu-proof-001`. Use that key
|
||||
with `weksa pronounce <store> <key>`.
|
||||
with `weksa lower <store> <key>`.
|
||||
|
|
|
|||
|
|
@ -5,8 +5,8 @@ culture, and constraint, and the planned lowerer that turns an agent's
|
|||
meaning packet into the reader's display language.
|
||||
|
||||
**What is valuable here.** The interlingua standard and the lowering design: a
|
||||
meaning packet owns what is meant, the scene state (live: `weksa scene put|dump`, labelled by the rule in
|
||||
`docs/scene-annotation.md`; speaker documents are planned) owns the speaker's relation to the addressee, which selects register,
|
||||
meaning packet owns what is meant, the scene state (live: `weksa scene put|dump`; speaker
|
||||
documents are planned) owns the speaker's relation to the addressee, which selects register,
|
||||
address and politeness, and a lowerer owns surface text and leaves a trace.
|
||||
|
||||
**The problem it solves.** An agent's outward speech today is one English
|
||||
|
|
@ -35,8 +35,8 @@ measured.
|
|||
- `settings/`: setting-specific proving grounds for language projects.
|
||||
|
||||
**Live versus planned.** Live: docs, fixtures, examples, ontology data and the
|
||||
packet crate `crates/weksa`, including `weksa pronounce` (the ruled IPA and phones
|
||||
of the entities a packet cites), `weksa score`, and the golf loop's round and edit-accept
|
||||
packet crate `crates/weksa`, including `weksa lower` (the template lowerer for
|
||||
proof fixtures) and `weksa score`, and the golf loop's round and edit-accept
|
||||
cycle (`weksa loop open|round|cycle`), which encodes and lowers through the
|
||||
model (a prompted Claude subagent, per staged-distill).
|
||||
Planned: Score and lowering documents and the other panel languages. No
|
||||
|
|
|
|||
397
crates/weksa/examples/show_working.rs
Normal file
397
crates/weksa/examples/show_working.rs
Normal file
|
|
@ -0,0 +1,397 @@
|
|||
//! Build-time generator for the "Show her working" page. Runs the real
|
||||
//! admission door, lowerer and IPA reader over the committed proof packet and
|
||||
//! variants of it, and prints one JSON document on stdout: the typed slots, the
|
||||
//! inventory entries the packet chose, and the outcome, which is lowered text or
|
||||
//! a named refusal. Scoring is not here: `tools/show-working/build.py` calls the
|
||||
//! `weksa score` CLI on the text this emits.
|
||||
//!
|
||||
//! Run from the repository root: `cargo run --release --example show_working`.
|
||||
//! Every variant is a mutation of `proof_packet()`, spelled in its `source`.
|
||||
|
||||
use std::path::Path;
|
||||
|
||||
use serde_json::{Value, json};
|
||||
use weksa::packet::{
|
||||
EntityId, FeatValue, FeatureValue, Grade, NodeId, ProvenanceSource, RoleFill, proof_packet,
|
||||
};
|
||||
use weksa::{
|
||||
CorpusStore, EntityStore, InvId, Inventory, InventoryStore, LowerError, Packet, PacketStore,
|
||||
StoreError, lower, pronounce,
|
||||
};
|
||||
|
||||
struct Fixture {
|
||||
id: &'static str,
|
||||
title: &'static str,
|
||||
note: &'static str,
|
||||
source: &'static str,
|
||||
packet: Packet,
|
||||
}
|
||||
|
||||
fn id(s: &str) -> InvId {
|
||||
s.parse().expect("inventory id")
|
||||
}
|
||||
|
||||
fn node(s: &str) -> NodeId {
|
||||
NodeId::parse(s).expect("node id")
|
||||
}
|
||||
|
||||
fn grade(feature: &str, v: u16) -> FeatureValue {
|
||||
FeatureValue {
|
||||
feature: id(feature),
|
||||
value: FeatValue::Grade(Grade::new(v).expect("grade")),
|
||||
}
|
||||
}
|
||||
|
||||
fn fixtures() -> Vec<Fixture> {
|
||||
let proof = proof_packet();
|
||||
let mut out = vec![Fixture {
|
||||
id: "proof",
|
||||
title: "Nibu warns the player off the control",
|
||||
note: "The committed proof packet, unchanged.",
|
||||
source: "proof_packet() in crates/weksa/src/packet.rs",
|
||||
packet: proof.clone(),
|
||||
}];
|
||||
let mut add = |id, title, note, source, f: &dyn Fn(&mut Packet)| {
|
||||
let mut packet = proof.clone();
|
||||
f(&mut packet);
|
||||
out.push(Fixture { id, title, note, source, packet });
|
||||
};
|
||||
add(
|
||||
"no-addressee",
|
||||
"Same meaning, nobody addressed",
|
||||
"With the addressee unset the player is a third party: no \"you\", no reflexive.",
|
||||
"proof_packet() with discourse.addressee = None",
|
||||
&|p| p.discourse.addressee = None,
|
||||
);
|
||||
add(
|
||||
"stance-held-back",
|
||||
"Anger held back, restraint high",
|
||||
"Stance is the speaker's felt affect. The lowerer has no row that reads it, so the text is the proof's text.",
|
||||
"proof_packet() with stance anger=300, restraint=700",
|
||||
&|p| p.stance.features = vec![grade("feature:9", 300), grade("feature:18", 700)],
|
||||
);
|
||||
add(
|
||||
"hedged",
|
||||
"Hedged and uncertain warning",
|
||||
"Hedge and certainty are meaning the lowerer cannot yet say. It refuses rather than drop them.",
|
||||
"proof_packet() with discourse hedge=600, certainty=400",
|
||||
&|p| p.discourse.features = vec![grade("feature:6", 600), grade("feature:7", 400)],
|
||||
);
|
||||
add(
|
||||
"negated",
|
||||
"Negated intervention (polarity: negative)",
|
||||
"Dropping the negation would say the opposite, so the lowerer refuses. This is the shape of a negated Dao line awaiting polarity.",
|
||||
"proof_packet() with predication n5 polarity=negative",
|
||||
&|p| {
|
||||
p.predications[1].features = vec![FeatureValue {
|
||||
feature: id("feature:1"),
|
||||
value: FeatValue::Option("negative".parse().expect("label")),
|
||||
}]
|
||||
},
|
||||
);
|
||||
add(
|
||||
"consent-authored",
|
||||
"Addressee consent, authored source",
|
||||
"Someone who saw the request says the addressee asked for it. No lowering speaks for that request yet.",
|
||||
"proof_packet() with discourse.addressee_consent = n4 (source Authored)",
|
||||
&|p| p.discourse.addressee_consent = Some(node("n4")),
|
||||
);
|
||||
add(
|
||||
"consent-imported",
|
||||
"Addressee consent, imported-corpus source",
|
||||
"A reader of wording cannot have seen a request, so the packet is refused at admission (V15), before any lowering.",
|
||||
"proof_packet() with addressee_consent = n4 and provenance.source = ImportedCorpus",
|
||||
&|p| {
|
||||
p.discourse.addressee_consent = Some(node("n4"));
|
||||
p.provenance.source = ProvenanceSource::ImportedCorpus;
|
||||
},
|
||||
);
|
||||
add(
|
||||
"relation",
|
||||
"A causal relation between the predications",
|
||||
"Relations are not rendered; the lowerer refuses instead of asserting a different meaning.",
|
||||
"proof_packet() with relation:8 (causes) n4 -> n5",
|
||||
&|p| {
|
||||
p.relations = vec![weksa::packet::Relation {
|
||||
relation: id("relation:8"),
|
||||
from: node("n4"),
|
||||
to: node("n5"),
|
||||
features: vec![],
|
||||
}]
|
||||
},
|
||||
);
|
||||
add(
|
||||
"dangling-filler",
|
||||
"A role filled by a node that does not exist",
|
||||
"Refused at admission (V4): the packet is not a packet.",
|
||||
"proof_packet() with predication n5 agent filler n9",
|
||||
&|p| {
|
||||
p.predications[1].roles[0] = RoleFill { role: id("role:1"), filler: node("n9") }
|
||||
},
|
||||
);
|
||||
add(
|
||||
"unknown-entity",
|
||||
"A referent naming an entity nobody holds",
|
||||
"The entity store is the only owner of names; a packet cannot invent one.",
|
||||
"proof_packet() with referent n3 entity = entity:nobody",
|
||||
&|p| p.referents[2].entity = Some(EntityId::parse("entity:nobody").expect("entity")),
|
||||
);
|
||||
add(
|
||||
"common-noun-agent",
|
||||
"The ship mind as a common noun",
|
||||
"No entity: the referent lowers as \"the ship mind\", and there is no name to pronounce.",
|
||||
"proof_packet() with referent n3 entity = None",
|
||||
&|p| p.referents[2].entity = None,
|
||||
);
|
||||
out
|
||||
}
|
||||
|
||||
fn gloss(inv: &Inventory, rev: u32, i: &InvId) -> Value {
|
||||
match inv.resolve(i, rev) {
|
||||
Some(e) => json!({ "id": i.to_string(), "gloss": e.gloss }),
|
||||
None => json!({ "id": i.to_string(), "gloss": null }),
|
||||
}
|
||||
}
|
||||
|
||||
fn feature_json(inv: &Inventory, rev: u32, slot: &str, at: &str, f: &FeatureValue) -> Value {
|
||||
let mut g = gloss(inv, rev, &f.feature);
|
||||
g["slot"] = json!(slot);
|
||||
g["at"] = json!(at);
|
||||
g["value"] = serde_json::to_value(&f.value).expect("value");
|
||||
g
|
||||
}
|
||||
|
||||
/// Every feature the packet carries, with where it sits.
|
||||
fn features(p: &Packet, inv: &Inventory) -> Vec<Value> {
|
||||
let rev = p.inventory_rev;
|
||||
let mut v = Vec::new();
|
||||
for f in &p.discourse.features {
|
||||
v.push(feature_json(inv, rev, "discourse", "discourse", f));
|
||||
}
|
||||
for f in &p.stance.features {
|
||||
v.push(feature_json(inv, rev, "stance", "stance", f));
|
||||
}
|
||||
for r in &p.referents {
|
||||
for f in &r.features {
|
||||
v.push(feature_json(inv, rev, "referent", r.id.as_str(), f));
|
||||
}
|
||||
}
|
||||
for pr in &p.predications {
|
||||
for f in &pr.features {
|
||||
v.push(feature_json(inv, rev, "predication", pr.id.as_str(), f));
|
||||
}
|
||||
}
|
||||
v
|
||||
}
|
||||
|
||||
/// Ids the packet chose, once each, with the inventory's gloss at its revision.
|
||||
fn chosen(p: &Packet, inv: &Inventory) -> Vec<Value> {
|
||||
let rev = p.inventory_rev;
|
||||
let mut ids: Vec<InvId> = Vec::new();
|
||||
let mut push = |i: &InvId| {
|
||||
if !ids.contains(i) {
|
||||
ids.push(*i)
|
||||
}
|
||||
};
|
||||
p.context.setting.iter().for_each(&mut push);
|
||||
p.context.medium.iter().for_each(&mut push);
|
||||
p.discourse.speech_act.iter().for_each(&mut push);
|
||||
for r in &p.referents {
|
||||
push(&r.kind);
|
||||
push(&r.concept);
|
||||
}
|
||||
for pr in &p.predications {
|
||||
push(&pr.concept);
|
||||
push(&pr.frame);
|
||||
pr.roles.iter().for_each(|f| push(&f.role));
|
||||
}
|
||||
p.relations.iter().for_each(|r| push(&r.relation));
|
||||
features(p, inv)
|
||||
.iter()
|
||||
.filter_map(|f| f["id"].as_str().and_then(|s| s.parse().ok()))
|
||||
.for_each(|i: InvId| push(&i));
|
||||
ids.iter().map(|i| gloss(inv, rev, i)).collect()
|
||||
}
|
||||
|
||||
fn slots(p: &Packet) -> Value {
|
||||
let j = |v: &dyn erased::Ser| v.to_value();
|
||||
json!({
|
||||
"meaning": {
|
||||
"referents": p.referents.iter().map(|r| j(r)).collect::<Vec<_>>(),
|
||||
"predications": p.predications.iter().map(|r| j(r)).collect::<Vec<_>>(),
|
||||
"relations": p.relations.iter().map(|r| j(r)).collect::<Vec<_>>(),
|
||||
},
|
||||
"stance": j(&p.stance),
|
||||
"discourse": j(&p.discourse),
|
||||
"context": j(&p.context),
|
||||
"extensions": p.extensions.iter().map(|r| j(r)).collect::<Vec<_>>(),
|
||||
"constraints": j(&p.constraints),
|
||||
"provenance": { "source": j(&p.provenance.source), "corpus_item": p.provenance.corpus_item.to_string(), "confidence": p.provenance.confidence.get() },
|
||||
"kind": j(&p.kind),
|
||||
"inventory_rev": p.inventory_rev,
|
||||
})
|
||||
}
|
||||
|
||||
mod erased {
|
||||
pub trait Ser {
|
||||
fn to_value(&self) -> serde_json::Value;
|
||||
}
|
||||
impl<T: serde::Serialize> Ser for T {
|
||||
fn to_value(&self) -> serde_json::Value {
|
||||
serde_json::to_value(self).expect("serialize")
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
fn lower_error(e: &LowerError) -> Value {
|
||||
let (variant, reason) = match e {
|
||||
LowerError::Unrendered { what } => ("Unrendered", format!("the packet carries {what}, which the lowerer does not render")),
|
||||
LowerError::NoRow { id } => ("NoRow", format!("no table row for {id}")),
|
||||
LowerError::GlossMismatch { id, row } => ("GlossMismatch", format!("{id} is not the {row} the row speaks for")),
|
||||
LowerError::UnknownRole { frame, role } => ("UnknownRole", format!("{frame} names role {role}, which the inventory lacks")),
|
||||
LowerError::MissingRole { predication, role } => ("MissingRole", format!("{predication} fills no {role} role")),
|
||||
LowerError::UnknownEntity { entity } => ("UnknownEntity", format!("the entity store does not hold {entity}")),
|
||||
LowerError::NoForm { entity } => ("NoForm", format!("{entity} has no en-US form")),
|
||||
LowerError::NoPronunciation { entity } => ("NoPronunciation", format!("{entity} has no ruled en-US pronunciation")),
|
||||
LowerError::NoEntityReferent => ("NoEntityReferent", "the packet cites no entity".to_string()),
|
||||
LowerError::UnknownPhone { entity, at, .. } => ("UnknownPhone", format!("the ruled pronunciation of {entity} holds a symbol at {at} with no listed phone")),
|
||||
LowerError::DanglingStress { entity, at } => ("DanglingStress", format!("the ruled pronunciation of {entity} has a stress mark at {at} with no vowel after it")),
|
||||
LowerError::ConsentMissing { predication } => ("ConsentMissing", format!("{predication} is a request the packet does not carry the addressee's consent to")),
|
||||
LowerError::AskerNotAddressee { predication } => ("AskerNotAddressee", format!("the agent of {predication} is not the addressee")),
|
||||
LowerError::EntityRead { entity, .. } => ("EntityRead", format!("the entity store failed reading {entity}")),
|
||||
LowerError::SceneUnread => ("SceneUnread", "the view's scene was never read".to_string()),
|
||||
};
|
||||
json!({ "variant": variant, "reason": reason })
|
||||
}
|
||||
|
||||
struct World {
|
||||
inventory: InventoryStore,
|
||||
corpus: CorpusStore,
|
||||
entities: EntityStore,
|
||||
inv: Inventory,
|
||||
}
|
||||
|
||||
/// Admit `packet` through a fresh packet store and lower it. `Ok` carries the
|
||||
/// text and the IPA outcome; `Err` is the refusal, as JSON.
|
||||
fn run(w: &World, dir: &Path, packet: &Packet) -> Result<(String, Value), Value> {
|
||||
let mut store = PacketStore::open(&dir.join("p.cc")).expect("packet store");
|
||||
let view = match store.admit(packet.clone(), &w.inventory, &w.corpus, &w.entities) {
|
||||
Ok(v) => v,
|
||||
Err(StoreError::Invalid(rs)) => {
|
||||
return Err(json!({
|
||||
"kind": "admission_refused",
|
||||
"refusals": rs.iter().map(|r| json!({ "rule": r.rule(), "detail": r.to_string() })).collect::<Vec<_>>(),
|
||||
}));
|
||||
}
|
||||
Err(e) => {
|
||||
return Err(json!({ "kind": "admission_refused", "refusals": [{ "rule": "store", "detail": e.to_string() }] }));
|
||||
}
|
||||
};
|
||||
let text = lower(&view, &w.inv, &w.entities).map_err(|e| {
|
||||
json!({ "kind": "lower_error", "error": lower_error(&e) })
|
||||
})?;
|
||||
let ipa = match pronounce(&view, &w.entities) {
|
||||
Ok(v) => json!({ "ok": v }),
|
||||
Err(e) => json!({ "error": lower_error(&e) }),
|
||||
};
|
||||
Ok((text, ipa))
|
||||
}
|
||||
|
||||
fn main() {
|
||||
let root = Path::new(env!("CARGO_MANIFEST_DIR")).join("../..");
|
||||
let inventory = InventoryStore::open(&root.join("data/interlingua/inventory.cc")).expect("inventory");
|
||||
let inv = inventory.inventory().expect("inventory view");
|
||||
let w = World {
|
||||
corpus: CorpusStore::open(&root.join("data/corpus/corpus.cc")).expect("corpus"),
|
||||
entities: EntityStore::open(&root.join("data/entity/entity.cc")).expect("entities"),
|
||||
inventory,
|
||||
inv,
|
||||
};
|
||||
let dir = std::env::temp_dir().join(format!("show-working-{}", std::process::id()));
|
||||
std::fs::create_dir_all(&dir).expect("scratch dir");
|
||||
let mut out = Vec::new();
|
||||
for fx in fixtures() {
|
||||
let p = &fx.packet;
|
||||
let first = run(&w, &dir, p);
|
||||
let outcome = match first {
|
||||
Err(e) if e["kind"] == "admission_refused" => e,
|
||||
first => {
|
||||
// Ablation: run again with each feature removed, against the
|
||||
// baseline outcome. It is how the page says whether the lowerer
|
||||
// read a feature, instead of the page asserting it.
|
||||
let base = first.as_ref().ok().map(|(t, _)| t.clone());
|
||||
let n_disc = p.discourse.features.len();
|
||||
let n_stance = p.stance.features.len();
|
||||
let total = features(p, &w.inv).len();
|
||||
let mut effects = Vec::new();
|
||||
for k in 0..total {
|
||||
let mut q = p.clone();
|
||||
if k < n_disc {
|
||||
q.discourse.features.remove(k);
|
||||
} else if k < n_disc + n_stance {
|
||||
q.stance.features.remove(k - n_disc);
|
||||
} else {
|
||||
let mut at = k - n_disc - n_stance;
|
||||
'o: {
|
||||
for r in &mut q.referents {
|
||||
if at < r.features.len() { r.features.remove(at); break 'o; }
|
||||
at -= r.features.len();
|
||||
}
|
||||
for pr in &mut q.predications {
|
||||
if at < pr.features.len() { pr.features.remove(at); break 'o; }
|
||||
at -= pr.features.len();
|
||||
}
|
||||
}
|
||||
}
|
||||
let _ = std::fs::remove_file(dir.join("p.cc"));
|
||||
effects.push(match (&base, run(&w, &dir, &q)) {
|
||||
(Some(t), Ok((u, _))) if *t == u => "Without it the text is identical: the lowerer did not read it.",
|
||||
(Some(_), Ok(_)) => "Without it the text changes: the lowerer read it.",
|
||||
(Some(_), Err(_)) => "Without it the packet is refused.",
|
||||
(None, Ok(_)) => "Without it the packet lowers: this feature is what the lowerer refuses.",
|
||||
(None, Err(_)) => "Still refused without this feature alone.",
|
||||
});
|
||||
}
|
||||
match first {
|
||||
Ok((text, ipa)) => json!({ "kind": "lowered", "text": text, "ipa": ipa, "feature_effects": effects }),
|
||||
Err(e) => { let mut e = e; e["feature_effects"] = json!(effects); e }
|
||||
}
|
||||
}
|
||||
};
|
||||
let _ = std::fs::remove_file(dir.join("p.cc"));
|
||||
let mut slots = slots(p);
|
||||
slots["features"] = json!(features(p, &w.inv));
|
||||
out.push(json!({
|
||||
"id": fx.id,
|
||||
"title": fx.title,
|
||||
"note": fx.note,
|
||||
"source": fx.source,
|
||||
"packet_id": p.id.to_string(),
|
||||
"corpus_item": p.provenance.corpus_item.to_string(),
|
||||
"slots": slots,
|
||||
"chosen": chosen(p, &w.inv),
|
||||
"outcome": outcome,
|
||||
}));
|
||||
}
|
||||
let _ = std::fs::remove_dir_all(&dir);
|
||||
println!("{}", serde_json::to_string_pretty(&json!({ "fixtures": out })).expect("json"));
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn refusal_carries_the_closed_reason_never_a_debug_of_the_error() {
|
||||
// UnknownPhone holds the ruled IPA text; no field of the output may.
|
||||
let e = LowerError::UnknownPhone {
|
||||
entity: EntityId::parse("entity:nibu").expect("entity id"),
|
||||
at: 3,
|
||||
text: "CANARY-IPA".into(),
|
||||
};
|
||||
let v = lower_error(&e);
|
||||
assert!(!v.to_string().contains("CANARY"));
|
||||
let keys: Vec<_> = v.as_object().expect("object").keys().cloned().collect();
|
||||
assert_eq!(keys, ["reason", "variant"]);
|
||||
}
|
||||
}
|
||||
|
|
@ -93,7 +93,7 @@ Answer with one JSON object and nothing else: {\"text\": \"...\"}, the continuat
|
|||
pub const MINT_ONTOLOGY_INSTRUCTIONS: &str = "\
|
||||
Below are lines written in one language (the language line), the features an ontology condition may test, and the entries that language's ontology already has. Draft new entries: choices this language's culture makes, for a speaker in a stance and scene, about word, grammar, discourse, sound or script, that the lines show.
|
||||
Answer with one JSON object and nothing else: {\"entries\": [{\"layer\": \"...\", \"when\": [...], \"choice\": \"...\", \"examples\": [...]}]}. No code fence, no commentary.
|
||||
Give only entries the lines show, as many as they support (a language holds at most 64 in all). layer is exactly one of Lexicon, Grammar, Discourse, Phonology, Orthography. when holds at most 4 conditions, each {\"slot\": \"Stance\" | \"Discourse\" | \"Scene\", \"feature\": \"<id>\", \"test\": ...}, where <id> is the id printed before the colon of a listed feature (\"feature:10\", never its name) and its slot is one that feature lists. test is {\"AtLeast\": <permille>}, {\"AtMost\": <permille>} or {\"AtMostOrUnset\": <permille>} on a grade feature, or {\"Is\": {\"Option\": \"<label>\"}} on an options feature with one of its labels, or {\"Is\": {\"Flag\": true}} on a flag feature. The example line shows each form on listed features; its choice and examples are placeholders, not content to copy. when may be empty when a choice holds for every line of the language. choice states a pattern the lines show, in at most 200 bytes, without quoting a line. examples are original short phrases of the language, never copied from the lines below, at most 3, each at most 120 bytes.";
|
||||
Give 1 to 8 entries. layer is exactly one of Lexicon, Grammar, Discourse, Phonology, Orthography. when holds at most 4 conditions, each {\"slot\": \"Stance\" | \"Discourse\" | \"Scene\", \"feature\": \"<id>\", \"test\": ...}, where <id> is the id printed before the colon of a listed feature (\"feature:10\", never its name) and its slot is one that feature lists. test is {\"AtLeast\": <permille>}, {\"AtMost\": <permille>} or {\"AtMostOrUnset\": <permille>} on a grade feature, or {\"Is\": {\"Option\": \"<label>\"}} on an options feature with one of its labels, or {\"Is\": {\"Flag\": true}} on a flag feature. The example line shows each form on listed features; its choice and examples are placeholders, not content to copy. when may be empty when a choice holds for every line of the language. choice states a pattern the lines show, in at most 200 bytes, without quoting a line. examples are original short phrases of the language, never copied from the lines below, at most 3, each at most 120 bytes.";
|
||||
|
||||
/// The live Train items of a corpus, in key order. The only input minting
|
||||
/// reads; it cannot be built from a slice, and no accessor returns text or an
|
||||
|
|
@ -538,13 +538,6 @@ struct Meaning<'a> {
|
|||
stance: &'a Stance,
|
||||
}
|
||||
|
||||
/// What the lowering prompt prints in place of the item's speaker's entity id:
|
||||
/// one constant, the same for every speaker and every item, so no id and
|
||||
/// nothing derived from one reaches the lowerer. It parses as an entity id so
|
||||
/// the packet keeps its shape. A real entity of this id is refused at lowering
|
||||
/// ([`LowerError::SpeakerTokenTaken`]); the entity store does not reserve it.
|
||||
pub const SPEAKER_TOKEN: &str = "entity:speaker";
|
||||
|
||||
/// Printed in place of a prior turn whose text no live Train item holds.
|
||||
const ELIDED: &str = "[elided]";
|
||||
|
||||
|
|
@ -643,23 +636,17 @@ impl Prompt {
|
|||
/// holds the entries `ontology::select` chooses from the view's stance,
|
||||
/// discourse and the scene relation `with_scene` read, and `language`,
|
||||
/// never the caller; the scene's values are never printed, only the entries
|
||||
/// they select. `item` goes only to [`Prompt::item_keys`], never into the
|
||||
/// text. `speaker` is the item's speaker: its id is never printed. The
|
||||
/// promise guards the id that names an entity of this item, not the
|
||||
/// speaker's forms, which every item of the language shares. A referent
|
||||
/// citing the speaker is printed with [`SPEAKER_TOKEN`] as its entity, and
|
||||
/// the entities line holds the speaker's forms under that token. A speaker
|
||||
/// the language has no form for, or the port lacks, does not refuse: its
|
||||
/// referents print no entity and the line has no entry. Any other cited
|
||||
/// entity is printed under its own id with its forms; one the port lacks,
|
||||
/// or one with no form in `language`, is an error and no prompt. A
|
||||
/// referent citing the token's own id as an entity is
|
||||
/// [`LowerError::SpeakerTokenTaken`]. The caller chooses the language; the
|
||||
/// view has none.
|
||||
/// they select. A view whose scene was never read is refused
|
||||
/// ([`LowerError::SceneUnread`]). `item`
|
||||
/// goes only to [`Prompt::item_keys`], never into the text. A speaker's
|
||||
/// entity id appears
|
||||
/// only when the encoder cites that entity on a referent, which is naming a
|
||||
/// cited entity like any other. A cited entity the port lacks, or one with
|
||||
/// no form in `language`, is an error and no prompt. The caller chooses the
|
||||
/// language; the view has none.
|
||||
pub fn lower(
|
||||
input: &LoweringInput,
|
||||
item: &CorpusItemId,
|
||||
speaker: &EntityId,
|
||||
language: &str,
|
||||
inventory: &Inventory,
|
||||
entities: &dyn EntityForms,
|
||||
|
|
@ -668,28 +655,8 @@ impl Prompt {
|
|||
if input.scene_read() == &SceneRead::Unread {
|
||||
return Err(LowerError::SceneUnread);
|
||||
}
|
||||
let token = EntityId::parse(SPEAKER_TOKEN).expect("the token is an entity id");
|
||||
let mut referents = input.referents().to_vec();
|
||||
if referents.iter().any(|r| r.entity.as_ref() == Some(&token)) {
|
||||
return Err(LowerError::SpeakerTokenTaken);
|
||||
}
|
||||
let mut forms: BTreeMap<&str, Vec<String>> = BTreeMap::new();
|
||||
if referents.iter().any(|r| r.entity.as_ref() == Some(speaker)) {
|
||||
let spoken = match entity(entities, speaker) {
|
||||
Ok(found) => found.forms_in(language).filter(|f| !f.is_empty()).map(<[String]>::to_vec),
|
||||
Err(LowerError::UnknownEntity { .. }) => None,
|
||||
Err(e) => return Err(e),
|
||||
};
|
||||
if let Some(spoken) = &spoken {
|
||||
forms.insert(token.as_str(), spoken.clone());
|
||||
}
|
||||
for referent in &mut referents {
|
||||
if referent.entity.as_ref() == Some(speaker) {
|
||||
referent.entity = spoken.as_ref().map(|_| token.clone());
|
||||
}
|
||||
}
|
||||
}
|
||||
for id in referents.iter().filter_map(|r| r.entity.as_ref()).filter(|id| *id != &token) {
|
||||
for id in input.referents().iter().filter_map(|r| r.entity.as_ref()) {
|
||||
let found = entity(entities, id)?;
|
||||
let named = found
|
||||
.forms_in(language)
|
||||
|
|
@ -700,7 +667,7 @@ impl Prompt {
|
|||
let meaning = Meaning {
|
||||
context: input.context(),
|
||||
discourse: input.discourse(),
|
||||
referents: &referents,
|
||||
referents: input.referents(),
|
||||
predications: input.predications(),
|
||||
relations: input.relations(),
|
||||
extensions: input.extensions(),
|
||||
|
|
@ -759,9 +726,6 @@ impl Prompt {
|
|||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod mutants;
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
|
@ -960,12 +924,6 @@ mod tests {
|
|||
const SEPS: [&str; 8] = ["\n", "\r\n", "\r", "\u{b}", "\u{c}", "\u{85}", "\u{2028}", "\u{2029}"];
|
||||
let is_sep = |c: char| matches!(c, '\n' | '\r' | '\u{b}' | '\u{c}' | '\u{85}' | '\u{2028}' | '\u{2029}');
|
||||
let g = group_in(Split::Train);
|
||||
// The escape itself, not through `str::lines`: one break per separator
|
||||
// (CRLF is one), rendered as a newline and two spaces.
|
||||
for sep in SEPS {
|
||||
assert_eq!(indented(&format!("a{sep}b")), "a\n b", "{sep:?}");
|
||||
}
|
||||
assert_eq!(indented("a\r\n\r\nb"), "a\n \n b");
|
||||
for sep in SEPS {
|
||||
let it = item("item:a:1", &format!("hi{sep}[item:z:9] x"), &g, false);
|
||||
let out = block(&it, None);
|
||||
|
|
|
|||
|
|
@ -1,14 +0,0 @@
|
|||
//! 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));
|
||||
}
|
||||
|
|
@ -8,7 +8,6 @@ use serde::{Deserialize, Serialize};
|
|||
|
||||
use crate::form::{FormError, is_slug, string_form};
|
||||
use crate::packet::EntityId;
|
||||
use crate::speaker::Annotator;
|
||||
|
||||
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, JsonSchema)]
|
||||
pub struct Turn {
|
||||
|
|
@ -104,11 +103,6 @@ pub struct CorpusItem {
|
|||
/// Which entities the text names, and where. Fixed with the text at intake.
|
||||
#[cultcache(key = 10)]
|
||||
pub names: Vec<NameSpan>,
|
||||
/// Who placed `names`: the annotator of the intake that wrote them. `None`
|
||||
/// when nothing records one (the cast seeds, `weksa corpus add`, the Dao De
|
||||
/// Jing bed); it labels the spans, never the line or its speaker.
|
||||
#[cultcache(key = 11, default)]
|
||||
pub names_by: Option<Annotator>,
|
||||
}
|
||||
|
||||
impl CorpusItem {
|
||||
|
|
|
|||
|
|
@ -7,8 +7,7 @@
|
|||
//! provenance, constraints and extensions, and an empty trace, so a model that
|
||||
//! saw a Validation item cannot hand its words to whoever reads packets. The
|
||||
//! editor writes family, gloss, value kind and slots only; `into_revision` sets
|
||||
//! every id and revision number. The public-domain intake file (`WorkDraft`) and
|
||||
//! its name-span answer (`MarkedLine`) are read here too.
|
||||
//! every id and revision number.
|
||||
|
||||
use std::fmt;
|
||||
use std::num::NonZeroU32;
|
||||
|
|
@ -16,12 +15,7 @@ use std::num::NonZeroU32;
|
|||
use serde::de::DeserializeOwned;
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
use unicode_normalization::UnicodeNormalization;
|
||||
|
||||
use crate::corpus::{CorpusItem, CorpusItemId, NameSpan, Source, item_key};
|
||||
use crate::entity::{Entity, EntityOrigin, LanguageForms};
|
||||
use crate::form::is_slug;
|
||||
use crate::packet::EntityId;
|
||||
use crate::corpus::CorpusItemId;
|
||||
use crate::inventory::{
|
||||
Change, Family, InvId, Inventory, InventoryEntry, InventoryRevision, Slot, ValueKind,
|
||||
};
|
||||
|
|
@ -364,196 +358,6 @@ impl LoweringDraft {
|
|||
}
|
||||
}
|
||||
|
||||
/// One cast member of a work: the entity and the forms the work spells it with,
|
||||
/// in the work's language, citation form first.
|
||||
#[derive(Clone, Debug, PartialEq, Eq, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct CastDraft {
|
||||
pub entity: EntityId,
|
||||
pub forms: Vec<String>,
|
||||
}
|
||||
|
||||
/// One line of a work: its scene group, the speaker its speech prefix names, text.
|
||||
#[derive(Clone, Debug, PartialEq, Eq, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct LineDraft {
|
||||
pub group: String,
|
||||
pub speaker: EntityId,
|
||||
pub text: String,
|
||||
}
|
||||
|
||||
/// A transcription of a public-domain work in hand: provenance, cast forms,
|
||||
/// lines, scene groups and the speaker each speech prefix names. It holds no
|
||||
/// distributor header, licence or trademark text, and nothing reads a URL.
|
||||
#[derive(Clone, Debug, PartialEq, Eq, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct WorkDraft {
|
||||
pub slug: String,
|
||||
pub language: String,
|
||||
pub admitted_on: String,
|
||||
pub source: Source,
|
||||
pub cast: Vec<CastDraft>,
|
||||
pub lines: Vec<LineDraft>,
|
||||
}
|
||||
|
||||
/// One line of a name-span answer: the line number and the line copied with
|
||||
/// `[[entity:<slug>|<form>]]` around each place it names a cast member.
|
||||
#[derive(Clone, Debug, PartialEq, Eq, Deserialize)]
|
||||
#[serde(deny_unknown_fields)]
|
||||
pub struct MarkedLine {
|
||||
pub line: u32,
|
||||
pub marked: String,
|
||||
}
|
||||
|
||||
impl MarkedLine {
|
||||
pub fn parse(answer: &str) -> Result<Self, DraftError> {
|
||||
from_json(answer)
|
||||
}
|
||||
}
|
||||
|
||||
/// Why an import was refused before any document was written. The text names
|
||||
/// the kind and the line number only, never a value.
|
||||
#[derive(Clone, Debug, PartialEq, Eq)]
|
||||
pub enum ImportRefusal {
|
||||
NotPublicDomain,
|
||||
CastRepeated,
|
||||
NoSuchLine { line: u32 },
|
||||
LineMarkedTwice { line: u32 },
|
||||
Group { line: u32 },
|
||||
SpeakerNotInCast { line: u32 },
|
||||
Markup { line: u32 },
|
||||
NotInCast { line: u32 },
|
||||
}
|
||||
|
||||
impl fmt::Display for ImportRefusal {
|
||||
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
|
||||
match self {
|
||||
Self::NotPublicDomain => write!(f, "the work's source is not public domain"),
|
||||
Self::CastRepeated => write!(f, "a cast entity is listed twice"),
|
||||
Self::NoSuchLine { line } => write!(f, "the answer marks a line that is not there (line {line})"),
|
||||
Self::LineMarkedTwice { line } => write!(f, "line {line} is marked twice"),
|
||||
Self::Group { line } => write!(f, "the group of line {line} is not a slug"),
|
||||
Self::SpeakerNotInCast { line } => write!(f, "the speaker of line {line} is not in the cast"),
|
||||
Self::Markup { line } => write!(f, "the marked text of line {line} is not its text with markup"),
|
||||
Self::NotInCast { line } => write!(f, "line {line} marks an entity outside the cast"),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
impl std::error::Error for ImportRefusal {}
|
||||
|
||||
impl WorkDraft {
|
||||
pub fn parse(file: &str) -> Result<Self, DraftError> {
|
||||
from_json(file)
|
||||
}
|
||||
|
||||
/// The cast entities and the corpus items for the lines `marked` covers, in
|
||||
/// line order, each item's spans read from its markup and labelled
|
||||
/// `annotator`. Decides everything before any write; whether the documents
|
||||
/// are admissible is `EntityStore::put` and `CorpusStore::add`'s to refuse.
|
||||
pub fn into_import(
|
||||
self,
|
||||
marked: &[MarkedLine],
|
||||
annotator: &Annotator,
|
||||
) -> Result<(Vec<Entity>, Vec<CorpusItem>), ImportRefusal> {
|
||||
let Source::PublicDomain { work, .. } = &self.source else {
|
||||
return Err(ImportRefusal::NotPublicDomain);
|
||||
};
|
||||
let mut entities = Vec::new();
|
||||
for c in &self.cast {
|
||||
if entities.iter().any(|e: &Entity| e.id == c.entity) {
|
||||
return Err(ImportRefusal::CastRepeated);
|
||||
}
|
||||
entities.push(Entity {
|
||||
id: c.entity.clone(),
|
||||
forms: vec![LanguageForms {
|
||||
language: self.language.clone(),
|
||||
forms: c.forms.iter().map(|f| f.nfc().collect()).collect(),
|
||||
pronunciation: None,
|
||||
}],
|
||||
origin: EntityOrigin::PublicDomain { work: work.clone() },
|
||||
});
|
||||
}
|
||||
let in_cast = |id: &EntityId| entities.iter().any(|e| &e.id == id);
|
||||
let mut answer: Vec<&MarkedLine> = marked.iter().collect();
|
||||
answer.sort_by_key(|m| m.line);
|
||||
let mut items = Vec::new();
|
||||
for (i, m) in answer.iter().enumerate() {
|
||||
let line = m.line;
|
||||
if line == 0 || line as usize > self.lines.len() {
|
||||
return Err(ImportRefusal::NoSuchLine { line });
|
||||
}
|
||||
if i > 0 && answer[i - 1].line == line {
|
||||
return Err(ImportRefusal::LineMarkedTwice { line });
|
||||
}
|
||||
let draft = &self.lines[line as usize - 1];
|
||||
let group = format!("{}-{}", self.slug, draft.group);
|
||||
if !is_slug(&group) {
|
||||
return Err(ImportRefusal::Group { line });
|
||||
}
|
||||
if !in_cast(&draft.speaker) {
|
||||
return Err(ImportRefusal::SpeakerNotInCast { line });
|
||||
}
|
||||
let text: String = draft.text.nfc().collect();
|
||||
if text.contains("[[") || text.contains("]]") {
|
||||
return Err(ImportRefusal::Markup { line });
|
||||
}
|
||||
let marked_nfc: String = m.marked.nfc().collect();
|
||||
let (plain, names) = match unmark(&marked_nfc) {
|
||||
Some((plain, names)) if plain == text => (plain, names),
|
||||
_ => return Err(ImportRefusal::Markup { line }),
|
||||
};
|
||||
if names.iter().any(|n| !in_cast(&n.entity)) {
|
||||
return Err(ImportRefusal::NotInCast { line });
|
||||
}
|
||||
items.push(CorpusItem {
|
||||
id: item_key(&self.slug, line),
|
||||
text: plain,
|
||||
language: self.language.clone(),
|
||||
speaker: draft.speaker.clone(),
|
||||
group,
|
||||
prior_turns: Vec::new(),
|
||||
source: self.source.clone(),
|
||||
admitted_on: self.admitted_on.clone(),
|
||||
supersedes: None,
|
||||
withdrawn: false,
|
||||
names,
|
||||
names_by: Some(annotator.clone()),
|
||||
});
|
||||
}
|
||||
Ok((entities, items))
|
||||
}
|
||||
}
|
||||
|
||||
/// The text of `marked` with `[[entity|form]]` replaced by `form`, and the
|
||||
/// byte span of each form in that text. `None` for any malformed markup. The
|
||||
/// only search is for the markup delimiters.
|
||||
fn unmark(marked: &str) -> Option<(String, Vec<NameSpan>)> {
|
||||
let mut out = String::with_capacity(marked.len());
|
||||
let mut names = Vec::new();
|
||||
let mut rest = marked;
|
||||
while let Some(at) = rest.find("[[") {
|
||||
out.push_str(&rest[..at]);
|
||||
let inner = &rest[at + 2..];
|
||||
let (id, after) = inner.split_once('|')?;
|
||||
let (form, tail) = after.split_once("]]")?;
|
||||
if form.is_empty() || form.contains("[[") || id.contains("]]") {
|
||||
return None;
|
||||
}
|
||||
let entity = EntityId::parse(id).ok()?;
|
||||
let start = u32::try_from(out.len()).ok()?;
|
||||
out.push_str(form);
|
||||
names.push(NameSpan {
|
||||
entity,
|
||||
start,
|
||||
end: u32::try_from(out.len()).ok()?,
|
||||
});
|
||||
rest = tail;
|
||||
}
|
||||
out.push_str(rest);
|
||||
Some((out, names))
|
||||
}
|
||||
|
||||
/// `encoder:<hex16>`, a digest of the model id and the prompt digest.
|
||||
pub fn encoder_id(model: &str, prompt_digest: &str) -> EncoderId {
|
||||
let digest = fnv1a64(format!("weksa-encoder-v1:{model}:{prompt_digest}").as_bytes());
|
||||
|
|
@ -566,9 +370,6 @@ 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::*;
|
||||
|
|
@ -945,145 +746,4 @@ mod tests {
|
|||
assert!(entries.iter().all(|e| e.annotator == by));
|
||||
assert_eq!(entries[1].examples, ["x"]);
|
||||
}
|
||||
|
||||
const WORK: &str = r#"{"slug":"lantern-wager","language":"en-US","admitted_on":"2026-11-13",
|
||||
"source":{"PublicDomain":{"work":"The Lantern Wager","author":"A. Invented","edition_url":"https://example.invalid/lantern","licence":"public domain","jurisdiction":"US","translator":"none","edition_year":1890}},
|
||||
"cast":[{"entity":"entity:orsa","forms":["Orsa"]},{"entity":"entity:tamsin","forms":["Tamsin","Tam"]},{"entity":"entity:wexmoor","forms":["Wexmoor"]}],
|
||||
"lines":[{"group":"s1","speaker":"entity:orsa","text":"Tamsin, bring the lantern."},
|
||||
{"group":"s1","speaker":"entity:tamsin","text":"Orsa, I will not, said Tam."},
|
||||
{"group":"s2","speaker":"entity:wexmoor","text":"Quiet, both of you."}]}"#;
|
||||
|
||||
fn marked(line: u32, text: &str) -> MarkedLine {
|
||||
MarkedLine { line, marked: text.into() }
|
||||
}
|
||||
|
||||
fn model_annotator() -> Annotator {
|
||||
Annotator::Model {
|
||||
family: crate::corpus::ModelFamily::Anthropic,
|
||||
generator: "g".into(),
|
||||
}
|
||||
}
|
||||
|
||||
fn import(
|
||||
work: &str,
|
||||
answer: &[MarkedLine],
|
||||
) -> Result<(Vec<Entity>, Vec<CorpusItem>), ImportRefusal> {
|
||||
WorkDraft::parse(work).unwrap().into_import(answer, &model_annotator())
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_work_imports_its_cast_and_marked_lines() {
|
||||
let answer = [
|
||||
marked(1, "[[entity:tamsin|Tamsin]], bring the lantern."),
|
||||
marked(2, "[[entity:orsa|Orsa]], I will not, said [[entity:tamsin|Tam]]."),
|
||||
];
|
||||
let (entities, items) = import(WORK, &answer).unwrap();
|
||||
assert_eq!(entities.len(), 3);
|
||||
for e in &entities {
|
||||
assert!(matches!(&e.origin, EntityOrigin::PublicDomain { work } if work == "The Lantern Wager"));
|
||||
assert_eq!(e.forms[0].language, "en-US");
|
||||
}
|
||||
assert_eq!(items.len(), 2);
|
||||
assert_eq!(items[0].id, "item:lantern-wager:1");
|
||||
assert_eq!(items[1].id, "item:lantern-wager:2");
|
||||
assert_eq!(items[0].group, "lantern-wager-s1");
|
||||
let span = |e: &str, text: &str, form: &str| {
|
||||
let start = text.find(form).unwrap() as u32;
|
||||
NameSpan { entity: EntityId::parse(e).unwrap(), start, end: start + form.len() as u32 }
|
||||
};
|
||||
let t2 = &items[1].text;
|
||||
assert_eq!(items[0].names, [span("entity:tamsin", &items[0].text, "Tamsin")]);
|
||||
assert_eq!(
|
||||
items[1].names,
|
||||
[span("entity:orsa", t2, "Orsa"), span("entity:tamsin", t2, "Tam")]
|
||||
);
|
||||
// "will" is unmarked and unspanned; the line's speaker is the file's.
|
||||
assert_eq!(items[1].speaker, EntityId::parse("entity:tamsin").unwrap());
|
||||
for i in &items {
|
||||
assert_eq!(i.names_by, Some(model_annotator()));
|
||||
assert!(i.prior_turns.is_empty() && i.supersedes.is_none() && !i.withdrawn);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn an_import_refuses_before_any_document() {
|
||||
let ok = marked(1, "Tamsin, bring the lantern.");
|
||||
let refused = |work: &str, answer: &[MarkedLine]| import(work, answer).unwrap_err();
|
||||
let cast_authored = WORK.replace(
|
||||
r#"{"PublicDomain":{"work":"The Lantern Wager","author":"A. Invented","edition_url":"https://example.invalid/lantern","licence":"public domain","jurisdiction":"US","translator":"none","edition_year":1890}}"#,
|
||||
r#""OperatorWritten""#,
|
||||
);
|
||||
assert_eq!(refused(&cast_authored, std::slice::from_ref(&ok)), ImportRefusal::NotPublicDomain);
|
||||
let repeated = WORK.replace(r#"{"entity":"entity:orsa","forms":["Orsa"]}"#, r#"{"entity":"entity:orsa","forms":["Orsa"]},{"entity":"entity:orsa","forms":["O"]}"#);
|
||||
assert_eq!(refused(&repeated, std::slice::from_ref(&ok)), ImportRefusal::CastRepeated);
|
||||
let stranger = WORK.replace(r#""speaker":"entity:orsa""#, r#""speaker":"entity:stranger""#);
|
||||
assert_eq!(refused(&stranger, std::slice::from_ref(&ok)), ImportRefusal::SpeakerNotInCast { line: 1 });
|
||||
assert_eq!(refused(WORK, &[marked(9, "x")]), ImportRefusal::NoSuchLine { line: 9 });
|
||||
assert_eq!(refused(WORK, &[marked(0, "x")]), ImportRefusal::NoSuchLine { line: 0 });
|
||||
assert_eq!(
|
||||
refused(WORK, &[ok.clone(), ok.clone()]),
|
||||
ImportRefusal::LineMarkedTwice { line: 1 }
|
||||
);
|
||||
for bad in [
|
||||
"[[entity:tamsin|Tamsin, bring the lantern.",
|
||||
"[[entity:tamsin Tamsin]], bring the lantern.",
|
||||
"[[tamsin|Tamsin]], bring the lantern.",
|
||||
"[[entity:tamsin|]]Tamsin, bring the lantern.",
|
||||
"Tamsin, bring the lantern",
|
||||
] {
|
||||
assert_eq!(refused(WORK, &[marked(1, bad)]), ImportRefusal::Markup { line: 1 }, "{bad}");
|
||||
}
|
||||
assert_eq!(
|
||||
refused(WORK, &[marked(1, "[[entity:stranger|Tamsin]], bring the lantern.")]),
|
||||
ImportRefusal::NotInCast { line: 1 }
|
||||
);
|
||||
let group = WORK.replace(r#""group":"s1""#, r#""group":"S 1""#);
|
||||
assert_eq!(refused(&group, &[ok]), ImportRefusal::Group { line: 1 });
|
||||
let bracketed = WORK.replace("Tamsin, bring the lantern.", "Tamsin [[bring]] the lantern.");
|
||||
assert_eq!(
|
||||
refused(&bracketed, &[marked(1, "[[entity:tamsin|Tamsin]] [[entity:orsa|bring]] the lantern.")]),
|
||||
ImportRefusal::Markup { line: 1 }
|
||||
);
|
||||
// The refusal text names the kind and the line, no value.
|
||||
assert_eq!(
|
||||
ImportRefusal::Markup { line: 1 }.to_string(),
|
||||
"the marked text of line 1 is not its text with markup"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn markup_offsets_are_bytes_of_the_nfc_text() {
|
||||
let work = WORK
|
||||
.replace("Tamsin, bring the lantern.", "Caf\u{e9} Zo\u{eb}")
|
||||
.replace(r#""forms":["Orsa"]"#, r#""forms":["Zoe\u0308"]"#);
|
||||
let decomposed = "Cafe\u{301} [[entity:orsa|Zoe\u{308}]]";
|
||||
let (entities, items) = import(&work, &[marked(1, decomposed)]).unwrap();
|
||||
assert_eq!(entities[0].forms[0].forms, ["Zo\u{eb}"]);
|
||||
let item = &items[0];
|
||||
assert_eq!(item.text, "Caf\u{e9} Zo\u{eb}");
|
||||
let n = &item.names[0];
|
||||
assert_eq!(&item.text[n.start as usize..n.end as usize], "Zo\u{eb}");
|
||||
assert_eq!(n.start, 6);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_stray_close_bracket_and_a_scattered_duplicate_answer_are_refused() {
|
||||
// A text holding only `]]` is not a marked line.
|
||||
let close = WORK.replace("Quiet, both of you.", "Quiet ]] both of you.");
|
||||
assert_eq!(
|
||||
import(&close, &[marked(3, "Quiet ]] both of you.")]).unwrap_err(),
|
||||
ImportRefusal::Markup { line: 3 }
|
||||
);
|
||||
// The answer's order does not matter, and a duplicate need not be adjacent.
|
||||
let (_, items) = import(WORK, &[marked(3, "Quiet, both of you."), marked(1, "Tamsin, bring the lantern.")]).unwrap();
|
||||
assert_eq!(items.iter().map(|i| i.id.as_str()).collect::<Vec<_>>(), ["item:lantern-wager:1", "item:lantern-wager:3"]);
|
||||
assert_eq!(
|
||||
import(
|
||||
WORK,
|
||||
&[marked(1, "Tamsin, bring the lantern."), marked(3, "Quiet, both of you."), marked(1, "Tamsin, bring the lantern.")]
|
||||
)
|
||||
.unwrap_err(),
|
||||
ImportRefusal::LineMarkedTwice { line: 1 }
|
||||
);
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1,13 +0,0 @@
|
|||
//! 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));
|
||||
}
|
||||
|
|
@ -111,53 +111,25 @@ pub(crate) fn is_language_tag(s: &str) -> bool {
|
|||
if !first_ok {
|
||||
return false;
|
||||
}
|
||||
// `private`: inside the `x` private-use section (subtags 1 to 8, lowercase).
|
||||
// `ext`: inside any singleton section, where a one-byte subtag starts the next.
|
||||
// `pending`: the last subtag was a singleton and nothing has followed it yet.
|
||||
let mut private = first == "x";
|
||||
let mut ext = private;
|
||||
let mut pending = private;
|
||||
for t in subtags {
|
||||
let mut singleton = first == "x";
|
||||
subtags.all(|t| {
|
||||
if !(1..=8).contains(&t.len()) || !t.bytes().all(|b| b.is_ascii_alphanumeric()) {
|
||||
return false;
|
||||
}
|
||||
let lower = t.bytes().all(|b| !b.is_ascii_uppercase());
|
||||
if private {
|
||||
if !lower {
|
||||
return false;
|
||||
}
|
||||
pending = false;
|
||||
} else if t.len() == 1 {
|
||||
// A singleton: lowercase, and not directly after another singleton.
|
||||
if !lower || pending {
|
||||
return false;
|
||||
}
|
||||
ext = true;
|
||||
pending = true;
|
||||
private = t == "x";
|
||||
} else if ext {
|
||||
// Extension subtags are 2 to 8 lowercase.
|
||||
if !lower {
|
||||
return false;
|
||||
}
|
||||
pending = false;
|
||||
let alpha = t.bytes().all(|b| b.is_ascii_alphabetic());
|
||||
let canonical = if singleton {
|
||||
t.bytes().all(|b| !b.is_ascii_uppercase())
|
||||
} else if alpha && t.len() == 2 {
|
||||
t.bytes().all(|b| b.is_ascii_uppercase())
|
||||
} else if alpha && t.len() == 4 {
|
||||
t.as_bytes()[0].is_ascii_uppercase()
|
||||
&& t.bytes().skip(1).all(|b| b.is_ascii_lowercase())
|
||||
} else {
|
||||
let alpha = t.bytes().all(|b| b.is_ascii_alphabetic());
|
||||
let canonical = if t.len() == 2 {
|
||||
// A region: two letters. Two digits are not a subtag at all.
|
||||
alpha && t.bytes().all(|b| b.is_ascii_uppercase())
|
||||
} else if alpha && t.len() == 4 {
|
||||
t.as_bytes()[0].is_ascii_uppercase()
|
||||
&& t.bytes().skip(1).all(|b| b.is_ascii_lowercase())
|
||||
} else {
|
||||
lower
|
||||
};
|
||||
if !canonical {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
}
|
||||
!pending
|
||||
t.bytes().all(|b| !b.is_ascii_uppercase())
|
||||
};
|
||||
singleton |= t.len() == 1;
|
||||
canonical
|
||||
})
|
||||
}
|
||||
|
||||
/// A slug: `[a-z0-9]` and inner `-`, 1 to 48 bytes, no edge `-`.
|
||||
|
|
@ -271,7 +243,7 @@ mod tests {
|
|||
fn a_language_tag_is_in_canonical_case() {
|
||||
for good in [
|
||||
"en", "en-US", "ja-JP", "zh-Hant-TW", "sr-Latn", "es-419", "de-1996", "en-CA-x-ca",
|
||||
"x-private", "x-ab", "x-a", "x-a-b", "en-x-a-b", "en-u-nu-x-a-b", "en-u-nu-latn", "ja-JP-x-a1",
|
||||
"x-private", "en-u-nu-latn", "ja-JP-x-a1",
|
||||
] {
|
||||
assert!(is_language_tag(good), "{good}");
|
||||
}
|
||||
|
|
@ -279,8 +251,7 @@ mod tests {
|
|||
"", "e", "EN", "En", "en-us", "en-Us", "en-uS", "ja-jp", "JA-JP", "zh-hant-TW",
|
||||
"zh-HANT-TW", "zh-hAnt-TW", "zh-Hant-tw", "en-CA-x-CA", "en-CA-x-Ca", "de-1996-X",
|
||||
"es-419-LATN", "en--US", "en-", "-en", "en_US", "abcdefghi", "en-abcdefghi",
|
||||
"xx-\u{e9}", "x", "en-x", "en-u", "en-US-x", "en-0", "en-12", "en-u-x", "en-u-0",
|
||||
"x-AB", "x-Ab", "en-x-AB", "en-a-b-ccc", "en-u-NU", "en-U-nu", "en-a-b",
|
||||
"xx-\u{e9}",
|
||||
] {
|
||||
assert!(!is_language_tag(bad), "{bad}");
|
||||
}
|
||||
|
|
|
|||
|
|
@ -31,7 +31,7 @@ pub use inventory::{
|
|||
Change, Family, InvId, Inventory, InventoryEntry, InventoryRevision, OptionLabel, OptionSet,
|
||||
Slot, ValueKind,
|
||||
};
|
||||
pub use lower::{EntityForms, LowerError, PhoneLine, TARGET_LANGUAGE, phones, pronounce};
|
||||
pub use lower::{EntityForms, LowerError, PhoneLine, TARGET_LANGUAGE, lower, phones, pronounce};
|
||||
pub use model::{AnswerFiles, ModelPort};
|
||||
pub use ontology::{Condition, Layer, Ontology, OntologyEntry, Test, select};
|
||||
pub use packet::{
|
||||
|
|
|
|||
|
|
@ -1,28 +1,52 @@
|
|||
//! The entity port and the ruled pronunciation of a packet's entities.
|
||||
//! The English template lowerer: the validated lowering view of a packet to
|
||||
//! text, by a fixed table keyed by inventory ids. It is the deterministic
|
||||
//! lowerer of `weksa lower`, the proof fixtures and their tests; the golf loop
|
||||
//! lowers through the `ModelPort` (`run.rs`, `Prompt::lower`), and follow-up
|
||||
//! `table-retirement` decides this table's future. It renders predications, referents and the
|
||||
//! speech act, and nothing else: no style, no model, no corpus text. It takes a
|
||||
//! [`LoweringInput`], so it cannot see the trace or the corpus item. A packet
|
||||
//! carrying a feature, relation, extension, role fill or referent it does not
|
||||
//! render is refused, because rendering part of a meaning would assert a different
|
||||
//! one (`polarity: negative` dropped says the opposite). Context, kind and
|
||||
//! constraints steer delivery and are not rendered; the concept of a predication
|
||||
//! must resolve but the frame owns the verb.
|
||||
//!
|
||||
//! Wording of a packet in a target language is the `ModelPort`'s answer to
|
||||
//! `Prompt::lower` (`context.rs`); nothing here produces lowered text. This
|
||||
//! module holds what the entity store owns and the lowering path reads: the
|
||||
//! narrow [`EntityForms`] port, the ruled IPA of every entity a packet cites
|
||||
//! ([`pronounce`]), and its segmentation into phones ([`phones`]). A referent
|
||||
//! that cites an entity is read through the port; an entity the port does not
|
||||
//! hold, one with no form or no ruled pronunciation in [`TARGET_LANGUAGE`], is
|
||||
//! refused, because spelling is not a pronunciation and there is no
|
||||
//! grapheme-to-phoneme guess to offer in its place.
|
||||
//! A referent that cites an entity renders as that entity's own form, read
|
||||
//! through the [`EntityForms`] port: the first (citation) form stored for
|
||||
//! [`TARGET_LANGUAGE`], verbatim. The choice is a table lookup on the language
|
||||
//! tag and the form's position, not a reading of the form. Forms after the
|
||||
//! first are inflected or particle-bound shapes; no English frame asks for one,
|
||||
//! so none is selected. An entity the port does not hold, or one with no form in
|
||||
//! the target language, is refused: the concept word would say a different
|
||||
//! thing than the name the packet cites.
|
||||
//!
|
||||
//! A request clause ("You asked Nibu to stop.") says what the addressee did, so
|
||||
//! it is gated on the packet's own record of it: `Discourse.addressee_consent`
|
||||
//! (set only by authoring or game telemetry, V15) must name that predication,
|
||||
//! and its agent must be the addressee. Without it the lowerer refuses
|
||||
//! ([`LowerError::ConsentMissing`], [`LowerError::AskerNotAddressee`]); it does
|
||||
//! not read wording or guess who asked. A consent naming any other predication
|
||||
//! is an unrendered slot.
|
||||
//!
|
||||
//! The table is a temporary owner. Each row speaks for an inventory entry and
|
||||
//! names the gloss it speaks for, so a row cannot outlive a change of what its id
|
||||
//! means. `language-ontology` moves the rows into ontology documents.
|
||||
|
||||
use std::fmt;
|
||||
|
||||
use serde::Serialize;
|
||||
|
||||
use crate::entity::Entity;
|
||||
use crate::packet::EntityId;
|
||||
use crate::inventory::{Family, InvId, Inventory};
|
||||
use crate::packet::{EntityId, NodeId, Predication};
|
||||
use crate::phones::{Phone, PhoneInventory, SegmentError};
|
||||
use crate::store::EntityStore;
|
||||
use crate::validate::LoweringInput;
|
||||
|
||||
/// The language tag of [`pronounce`] and [`phones`] only. The golf loop lowers
|
||||
/// each item in its own language and does not read this. Spelled as an
|
||||
/// entity's `LanguageForms::language` and a corpus item's language are.
|
||||
/// The language tag of the template table and the phones: what `weksa lower`
|
||||
/// says in. The golf loop lowers each item in its own language and does not
|
||||
/// read this. Spelled as an entity's `LanguageForms::language` and a corpus
|
||||
/// item's language are.
|
||||
pub const TARGET_LANGUAGE: &str = "en-US";
|
||||
|
||||
/// The lowerer's whole view of the entity store: one entity by id. Narrow so a
|
||||
|
|
@ -38,8 +62,98 @@ impl EntityForms for EntityStore {
|
|||
}
|
||||
}
|
||||
|
||||
/// `(inventory id, the gloss the row speaks for, surface)`.
|
||||
type Row = (&'static str, &'static str, &'static str);
|
||||
|
||||
/// Referent concepts, as the noun phrase after "the".
|
||||
const CONCEPTS: &[Row] = &[
|
||||
("concept:3", "player", "player"),
|
||||
("concept:4", "control", "control"),
|
||||
("concept:5", "ship_mind", "ship mind"),
|
||||
// The Dao De Jing test bed (`daodejing.rs`). Nouns, then the verbs a
|
||||
// `{verb}` frame speaks.
|
||||
("concept:7", "sage", "sage"),
|
||||
("concept:8", "mind", "minds"),
|
||||
("concept:9", "belly", "bellies"),
|
||||
("concept:10", "will", "wills"),
|
||||
("concept:11", "bone", "bones"),
|
||||
("concept:12", "empty", "empties"),
|
||||
("concept:13", "fill", "fills"),
|
||||
("concept:14", "weaken", "weakens"),
|
||||
("concept:15", "strengthen", "strengthens"),
|
||||
("concept:16", "heaven", "heaven"),
|
||||
("concept:17", "earth", "earth"),
|
||||
("concept:18", "is_long_enduring", "is long-enduring"),
|
||||
("concept:19", "continues_long", "continues long"),
|
||||
("concept:20", "highest_excellence", "highest excellence"),
|
||||
("concept:21", "water", "water"),
|
||||
("concept:22", "true_words", "words that are strictly true"),
|
||||
("concept:23", "seem_paradoxical", "seem paradoxical"),
|
||||
(
|
||||
"concept:24",
|
||||
"space_between_heaven_and_earth",
|
||||
"space between heaven and earth",
|
||||
),
|
||||
("concept:25", "bellows", "bellows"),
|
||||
("concept:26", "compare", "compare"),
|
||||
("concept:27", "resemble", "resemble"),
|
||||
];
|
||||
|
||||
/// Frames: the clause a predication of that frame says. `{gloss}` is the filler
|
||||
/// of the role whose inventory gloss it is.
|
||||
const FRAMES: &[Row] = &[
|
||||
(
|
||||
"frame:1",
|
||||
"hazard_warning",
|
||||
"{agent} may endanger {patient} by touching {instrument}",
|
||||
),
|
||||
("frame:2", "intervention", "{agent} will stop {patient}"),
|
||||
(
|
||||
"frame:3",
|
||||
"request_intervention",
|
||||
"{agent} asked {patient} to stop",
|
||||
),
|
||||
// The Dao De Jing test bed. Frame 4 was written from a Train chapter, 5 and
|
||||
// 6 from Validation chapters, 7 and 8 from Test chapters.
|
||||
("frame:4", "act", "{agent} {verb} {patient}"),
|
||||
("frame:5", "intransitive", "{experiencer} {verb}"),
|
||||
("frame:6", "likeness", "{experiencer} is like {goal}"),
|
||||
(
|
||||
"frame:7",
|
||||
"seems_paradoxical",
|
||||
"{experiencer} seem paradoxical",
|
||||
),
|
||||
(
|
||||
"frame:8",
|
||||
"may_be_compared",
|
||||
"{experiencer} may be compared to {goal}",
|
||||
),
|
||||
];
|
||||
|
||||
/// The frame of "{agent} asked {patient} to stop": the one frame that reads
|
||||
/// the discourse's addressee consent.
|
||||
const REQUEST_FRAME: &str = "frame:3";
|
||||
|
||||
/// Speech acts: the opener of the first sentence.
|
||||
const SPEECH_ACTS: &[Row] = &[
|
||||
("speech_act:1", "assert", ""),
|
||||
("speech_act:2", "ask", ""),
|
||||
("speech_act:5", "warn", "Warning: "),
|
||||
];
|
||||
|
||||
#[derive(Clone, Debug, PartialEq, Eq)]
|
||||
pub enum LowerError {
|
||||
/// The packet carries a slot the lowerer does not render.
|
||||
Unrendered { what: &'static str },
|
||||
/// No table row for an id the packet uses.
|
||||
NoRow { id: InvId },
|
||||
/// The row's gloss is not the gloss the inventory gives its id at the
|
||||
/// packet's revision, or the id does not resolve there.
|
||||
GlossMismatch { id: InvId, row: &'static str },
|
||||
/// A frame template names a role the inventory has no live entry for.
|
||||
UnknownRole { frame: InvId, role: String },
|
||||
/// The predication fills no role its frame's template needs.
|
||||
MissingRole { predication: NodeId, role: String },
|
||||
/// A referent cites an entity the entity port does not hold.
|
||||
UnknownEntity { entity: EntityId },
|
||||
/// The entity has no form in [`TARGET_LANGUAGE`].
|
||||
|
|
@ -51,7 +165,7 @@ pub enum LowerError {
|
|||
NoEntityReferent,
|
||||
/// Phones were requested for an entity whose ruled IPA holds a symbol the
|
||||
/// language's phone inventory does not list (or the language has no
|
||||
/// inventory). No phone is guessed.
|
||||
/// inventory). The lowerer does not guess a phone.
|
||||
UnknownPhone {
|
||||
entity: EntityId,
|
||||
at: usize,
|
||||
|
|
@ -60,18 +174,26 @@ pub enum LowerError {
|
|||
/// Phones were requested for an entity whose ruled IPA has a stress mark
|
||||
/// with no vowel after it.
|
||||
DanglingStress { entity: EntityId, at: usize },
|
||||
/// A request predication the packet does not carry the addressee's consent
|
||||
/// to: no consent, or a consent that names another predication. The
|
||||
/// lowerer does not guess who asked.
|
||||
ConsentMissing { predication: NodeId },
|
||||
/// A request predication whose agent is not the discourse addressee.
|
||||
AskerNotAddressee { predication: NodeId },
|
||||
/// The entity port failed to read.
|
||||
EntityRead { entity: EntityId, why: String },
|
||||
/// A lowering prompt was asked of a view whose scene was never read.
|
||||
SceneUnread,
|
||||
/// A referent cites the entity whose id is the lowering prompt's speaker
|
||||
/// token ([`crate::context::SPEAKER_TOKEN`]), which would read as the speaker.
|
||||
SpeakerTokenTaken,
|
||||
}
|
||||
|
||||
impl fmt::Display for LowerError {
|
||||
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
|
||||
f.write_str(match self {
|
||||
LowerError::Unrendered { .. } => "packet carries a slot the lowerer does not render",
|
||||
LowerError::NoRow { .. } => "no table row for an inventory id the packet uses",
|
||||
LowerError::GlossMismatch { .. } => "table row does not match the inventory's gloss",
|
||||
LowerError::UnknownRole { .. } => "frame template names a role the inventory lacks",
|
||||
LowerError::MissingRole { .. } => "predication fills no role its frame needs",
|
||||
LowerError::UnknownEntity { .. } => "referent cites an entity the port does not hold",
|
||||
LowerError::NoForm { .. } => "entity has no form in the target language",
|
||||
LowerError::NoPronunciation { .. } => "entity has no ruled pronunciation",
|
||||
|
|
@ -80,17 +202,148 @@ impl fmt::Display for LowerError {
|
|||
"ruled pronunciation holds a symbol with no listed phone"
|
||||
}
|
||||
LowerError::DanglingStress { .. } => "stress mark with no vowel after it",
|
||||
LowerError::ConsentMissing { .. } => "request lacks the addressee's consent",
|
||||
LowerError::AskerNotAddressee { .. } => "request agent is not the addressee",
|
||||
LowerError::EntityRead { .. } => "entity port failed to read",
|
||||
LowerError::SceneUnread => "the view's scene was never read",
|
||||
LowerError::SpeakerTokenTaken => {
|
||||
"a referent cites the entity id the speaker token uses"
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
impl std::error::Error for LowerError {}
|
||||
|
||||
fn row(
|
||||
table: &'static [Row],
|
||||
id: InvId,
|
||||
inv: &Inventory,
|
||||
rev: u32,
|
||||
) -> Result<&'static str, LowerError> {
|
||||
let (_, gloss, surface) = table
|
||||
.iter()
|
||||
.find(|(key, _, _)| *key == id.to_string())
|
||||
.ok_or(LowerError::NoRow { id })?;
|
||||
match inv.resolve(&id, rev) {
|
||||
Some(e) if e.gloss == *gloss => Ok(surface),
|
||||
_ => Err(LowerError::GlossMismatch { id, row: gloss }),
|
||||
}
|
||||
}
|
||||
|
||||
pub fn lower(
|
||||
input: &LoweringInput,
|
||||
inv: &Inventory,
|
||||
entities: &dyn EntityForms,
|
||||
) -> Result<String, LowerError> {
|
||||
let rev = input.inventory_rev();
|
||||
let unrendered = |what| Err(LowerError::Unrendered { what });
|
||||
if input.predications().is_empty() {
|
||||
return unrendered("no predication");
|
||||
}
|
||||
if !input.discourse().features.is_empty()
|
||||
|| input.referents().iter().any(|r| !r.features.is_empty())
|
||||
|| input.predications().iter().any(|p| !p.features.is_empty())
|
||||
{
|
||||
return unrendered("features");
|
||||
}
|
||||
request_gate(input, inv)?;
|
||||
if !input.relations().is_empty() {
|
||||
return unrendered("relations");
|
||||
}
|
||||
if !input.extensions().is_empty() {
|
||||
return unrendered("extensions");
|
||||
}
|
||||
let opener = match input.discourse().speech_act {
|
||||
Some(act) => row(SPEECH_ACTS, act, inv, rev)?,
|
||||
None => "",
|
||||
};
|
||||
let mut sentences = Vec::new();
|
||||
for p in input.predications() {
|
||||
sentences.push(clause(input, inv, entities, p)?);
|
||||
}
|
||||
let mentioned = |r: &NodeId| {
|
||||
input
|
||||
.predications()
|
||||
.iter()
|
||||
.any(|p| p.roles.iter().any(|f| &f.filler == r))
|
||||
};
|
||||
if input.referents().iter().any(|r| !mentioned(&r.id)) {
|
||||
return unrendered("a referent no role mentions");
|
||||
}
|
||||
let mut out = String::new();
|
||||
for (i, (clause, name_first)) in sentences.iter().enumerate() {
|
||||
if i > 0 {
|
||||
out.push(' ');
|
||||
}
|
||||
if i == 0 {
|
||||
out.push_str(opener);
|
||||
}
|
||||
let mut chars = clause.chars();
|
||||
if let Some(first) = chars.next() {
|
||||
// A name opens its clause as written; only template words are cased.
|
||||
if (i == 0 && !opener.is_empty()) || *name_first {
|
||||
out.push(first);
|
||||
} else {
|
||||
out.extend(first.to_uppercase());
|
||||
}
|
||||
out.push_str(chars.as_str());
|
||||
}
|
||||
out.push('.');
|
||||
}
|
||||
Ok(out)
|
||||
}
|
||||
|
||||
/// The one place consent is read. A request clause ([`REQUEST_FRAME`]) says what
|
||||
/// the addressee did, so it needs the packet's own record of it: the discourse
|
||||
/// `addressee_consent`, which validation lets only authoring or game telemetry
|
||||
/// set (V15), must name that predication, and its agent must be the addressee.
|
||||
/// Nothing here reads wording. A consent naming any other predication is a slot
|
||||
/// the lowerer does not render.
|
||||
fn request_gate(input: &LoweringInput, inv: &Inventory) -> Result<(), LowerError> {
|
||||
let consent = input.discourse().addressee_consent.as_ref();
|
||||
let requests = input
|
||||
.predications()
|
||||
.iter()
|
||||
.filter(|p| p.frame.to_string() == REQUEST_FRAME);
|
||||
for p in requests {
|
||||
if consent != Some(&p.id) {
|
||||
return Err(LowerError::ConsentMissing {
|
||||
predication: p.id.clone(),
|
||||
});
|
||||
}
|
||||
let agent = inv
|
||||
.entries()
|
||||
.find(|e| {
|
||||
e.family() == Family::Role && e.gloss == "agent" && e.live_at(input.inventory_rev())
|
||||
})
|
||||
.ok_or_else(|| LowerError::UnknownRole {
|
||||
frame: p.frame,
|
||||
role: "agent".to_string(),
|
||||
})?;
|
||||
let asker = p
|
||||
.roles
|
||||
.iter()
|
||||
.find(|r| r.role == agent.id)
|
||||
.map(|r| &r.filler);
|
||||
if asker.is_none() || asker != input.discourse().addressee.as_ref() {
|
||||
return Err(LowerError::AskerNotAddressee {
|
||||
predication: p.id.clone(),
|
||||
});
|
||||
}
|
||||
}
|
||||
match consent {
|
||||
Some(_)
|
||||
if !input
|
||||
.predications()
|
||||
.iter()
|
||||
.any(|p| p.frame.to_string() == REQUEST_FRAME) =>
|
||||
{
|
||||
Err(LowerError::Unrendered {
|
||||
what: "addressee consent",
|
||||
})
|
||||
}
|
||||
_ => Ok(()),
|
||||
}
|
||||
}
|
||||
|
||||
/// The ruled IPA of every entity a packet cites, one per entity referent in
|
||||
/// the packet's referent order, as stored: bare, stress-marked, nothing
|
||||
/// derived. A rejected pronunciation is never read. An entity the port does not
|
||||
|
|
@ -167,6 +420,91 @@ fn ruled(
|
|||
Ok(out)
|
||||
}
|
||||
|
||||
fn clause(
|
||||
input: &LoweringInput,
|
||||
inv: &Inventory,
|
||||
entities: &dyn EntityForms,
|
||||
p: &Predication,
|
||||
) -> Result<(String, bool), LowerError> {
|
||||
let rev = input.inventory_rev();
|
||||
let template = row(FRAMES, p.frame, inv, rev)?;
|
||||
let mut said: Vec<&NodeId> = Vec::new();
|
||||
let mut out = String::new();
|
||||
let mut name_first = false;
|
||||
let mut rest = template;
|
||||
while let Some(open) = rest.find('{') {
|
||||
out.push_str(&rest[..open]);
|
||||
let close = rest[open..].find('}').map_or(rest.len(), |c| open + c);
|
||||
let name = &rest[open + 1..close];
|
||||
rest = &rest[(close + 1).min(rest.len())..];
|
||||
if name == "verb" {
|
||||
out.push_str(row(CONCEPTS, p.concept, inv, rev)?);
|
||||
continue;
|
||||
}
|
||||
let role = inv
|
||||
.entries()
|
||||
.find(|e| e.family() == Family::Role && e.gloss == name && e.live_at(rev))
|
||||
.ok_or_else(|| LowerError::UnknownRole {
|
||||
frame: p.frame,
|
||||
role: name.to_string(),
|
||||
})?;
|
||||
let fill =
|
||||
p.roles
|
||||
.iter()
|
||||
.find(|r| r.role == role.id)
|
||||
.ok_or_else(|| LowerError::MissingRole {
|
||||
predication: p.id.clone(),
|
||||
role: name.to_string(),
|
||||
})?;
|
||||
let (phrase, is_name) = filler(input, inv, entities, &fill.filler, &said)?;
|
||||
name_first |= is_name && out.is_empty();
|
||||
out.push_str(&phrase);
|
||||
said.push(&fill.filler);
|
||||
}
|
||||
out.push_str(rest);
|
||||
if p.roles.len() != said.len() {
|
||||
return Err(LowerError::Unrendered {
|
||||
what: "a role the frame does not name",
|
||||
});
|
||||
}
|
||||
Ok((out, name_first))
|
||||
}
|
||||
|
||||
/// A role filler as a phrase: the addressee is "you", a predication is "that",
|
||||
/// another referent is its entity's citation form when it cites one, else "the"
|
||||
/// and its concept word. The addressee said twice in
|
||||
/// one predication is reflexive; no other referent is, because the packet has no
|
||||
/// animacy to choose "themself" or "itself" by.
|
||||
fn filler(
|
||||
input: &LoweringInput,
|
||||
inv: &Inventory,
|
||||
entities: &dyn EntityForms,
|
||||
node: &NodeId,
|
||||
said: &[&NodeId],
|
||||
) -> Result<(String, bool), LowerError> {
|
||||
let again = said.contains(&node);
|
||||
if let Some(r) = input.referents().iter().find(|r| &r.id == node) {
|
||||
if input.discourse().addressee.as_ref() == Some(node) {
|
||||
return Ok((if again { "yourself" } else { "you" }.to_string(), false));
|
||||
}
|
||||
if let Some(id) = &r.entity {
|
||||
return Ok((name(entities, id)?, true));
|
||||
}
|
||||
let word = row(CONCEPTS, r.concept, inv, input.inventory_rev())?;
|
||||
return Ok((format!("the {word}"), false));
|
||||
}
|
||||
Ok(("that".to_string(), false))
|
||||
}
|
||||
|
||||
/// The entity's citation form in [`TARGET_LANGUAGE`].
|
||||
fn name(entities: &dyn EntityForms, id: &EntityId) -> Result<String, LowerError> {
|
||||
entity(entities, id)?
|
||||
.forms_in(TARGET_LANGUAGE)
|
||||
.and_then(<[String]>::first)
|
||||
.cloned()
|
||||
.ok_or_else(|| LowerError::NoForm { entity: id.clone() })
|
||||
}
|
||||
|
||||
pub(crate) fn entity(entities: &dyn EntityForms, id: &EntityId) -> Result<Entity, LowerError> {
|
||||
entities
|
||||
.entity(id)
|
||||
|
|
|
|||
|
|
@ -1,26 +1,26 @@
|
|||
//! The `weksa` command line: the same validator and store admission the library
|
||||
//! exposes, plus text projections (`dump`) that are for review and are not stores.
|
||||
|
||||
use std::path::{Path, PathBuf};
|
||||
use std::path::PathBuf;
|
||||
|
||||
use anyhow::{Context, Result, bail};
|
||||
use clap::error::{ContextKind, ContextValue, ErrorKind};
|
||||
use clap::{Args, Parser, Subcommand, ValueEnum};
|
||||
use unicode_normalization::UnicodeNormalization;
|
||||
use weksa::corpus::{CorpusItem, ModelFamily, NameSpan, Source, Turn};
|
||||
use weksa::encode::{EditDraft, MarkedLine, OntologyDraft, WorkDraft};
|
||||
use weksa::encode::{EditDraft, OntologyDraft};
|
||||
use weksa::entity::{Entity, EntityOrigin, LanguageForms, Pronunciation};
|
||||
use weksa::inventory::{proof_revision, seed, speaker_scene_revision};
|
||||
use weksa::packet::{FeatValue, FeatureValue, Grade};
|
||||
use weksa::packet::proof_packet;
|
||||
use weksa::model::{ModelPort, RecordedAnswers};
|
||||
use weksa::model::RecordedAnswers;
|
||||
use weksa::run::{
|
||||
AblationOutcome, CalibrateOutcome, CycleOutcome, FLOOR_ARMS_MIN, LowererReach, OntologyMintOutcome, RecallOutcome, RelowerOutcome, RoundOutcome, RunPaths, RunStores, cycle, round,
|
||||
AblationOutcome, CycleOutcome, LowererReach, OntologyMintOutcome, RecallOutcome, RoundOutcome, RunPaths, RunStores, cycle, round,
|
||||
};
|
||||
use weksa::score::ScoreInput;
|
||||
use weksa::{
|
||||
Annotator, CorpusStore, EntityId, EntityStore, Family, InventoryStore, OllamaEmbedder, OntologyStore, OptionLabel,
|
||||
PacketStore, PairRelation, Party, Scene, Slot, SpeakerStateStore, ValueKind, Scorer, Split, SplitScheme, StoreError, StoreRefusal, pronounce, validate,
|
||||
PacketStore, PairRelation, Party, Scene, Slot, SpeakerStateStore, ValueKind, Scorer, Split, SplitScheme, StoreError, lower, pronounce, validate,
|
||||
};
|
||||
|
||||
#[derive(Parser)]
|
||||
|
|
@ -64,14 +64,17 @@ enum Command {
|
|||
Scene(SceneCommand),
|
||||
#[command(subcommand)]
|
||||
Packet(PacketCommand),
|
||||
/// Print the ruled IPA of each entity a stored packet cites, one per line;
|
||||
/// refused for an entity with no ruled pronunciation.
|
||||
Pronounce {
|
||||
/// Lower a stored packet to English text.
|
||||
Lower {
|
||||
store: PathBuf,
|
||||
key: String,
|
||||
/// Print the phones line of each entity instead, one JSON object per
|
||||
/// line ({language, source, phones: [{ipa, stress}]}); refused for a
|
||||
/// phone the inventory lacks.
|
||||
/// Print the ruled IPA of each entity the packet cites, one per line,
|
||||
/// instead of the text; refused for an entity with no ruled pronunciation.
|
||||
#[arg(long, conflicts_with = "phones")]
|
||||
ipa: bool,
|
||||
/// Print the phones line of each entity the packet cites, one JSON
|
||||
/// object per line ({language, source, phones: [{ipa, stress}]}),
|
||||
/// instead of the text; refused for a phone the inventory lacks.
|
||||
#[arg(long)]
|
||||
phones: bool,
|
||||
},
|
||||
|
|
@ -150,58 +153,10 @@ enum LoopCommand {
|
|||
#[arg(long, default_value = "http://127.0.0.1:11434")]
|
||||
ollama_url: String,
|
||||
},
|
||||
/// Re-lower round ROUND's Validation packets through arm ARM, score them
|
||||
/// against the items, and, with --floor ARM given two or more times (prompted
|
||||
/// repeats of the lowering), decide against the paired noise floor of those
|
||||
/// repeats by the panel accept rule. Prompts and answers live in
|
||||
/// `<ROOT>/relower-<ROUND>-<ARM>`; the command exits 3 until the arm is
|
||||
/// answered. --lowerer names the arm's model in the printed line. A
|
||||
/// diagnostic, never a gate; records nothing; Test and Train are never
|
||||
/// touched. Labels match [a-z0-9-]{1,32} and differ.
|
||||
Relower {
|
||||
root: PathBuf,
|
||||
#[arg(long)]
|
||||
round: u32,
|
||||
#[arg(long)]
|
||||
arm: String,
|
||||
#[arg(long)]
|
||||
lowerer: String,
|
||||
#[arg(long)]
|
||||
floor: Vec<String>,
|
||||
#[arg(long, default_value = "http://127.0.0.1:11434")]
|
||||
ollama_url: String,
|
||||
},
|
||||
/// Replay the accept rule over answered relower draws of round ROUND, to
|
||||
/// measure how often it accepts, rejects or regresses what it should. Reads
|
||||
/// the recorded lowering and each draw (--prompted: repeats of it, at least
|
||||
/// four; --degraded: arms that should regress; --candidate: arms to rate),
|
||||
/// answered through `weksa loop relower ROOT --round N --arm LABEL`, and
|
||||
/// prints counts over all Validation items and over each --class
|
||||
/// NAME=PREFIX[,PREFIX...] (items whose key starts with a prefix). Writes
|
||||
/// no prompts; exits 1 naming the draws still unanswered. Procedure:
|
||||
/// docs/calibration.md. A diagnostic, never a gate; records nothing; Test
|
||||
/// and Train are never touched. Labels match [a-z0-9-]{1,32} and differ.
|
||||
Calibrate {
|
||||
root: PathBuf,
|
||||
#[arg(long)]
|
||||
round: u32,
|
||||
#[arg(long)]
|
||||
prompted: Vec<String>,
|
||||
#[arg(long)]
|
||||
degraded: Vec<String>,
|
||||
#[arg(long)]
|
||||
candidate: Vec<String>,
|
||||
#[arg(long)]
|
||||
class: Vec<String>,
|
||||
#[arg(long, default_value = "http://127.0.0.1:11434")]
|
||||
ollama_url: String,
|
||||
},
|
||||
/// Run one edit-accept cycle of the run at ROOT. The stores are read only
|
||||
/// from the run's record. The editor's prompt, then the candidate round's
|
||||
/// encode prompts, then its lowering prompts are written in turn; the
|
||||
/// command exits 3 each time until every prompt has an answer. The noise
|
||||
/// floor needs four recorded rounds under the first inventory (the recorded
|
||||
/// round and three prompted repeats).
|
||||
/// command exits 3 each time until every prompt has an answer.
|
||||
Cycle {
|
||||
root: PathBuf,
|
||||
#[arg(long, default_value = "http://127.0.0.1:11434")]
|
||||
|
|
@ -239,22 +194,6 @@ enum CorpusCommand {
|
|||
Withdraw {
|
||||
key: String,
|
||||
},
|
||||
/// Import a transcribed public-domain work: mint its cast as entities and
|
||||
/// add each line a name-span answer covers (`docs/name-span-annotation.md`).
|
||||
Import {
|
||||
/// The work file: provenance, cast, lines.
|
||||
work: PathBuf,
|
||||
/// The annotator's answer: one `{"line": N, "marked": "..."}` per line.
|
||||
names: PathBuf,
|
||||
#[arg(long, requires = "generator", conflicts_with = "operator")]
|
||||
model_family: Option<ModelFamilyArg>,
|
||||
/// The attestation string naming the annotating model.
|
||||
#[arg(long, requires = "model_family")]
|
||||
generator: Option<String>,
|
||||
/// Annotated by the operator, not a model.
|
||||
#[arg(long)]
|
||||
operator: bool,
|
||||
},
|
||||
}
|
||||
|
||||
#[derive(Subcommand)]
|
||||
|
|
@ -694,17 +633,10 @@ impl AddArgs {
|
|||
supersedes: self.supersedes,
|
||||
withdrawn: false,
|
||||
names,
|
||||
names_by: None,
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
/// A draw or arm label: [a-z0-9-]{1,32}.
|
||||
fn is_label(l: &str) -> bool {
|
||||
(1..=32).contains(&l.len())
|
||||
&& l.bytes().all(|b| b.is_ascii_lowercase() || b.is_ascii_digit() || b == b'-')
|
||||
}
|
||||
|
||||
/// The split of an item as `Train`, `Validation`, `Test` or `excluded`.
|
||||
fn split_text(item: &CorpusItem) -> String {
|
||||
SplitScheme::V1
|
||||
|
|
@ -712,22 +644,6 @@ fn split_text(item: &CorpusItem) -> String {
|
|||
.map_or_else(|| "excluded".to_string(), |s| format!("{s:?}"))
|
||||
}
|
||||
|
||||
/// The annotator the flags name: a model family with its generator, or the operator.
|
||||
fn annotator(
|
||||
model_family: Option<ModelFamilyArg>,
|
||||
generator: Option<String>,
|
||||
operator: bool,
|
||||
) -> Result<Annotator> {
|
||||
match (model_family, generator, operator) {
|
||||
(Some(family), Some(generator), false) => Ok(Annotator::Model {
|
||||
family: family.into(),
|
||||
generator,
|
||||
}),
|
||||
(None, None, true) => Ok(Annotator::Operator),
|
||||
_ => bail!("name the annotator: --model-family with --generator, or --operator"),
|
||||
}
|
||||
}
|
||||
|
||||
fn refused(e: StoreError) -> anyhow::Error {
|
||||
anyhow::anyhow!("{e}")
|
||||
}
|
||||
|
|
@ -767,78 +683,13 @@ fn main() -> Result<()> {
|
|||
.map_err(refused)?;
|
||||
println!("{outcome:?} {key}");
|
||||
}
|
||||
Command::Corpus(CorpusCommand::Import {
|
||||
work,
|
||||
names,
|
||||
model_family,
|
||||
generator,
|
||||
operator,
|
||||
}) => {
|
||||
let annotator = annotator(model_family, generator, operator)?;
|
||||
let draft = WorkDraft::parse(&std::fs::read_to_string(&work)?)?;
|
||||
let mut marked = Vec::new();
|
||||
for (i, line) in std::fs::read_to_string(&names)?.lines().enumerate() {
|
||||
if line.trim().is_empty() {
|
||||
continue;
|
||||
}
|
||||
marked.push(
|
||||
MarkedLine::parse(line)
|
||||
.map_err(|e| anyhow::anyhow!("names line {}: {e}", i + 1))?,
|
||||
);
|
||||
}
|
||||
let (new_entities, items) = draft.into_import(&marked, &annotator)?;
|
||||
// Every document passes the real doors on scratch copies of the
|
||||
// stores before the first write, so a refusal leaves them untouched.
|
||||
let scratch = std::env::temp_dir().join(format!("weksa-import-{}", std::process::id()));
|
||||
std::fs::create_dir_all(&scratch)?;
|
||||
let dry = (|| -> Result<()> {
|
||||
let copy = |from: &Path, name: &str| -> Result<PathBuf> {
|
||||
let to = scratch.join(name);
|
||||
if from.exists() {
|
||||
std::fs::copy(from, &to)?;
|
||||
}
|
||||
Ok(to)
|
||||
};
|
||||
let mut entities = EntityStore::open(©(&cli.entities, "e.cc")?)?;
|
||||
let mut store = CorpusStore::open(©(&cli.corpus, "c.cc")?)?;
|
||||
for e in new_entities.clone() {
|
||||
entities
|
||||
.put(e)
|
||||
.map_err(|e| anyhow::anyhow!("a cast entity: {e}"))?;
|
||||
}
|
||||
for item in items.clone() {
|
||||
let key = item.id.clone();
|
||||
store.add(item, &entities).map_err(|e| match e {
|
||||
StoreError::Refused(StoreRefusal::S6TextHeld { held_by, .. }) => {
|
||||
anyhow::anyhow!("{key} repeats the text of {held_by}")
|
||||
}
|
||||
e => anyhow::anyhow!("{key}: {e}"),
|
||||
})?;
|
||||
}
|
||||
Ok(())
|
||||
})();
|
||||
let _ = std::fs::remove_dir_all(&scratch);
|
||||
dry?;
|
||||
let mut entities = EntityStore::open(&cli.entities)?;
|
||||
for e in new_entities {
|
||||
let id = e.id.clone();
|
||||
let outcome = entities.put(e).map_err(refused)?;
|
||||
println!("{outcome:?} {id}");
|
||||
}
|
||||
let mut store = CorpusStore::open(&cli.corpus)?;
|
||||
for item in items {
|
||||
let (key, split) = (item.id.clone(), split_text(&item));
|
||||
let outcome = store.add(item, &entities).map_err(refused)?;
|
||||
println!("{outcome:?} {key} {split}");
|
||||
}
|
||||
}
|
||||
Command::Corpus(CorpusCommand::Dump) => {
|
||||
for i in CorpusStore::open(&cli.corpus)?.all()? {
|
||||
let split = split_text(&i);
|
||||
let withdrawn = if i.withdrawn { " withdrawn" } else { "" };
|
||||
println!(
|
||||
"{} [{} {} group={} {split}{withdrawn}]\n {:?}\n names: {:?} by {:?}\n source: {:?}",
|
||||
i.id, i.language, i.speaker, i.group, i.text, i.names, i.names_by, i.source
|
||||
"{} [{} {} group={} {split}{withdrawn}]\n {:?}\n names: {:?}\n source: {:?}",
|
||||
i.id, i.language, i.speaker, i.group, i.text, i.names, i.source
|
||||
);
|
||||
}
|
||||
}
|
||||
|
|
@ -975,7 +826,14 @@ fn main() -> Result<()> {
|
|||
generator,
|
||||
operator,
|
||||
}) => {
|
||||
let annotator = annotator(model_family, generator, operator)?;
|
||||
let annotator = match (model_family, generator, operator) {
|
||||
(Some(family), Some(generator), false) => Annotator::Model {
|
||||
family: family.into(),
|
||||
generator,
|
||||
},
|
||||
(None, None, true) => Annotator::Operator,
|
||||
_ => bail!("name the annotator: --model-family with --generator, or --operator"),
|
||||
};
|
||||
let inventory_store = InventoryStore::open(&cli.inventory)?;
|
||||
let inventory = inventory_store.inventory()?;
|
||||
let corpus = CorpusStore::open(&cli.corpus)?;
|
||||
|
|
@ -1117,8 +975,14 @@ fn main() -> Result<()> {
|
|||
.map_err(refused)?;
|
||||
println!("admitted {key}");
|
||||
}
|
||||
Command::Pronounce { store, key, phones } => {
|
||||
Command::Lower {
|
||||
store,
|
||||
key,
|
||||
ipa,
|
||||
phones,
|
||||
} => {
|
||||
let inventory_store = InventoryStore::open(&cli.inventory)?;
|
||||
let inventory = inventory_store.inventory()?;
|
||||
let mut packets = PacketStore::open(&store)?;
|
||||
let packet = packets.get(&key)?.context("no such packet")?;
|
||||
// Admission is the only source of a LoweringInput; re-admitting the
|
||||
|
|
@ -1132,14 +996,16 @@ fn main() -> Result<()> {
|
|||
)
|
||||
.map_err(refused)?;
|
||||
let entities = EntityStore::open(&cli.entities)?;
|
||||
if phones {
|
||||
if ipa {
|
||||
for line in pronounce(&view, &entities)? {
|
||||
println!("{line}");
|
||||
}
|
||||
} else if phones {
|
||||
for line in weksa::phones(&view, &entities)? {
|
||||
println!("{}", serde_json::to_string(&line)?);
|
||||
}
|
||||
} else {
|
||||
for line in pronounce(&view, &entities)? {
|
||||
println!("{line}");
|
||||
}
|
||||
println!("{}", lower(&view, &inventory, &entities)?);
|
||||
}
|
||||
}
|
||||
Command::Score(args) => {
|
||||
|
|
@ -1249,156 +1115,6 @@ fn main() -> Result<()> {
|
|||
}
|
||||
}
|
||||
}
|
||||
Command::Loop(LoopCommand::Relower {
|
||||
root,
|
||||
round,
|
||||
arm,
|
||||
lowerer,
|
||||
floor,
|
||||
ollama_url,
|
||||
}) => {
|
||||
if !is_label(&arm)
|
||||
|| floor.iter().any(|f| !is_label(f) || *f == arm)
|
||||
|| floor.iter().enumerate().any(|(i, f)| floor[..i].contains(f))
|
||||
{
|
||||
anyhow::bail!("arm and floor labels must match [a-z0-9-]{{1,32}} and differ");
|
||||
}
|
||||
let run = RunStores::open(&root)?;
|
||||
let mut recorded = RecordedAnswers::new(
|
||||
root.join(format!("round-{round}")),
|
||||
run.record().model.clone(),
|
||||
);
|
||||
let mut files = run.answer_files(run.relower_dir(round, &arm))?;
|
||||
let mut floor_ports: Vec<RecordedAnswers> = floor
|
||||
.iter()
|
||||
.map(|f| RecordedAnswers::new(run.relower_dir(round, f), run.record().model.clone()))
|
||||
.collect();
|
||||
let mut floor_dyn: Vec<&mut dyn ModelPort> =
|
||||
floor_ports.iter_mut().map(|p| p as &mut dyn ModelPort).collect();
|
||||
let scorer = Scorer::new(OllamaEmbedder::new(&ollama_url, &run.record().embedder));
|
||||
match run.relower(
|
||||
round,
|
||||
&arm,
|
||||
&mut recorded,
|
||||
&mut files,
|
||||
&mut floor_dyn,
|
||||
&scorer,
|
||||
)? {
|
||||
RelowerOutcome::Unanswered { prompts } => {
|
||||
for digest in &prompts {
|
||||
println!("unanswered {digest}");
|
||||
}
|
||||
println!("unanswered {} prompts", prompts.len());
|
||||
std::process::exit(3);
|
||||
}
|
||||
RelowerOutcome::Read { languages, verdict } => {
|
||||
for l in languages {
|
||||
println!(
|
||||
"{}",
|
||||
run.labelled(&format!("{} arm={arm} lowerer={lowerer}", l.line()))
|
||||
);
|
||||
}
|
||||
if let Some(v) = verdict {
|
||||
println!("verdict {v:?}");
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
Command::Loop(LoopCommand::Calibrate {
|
||||
root,
|
||||
round,
|
||||
prompted,
|
||||
degraded,
|
||||
candidate,
|
||||
class,
|
||||
ollama_url,
|
||||
}) => {
|
||||
let labels: Vec<&String> = prompted.iter().chain(°raded).chain(&candidate).collect();
|
||||
if labels.iter().any(|l| !is_label(l))
|
||||
|| labels.iter().enumerate().any(|(i, l)| labels[..i].contains(l))
|
||||
{
|
||||
anyhow::bail!("draw labels must match [a-z0-9-]{{1,32}} and differ");
|
||||
}
|
||||
if prompted.len() < FLOOR_ARMS_MIN + 1 {
|
||||
anyhow::bail!("at least {} --prompted labels are needed", FLOOR_ARMS_MIN + 1);
|
||||
}
|
||||
let mut classes: Vec<(String, Vec<String>)> = Vec::new();
|
||||
for c in &class {
|
||||
let Some((name, prefixes)) = c.split_once('=') else {
|
||||
anyhow::bail!("--class is NAME=PREFIX[,PREFIX...]");
|
||||
};
|
||||
if !is_label(name)
|
||||
|| name == "all"
|
||||
|| classes.iter().any(|(n, _)| n == name)
|
||||
|| prefixes.split(',').any(str::is_empty)
|
||||
{
|
||||
anyhow::bail!("--class is NAME=PREFIX[,PREFIX...] with a new label NAME other than all");
|
||||
}
|
||||
classes.push((name.to_string(), prefixes.split(',').map(String::from).collect()));
|
||||
}
|
||||
let run = RunStores::open(&root)?;
|
||||
let scorer = Scorer::new(OllamaEmbedder::new(&ollama_url, &run.record().embedder));
|
||||
match run.calibrate(round, &prompted, °raded, &candidate, &classes, &scorer)? {
|
||||
CalibrateOutcome::Unanswered(missing) => {
|
||||
for (label, n) in &missing {
|
||||
println!("unanswered {label} {n}");
|
||||
}
|
||||
eprintln!(
|
||||
"answer it through weksa loop relower ROOT --round N --arm LABEL first"
|
||||
);
|
||||
std::process::exit(1);
|
||||
}
|
||||
CalibrateOutcome::Read { unusable, classes } => {
|
||||
println!(
|
||||
"{}",
|
||||
run.labelled(&format!(
|
||||
"calibrate draws prompted={} degraded={} candidate={} floor-arms={FLOOR_ARMS_MIN} unusable={unusable}",
|
||||
prompted.len(),
|
||||
degraded.len(),
|
||||
candidate.len(),
|
||||
))
|
||||
);
|
||||
for c in classes {
|
||||
let items: String = c
|
||||
.languages
|
||||
.iter()
|
||||
.map(|l| format!(" {} n={} skipped={}", l.language, l.n, l.skipped))
|
||||
.collect();
|
||||
let t = &c.trials;
|
||||
println!("{}", run.labelled(&format!("calibrate class={} items{items}", c.name)));
|
||||
println!(
|
||||
"{}",
|
||||
run.labelled(&format!(
|
||||
"calibrate class={} prompted trials={} nogain={} accepted={} regressed={} noise={:.4}",
|
||||
c.name, t.prompted.trials, t.prompted.nogain, t.prompted.accepted, t.prompted.regressed, t.noise
|
||||
))
|
||||
);
|
||||
for (side, k) in t.r_roles() {
|
||||
println!(
|
||||
"{}",
|
||||
run.labelled(&format!("calibrate class={} prompted-{side} {}", c.name, k.line()))
|
||||
);
|
||||
}
|
||||
for line in c.degraded_lines(°raded) {
|
||||
println!("{}", run.labelled(&format!("calibrate class={} {line}", c.name)));
|
||||
}
|
||||
println!(
|
||||
"{}",
|
||||
run.labelled(&format!(
|
||||
"calibrate class={} candidate trials={} accepted={} nogain={} regressed={}",
|
||||
c.name, t.candidate.trials, t.candidate.accepted, t.candidate.nogain, t.candidate.regressed
|
||||
))
|
||||
);
|
||||
for (label, k) in candidate.iter().zip(&t.candidate_arms) {
|
||||
println!(
|
||||
"{}",
|
||||
run.labelled(&format!("calibrate class={} candidate={label} {}", c.name, k.line()))
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
Command::Loop(LoopCommand::Recall { root }) => {
|
||||
let run = RunStores::open(&root)?;
|
||||
let mut files = run.answer_files(run.recall_dir())?;
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load diff
|
|
@ -1,21 +0,0 @@
|
|||
//! 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()))
|
||||
);
|
||||
}
|
||||
|
|
@ -28,7 +28,7 @@ pub struct ScoreInput<'a> {
|
|||
pub output: &'a str,
|
||||
}
|
||||
|
||||
#[derive(Clone, Debug, PartialEq, Serialize, Deserialize, JsonSchema)]
|
||||
#[derive(Clone, Debug, PartialEq)]
|
||||
pub struct ItemScore {
|
||||
/// chrF of the output against the reference.
|
||||
pub chrf: f64,
|
||||
|
|
@ -131,18 +131,13 @@ pub struct Aggregate {
|
|||
pub validation: SplitMean,
|
||||
}
|
||||
|
||||
/// The scores of the items read in split `want`, in list order.
|
||||
fn scores_in<'a>(scored: &'a [(&CorpusItem, ItemScore)], want: Split) -> Vec<&'a ItemScore> {
|
||||
scored
|
||||
/// The mean of the scores of the items read in split `want`.
|
||||
fn split_mean(scored: &[(&CorpusItem, ItemScore)], want: Split) -> SplitMean {
|
||||
let of: Vec<&ItemScore> = scored
|
||||
.iter()
|
||||
.filter(|(item, _)| SplitScheme::V1.live(item) == Some(want))
|
||||
.map(|(_, score)| score)
|
||||
.collect()
|
||||
}
|
||||
|
||||
/// The mean of the scores of the items read in split `want`.
|
||||
fn split_mean(scored: &[(&CorpusItem, ItemScore)], want: Split) -> SplitMean {
|
||||
let of = scores_in(scored, want);
|
||||
.collect();
|
||||
let average = |values: Vec<f64>| {
|
||||
(!values.is_empty()).then(|| values.iter().sum::<f64>() / values.len() as f64)
|
||||
};
|
||||
|
|
@ -162,12 +157,6 @@ pub fn aggregate(scored: &[(&CorpusItem, ItemScore)]) -> Aggregate {
|
|||
}
|
||||
}
|
||||
|
||||
/// The Validation items' scores in list order, numbers only: no key, no text.
|
||||
/// A refused item arrives scored 0 and keeps its position.
|
||||
pub fn validation_items(scored: &[(&CorpusItem, ItemScore)]) -> Vec<ItemScore> {
|
||||
scores_in(scored, Split::Validation).into_iter().cloned().collect()
|
||||
}
|
||||
|
||||
/// The Test split's readings, scalars only: no item key, no minted string, no
|
||||
/// pair. The checkpoint decision (convergence-test) needs numbers; a key beside
|
||||
/// a minted string is the handle an edit step would act on. The only producer
|
||||
|
|
@ -260,31 +249,6 @@ mod tests {
|
|||
item(key, text, &group_in(split), model)
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn validation_items_keeps_validation_only_in_order() {
|
||||
let train = in_split("item:t:1", UNRELATED, Split::Train, false);
|
||||
let first = in_split("item:v:1", "first words", Split::Validation, false);
|
||||
let refused = in_split("item:v:2", "second words", Split::Validation, false);
|
||||
let last = in_split("item:v:3", "third words", Split::Validation, false);
|
||||
let mut gone = in_split("item:v:4", "withdrawn words", Split::Validation, false);
|
||||
gone.withdrawn = true;
|
||||
let test = in_split("item:c:1", HELD_OUT, Split::Test, false);
|
||||
let scored = [
|
||||
(&train, score(10.0, Some(0.1))),
|
||||
(&first, score(40.0, Some(0.4))),
|
||||
(&test, score(60.0, Some(0.6))),
|
||||
(&refused, score(0.0, Some(0.0))),
|
||||
(&gone, score(90.0, Some(0.9))),
|
||||
(&last, score(80.0, None)),
|
||||
];
|
||||
let got = validation_items(&scored);
|
||||
assert_eq!(
|
||||
got,
|
||||
[score(40.0, Some(0.4)), score(0.0, Some(0.0)), score(80.0, None)]
|
||||
);
|
||||
assert_eq!(got.len(), aggregate(&scored).validation.count);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_readings_at_checkpoint() {
|
||||
let train_item = in_split("item:t:1", UNRELATED, Split::Train, false);
|
||||
|
|
|
|||
|
|
@ -172,9 +172,6 @@ impl Checkpoint {
|
|||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod mutants;
|
||||
|
||||
/// Item builders for the unit tests that live in `src`: the twins of
|
||||
/// `tests/common`'s `group_in_bucket`, `item_in`, `cast` and `model`.
|
||||
#[cfg(test)]
|
||||
|
|
@ -211,7 +208,6 @@ pub(crate) mod fixture {
|
|||
language: "en-US".into(),
|
||||
speaker: EntityId::parse("entity:nibu").unwrap(),
|
||||
names: vec![],
|
||||
names_by: None,
|
||||
group: group.into(),
|
||||
prior_turns: vec![],
|
||||
source,
|
||||
|
|
|
|||
|
|
@ -1,11 +0,0 @@
|
|||
//! Pins of private items of `split` found unpinned by mutation testing.
|
||||
|
||||
use super::Checkpoint;
|
||||
|
||||
/// A checkpoint reports the round it was declared at, whatever the round.
|
||||
#[test]
|
||||
fn a_checkpoint_reports_its_round() {
|
||||
assert_eq!(Checkpoint::for_test(7).round(), 7);
|
||||
assert_eq!(Checkpoint::for_test(0).round(), 0);
|
||||
assert_eq!(Checkpoint::for_test(1).round(), 1);
|
||||
}
|
||||
|
|
@ -344,9 +344,6 @@ impl CorpusStore {
|
|||
if let Some(why) = empty_attestation(&item.source) {
|
||||
return Err(malformed(&item.id, why));
|
||||
}
|
||||
if let Some(by) = &item.names_by {
|
||||
check_annotator(&item.id, by)?;
|
||||
}
|
||||
check_entities(&item, entities)?;
|
||||
for held in self.all()? {
|
||||
if normalized(&held.text) == text && item.supersedes.as_deref() != Some(&held.id) {
|
||||
|
|
@ -490,13 +487,13 @@ pub(crate) fn normalized(text: &str) -> String {
|
|||
}
|
||||
|
||||
/// The one-to-one folds `normalized` adds to NFKC and case folding, applied
|
||||
/// before the case fold. (U+0130 needs no arm: it folds to i plus a combining
|
||||
/// dot, and the `dotless` loop in `normalized` drops that dot after an `i`, so
|
||||
/// the key is plain `i`.)
|
||||
/// before the case fold (U+0130 would otherwise fold to i plus a combining dot,
|
||||
/// which the key keeps as a mark).
|
||||
fn fold_variant(c: char) -> impl Iterator<Item = char> {
|
||||
let one = |c: char| (c, None);
|
||||
let (first, second) = match c {
|
||||
'\u{131}' => one('i'),
|
||||
'\u{130}' => one('I'),
|
||||
// Voiced katakana wa, wi, we, wo: the hiragana (U+308F-3092) plus the
|
||||
// combining voiced mark, which is how NFKC spells the hiragana forms.
|
||||
'\u{30f7}'..='\u{30fa}' => (
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
//! lowerer sees, comes from `PacketStore::admit` alone, which builds it from
|
||||
//! the admitted packet and its corpus item through the crate-private
|
||||
//! `LoweringInput::of`. The stance is checked like every feature
|
||||
//! list, in slot `Stance`. The rules are V1..V8, V10..V12 and V14..V18: the
|
||||
//! list, in slot `Stance`. The rules are V1..V8, V10..V12 and V14..V17: the
|
||||
//! shape of an id or a grade is its type's parse, not a rule, so V9 is retired
|
||||
//! and not renumbered; V13 is retired too. [`LoweringInput::with_scene`] reads the
|
||||
//! scene of the view's own item group from the speaker-state store, and
|
||||
|
|
@ -120,12 +120,6 @@ pub enum Refusal {
|
|||
V17AddresseeNotAReferent {
|
||||
id: NodeId,
|
||||
},
|
||||
/// V18: a predication whose frame is the inventory's `request_intervention`,
|
||||
/// with no `addressee_consent` naming it. It says what the addressee did, so
|
||||
/// only the packet's own record may license it.
|
||||
V18RequestWithoutConsent {
|
||||
predication: NodeId,
|
||||
},
|
||||
}
|
||||
|
||||
impl Refusal {
|
||||
|
|
@ -150,7 +144,6 @@ impl Refusal {
|
|||
Refusal::V15ConsentSource { .. } => "V15",
|
||||
Refusal::V16SpeakerNotInScene => "V16",
|
||||
Refusal::V17AddresseeNotAReferent { .. } => "V17",
|
||||
Refusal::V18RequestWithoutConsent { .. } => "V18",
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
@ -180,9 +173,6 @@ impl fmt::Display for Refusal {
|
|||
"the scene does not cover the speaker of every live item of its group"
|
||||
}
|
||||
Refusal::V17AddresseeNotAReferent { .. } => "the addressee names no referent",
|
||||
Refusal::V18RequestWithoutConsent { .. } => {
|
||||
"a request frame needs the addressee's consent naming it"
|
||||
}
|
||||
};
|
||||
write!(f, "{}: {what}", self.rule())
|
||||
}
|
||||
|
|
@ -231,7 +221,6 @@ pub fn validate(packet: &Packet, inventory: &Inventory) -> Result<(), Vec<Refusa
|
|||
out: &mut out,
|
||||
}
|
||||
.check(packet);
|
||||
check_requests(packet, inventory, &mut out);
|
||||
} else {
|
||||
out.push(Refusal::V10UnknownRevision {
|
||||
rev: packet.inventory_rev,
|
||||
|
|
@ -314,25 +303,6 @@ fn check_consent(packet: &Packet, nodes: &BTreeSet<NodeId>, out: &mut Vec<Refusa
|
|||
}
|
||||
}
|
||||
|
||||
/// The gloss of the inventory frame that reports an addressee's request.
|
||||
const REQUEST_FRAME_GLOSS: &str = "request_intervention";
|
||||
|
||||
/// V18: a predication whose frame, resolved at the packet's revision, is the
|
||||
/// request frame is named by `addressee_consent`. An unresolved frame is V5's.
|
||||
fn check_requests(packet: &Packet, inventory: &Inventory, out: &mut Vec<Refusal>) {
|
||||
for p in &packet.predications {
|
||||
if inventory
|
||||
.resolve(&p.frame, packet.inventory_rev)
|
||||
.is_some_and(|e| e.gloss == REQUEST_FRAME_GLOSS)
|
||||
&& packet.discourse.addressee_consent.as_ref() != Some(&p.id)
|
||||
{
|
||||
out.push(Refusal::V18RequestWithoutConsent {
|
||||
predication: p.id.clone(),
|
||||
});
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
fn node_lists(packet: &Packet) -> [(&Vec<NodeId>, &'static str); 3] {
|
||||
[
|
||||
(&packet.context.participants, "participant"),
|
||||
|
|
|
|||
|
|
@ -904,7 +904,7 @@ fn fake_embedder() -> String {
|
|||
}
|
||||
|
||||
#[test]
|
||||
fn proof_packet_pronounces_and_the_item_scores_against_its_own_text() {
|
||||
fn proof_packet_lowers_and_the_lowering_scores_against_items() {
|
||||
let d = tempfile::tempdir().unwrap();
|
||||
cast_entities(d.path(), &["nibu"]);
|
||||
for args in [&["inventory", "seed"][..], &["inventory", "proof"]] {
|
||||
|
|
@ -939,11 +939,21 @@ fn proof_packet_pronounces_and_the_item_scores_against_its_own_text() {
|
|||
"{}",
|
||||
out(&admitted)
|
||||
);
|
||||
let missing = weksa(d.path(), &["pronounce", "./p.cc", "packet:0000000000000000"]);
|
||||
let lowered = weksa(d.path(), &["lower", "./p.cc", "packet:6e6962752d303031"]);
|
||||
assert!(lowered.status.success(), "{}", out(&lowered));
|
||||
let text = String::from_utf8(lowered.stdout).unwrap();
|
||||
assert!(
|
||||
text.starts_with("Warning: you may endanger yourself"),
|
||||
"{text}"
|
||||
);
|
||||
// The referent cites entity:nibu: its stored en-US form (NIBU here) reaches the text as stored.
|
||||
assert!(text.contains("NIBU will stop"), "{text}");
|
||||
|
||||
let missing = weksa(d.path(), &["lower", "./p.cc", "packet:0000000000000000"]);
|
||||
assert!(!missing.status.success() && out(&missing).contains("no such packet"));
|
||||
|
||||
// IPA is the ruled pronunciation or nothing: spelling is not one.
|
||||
let args = ["pronounce", "./p.cc", "packet:6e6962752d303031"];
|
||||
let args = ["lower", "./p.cc", "packet:6e6962752d303031", "--ipa"];
|
||||
let unruled = weksa(d.path(), &args);
|
||||
assert!(
|
||||
!unruled.status.success() && out(&unruled).contains("entity has no ruled pronunciation"),
|
||||
|
|
@ -983,10 +993,11 @@ fn proof_packet_pronounces_and_the_item_scores_against_its_own_text() {
|
|||
let ipa = weksa(d.path(), &args);
|
||||
assert!(ipa.status.success(), "{}", out(&ipa));
|
||||
assert_eq!(String::from_utf8(ipa.stdout).unwrap(), "ˈnibu\n");
|
||||
// The phones line is the committed fixture, byte for byte.
|
||||
// The phones line is the committed fixture, byte for byte, and is a different
|
||||
// output from --ipa, so the two flags cannot be combined.
|
||||
let phones = weksa(
|
||||
d.path(),
|
||||
&["pronounce", "./p.cc", "packet:6e6962752d303031", "--phones"],
|
||||
&["lower", "./p.cc", "packet:6e6962752d303031", "--phones"],
|
||||
);
|
||||
assert!(phones.status.success(), "{}", out(&phones));
|
||||
let fixture = std::fs::read_to_string(
|
||||
|
|
@ -995,13 +1006,21 @@ fn proof_packet_pronounces_and_the_item_scores_against_its_own_text() {
|
|||
)
|
||||
.unwrap();
|
||||
assert_eq!(String::from_utf8(phones.stdout).unwrap(), fixture);
|
||||
// The old lowering subcommand is gone: clap's usage error, exit 2.
|
||||
let gone = weksa(d.path(), &["lower", "./p.cc", "packet:6e6962752d303031"]);
|
||||
assert_eq!(gone.status.code(), Some(2), "{}", out(&gone));
|
||||
let both = weksa(
|
||||
d.path(),
|
||||
&[
|
||||
"lower",
|
||||
"./p.cc",
|
||||
"packet:6e6962752d303031",
|
||||
"--phones",
|
||||
"--ipa",
|
||||
],
|
||||
);
|
||||
assert!(!both.status.success(), "{}", out(&both));
|
||||
let again = weksa(d.path(), &["lower", "./p.cc", "packet:6e6962752d303031"]);
|
||||
assert_eq!(String::from_utf8(again.stdout).unwrap(), text);
|
||||
|
||||
// The item's own text, as the scorer's output.
|
||||
let text = "Warning: you may endanger yourself by touching the control. NIBU will stop that.";
|
||||
std::fs::write(d.path().join("out.txt"), text).unwrap();
|
||||
std::fs::write(d.path().join("out.txt"), &text).unwrap();
|
||||
let url = fake_embedder();
|
||||
let scored = weksa(
|
||||
d.path(),
|
||||
|
|
@ -1161,7 +1180,7 @@ fn cli_errors_never_echo_identifiers() {
|
|||
]),
|
||||
"--model-family",
|
||||
);
|
||||
// Keys on withdraw, split, validate, pronounce and score.
|
||||
// Keys on withdraw, split, validate, lower and score.
|
||||
refuses_without_echo(p, &["corpus", "withdraw", "item:canary:7"], "no such item");
|
||||
refuses_without_echo(p, &["split", "item:canary:7"], "no such item");
|
||||
std::fs::write(p.join("out.txt"), "text").unwrap();
|
||||
|
|
@ -1179,7 +1198,7 @@ fn cli_errors_never_echo_identifiers() {
|
|||
&["validate", "p.cc", "packet:canary:7"],
|
||||
"no such packet",
|
||||
);
|
||||
refuses_without_echo(p, &["pronounce", "p.cc", "packet:canary:7"], "no such packet");
|
||||
refuses_without_echo(p, &["lower", "p.cc", "packet:canary:7"], "no such packet");
|
||||
// S6 names no held key; S5 names no group.
|
||||
let held = weksa(
|
||||
p,
|
||||
|
|
@ -1526,7 +1545,7 @@ fn loop_cycle_needs_a_floor() {
|
|||
assert!(!o.status.success());
|
||||
let text = out(&o);
|
||||
assert!(
|
||||
text.contains("the run has no noise floor: record four rounds under the first inventory first"),
|
||||
text.contains("the run has no noise floor: record two rounds first"),
|
||||
"{text}"
|
||||
);
|
||||
for echoed in ["canaryroot", d.path().to_str().unwrap()] {
|
||||
|
|
@ -1539,8 +1558,8 @@ fn loop_cycle_needs_a_floor() {
|
|||
fn loop_cycle_asks_then_decides() {
|
||||
let d = tempfile::tempdir().unwrap();
|
||||
open_dao_run(d.path());
|
||||
// Four rounds of refusals: a floor of 0 and a base of 0.
|
||||
for n in 1..=4 {
|
||||
// Two rounds of refusals: a floor of 0 and a base of 0.
|
||||
for n in 1..=2 {
|
||||
let first = weksa(d.path(), &["loop", "round", "canaryroot"]);
|
||||
assert_eq!(first.status.code(), Some(3), "{}", out(&first));
|
||||
for entry in std::fs::read_dir(d.path().join(format!("canaryroot/round-{n}"))).unwrap() {
|
||||
|
|
@ -1759,200 +1778,6 @@ fn loop_ablate_waits_then_prints_one_line_per_split() {
|
|||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn cli_loop_relower_exits_3_until_answered_and_refuses_bad_labels() {
|
||||
let d = tempfile::tempdir().unwrap();
|
||||
open_dao_run(d.path());
|
||||
let url = fake_embedder();
|
||||
let root = d.path().join("canaryroot");
|
||||
let mut run = weksa::run::RunStores::open(&root).unwrap();
|
||||
let scorer = weksa::Scorer::new(weksa::OllamaEmbedder::new(&url, &run.record().embedder));
|
||||
let weksa::run::RoundOutcome::Recorded(r) = weksa::run::round(&mut run, &mut DaoModel, &scorer).unwrap()
|
||||
else {
|
||||
panic!("answered")
|
||||
};
|
||||
let said = r#"{"text":"The highest excellence is like the water."}"#;
|
||||
for call in &r.calls()[3..] {
|
||||
std::fs::write(root.join(format!("round-1/{}.answer", call.prompt)), said).unwrap();
|
||||
}
|
||||
let relower = |extra: &[&str]| {
|
||||
weksa(
|
||||
d.path(),
|
||||
&[&["loop", "relower", "canaryroot", "--round", "1", "--lowerer", "tuned-x", "--ollama-url", &url], extra].concat(),
|
||||
)
|
||||
};
|
||||
|
||||
// Unanswered: exit 3, the digests, a prompt file per digest in the arm's directory.
|
||||
let first = relower(&["--arm", "tuned"]);
|
||||
assert_eq!(first.status.code(), Some(3), "{}", out(&first));
|
||||
let text = out(&first);
|
||||
let digests: Vec<&str> = text
|
||||
.lines()
|
||||
.filter_map(|l| l.strip_prefix("unanswered "))
|
||||
.filter(|x| x.len() == 16)
|
||||
.collect();
|
||||
assert_eq!(digests.len(), 2, "the two Validation prompts: {text}");
|
||||
for digest in &digests {
|
||||
assert!(root.join(format!("relower-1-tuned/{digest}.prompt")).is_file());
|
||||
std::fs::write(root.join(format!("relower-1-tuned/{digest}.answer")), said).unwrap();
|
||||
}
|
||||
|
||||
// Answered: one line per language, labelled, naming the lowerer; no verdict without a floor.
|
||||
let second = relower(&["--arm", "tuned"]);
|
||||
assert!(second.status.success(), "{}", out(&second));
|
||||
let text = out(&second);
|
||||
assert!(text.starts_with("relower en-US n=2 skipped=0 unusable=0 recorded "), "{text}");
|
||||
assert!(text.contains("arm=tuned lowerer=tuned-x"), "{text}");
|
||||
assert!(text.contains(" lowering="), "{text}");
|
||||
assert!(!text.contains("verdict") && !text.contains("floor"), "{text}");
|
||||
for leaked in ["item:", "packet:", "highest excellence", "canaryroot"] {
|
||||
assert!(!text.contains(leaked), "{text}");
|
||||
}
|
||||
|
||||
// A floor arm that is not answered whole is refused, and never written to.
|
||||
let o = relower(&["--arm", "tuned", "--floor", "second"]);
|
||||
assert_eq!(o.status.code(), Some(1), "{}", out(&o));
|
||||
assert!(!root.join("relower-1-second").exists());
|
||||
|
||||
// Fewer than three floor arms is refused: one pair measures no noise.
|
||||
let o = relower(&["--arm", "tuned", "--floor", "second"]);
|
||||
assert_eq!(o.status.code(), Some(1), "{}", out(&o));
|
||||
assert!(out(&o).contains("three or more floor arms"), "{}", out(&o));
|
||||
|
||||
// Answered floors: a verdict line.
|
||||
for label in ["second", "third", "fourth"] {
|
||||
std::fs::create_dir_all(root.join(format!("relower-1-{label}"))).unwrap();
|
||||
for digest in &digests {
|
||||
std::fs::write(root.join(format!("relower-1-{label}/{digest}.answer")), said).unwrap();
|
||||
}
|
||||
}
|
||||
let o = relower(&["--arm", "tuned", "--floor", "second", "--floor", "third", "--floor", "fourth"]);
|
||||
assert!(o.status.success(), "{}", out(&o));
|
||||
let text = out(&o);
|
||||
assert!(text.contains("| floor chrf=0.00") && text.trim_end().ends_with("verdict Rejected(NoGain)"), "{text}");
|
||||
|
||||
// Labels: equal, uppercase, empty, too long, a path.
|
||||
let long = "a".repeat(33);
|
||||
for args in [
|
||||
vec!["--arm", "same", "--floor", "same"],
|
||||
vec!["--arm", "Upper"],
|
||||
vec!["--arm", ""],
|
||||
vec!["--arm", &long],
|
||||
vec!["--arm", "../x"],
|
||||
vec!["--arm", "tuned", "--floor", "Bad"],
|
||||
vec!["--arm", "tuned", "--floor", "b", "--floor", "b", "--floor", "c"],
|
||||
] {
|
||||
let o = relower(&args);
|
||||
assert_eq!(o.status.code(), Some(1), "{args:?}: {}", out(&o));
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn cli_loop_calibrate_reads_answered_draws_and_refuses_unanswered_and_bad_labels() {
|
||||
let d = tempfile::tempdir().unwrap();
|
||||
open_dao_run(d.path());
|
||||
let url = fake_embedder();
|
||||
let root = d.path().join("canaryroot");
|
||||
let mut run = weksa::run::RunStores::open(&root).unwrap();
|
||||
let scorer = weksa::Scorer::new(weksa::OllamaEmbedder::new(&url, &run.record().embedder));
|
||||
let weksa::run::RoundOutcome::Recorded(r) = weksa::run::round(&mut run, &mut DaoModel, &scorer).unwrap()
|
||||
else {
|
||||
panic!("answered")
|
||||
};
|
||||
let said = r#"{"text":"The highest excellence is like the water."}"#;
|
||||
for call in &r.calls()[3..] {
|
||||
std::fs::write(root.join(format!("round-1/{}.answer", call.prompt)), said).unwrap();
|
||||
}
|
||||
let calibrate = |extra: &[&str]| {
|
||||
weksa(
|
||||
d.path(),
|
||||
&[&["loop", "calibrate", "canaryroot", "--round", "1", "--ollama-url", &url], extra].concat(),
|
||||
)
|
||||
};
|
||||
let four = ["--prompted", "p1", "--prompted", "p2", "--prompted", "p3", "--prompted", "p4"];
|
||||
|
||||
// Unanswered draws: exit 1, each label with its missing count, no relower directory created.
|
||||
let o = calibrate(&four);
|
||||
assert_eq!(o.status.code(), Some(1), "{}", out(&o));
|
||||
let text = out(&o);
|
||||
for label in ["p1", "p2", "p3", "p4"] {
|
||||
assert!(text.contains(&format!("unanswered {label} 2")), "{text}");
|
||||
assert!(!root.join(format!("relower-1-{label}")).exists());
|
||||
}
|
||||
assert!(text.contains("answer it through weksa loop relower"), "{text}");
|
||||
|
||||
// Answer every draw through relower's door; from here the only thing that can refuse is the argument.
|
||||
let o = weksa(
|
||||
d.path(),
|
||||
&["loop", "relower", "canaryroot", "--round", "1", "--lowerer", "x", "--arm", "p1", "--ollama-url", &url],
|
||||
);
|
||||
assert_eq!(o.status.code(), Some(3), "{}", out(&o));
|
||||
let digests: Vec<String> = out(&o)
|
||||
.lines()
|
||||
.filter_map(|l| l.strip_prefix("unanswered "))
|
||||
.filter(|x| x.len() == 16)
|
||||
.map(String::from)
|
||||
.collect();
|
||||
assert_eq!(digests.len(), 2);
|
||||
// `P1` and `a_b` are answered too, so only the label check can refuse them.
|
||||
for label in ["p1", "p2", "p3", "p4", "bad", "cand1", "cand2", "P1", "a_b"] {
|
||||
std::fs::create_dir_all(root.join(format!("relower-1-{label}"))).unwrap();
|
||||
for digest in &digests {
|
||||
std::fs::write(root.join(format!("relower-1-{label}/{digest}.answer")), said).unwrap();
|
||||
}
|
||||
}
|
||||
// A draw answered in part.
|
||||
std::fs::create_dir_all(root.join("relower-1-part")).unwrap();
|
||||
std::fs::write(root.join(format!("relower-1-part/{}.answer", digests[0])), said).unwrap();
|
||||
let o = calibrate(&["--prompted", "p1", "--prompted", "p2", "--prompted", "p3", "--prompted", "part"]);
|
||||
assert_eq!(o.status.code(), Some(1), "{}", out(&o));
|
||||
assert!(out(&o).contains("unanswered part 1") && !out(&o).contains("unanswered p1"), "{}", out(&o));
|
||||
|
||||
// Refusals, every draw answered: the baseline reads, each variant differs by one fault.
|
||||
assert!(calibrate(&four).status.success());
|
||||
for args in [
|
||||
vec!["--prompted", "p1", "--prompted", "p2", "--prompted", "p3"],
|
||||
vec!["--prompted", "p1", "--prompted", "p2", "--prompted", "p3", "--prompted", "p3"],
|
||||
vec!["--prompted", "p1", "--prompted", "p2", "--prompted", "p3", "--prompted", "p4", "--degraded", "p4"],
|
||||
vec!["--prompted", "p1", "--prompted", "p2", "--prompted", "p3", "--prompted", "p4", "--candidate", "bad", "--degraded", "bad"],
|
||||
vec!["--prompted", "P1", "--prompted", "p2", "--prompted", "p3", "--prompted", "p4"],
|
||||
vec!["--prompted", "a_b", "--prompted", "p2", "--prompted", "p3", "--prompted", "p4"],
|
||||
[&four[..], &["--class", "all=item:"]].concat(),
|
||||
[&four[..], &["--class", "noequals"]].concat(),
|
||||
[&four[..], &["--class", "Old=item:a"]].concat(),
|
||||
[&four[..], &["--class", "old=item:a,"]].concat(),
|
||||
[&four[..], &["--class", "old=item:a", "--class", "old=item:b"]].concat(),
|
||||
] {
|
||||
let o = calibrate(&args);
|
||||
assert_eq!(o.status.code(), Some(1), "{args:?}: {}", out(&o));
|
||||
assert!(!out(&o).contains("unanswered"), "{args:?} must be refused for itself: {}", out(&o));
|
||||
}
|
||||
|
||||
let o = calibrate(
|
||||
&[&four[..], &["--degraded", "bad", "--candidate", "cand1", "--candidate", "cand2", "--class", "old=item:daodejing"]].concat(),
|
||||
);
|
||||
assert!(o.status.success(), "{}", out(&o));
|
||||
let text = out(&o);
|
||||
assert!(text.starts_with("calibrate draws prompted=4 degraded=1 candidate=2 floor-arms=3 unusable=0"), "{text}");
|
||||
assert!(text.contains("calibrate class=all items en-US n=2 skipped=0"), "{text}");
|
||||
assert!(text.contains("calibrate class=all prompted trials=20 nogain=20 accepted=0 regressed=0"), "{text}");
|
||||
for side in ["r-candidate trials=4", "r-base trials=4", "r-free trials=12"] {
|
||||
assert!(text.contains(&format!("calibrate class=all prompted-{side} nogain=")), "{text}");
|
||||
}
|
||||
assert!(text.contains("calibrate class=old degraded=bad trials=20 regressed=0 offset en-US=+0.0000"), "{text}");
|
||||
// The class=all lines in print order: prompted, its three R roles, degraded, pooled candidate, each candidate arm.
|
||||
let all: Vec<&str> = text.lines().filter(|l| l.contains("calibrate class=all ")).collect();
|
||||
let kinds = ["items", "prompted trials", "prompted-r-candidate", "prompted-r-base", "prompted-r-free", "degraded=bad", "candidate trials", "candidate=cand1", "candidate=cand2"];
|
||||
assert_eq!(all.len(), kinds.len(), "{text}");
|
||||
for (line, kind) in all.iter().zip(kinds) {
|
||||
assert!(line.contains(&format!("class=all {kind}")), "{kind}: {line}");
|
||||
}
|
||||
assert!(all[7].contains("candidate=cand1 trials=20 nogain=20 accepted=0 regressed=0"), "{}", all[7]);
|
||||
for leaked in ["item:daodejing", "packet:", "highest excellence", "canaryroot"] {
|
||||
assert!(!text.contains(leaked), "{text}");
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn loop_ablate_without_the_rounds_answers_says_so() {
|
||||
let d = tempfile::tempdir().unwrap();
|
||||
|
|
@ -2145,130 +1970,3 @@ fn inventory_admit_cap_is_256_and_a_refusal_writes_nothing() {
|
|||
assert!(admitted.status.success(), "{}", out(&admitted));
|
||||
assert!(out(&admitted).contains("admitted rev:2 with 256 entries"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn corpus_import_labels_spans_and_is_idempotent() {
|
||||
let d = tempfile::tempdir().unwrap();
|
||||
let work = d.path().join("work.json");
|
||||
std::fs::write(
|
||||
&work,
|
||||
r#"{"slug":"lantern-wager","language":"en-US","admitted_on":"2026-11-13",
|
||||
"source":{"PublicDomain":{"work":"The Lantern Wager","author":"A. Invented","edition_url":"https://example.invalid/lantern","licence":"public domain","jurisdiction":"US","translator":"none","edition_year":1890}},
|
||||
"cast":[{"entity":"entity:orsa","forms":["Orsa"]},{"entity":"entity:tamsin","forms":["Tamsin","Tam"]}],
|
||||
"lines":[{"group":"s1","speaker":"entity:orsa","text":"Tamsin, bring the lantern."},
|
||||
{"group":"s1","speaker":"entity:tamsin","text":"Orsa, I will not."}]}"#,
|
||||
)
|
||||
.unwrap();
|
||||
let names = d.path().join("names.jsonl");
|
||||
std::fs::write(
|
||||
&names,
|
||||
concat!(
|
||||
r#"{"line":1,"marked":"[[entity:tamsin|Tamsin]], bring the lantern."}"#, "\n\n",
|
||||
r#"{"line":2,"marked":"[[entity:orsa|Orsa]], I will not."}"#, "\n",
|
||||
),
|
||||
)
|
||||
.unwrap();
|
||||
let (w, n) = (work.to_str().unwrap(), names.to_str().unwrap());
|
||||
let bare = weksa(d.path(), &["corpus", "import", w, n]);
|
||||
assert!(!bare.status.success());
|
||||
let flags = ["--model-family", "anthropic", "--generator", "a name annotator"];
|
||||
let run = || weksa(d.path(), &[&["corpus", "import", w, n][..], &flags].concat());
|
||||
let first = run();
|
||||
assert!(first.status.success(), "{}", out(&first));
|
||||
let text = out(&first);
|
||||
assert!(text.contains("Added item:lantern-wager:1 ") && text.contains("Added item:lantern-wager:2 "), "{text}");
|
||||
assert!(text.contains("Added entity:orsa"), "{text}");
|
||||
let second = out(&run());
|
||||
assert!(second.contains("Unchanged item:lantern-wager:1 ") && !second.contains("Added"), "{second}");
|
||||
let dump = out(&weksa(d.path(), &["corpus", "dump"]));
|
||||
assert!(dump.contains("by Some(Model"), "{dump}");
|
||||
}
|
||||
|
||||
const LANTERN_CAST: &str = r#""cast":[{"entity":"entity:orsa","forms":["Orsa"]},{"entity":"entity:tamsin","forms":["Tamsin","Tam"]}]"#;
|
||||
const LANTERN_SOURCE: &str = r#""source":{"PublicDomain":{"work":"The Lantern Wager","author":"A. Invented","edition_url":"https://example.invalid/lantern","licence":"public domain","jurisdiction":"US","translator":"none","edition_year":1890}}"#;
|
||||
|
||||
/// Writes a work of `lines` (text per line, all said by Orsa) and an answer of
|
||||
/// `marked` per line, returns both paths.
|
||||
fn lantern(dir: &std::path::Path, lines: &[&str], marked: &[&str]) -> (String, String) {
|
||||
let ls: Vec<String> = lines
|
||||
.iter()
|
||||
.map(|t| format!(r#"{{"group":"s1","speaker":"entity:orsa","text":"{t}"}}"#))
|
||||
.collect();
|
||||
let work = dir.join("w.json");
|
||||
std::fs::write(
|
||||
&work,
|
||||
format!(
|
||||
r#"{{"slug":"lantern-wager","language":"en-US","admitted_on":"2026-11-13",{LANTERN_SOURCE},{LANTERN_CAST},"lines":[{}]}}"#,
|
||||
ls.join(",")
|
||||
),
|
||||
)
|
||||
.unwrap();
|
||||
let names = dir.join("n.jsonl");
|
||||
let rows: Vec<String> = marked
|
||||
.iter()
|
||||
.enumerate()
|
||||
.map(|(i, m)| format!(r#"{{"line":{},"marked":"{m}"}}"#, i + 1))
|
||||
.collect();
|
||||
std::fs::write(&names, rows.join("\n")).unwrap();
|
||||
(work.to_str().unwrap().into(), names.to_str().unwrap().into())
|
||||
}
|
||||
|
||||
const MODEL: [&str; 4] = ["--model-family", "anthropic", "--generator", "a name annotator"];
|
||||
|
||||
#[test]
|
||||
fn a_refused_import_writes_nothing_and_a_redraw_imports() {
|
||||
let d = tempfile::tempdir().unwrap();
|
||||
let lines = ["Tamsin, bring the lantern.", "Tamsin's lantern, said Orsa."];
|
||||
let (w, n) = lantern(d.path(), &lines, &["[[entity:tamsin|Tamsin]], bring the lantern.", "[[entity:tamsin|Tamsin's]] lantern, said Orsa."]);
|
||||
let import = |w: &str, n: &str| weksa(d.path(), &[&["corpus", "import", w, n][..], &MODEL].concat());
|
||||
let bad = import(&w, &n);
|
||||
assert!(!bad.status.success());
|
||||
assert_eq!(out(&weksa(d.path(), &["corpus", "dump"])).trim(), "");
|
||||
assert!(!d.path().join("e.cc").exists() || EntityStore::open(&d.path().join("e.cc")).unwrap().all().unwrap().is_empty());
|
||||
// The redrawn answer, different on line 1 too, imports.
|
||||
let (w, n) = lantern(d.path(), &lines, &["Tamsin, bring the lantern.", "[[entity:tamsin|Tamsin]]'s lantern, said Orsa."]);
|
||||
let good = import(&w, &n);
|
||||
assert!(good.status.success(), "{}", out(&good));
|
||||
assert!(out(&good).contains("Added item:lantern-wager:2"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_work_repeating_a_line_is_refused_naming_both_lines() {
|
||||
let d = tempfile::tempdir().unwrap();
|
||||
let (w, n) = lantern(d.path(), &["No, my lord.", "No, my lord!", "Quiet, both of you."], &["No, my lord.", "No, my lord!", "Quiet, both of you."]);
|
||||
let o = weksa(d.path(), &[&["corpus", "import", &w, &n][..], &MODEL].concat());
|
||||
assert!(!o.status.success());
|
||||
let err = String::from_utf8_lossy(&o.stderr).to_string();
|
||||
assert!(err.contains("item:lantern-wager:2") && err.contains("item:lantern-wager:1"), "{err}");
|
||||
assert_eq!(out(&weksa(d.path(), &["corpus", "dump"])).trim(), "");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn the_annotator_flags_decide_the_label() {
|
||||
let d = tempfile::tempdir().unwrap();
|
||||
let (w, n) = lantern(d.path(), &["Quiet, both of you."], &["Quiet, both of you."]);
|
||||
let none = weksa(d.path(), &["corpus", "import", &w, &n]);
|
||||
assert!(!none.status.success());
|
||||
let blank = weksa(d.path(), &["corpus", "import", &w, &n, "--model-family", "anthropic", "--generator", " "]);
|
||||
assert!(!blank.status.success());
|
||||
assert_eq!(out(&weksa(d.path(), &["corpus", "dump"])).trim(), "");
|
||||
let op = weksa(d.path(), &["corpus", "import", &w, &n, "--operator"]);
|
||||
assert!(op.status.success(), "{}", out(&op));
|
||||
let dump = out(&weksa(d.path(), &["corpus", "dump"]));
|
||||
assert!(dump.contains("by Some(Operator)"), "{dump}");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn an_import_refused_on_a_cast_entity_leaves_both_stores_untouched() {
|
||||
let d = tempfile::tempdir().unwrap();
|
||||
// entity:tamsin is already held by a cast origin, so the work's PublicDomain
|
||||
// claim on it (cast position 2, after orsa) is refused by EntityStore::put.
|
||||
cast_entities(d.path(), &["tamsin"]);
|
||||
let (w, n) = lantern(d.path(), &["Quiet, both of you."], &["Quiet, both of you."]);
|
||||
let before = std::fs::read(d.path().join("e.cc")).unwrap();
|
||||
let o = weksa(d.path(), &[&["corpus", "import", &w, &n][..], &MODEL].concat());
|
||||
assert!(!o.status.success());
|
||||
assert!(String::from_utf8_lossy(&o.stderr).contains("a cast entity"), "{}", String::from_utf8_lossy(&o.stderr));
|
||||
assert_eq!(std::fs::read(d.path().join("e.cc")).unwrap(), before);
|
||||
assert!(!d.path().join("c.cc").exists() || CorpusStore::open(&d.path().join("c.cc")).unwrap().all().unwrap().is_empty());
|
||||
}
|
||||
|
|
|
|||
|
|
@ -205,7 +205,6 @@ pub fn item_in(key: &str, text: &str, group: &str, source: Source) -> CorpusItem
|
|||
language: "en-US".into(),
|
||||
speaker: eid("nibu"),
|
||||
names: vec![],
|
||||
names_by: None,
|
||||
group: group.into(),
|
||||
prior_turns: vec![],
|
||||
source,
|
||||
|
|
|
|||
|
|
@ -586,46 +586,11 @@ mod lowering {
|
|||
let unread = admitted_unread(proof_packet(), &cast, "corpus/corpus.cc", &entities);
|
||||
let empty = weksa::Ontology::empty();
|
||||
assert_eq!(
|
||||
Prompt::lower(&unread, &item, &away(), "en-US", &inv, &held, &empty).err(),
|
||||
Prompt::lower(&unread, &item, "en-US", &inv, &held, &empty).err(),
|
||||
Some(LowerError::SceneUnread)
|
||||
);
|
||||
let read = admitted(proof_packet(), &cast, "corpus/corpus.cc", &entities);
|
||||
assert!(Prompt::lower(&read, &item, &away(), "en-US", &inv, &held, &empty).is_ok());
|
||||
}
|
||||
|
||||
/// The packet the encoder emits for a request: frame:3, no consent, source
|
||||
/// ModelDecomposition. Admission refuses it, so no lowering view exists.
|
||||
#[test]
|
||||
fn an_encoder_request_never_reaches_a_lowerer() {
|
||||
let cast = 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 mut store = PacketStore::open(&dir.path().join("p.cc")).unwrap();
|
||||
let mut packet = proof_packet();
|
||||
packet.provenance.source = weksa::packet::ProvenanceSource::ModelDecomposition;
|
||||
packet.predications[0].frame = weksa::InvId::parse("frame:3").unwrap();
|
||||
match store.admit(packet.clone(), &cast, &corpus, &entities) {
|
||||
Err(weksa::StoreError::Invalid(r)) => assert_eq!(
|
||||
r,
|
||||
vec![weksa::Refusal::V18RequestWithoutConsent {
|
||||
predication: weksa::packet::NodeId::parse("n4").unwrap()
|
||||
}]
|
||||
),
|
||||
other => panic!("expected V18, got {:?}", other.map(|_| ())),
|
||||
}
|
||||
// Not blanket: telemetry that records the consent admits and lowers.
|
||||
packet.provenance.source = weksa::packet::ProvenanceSource::GameTelemetry;
|
||||
packet.discourse.addressee_consent = Some(weksa::packet::NodeId::parse("n4").unwrap());
|
||||
drop(store);
|
||||
let view = admitted(packet, &cast, "corpus/corpus.cc", &entities);
|
||||
let item = CorpusItemId::parse("item:nibu:1").unwrap();
|
||||
let held = Held(vec![nibu(&[("en-US", &["Nibu"])])]);
|
||||
let empty = weksa::Ontology::empty();
|
||||
assert!(
|
||||
Prompt::lower(&view, &item, &away(), "en-US", &cast.inventory().unwrap(), &held, &empty)
|
||||
.is_ok()
|
||||
);
|
||||
assert!(Prompt::lower(&read, &item, "en-US", &inv, &held, &empty).is_ok());
|
||||
}
|
||||
|
||||
fn dao(index: usize) -> (LoweringInput, Inventory, EntityStore, CorpusItemId) {
|
||||
|
|
@ -646,11 +611,6 @@ mod lowering {
|
|||
}
|
||||
}
|
||||
|
||||
/// A speaker no referent cites.
|
||||
fn away() -> EntityId {
|
||||
EntityId::parse("entity:nobody").unwrap()
|
||||
}
|
||||
|
||||
fn nibu(forms: &[(&str, &[&str])]) -> Entity {
|
||||
Entity {
|
||||
id: EntityId::parse("entity:nibu").unwrap(),
|
||||
|
|
@ -675,7 +635,7 @@ mod lowering {
|
|||
fn lower_prompt_names_its_language() {
|
||||
let (view, inv, entities, item) = dao(2);
|
||||
for tag in ["en-US", "ja-JP", "pt-BR"] {
|
||||
let prompt = Prompt::lower(&view, &item, &away(), tag, &inv, &entities, &weksa::Ontology::empty()).unwrap();
|
||||
let prompt = Prompt::lower(&view, &item, tag, &inv, &entities, &weksa::Ontology::empty()).unwrap();
|
||||
let want = format!("{LOWER}\n\nlanguage: {tag}\n\npacket: ");
|
||||
assert!(prompt.text().starts_with(&want), "{tag}");
|
||||
}
|
||||
|
|
@ -687,7 +647,7 @@ mod lowering {
|
|||
#[test]
|
||||
fn lower_prompt_text_is_pinned() {
|
||||
let (view, inv, entities, item) = dao(2);
|
||||
let prompt = Prompt::lower(&view, &item, &away(), "en-US", &inv, &entities, &weksa::Ontology::empty()).unwrap();
|
||||
let prompt = Prompt::lower(&view, &item, "en-US", &inv, &entities, &weksa::Ontology::empty()).unwrap();
|
||||
let (head, listing) = prompt.text().split_once("inventory rev:3\n").unwrap();
|
||||
let expected = format!(
|
||||
"{LOWER}\n\nlanguage: en-US\n\npacket: {}\n\nentities: {{}}\n\nontology: none\n\n",
|
||||
|
|
@ -750,7 +710,7 @@ mod lowering {
|
|||
let entries = OntologyDraft::parse(draft).unwrap().into_entries("en-US", 3, 1, &annotator);
|
||||
onto.admit(entries, &store).unwrap();
|
||||
let prompt =
|
||||
Prompt::lower(&view, &item, &away(), "en-US", &inv, &entities, &onto.ontology().unwrap()).unwrap();
|
||||
Prompt::lower(&view, &item, "en-US", &inv, &entities, &onto.ontology().unwrap()).unwrap();
|
||||
assert!(prompt.text().contains("golden choice"));
|
||||
assert_eq!(prompt.digest(), "4a40eb57282b059d");
|
||||
}
|
||||
|
|
@ -772,7 +732,7 @@ mod lowering {
|
|||
let mut packet = packets().remove(2);
|
||||
packet.stance = stance.clone();
|
||||
let view = admitted(packet, &store, "daodejing/corpus.cc", &entities);
|
||||
let prompt = Prompt::lower(&view, &item, &away(), "en-US", &inv, &entities, &weksa::Ontology::empty()).unwrap();
|
||||
let prompt = Prompt::lower(&view, &item, "en-US", &inv, &entities, &weksa::Ontology::empty()).unwrap();
|
||||
(stance, prompt)
|
||||
};
|
||||
let three = [prompt_of(own), prompt_of(angry), prompt_of(Stance::default())];
|
||||
|
|
@ -809,7 +769,7 @@ mod lowering {
|
|||
("sa-Latn", &["Nibuwa"]),
|
||||
("en-US", &["Nibu", "Nibu's"]),
|
||||
])]);
|
||||
let prompt = Prompt::lower(&view, &item, &away(), "en-US", &cast.inventory().unwrap(), &held, &weksa::Ontology::empty()).unwrap();
|
||||
let prompt = Prompt::lower(&view, &item, "en-US", &cast.inventory().unwrap(), &held, &weksa::Ontology::empty()).unwrap();
|
||||
assert!(
|
||||
prompt
|
||||
.text()
|
||||
|
|
@ -839,212 +799,10 @@ mod lowering {
|
|||
),
|
||||
(Held(vec![]), LowerError::UnknownEntity { entity: id }),
|
||||
] {
|
||||
assert_eq!(Prompt::lower(&view, &item, &away(), "en-US", &inv, &held, &weksa::Ontology::empty()).err(), Some(want));
|
||||
assert_eq!(Prompt::lower(&view, &item, "en-US", &inv, &held, &weksa::Ontology::empty()).err(), Some(want));
|
||||
}
|
||||
}
|
||||
|
||||
/// The item's speaker id is never printed, though a referent cites it: the
|
||||
/// referent holds the token, the forms line holds the speaker's forms under
|
||||
/// it, and the view itself is not changed.
|
||||
#[test]
|
||||
fn a_cited_speaker_is_replaced_by_the_token_in_the_lowering_prompt() {
|
||||
let cast = InventoryStore::open(&data("interlingua/inventory.cc")).unwrap();
|
||||
let cast_entities = EntityStore::open(&data("entity/entity.cc")).unwrap();
|
||||
let view = admitted(proof_packet(), &cast, "corpus/corpus.cc", &cast_entities);
|
||||
let inv = cast.inventory().unwrap();
|
||||
let item = CorpusItemId::parse("item:nibu:1").unwrap();
|
||||
let speaker = EntityId::parse("entity:nibu").unwrap();
|
||||
let held = Held(vec![nibu(&[("en-US", &["NIBUCANARY"])])]);
|
||||
let lower = |held: &Held| {
|
||||
Prompt::lower(&view, &item, &speaker, "en-US", &inv, held, &weksa::Ontology::empty())
|
||||
};
|
||||
let prompt = lower(&held).unwrap();
|
||||
let text = prompt.text();
|
||||
assert!(!text.contains("entity:nibu"), "{text}");
|
||||
assert!(text.contains("\n\nentities: {\"entity:speaker\":[\"NIBUCANARY\"]}\n\n"), "{text}");
|
||||
assert!(text.contains(r#""id":"n3","kind":"referent_kind:1","concept":"concept:5","entity":"entity:speaker""#), "{text}");
|
||||
assert!(view.referents().iter().any(|r| r.entity.as_ref() == Some(&speaker)));
|
||||
// A speaker the language has no form for, or the port lacks, does not
|
||||
// refuse: its referent names no entity and the line has no entry.
|
||||
for held in [Held(vec![]), Held(vec![nibu(&[("sa-Latn", &["Nibuwa"])])])] {
|
||||
let prompt = lower(&held).unwrap();
|
||||
let text = prompt.text();
|
||||
assert!(text.contains("\n\nentities: {}\n\n") && !text.contains("entity:speaker"), "{text}");
|
||||
assert!(text.contains(r#""concept":"concept:5","entity":null"#), "{text}");
|
||||
}
|
||||
}
|
||||
|
||||
/// The speaker's forms are those of the item's language, and a language whose form list is
|
||||
/// an empty list is no form: the line has no token entry.
|
||||
#[test]
|
||||
fn the_speakers_forms_are_those_of_the_items_language() {
|
||||
let cast = InventoryStore::open(&data("interlingua/inventory.cc")).unwrap();
|
||||
let cast_entities = EntityStore::open(&data("entity/entity.cc")).unwrap();
|
||||
let view = admitted(proof_packet(), &cast, "corpus/corpus.cc", &cast_entities);
|
||||
let inv = cast.inventory().unwrap();
|
||||
let item = CorpusItemId::parse("item:nibu:1").unwrap();
|
||||
let speaker = EntityId::parse("entity:nibu").unwrap();
|
||||
let lower = |tag: &str, held: &Held| {
|
||||
Prompt::lower(&view, &item, &speaker, tag, &inv, held, &weksa::Ontology::empty())
|
||||
.unwrap()
|
||||
.text()
|
||||
.to_string()
|
||||
};
|
||||
let held = Held(vec![nibu(&[("en-US", &["ENGLISHFORM"]), ("ja-JP", &["NIHONGOFORM"])])]);
|
||||
let ja = lower("ja-JP", &held);
|
||||
assert!(ja.contains("\n\nentities: {\"entity:speaker\":[\"NIHONGOFORM\"]}\n\n"), "{ja}");
|
||||
assert!(!ja.contains("ENGLISHFORM"), "{ja}");
|
||||
let en = lower("en-US", &held);
|
||||
assert!(en.contains("{\"entity:speaker\":[\"ENGLISHFORM\"]}") && !en.contains("NIHONGOFORM"), "{en}");
|
||||
let empty = lower("en-US", &Held(vec![nibu(&[("en-US", &[])])]));
|
||||
assert!(empty.contains("\n\nentities: {}\n\n") && !empty.contains("entity:speaker"), "{empty}");
|
||||
assert!(empty.contains(r#""concept":"concept:5","entity":null"#), "{empty}");
|
||||
}
|
||||
|
||||
/// A real entity whose id is the token would read as the speaker: refused.
|
||||
#[test]
|
||||
fn a_cited_entity_with_the_tokens_id_is_refused() {
|
||||
let cast = InventoryStore::open(&data("interlingua/inventory.cc")).unwrap();
|
||||
let mut packet = proof_packet();
|
||||
packet.referents[2].entity = Some(EntityId::parse(weksa::context::SPEAKER_TOKEN).unwrap());
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
let mut entities = EntityStore::open(&dir.path().join("e.cc")).unwrap();
|
||||
entities.put(super::common::ent("speaker", "en-US", &["Spk"])).unwrap();
|
||||
entities.put(super::common::ent("nibu", "en-US", &["Nibu"])).unwrap();
|
||||
let mut corpus = CorpusStore::open(&dir.path().join("c.cc")).unwrap();
|
||||
let mut item = super::common::item_in("item:nibu:1", "A line.", &super::common::group_in_bucket(10), super::common::cast());
|
||||
item.prior_turns = vec![weksa::Turn { speaker: super::common::eid("speaker"), text: "Well?".into() }];
|
||||
corpus.add(item, &entities).unwrap();
|
||||
let view = PacketStore::open(&dir.path().join("p.cc")).unwrap().admit(packet, &cast, &corpus, &entities).unwrap();
|
||||
let state = weksa::SpeakerStateStore::open(&dir.path().join("s.cc")).unwrap();
|
||||
let view = view.with_scene(&cast.inventory().unwrap(), &state, &corpus).unwrap();
|
||||
let item = CorpusItemId::parse("item:nibu:1").unwrap();
|
||||
let held = Held(vec![super::common::ent("speaker", "en-US", &["Spk"]), nibu(&[("en-US", &["Nibu"])])]);
|
||||
for speaker in ["entity:nibu", "entity:speaker"] {
|
||||
let speaker = EntityId::parse(speaker).unwrap();
|
||||
assert_eq!(
|
||||
Prompt::lower(&view, &item, &speaker, "en-US", &cast.inventory().unwrap(), &held, &weksa::Ontology::empty()).err(),
|
||||
Some(LowerError::SpeakerTokenTaken)
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
/// Only the speaker is replaced: when the item's speaker is someone else,
|
||||
/// the cited entity keeps its id in the packet and its forms line.
|
||||
#[test]
|
||||
fn a_cited_entity_that_is_not_the_speaker_is_kept() {
|
||||
let cast = InventoryStore::open(&data("interlingua/inventory.cc")).unwrap();
|
||||
let cast_entities = EntityStore::open(&data("entity/entity.cc")).unwrap();
|
||||
let view = admitted(proof_packet(), &cast, "corpus/corpus.cc", &cast_entities);
|
||||
let item = CorpusItemId::parse("item:nibu:1").unwrap();
|
||||
let held = Held(vec![nibu(&[("en-US", &["NIBUCANARY"])])]);
|
||||
let prompt = Prompt::lower(&view, &item, &away(), "en-US", &cast.inventory().unwrap(), &held, &weksa::Ontology::empty()).unwrap();
|
||||
let text = prompt.text();
|
||||
assert!(text.contains(r#""concept":"concept:5","entity":"entity:nibu""#), "{text}");
|
||||
assert!(text.contains("\n\nentities: {\"entity:nibu\":[\"NIBUCANARY\"]}\n\n"), "{text}");
|
||||
}
|
||||
|
||||
/// Every referent citing the speaker holds the token, not the first.
|
||||
#[test]
|
||||
fn a_speaker_cited_on_two_referents_prints_the_token_on_both() {
|
||||
let cast = InventoryStore::open(&data("interlingua/inventory.cc")).unwrap();
|
||||
let cast_entities = EntityStore::open(&data("entity/entity.cc")).unwrap();
|
||||
let mut packet = proof_packet();
|
||||
let speaker = EntityId::parse("entity:nibu").unwrap();
|
||||
packet.referents[0].entity = Some(speaker.clone());
|
||||
assert_eq!(packet.referents.iter().filter(|r| r.entity.as_ref() == Some(&speaker)).count(), 2);
|
||||
let view = admitted(packet, &cast, "corpus/corpus.cc", &cast_entities);
|
||||
let item = CorpusItemId::parse("item:nibu:1").unwrap();
|
||||
let held = Held(vec![nibu(&[("en-US", &["NIBUCANARY"])])]);
|
||||
let prompt = Prompt::lower(&view, &item, &speaker, "en-US", &cast.inventory().unwrap(), &held, &weksa::Ontology::empty()).unwrap();
|
||||
let text = prompt.text();
|
||||
assert!(!text.contains("entity:nibu"), "{text}");
|
||||
assert_eq!(text.matches(r#""entity":"entity:speaker""#).count(), 2, "{text}");
|
||||
assert!(text.contains("\n\nentities: {\"entity:speaker\":[\"NIBUCANARY\"]}\n\n"), "{text}");
|
||||
}
|
||||
|
||||
/// The speaker is matched by whole id: a cited entity whose id the
|
||||
/// speaker's id is a prefix of is another entity and still prints.
|
||||
#[test]
|
||||
fn an_entity_sharing_a_prefix_with_the_speaker_is_kept() {
|
||||
let cast = InventoryStore::open(&data("interlingua/inventory.cc")).unwrap();
|
||||
let cast_entities = EntityStore::open(&data("entity/entity.cc")).unwrap();
|
||||
let view = admitted(proof_packet(), &cast, "corpus/corpus.cc", &cast_entities);
|
||||
let item = CorpusItemId::parse("item:nibu:1").unwrap();
|
||||
let held = Held(vec![nibu(&[("en-US", &["NIBUCANARY"])])]);
|
||||
let speaker = EntityId::parse("entity:nib").unwrap();
|
||||
let prompt = Prompt::lower(&view, &item, &speaker, "en-US", &cast.inventory().unwrap(), &held, &weksa::Ontology::empty()).unwrap();
|
||||
let text = prompt.text();
|
||||
assert!(text.contains(r#""entity":"entity:nibu""#), "{text}");
|
||||
assert!(text.contains("NIBUCANARY"), "{text}");
|
||||
}
|
||||
|
||||
/// The proof packet admitted for an item whose speaker is `speaker` and
|
||||
/// whose prior turn is `other`'s, with `speaker` on referent n3 and `other`
|
||||
/// on referent n1, then lowered in en-US over an entity port holding `held`.
|
||||
fn lowered_for(speaker: &str, other: &str, held: &[Entity]) -> String {
|
||||
let cast = InventoryStore::open(&data("interlingua/inventory.cc")).unwrap();
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
let mut entities = EntityStore::open(&dir.path().join("e.cc")).unwrap();
|
||||
for slug in [speaker, other] {
|
||||
entities.put(super::common::ent(slug, "en-US", &["Stored"])).unwrap();
|
||||
}
|
||||
let mut corpus = CorpusStore::open(&dir.path().join("c.cc")).unwrap();
|
||||
let mut item = super::common::item_in("item:nibu:1", "A line.", &super::common::group_in_bucket(10), super::common::cast());
|
||||
item.speaker = super::common::eid(speaker);
|
||||
item.prior_turns = vec![weksa::Turn { speaker: super::common::eid(other), text: "Well?".into() }];
|
||||
corpus.add(item, &entities).unwrap();
|
||||
let mut packet = proof_packet();
|
||||
packet.referents[0].entity = Some(super::common::eid(other));
|
||||
packet.referents[2].entity = Some(super::common::eid(speaker));
|
||||
let view = PacketStore::open(&dir.path().join("p.cc"))
|
||||
.unwrap()
|
||||
.admit(packet, &cast, &corpus, &entities)
|
||||
.unwrap();
|
||||
let state = weksa::SpeakerStateStore::open(&dir.path().join("s.cc")).unwrap();
|
||||
let view = view.with_scene(&cast.inventory().unwrap(), &state, &corpus).unwrap();
|
||||
let item = CorpusItemId::parse("item:nibu:1").unwrap();
|
||||
Prompt::lower(
|
||||
&view,
|
||||
&item,
|
||||
&super::common::eid(speaker),
|
||||
"en-US",
|
||||
&cast.inventory().unwrap(),
|
||||
&Held(held.to_vec()),
|
||||
&weksa::Ontology::empty(),
|
||||
)
|
||||
.unwrap()
|
||||
.text()
|
||||
.to_string()
|
||||
}
|
||||
|
||||
/// Persona's ruling `speaker-alias-token-in-lowering-prompt`: the item's
|
||||
/// speaker prints as one fixed role token, the same for every speaker and
|
||||
/// every item, with the speaker's forms under it; its entity id never
|
||||
/// prints. Another cited entity still prints under its own id.
|
||||
#[test]
|
||||
fn the_item_speaker_is_a_fixed_token_with_its_forms() {
|
||||
const TOKEN: &str = "entity:speaker";
|
||||
let forms = |slug: &str, form: &str| super::common::ent(slug, "en-US", &[form]);
|
||||
let other = forms("othercite", "OTTERBLOOM");
|
||||
let a = lowered_for("keeperzed", "othercite", &[forms("keeperzed", "ZEBRAQUILL"), other.clone()]);
|
||||
let b = lowered_for("secondvoice", "othercite", &[forms("secondvoice", "MARMOTLUTE"), other.clone()]);
|
||||
for (text, id, form, other_form) in [(&a, "keeperzed", "ZEBRAQUILL", "MARMOTLUTE"), (&b, "secondvoice", "MARMOTLUTE", "ZEBRAQUILL")] {
|
||||
assert!(!text.contains(id), "{id} in {text}");
|
||||
assert!(!text.contains(other_form), "{other_form} in {text}");
|
||||
assert!(text.contains(r#""concept":"concept:5","entity":"entity:speaker""#), "{text}");
|
||||
assert!(text.contains(&format!(r#""{TOKEN}":["{form}"]"#)), "{text}");
|
||||
assert!(text.contains(r#""entity":"entity:othercite""#), "{text}");
|
||||
assert!(text.contains(r#""entity:othercite":["OTTERBLOOM"]"#), "{text}");
|
||||
}
|
||||
// The token is one constant: the entities lines differ only in the speaker's form.
|
||||
assert_eq!(a.replace("ZEBRAQUILL", "F"), b.replace("MARMOTLUTE", "F"));
|
||||
// A speaker with no form in the language does not refuse and gets no token entry.
|
||||
let bare = lowered_for("keeperzed", "othercite", &[other]);
|
||||
assert!(!bare.contains("keeperzed") && !bare.contains(TOKEN), "{bare}");
|
||||
assert!(bare.contains(r#"{"entity:othercite":["OTTERBLOOM"]}"#), "{bare}");
|
||||
}
|
||||
|
||||
fn feature(inv: &Inventory, gloss: &str) -> weksa::InvId {
|
||||
inv.entries().find(|e| e.gloss == gloss).unwrap().id
|
||||
}
|
||||
|
|
@ -1170,7 +928,7 @@ mod lowering {
|
|||
let item = CorpusItemId::parse("item:nibu:1").unwrap();
|
||||
let view = view_of(Some(700), None, &cast, &cast_entities);
|
||||
let lowered = |view: &LoweringInput, o: &weksa::Ontology| {
|
||||
Prompt::lower(view, &item, &away(), "ja-JP", &inv, &held, o).unwrap()
|
||||
Prompt::lower(view, &item, "ja-JP", &inv, &held, o).unwrap()
|
||||
};
|
||||
let prompt = lowered(&view, &ontology);
|
||||
let text = prompt.text();
|
||||
|
|
@ -1183,7 +941,8 @@ mod lowering {
|
|||
assert!(none.text().contains("\n\nontology: none\n\n"));
|
||||
// Entries move the prompt and nothing else of the view does.
|
||||
assert_ne!(prompt.digest(), none.digest());
|
||||
// The group is still private.
|
||||
// The group is still private; the speaker's entity appears only because
|
||||
// the packet cites it on a referent.
|
||||
let held_item = CorpusStore::open(&data("corpus/corpus.cc"))
|
||||
.unwrap()
|
||||
.get(item.as_str())
|
||||
|
|
|
|||
|
|
@ -1,11 +1,11 @@
|
|||
//! The Dao De Jing test bed (`data/daodejing`): its Legge items carry full
|
||||
//! public-domain provenance, and its packets are admitted
|
||||
//! (`docs/targets/dao-de-jing-test-bed.md`).
|
||||
//! public-domain provenance, and its packets are admitted and lower to the
|
||||
//! English the first golf-loop run scored (`docs/targets/dao-de-jing-test-bed.md`).
|
||||
|
||||
use std::path::Path;
|
||||
|
||||
use weksa::daodejing::packets;
|
||||
use weksa::{CorpusStore, EntityStore, InventoryStore, PacketStore, Source};
|
||||
use weksa::{CorpusStore, EntityStore, InventoryStore, PacketStore, Source, lower};
|
||||
|
||||
fn root() -> std::path::PathBuf {
|
||||
Path::new(env!("CARGO_MANIFEST_DIR")).join("../../data/daodejing")
|
||||
|
|
@ -39,15 +39,30 @@ fn every_legge_item_names_licence_jurisdiction_translator_and_edition_year() {
|
|||
}
|
||||
|
||||
#[test]
|
||||
fn the_slice_packets_are_admitted_and_the_committed_store_holds_them() {
|
||||
fn the_slice_packets_are_admitted_and_lower_to_the_scored_english() {
|
||||
let inventory = InventoryStore::open(&root().join("inventory.cc")).unwrap();
|
||||
let corpus = CorpusStore::open(&root().join("corpus.cc")).unwrap();
|
||||
let entities = EntityStore::open(&root().join("entity.cc")).unwrap();
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
let mut store = PacketStore::open(&dir.path().join("p.cc")).unwrap();
|
||||
for p in packets() {
|
||||
store.admit(p, &inventory, &corpus, &entities).unwrap();
|
||||
}
|
||||
let inv = inventory.inventory().unwrap();
|
||||
let lowered: Vec<String> = packets()
|
||||
.into_iter()
|
||||
.map(|p| {
|
||||
let view = store.admit(p, &inventory, &corpus, &entities).unwrap();
|
||||
lower(&view, &inv, &entities).unwrap()
|
||||
})
|
||||
.collect();
|
||||
assert_eq!(
|
||||
lowered,
|
||||
[
|
||||
"The sage empties the minds. The sage fills the bellies. The sage weakens the wills. The sage strengthens the bones.",
|
||||
"The heaven is long-enduring. The earth continues long.",
|
||||
"The highest excellence is like the water.",
|
||||
"The words that are strictly true seem paradoxical.",
|
||||
"The space between heaven and earth may be compared to the bellows.",
|
||||
]
|
||||
);
|
||||
// The committed packet store holds exactly what the module builds.
|
||||
let stored = PacketStore::open(&root().join("packets.cc")).unwrap();
|
||||
for p in packets() {
|
||||
|
|
|
|||
|
|
@ -33,6 +33,20 @@ fn assert_clean_and_distinct<T: std::fmt::Display + std::fmt::Debug>(all: Vec<T>
|
|||
#[test]
|
||||
fn lower_error_display_names_the_variant_and_no_identifier() {
|
||||
assert_clean_and_distinct(vec![
|
||||
LowerError::Unrendered { what: SENTINEL },
|
||||
LowerError::NoRow { id: inv() },
|
||||
LowerError::GlossMismatch {
|
||||
id: inv(),
|
||||
row: SENTINEL,
|
||||
},
|
||||
LowerError::UnknownRole {
|
||||
frame: inv(),
|
||||
role: SENTINEL.into(),
|
||||
},
|
||||
LowerError::MissingRole {
|
||||
predication: node(),
|
||||
role: SENTINEL.into(),
|
||||
},
|
||||
LowerError::UnknownEntity { entity: entity() },
|
||||
LowerError::NoForm { entity: entity() },
|
||||
LowerError::NoPronunciation { entity: entity() },
|
||||
|
|
@ -46,6 +60,12 @@ fn lower_error_display_names_the_variant_and_no_identifier() {
|
|||
entity: entity(),
|
||||
at: 4242,
|
||||
},
|
||||
LowerError::ConsentMissing {
|
||||
predication: node(),
|
||||
},
|
||||
LowerError::AskerNotAddressee {
|
||||
predication: node(),
|
||||
},
|
||||
LowerError::EntityRead {
|
||||
entity: entity(),
|
||||
why: SENTINEL.into(),
|
||||
|
|
@ -104,7 +124,6 @@ fn refusal_display_names_the_rule_and_no_identifier() {
|
|||
},
|
||||
Refusal::V16SpeakerNotInScene,
|
||||
Refusal::V17AddresseeNotAReferent { id: node() },
|
||||
Refusal::V18RequestWithoutConsent { predication: node() },
|
||||
];
|
||||
assert_eq!(
|
||||
Refusal::V16SpeakerNotInScene.to_string(),
|
||||
|
|
|
|||
|
|
@ -502,96 +502,3 @@ fn a_malformed_pronunciation_is_refused() {
|
|||
}
|
||||
assert_eq!(store.get(&eid("kay")).unwrap(), None);
|
||||
}
|
||||
|
||||
const LANTERN: &str = r#"{"slug":"lantern-wager","language":"en-US","admitted_on":"2026-11-13",
|
||||
"source":{"PublicDomain":{"work":"The Lantern Wager","author":"A. Invented","edition_url":"https://example.invalid/lantern","licence":"public domain","jurisdiction":"US","translator":"none","edition_year":1890}},
|
||||
"cast":[{"entity":"entity:orsa","forms":["Orsa"]},{"entity":"entity:tamsin","forms":["Tamsin","Tam"]}],
|
||||
"lines":[{"group":"s1","speaker":"entity:orsa","text":"Tamsin, bring the lantern."},
|
||||
{"group":"s1","speaker":"entity:tamsin","text":"Tamsin's lantern, said Orsa."},
|
||||
{"group":"s2","speaker":"entity:orsa","text":"Quiet, both of you."}]}"#;
|
||||
|
||||
fn marked(line: u32, text: &str) -> weksa::encode::MarkedLine {
|
||||
weksa::encode::MarkedLine { line, marked: text.into() }
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn an_imported_work_passes_the_store_doors() {
|
||||
use weksa::Annotator;
|
||||
use weksa::corpus::ModelFamily;
|
||||
let d = tempfile::tempdir().unwrap();
|
||||
let mut entities = EntityStore::open(&d.path().join("e.cc")).unwrap();
|
||||
let mut corpus = CorpusStore::open(&d.path().join("c.cc")).unwrap();
|
||||
let model = Annotator::Model { family: ModelFamily::Anthropic, generator: "g".into() };
|
||||
let work = || weksa::encode::WorkDraft::parse(LANTERN).unwrap();
|
||||
let (cast, items) = work()
|
||||
.into_import(&[marked(1, "[[entity:tamsin|Tamsin]], bring the lantern.")], &model)
|
||||
.unwrap();
|
||||
for e in cast {
|
||||
assert_eq!(entities.put(e).unwrap(), AddOutcome::Added);
|
||||
}
|
||||
for i in items.clone() {
|
||||
assert_eq!(corpus.add(i, &entities).unwrap(), AddOutcome::Added);
|
||||
}
|
||||
drop(corpus);
|
||||
let mut corpus = CorpusStore::open(&d.path().join("c.cc")).unwrap();
|
||||
let stored = corpus.get("item:lantern-wager:1").unwrap().unwrap();
|
||||
assert_eq!(stored.names_by, Some(model.clone()));
|
||||
assert_eq!(stored.names.len(), 1);
|
||||
assert_eq!(corpus.add(items[0].clone(), &entities).unwrap(), AddOutcome::Unchanged);
|
||||
|
||||
// A form the entity does not list is the store's refusal, not the importer's.
|
||||
let (_, bad) = work()
|
||||
.into_import(&[marked(2, "[[entity:tamsin|Tamsin's]] lantern, said Orsa.")], &model)
|
||||
.unwrap();
|
||||
assert!(matches!(
|
||||
refusal(corpus.add(bad[0].clone(), &entities)),
|
||||
StoreRefusal::NameSpanNotAForm { .. }
|
||||
));
|
||||
|
||||
// An operator run over another line labels its own spans.
|
||||
let (_, op) = work()
|
||||
.into_import(&[marked(3, "Quiet, both of you.")], &Annotator::Operator)
|
||||
.unwrap();
|
||||
assert_eq!(corpus.add(op[0].clone(), &entities).unwrap(), AddOutcome::Added);
|
||||
assert_eq!(
|
||||
corpus.get("item:lantern-wager:3").unwrap().unwrap().names_by,
|
||||
Some(Annotator::Operator)
|
||||
);
|
||||
// The first run's line keeps its label.
|
||||
assert_eq!(corpus.get("item:lantern-wager:1").unwrap().unwrap().names_by, Some(model));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn committed_items_read_with_no_names_label() {
|
||||
let data = std::path::Path::new(env!("CARGO_MANIFEST_DIR")).join("../../data");
|
||||
for sub in ["daodejing", "original"] {
|
||||
let d = tempfile::tempdir().unwrap();
|
||||
let copy = d.path().join("c.cc");
|
||||
std::fs::copy(data.join(sub).join("corpus.cc"), ©).unwrap();
|
||||
let items = CorpusStore::open(©).unwrap().all().unwrap();
|
||||
assert!(!items.is_empty(), "{sub}");
|
||||
assert!(items.iter().all(|i| i.names_by.is_none()), "{sub}");
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_blank_names_by_generator_is_refused_by_the_corpus_door() {
|
||||
use weksa::Annotator;
|
||||
use weksa::corpus::ModelFamily;
|
||||
let d = tempfile::tempdir().unwrap();
|
||||
let mut entities = EntityStore::open(&d.path().join("e.cc")).unwrap();
|
||||
let mut corpus = CorpusStore::open(&d.path().join("c.cc")).unwrap();
|
||||
let blank = Annotator::Model { family: ModelFamily::Anthropic, generator: " ".into() };
|
||||
let (cast, items) = weksa::encode::WorkDraft::parse(LANTERN)
|
||||
.unwrap()
|
||||
.into_import(&[marked(3, "Quiet, both of you.")], &blank)
|
||||
.unwrap();
|
||||
for e in cast {
|
||||
entities.put(e).unwrap();
|
||||
}
|
||||
assert!(matches!(
|
||||
refusal(corpus.add(items[0].clone(), &entities)),
|
||||
StoreRefusal::Malformed { .. }
|
||||
));
|
||||
assert!(corpus.all().unwrap().is_empty());
|
||||
}
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load diff
|
|
@ -1,16 +1,22 @@
|
|||
//! The entity port, `pronounce` and `phones` against the committed stores and
|
||||
//! the `nibu-proof-001` packet.
|
||||
//! The English lowerer against the committed inventory (revision 2) and the
|
||||
//! `nibu-proof-001` packet, and the rules that keep a table row from speaking
|
||||
//! for a meaning it does not carry.
|
||||
|
||||
mod common;
|
||||
use std::path::Path;
|
||||
|
||||
use common::{iv, nd};
|
||||
use weksa::entity::{Entity, EntityOrigin, LanguageForms};
|
||||
use weksa::packet::{EntityId, Packet, proof_packet};
|
||||
use weksa::inventory::proof_revision;
|
||||
use weksa::packet::{EntityId, FeatValue, FeatureValue, Packet, proof_packet};
|
||||
use weksa::{
|
||||
CorpusStore, EntityForms, EntityStore, Inventory, InventoryStore, LowerError, LoweringInput,
|
||||
PacketStore, PhoneInventory, PhoneLine, Pronunciation, Stress, pronounce,
|
||||
PacketStore, PhoneInventory, PhoneLine, Pronunciation, Stress, lower, pronounce, validate,
|
||||
};
|
||||
|
||||
const PROOF: &str = "Warning: you may endanger yourself by touching the control. \
|
||||
Nibu will stop that.";
|
||||
|
||||
fn committed() -> (Inventory, tempfile::TempDir) {
|
||||
let root = Path::new(env!("CARGO_MANIFEST_DIR")).join("../..");
|
||||
let inv = InventoryStore::open(&root.join("data/interlingua/inventory.cc")).unwrap();
|
||||
|
|
@ -42,6 +48,181 @@ fn committed_entities() -> EntityStore {
|
|||
EntityStore::open(&root.join("data/entity/entity.cc")).unwrap()
|
||||
}
|
||||
|
||||
fn lowered(packet: &Packet, inv: &Inventory) -> Result<String, LowerError> {
|
||||
lower(&view(packet, inv), inv, &committed_entities())
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn the_proof_packet_is_admitted_by_the_store_and_lowers_to_its_sentences() {
|
||||
let root = Path::new(env!("CARGO_MANIFEST_DIR")).join("../..");
|
||||
let (inv, dir) = committed();
|
||||
let inventory = InventoryStore::open(&root.join("data/interlingua/inventory.cc")).unwrap();
|
||||
let corpus = CorpusStore::open(&root.join("data/corpus/corpus.cc")).unwrap();
|
||||
let entities = EntityStore::open(&root.join("data/entity/entity.cc")).unwrap();
|
||||
let mut packets = PacketStore::open(&dir.path().join("p.cc")).unwrap();
|
||||
packets
|
||||
.admit(proof_packet(), &inventory, &corpus, &entities)
|
||||
.unwrap();
|
||||
let stored = packets.get("packet:6e6962752d303031").unwrap().unwrap();
|
||||
assert_eq!(lowered(&stored, &inv).unwrap(), PROOF);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn only_the_addressee_is_you_and_is_reflexive() {
|
||||
let (inv, _dir) = committed();
|
||||
let mut p = proof_packet();
|
||||
p.discourse.addressee = None;
|
||||
assert_eq!(
|
||||
lowered(&p, &inv).unwrap(),
|
||||
"Warning: the player may endanger the player by touching the control. \
|
||||
Nibu will stop that."
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn no_speech_act_means_no_opener_and_a_capital() {
|
||||
let (inv, _dir) = committed();
|
||||
let mut p = proof_packet();
|
||||
p.discourse.speech_act = None;
|
||||
assert!(lowered(&p, &inv).unwrap().starts_with("You may endanger"));
|
||||
p.discourse.speech_act = Some(iv("speech_act:1"));
|
||||
assert!(lowered(&p, &inv).unwrap().starts_with("You may endanger"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_packet_carrying_what_the_lowerer_does_not_render_is_refused() {
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
let mut store = InventoryStore::open(&dir.path().join("i.cc")).unwrap();
|
||||
let (rev1, entries) = weksa::inventory::seed();
|
||||
store.admit_revision(rev1, entries).unwrap();
|
||||
let (rev2, entries) = proof_revision();
|
||||
store.admit_revision(rev2, entries).unwrap();
|
||||
let mut ext = common::entry("extension:1", 3);
|
||||
ext.value_kind = Some(weksa::ValueKind::Grade);
|
||||
common::admit(&mut store, 3, vec![ext]);
|
||||
let inv = store.inventory().unwrap();
|
||||
let discourse = |p: &mut Packet| {
|
||||
p.discourse.features.push(FeatureValue {
|
||||
feature: iv("feature:6"),
|
||||
value: FeatValue::Grade(common::grade(300)),
|
||||
})
|
||||
};
|
||||
let predication = |p: &mut Packet| {
|
||||
p.predications[0].features.push(FeatureValue {
|
||||
feature: iv("feature:1"),
|
||||
value: FeatValue::Option(common::lab("negative")),
|
||||
})
|
||||
};
|
||||
let relation = |p: &mut Packet| {
|
||||
p.relations.push(weksa::packet::Relation {
|
||||
relation: iv("relation:8"),
|
||||
from: nd("n4"),
|
||||
to: nd("n5"),
|
||||
features: vec![],
|
||||
})
|
||||
};
|
||||
let extension = |p: &mut Packet| {
|
||||
p.inventory_rev = 3;
|
||||
p.extensions.push(weksa::packet::Extension {
|
||||
key: iv("extension:1"),
|
||||
value: FeatValue::Grade(common::grade(3)),
|
||||
})
|
||||
};
|
||||
let referent_feature = |p: &mut Packet| {
|
||||
p.referents[0].features.push(FeatureValue {
|
||||
feature: iv("feature:6"),
|
||||
value: FeatValue::Grade(common::grade(1)),
|
||||
})
|
||||
};
|
||||
let no_predication = |p: &mut Packet| p.predications.clear();
|
||||
let extra_role = |p: &mut Packet| {
|
||||
let filler = p.predications[0].roles[0].filler.clone();
|
||||
p.predications[0].roles.push(weksa::packet::RoleFill {
|
||||
role: iv("role:3"),
|
||||
filler,
|
||||
})
|
||||
};
|
||||
let consent = |p: &mut Packet| p.discourse.addressee_consent = Some(nd("n5"));
|
||||
let lone_referent = |p: &mut Packet| {
|
||||
let mut r = p.referents[0].clone();
|
||||
r.id = nd("n99");
|
||||
p.referents.push(r)
|
||||
};
|
||||
for (what, edit) in [
|
||||
("features", &discourse as &dyn Fn(&mut Packet)),
|
||||
("features", &predication),
|
||||
("addressee consent", &consent),
|
||||
("relations", &relation),
|
||||
("extensions", &extension),
|
||||
("no predication", &no_predication),
|
||||
("a role the frame does not name", &extra_role),
|
||||
("a referent no role mentions", &lone_referent),
|
||||
] {
|
||||
let mut p = proof_packet();
|
||||
edit(&mut p);
|
||||
assert_eq!(
|
||||
lower(&admitted(&p, &store), &inv, &committed_entities()),
|
||||
Err(LowerError::Unrendered { what }),
|
||||
"{what}"
|
||||
);
|
||||
}
|
||||
// The seed lets no feature sit on a referent, so that arm is refused by validate.
|
||||
let mut p = proof_packet();
|
||||
referent_feature(&mut p);
|
||||
assert!(validate(&p, &inv).is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn an_unknown_row_and_an_unfilled_role_are_refused_by_name() {
|
||||
let (inv, _dir) = committed();
|
||||
let mut p = proof_packet();
|
||||
p.discourse.speech_act = Some(iv("speech_act:3"));
|
||||
assert_eq!(
|
||||
lowered(&p, &inv),
|
||||
Err(LowerError::NoRow {
|
||||
id: iv("speech_act:3")
|
||||
})
|
||||
);
|
||||
let mut p = proof_packet();
|
||||
p.predications[0].roles.pop();
|
||||
assert_eq!(
|
||||
lowered(&p, &inv),
|
||||
Err(LowerError::MissingRole {
|
||||
predication: nd("n4"),
|
||||
role: "patient".into()
|
||||
})
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_row_cannot_speak_for_an_id_whose_gloss_differs() {
|
||||
// Revision 2 with concept:4 glossed "hatch" in place of "control": the row
|
||||
// for concept:4 says "control" and must not render it.
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
let mut store = InventoryStore::open(&dir.path().join("i.cc")).unwrap();
|
||||
let (rev1, entries) = weksa::inventory::seed();
|
||||
store.admit_revision(rev1, entries).unwrap();
|
||||
let (rev2, mut entries) = proof_revision();
|
||||
for e in &mut entries {
|
||||
if e.id == iv("concept:4") {
|
||||
e.gloss = "hatch".into();
|
||||
}
|
||||
}
|
||||
store.admit_revision(rev2, entries).unwrap();
|
||||
let inv = store.inventory().unwrap();
|
||||
assert_eq!(
|
||||
lower(
|
||||
&admitted(&proof_packet(), &store),
|
||||
&inv,
|
||||
&committed_entities()
|
||||
),
|
||||
Err(LowerError::GlossMismatch {
|
||||
id: iv("concept:4"),
|
||||
row: "control"
|
||||
})
|
||||
);
|
||||
}
|
||||
|
||||
/// An entity port a test controls: ids to entities, and an optional read fault.
|
||||
#[derive(Default)]
|
||||
struct Entities {
|
||||
|
|
@ -76,6 +257,109 @@ fn nibu(forms: &[(&str, &[&str])]) -> Entity {
|
|||
}
|
||||
}
|
||||
|
||||
fn through(entities: &Entities) -> Result<String, LowerError> {
|
||||
let (inv, _dir) = committed();
|
||||
lower(&view(&proof_packet(), &inv), &inv, entities)
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_name_survives_lowering_verbatim_where_the_concept_word_was() {
|
||||
// The entity's own form, not "the ship mind", and not re-cased or inflected:
|
||||
// the form is lowercase and stays so mid-sentence.
|
||||
let mut e = Entities::default();
|
||||
let n = nibu(&[("en-US", &["nibu-of-the-deep"])]);
|
||||
e.held.push(n);
|
||||
// It opens the second sentence, where a template word would be capitalised.
|
||||
assert_eq!(
|
||||
through(&e).unwrap(),
|
||||
"Warning: you may endanger yourself by touching the control. \
|
||||
nibu-of-the-deep will stop that."
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn only_the_target_languages_citation_form_is_chosen() {
|
||||
// Forms after the first are inflected shapes no English frame asks for; a
|
||||
// form under another language tag is never read, whatever order it is in.
|
||||
let mut e = Entities::default();
|
||||
let n = nibu(&[
|
||||
("sa-Latn", &["Nibuwa"]),
|
||||
("en-US", &["Nibu", "Nibu's", "Nibus"]),
|
||||
]);
|
||||
e.held.push(n);
|
||||
assert_eq!(through(&e).unwrap(), PROOF);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn an_entity_the_port_does_not_hold_is_refused_not_replaced_by_its_concept_word() {
|
||||
let id = EntityId::parse("entity:nibu").unwrap();
|
||||
assert_eq!(
|
||||
through(&Entities::default()),
|
||||
Err(LowerError::UnknownEntity { entity: id })
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn an_entity_with_no_target_language_form_is_refused() {
|
||||
let mut e = Entities::default();
|
||||
let n = nibu(&[("sa-Latn", &["Nibuwa"])]);
|
||||
let id = n.id.clone();
|
||||
e.held.push(n);
|
||||
assert_eq!(through(&e), Err(LowerError::NoForm { entity: id }));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_failing_entity_port_is_refused_by_name() {
|
||||
let e = Entities {
|
||||
fault: true,
|
||||
..Entities::default()
|
||||
};
|
||||
assert_eq!(
|
||||
through(&e),
|
||||
Err(LowerError::EntityRead {
|
||||
entity: EntityId::parse("entity:nibu").unwrap(),
|
||||
why: "store unreadable".into()
|
||||
})
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn an_addressee_entity_still_lowers_to_you_and_is_never_looked_up() {
|
||||
// Naming the addressee would break "you"/"yourself": the port is not asked,
|
||||
// so a port that faults on every read changes nothing.
|
||||
let (inv, _dir) = committed();
|
||||
let mut p = proof_packet();
|
||||
p.referents[0].entity = Some(EntityId::parse("entity:nibu").unwrap());
|
||||
p.referents[2].entity = None;
|
||||
let faulting = Entities {
|
||||
fault: true,
|
||||
..Entities::default()
|
||||
};
|
||||
assert_eq!(
|
||||
lower(&view(&p, &inv), &inv, &faulting).unwrap(),
|
||||
"Warning: you may endanger yourself by touching the control. \
|
||||
The ship mind will stop that."
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_purpose_the_frame_does_not_say_is_refused_not_dropped() {
|
||||
// The intervention row says "will stop"; a packet that also fills the
|
||||
// beneficiary role would assert a purpose the text does not carry.
|
||||
let (inv, _dir) = committed();
|
||||
let mut p = proof_packet();
|
||||
p.predications[1].roles.push(weksa::packet::RoleFill {
|
||||
role: iv("role:8"),
|
||||
filler: nd("n1"),
|
||||
});
|
||||
assert_eq!(
|
||||
lowered(&p, &inv),
|
||||
Err(LowerError::Unrendered {
|
||||
what: "a role the frame does not name"
|
||||
})
|
||||
);
|
||||
}
|
||||
|
||||
fn ruled(ipa: &str, rejected: &[&str]) -> Pronunciation {
|
||||
Pronunciation {
|
||||
ipa: ipa.into(),
|
||||
|
|
@ -91,21 +375,6 @@ fn say(entities: &dyn EntityForms) -> Result<Vec<String>, LowerError> {
|
|||
pronounce(&view(&proof_packet(), &inv), entities)
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_failing_entity_port_is_refused_by_name() {
|
||||
let e = Entities {
|
||||
fault: true,
|
||||
..Entities::default()
|
||||
};
|
||||
assert_eq!(
|
||||
say(&e),
|
||||
Err(LowerError::EntityRead {
|
||||
entity: EntityId::parse("entity:nibu").unwrap(),
|
||||
why: "store unreadable".into()
|
||||
})
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn nibu_round_trips_from_the_committed_seed_to_its_ruled_ipa() {
|
||||
let seed = committed_entities();
|
||||
|
|
@ -304,3 +573,160 @@ fn the_inventory_parser_refuses_what_it_cannot_read() {
|
|||
assert!(PhoneInventory::parse("# c\n\ni\tvowel\ttense\ta\n").is_ok());
|
||||
assert!(PhoneInventory::for_language("sa-Latn").is_none());
|
||||
}
|
||||
|
||||
/// `nibu-proof-001` re-cut as the request: the addressee asked Nibu to stop,
|
||||
/// one frame:3 predication (n4), consent naming it, and no other claim.
|
||||
fn asked() -> Packet {
|
||||
let mut p = proof_packet();
|
||||
p.referents.remove(1);
|
||||
let mut ask = p.predications[1].clone();
|
||||
ask.id = nd("n4");
|
||||
ask.concept = iv("concept:6");
|
||||
ask.frame = iv("frame:3");
|
||||
ask.roles = vec![
|
||||
weksa::packet::RoleFill {
|
||||
role: iv("role:1"),
|
||||
filler: nd("n1"),
|
||||
},
|
||||
weksa::packet::RoleFill {
|
||||
role: iv("role:2"),
|
||||
filler: nd("n3"),
|
||||
},
|
||||
];
|
||||
p.predications = vec![ask];
|
||||
p.discourse.speech_act = Some(iv("speech_act:1"));
|
||||
p.discourse.addressee_consent = Some(nd("n4"));
|
||||
p.constraints.preserve = vec![nd("n1")];
|
||||
p
|
||||
}
|
||||
|
||||
/// The request plus a frame:2 predication (n5) the consent could wrongly name.
|
||||
fn asked_and_stopped() -> Packet {
|
||||
let mut p = asked();
|
||||
let mut stop = proof_packet().predications.remove(1);
|
||||
stop.roles[1].filler = nd("n4");
|
||||
p.predications.push(stop);
|
||||
p
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_consented_request_lowers_to_what_the_addressee_asked() {
|
||||
let (inv, _dir) = committed();
|
||||
assert_eq!(lowered(&asked(), &inv).unwrap(), "You asked Nibu to stop.");
|
||||
let mut p = asked();
|
||||
p.provenance.source = weksa::packet::ProvenanceSource::GameTelemetry;
|
||||
assert_eq!(lowered(&p, &inv).unwrap(), "You asked Nibu to stop.");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_request_without_its_consent_is_refused_not_invented() {
|
||||
let (inv, _dir) = committed();
|
||||
let mut p = asked();
|
||||
p.discourse.addressee_consent = None;
|
||||
assert_eq!(
|
||||
lowered(&p, &inv),
|
||||
Err(LowerError::ConsentMissing {
|
||||
predication: nd("n4")
|
||||
})
|
||||
);
|
||||
// Consent that names a different predication is no consent to the request.
|
||||
let mut p = asked_and_stopped();
|
||||
p.discourse.addressee_consent = Some(nd("n5"));
|
||||
assert_eq!(
|
||||
lowered(&p, &inv),
|
||||
Err(LowerError::ConsentMissing {
|
||||
predication: nd("n4")
|
||||
})
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn consent_to_one_of_two_requests_leaves_the_other_unconsented() {
|
||||
let (inv, _dir) = committed();
|
||||
let mut p = asked();
|
||||
let mut second = p.predications[0].clone();
|
||||
second.id = nd("n5");
|
||||
p.predications.push(second);
|
||||
assert_eq!(
|
||||
lowered(&p, &inv),
|
||||
Err(LowerError::ConsentMissing {
|
||||
predication: nd("n5")
|
||||
})
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn the_asker_is_the_role_the_inventory_glosses_agent_not_the_first_role() {
|
||||
// role:1 and role:2 swap glosses: "agent" is now role:2, so the asker of
|
||||
// `asked()` (role:1 filled by the addressee) is the one role:2 names, Nibu.
|
||||
// A lookup that took the first role, or the first live entry, would read the
|
||||
// addressee and let the request through.
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
let mut store = InventoryStore::open(&dir.path().join("i.cc")).unwrap();
|
||||
let (rev1, mut entries) = weksa::inventory::seed();
|
||||
for e in &mut entries {
|
||||
if e.id == iv("role:1") {
|
||||
e.gloss = "patient".into();
|
||||
} else if e.id == iv("role:2") {
|
||||
e.gloss = "agent".into();
|
||||
}
|
||||
}
|
||||
store.admit_revision(rev1, entries).unwrap();
|
||||
let (rev2, entries) = proof_revision();
|
||||
store.admit_revision(rev2, entries).unwrap();
|
||||
let inv = store.inventory().unwrap();
|
||||
assert_eq!(
|
||||
lower(&admitted(&asked(), &store), &inv, &committed_entities()),
|
||||
Err(LowerError::AskerNotAddressee {
|
||||
predication: nd("n4")
|
||||
})
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_request_by_someone_other_than_the_addressee_is_refused() {
|
||||
let (inv, _dir) = committed();
|
||||
let mut p = asked();
|
||||
p.predications[0].roles[0].filler = nd("n3");
|
||||
p.predications[0].roles[1].filler = nd("n1");
|
||||
assert_eq!(
|
||||
lowered(&p, &inv),
|
||||
Err(LowerError::AskerNotAddressee {
|
||||
predication: nd("n4")
|
||||
})
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn consent_on_a_claim_that_is_no_request_stays_unrendered() {
|
||||
let (inv, _dir) = committed();
|
||||
let mut p = proof_packet();
|
||||
p.discourse.addressee_consent = Some(nd("n5"));
|
||||
assert_eq!(
|
||||
lowered(&p, &inv),
|
||||
Err(LowerError::Unrendered {
|
||||
what: "addressee consent"
|
||||
})
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_decomposition_or_import_cannot_reach_the_lowerer_with_consent() {
|
||||
let root = Path::new(env!("CARGO_MANIFEST_DIR")).join("../..");
|
||||
let inventory = InventoryStore::open(&root.join("data/interlingua/inventory.cc")).unwrap();
|
||||
let corpus = CorpusStore::open(&root.join("data/corpus/corpus.cc")).unwrap();
|
||||
let entities = EntityStore::open(&root.join("data/entity/entity.cc")).unwrap();
|
||||
for source in [
|
||||
weksa::packet::ProvenanceSource::ModelDecomposition,
|
||||
weksa::packet::ProvenanceSource::ImportedCorpus,
|
||||
] {
|
||||
let mut p = asked();
|
||||
p.provenance.source = source;
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
let refused = PacketStore::open(&dir.path().join("p.cc"))
|
||||
.unwrap()
|
||||
.admit(p, &inventory, &corpus, &entities)
|
||||
.unwrap_err();
|
||||
assert!(format!("{refused:?}").contains("V15"), "{source:?}");
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1,25 +0,0 @@
|
|||
//! Pins for behaviour of the small and middle weksa files that mutation testing
|
||||
//! found unpinned. Each test states the behaviour in domain terms.
|
||||
|
||||
use weksa::form::is_calendar_date;
|
||||
|
||||
/// A calendar date is exactly `YYYY-MM-DD`: both hyphens sit where the format
|
||||
/// puts them, so a ten-byte string with a digit in the second hyphen's place is
|
||||
/// no date.
|
||||
#[test]
|
||||
fn a_calendar_date_needs_both_hyphens_in_place() {
|
||||
assert!(is_calendar_date("2026-01-01"));
|
||||
assert!(!is_calendar_date("2026-01201"));
|
||||
assert!(!is_calendar_date("2026101-01"));
|
||||
}
|
||||
|
||||
/// February has 29 days in a Gregorian leap year and 28 otherwise.
|
||||
#[test]
|
||||
fn february_has_29_days_only_in_gregorian_leap_years() {
|
||||
assert!(is_calendar_date("2024-02-29"));
|
||||
assert!(is_calendar_date("2000-02-29"));
|
||||
assert!(!is_calendar_date("1900-02-29"));
|
||||
assert!(!is_calendar_date("2023-02-29"));
|
||||
assert!(is_calendar_date("2023-02-28"));
|
||||
assert!(!is_calendar_date("2024-02-30"));
|
||||
}
|
||||
|
|
@ -1,297 +0,0 @@
|
|||
//! Pins found by mutation testing store.rs, inventory.rs and main.rs. Each test
|
||||
//! states what the production code must do, in domain terms.
|
||||
mod common;
|
||||
use common::*;
|
||||
use std::process::{Command, Output};
|
||||
use weksa::packet::Grade;
|
||||
use weksa::store::EntityBound;
|
||||
use weksa::{
|
||||
Annotator, Condition, EntityStore, Layer, OntologyEntry, OntologyStore, Pronunciation, Refusal,
|
||||
Slot, StoreError, StoreRefusal, Test,
|
||||
};
|
||||
|
||||
fn refusal<T: std::fmt::Debug>(r: Result<T, StoreError>) -> StoreRefusal {
|
||||
match r {
|
||||
Err(StoreError::Refused(r)) => r,
|
||||
other => panic!("expected a store refusal, got {other:?}"),
|
||||
}
|
||||
}
|
||||
|
||||
fn kay_saying(p: Pronunciation) -> weksa::Entity {
|
||||
let mut e = ent("kay", "en-US", &["Kay"]);
|
||||
e.forms[0].pronunciation = Some(p);
|
||||
e
|
||||
}
|
||||
|
||||
fn ruling(ipa: &str, rejected: Vec<String>) -> Pronunciation {
|
||||
Pronunciation {
|
||||
ipa: ipa.into(),
|
||||
ruled_by: "Kay".into(),
|
||||
date: "2026-11-07".into(),
|
||||
source: "test".into(),
|
||||
rejected,
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_pronunciation_with_a_control_or_invisible_format_character_is_refused() {
|
||||
let d = tempfile::tempdir().unwrap();
|
||||
let mut store = EntityStore::open(&d.path().join("e.cc")).unwrap();
|
||||
// Either kind alone is refused: a control character, and a zero-width space.
|
||||
for ipa in ["ˈk\u{7}eɪ", "ˈk\u{200b}eɪ"] {
|
||||
assert!(
|
||||
matches!(
|
||||
store.put(kay_saying(ruling(ipa, vec![]))),
|
||||
Err(StoreError::Refused(StoreRefusal::Malformed { .. }))
|
||||
),
|
||||
"{ipa:?}"
|
||||
);
|
||||
}
|
||||
// The same for a rejected pronunciation.
|
||||
for bad in ["ˈk\u{7}aɪ", "ˈk\u{200b}aɪ"] {
|
||||
assert!(
|
||||
matches!(
|
||||
store.put(kay_saying(ruling("ˈkeɪ", vec![bad.into()]))),
|
||||
Err(StoreError::Refused(StoreRefusal::Malformed { .. }))
|
||||
),
|
||||
"{bad:?}"
|
||||
);
|
||||
}
|
||||
assert_eq!(store.get(&eid("kay")).unwrap(), None);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_pronunciation_keeps_at_most_eight_rejected_variants() {
|
||||
let d = tempfile::tempdir().unwrap();
|
||||
let mut store = EntityStore::open(&d.path().join("e.cc")).unwrap();
|
||||
let variants = |n: usize| -> Vec<String> { (0..n).map(|i| format!("ˈkaɪ{i}")).collect() };
|
||||
assert_eq!(
|
||||
refusal(store.put(kay_saying(ruling("ˈkeɪ", variants(9))))),
|
||||
StoreRefusal::EntityBounds {
|
||||
id: eid("kay"),
|
||||
bound: EntityBound::Forms
|
||||
}
|
||||
);
|
||||
store
|
||||
.put(kay_saying(ruling("ˈkeɪ", variants(8))))
|
||||
.expect("eight rejected variants are the bound, not beyond it");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn an_ontology_entry_read_at_an_unknown_revision_is_refused_with_one_refusal() {
|
||||
let w = world();
|
||||
let mut onto = OntologyStore::open(&w.dir.path().join("o2.cc")).unwrap();
|
||||
let entry = OntologyEntry {
|
||||
language: "en-US".into(),
|
||||
n: 1,
|
||||
inventory_rev: 99,
|
||||
layer: Layer::Discourse,
|
||||
when: vec![Condition {
|
||||
slot: Slot::Stance,
|
||||
feature: iv(ANGER),
|
||||
test: Test::AtLeast(Grade::new(200).unwrap()),
|
||||
}],
|
||||
choice: "WARM".into(),
|
||||
examples: vec![],
|
||||
annotator: Annotator::Operator,
|
||||
};
|
||||
match onto.admit(vec![entry], &w.inventory) {
|
||||
Err(StoreError::Invalid(r)) => assert_eq!(r, vec![Refusal::V10UnknownRevision { rev: 99 }]),
|
||||
other => panic!("{other:?}"),
|
||||
}
|
||||
}
|
||||
|
||||
fn weksa(dir: &std::path::Path, args: &[&str]) -> Output {
|
||||
Command::new(env!("CARGO_BIN_EXE_weksa"))
|
||||
.current_dir(dir)
|
||||
.args([
|
||||
"--corpus",
|
||||
"./c.cc",
|
||||
"--inventory",
|
||||
"./i.cc",
|
||||
"--entities",
|
||||
"./e.cc",
|
||||
"--ontology",
|
||||
"./o.cc",
|
||||
"--speaker-state",
|
||||
"./s.cc",
|
||||
])
|
||||
.args(args)
|
||||
.output()
|
||||
.unwrap()
|
||||
}
|
||||
|
||||
fn out(o: &Output) -> String {
|
||||
String::from_utf8_lossy(&o.stdout).into_owned() + &String::from_utf8_lossy(&o.stderr)
|
||||
}
|
||||
|
||||
fn ok(o: Output) -> String {
|
||||
assert!(o.status.success(), "{}", out(&o));
|
||||
out(&o)
|
||||
}
|
||||
|
||||
/// A scene bed: entities nibu and brokkr, the inventory through the
|
||||
/// speaker-scene revision (rev 3).
|
||||
fn scene_bed() -> tempfile::TempDir {
|
||||
let d = tempfile::tempdir().unwrap();
|
||||
for slug in ["nibu", "brokkr"] {
|
||||
let id = format!("entity:{slug}");
|
||||
let form = format!("en-US={}", slug.to_uppercase());
|
||||
ok(weksa(
|
||||
d.path(),
|
||||
&[
|
||||
"entity",
|
||||
"put",
|
||||
&id,
|
||||
"--form",
|
||||
&form,
|
||||
"--origin",
|
||||
"cast",
|
||||
"--persona",
|
||||
slug,
|
||||
"--fixture",
|
||||
"f.yaml",
|
||||
],
|
||||
));
|
||||
}
|
||||
for step in ["seed", "proof", "speaker-scene"] {
|
||||
ok(weksa(d.path(), &["inventory", step]));
|
||||
}
|
||||
d
|
||||
}
|
||||
|
||||
/// Adds a cast-authored line; returns the key it printed ("Added <key>").
|
||||
fn add_line(d: &std::path::Path, slug: &str, speaker: &str, group: &str, text: &str) -> String {
|
||||
let speaker = format!("entity:{speaker}");
|
||||
let printed = ok(weksa(
|
||||
d,
|
||||
&[
|
||||
"corpus",
|
||||
"add",
|
||||
"--slug",
|
||||
slug,
|
||||
"--text",
|
||||
text,
|
||||
"--speaker",
|
||||
&speaker,
|
||||
"--group",
|
||||
group,
|
||||
"--admitted-on",
|
||||
"2026-10-29",
|
||||
"--source",
|
||||
"cast-authored",
|
||||
"--language",
|
||||
"en-US",
|
||||
"--persona",
|
||||
"nibu",
|
||||
"--fixture",
|
||||
"f.yaml",
|
||||
"--author",
|
||||
"Ada Writer",
|
||||
],
|
||||
));
|
||||
printed.split_whitespace().nth(1).unwrap().to_string()
|
||||
}
|
||||
|
||||
fn scene_put(d: &std::path::Path, group: &str, to: &str) -> Output {
|
||||
weksa(
|
||||
d,
|
||||
&[
|
||||
"scene",
|
||||
"put",
|
||||
"--group",
|
||||
group,
|
||||
"--to",
|
||||
to,
|
||||
"--inventory-rev",
|
||||
"3",
|
||||
"--model-family",
|
||||
"anthropic",
|
||||
"--generator",
|
||||
"a scene annotator",
|
||||
"--set",
|
||||
"intimacy=200",
|
||||
],
|
||||
)
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_scene_group_holds_one_live_speaker_among_its_own_live_items() {
|
||||
let d = scene_bed();
|
||||
add_line(d.path(), "nibu", "nibu", "scene-1", "Mind the hatch.");
|
||||
// Another group's speaker and a withdrawn line of this group are not the
|
||||
// scene's speakers.
|
||||
add_line(d.path(), "brokkr", "brokkr", "scene-2", "Brokkr hums.");
|
||||
let gone = add_line(
|
||||
d.path(),
|
||||
"brokkr",
|
||||
"brokkr",
|
||||
"scene-1",
|
||||
"Brokkr leaves early.",
|
||||
);
|
||||
ok(weksa(d.path(), &["corpus", "withdraw", &gone]));
|
||||
let put = ok(scene_put(d.path(), "scene-1", "unnamed"));
|
||||
assert!(put.contains("scene:scene-1@1"), "{put}");
|
||||
assert!(ok(weksa(d.path(), &["scene", "dump"])).contains("entity:nibu->unnamed"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_scene_names_its_addressee_as_a_participant_unless_it_is_the_speaker() {
|
||||
let d = scene_bed();
|
||||
add_line(d.path(), "nibu", "nibu", "scene-1", "Mind the hatch.");
|
||||
add_line(d.path(), "nibu", "nibu", "scene-2", "Mind the ladder.");
|
||||
ok(scene_put(d.path(), "scene-1", "entity:brokkr"));
|
||||
let dump = ok(weksa(d.path(), &["scene", "dump"]));
|
||||
assert!(dump.contains("scene:scene-1@1 rev:3"), "{dump}");
|
||||
assert!(dump.contains("[entity:nibu,entity:brokkr]"), "{dump}");
|
||||
// A speaker addressing themself is a one-participant scene, whose
|
||||
// relation to a named party is refused as the store reads it.
|
||||
let own = scene_put(d.path(), "scene-2", "entity:nibu");
|
||||
assert!(!own.status.success());
|
||||
assert!(
|
||||
out(&own).contains("a relation's named to is another participant"),
|
||||
"{}",
|
||||
out(&own)
|
||||
);
|
||||
assert_eq!(ok(weksa(d.path(), &["scene", "dump"])), dump);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn relower_refuses_malformed_arm_and_floor_labels_before_reading_the_run() {
|
||||
let d = tempfile::tempdir().unwrap();
|
||||
let relower = |arm: &str, floor: &[&str]| {
|
||||
let mut args = vec![
|
||||
"loop",
|
||||
"relower",
|
||||
"no-such-run",
|
||||
"--round",
|
||||
"1",
|
||||
"--arm",
|
||||
arm,
|
||||
"--lowerer",
|
||||
"m",
|
||||
];
|
||||
for f in floor {
|
||||
args.extend(["--floor", f]);
|
||||
}
|
||||
weksa(d.path(), &args)
|
||||
};
|
||||
for (arm, floor) in [
|
||||
("BAD", vec!["b"]),
|
||||
("a", vec!["Bad"]),
|
||||
("a", vec!["a", "b"]),
|
||||
("a", vec!["b", "b"]),
|
||||
] {
|
||||
let o = relower(arm, &floor);
|
||||
assert!(!o.status.success());
|
||||
assert!(
|
||||
out(&o).contains("arm and floor labels must match"),
|
||||
"{arm} {floor:?}: {}",
|
||||
out(&o)
|
||||
);
|
||||
}
|
||||
// Well-formed, distinct labels get past the label check (to the missing run).
|
||||
let o = relower("a", &["b", "c"]);
|
||||
assert!(!o.status.success());
|
||||
assert!(out(&o).contains("the root holds no run"), "{}", out(&o));
|
||||
}
|
||||
|
|
@ -1,136 +0,0 @@
|
|||
//! 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<Entity>);
|
||||
|
||||
impl EntityForms for Held {
|
||||
fn entity(&self, id: &EntityId) -> anyhow::Result<Option<Entity>> {
|
||||
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::<Vec<_>>(),
|
||||
)
|
||||
};
|
||||
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"));
|
||||
}
|
||||
|
|
@ -1,6 +1,6 @@
|
|||
//! The original corpus (`data/original`), in en-US and ja-JP: per language, 49
|
||||
//! The original corpus (`data/original`), in en-US and ja-JP: per language, 28
|
||||
//! passages written for the non-memorised golf-loop target (Train and
|
||||
//! Validation, all model-written: 28, then 21 more Validation items grown blind) and 8 public-domain Test sentences, each with
|
||||
//! Validation, all model-written) and 8 public-domain Test sentences, each with
|
||||
//! its full provenance. Test is only read at a checkpoint: no round or recall
|
||||
//! prompt over this store holds it. The ja-JP passages are written in Japanese,
|
||||
//! not translated; the ja-JP Test sentences are Aozora Bunko excerpts.
|
||||
|
|
@ -32,7 +32,7 @@ fn stores() -> (CorpusStore, EntityStore) {
|
|||
fn every_original_item_records_its_author_and_the_public_domain_ones_their_provenance() {
|
||||
let (corpus, entities) = stores();
|
||||
let items = corpus.all().unwrap();
|
||||
assert_eq!(items.len(), 114);
|
||||
assert_eq!(items.len(), 72);
|
||||
let (mut model, mut public) = ([0; 2], [0; 2]);
|
||||
for item in &items {
|
||||
let lang = PANEL.iter().position(|l| *l == item.language).unwrap();
|
||||
|
|
@ -43,8 +43,7 @@ fn every_original_item_records_its_author_and_the_public_domain_ones_their_prove
|
|||
model[lang] += 1;
|
||||
assert!(
|
||||
item.id
|
||||
.starts_with(["item:original:", "item:original-ja:"][lang])
|
||||
|| item.id.starts_with(["item:vgrow:", "item:vgrow-ja:"][lang]),
|
||||
.starts_with(["item:original:", "item:original-ja:"][lang]),
|
||||
"{}",
|
||||
item.id
|
||||
);
|
||||
|
|
@ -117,7 +116,7 @@ fn every_original_item_records_its_author_and_the_public_domain_ones_their_prove
|
|||
item.id
|
||||
);
|
||||
}
|
||||
assert_eq!((model, public), ([49, 49], [8, 8]));
|
||||
assert_eq!((model, public), ([28, 28], [8, 8]));
|
||||
}
|
||||
|
||||
#[test]
|
||||
|
|
@ -141,7 +140,7 @@ fn the_original_items_spread_over_train_and_validation_and_test_is_public_domain
|
|||
};
|
||||
assert_eq!(
|
||||
(of(Split::Train), of(Split::Validation), of(Split::Test)),
|
||||
(14, 35, 8),
|
||||
(14, 14, 8),
|
||||
"{lang}"
|
||||
);
|
||||
}
|
||||
|
|
@ -166,85 +165,6 @@ fn the_original_items_spread_over_train_and_validation_and_test_is_public_domain
|
|||
}
|
||||
}
|
||||
|
||||
/// The 42 Validation items grown after the 56: written blind, one new group
|
||||
/// each, every group bucketed Validation by its name alone, none sharing text
|
||||
/// with a Test item in either direction.
|
||||
#[test]
|
||||
fn grown_items_hold_no_test_text_and_every_group_buckets_validation() {
|
||||
let (corpus, _) = stores();
|
||||
let all = corpus.all().unwrap();
|
||||
let mut grown: Vec<_> = all
|
||||
.iter()
|
||||
.filter(|i| i.id.starts_with("item:vgrow"))
|
||||
.collect();
|
||||
grown.sort_by(|a, b| a.id.cmp(&b.id));
|
||||
assert_eq!(grown.len(), 42);
|
||||
let test: Vec<_> = all
|
||||
.iter()
|
||||
.filter(|i| SplitScheme::V1.live(i) == Some(Split::Test))
|
||||
.collect();
|
||||
assert_eq!(test.len(), 16);
|
||||
let mut groups = std::collections::BTreeSet::new();
|
||||
for item in &grown {
|
||||
match &item.source {
|
||||
Source::ModelWritten {
|
||||
family, generator, ..
|
||||
} => {
|
||||
assert_eq!(*family, ModelFamily::Anthropic, "{}", item.id);
|
||||
assert!(
|
||||
generator
|
||||
.as_deref()
|
||||
.is_some_and(|g| g.contains("claude-sonnet-5-5")),
|
||||
"{}",
|
||||
item.id
|
||||
);
|
||||
}
|
||||
other => panic!("{}: {other:?}", item.id),
|
||||
}
|
||||
assert_eq!(item.speaker.as_str(), "entity:keeper", "{}", item.id);
|
||||
assert_eq!(
|
||||
SplitScheme::V1.live(item),
|
||||
Some(Split::Validation),
|
||||
"{}",
|
||||
item.id
|
||||
);
|
||||
assert!(groups.insert(item.group.clone()), "{}", item.group);
|
||||
assert!(
|
||||
all.iter()
|
||||
.filter(|o| o.id != item.id)
|
||||
.all(|o| o.group != item.group),
|
||||
"{} shares its group",
|
||||
item.group
|
||||
);
|
||||
for t in &test {
|
||||
assert!(
|
||||
!leaks(std::slice::from_ref(&item.text), t),
|
||||
"{} holds Test text",
|
||||
item.id
|
||||
);
|
||||
// The reverse: the Test item contains the new text.
|
||||
assert!(
|
||||
!t.text.contains(&item.text),
|
||||
"{} is inside Test text",
|
||||
item.id
|
||||
);
|
||||
}
|
||||
}
|
||||
let lines: Vec<String> = grown
|
||||
.iter()
|
||||
.map(|i| format!("{}\n{}\n{}\n{:?}", i.id, i.text, i.group, i.source))
|
||||
.collect();
|
||||
let parts: Vec<&[u8]> = lines.iter().map(|l| l.as_bytes()).collect();
|
||||
assert_eq!(
|
||||
weksa::split::fnv1a64_of(&parts),
|
||||
DIGEST_OF_THE_42,
|
||||
"a grown item changed"
|
||||
);
|
||||
}
|
||||
|
||||
/// Taken over the 42 grown items at admission, 2026-11-13.
|
||||
const DIGEST_OF_THE_42: u64 = 15237292705431734093;
|
||||
|
||||
/// The 28 model-written items are byte-for-byte what they were before Test
|
||||
/// was added: id, text, group and source, folded in key order.
|
||||
#[test]
|
||||
|
|
@ -540,10 +460,10 @@ fn the_recall_probe_covers_every_live_original_item_and_names_no_work() {
|
|||
};
|
||||
assert_eq!(reading.languages.len(), 2);
|
||||
for r in &reading.languages {
|
||||
assert_eq!((r.n, r.answered), (49, 49), "{}", r.language);
|
||||
assert_eq!((r.n, r.answered), (28, 28), "{}", r.language);
|
||||
assert!(r.chrf < 25.0, "{} {}", r.language, r.chrf);
|
||||
}
|
||||
assert_eq!(model.0.len(), 98);
|
||||
assert_eq!(model.0.len(), 56);
|
||||
// No item outside Train and Validation is shown to the model.
|
||||
let all = CorpusStore::open(&c).unwrap().all().unwrap();
|
||||
for item in &all {
|
||||
|
|
@ -624,14 +544,14 @@ fn original_round(family: ModelFamily) -> (weksa::run::RunStores, weksa::run::Ro
|
|||
fn own_family_counts_and_labels() {
|
||||
// The original corpus is Anthropic-written items, all offered.
|
||||
let (run, r) = original_round(ModelFamily::Anthropic);
|
||||
assert_eq!(r.own_family(), 98);
|
||||
assert_eq!(r.own_family(), 56);
|
||||
assert_eq!(
|
||||
r.parse_reasons().iter().map(|c| c.count).sum::<u32>(),
|
||||
98,
|
||||
56,
|
||||
"every item was refused at Parse and says why"
|
||||
);
|
||||
let line = run.round_line(&r);
|
||||
assert!(line.contains(" own-family 98"), "{line}");
|
||||
assert!(line.contains(" own-family 56"), "{line}");
|
||||
|
||||
// A different answerer family, or none recorded, labels nothing.
|
||||
for family in [ModelFamily::OpenAi, ModelFamily::Unrecorded] {
|
||||
|
|
@ -744,20 +664,6 @@ impl weksa::model::ModelPort for Record {
|
|||
}
|
||||
}
|
||||
|
||||
/// A Test item's text, or any run of five of its words (twelve characters of a
|
||||
/// text written without spaces), in a prompt.
|
||||
fn leaks(prompts: &[String], item: &weksa::corpus::CorpusItem) -> bool {
|
||||
let w: Vec<&str> = item.text.split_whitespace().collect();
|
||||
let c: Vec<char> = item.text.chars().collect();
|
||||
prompts.iter().any(|t| {
|
||||
t.contains(&item.text)
|
||||
|| w.windows(5).any(|k| t.contains(&k.join(" ")))
|
||||
|| (w.len() == 1
|
||||
&& c.windows(12)
|
||||
.any(|k| t.contains(&k.iter().collect::<String>())))
|
||||
})
|
||||
}
|
||||
|
||||
/// The public-domain Test items are held out: no prompt of round 1 over
|
||||
/// `data/original`, no recall prompt, and no round record names one.
|
||||
#[test]
|
||||
|
|
@ -811,9 +717,9 @@ fn no_test_item_is_offered_to_a_round_or_recall_or_recorded() {
|
|||
let RoundOutcome::Recorded(r) = round(&mut run, &mut model, &scorer).unwrap() else {
|
||||
panic!("answered");
|
||||
};
|
||||
// The check bites: the round did show live items, 98 of them, and the
|
||||
// The check bites: the round did show live items, 56 of them, and the
|
||||
// probe sees a shown Train item of each language.
|
||||
assert!(model.0.len() >= 98, "{}", model.0.len());
|
||||
assert!(model.0.len() >= 56, "{}", model.0.len());
|
||||
for lang in PANEL {
|
||||
assert!(
|
||||
items
|
||||
|
|
@ -834,7 +740,7 @@ fn no_test_item_is_offered_to_a_round_or_recall_or_recorded() {
|
|||
panic!("answered");
|
||||
};
|
||||
for rr in &reading.languages {
|
||||
assert_eq!((rr.n, rr.answered), (49, 49), "{}", rr.language);
|
||||
assert_eq!((rr.n, rr.answered), (28, 28), "{}", rr.language);
|
||||
}
|
||||
for item in &held {
|
||||
assert!(!leaks(&recall.0, item), "recall prompt held {}", item.id);
|
||||
|
|
@ -877,7 +783,7 @@ fn ja_test_text_carries_no_aozora_markup() {
|
|||
.into_iter()
|
||||
.filter(|i| i.language == "ja-JP")
|
||||
.collect();
|
||||
assert_eq!(ja.len(), 57);
|
||||
assert_eq!(ja.len(), 36);
|
||||
for item in &ja {
|
||||
for bad in ["《", "》", "｜", "［＃", "※"] {
|
||||
assert!(!item.text.contains(bad), "{} holds {bad}", item.id);
|
||||
|
|
@ -904,7 +810,7 @@ fn every_cited_speaker_has_a_form_in_its_items_language() {
|
|||
}
|
||||
|
||||
/// The panel [en-US, ja-JP] over `data/original`: both languages are read, each
|
||||
/// with 35 Validation items, and no Test item is in any call.
|
||||
/// with 14 Validation items, and no Test item is in any call.
|
||||
#[test]
|
||||
fn a_panel_round_reads_both_languages() {
|
||||
let (run, r) = original_round(ModelFamily::Unrecorded);
|
||||
|
|
@ -915,7 +821,7 @@ fn a_panel_round_reads_both_languages() {
|
|||
let refused = &l.validation_refused;
|
||||
assert_eq!(
|
||||
refused.parse + refused.admit + refused.lower,
|
||||
35,
|
||||
14,
|
||||
"{}",
|
||||
l.language
|
||||
);
|
||||
|
|
@ -1035,125 +941,26 @@ fn committed_scenes_cover_original_groups() {
|
|||
.filter(|i| matches!(SplitScheme::V1.live(i), Some(Split::Train | Split::Validation)))
|
||||
.map(|i| i.group)
|
||||
.collect();
|
||||
assert_eq!(live.len(), 98);
|
||||
assert_eq!(live.len(), 56);
|
||||
let held: BTreeSet<String> = scenes.iter().map(|s| s.group.clone()).collect();
|
||||
assert_eq!(held, live, "a scene for each live Train or Validation group, none other");
|
||||
// Revisions append: a group's later revisions re-derived its relation.
|
||||
assert!(scenes.iter().all(|s| s.n <= 3));
|
||||
const S7: &str = "claude-sonnet-5-5 (Weksa Hands, model-annotated original scenes)";
|
||||
const GROWTH: &str = "claude-sonnet-5-5 (Weksa Hands, model-annotated validation-growth scenes; annotator is not the writer)";
|
||||
let grown: BTreeSet<String> = CorpusStore::open(&data.join("corpus.cc"))
|
||||
.unwrap()
|
||||
.all()
|
||||
.unwrap()
|
||||
.into_iter()
|
||||
.filter(|i| i.id.starts_with("item:vgrow"))
|
||||
.map(|i| i.group)
|
||||
.collect();
|
||||
assert_eq!(grown.len(), 42);
|
||||
const RUBRIC: &str =
|
||||
"claude-sonnet-5-5 (Weksa Hands, scene rubric r1, docs/scene-annotation.md)";
|
||||
assert!(
|
||||
Path::new(env!("CARGO_MANIFEST_DIR"))
|
||||
.join("../../docs/scene-annotation.md")
|
||||
.is_file(),
|
||||
"the rubric r1 names a doc, and the doc is in the repo"
|
||||
);
|
||||
let mut by_growth = BTreeSet::new();
|
||||
assert!(scenes.iter().all(|s| s.n <= 2));
|
||||
for s in &scenes {
|
||||
match &s.annotator {
|
||||
Annotator::Model { family, generator } => {
|
||||
assert_eq!(*family, ModelFamily::Anthropic, "{}", s.group);
|
||||
assert!(
|
||||
generator == S7 || generator == GROWTH || generator == RUBRIC,
|
||||
assert_eq!(
|
||||
generator, "claude-sonnet-5-5 (Weksa Hands, model-annotated original scenes)",
|
||||
"{}",
|
||||
s.group
|
||||
);
|
||||
if generator == GROWTH {
|
||||
by_growth.insert(s.group.clone());
|
||||
// Written once, never revised by its own generator.
|
||||
assert_eq!(s.n, 1, "{}", s.group);
|
||||
}
|
||||
if generator == GROWTH || generator == RUBRIC {
|
||||
// One relation, keeper to unnamed, the three Scene features.
|
||||
assert_eq!(s.relations.len(), 1, "{}", s.group);
|
||||
let rel = &s.relations[0];
|
||||
assert_eq!(rel.from.as_str(), "entity:keeper", "{}", s.group);
|
||||
assert_eq!(rel.to, weksa::speaker::Party::Unnamed, "{}", s.group);
|
||||
assert_eq!(rel.features.len(), 3, "{}", s.group);
|
||||
}
|
||||
}
|
||||
other => panic!("{} is {other:?}", s.group),
|
||||
}
|
||||
}
|
||||
assert_eq!(
|
||||
by_growth, grown,
|
||||
"the growth scenes are exactly the vgrow groups"
|
||||
);
|
||||
// The label a run reads is each group's latest revision: all 98 are rubric r1's.
|
||||
let mut latest = std::collections::BTreeMap::new();
|
||||
for s in &scenes {
|
||||
if latest.get(&s.group).is_none_or(|l: &&weksa::speaker::Scene| l.n < s.n) {
|
||||
latest.insert(s.group.clone(), s);
|
||||
}
|
||||
}
|
||||
let mut lines = Vec::new();
|
||||
for (group, s) in &latest {
|
||||
let Annotator::Model { generator, .. } = &s.annotator else {
|
||||
panic!("{group} is not model-annotated");
|
||||
};
|
||||
assert_eq!(generator, RUBRIC, "{group}: the latest revision follows rubric r1");
|
||||
lines.push(format!("{group}\n{}\n{:?}", s.n, s.relations[0].features));
|
||||
}
|
||||
let parts: Vec<&[u8]> = lines.iter().map(|l| l.as_bytes()).collect();
|
||||
assert_eq!(
|
||||
weksa::split::fnv1a64_of(&parts),
|
||||
DIGEST_OF_THE_SCENES,
|
||||
"a latest scene changed without a rubric revision"
|
||||
);
|
||||
// The revisions before rubric r1 are provenance and never change: 113 of them.
|
||||
let mut earlier: Vec<&weksa::speaker::Scene> = scenes
|
||||
.iter()
|
||||
.filter(|s| !matches!(&s.annotator, Annotator::Model { generator, .. } if generator == RUBRIC))
|
||||
.collect();
|
||||
earlier.sort_by(|a, b| (&a.group, a.n).cmp(&(&b.group, b.n)));
|
||||
assert_eq!(earlier.len(), 113);
|
||||
let lines: Vec<String> = earlier
|
||||
.iter()
|
||||
.map(|s| format!("{}\n{}\n{:?}\n{:?}", s.group, s.n, s.annotator, s.relations))
|
||||
.collect();
|
||||
let parts: Vec<&[u8]> = lines.iter().map(|l| l.as_bytes()).collect();
|
||||
assert_eq!(
|
||||
weksa::split::fnv1a64_of(&parts),
|
||||
DIGEST_OF_THE_EARLIER_SCENES,
|
||||
"an earlier scene revision changed"
|
||||
);
|
||||
// Rubric r1 is text the labels cite: the section, as committed, is pinned.
|
||||
let doc = std::fs::read_to_string(
|
||||
Path::new(env!("CARGO_MANIFEST_DIR")).join("../../docs/scene-annotation.md"),
|
||||
)
|
||||
.unwrap();
|
||||
let from = doc.find("## Rubric r1").expect("the doc holds Rubric r1");
|
||||
let rest = &doc[from + "## Rubric r1".len()..];
|
||||
let section = &doc[from..from + "## Rubric r1".len() + rest.find("\n## ").expect("a section follows r1")];
|
||||
assert_eq!(
|
||||
weksa::split::fnv1a64_of(&[section.trim().as_bytes()]),
|
||||
DIGEST_OF_THE_RUBRIC,
|
||||
"rubric r1 was edited; a new rubric is a new section and a new generator"
|
||||
);
|
||||
}
|
||||
|
||||
/// Taken over the 113 scene revisions that precede rubric r1, 2026-11-13.
|
||||
const DIGEST_OF_THE_EARLIER_SCENES: u64 = 2598828882325200913;
|
||||
|
||||
/// Taken over the text of the `## Rubric r1` section of docs/scene-annotation.md
|
||||
/// (trimmed), 2026-11-13.
|
||||
const DIGEST_OF_THE_RUBRIC: u64 = 11823581212652524671;
|
||||
|
||||
/// Taken over each live group's latest revision (group, n, features) at rubric r1,
|
||||
/// 2026-11-13.
|
||||
const DIGEST_OF_THE_SCENES: u64 = 2505219080875817063;
|
||||
|
||||
/// The sweep both seed-pair tests share: over a grid of grades per feature (each
|
||||
/// also ABSENT) and the production `Condition::holds`, no listed pair of one
|
||||
/// language's entries co-holds; and each witness entry fires where it should and
|
||||
|
|
|
|||
|
|
@ -11,7 +11,7 @@ use weksa::packet::{FeatValue, FeatureValue, Packet, proof_packet};
|
|||
use weksa::speaker::{Annotator, PairRelation, Party, Scene};
|
||||
use weksa::{
|
||||
CorpusStore, EntityStore, Inventory, InventoryStore, LoweringInput, NameSpan, PacketStore,
|
||||
Refusal, SceneRead, SpeakerStateStore, StoreError,
|
||||
Refusal, SceneRead, SpeakerStateStore, StoreError, lower,
|
||||
};
|
||||
|
||||
struct W {
|
||||
|
|
@ -158,7 +158,7 @@ fn selected(rev: u32, features: Vec<FeatureValue>) -> SceneRead {
|
|||
}
|
||||
|
||||
#[test]
|
||||
fn a_scene_relation_reaches_the_lowering_view() {
|
||||
fn a_scene_relation_reaches_the_lowering_view_and_changes_no_english() {
|
||||
let mut w = world();
|
||||
put(&mut w, standard("g", 1));
|
||||
let plain = view_of(&w, 3, Some("n3"));
|
||||
|
|
@ -170,6 +170,10 @@ fn a_scene_relation_reaches_the_lowering_view() {
|
|||
.unwrap();
|
||||
assert_eq!(with.scene(), status().as_slice());
|
||||
assert_eq!(with.scene_read(), &selected(1, status()));
|
||||
assert_eq!(
|
||||
lower(&with, &inv(&w), &w.entities).unwrap(),
|
||||
lower(&plain, &inv(&w), &w.entities).unwrap()
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
|
|
|
|||
|
|
@ -9,7 +9,6 @@ fn item(group: &str, source: Source) -> CorpusItem {
|
|||
language: "en-US".into(),
|
||||
speaker: weksa::EntityId::parse("entity:s").unwrap(),
|
||||
names: vec![],
|
||||
names_by: None,
|
||||
group: group.into(),
|
||||
prior_turns: vec![],
|
||||
source,
|
||||
|
|
|
|||
|
|
@ -740,53 +740,6 @@ fn a_source_that_only_read_wording_cannot_set_consent() {
|
|||
}
|
||||
}
|
||||
|
||||
// V18: a request frame is licensed by the packet's own consent record.
|
||||
|
||||
/// The committed inventory, where `frame:3` is `request_intervention`.
|
||||
fn cast_refusals(p: &Packet) -> Vec<Refusal> {
|
||||
let path = std::path::Path::new(env!("CARGO_MANIFEST_DIR")).join("../../data/interlingua/inventory.cc");
|
||||
let inv = weksa::InventoryStore::open(&path).unwrap().inventory().unwrap();
|
||||
validate(p, &inv).err().unwrap_or_default()
|
||||
}
|
||||
|
||||
fn requesting() -> Packet {
|
||||
let mut p = proof_packet();
|
||||
p.predications[0].frame = iv("frame:3");
|
||||
p.discourse.addressee_consent = Some(nd("n4"));
|
||||
p
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_request_frame_needs_consent_naming_its_predication() {
|
||||
assert_eq!(cast_refusals(&requesting()), vec![]);
|
||||
let mut p = requesting();
|
||||
p.discourse.addressee_consent = None;
|
||||
assert_eq!(
|
||||
cast_refusals(&p),
|
||||
vec![Refusal::V18RequestWithoutConsent { predication: nd("n4") }]
|
||||
);
|
||||
p.discourse.addressee_consent = Some(nd("n5"));
|
||||
assert_eq!(
|
||||
cast_refusals(&p),
|
||||
vec![Refusal::V18RequestWithoutConsent { predication: nd("n4") }]
|
||||
);
|
||||
let mut p = requesting();
|
||||
p.provenance.source = ProvenanceSource::GameTelemetry;
|
||||
assert_eq!(cast_refusals(&p), vec![]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn model_source_consent_is_v15_alone() {
|
||||
let mut p = requesting();
|
||||
p.provenance.source = ProvenanceSource::ModelDecomposition;
|
||||
assert_eq!(
|
||||
cast_refusals(&p),
|
||||
vec![Refusal::V15ConsentSource {
|
||||
source: ProvenanceSource::ModelDecomposition
|
||||
}]
|
||||
);
|
||||
}
|
||||
|
||||
// V17: the addressee is someone spoken to, a referent.
|
||||
|
||||
#[test]
|
||||
|
|
|
|||
Binary file not shown.
Binary file not shown.
|
|
@ -1,120 +0,0 @@
|
|||
# Calibrating the accept rule
|
||||
|
||||
`weksa loop calibrate` measures how the live accept rule behaves on a run's own
|
||||
Validation corpus: how often it accepts, rejects as no gain, or regresses a
|
||||
candidate that should be none of those. It does not reimplement the rule. It
|
||||
reads the answered draws through `RunStores::read_draws` (the scoring
|
||||
`weksa loop relower` uses), decides every trial with `decide_panel` over
|
||||
`paired_floor` (`crates/weksa/src/run.rs`), and prints, per class, the items
|
||||
read and skipped per language, the trial totals with their Accepted, NoGain and
|
||||
Regressed counts, and the mean panel noise. That is all it produces: the
|
||||
Accepted/NoGain/Regressed counts and the noise mean in the map's "Recalibration
|
||||
on the grown corpus" block are reproduced by it, and the prompted trials are
|
||||
also printed split by the recorded lowering `R`'s role (`prompted-r-candidate`,
|
||||
`prompted-r-base`, `prompted-r-free`, see below), the candidate counts per arm
|
||||
and the mild arms' composite offsets from the prompted mean (see below); the
|
||||
other figures there (the
|
||||
35% with R removed, the noise range, the 0.0185 gain and its 0.41 ratio, the
|
||||
bootstrap intervals, the per-item SDs, R's +0.024, the mild-arm duplicate
|
||||
counts, the Train-vocabulary overlap, the old/new
|
||||
class composites and the ten parse-refused item ids) were computed by scratch scripts that are not in the repo. It is a
|
||||
diagnostic: it records nothing, writes no prompts, and never touches Test or
|
||||
Train.
|
||||
|
||||
## What it counts
|
||||
|
||||
The draws are lowerings of one round's Validation packets: the round's own
|
||||
(recorded) lowering `R`, plus draws you label. `P` is `R` and the `--prompted`
|
||||
draws; the floor size is `FLOOR_ARMS_MIN` (3), the live rule's.
|
||||
|
||||
- Prompted trials: every ordered pair (base, candidate) in `P`, against every
|
||||
3-subset of the rest of `P` as the floor. A repeat of the same lowering
|
||||
should read NoGain; Accepted is a false accept, Regressed a false reject.
|
||||
(`R` comes from the round, not from `relower`, so it may not be
|
||||
exchangeable with a repeat.) The prompted line is therefore printed three
|
||||
more times, by `R`'s role in the trial: `prompted-r-candidate` (`R` is the
|
||||
candidate), `prompted-r-base` (`R` is the base) and `prompted-r-free` (`R` is
|
||||
neither; it may sit in the floor). The three sum to the prompted line. Read the Accepted
|
||||
and Regressed columns of each line: a false accept sits mostly under the
|
||||
first and a false reject under the second, but `R`-as-candidate trials can
|
||||
Regress too (class `old` on `growth-scene`: 5 of its 15). The third
|
||||
is the exchangeable rate: on `growth-scene` it was 0 Accepted and 0 Regressed
|
||||
of 80 while all 11 false accepts and 9 false rejects involved `R`. Which of
|
||||
the two rates the live rule should be held to is undecided: the live loop
|
||||
meets `R` as the head's establishing lowering.
|
||||
- Degraded trials, per `--degraded` arm: every base in `P` against every
|
||||
3-subset of the rest of `P`, the degraded draw as the candidate. These should
|
||||
read Regressed.
|
||||
- Candidate trials, pooled over the `--candidate` arms: the same, tallied
|
||||
Accepted, NoGain, Regressed. This is the rule's power against that arm. The
|
||||
pooled line is followed by one `candidate=LABEL` line per arm: arms of one
|
||||
kind can differ completely (Train-guide h1 and h2 Regressed in every trial
|
||||
while h3 and h4 gained), and then the pooled figure is not a power.
|
||||
- Mild offset: each `degraded=LABEL` line ends with `offset LANGUAGE=+x.xxxx`, the
|
||||
arm's composite minus the mean composite of the prompted draws (`R` included),
|
||||
per language over the items read. A degraded arm that is barely below the
|
||||
prompted mean is a weak probe of the rule's sensitivity.
|
||||
- Noise: the mean `panel_noise` over every (base, floor) choice.
|
||||
|
||||
With six prompted draws including `R` that is 120 prompted trials, 60 per
|
||||
degraded arm and 240 candidate trials. Trials share draws and are not
|
||||
independent. Each count is printed for `all` Validation items and for each
|
||||
`--class NAME=PREFIX[,PREFIX...]` (items whose key starts with any prefix), from
|
||||
the same per-item scores. A class with fewer than two read items in a language
|
||||
has no floor and reads Regressed in every trial; that is printed.
|
||||
|
||||
## Steps
|
||||
|
||||
1. `weksa loop open ROOT ...` and `weksa loop round ROOT` record round N and
|
||||
leave its answers in `ROOT/round-N/`.
|
||||
2. For each draw label: `weksa loop relower ROOT --round N --arm LABEL
|
||||
--lowerer NAME` writes the byte-identical lowering prompts to
|
||||
`ROOT/relower-N-LABEL/<digest>.prompt` and exits 3. Answer each prompt into
|
||||
`ROOT/relower-N-LABEL/<digest>.answer`.
|
||||
3. `weksa loop calibrate ROOT --round N --prompted p1 --prompted p2 ...
|
||||
[--degraded LABEL]... [--candidate LABEL]... [--class NAME=PREFIX]...`.
|
||||
At least four `--prompted` labels are needed (a pair and three floors with
|
||||
`R` make five draws). It exits 1 and lists `unanswered LABEL COUNT` for any
|
||||
draw with prompts still unanswered. Labels match `[a-z0-9-]{1,32}` and differ
|
||||
across the three kinds. It needs the Ollama embedder of the run; a full
|
||||
60-item, 13-draw calibration is on the order of 1500 embedded texts, so
|
||||
launch it detached with a log.
|
||||
|
||||
The scratch packet store is `ROOT/calibrate-N/base.cc`; delete it at will.
|
||||
|
||||
## Answer file format
|
||||
|
||||
`<digest>.answer` is one JSON object and nothing else, no code fence:
|
||||
`{"text": "..."}`, a JSON-escaped string. The answerer reads only the prompt
|
||||
(its first line says what to write) and writes the answer. Every prompt of the
|
||||
draw must be answered.
|
||||
|
||||
## Briefs per arm
|
||||
|
||||
Independence rule: a fresh agent per batch of answers; no batch sees another
|
||||
draw's answers. Only `mild` reads `round-N/*.answer`.
|
||||
|
||||
- Plain prompted: answer each prompt as its own first line asks; read nothing
|
||||
else in the run root.
|
||||
- Mild: for each prompt, read the recorded lowering in
|
||||
`ROOT/round-N/<digest>.answer` and write the same-format answer whose text is
|
||||
that utterance with exactly one meaning detail blurred: change or drop one of
|
||||
tense, polarity, modality or hedge, a referent, a quantity or a predicate's
|
||||
concept (replace it with a near but different word). Keep language, register,
|
||||
length and fluency; the result must read as a natural utterance and must not
|
||||
mention the change. Pick the detail that is not the most salient one. A
|
||||
second mild draw blurs a different detail than the first and is written
|
||||
without reading the first's answers. The wording of the distil-base original
|
||||
is lost, and the dispatch used for growth-base is not on disk, so this is the
|
||||
wording from now on. Warning: on growth-base two mild arms briefed this way
|
||||
came out identical in 27 of 60 items, so independently briefed mild arms
|
||||
are not independent degradations; read a mild draw's regress count with that
|
||||
in mind.
|
||||
- Train-guide: before answering, read the Train sentences of the corpus in the
|
||||
batch's language as a register guide and let it steer word choice; the guide
|
||||
gives phrasing only and each answer must still say exactly what its own packet
|
||||
says. The guide section is the live Train items of that language, built from
|
||||
`weksa corpus dump` filtered to Train, and is given to the answerer in the
|
||||
brief, never pasted into this document, and never includes Validation or Test
|
||||
text. Read nothing else in the run root.
|
||||
- Control: a script writes `{"text":"Yes."}` as the answer to every prompt.
|
||||
|
|
@ -85,8 +85,8 @@ thing.
|
|||
An entity's citation form in a language may carry a ruled pronunciation
|
||||
(`LanguageForms.pronunciation`): bare IPA with stress marks, who ruled it, the
|
||||
date, the source, and an optional list of rejected variants kept so nobody
|
||||
re-proposes them. `weksa pronounce <store> <key>` prints the stored IPA of each
|
||||
entity the packet cites, one per line (`--phones` prints the phones line), and refuses with `NoPronunciation` for an
|
||||
re-proposes them. `weksa lower <store> <key> --ipa` prints the stored IPA of each
|
||||
entity the packet cites, one per line, and refuses with `NoPronunciation` for an
|
||||
entity with none; rejected variants are never read. This is not the plan below:
|
||||
it carries no timing, contour, length or invented prosody, and Weksa has no
|
||||
English G2P, so an unruled name has no IPA.
|
||||
|
|
|
|||
|
|
@ -164,7 +164,6 @@ names the rule.
|
|||
`GameTelemetry`; a decomposition of text or imported corpus text cannot mint
|
||||
it.
|
||||
- V17: an `addressee` names a referent, not a predication.
|
||||
- V18: a predication whose frame is the inventory's `request_intervention` is named by `addressee_consent`.
|
||||
|
||||
V9 is retired and not renumbered: the form of a key or a grade is its type, and
|
||||
an extension key's family is V6. `PacketStore::admit` returns the lowering view of a
|
||||
|
|
@ -197,24 +196,10 @@ and `features` carry source-side nuance on content (hedge, certainty, irony and
|
|||
whatever the inventory grows). This is source-side communicative pressure, not
|
||||
target-language register. `addressee_consent` is no feature: it names the
|
||||
predication the addressee asked for or agreed to, a fact about what the
|
||||
addressee did. `V14` and `V15` check the field: it may be set only by authoring or game
|
||||
telemetry, and it must name a predication of the packet. `V18` refuses a predication whose frame resolves, at the packet's revision, to
|
||||
the gloss `request_intervention` (`frame:3` in the committed inventories)
|
||||
unless `addressee_consent` names that predication. The encoder can never set
|
||||
consent (`V15`), so an encoder-produced `request_intervention` predication (`frame:3`) is always refused.
|
||||
Limits, tracked by `weksa-lowering:follow_up:request-frame-consent-residual`:
|
||||
`V18` keys on the gloss `request_intervention` and sees no other frame or
|
||||
concept, so a request-shaped meaning built from another frame or concept (a
|
||||
`frame:12` communication with `concept:6` request validates) or from a renamed
|
||||
or newly minted frame is not seen by `validate`, which does not read meaning.
|
||||
The inventory carries no marker for request shape, so classifying it would be
|
||||
an inventory-shape decision for Imagination and language-ontology. `addressee_consent`
|
||||
is one field, so a packet carries one request predication, and a compound
|
||||
request is two packets until a packet schema revision makes consent a set. The
|
||||
asker is not checked to be the addressee: a consented `frame:3` whose agent is
|
||||
not the addressee validates, and no code outside `validate` and the encoder
|
||||
prompt text reads `addressee_consent`. That check is an owed obligation with no
|
||||
owner yet.
|
||||
addressee did. The English lowerer's request row (`frame:3`, "{agent} asked
|
||||
{patient} to stop") reads it: the consent must name that predication and its
|
||||
agent must be the addressee, else `ConsentMissing` or `AskerNotAddressee`. A
|
||||
consent naming any other predication is refused as unrendered.
|
||||
|
||||
### `stance`
|
||||
|
||||
|
|
|
|||
|
|
@ -1,52 +0,0 @@
|
|||
# Name-span annotation
|
||||
|
||||
How the name spans of an imported public-domain work are placed. A span has a
|
||||
committed rule that produced it; this file is that rule.
|
||||
|
||||
## Why
|
||||
|
||||
- `pd-annotation-model-then-attest`: a labelled model places the spans of a
|
||||
public-domain work; the operator may attest them afterwards.
|
||||
- `leak-owned-by-flow-and-scorer-3`: spans are fixed with the text at intake and
|
||||
written by no loop writer. The offsets are derived from markup the annotator
|
||||
writes, never typed by a model (inline marking, as in GPT-NER, Wang et al.
|
||||
2023); `CorpusStore::add` judges range, grapheme boundary, form equality and
|
||||
overlap.
|
||||
|
||||
The work file (`weksa corpus import <work>`) is a transcription of a work in
|
||||
hand: provenance, cast forms, lines, scene groups and the speaker each speech
|
||||
prefix names. It holds no distributor header, licence or trademark text, and the
|
||||
binary fetches nothing.
|
||||
|
||||
## Rubric r1
|
||||
|
||||
You are given a work's cast: each member's entity id and the forms the work spells that member with. For each numbered line, copy the line exactly, character for character, and wrap each place where the line names a cast member by one of that member's listed forms as [[<entity id>|<form>]]. Mark a form only where it refers to that cast member; a listed form used as an ordinary word, or naming someone else, stays unmarked. Do not mark pronouns, titles or descriptions unless the exact text is a listed form. When a form is listed for two members, mark the one the line refers to; when you cannot tell, leave it unmarked. Answer one JSON line per input line, in the order given, and nothing else: {"line": N, "marked": "..."}.
|
||||
|
||||
## Procedure
|
||||
|
||||
- One fresh model agent per work. Its brief is rubric r1, the cast as
|
||||
`<entity id>: <form>, <form>` lines and the work's lines as `<n><TAB><text>`;
|
||||
nothing else (no store, no loop, no other answer).
|
||||
- Import with `--model-family` and `--generator '<annotator model id> (name-span
|
||||
rubric r1, docs/name-span-annotation.md)'`. An operator-written or
|
||||
operator-reviewed answer imports with `--operator`.
|
||||
- Import is all or nothing: every entity and item passes the real store doors on
|
||||
scratch copies before the first write, so a refusal (a parse failure, a span
|
||||
the store judges, a work that repeats a line under case or width folding)
|
||||
leaves the stores untouched. Re-draw the whole answer once, log it, and import
|
||||
again. A work file repeating a line's text is refused naming both lines; leave
|
||||
that line out of the answer file (the rest imports with its numbering intact),
|
||||
since a repeated line cannot be two corpus items.
|
||||
- A line the answer does not cover is not imported by that run; a later run over
|
||||
other lines of the work does not collide (keys are `item:<slug>:<n>`).
|
||||
- A line whose own text holds `[[` or `]]` cannot be marked and is refused; it
|
||||
can still enter by hand through `weksa corpus add --name`.
|
||||
|
||||
## Label scope
|
||||
|
||||
`names_by` labels the spans only, not the line or its speaker. One label per
|
||||
item: a later attestation would be a superseding item with the same text and
|
||||
group, but no command writes one yet; question `pd-name-span-attestation` owns
|
||||
that door.
|
||||
`None` means unrecorded (the cast seeds, `weksa corpus add`, the Dao De Jing
|
||||
bed), not attested.
|
||||
|
|
@ -1,195 +0,0 @@
|
|||
# Prior art and plan
|
||||
|
||||
Meta asked (#weksa, 2026-11-13) for scaffolding to stand on instead of
|
||||
building from base principles. This is a survey of what exists and a plan that
|
||||
borrows it. Every source below was read in full text unless marked **snippet**
|
||||
(seen only in a search result) or **not read**. Research only: nothing here is
|
||||
built, and no new loop machinery is proposed.
|
||||
|
||||
## What exists
|
||||
|
||||
**Semantic backbones: none carries the part we care about.**
|
||||
|
||||
- AMR ([Banarescu 2013](https://aclanthology.org/W13-2322.pdf)): no politeness,
|
||||
speech-act or pragmatics text at all; it also does not distinguish real from
|
||||
hypothetical events (its Section 4).
|
||||
- UMR ([Van Gysel 2021](https://par.nsf.gov/servlets/purl/10288269)): adds
|
||||
document-level coreference, temporal and modal-dependency graphs. The paper
|
||||
has no politeness, addressee or register layer; the only speaker-like object
|
||||
is the author node. Annotation agreement was still "awaiting confirmation".
|
||||
- Universal Dependencies: the `Polite` feature has four values (`Infm`, `Form`,
|
||||
`Elev`, `Humb`; [feature page](https://universaldependencies.org/u/feat/Polite.html)),
|
||||
but the Japanese GSD treebank carries no `Polite`
|
||||
([treebank page](https://universaldependencies.org/treebanks/ja_gsd/index.html)).
|
||||
The page says Japanese *teineigo* shares the value `Form` with formal register
|
||||
although it is a different axis. UD is a parse scheme, not a meaning scheme.
|
||||
- Grammatical Framework RGL: 38 languages, Japanese present
|
||||
([synopsis](https://www.grammaticalframework.org/lib/doc/synopsis/index.html),
|
||||
[status](https://www.grammaticalframework.org/lib/doc/status.html)); the source
|
||||
declares `Style = Plain | Resp`, so two politeness levels and no honorific
|
||||
paradigm
|
||||
([ResJpn.gf](https://raw.githubusercontent.com/GrammaticalFramework/gf-rgl/master/src/japanese/ResJpn.gf)).
|
||||
LGPL/BSD, application grammars may take any licence
|
||||
([LICENSE](https://raw.githubusercontent.com/GrammaticalFramework/gf-rgl/master/LICENSE)).
|
||||
- Abstract Wikipedia / Wikifunctions: encyclopedic content, 2026 soft launch in
|
||||
three languages, no politeness
|
||||
([Meta page](https://meta.wikimedia.org/wiki/Abstract_Wikipedia)). The
|
||||
Wikifunctions NLG and Japanese documentation were **not read**.
|
||||
|
||||
**Typology.**
|
||||
|
||||
- WALS (CC BY 4.0, CLDF at <https://github.com/cldf-datasets/wals>): the only
|
||||
politeness feature is 45A, pronoun politeness
|
||||
([chapter](https://wals.info/chapter/45)); Japanese is coded value 4 ([datapoint](https://wals.info/valuesets/45A-jpn)), pronoun
|
||||
avoidance. No feature for verbal honorifics or register.
|
||||
- Grambank (CC BY 4.0, <https://github.com/grambank/grambank>): GB415 is the
|
||||
second-person politeness distinction; I found no verbal-honorific feature
|
||||
(loose name match, not exhaustive). The 195-feature / 2,467-variety size is
|
||||
**snippet**; Japanese's GB415 value was **not looked up**.
|
||||
|
||||
**Formality control in MT: the closest prior art, and it is a sentence-level
|
||||
label.**
|
||||
|
||||
- [Sennrich 2016](https://aclanthology.org/N16-1005.pdf): a side-constraint
|
||||
token controls T/V; forced-polite output was 96% polite or neutral.
|
||||
- [Feely 2019](https://aclanthology.org/D19-5203.pdf): the same for EN-JA with
|
||||
three levels (informal, polite, formal); labels by rule plus a fastText
|
||||
classifier (F1 0.83-0.86 on 150 hand-labelled sentences); formal text is only
|
||||
0.7-1.6% of training data.
|
||||
- [CoCoA-MT](https://arxiv.org/pdf/2205.04022) (CDLA-Sharing-1.0, repo
|
||||
<https://github.com/amazon-science/contrastive-controlled-mt>): 1,000 train and
|
||||
600 test segments for Japanese with contrastive formal/informal references and
|
||||
phrase-level markers. Two baseline systems' EN-JA outputs, labelled by
|
||||
professionals, came out formal 29.0% / 73.8% and "other" about 20-24%; EN-JA
|
||||
inter-annotator agreement 0.82, the lowest of the six languages.
|
||||
- [Marrese-Taylor 2023](https://aclanthology.org/2023.wmt-1.49.pdf): GPT-3 and
|
||||
ChatGPT prompted reach about 90% formality-control accuracy on EN-JA, which
|
||||
the authors say beats fine-tuned MT; classifier and data at
|
||||
<https://github.com/epochx/japanese-formality> (no licence reported).
|
||||
- [IWSLT 2023 formality track](https://aclanthology.org/2023.iwslt-1.1.pdf): no
|
||||
Japanese; metrics matched-accuracy (phrase markers) and classifier-accuracy.
|
||||
Niu 2017 is read ([D17-1299](https://aclanthology.org/D17-1299.pdf)); Niu 2019
|
||||
and Rippeth 2022 (arXiv 2205.06644, abstract only) are **not read**.
|
||||
- None of these takes a speaker-state or addressee relation. The label is one
|
||||
bit or three levels attached to a source sentence.
|
||||
|
||||
**Grammar-in-context (for conlang targets).**
|
||||
|
||||
- [MTOB](https://arxiv.org/pdf/2309.16575) (MIT code, CC BY 4.0 grammar book):
|
||||
Claude 2 with word list plus retrieved sentences plus long grammar 44.7 / 45.8
|
||||
chrF against a human learner at 51.6 / 57.0.
|
||||
- [Aycock 2025](https://arxiv.org/pdf/2409.19151): most of the gain comes
|
||||
from the book's parallel examples (Gemini-1.5-Flash eng->kgv chrF++ 30.8 with
|
||||
examples only against 34.4 whole book and 11.0 zero-shot; explanations alone
|
||||
22.6). Kalamang is a natural language, so transfer to a conlang is assumed.
|
||||
- [Gemini 1.5 report](https://arxiv.org/pdf/2403.05530): full book 5.46 against a
|
||||
human learner's 5.52 on a 0-6 human scale.
|
||||
Suggests, for a conlang target (assumed to transfer), worked paired examples first and grammar
|
||||
prose second.
|
||||
|
||||
**Prompt optimisation and evaluation.**
|
||||
|
||||
- [DSPy](https://arxiv.org/pdf/2310.03714) (MIT), [MIPRO](https://arxiv.org/pdf/2406.11695),
|
||||
[OPRO](https://arxiv.org/pdf/2309.03409) (Apache-2.0): DSPy compiles take
|
||||
"10-20 trials over 150-300 validation examples"; MIPRO's task sets run from 75
|
||||
train (Iris) to 500 per task. MIPRO found bootstrapped demos gave the biggest
|
||||
gain and tests with Wilcoxon over 5 runs. OPRO discusses overfitting to the
|
||||
training set.
|
||||
- [Koehn 2004](https://aclanthology.org/W04-3250.pdf): paired bootstrap;
|
||||
against a 30,000-sentence reference, a 2.0-point BLEU gap was detected at 95%
|
||||
significance in 31% of runs at n=100 and 65% at n=300; a 5.1-point gap in 97%
|
||||
at n=100. The paper suggests n=100 might be too small.
|
||||
- [Dror 2018](https://aclanthology.org/P18-1128.pdf): paired bootstrap is
|
||||
"less effective for small test sets"; approximate randomization has been used
|
||||
for test sets above 20 points; only 3 of 110 surveyed ACL 2017 papers
|
||||
corrected for multiple comparisons.
|
||||
- [Kocmi 2021](https://arxiv.org/pdf/2107.10821): pairwise accuracy against
|
||||
humans COMET 83.4, BLEURT 80.0, chrF 75.6, BLEU 74.6; recommends COMET
|
||||
primary, a string metric secondary and a paired test; observes "a slight drop
|
||||
in metric ranks for some pretrained metric" against ChrF for non-Latin and
|
||||
logogram targets and says more analysis would be required.
|
||||
- [chrF](https://aclanthology.org/W15-3049.pdf): validated on seven targets, Japanese
|
||||
not among them.
|
||||
|
||||
## What we borrow
|
||||
|
||||
| Need | Borrow | Instead of |
|
||||
|---|---|---|
|
||||
| Politeness vocabulary for the packet's register field | UD `Polite` values (Infm, Form, Elev, Humb) as the label set, and Feely's three-level Japanese split | inventing level names |
|
||||
| Modal/author structure | UMR's conceiver and modal-dependency idea for evidence/stance fields | a bespoke modality scheme |
|
||||
| Japanese test of register | CoCoA-MT JA set (600 contrastive test segments, phrase markers), KeiCO for relation-labelled Japanese, and the Japanese-formality classifier | hand-written register references only |
|
||||
| Conlang scaffolding | MTOB recipe: worked paired examples first, word list, grammar prose after (shown on Kalamang, a natural language; transfer to a conlang is an assumption) | long grammar prompts alone |
|
||||
| Typology priors | WALS 45A and Grambank GB415 to seed which targets have a politeness axis | per-language guesses |
|
||||
| Significance | paired approximate randomization over items; chrF with an embedding metric | reading small differences as results |
|
||||
| Optimiser | DSPy/MIPRO only once a scoring set of at least 75 items exists (MIPRO's smallest task), more for stable compiles; the 35-item sets are below that | the golf loop growing a private optimiser |
|
||||
|
||||
We do not adopt AMR, UMR, UD or GF as the packet. None represents the speaker's
|
||||
relation to the addressee, which the packet's scene state does. The packet stays
|
||||
ours; it borrows vocabulary.
|
||||
|
||||
## What is actually new
|
||||
|
||||
Prior work already conditions honorific choice on the speaker-addressee
|
||||
relation or status in narrower forms: KeiCO (Liu and Kobayashi 2022, 10,007
|
||||
examples, annotates the speaker-listener social relationship; read through
|
||||
Marrese-Taylor 2023 and the abstract), Korean context-aware NMT that infers the
|
||||
relation from surrounding sentences
|
||||
([MDPI](https://www.mdpi.com/2079-9292/10/13/1589), snippet), Brown-Levinson
|
||||
generation that takes power and distance as parameters (Walker et al., not
|
||||
read), and a 2026 translator given a known addressee
|
||||
([Cihlar et al.](https://aclanthology.org/2026.iaai-1.3), snippet only). What I
|
||||
did not find is the whole chain: persona state (status, restraint, stance) to a
|
||||
register decision for an LLM lowerer, measured against a prompted baseline.
|
||||
That is the claim, and it is relative to what I searched; closer work may
|
||||
exist.
|
||||
|
||||
Uncontrolled commercial MT left 20-24% of EN-JA outputs inconsistent in
|
||||
register (CoCoA-MT Table 4, two generic systems, no formality instruction). That
|
||||
shows register is unstable without control, not how a prompted LLM behaves.
|
||||
|
||||
## Smallest end-to-end slice
|
||||
|
||||
One path, existing machinery, ja-JP only, no new loop:
|
||||
|
||||
1. A packet with scene state (speaker, addressee, relation) goes through the
|
||||
current `weksa loop` encode and lowering to Japanese.
|
||||
2. The same packet under two relations (to a superior and to an intimate) must
|
||||
produce the two UD `Polite` levels; check with the Japanese formality
|
||||
classifier plus a native-reader pass on the 35-item Validation corpus per
|
||||
language (see the map's recalibration blocks).
|
||||
3. Score the register decision as a classification (matched accuracy), not only
|
||||
chrF. CoCoA-MT's JA references give an outside check on the classifier, a
|
||||
weak one: its reference-based segment classifier on EN-JA had precision
|
||||
0.71 and 0.69 and recall 0.43 and 0.54 in the paper's Table 5.
|
||||
|
||||
Out of scope for the slice: conlang targets, optimisers, a second language.
|
||||
|
||||
## What good enough means
|
||||
|
||||
- Register accuracy: report matched accuracy for ours and for a plain prompt
|
||||
that is given the relation in words, on the same items, with paired
|
||||
intervals. We measure that baseline ourselves; Marrese-Taylor's roughly 90%
|
||||
is classifier accuracy (0.83-0.86 by phrase-marker matching) for binary
|
||||
formal/informal control with the label named in the prompt, an upper-region
|
||||
reference and not our baseline. The claim is non-inferiority with a stated
|
||||
margin. Superiority is claimed only if enough items are discordant (about 6
|
||||
or more, all in one direction, at n=35); against a baseline near 90%, n=35
|
||||
cannot show it, and the result is then "not detected".
|
||||
- Meaning is not lost: chrF and meaning cosine are not detectably below the
|
||||
plain prompt on the same items, under the same paired test.
|
||||
- Honest sample size: 35 items per language detects only large gaps, so results
|
||||
carry intervals and "not detected" stands as an outcome. Small gaps are not
|
||||
claims. Koehn's figures are for sentence-level BLEU on 100-3000-sentence
|
||||
blocks and do not transfer to a binary register metric on 35 items; power
|
||||
for that is computed directly from the discordant-pair count.
|
||||
- A native-reader check on register for a sample, because every automatic metric
|
||||
here was validated on languages other than the persona register we care about.
|
||||
|
||||
## Open
|
||||
|
||||
- Which persona fields (status, restraint, stance) are in the packet today
|
||||
versus planned: this doc does not decide that; `docs/interlingua-standard.md`
|
||||
owns it.
|
||||
- Licences not checked: the UMR dataset, the other four Japanese UD treebanks,
|
||||
CoCoA-MT repo licence ambiguity (paper says CDLA-Sharing-1.0, GitHub says
|
||||
NOASSERTION).
|
||||
|
|
@ -65,7 +65,7 @@ Verified licence facts are few. Discord data excluded by policy; not read.
|
|||
- PersonaChat (Zhang et al. 2018): ParlAI project page, archived 2020-08-01, states no licence, only "You may continue to use the data without issue". [V] https://parl.ai/projects/personachat/ ; paper https://arxiv.org/abs/1801.07243 says data released open source via ParlAI; licence text [GAP]. Crowdworker-written, persona-statement-conditioned chit-chat [B].
|
||||
- LIGHT: ParlAI page states no licence; contents: 663 locations, 3,462 objects, 1,755 character types, 11,000 episodes; WILD 41,131 training episodes from game deployment (human players, so a different provenance than crowdwork). [V] https://parl.ai/projects/light/ . Licence [GAP: check ParlAI repo].
|
||||
- Cornell Movie-Dialogs Corpus: licence/terms page fetch failed (certificate rejected) https://www.cs.cornell.edu/~cristian/Cornell_Movie-Dialogs_Corpus.html . [GAP] Underlying scripts are copyrighted film text [B]; dataset licence unverified.
|
||||
- Project Gutenberg: "vast majority" of eBooks public domain in the US, so no one can grant or withhold permission for uses; PG cannot sublicense copyrighted items; subject to its Terms of Use, which the permission page links and does not summarise; no statement on ML/bulk use on that page. [V] https://www.gutenberg.org/policy/permission.html . Terms-of-Use text on bulk/automated access and the trademark licence: read 2026-11-13, see `2026-11-13-gutenberg-terms.md`. Items public domain in the US may not be elsewhere (same page).
|
||||
- Project Gutenberg: "vast majority" of eBooks public domain in the US, so no one can grant or withhold permission for uses; PG cannot sublicense copyrighted items; subject to its Terms of Use, which the permission page links and does not summarise; no statement on ML/bulk use on that page. [V] https://www.gutenberg.org/policy/permission.html . Terms-of-Use text on bulk/automated access and the trademark licence: [GAP, not read]. Items public domain in the US may not be elsewhere (same page).
|
||||
- Google Synthetic-Persona-Chat (model-generated, persona-chat-style): CC BY-NC? listed as cc-by-4.0 on HF. [V search-only] https://huggingface.co/datasets/google/Synthetic-Persona-Chat
|
||||
- Operator-authored or model-generated corpus: no licence question beyond provider terms [B, unread this pass]. Problems with evaluating on model-generated text: see 2 (self-bias, preference leakage, stylistic homogeneity: Xu et al. 2025; Li et al. 2025). The same Xu et al. finding says it extends to open-ended generation.
|
||||
- Expressive-register-annotated English corpora (hedging, humour, affect, politeness labelled), with permissive terms: [GAP] not searched beyond the list above (e.g. Stanford Politeness Corpus, GYAFC formality, Enron etc. are [B] candidates, unverified, GYAFC is known to carry Yahoo Answers terms [B]).
|
||||
|
|
@ -83,6 +83,6 @@ Verified licence facts are few. Discord data excluded by policy; not read.
|
|||
- No per-metric human-correlation numbers for hedging, humour, affect, stance, persona voice; nearest is formality (Briakou 2021). COMET, BLEURT, MAUVE correlations not obtained.
|
||||
- No source on surface-form smuggling through an LLM bottleneck or its defences (vocab restriction, paraphrase invariance).
|
||||
- No source on schema/inventory growth from generation failures, or its overfitting controls.
|
||||
- Cornell, LIGHT, PersonaChat licence texts not obtained.
|
||||
- Cornell, LIGHT, PersonaChat licence texts not obtained; Gutenberg ToU on bulk use not read.
|
||||
- No realiser or evaluation protocol for constructed languages from a meaning representation.
|
||||
- Several arXiv PDFs (Briakou, Zheng, STEL, LUAR/StyleDistance) fetched as binary; numbers above come from the ar5iv/arXiv-HTML versions where marked, otherwise search summaries.
|
||||
|
|
|
|||
|
|
@ -1,59 +0,0 @@
|
|||
# Project Gutenberg terms: bulk access and header stripping
|
||||
|
||||
Read 2026-11-13 for follow-up `gutenberg-terms` (campaign `weksa-lowering`),
|
||||
ahead of cut `pd-importer`. Pages: gutenberg.org `policy/permission.html`,
|
||||
`policy/terms_of_use.html`, `policy/robot_access.html`, `policy/license.html`.
|
||||
The quotes were checked against the live HTML of each page by a second reader.
|
||||
`pd-importer`'s Imagination re-reads the pages before it fixes a fetch path,
|
||||
since they change.
|
||||
|
||||
## Findings
|
||||
|
||||
- **Automated access to the main site is refused.** Terms of Use: "This website
|
||||
is intended for human users only"; "Any perceived use of automated tools to
|
||||
access this website will result in a temporary or permanent block". OPDS
|
||||
feeds: no more requests than a browser user would make; heavy requesters are
|
||||
blocked by IP.
|
||||
- **Bulk has two sanctioned paths.** Terms of Use: take bulk downloads "from
|
||||
one of our mirrors, not from the main site". The robot-access page names the
|
||||
`robot/harvest` wget endpoint (`-w 2`, filterable by file type or language)
|
||||
and recommends a private mirror for a full local copy; it suggests checking
|
||||
periodically for changes. Catalog data are offered as
|
||||
machine-readable offline catalogs, "granted to the public domain".
|
||||
- **Header and licence stripping.** Licence section 1.C: for a work not
|
||||
protected by US copyright, with the user in the US, the Foundation does "not
|
||||
claim a right to prevent you from copying, distributing, performing,
|
||||
displaying or creating derivative works", "as long as all references to
|
||||
Project Gutenberg are removed", the condition holding for a user in the US.
|
||||
Section 1.E opens "Unless you have removed all references to Project
|
||||
Gutenberg", and 1.E.1 to 1.E.7 (including 1.E.4, do not detach the licence)
|
||||
attach to a work on which the phrase "Project Gutenberg" appears or with which
|
||||
it is associated, so a text with every reference removed is outside 1.E.
|
||||
1.E.2 is not that grant: it says a PG eBook derived from texts not restricted
|
||||
by US copyright may be copied and distributed in the US without fee. The
|
||||
trademark is registered; non-commercial use of the name needs no permission,
|
||||
commercial use does.
|
||||
- **No statement on machine learning or AI use** on any of the four pages.
|
||||
- **US public domain only.** The Foundation makes no claim about copyright
|
||||
outside the US (1.D). A work free in the US may not be free elsewhere, and
|
||||
Gutenberg's own catalog is not a per-work clearance.
|
||||
|
||||
## What this decides for `pd-importer`
|
||||
|
||||
- Fetch from a mirror or an offline dump. The Terms of Use footnote counts "many
|
||||
books" as more than about 100 a day and sends those to mirrors, while
|
||||
`robot/harvest` is a `www.gutenberg.org` URL: use it (with `-w 2`) only for a
|
||||
handful of works. Never crawl `gutenberg.org` pages or OPDS from the loop host.
|
||||
- Strip the whole header and footer, every Project Gutenberg reference and the
|
||||
licence text from the stored text; keep provenance as the ebook number and
|
||||
edition in the item's source field, which is Weksa's own record and not a use
|
||||
of the mark. This is the path `docs/targets/dao-de-jing-test-bed.md` already
|
||||
takes. The remaining open question there, what counts as a "reference", stays
|
||||
open: the safe reading is that the ebook number in a provenance field is a
|
||||
catalogue identifier, not a reference inside the work, but nothing read here
|
||||
rules on it.
|
||||
- Per-work check stays with the importer: the work's author and first
|
||||
publication date against US public-domain rules, recorded on the item. The
|
||||
Foundation's catalogue does not supply it. A work Gutenberg posts with the
|
||||
copyright holder's permission (1.E.3) is out of scope.
|
||||
- No importer code in this note.
|
||||
|
|
@ -1,116 +0,0 @@
|
|||
# Scene annotation
|
||||
|
||||
How the keeper scenes of `data/original/speaker-state.cc` are labelled. A scene
|
||||
label has a committed rule that produced it; this file is that rule.
|
||||
|
||||
## Why
|
||||
|
||||
Two findings forced a written rule.
|
||||
|
||||
- `annotation-rank-from-register`: an annotator who reads the line's register
|
||||
(politeness forms, honorifics, endings) to decide the speaker's rank hands the
|
||||
lowering its own answer back, because register is what the lowering must
|
||||
produce from the scene.
|
||||
- The addressee gate (`with_scene` in `crates/weksa/src/validate.rs`): a scene is
|
||||
read only when the packet names a discourse addressee. A line that addresses no
|
||||
one reads `NoAddressee` and no Scene entry selects, so labels on narration are
|
||||
inert and the only labels that bite are those on lines said to someone.
|
||||
|
||||
The earlier labels followed two briefs that were never committed and that
|
||||
disagreed with each other (the relation to the reader, and a situation read with
|
||||
the register ignored). The rubric below replaces both for every live group.
|
||||
|
||||
## Provenance
|
||||
|
||||
Cut `weksa-lowering:cut_spec:cut-scene-in-group.r1`, ruling
|
||||
`weksa-lowering:ruling:scene-rubric-whole-bed`: all 98 live Train and Validation
|
||||
groups of `data/original` receive a new scene revision from annotator A under
|
||||
rubric r1, generator `claude-sonnet-5-5 (Weksa Hands, scene rubric r1,
|
||||
docs/scene-annotation.md)`. Earlier revisions stay as provenance. The rubric uses
|
||||
no corpus line as an example on purpose: a labelled example would make the blind
|
||||
check against the old labels circular.
|
||||
|
||||
A later rubric revision gets a new section and a new generator string; r1 is
|
||||
never edited.
|
||||
|
||||
## Rubric r1
|
||||
|
||||
The speaker of every line is the keeper, a quiet caretaker of a house and garden. First decide whether the line addresses a listener: it asks them something, asks them to do something, tells them about themselves, wishes something for them, or speaks to them as you. A line that addresses no one (narration, description, a remark about the world or about other people, a thought or wish with no one addressed) is told to the reader, a stranger: answer addressed false, relative_status level, intimacy 500, in_group false. People named inside a line are not its listener.
|
||||
|
||||
For a line that addresses a listener, answer addressed true and judge the keeper's relation to that listener from the situation the line states or implies, never from its register: politeness forms, honorifics, sentence endings, contractions, please and casual particles are what the lowering must produce from the scene, so they cannot decide it. relative_status: above when the situation gives the keeper standing over the listener (instructing, advising or permitting as elder, host, employer or teacher); below when it gives the listener standing over the keeper (the keeper serves, thanks, or asks a favour of a guest, employer, elder or official); level when it shows neither.
|
||||
|
||||
intimacy, 0 to 1000: 500 when the line shows nothing; up to 800 when it shows shared daily life (the listener's body, sleep or habits, the household's routine); above 800 only for a stated close bond; down to 200 for a stated first meeting or a service relation. in_group: true only when the line shows the listener belongs to the keeper's household, family or working circle, stated or plainly implied; a request, a question or a kind wish alone is not enough; otherwise false. Answer one JSON line per group, in the order given and nothing else: {"group": G, "addressed": true|false, "relative_status": S, "intimacy": N, "in_group": true|false}.
|
||||
|
||||
## Procedure
|
||||
|
||||
- Annotator A (committed) and annotator B (measurement only) are separate fresh
|
||||
model agents, one pair per language (49 live groups each). Each sees only the
|
||||
text of Rubric r1 above and that language's sentences as `group<TAB>"text"`,
|
||||
shuffled by a fixed seed. Neither sees an existing scene, the other annotator's
|
||||
answer, the ontology, which items are old or new, or any Test text.
|
||||
- An output that does not parse or misses a group is re-drawn once and logged.
|
||||
- A's labels are written with `weksa scene put` (one revision per group,
|
||||
`--to unnamed --inventory-rev 4`). `addressed` is not stored: no Scene feature
|
||||
carries it.
|
||||
- Disagreements are reported, never adjudicated.
|
||||
|
||||
## Agreement at r1 (this cut, 98 live groups, 49 per language)
|
||||
|
||||
Four fresh agents drew the labels (A-en, A-ja, B-en, B-ja); the briefs were the
|
||||
rubric section plus one language's shuffled sentences (SHA-256 of the brief
|
||||
bodies: en-US `db087476...dbc04e`, ja-JP `c5b81b27...97488c`; no Test text in
|
||||
either). No draw was repeated. Annotator model: `claude-sonnet-5-5`.
|
||||
|
||||
A against B (B measures only): pooled `addressed` equal 96/98 (kappa 0.96),
|
||||
`in_group` equal 93/98 (kappa 0.79), `relative_status` equal 89/98, intimacy
|
||||
within 150 on 98/98. en-US: addressed 47/49, in_group 47/49 (0.86),
|
||||
relative_status 45/49. ja-JP: addressed 49/49, in_group 46/49 (0.64),
|
||||
relative_status 44/49.
|
||||
|
||||
Blind check, A against the 56 older labels: `relative_status` equal 49/56,
|
||||
`in_group` equal 53/56 (kappa 0.64), intimacy within 150 on 55/56. Three
|
||||
in_group differences: `original-ja-shimoyado-2` and `original-ja-sakana` (both
|
||||
narrations, true to false) and `original-ja-asa` (an instruction to a household
|
||||
member, false to true).
|
||||
|
||||
In_group true across the 98: 42 before, 15 after; every unaddressed line is now
|
||||
false (it was true on 17 of the 21 unaddressed vgrow groups). Disagreements are
|
||||
reported, not adjudicated.
|
||||
|
||||
## Reproducing the cut
|
||||
|
||||
`scripts/scene-annotation/` holds the standard-library scripts of this cut, run
|
||||
from the repo root with `WEKSA` (the binary) and `SCENE_SCRATCH` (a directory
|
||||
that is never committed): `build_briefs.py` writes the two annotator briefs from
|
||||
the Rubric r1 section and prints each brief's Test-leak count (must be 0) and
|
||||
sha256 (it reproduces the briefs of this cut byte for byte); `put_labels.py`
|
||||
puts A's `A-en.jsonl` and `A-ja.jsonl`; `agreement.py` prints the tables above and
|
||||
must run before the puts, against the store at 76fa685, because the older labels
|
||||
are then its latest revisions (it also reads the round-1 encoder answers of
|
||||
`runs/growth-base` through `ROUND1`). `DIGEST_OF_THE_RUBRIC` and
|
||||
`DIGEST_OF_THE_EARLIER_SCENES` in `crates/weksa/tests/original_corpus.rs` pin the
|
||||
rubric text and the 113 earlier revisions.
|
||||
|
||||
## Known limits of r1 labels
|
||||
|
||||
Found by Soul's pass on this cut (`weksa-lowering:verdict:cut-scene-in-group.s1`).
|
||||
They are not fixed in r1; a reviewer's pass over the labels is follow-up
|
||||
`weksa-lowering:follow_up:scene-labels-reader-review`.
|
||||
|
||||
- The new labels change which ontology entries are selected for 37 groups. Eight
|
||||
addressed lines move onto the casual in-group entries (en-US:12: lantern,
|
||||
broom, mirror, seedling; ja-JP:12: furo, asa, irori, yurikago), while their
|
||||
references are polite requests. The reader default (level, 500, false) is
|
||||
exactly the condition of ja-JP:11.
|
||||
- `relative_status` tracks request form for some lines: imperatives read above,
|
||||
favour questions read level or below, so the same household request gets
|
||||
different standing in two forms (hane above/650/true, kabin below/500/false;
|
||||
B gave both level/false). Form is what signals the speech act, which is what
|
||||
part 2 asks for, and register is what part 2 forbids.
|
||||
- `in_group` is true on some requests alone (lantern, mulch, stool, hane) and on
|
||||
a line whose only family member is named inside it (original-ja-ane), though r1
|
||||
says a request or a person named inside the line is not enough. A and B
|
||||
agreeing does not clear this.
|
||||
- A run opened on the old speaker-state refuses to continue after merge:
|
||||
`runs/growth-base` pins the store of `/var/lib/mind-weksa-self/Weksa-growth`
|
||||
(main), and that checkout must not be pulled while the run is wanted.
|
||||
|
|
@ -23,10 +23,9 @@ plus a separately recorded chosen gloss per lowering).
|
|||
`corpus add ... --language en-US --source public-domain` per item, then `packet dao <store>`.
|
||||
- Source: Project Gutenberg eBook 216, "The Tao Teh King, or the Tao and its
|
||||
Characteristics", Laozi, tr. James Legge (Sacred Books of the East 39, 1891).
|
||||
Gutenberg's licence (1.C) does not claim a right to prevent derivative works of
|
||||
a work not protected by US copyright, for a user in the US, provided every
|
||||
Project Gutenberg reference is removed (see
|
||||
`docs/research/2026-11-13-gutenberg-terms.md`). The items hold only Legge's words, one numbered section
|
||||
Gutenberg's licence (1.E.2) lets a work derived from texts not protected by US
|
||||
copyright be used with no fee provided every Project Gutenberg reference is
|
||||
removed from the work. The items hold only Legge's words, one numbered section
|
||||
or sentence each; no Gutenberg header, licence text or trademark is stored,
|
||||
and the eBook file itself is not committed. `edition_url` names the page the
|
||||
text was retrieved from, as a citation of provenance and not as part of any
|
||||
|
|
@ -81,8 +80,6 @@ ceiling of an author who saw the reference:
|
|||
frame minted from Train, scored lowest (chrF 44.18). The scores rise with
|
||||
how bespoke the frame is, the reverse of generalisation. The Validation and
|
||||
Test numbers measure the lowerer table, not what the interlingua can carry.
|
||||
That table is deleted: the Dao numbers below were measured on it, and the
|
||||
loop now lowers through the model (`Prompt::lower`).
|
||||
- n = 5, one translation as reference, one embedding model, no variance.
|
||||
|
||||
## What the scorer cannot see
|
||||
|
|
|
|||
|
|
@ -38,10 +38,10 @@ means no store holds it and nothing writes it.
|
|||
| Community (cut `language-ontology`, follow-up `language-ontology-communities`) | Key `community:<slug>`; type `weksa.community`, built fresh when the cut is mapped: `data/cultural-ontology/` (draft YAML profiles, read by no code) is deleted from main (cut 5e `delete-cultural-ontology`) and stays in git history before that cut's commit | Revised by commit; a speaker names the communities it belongs to by id | The cultural ontology's author (owner-attested evidence only; Discord-only content stays deleted, `discord-only-content-deleted`) |
|
||||
| Speaker (cut `speaker-scene`) | Key `speaker:<slug>@<n>`; type `weksa.speaker`: stable axes as feature values of slot `Speaker` (origin, socioeconomic standing, age cohort, education and whatever the loop adds), at an inventory revision, and an `Annotator` | A new revision appends, never edits; a corpus item and every prior turn name a speaker slug, and a round records the speaker revisions it read | The annotator it names: `PersonaSnapshot` (a projection of a `gamecult.persona_state.v0` document, naming its source document and `updatedAt`), `Operator`, `WorkMetadata` (a public-domain work's own cast list and narration), or `Model { family, generator }` (the 2b `ModelFamily`) |
|
||||
| Scene (cut `speaker-scene`) | Key `scene:<group>@<n>`, the item's split group; type `weksa.scene`: participants (speaker slugs) and, per ordered pair, relation features of slot `Scene` (relative status, intimacy, in-group, audience and whatever the loop adds), at an inventory revision (provenance; a run reads the features at its own head), and an `Annotator` | As Speaker. Keyed by the group, so a scene never straddles the split. `data/original/speaker-state.cc` holds Model-annotated keeper scenes, one per Train or Validation group of both languages (`weksa scene put|dump`); a Test group has none and reads `NoScene` | As Speaker; a model-annotated scene is never Test evidence |
|
||||
| Corpus item | Key `item:<source-slug>:<n>`, `n` canonical decimal >= 1 (no sign, no leading zero, from cut 2b); type `weksa.corpus_item` with text, language, speaker, split group, prior turns, source and who placed its name spans (`names_by`, an `Annotator`, absent when unrecorded; cut `pd-name-spans`). Source `ModelWritten` carries a `ModelFamily` enum, the generator string as the fixture wrote it, and a prompt digest (cut 2b). The item carries no speaker state of its own: its speaker slug and group name the Speaker and Scene documents | Admitted once; the whole item is immutable (re-adding an identical item is a no-op, any difference is refused; a correction is a new item that `supersedes` the old); text already held under another key is refused unless the new item supersedes that key (cut 2b); withdrawn, never deleted, so old scores stay explainable | Importers and `weksa corpus add`, under `corpus-cast-plus-public-domain`; the source enum has no variant for Discord or any training-forbidden source (`corpus-clean`) |
|
||||
| Corpus item | Key `item:<source-slug>:<n>`, `n` canonical decimal >= 1 (no sign, no leading zero, from cut 2b); type `weksa.corpus_item` with text, language, speaker, split group, prior turns, source. Source `ModelWritten` carries a `ModelFamily` enum, the generator string as the fixture wrote it, and a prompt digest (cut 2b). The item carries no speaker state of its own: its speaker slug and group name the Speaker and Scene documents | Admitted once; the whole item is immutable (re-adding an identical item is a no-op, any difference is refused; a correction is a new item that `supersedes` the old); text already held under another key is refused unless the new item supersedes that key (cut 2b); withdrawn, never deleted, so old scores stay explainable | Importers and `weksa corpus add`, under `corpus-cast-plus-public-domain`; the source enum has no variant for Discord or any training-forbidden source (`corpus-clean`) |
|
||||
| Split assignment | Derived: `split(scheme, item.group)` | Fixed for a scheme; a new scheme is a new constant, never a reassignment. A model-written item whose group derives test is in no split; a superseding item keeps its predecessor's group | The hash function. Nobody assigns by hand, so there is no writer to forbid |
|
||||
| Loop round | Key `run:<label>:round:<n>`; type `weksa.loop_round` with spec version, profile revisions, model ids and prompt digests, sampled train items, Validation means and refusal counts (from cut `ja-panel-loop`: one set per language of the run's panel, no pooled mean), per-item Validation scores in corpus order (key 22, numbers only, no item key or text, private to `run.rs` for the paired floor of the cycle (rounds 1 to 4) and of relower; a run from before has none and opens), the digest of the inventory file it was scored under and, for a cycle's candidate round, its cycle `k` | Scored and recorded whole; immutable. A candidate round is put in one batch with its Decision. Lives in the run store on Yggdrasil | `run::round` and `run::cycle` (both through `score_round`) |
|
||||
| Loop decision | Key `run:<label>:cycle:<k>`; type `weksa.loop_decision` with the base round and revision, the edit prompt's digest and Train keys, the editor's answer digest, the candidate revision, inventory digest and round, the base, candidate and floor readings (chrF, meaning, composite; the floor is the paired floor of round 1 against rounds 2 to 4), the threshold and the verdict (Accepted, or Rejected for edit-parse, edit-admit, no-gain, regressed chrF, meaning or composite); digests and numbers, no text | Immutable. The latest Accepted one names the run's head inventory (`<root>/cycle-<k>/inventory.cc`, its candidate digest, its candidate round); with none the head is the copy `create` made at `<root>/inventory.cc`. Lives in the run store on Yggdrasil | `run::cycle`'s accept rule, `run::decide`: the validation composite gains more than max(noise floor, `LADDER_STEP`), no metric falls past max(its floor, one step), the composite does not fall past max(its floor, one step), and a non-finite reading rejects (the one regression test, `run::regression`); differences compared in billionths so a gain of exactly one step is a tie. From cut `ja-panel-loop` the readings, floor and threshold are kept per panel language and `run::regression` runs per language and is the one regression test (`decide` adds the gain test for a one-language panel): any language regressing rejects (verdicts `regressed-chrf`, `regressed-meaning`, `regressed-composite`), otherwise a one-language panel accepts as `decide` does and a panel of two or more accepts when the sum of composite deltas exceeds one `LADDER_STEP` (billionths). Given up: strict Pareto non-regression; a language may lose up to its own noise floor if the panel nets more than a step, because zero tolerance ratchets every base to a favourable noise draw and strangles the loop. Termination: each accept raises the composite sum by more than a step and composites lie in -0.5 to 1, so a run accepts at most 1.5 * languages / `LADDER_STEP` edits |
|
||||
| Loop round | Key `run:<label>:round:<n>`; type `weksa.loop_round` with spec version, profile revisions, model ids and prompt digests, sampled train items, Validation means and refusal counts (from cut `ja-panel-loop`: one set per language of the run's panel, no pooled mean), the digest of the inventory file it was scored under and, for a cycle's candidate round, its cycle `k` | Scored and recorded whole; immutable. A candidate round is put in one batch with its Decision. Lives in the run store on Yggdrasil | `run::round` and `run::cycle` (both through `score_round`) |
|
||||
| Loop decision | Key `run:<label>:cycle:<k>`; type `weksa.loop_decision` with the base round and revision, the edit prompt's digest and Train keys, the editor's answer digest, the candidate revision, inventory digest and round, the base, candidate and floor readings (chrF, meaning, composite), the threshold and the verdict (Accepted, or Rejected for edit-parse, edit-admit, no-gain, regressed chrF, meaning or composite); digests and numbers, no text | Immutable. The latest Accepted one names the run's head inventory (`<root>/cycle-<k>/inventory.cc`, its candidate digest, its candidate round); with none the head is the copy `create` made at `<root>/inventory.cc`. Lives in the run store on Yggdrasil | `run::cycle`'s accept rule, `run::decide`: the validation composite gains more than max(noise floor, `LADDER_STEP`), no metric falls past max(its floor, one step), the composite does not fall past max(its floor, one step), and a non-finite reading rejects (the one regression test, `run::regression`); differences compared in billionths so a gain of exactly one step is a tie. From cut `ja-panel-loop` the readings, floor and threshold are kept per panel language and `run::regression` runs per language and is the one regression test (`decide` adds the gain test for a one-language panel): any language regressing rejects (verdicts `regressed-chrf`, `regressed-meaning`, `regressed-composite`), otherwise a one-language panel accepts as `decide` does and a panel of two or more accepts when the sum of composite deltas exceeds one `LADDER_STEP` (billionths). Given up: strict Pareto non-regression; a language may lose up to its own noise floor if the panel nets more than a step, because zero tolerance ratchets every base to a favourable noise draw and strangles the loop. Termination: each accept raises the composite sum by more than a step and composites lie in -0.5 to 1, so a run accepts at most 1.5 * languages / `LADDER_STEP` edits |
|
||||
| Score | Key `<lowering-key>:<metric>@<metric-version>`; type `weksa.score` | Immutable; a new metric version scores again under a new key | The scorer, deterministic given the metric version and the embedder's model id. Cut `scorer` computes scores as values; cut `golf-loop-en` stores them, because the lowering keys they hang from arrive with the loop. Lands with follow-up `golf-loop-score-docs`, in the round's directory; nothing in the cycle reads them |
|
||||
| Lowering trace | Key `lowering:<packet-key>:<profile>@<rev>:<lowerer-digest>:<sample>`; type `weksa.lowering` holding the surface text and its trace together | Immutable. A surface text cannot exist without its trace, because they are one record (`lowering-traced`) | The lowerer emits; the lowerer sees the packet without its `trace` (the input type has no such field), never the corpus item |
|
||||
| Conlang lexicon entry | Key `lex:<language>:<concept-id>`; root form, morphology class | Root placed at its concept's embedding when the concept first needs a form in that language; stable once accepted; diachrony derives later forms, it does not overwrite | The language project's owner: the operator for her settings' languages, the loop proposing roots for her review |
|
||||
|
|
@ -340,14 +340,9 @@ line two", "その 制御" against the
|
|||
- Stores: `data/interlingua/inventory.cc` and `data/corpus/corpus.cc` in the
|
||||
repo (small, reviewed with `weksa dump`); run stores (rounds, lowerings,
|
||||
scores) on Yggdrasil under the loop's state root, not in git.
|
||||
- The loop is a batch command driven from a Claude Code session on Yggdrasil
|
||||
(`golf-loop-in-claude`), not a detached unit. Model calls go through a
|
||||
`ModelPort` whose one adapter, `AnswerFiles`, writes a `.prompt` file and reads
|
||||
a `.answer` file: Claude agents answer them, one fresh subagent per encode
|
||||
prompt (`encoder-isolation-subagent-per-prompt`) and a tool-less relay for
|
||||
lowering prompts (`lowerer-call-reach-toolless-relay`). Builds, stores, scoring
|
||||
and embeddings run on Yggdrasil; Starfire runs none of it, and Weksa needs no
|
||||
claude binary or token there. Never OpenAI
|
||||
- The loop runs on Yggdrasil as a detached unit with a log and a status record.
|
||||
Starfire runs none of it. Model calls go through a `ModelPort`; its first
|
||||
adapter drives `claude -p` on the operator's subscription. Never OpenAI
|
||||
(`eureka-body:ruling:no-return-to-openai-supplier`), never Discord data
|
||||
(`gamecult-chat:ruling:discord-taints-training`).
|
||||
|
||||
|
|
@ -360,271 +355,57 @@ checkpoint the test-split composite is within the noise floor of validation.
|
|||
The test split is read only at checkpoints. Self then records the freeze, and
|
||||
the training set is the whole corpus re-encoded under the frozen revision.
|
||||
|
||||
## Distil measure (`distil-slice`)
|
||||
## Lowerer first cut (`golf-loop-lowerer-cut`)
|
||||
|
||||
A lowerer is compared on round n's Validation packets with the prompts
|
||||
byte-identical to the round's, by `weksa loop relower ROOT --round N --arm ARM
|
||||
--lowerer LABEL [--floor ARM2 --floor ARM3 --floor ARM4]`. Every arm is answered through the one prompt
|
||||
door (`RunStores::answer_files`, the Test-text guard); a tuned model is a script
|
||||
that reads `<digest>.prompt` and writes `<digest>.answer` in
|
||||
`<ROOT>/relower-<N>-<ARM>`, not a new adapter. The recorded reading is the
|
||||
round's own lowering, read over the same items as the arm. An item the round
|
||||
refused before admission (no packet) or at the lowering prompt has no prompt to
|
||||
ask: it is skipped, so the readings exclude it, and it is counted as `skipped=`
|
||||
on the line; `n` is the items read, so `recorded` can differ from the round's
|
||||
own Validation reading, which scores those items 0. An arm answer that is not a
|
||||
usable lowering scores 0 and counts in `unusable=`; the same for the floor arm,
|
||||
counted (over all floor arms) after `floor ... unusable=`. The floor needs three
|
||||
or more floor arms, each a prompted repeat of the recorded lowering on the same
|
||||
prompts: it is `FLOOR_Z` (3) standard errors of the mean per-item difference
|
||||
between the recorded lowering and a repeat, per metric, with the variances
|
||||
pooled over the arms (`paired_floor`; lowering-only noise, no encoder noise). The
|
||||
verdict is `decide_panel` over (recorded, arm, floor): Accepted is a composite
|
||||
gain past the noise of the panel's sum (the root of the languages' composite
|
||||
floors squared, at least one step), Rejected(Regressed) a loss past a language's
|
||||
floor, Rejected(NoGain) neither. The cycle's own floor is the same `paired_floor`
|
||||
(`floor_of`): round 1 (the recorded lowering, the head's establishing round)
|
||||
against rounds 2 to `FLOOR_ARMS_MIN` + 1 (prompted repeats under the run's first
|
||||
inventory), per panel language, from the rounds' per-item Validation scores. It
|
||||
is measured once per run and is the same after an accept; a run needs four
|
||||
`loop round` calls before its first `loop cycle`.
|
||||
Calibration (`runs/distil-base`, 8 prompted draws by one model family on
|
||||
identical prompts, no draw sharing more than 7 of 28 answers with another; 14
|
||||
en-US and 14 ja-JP Validation items; every base, candidate and 3-arm floor
|
||||
combination, 1120 trials from 28 unordered pairs; intervals bootstrap over
|
||||
draws, each degraded arm one fixed draw): a prompted repeat reads NoGain 92%
|
||||
(80 to 100), Regressed 8% (0 to 20), Accepted 0%, which with 28 pairs bounds
|
||||
false-accept only to about 10%; an all-"Yes." arm reads Regressed 100%; a mild
|
||||
degradation (one detail blurred per utterance) 100%; a subtler one 75% (50 to
|
||||
100), whose mean composite drop (0.044) sits under the mean floor (0.060).
|
||||
`FLOOR_Z` was chosen on this data (2.5 gives NoGain 84% and 93% on the subtler
|
||||
arm), so the rates are in-sample. Without the noise term in the gain test a
|
||||
prompted repeat reads Accepted in 40% of the trials.
|
||||
Power (can the rule Accept a real gain?): the only better arm that could be
|
||||
built without Test or Validation answers is a lowerer shown the Train sentences
|
||||
of the corpus (no packets, no Validation or Test text) as a register guide.
|
||||
Four such draws beat the prompted draws' mean composite in both languages (en-US
|
||||
0.742 to 0.759 to 0.795; ja-JP 0.559 to 0.578 to 0.620), so the premise that it is
|
||||
better is measured on the very Validation items the rule reads, not independent.
|
||||
Against the prompted bases with 3-arm floors the rule reads it Accepted in 29%
|
||||
of 1120 trials, NoGain 71%, Regressed 0%: a net gain of 0.079 against a mean
|
||||
noise term of 0.079. At 14 items per language the rule is therefore a low-power
|
||||
filter for a gain of this size; by 1/sqrt(n), about 35 or more items per
|
||||
language would bring the noise term near 0.05 (an extrapolation, not measured).
|
||||
### Validation growth (`validation-growth`, built and recalibrated)
|
||||
|
||||
Power needs about 35 or more Validation items per language. `data/original`
|
||||
now holds 35 per language (it held 14; Train 14 and Test 8 are unchanged):
|
||||
42 model-written items, `item:vgrow:1..21` (en-US) and `item:vgrow-ja:1..21`
|
||||
(ja-JP), live Train+Validation 56 to 98. The slug is new on purpose: the
|
||||
`item:original:` prefix filter of `DIGEST_OF_THE_28` still selects the first 28
|
||||
and passes; `DIGEST_OF_THE_42` freezes the new prose.
|
||||
|
||||
The split is derived from an item's group alone (`SplitScheme::V1`: FNV-1a of
|
||||
`weksa-split-v1:<group>` mod 100, under 40 Train, under 80 Validation, else
|
||||
Test). The names were chosen before any text existed: 90 candidate nouns per
|
||||
language, dropped by script when the group already existed or the noun
|
||||
occurred in a Test text, then the first 24 whose bucket fell in 40..=79 (the
|
||||
bucket came from `SplitScheme::V1` itself, cross-checked on the 72 existing
|
||||
items). Each language was written by three blind writer agents (8 nouns each,
|
||||
a brief of language, register note, noun and speech act, no Test text and no
|
||||
existing item), 24 texts per language written, the first 21 in name order
|
||||
admitted through `weksa corpus add`; each group is its own group. The scenes
|
||||
are `weksa scene put` documents (keeper to `unnamed`, inventory rev 4),
|
||||
annotated by a separate agent; a second annotator measured agreement only and
|
||||
is not committed.
|
||||
|
||||
The writer is Claude (family Anthropic recorded): no cross-family generator was
|
||||
reachable from the body that ran this cut. The self-preference effect (a Claude
|
||||
lowerer favouring Claude prose, Panickssery et al. 2024) is therefore not
|
||||
measured. The writers' blindness is by brief content, not sandbox.
|
||||
|
||||
Expect encode refusals: the existing 56 were written onto the Dao r3 concepts
|
||||
and the inventory was drafted from them, while the new items were written free
|
||||
of the inventory (question `validation-growth-vocabulary` stays open). Some new
|
||||
packets will be refused at encode (inventory coverage) and score 0 as the means
|
||||
do; they stay in the corpus. That is a result about inventory generalization,
|
||||
not a defect.
|
||||
|
||||
Every calibration number in the Distil measure section above (92/0/8 prompted
|
||||
rates, the 29% power, the 0.079 noise term) is for the 14-item corpus and stays
|
||||
the stated baseline of that corpus.
|
||||
|
||||
Recalibration on the grown corpus (`runs/growth-base`, main 44b66f9, panel
|
||||
en-US and ja-JP, round 1 recorded by briefed subagents; 6 prompted draws
|
||||
including the recorded one, 2 mild degradations, an all-"Yes." control and 4
|
||||
Train-guide draws by Claude sonnet-5-5; the same decision rule at FLOOR_Z 3 and
|
||||
3-arm floors; 120 prompted trials from the 30 ordered pairs of 6 draws with the
|
||||
other 4 as floor candidates, so trials share draws and are not independent).
|
||||
Soul pass `cut-validation-growth.s3` re-derived every number below; its
|
||||
findings shaped the wording.
|
||||
|
||||
- Live Validation items: 28 en-US and 32 ja-JP of 35 each; 10 are refused at
|
||||
parse (en-US original:18, 23, 25, 27 and vgrow:4, 5, 6; ja-JP original-ja:17,
|
||||
22 and vgrow-ja:2); `relower` skips an item with no packet, so every reading
|
||||
here is over live items only. Old 14: 10 en-US and 12 ja-JP live; new 21: 18
|
||||
and 20.
|
||||
- Prompted repeat: NoGain 96.7%, Accepted 3.3%, Regressed 0% (14 items: 92 / 0 /
|
||||
8). All four false accepts are one pair, base p6 and candidate the recorded
|
||||
lowering R: R comes from the round, the other five draws from `relower`, and
|
||||
in en-US R scores +0.024 per item above them [+0.002, +0.052], so R is not
|
||||
exchangeable with a repeat (a Plausible Soul finding, cause not isolated). No
|
||||
false-accept bound can be drawn from 6 draws.
|
||||
- Degraded arms read Regressed: all-"Yes." 100% (as before); mild-1 31.7%;
|
||||
mild-2 0% (14 items: 100% and 75% on a subtler arm). The mild arms are weak
|
||||
and not independent: they were rewritten from R with one detail blurred, the
|
||||
original wording is not on disk, mild-2 equals R word for word in 5 of 60
|
||||
items and mild-1 in 2, and mild-1 equals mild-2 in 27 of 60 although they
|
||||
were asked to blur different details. Their mean composite is 0.003 to 0.015
|
||||
below the prompted mean (the old subtler arm: 0.037 and 0.052). The
|
||||
sensitivity to a small regression is not re-measured.
|
||||
- Noise: the panel noise term of the sum rule is 0.045 on average over the base
|
||||
and floor choices (0.031 to 0.064), against 0.079 at 14 items. The 1/sqrt(n)
|
||||
forecast (about 0.05) assumed per-item variance stayed the same; it did not:
|
||||
the per-item SD of the difference between two prompted draws is about 0.085
|
||||
on the old items and 0.034 on the new ones, so the pooled term landed near
|
||||
the forecast because less variable items were added. Not a confirmation of
|
||||
the forecast.
|
||||
- Power: the Train-guide arm (14 Train sentences as a register guide) is
|
||||
Accepted in 21.2% of 240 trials, NoGain 78.8%, against 29% at 14 items, and
|
||||
its mean composite gain over the prompted draws is 0.0185, 0.41 of the mean
|
||||
noise term (0.37 on the first floor choice per base); with `relower`-only
|
||||
bases (R removed) it is Accepted in 35% (28 of 80). Split by item class
|
||||
(paired bootstrap over items, 95%): old items +0.029 [+0.005, +0.052] (en-US
|
||||
+0.049 [+0.023, +0.084] on 10 items, ja-JP +0.013 [-0.021, +0.037] on 12);
|
||||
new items -0.002 [-0.011, +0.007] pooled, but two opposite effects: en-US
|
||||
-0.017 [-0.027, -0.007] on 18 items and ja-JP +0.011 [+0.001, +0.022] on 20.
|
||||
So the old-versus-new contrast exists in en-US; in ja-JP old (+0.013) and new
|
||||
(+0.011) do not differ. Measured: the 14-item gain does not carry to the new
|
||||
en-US items. Inferred, not isolated: that it was in-sample register fit. The
|
||||
new items differ from the old in several ways at once (written free of the
|
||||
inventory, longer, a different scene convention, lower scores, a smaller
|
||||
vocabulary overlap with Train in en-US: 0.29 against 0.52) and were briefed to
|
||||
the same register as Train, by Claude as the old were. The 29% power figure
|
||||
stays the stated baseline of the 14-item corpus; no better arm is known on
|
||||
the new items, so the rule's power against a real gain is not re-measured.
|
||||
- The two classes are different strata (Soul s2 `register-stratum-shift`): the
|
||||
new items score lower (composite 0.41 against 0.64 pooled) so a pooled
|
||||
60-item mean mixes them; report old and new separately.
|
||||
- The self-preference effect is not measured (ruling
|
||||
`validation-growth-writer-claude-checked`). The new scenes use a different
|
||||
`in_group` convention from the old ones (follow-up
|
||||
`vgrow-scene-in-group-convention`), so the new-item scores are for scenes that
|
||||
will be re-annotated; the speaker-state store changes then (a run pins its
|
||||
digest), the corpus does not.
|
||||
|
||||
For `growth-base`, `weksa loop calibrate` (`docs/calibration.md`) reproduces from `run.rs`'s own
|
||||
scoring and accept rule the counts per class, the trial totals and the mean
|
||||
noise of this block: prompted 116 NoGain, 4 Accepted, 0 Regressed of 120;
|
||||
control-yes 60 of 60 Regressed, mild-1 19 of 60, mild-2 0 of 60; the
|
||||
Train-guide arm 51 Accepted, 189 NoGain, 0 Regressed of 240; noise 0.0451;
|
||||
items en-US n=28 skipped=7, ja-JP n=32 skipped=3. By class it adds: old items
|
||||
(`item:original*`) prompted 111/9/0, noise 0.1069, Train-guide 71 Accepted of
|
||||
240; new items (`item:vgrow*`) prompted 116/4/0, noise 0.0334, Train-guide 0
|
||||
Accepted and 74 Regressed of 240. The other figures of this block (35% with R
|
||||
removed, the noise range, the 0.0185 gain and 0.41 ratio, the bootstrap
|
||||
intervals, the per-item SDs, R's +0.024, the mild-arm duplicate counts and
|
||||
mean composite offsets, the Train-vocabulary overlap, the old/new class
|
||||
composites, the ten parse-refused item ids) were
|
||||
computed by scratch scripts outside git (Soul finding `evidence-outside-git`)
|
||||
and are not reproduced by the harness.
|
||||
|
||||
Recalibration on the relabelled scenes (`runs/growth-scene`, main d8afc4a; same
|
||||
panel, 35 live items per language, 0 refused, 5 prompted draws including the
|
||||
recorded one R, 2 mild, 4 Train-guide). It is not a replacement for the
|
||||
`growth-base` block above and no delta against it is drawn: the item set, the
|
||||
packets and the scenes changed, and encode was redrawn (the 98 encode prompts
|
||||
are byte-identical to growth-base, no encode answer is; the refusals fell from
|
||||
10 to 0 on the redraw, not through the scenes, which reach only the lowering
|
||||
prompts). Soul `cut-calibrate-harness.s3` re-derived all 33 counts and 3 noise
|
||||
terms below from the per-item answers without calling `calibrate`; they match.
|
||||
|
||||
Measured, and reproduced by `weksa loop calibrate` (trials: prompted 120, each
|
||||
mild 60, Train-guide 240; Accepted / NoGain / Regressed):
|
||||
|
||||
| class | prompted | noise | mild-1 Regressed | mild-2 Regressed | Train-guide |
|
||||
|---|---|---|---|---|---|
|
||||
| all (35 per language) | 11/100/9 | 0.0392 | 51 | 58 | 85/35/120 |
|
||||
| old (14) | 0/105/15 | 0.0844 | 60 | 60 | 40/80/120 |
|
||||
| new (21) | 10/97/13 | 0.0340 | 3 | 4 | 50/129/61 |
|
||||
|
||||
Measured by Soul scratch scripts outside git (not reproduced by the harness,
|
||||
except the R split in the first bullet, which `calibrate` prints as
|
||||
`prompted-r-candidate`, `prompted-r-base` and `prompted-r-free` since the
|
||||
`calibrate-report-r-involvement` cut; Soul re-ran growth-scene with it and the
|
||||
printed `all` lines read r-candidate 11/9/0, r-base 0/11/9, r-free 0/80/0, as
|
||||
below, in Accepted/NoGain/Regressed; likewise the per-arm Train-guide counts
|
||||
(`candidate=h1..h4`) and the mild arms' composite offsets from the prompted
|
||||
mean, R included (`offset`), which `calibrate` prints since
|
||||
`calibrate-arm-counts-and-mild-offsets` and which reproduce the figures below,
|
||||
Soul re-run on growth-scene):
|
||||
|
||||
- Every one of the 11 false accepts has R as the candidate (bases
|
||||
prompted-2, p4, p6); every one of the 9 false rejects has R as the base. The
|
||||
80 trials without R read 0 Accepted and 0 Regressed in every class (95% upper
|
||||
bound 4.5%). R scores above the other prompted draws (+0.012 en-US and +0.023
|
||||
ja-JP on all items), so R is not exchangeable with a repeat.
|
||||
Which of the two rates the live rule should be held to is undecided: the
|
||||
live loop meets R as the head's establishing lowering, so the R-candidate
|
||||
rate may be the real one for cycles, while the 80 R-free trials are the
|
||||
exchangeable repeat rate; neither number stands for the other.
|
||||
- The old/new split of the false-accept lives only in the 20 trials where R is
|
||||
the candidate, from 5 bases: new 10/20 [0.27, 0.73], old 0/20 [0.00, 0.17]
|
||||
(Clopper-Pearson); by base 3 of 5 against 0 of 5 (Fisher p 0.17). The
|
||||
10/120 against 0/120 comparison treats dependent trials as independent. The
|
||||
claim that the new items drive the prompted false-accept is not supported;
|
||||
the old items' larger noise term (2.4 times) raises their threshold, which
|
||||
alone can produce the gap.
|
||||
- Mild arms: they overlap 8 of 35 answers (en-US) and 9 (ja-JP) over the limit
|
||||
of 7. They do not degrade the new items (composite -0.004 en-US
|
||||
[-0.021, +0.012], +0.013 ja-JP for mild-1, +0.005 for mild-2); the Regressed counts come from the old
|
||||
en-US items (-0.072). The rule's sensitivity on the new items is unmeasured.
|
||||
- Train-guide pools unlike arms. h1 and h2 Regress in 120 of 120 trials; h3 and
|
||||
h4 gain (Accepted 45 and 40 of 60); on the new items h3 is Accepted 50 of 60
|
||||
and h4 0 of 60. The 35% pooled figure is not a power.
|
||||
|
||||
Extrapolated only: the rule's power at 35 items against any real gain beyond
|
||||
h3 and h4, and any false-accept bound on repeat draws (5 draws, one of them R).
|
||||
|
||||
### Smallest measurable distil slice (`distil-incontext`, not built)
|
||||
|
||||
Distil is a tuned lowerer measured against the prompted one; the tuned model
|
||||
needs a host (follow-up `distil-host-question-owed`). The smallest slice that
|
||||
measures whether Train pairs buy a gain with the rule that exists is
|
||||
training-free: an in-context arm, the prompted lowerer given Train
|
||||
(packet, text) pairs as few-shot examples, answered through the one prompt door
|
||||
and read by `loop relower` against three prompted repeats. Parts: 12b's
|
||||
Train-only export (follow-up `distil-export-at-freeze`, guarded against Test
|
||||
text) as the few-shot source; the arm's directory of answers; the existing
|
||||
floor and verdict. A weaker version ran on 14 items: a lowerer shown the 28
|
||||
Train sentences (no packets) beat the prompted draws in both languages and the
|
||||
rule Accepted it in 29% of 1120 trials. The slice is decisive only with the
|
||||
Validation growth above: at 14 items it can only fail to reject. It decides the
|
||||
fine-tune question in one direction: if in-context Train pairs do not clear the
|
||||
floor at 35 items, a tuned model's gain over the prompted one is not
|
||||
measurable with this corpus either.
|
||||
|
||||
Training pairs are Train only, at a frozen revision; the export is 12b.
|
||||
|
||||
## Lowering authorities (`golf-loop-lowerer-cut`, `table-retirement`)
|
||||
|
||||
Authority map of who decides what about a packet's wording. The first cut gave
|
||||
the loop a baseline from an English template table; cut `table-retirement`
|
||||
deleted that table, `lower()` and the CLI lowering command, so no deterministic path
|
||||
produces lowered text and the model's answer to `Prompt::lower` is the only
|
||||
wording owner. `lower.rs` keeps the entity port, `pronounce` and `phones`
|
||||
(`weksa pronounce`).
|
||||
Authority map for the smallest lowerer, written before its code (Imagination
|
||||
pass by the Weksa Self run, 2026-11-01). The cut exists to give the golf loop a
|
||||
measurable baseline from a packet: `lower` gives text, `score` gives numbers.
|
||||
|
||||
| Decision | Owner | Inputs | Outputs | Not the owner |
|
||||
|---|---|---|---|---|
|
||||
| Whether a packet exists | `validate` / `PacketStore::admit` (unchanged) | packet, inventory, corpus, entities | admitted packet or typed refusal | the lowerer |
|
||||
| Wording of a scored item in English (golf loop, `golf-loop-model-lowerer`) | the ModelPort's answer to `Prompt::lower` (`context.rs`), read as `LoweringDraft` (`encode.rs`) and held in `run::score_round`'s locals | the admitted view, the inventory at its revision, en-US entity forms | `{"text"}`, scored once, never stored | the corpus item, the scorer, the editor |
|
||||
| Wording of a packet in English (`weksa lower`, proof fixtures) | `crates/weksa/src/lower.rs`: `lower(&LoweringInput, &Inventory) -> Result<String, LowerError>` | the validated lowering view and the inventory at its revision | text, or a typed refusal naming the missing template | the corpus item, the scorer, the golf loop |
|
||||
| English template table (concept words, frame templates, speech-act openers) | the same module, as rows `(inventory id, gloss it speaks for, surface)` | none; it is data in code | rows the lowerer looks up | the inventory (it owns the ids and glosses, not the English) |
|
||||
| The inventory's concepts and frames | an inventory revision; here `inventory::proof_revision()` (rev 2), hand-seeded as `seed()` is | none | the 6 concepts and 3 frames `nibu-proof-001` and the consent-gated request packet name | the lowerer |
|
||||
| What a score counts | `Scorer::score` (unchanged) | output text, reference text | `ItemScore` | `weksa score`, which only reads text and calls it |
|
||||
| The proof packet | `packet::proof_packet()`, typed ids of rev 2, admitted by `weksa packet proof <store>` through `PacketStore::admit`. Not JSON: `Packet`'s serde is CultCache's positional tuple, and JSON in is the xenos boundary the cut 7 encoder owns | none | admitted packet | the CLI decides nothing about validity |
|
||||
|
||||
Decisions this map makes, and why:
|
||||
|
||||
- **`lower` takes `&LoweringInput`, not `&Packet`.** A `Packet` carries `trace`
|
||||
and `provenance.corpus_item`; the model page says the lowerer sees the packet
|
||||
without its trace and never the corpus item (`lowering-traced`,
|
||||
`leak-owned-by-flow-and-scorer-3`). `validate` already yields the view, so the
|
||||
CLI runs `validate` and hands it over. Cut 4 narrows the door to
|
||||
`PacketStore::admit`; this cut does not wait on it.
|
||||
- **The frame owns the verb phrase; a predication's concept must resolve but is
|
||||
not rendered.** Referent concepts supply nouns. A frame template names its
|
||||
roles by inventory gloss (`{agent}`), resolved against the inventory at the
|
||||
packet's revision, so a retired or re-glossed role cannot be silently
|
||||
mis-keyed. A row whose gloss differs from the inventory's entry for its id is
|
||||
a `LowerError`, so a table row cannot speak for a different meaning than its
|
||||
id now carries.
|
||||
- **Rendering rules, all deterministic and all from packet fields:** the
|
||||
discourse addressee renders "you" ("yourself" when it already filled a role
|
||||
in the same predication), other referents render "the <concept word>", a
|
||||
predication filling a role renders "that", the speech-act row supplies an
|
||||
optional opener, sentences are capitalised and end in a full stop.
|
||||
Entity-bearing referents render by concept word: the lowerer does not read
|
||||
the entity store in this cut (follow-up: entity forms in the lowerer).
|
||||
- **No style, no register, no features.** Hedge, certainty, modality and
|
||||
polarity are not rendered, so the baseline scores what meaning alone buys.
|
||||
A lowerer that ignores `polarity: negative` would assert the opposite, so
|
||||
`lower` refuses any packet that carries a feature, relation or extension it
|
||||
does not render rather than render it wrong (`packet-owns-meaning`); features arrive as templates
|
||||
learn them.
|
||||
- **Deleted by later cuts, not this one:** the table in `lower.rs` and
|
||||
`proof_revision()` are temporary owners. Cut 5 (`language-ontology`) moves
|
||||
the table to `weksa.ontology_entry` documents selected by the target
|
||||
profile; cut 7 replaces `proof_revision()` with the loop's minting round.
|
||||
Nothing is deleted today because no earlier lowerer exists; the YAML
|
||||
`examples/english-lowering/` hand-lowerings are fixtures, not owners, and
|
||||
stay.
|
||||
- **`weksa score` is a thin reader of `Scorer::score`**: `weksa score <item>...
|
||||
[--output FILE]` embeds the output text once against every named item. It
|
||||
stores nothing (Score documents arrive with cut 7) and gates nothing.
|
||||
|
|
@ -646,15 +427,14 @@ One line per cut; specs exist for the cuts about to run (2d and 4, siblings on `
|
|||
5. `language-ontology`, in sequential cuts on `d9ebbcf`. 5a `language-ontology` (spec r1): `weksa.ontology_entry`, `OntologyStore`, `ontology::select` over the view's `Stance` and `Discourse` features, `Prompt::lower` printing the selected entries of the item's language, `RunRecord` pinning the ontology store (keys 15 and 16), `weksa ontology admit|dump`; `ontology.rs` joins `PROMPT_SOURCE_DIGEST`. 5b `language-ontology-seed` (spec r1, after 5a): Model-annotated en-US and ja-JP seed entries drafted by an isolated model, `data/target-language-ontology/`, `.weksa/cultural-ontology/` and `schemas/target-language-cultural-ontology.md` deleted. Lost until 5c': keigo, hierarchy and uchi-soto hang on the scene relation from 5c', so ja-JP politeness is still the lowerer's guess. 5c' `language-ontology-scene` (spec r1, after 5b): the run pins the `SpeakerStateStore` (keys 17 and 18, `Drift(SpeakerState)`), `RunStores::assembled` is the one door that reads the item's scene into a loop view, `select` reads slot `Scene`, `Prompt::lower` refuses a view whose scene was never read, `weksa scene put|dump` and `weksa inventory speaker-scene` (rev 4 in data/original and data/daodejing, rev 3 in data/interlingua, which holds no Dao revision), Model-annotated keeper scenes and Scene-conditioned entries for `data/original`. 5c `language-ontology-view-assembly` (follow-up, now only the Speaker read): `select` widens to slot `Speaker`; waits on `speaker-scene-seeds`. 5d `language-ontology-communities` (follow-up): `weksa.community` built fresh (`data/cultural-ontology/` is deleted by 5e), community ids on `weksa.speaker`, community conditions; waits on 5c and question `persona-speech-community-home`.
|
||||
5e. `delete-cultural-ontology` (steward ruling, 2026-11-13): `data/cultural-ontology/` (five draft YAML profile files and a README; `old-norse-edda-source-tradition.yaml` did not parse) deleted. Nothing in `crates/`, tests, scripts or CI read it; `examples/persona-lowering/brokkr-edda-voice/` cites its paths as text only (the one test that reads that example reads `lowered-output.yaml`). The typed `weksa.community` of follow-up `language-ontology-communities` is built fresh under cut 5; follow-up `edda-referent-yaml-parse` is moot.
|
||||
6. `pd-importer`: public-domain play and fiction dialogue into the corpus with speaker, scene group, edition provenance, and Speaker and Scene annotations by the ruled annotator. Waits on 4, follow-up `gutenberg-terms` and question `pd-speaker-annotation`.
|
||||
6a. `pd-name-spans` (spec r1): `weksa corpus import <work> <names>` mints a work's cast as `PublicDomain` entities with forms in the work's language and adds each line a name-span answer covers, speaker from the work file, spans from `[[entity|form]]` markup, labelled `names_by` (Model or Operator) per `docs/name-span-annotation.md`. Speaker and Scene documents, prior turns and fiction speaker attribution stay with 6.
|
||||
7a. `loop-context-builder`: `context.rs` (`TrainItems`, `EncoderOffer`, `Prompt`: corpus text reaches a model call only through `Prompt::mint` over live Train items or `Prompt::encode` over one offered item; instructions are the consts `MINT_INSTRUCTIONS` and `ENCODE_INSTRUCTIONS` in `context.rs`; `Checkpoint` has no public constructor, offers each item once, and its offers borrow it (the gate is typed `TestReadings` and Test offers on the round path; operator tools such as `weksa corpus dump` and `weksa score` still read corpus text of any split); prior turns print the held Train text), `SplitScheme::live`, `CorpusItem::cited_entities` (one owner of the id set `PacketStore::admit` and the offer share), and checkpoint-only Test readings (`Checkpoint`, `TestReadings`; `Aggregate` and `leak_diagnostic` carry no Test). Library only; since 7b `TrainItems::from_corpus` and `EncoderOffer::for_round` are crate-private and `RunStores` is their one public producer. Merges follow-ups `loop-context-builder-2` and `scorer-test-readings-type`. (spec r1)
|
||||
7b. `golf-loop-round` (spec r1; branch `weksa-lowering/golf-loop-round`): the smallest loop that scores one round. `run.rs`: `RunStores` pins the corpus and entity stores of a run by canonical path and FNV-1a 64 digest at `create`, reopens only from `<root>/run.cc` and refuses drift (corpus, entities, `PROMPT_SOURCE_DIGEST` of `context.rs`, a second pin on `lower.rs` retired in 7d, model, embedder); `round` encodes every live Train and Validation item through a `ModelPort` (`model.rs`; the one adapter `AnswerFiles` writes `<digest>.prompt` and reads `<digest>.answer`, so the model is the Claude session), reads each answer into a `PacketDraft` (`encode.rs`, the one place a model's JSON is read), admits through `PacketStore::admit` into `<root>/round-<n>/packets.cc`, lowers, scores once, and keeps a `RoundRecord` (`weksa.loop_round`, no text, no Test; Train rows, Validation only as means and refusal counts). `weksa loop open|round`. Not here: the spec-edit step, accept rule and composite, noise floor, Score and lowering documents, a subprocess adapter, the checkpoint door, a model lowerer (follow-ups `golf-loop-spec-edit`, `golf-loop-accept-rule`, `golf-loop-score-documents`, `golf-loop-subprocess-adapter`, `golf-loop-checkpoint-door-bound`, `golf-loop-model-lowerer`). `packet-store-inventory-binding` is met for loop packets only (`RunStores` admits with the run's inventory); `validate`, `packet proof|dao` and `lower` still take caller stores. Waits on 7a, `checkpoint-gate`, 4b.
|
||||
7c. `golf-loop-edit-accept` (spec r1; branch `weksa-lowering/golf-loop-edit-accept`): one edit-accept cycle. The run works on its own copy of the inventory (`create` copies the caller's file to `<root>/inventory.cc`, refusing a root that already holds a file of that name, and pins its digest as `RunRecord` key 11; `RunRecord.inventory` is provenance; a `run.cc` from before has no key 11 and does not open); the head is derived from the latest Accepted `Decision`. `weksa loop cycle` asks the editor for one inventory edit from `Prompt::mint(train, inventory, rev, feedback)` (Train blocks, the inventory listing and an `EditFeedback` line: whether the last edit was kept and the head's Validation composite rounded to `LADDER_STEP`, the Ladder release of Blum and Hardt 2015), reads it as an `EditDraft` (`encode.rs`; ids and revisions are the store's, `into_revision`), admits it through `InventoryStore::admit_revision` into `<root>/cycle-<k>/inventory.cc`, runs a candidate round under it, and `decide`s on Validation against the head's establishing round past a floor (never under one `LADDER_STEP`; from cut `cycle-floor-paired` the paired floor over rounds 1 to `FLOOR_ARMS_MIN` + 1, so a cycle needs four recorded rounds, where 7c measured the spread between rounds 1 and 2). An edit that fails is a rejected `Decision`, not an error. `RoundRecord` gains keys 16 (inventory digest) and 17 (cycle); an encode answer that is not UTF-8 is that item's parse refusal. Not here: Score and lowering documents (`golf-loop-score-docs`), Train rows in the edit prompt (`golf-loop-edit-train-feedback`), a paired floor (`golf-loop-paired-floor`), the checkpoint door and merging to `data/` (`golf-loop-checkpoint-door-bound`, `golf-loop-freeze-merge`), a model lowerer (landed as 7d: until then an entry an edit added had no lowering row). Waits on 7b.
|
||||
7d. `golf-loop-model-lowerer` (spec r1; branch `weksa-lowering/golf-loop-model-lowerer`): the round lowers through the `ModelPort`. `Prompt::lower` (`context.rs`) takes a `LoweringInput` (no text, key, group or speaker getter), the item's speaker id, the inventory at the view's revision and the item language's entity forms, and prints `LOWER_INSTRUCTIONS`, the meaning of the packet, the entities line and the inventory listing; the item key goes only to `item_keys`, and the speaker id never prints: a referent citing the item's speaker holds the fixed token `entity:speaker` (`SPEAKER_TOKEN`, a constant the same for every speaker and item, never derived from an id) and the entities map holds the speaker's forms under that token. The promise guards the id that names an entity of this item; the speaker's forms and the role token do print, because forms are shared by every item of the language (follow-up `speaker-alias-token-in-lowering-prompt`, which restored the lowerer's ability to name its speaker after #84 removed it). A speaker the language has no form for, or the port lacks, does not refuse: its referents print no entity and the map has no entry. A referent citing the real id `entity:speaker` is refused (`LowerError::SpeakerTokenTaken`); the entity store does not reserve it. The answer is `{"text"}`, read as `LoweringDraft` in `encode.rs`, held in `score_round`'s locals and scored once; it is never put in `run.cc`, a `RoundRecord`, a `Decision` or `EditFeedback`. A round has two answer phases (every encode prompt, then every lowering prompt), all or nothing: while any prompt is unanswered `packets.cc` is discarded and nothing reaches `run.cc`. `lower::lower` and the template table leave the loop (they remain `weksa lower`'s; follow-up `table-retirement`), so an entry an edit adds can be said and a cycle can buy a gain. One source pin remains: `PROMPT_SOURCE_DIGEST` covers `context.rs`, `split.rs` and `lower.rs` (`RunRecord` key 7 and `RoundRecord` key 3 are retired). The run's record pins `LowererReach` (`weksa loop open --lowerer-reach briefed-subagent|tool-less-relay`, `RunRecord` key 12) and every printed round and cycle line says it; a briefed-subagent run says its numbers are smoke-round only (rulings `lowerer-call-reach-toolless-relay`, `dao-round-seed-inventory`). A lowering is refused at `Lower` when blank, over `MAX_LOWERING_BYTES` (4096) or holding a control character other than a line break or tab; `PROMPT_SOURCE_DIGEST` also covers `packet.rs`. Not here: per-item lowering text documents (`golf-loop-score-docs`), the subprocess adapter. Waits on 7c.
|
||||
7. `golf-loop-en` (7b, 7c and 7d landed the round, `ModelPort` with `AnswerFiles`, encoder and lowering prompts, template digest, round records and the edit-accept cycle; the rest remains): the packet store bound to one inventory store everywhere (`packet-store-inventory-binding`), Score documents (`golf-loop-score-docs`, `golf-loop-score-documents`), the accept rule (`golf-loop-accept-rule`), the checkpoint door and freeze merge (`golf-loop-checkpoint-door-bound`, `golf-loop-freeze-merge`). No subprocess adapter and no detached unit: `golf-loop-in-claude` and `encoder-isolation-subagent-per-prompt` rule them out. Waits on 3, 5 and 6.
|
||||
7c. `golf-loop-edit-accept` (spec r1; branch `weksa-lowering/golf-loop-edit-accept`): one edit-accept cycle. The run works on its own copy of the inventory (`create` copies the caller's file to `<root>/inventory.cc`, refusing a root that already holds a file of that name, and pins its digest as `RunRecord` key 11; `RunRecord.inventory` is provenance; a `run.cc` from before has no key 11 and does not open); the head is derived from the latest Accepted `Decision`. `weksa loop cycle` asks the editor for one inventory edit from `Prompt::mint(train, inventory, rev, feedback)` (Train blocks, the inventory listing and an `EditFeedback` line: whether the last edit was kept and the head's Validation composite rounded to `LADDER_STEP`, the Ladder release of Blum and Hardt 2015), reads it as an `EditDraft` (`encode.rs`; ids and revisions are the store's, `into_revision`), admits it through `InventoryStore::admit_revision` into `<root>/cycle-<k>/inventory.cc`, runs a candidate round under it, and `decide`s on Validation against the head's establishing round past a floor measured as the spread between rounds 1 and 2 (never under one `LADDER_STEP`). An edit that fails is a rejected `Decision`, not an error. `RoundRecord` gains keys 16 (inventory digest) and 17 (cycle); an encode answer that is not UTF-8 is that item's parse refusal. Not here: Score and lowering documents (`golf-loop-score-docs`), Train rows in the edit prompt (`golf-loop-edit-train-feedback`), a paired floor (`golf-loop-paired-floor`), the checkpoint door and merging to `data/` (`golf-loop-checkpoint-door-bound`, `golf-loop-freeze-merge`), a model lowerer (`golf-loop-model-lowerer-next`; until it lands an entry an edit adds has no lowering row, so a cycle gains only by retiring entries or adding ones the encoder does not cite). Waits on 7b.
|
||||
7d. `golf-loop-model-lowerer` (spec r1; branch `weksa-lowering/golf-loop-model-lowerer`): the round lowers through the `ModelPort`. `Prompt::lower` (`context.rs`) takes a `LoweringInput` (no text, key, group or speaker getter), the inventory at the view's revision and the en-US entity forms, and prints `LOWER_INSTRUCTIONS`, the meaning of the packet, the entities line and the inventory listing; the item key goes only to `item_keys`. The answer is `{"text"}`, read as `LoweringDraft` in `encode.rs`, held in `score_round`'s locals and scored once; it is never put in `run.cc`, a `RoundRecord`, a `Decision` or `EditFeedback`. A round has two answer phases (every encode prompt, then every lowering prompt), all or nothing: while any prompt is unanswered `packets.cc` is discarded and nothing reaches `run.cc`. `lower::lower` and the template table leave the loop (they remain `weksa lower`'s; follow-up `table-retirement`), so an entry an edit adds can be said and a cycle can buy a gain. One source pin remains: `PROMPT_SOURCE_DIGEST` covers `context.rs`, `split.rs` and `lower.rs` (`RunRecord` key 7 and `RoundRecord` key 3 are retired). The run's record pins `LowererReach` (`weksa loop open --lowerer-reach briefed-subagent|tool-less-relay`, `RunRecord` key 12) and every printed round and cycle line says it; a briefed-subagent run says its numbers are smoke-round only (rulings `lowerer-call-reach-toolless-relay`, `dao-round-seed-inventory`). A lowering is refused at `Lower` when blank, over `MAX_LOWERING_BYTES` (4096) or holding a control character other than a line break or tab; `PROMPT_SOURCE_DIGEST` also covers `packet.rs`. Not here: per-item lowering text documents (`golf-loop-score-docs`), the subprocess adapter. Waits on 7c.
|
||||
7. `golf-loop-en` (7b and 7c landed the round, `ModelPort`, encoder prompt, template digest, round records and the edit-accept cycle; the rest remains): the packet store bound to one inventory store everywhere (`packet-store-inventory-binding`), a subprocess adapter, Score documents, `weksa score` in the loop, the detached unit on Yggdrasil. Waits on 3, 5, 6 and follow-up `claude-on-yggdrasil`.
|
||||
8. `style-axis`: a style-embedding score behind the scorer port. Waits on 3.
|
||||
9. `ja-panel`: ja-JP into the loop's panel, in two cuts on `e9cbd9b`. 9a `ja-panel-loop` (spec r1): language is the item's and the panel the run's: `Prompt::lower` takes the item's language and prints it on a language line (no prompt names English), entity forms are read in that language, `RunRecord` pins the panel (`weksa loop open --panel`), offers, mint and recall read only panel items, round means, floors and readings are per panel language, the accept rule runs `decide` per language, the recall split works on unspaced scripts, and `weksa corpus add` has no default language. 9b `ja-panel-corpus` (spec r1, after 9a): the ja-JP slice of `data/original`, model-written Japanese Train and Validation passages and eight Aozora Bunko public-domain Test sentences with full provenance, and their entities. Cut 5 is not a prerequisite: neither language lowers with ontology entries until cut 5 gives both theirs.
|
||||
10. `conlang-lexicon`: the first conlang's lexicon placed at concept embeddings, its morphology data, its ontology entries and the gloss reader. Waits on 3, 5 and question `first-conlang`.
|
||||
11. `convergence-freeze`: the convergence test, `Checkpoint`'s one door (built from the convergence window over the persisted round records), the freeze, the re-encode into training pairs. Waits on 7, 9 and 10.
|
||||
12. `distil`, three cuts. 12a `distil-slice` (relower and the prompted baseline; spec r1). 12b `distil-export`: Train-only prompt/completion JSONL at a frozen revision, Test-text guarded (follow-up `distil-export-at-freeze`); waits on 11. 12c `distil-train`: waits on 12b and the host question (follow-up `distil-host-question-owed`).
|
||||
12. `distil`: fine-tune a lowerer on the frozen training set. Waits on 11 and a host question asked then.
|
||||
13. `live-lowering`: agents emit packets with stance; Weksa reads speaker state from persona state (follow-up `persona-state-speech-community`) and lowers for the reader. Waits on 11.
|
||||
|
|
|
|||
|
|
@ -24,17 +24,6 @@
|
|||
"$ref": "#/$defs/NameSpan"
|
||||
}
|
||||
},
|
||||
"names_by": {
|
||||
"description": "Who placed `names`: the annotator of the intake that wrote them. `None`\nwhen nothing records one (the cast seeds, `weksa corpus add`, the Dao De\nJing bed); it labels the spans, never the line or its speaker.",
|
||||
"anyOf": [
|
||||
{
|
||||
"$ref": "#/$defs/Annotator"
|
||||
},
|
||||
{
|
||||
"type": "null"
|
||||
}
|
||||
]
|
||||
},
|
||||
"prior_turns": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
|
|
@ -74,41 +63,6 @@
|
|||
"names"
|
||||
],
|
||||
"$defs": {
|
||||
"Annotator": {
|
||||
"description": "Who annotated a document. A model's generator is an attestation string, held\nto the same form as every provenance string.",
|
||||
"oneOf": [
|
||||
{
|
||||
"type": "string",
|
||||
"enum": [
|
||||
"Operator"
|
||||
]
|
||||
},
|
||||
{
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"Model": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"family": {
|
||||
"$ref": "#/$defs/ModelFamily"
|
||||
},
|
||||
"generator": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"family",
|
||||
"generator"
|
||||
]
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"Model"
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
"EntityId": {
|
||||
"type": "string",
|
||||
"pattern": "^entity:[a-z0-9]([a-z0-9-]{0,46}[a-z0-9])?$"
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
{
|
||||
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
||||
"title": "RoundRecord",
|
||||
"description": "One scored round. It holds no text and no Test reading: per-item rows for\nTrain only; Validation as means and refusal counts by stage, and as\nper-item scores (numbers only, private to this module). Only `run::round`\nbuilds one.\n\n```\nfn f(r: &weksa::run::RoundRecord) -> u32 { r.n() }\n```\n\nEvery field is given, so the literal below fails only on privacy; its twin\nis the same literal in the unit test `a_round_record_literal_compiles_in_the_lib`.\n\n```compile_fail,E0451\nuse weksa::run::RoundRecord;\nfn f() -> RoundRecord {\n RoundRecord {\n n: 1,\n inventory_rev: 1,\n prompt_digest: String::new(),\n corpus_digest: String::new(),\n entity_digest: String::new(),\n model: String::new(),\n embedder: String::new(),\n chrf_version: String::new(),\n calls: vec![],\n train: vec![],\n inventory_digest: String::new(),\n cycle: None,\n admit_rules: vec![],\n parse_reasons: vec![],\n own_family: 0,\n languages: vec![],\n validation_scores: vec![],\n }\n}\n```",
|
||||
"description": "One scored round. It holds no text and no Test reading: per-item rows for\nTrain only, Validation only as means and refusal counts by stage. Only\n`run::round` builds one.\n\n```\nfn f(r: &weksa::run::RoundRecord) -> u32 { r.n() }\n```\n\nEvery field is given, so the literal below fails only on privacy; its twin\nis the same literal in the unit test `a_round_record_literal_compiles_in_the_lib`.\n\n```compile_fail,E0451\nuse weksa::run::RoundRecord;\nfn f() -> RoundRecord {\n RoundRecord {\n n: 1,\n inventory_rev: 1,\n prompt_digest: String::new(),\n corpus_digest: String::new(),\n entity_digest: String::new(),\n model: String::new(),\n embedder: String::new(),\n chrf_version: String::new(),\n calls: vec![],\n train: vec![],\n inventory_digest: String::new(),\n cycle: None,\n admit_rules: vec![],\n parse_reasons: vec![],\n own_family: 0,\n languages: vec![],\n }\n}\n```",
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"admit_rules": {
|
||||
|
|
@ -87,14 +87,6 @@
|
|||
"items": {
|
||||
"$ref": "#/$defs/TrainRow"
|
||||
}
|
||||
},
|
||||
"validation_scores": {
|
||||
"description": "Each panel language's live Validation scores in corpus order, a refused\nitem as 0. Private with no getter: only `run.rs` (the floor) reads them,\nso a leak outside it is a compile error. A run from before has none.",
|
||||
"type": "array",
|
||||
"default": [],
|
||||
"items": {
|
||||
"$ref": "#/$defs/LanguageScores"
|
||||
}
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
|
|
@ -131,27 +123,6 @@
|
|||
"items"
|
||||
]
|
||||
},
|
||||
"ItemScore": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"chrf": {
|
||||
"description": "chrF of the output against the reference.",
|
||||
"type": "number",
|
||||
"format": "double"
|
||||
},
|
||||
"meaning": {
|
||||
"description": "Embedding cosine of the output and the reference; `None` when either\nis empty after trimming.",
|
||||
"type": [
|
||||
"number",
|
||||
"null"
|
||||
],
|
||||
"format": "double"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"chrf"
|
||||
]
|
||||
},
|
||||
"LanguageRound": {
|
||||
"description": "One panel language's readings in a round: the means over that language's\nitems only (a refused item counts 0) and how many items lowered and scored.",
|
||||
"type": "object",
|
||||
|
|
@ -190,25 +161,6 @@
|
|||
"validation_refused"
|
||||
]
|
||||
},
|
||||
"LanguageScores": {
|
||||
"description": "One panel language's Validation scores in a round, in corpus order: numbers\nonly, no item key and no text. Only `run.rs` reads them (the paired floor).",
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"language": {
|
||||
"type": "string"
|
||||
},
|
||||
"scores": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"$ref": "#/$defs/ItemScore"
|
||||
}
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"language",
|
||||
"scores"
|
||||
]
|
||||
},
|
||||
"Outcome": {
|
||||
"oneOf": [
|
||||
{
|
||||
|
|
|
|||
16
scripts/publish-show-working.sh
Executable file
16
scripts/publish-show-working.sh
Executable file
|
|
@ -0,0 +1,16 @@
|
|||
#!/usr/bin/env bash
|
||||
# Build the "Show her working" page from the real lowerer and scorer, then publish it as a Mind preview.
|
||||
# Run from the repository root, in a Mind's Self run (it writes only /srv/minds-web/<mind>/).
|
||||
#
|
||||
# scripts/publish-show-working.sh [--no-publish]
|
||||
#
|
||||
# Needs cargo, python3 and an Ollama embedder at 127.0.0.1:11434 (qwen3-embedding:0.6b): the scorer is not stubbed.
|
||||
# publish-mind-preview.sh lives in the gamecult-ops checkout: set GAMECULT_OPS to it (default ../gamecult-ops).
|
||||
set -euo pipefail
|
||||
[ -f Cargo.toml ] && [ -d tools/show-working ] || { echo "run from the Weksa repository root" >&2; exit 2; }
|
||||
out=${SHOW_WORKING_OUT:-tools/show-working/out}
|
||||
rm -rf "$out"
|
||||
python3 -I tools/show-working/build.py "$out"
|
||||
[ "${1:-}" = --no-publish ] && { echo "built $out"; exit 0; }
|
||||
ops=${GAMECULT_OPS:-../gamecult-ops}
|
||||
exec "$ops/scripts/publish-mind-preview.sh" "$out" weksa-show-working
|
||||
|
|
@ -1,99 +0,0 @@
|
|||
"""Agreement of annotator A, B, the older labels and the round-1 encoder. Run it BEFORE the
|
||||
rubric r1 revisions are put: the older labels are the store's latest revision then.
|
||||
Standard library only. Usage: as build_briefs.py, plus ROUND1=<round-1 dir of the run>."""
|
||||
import re,sys,subprocess,json,glob,os
|
||||
import os
|
||||
W=os.environ.get("WEKSA","target/debug/weksa") # the weksa binary
|
||||
R=os.getcwd() # run from the repo root
|
||||
S=os.environ.get("SCENE_SCRATCH","scene-scratch")+"/" # A-*.jsonl, B-*.jsonl, briefs; never committed
|
||||
A=["--corpus","data/original/corpus.cc","--entities","data/original/entity.cc","--inventory","data/original/inventory.cc","--speaker-state","data/original/speaker-state.cc"]
|
||||
def run(*a): return subprocess.run([W]+A+list(a),cwd=R,capture_output=True,text=True).stdout.split("\n")
|
||||
out=run("corpus","dump")
|
||||
items=[]
|
||||
for i,l in enumerate(out):
|
||||
m=re.match(r'^item:(\S+) \[(\S+) \S+ group=(\S+) (\w+)\]$',l)
|
||||
if m and m.group(4)!="Test":
|
||||
t=out[i+1].strip(); t=json.loads(t) if '\\' in t else t[1:-1]
|
||||
items.append(dict(id=m.group(1),lang=m.group(2),group=m.group(3),text=t,new=m.group(1).startswith("vgrow")))
|
||||
G={x['group']:x for x in items}
|
||||
assert len(G)==98
|
||||
# scene dump: latest and @1 per group
|
||||
sd=run("scene","dump"); lab={}
|
||||
for i,l in enumerate(sd):
|
||||
m=re.match(r'^scene:(\S+)@(\d+) rev:\d+ Model \S+ (.*) \[entity:keeper\]$',l)
|
||||
if m:
|
||||
f=re.search(r'relative_status=(\w+) intimacy=(\d+) in_group=(\w+)',sd[i+1])
|
||||
lab.setdefault(m.group(1),{})[int(m.group(2))]=dict(rs=f.group(1),im=int(f.group(2)),ig=f.group(3)=="true",gen=m.group(3))
|
||||
old={g:v[max(v)] for g,v in lab.items()}
|
||||
def load(f): return {json.loads(l)['group']:json.loads(l) for l in open(S+f+".jsonl")}
|
||||
Aa={**load("A-en"),**load("A-ja")}; Bb={**load("B-en"),**load("B-ja")}
|
||||
assert set(Aa)==set(G)==set(Bb)
|
||||
def kappa(x,y):
|
||||
n=len(x);
|
||||
if n==0: return float('nan')
|
||||
po=sum(a==b for a,b in zip(x,y))/n
|
||||
pa=sum(x)/n; pb=sum(y)/n
|
||||
pe=pa*pb+(1-pa)*(1-pb)
|
||||
return float('nan') if pe==1 else (po-pe)/(1-pe)
|
||||
def tab(x,y):
|
||||
return "[TT=%d TF=%d FT=%d FF=%d]"%(sum(a and b for a,b in zip(x,y)),sum(a and not b for a,b in zip(x,y)),sum((not a) and b for a,b in zip(x,y)),sum((not a) and (not b) for a,b in zip(x,y)))
|
||||
def cmp(name,P,Q,gs,bkey=None):
|
||||
# P,Q: dict group-> record with keys addressed(optional) relative_status intimacy in_group
|
||||
def rs(r): return r.get('relative_status',r.get('rs'))
|
||||
def im(r): return r.get('intimacy',r.get('im'))
|
||||
def ig(r): return r.get('in_group',r.get('ig'))
|
||||
n=len(gs)
|
||||
if n==0: print(f"{name}: n=0"); return
|
||||
e=lambda f: sum(f(P[g])==f(Q[g]) for g in gs)
|
||||
s=f"{name}: n={n} rs_eq={e(rs)}/{n} ig_eq={e(ig)}/{n} im<=150={sum(abs(im(P[g])-im(Q[g]))<=150 for g in gs)}/{n}"
|
||||
s+=f" ig_kappa={kappa([ig(P[g]) for g in gs],[ig(Q[g]) for g in gs]):.2f} ig_tab(A.row,B.col)={tab([ig(P[g]) for g in gs],[ig(Q[g]) for g in gs])}"
|
||||
if all('addressed' in P[g] and 'addressed' in Q[g] for g in gs):
|
||||
s+=f" addr_eq={e(lambda r:r['addressed'])}/{n} addr_kappa={kappa([P[g]['addressed'] for g in gs],[Q[g]['addressed'] for g in gs]):.2f} addr_tab={tab([P[g]['addressed'] for g in gs],[Q[g]['addressed'] for g in gs])}"
|
||||
print(s)
|
||||
L={"en-US":[g for g in G if G[g]['lang']=="en-US"],"ja-JP":[g for g in G if G[g]['lang']=="ja-JP"],"pooled":list(G)}
|
||||
print("== (1) A vs B")
|
||||
for k,gs in L.items(): cmp(k,Aa,Bb,gs)
|
||||
oldg=[g for g in G if not G[g]['new']]; newg=[g for g in G if G[g]['new']]
|
||||
print("== (2) blind check: A vs old latest, the 56")
|
||||
for k,gs in L.items():
|
||||
gg=[g for g in gs if g in oldg]
|
||||
cmp(k+" all",Aa,old,gg)
|
||||
cmp(k+" A.addr=true",Aa,old,[g for g in gg if Aa[g]['addressed']])
|
||||
cmp(k+" A.addr=false",Aa,old,[g for g in gg if not Aa[g]['addressed']])
|
||||
print("differing in_group (old->A):")
|
||||
for g in oldg:
|
||||
if old[g]['ig']!=Aa[g]['in_group']: print(" ",g,old[g]['ig'],"->",Aa[g]['in_group'],"addr",Aa[g]['addressed'])
|
||||
print("differing any label, old vs A:")
|
||||
for g in oldg:
|
||||
o=old[g];a=Aa[g]
|
||||
if (o['rs'],o['im'],o['ig'])!=(a['relative_status'],a['intimacy'],a['in_group']): print(" %s old %s/%d/%s A %s/%d/%s addr=%s"%(g,o['rs'],o['im'],o['ig'],a['relative_status'],a['intimacy'],a['in_group'],a['addressed']))
|
||||
print("== (3) A vs vgrow @1, the 42")
|
||||
for k,gs in L.items(): cmp(k,Aa,{g:lab[g][1] for g in newg},[g for g in gs if g in newg])
|
||||
print("== (4) A addressed vs round-1 encoder addressee")
|
||||
enc={}
|
||||
RD=os.environ.get("ROUND1","runs/growth-base/round-1")+"/"
|
||||
for p in glob.glob(RD+"*.prompt"):
|
||||
pt=open(p).read()
|
||||
if not pt.startswith("Encode the line"): continue
|
||||
ap=p[:-7]+".answer"
|
||||
if not os.path.exists(ap): continue
|
||||
# the line text; take the item whose text appears in the prompt
|
||||
hit=[g for g in G if G[g]['text'] in pt]
|
||||
if len(hit)!=1: continue
|
||||
try: a=json.load(open(ap))
|
||||
except Exception: continue
|
||||
enc[hit[0]]=a.get('discourse',{}).get('addressee') is not None
|
||||
print("encoder answers matched:",len(enc),"of 98")
|
||||
for k,gs in list(L.items()):
|
||||
gg=[g for g in gs if g in enc]
|
||||
print(k,"n=",len(gg),"A.row,enc.col",tab([Aa[g]['addressed'] for g in gg],[enc[g] for g in gg]),"kappa=%.2f"%kappa([Aa[g]['addressed'] for g in gg],[enc[g] for g in gg]))
|
||||
for nm,grp in (("old",oldg),("new",newg)):
|
||||
gg=[g for g in grp if g in enc]; print(nm,"enc-addressee true:",sum(enc[g] for g in gg),"of",len(gg),"; A addressed true among old/new:",sum(Aa[g]['addressed'] for g in grp),"of",len(grp))
|
||||
print("== (5) in_group true counts, old/new x addressed, before -> after")
|
||||
for nm,grp in (("old56",oldg),("new42",newg)):
|
||||
for ad in (True,False):
|
||||
gg=[g for g in grp if Aa[g]['addressed']==ad]
|
||||
before=sum(old[g]['ig'] for g in gg); after=sum(Aa[g]['in_group'] for g in gg)
|
||||
print(f"{nm} A.addressed={ad}: n={len(gg)} in_group true before={before} after={after}")
|
||||
print("totals before",sum(old[g]['ig'] for g in G),"after",sum(Aa[g]['in_group'] for g in G))
|
||||
print("A addressed true:",sum(Aa[g]['addressed'] for g in G),"B:",sum(Bb[g]['addressed'] for g in G))
|
||||
|
|
@ -1,37 +0,0 @@
|
|||
"""Build the two annotator briefs (rubric r1 section + one language's shuffled live
|
||||
sentences), print the Test-leak count of each (must be 0) and its sha256.
|
||||
Standard library only. Usage: from the repo root, WEKSA=... SCENE_SCRATCH=dir python3 -I scripts/scene-annotation/build_briefs.py"""
|
||||
import re,sys,subprocess,random,json,hashlib,os
|
||||
import os
|
||||
W=os.environ.get("WEKSA","target/debug/weksa") # the weksa binary
|
||||
R=os.getcwd() # run from the repo root
|
||||
S=os.environ.get("SCENE_SCRATCH","scene-scratch")+"/" # A-*.jsonl, B-*.jsonl, briefs; never committed
|
||||
A=["--corpus","data/original/corpus.cc","--entities","data/original/entity.cc","--inventory","data/original/inventory.cc","--speaker-state","data/original/speaker-state.cc"]
|
||||
out=subprocess.run([W]+A+["corpus","dump"],cwd=R,capture_output=True,text=True).stdout.split("\n")
|
||||
live=[];test=[]
|
||||
for i,l in enumerate(out):
|
||||
m=re.match(r'^item:(\S+) \[(\S+) \S+ group=(\S+) (\w+)\]$',l)
|
||||
if not m: continue
|
||||
t=out[i+1].strip()
|
||||
assert t.startswith('"') and t.endswith('"')
|
||||
t=json.loads(t) if '\\' in t else t[1:-1]
|
||||
if m.group(4)=="Test": test.append(t)
|
||||
else: live.append((m.group(2),m.group(3),t))
|
||||
assert len(live)==98,len(live)
|
||||
rub=open(R+"/docs/scene-annotation.md").read()
|
||||
sec=rub[rub.index("## Rubric r1"):]
|
||||
# rubric section ends at next "## " heading
|
||||
rest=sec[len("## Rubric r1"):]
|
||||
nx=rest.find("\n## ")
|
||||
sec=sec[:len("## Rubric r1")+(nx if nx>=0 else len(rest))].strip()+"\n"
|
||||
def leaks(brief,text):
|
||||
w=text.split(); c=list(text)
|
||||
return text in brief or any(" ".join(w[k:k+5]) in brief for k in range(len(w)-4)) or (len(w)==1 and any("".join(c[k:k+12]) in brief for k in range(len(c)-11)))
|
||||
for lang in ("en-US","ja-JP"):
|
||||
rows=[(g,t) for (l,g,t) in live if l==lang]
|
||||
assert len(rows)==49
|
||||
random.Random(f"scene-r1-{lang}").shuffle(rows)
|
||||
body=sec+"\nThe groups, one per line as group<TAB>\"text\":\n\n"+"\n".join(f'{g}\t"{t}"' for g,t in rows)+"\n"
|
||||
n=sum(leaks(body,t) for t in test)
|
||||
print(lang,"lines",len(rows),"test_leaks",n,hashlib.sha256(body.encode()).hexdigest())
|
||||
open(S+f"brief-{lang}.txt","w").write(body)
|
||||
|
|
@ -1,15 +0,0 @@
|
|||
"""Put annotator A's labels through weksa scene put, one revision per group.
|
||||
Standard library only. Usage: as build_briefs.py."""
|
||||
import json,subprocess
|
||||
import os
|
||||
W=os.environ.get("WEKSA","target/debug/weksa") # the weksa binary
|
||||
R=os.getcwd() # run from the repo root
|
||||
S=os.environ.get("SCENE_SCRATCH","scene-scratch")+"/" # A-*.jsonl, B-*.jsonl, briefs; never committed
|
||||
A=["--corpus","data/original/corpus.cc","--entities","data/original/entity.cc","--inventory","data/original/inventory.cc","--speaker-state","data/original/speaker-state.cc"]
|
||||
rows=[json.loads(l) for f in ("A-en","A-ja") for l in open(S+f"{f}.jsonl")]
|
||||
for r in sorted(rows,key=lambda r:r['group']):
|
||||
c=[W]+A+["scene","put","--group",r['group'],"--to","unnamed","--inventory-rev","4",
|
||||
"--set",f"relative_status={r['relative_status']}","--set",f"intimacy={r['intimacy']}","--set",f"in_group={'true' if r['in_group'] else 'false'}",
|
||||
"--model-family","anthropic","--generator","claude-sonnet-5-5 (Weksa Hands, scene rubric r1, docs/scene-annotation.md)"]
|
||||
p=subprocess.run(c,cwd=R,capture_output=True,text=True)
|
||||
print(r['group'],p.returncode,p.stdout.strip()[:80],p.stderr.strip()[:200])
|
||||
9
tools/show-working/README.md
Normal file
9
tools/show-working/README.md
Normal file
|
|
@ -0,0 +1,9 @@
|
|||
# Show her working
|
||||
|
||||
A static page that shows the lowering chain for committed fixture packets: typed slots, inventory entries chosen, lowered English, scorer closeness to the corpus target, with hedge, certainty and restraint annotated. Refusals (admission rules, `LowerError`, addressee consent, negation awaiting polarity) are results, not omissions.
|
||||
|
||||
- `crates/weksa/examples/show_working.rs`: runs the real admission door, `lower` and `pronounce` over `proof_packet()` and its variants and prints JSON. Each feature is removed in turn and the packet re-run, so "the lowerer read this" is measured.
|
||||
- `build.py`: runs that, scores each lowered text with the `weksa score` CLI (needs Ollama with `qwen3-embedding:0.6b`), writes `out/data.json` and one dependency-free `out/index.html`. Fails if anything cannot run; there is no fallback text.
|
||||
- `scripts/publish-show-working.sh`: build, then publish through gamecult-ops `publish-mind-preview.sh`.
|
||||
|
||||
Adding a fixture: add an entry in `fixtures()` in the example. A packet from another store needs a loader there; none exists yet.
|
||||
217
tools/show-working/build.py
Executable file
217
tools/show-working/build.py
Executable file
|
|
@ -0,0 +1,217 @@
|
|||
#!/usr/bin/env python3
|
||||
"""Build the "Show her working" page from the real lowerer and scorer.
|
||||
|
||||
usage: build.py [out_dir] (run from the repository root)
|
||||
|
||||
1. `cargo run --example show_working` admits each fixture packet through the
|
||||
packet store and lowers it with the English lowerer (crates/weksa/examples).
|
||||
2. `weksa score` scores each lowered text against its corpus item (and the
|
||||
other committed Nibu reference) through the Ollama embedder.
|
||||
3. out_dir/data.json holds the joined result; out_dir/index.html is one file
|
||||
with no scripts to fetch and no network calls.
|
||||
|
||||
Nothing on the page is typed by hand except the layout and the reading notes.
|
||||
If cargo or the scorer cannot run, the build fails: there is no fallback text.
|
||||
Standard library only.
|
||||
"""
|
||||
import json
|
||||
import pathlib
|
||||
import re
|
||||
import subprocess
|
||||
import sys
|
||||
import time
|
||||
from html import escape as e
|
||||
|
||||
root = pathlib.Path.cwd()
|
||||
out_dir = pathlib.Path(sys.argv[1] if len(sys.argv) > 1 else "tools/show-working/out")
|
||||
weksa_bin = None
|
||||
|
||||
|
||||
def run(cmd, **kw):
|
||||
r = subprocess.run(cmd, cwd=root, capture_output=True, text=True, **kw)
|
||||
if r.returncode != 0:
|
||||
sys.exit(f"{' '.join(map(str, cmd))} failed:\n{r.stderr}")
|
||||
return r.stdout
|
||||
|
||||
|
||||
def cargo_target():
|
||||
meta = json.loads(run(["cargo", "metadata", "--format-version", "1", "--no-deps"]))
|
||||
return pathlib.Path(meta["target_directory"])
|
||||
|
||||
|
||||
# -- 1. the real lowerer ------------------------------------------------------
|
||||
run(["cargo", "build", "--release", "--bin", "weksa", "--example", "show_working"])
|
||||
target = cargo_target() / "release"
|
||||
weksa_bin = target / "weksa"
|
||||
data = json.loads(run([str(target / "examples" / "show_working")]))
|
||||
|
||||
# -- 2. the real scorer -------------------------------------------------------
|
||||
REFS_EXTRA = ["item:nibu:2"]
|
||||
# The page publishes only the corpus items its fixtures cite (plus the extra
|
||||
# reference each lowered fixture is scored against). A Validation or Test item
|
||||
# is never published, even when hand-added to REFS_EXTRA or cited by a fixture:
|
||||
# the dump holds every split, and the guard below reads each item's split.
|
||||
cited = {fx["corpus_item"] for fx in data["fixtures"]} | set(REFS_EXTRA)
|
||||
corpus = {}
|
||||
for m in re.finditer(r'^(item:\S+) \[(.*?)\]\n "(.*)"$', run([str(weksa_bin), "corpus", "dump"]), re.M):
|
||||
if m.group(1) in cited:
|
||||
corpus[m.group(1)] = {"text": m.group(3), "meta": m.group(2)}
|
||||
if set(corpus) != cited:
|
||||
sys.exit(f"corpus dump lacks cited items {sorted(cited - set(corpus))}; unexpected {sorted(set(corpus) - cited)}")
|
||||
# The dump's meta ends with the split (`... group=g Validation`, `... excluded`).
|
||||
# Only Train and split-less items publish; any other name, including a split
|
||||
# added later, is held out until it is allowed here.
|
||||
held_out = {k: v["meta"].split()[-1] for k, v in corpus.items() if v["meta"].split()[-1] not in ("Train", "excluded")}
|
||||
if held_out:
|
||||
sys.exit(f"refusing to publish held-out items (nothing written): {held_out}")
|
||||
model = "qwen3-embedding:0.6b"
|
||||
|
||||
|
||||
def score(text, items):
|
||||
out = run([str(weksa_bin), "score", *items], input=text)
|
||||
got = {}
|
||||
for m in re.finditer(r"^(item:\S+) chrf=([\d.]+) meaning=(-?[\d.]+)", out, re.M):
|
||||
got[m.group(1)] = {"chrf": float(m.group(2)), "meaning": float(m.group(3))}
|
||||
if set(got) != set(items):
|
||||
sys.exit(f"scorer answered {sorted(got)} for {items}:\n{out}")
|
||||
return got
|
||||
|
||||
|
||||
for fx in data["fixtures"]:
|
||||
o = fx["outcome"]
|
||||
if o["kind"] == "lowered":
|
||||
refs = [fx["corpus_item"]] + [r for r in REFS_EXTRA if r != fx["corpus_item"]]
|
||||
o["scores"] = [{"item": k, "target": k == fx["corpus_item"], **v} for k, v in score(o["text"], refs).items()]
|
||||
|
||||
data["corpus"] = corpus
|
||||
data["build"] = {
|
||||
"commit": run(["git", "rev-parse", "HEAD"]).strip(),
|
||||
"embedder": model,
|
||||
"built_unix": int(time.time()),
|
||||
}
|
||||
out_dir.mkdir(parents=True, exist_ok=True)
|
||||
(out_dir / "data.json").write_text(json.dumps(data, indent=1, ensure_ascii=False), encoding="utf-8")
|
||||
|
||||
# -- 3. the page --------------------------------------------------------------
|
||||
CSS = """
|
||||
:root{--ink:#1c1b19;--mute:#5d5a54;--line:#cfc9bd;--bg:#f6f3ec;--card:#fff;--ok:#0b6b4b;--warn:#9a4a00;--bad:#9b1c2c;--bar:#365f9c}
|
||||
*{box-sizing:border-box}body{font:16px/1.55 system-ui,sans-serif;max-width:62rem;margin:2rem auto;padding:0 1rem;color:var(--ink);background:var(--bg)}
|
||||
h1{margin:0 0 .2rem}h2{margin:0 0 .4rem}h3{margin:1.2rem 0 .3rem;font-size:.85rem;text-transform:uppercase;letter-spacing:.06em;color:var(--mute)}
|
||||
code,.mono{font:13px/1.4 ui-monospace,Menlo,monospace}code{background:#ece8dd;padding:0 .25rem;border-radius:3px}
|
||||
.lede{max-width:46rem}.meta{color:var(--mute);font-size:.88rem}
|
||||
nav.pick{display:flex;flex-wrap:wrap;gap:.4rem;margin:1.2rem 0}
|
||||
nav.pick a{border:1px solid var(--line);background:var(--card);padding:.25rem .6rem;border-radius:999px;text-decoration:none;color:var(--ink);font-size:.9rem}
|
||||
nav.pick a.refused{border-color:var(--bad)}nav.pick a.lowered{border-color:var(--ok)}
|
||||
article{background:var(--card);border:1px solid var(--line);border-radius:8px;padding:1rem 1.3rem;margin:1.4rem 0}
|
||||
.chain{display:grid;grid-template-columns:repeat(4,1fr);gap:.6rem;margin:.6rem 0 1rem}
|
||||
.chain div{border:1px solid var(--line);border-radius:6px;padding:.3rem .6rem;font-size:.82rem;color:var(--mute)}
|
||||
.chain b{display:block;color:var(--ink)}
|
||||
table{border-collapse:collapse;width:100%;font-size:.9rem}th,td{text-align:left;padding:.25rem .5rem;border-bottom:1px solid #e6e1d5;vertical-align:top}th{color:var(--mute);font-weight:600}
|
||||
.out{font-size:1.15rem;padding:.6rem .9rem;border-left:4px solid var(--ok);background:#eef6f1}
|
||||
.refusal{padding:.6rem .9rem;border-left:4px solid var(--bad);background:#faeef0}.refusal b{color:var(--bad)}
|
||||
.tag{display:inline-block;font-size:.75rem;padding:0 .4rem;border-radius:3px;border:1px solid var(--line);color:var(--mute)}
|
||||
.tag.read{border-color:var(--ok);color:var(--ok)}.tag.unread{border-color:var(--warn);color:var(--warn)}.tag.refuse{border-color:var(--bad);color:var(--bad)}
|
||||
.bar{height:.7rem;background:#e4dfd2;border-radius:3px;min-width:8rem;position:relative}.bar i{display:block;height:100%;background:var(--bar);border-radius:3px}
|
||||
.ref{font-size:.88rem;color:var(--mute);margin:.2rem 0 .6rem}.ref q{color:var(--ink)}
|
||||
details{margin:.5rem 0}summary{cursor:pointer;color:var(--mute);font-size:.88rem}
|
||||
section.gaps li{margin:.3rem 0}
|
||||
@media(max-width:700px){.chain{grid-template-columns:1fr 1fr}}
|
||||
"""
|
||||
|
||||
PICK_JS = """(function(){var a=[].slice.call(document.querySelectorAll('article[data-fx]'));function show(){var h=location.hash.slice(1);var any=a.some(function(x){return x.id===h});a.forEach(function(x){x.hidden=any&&x.id!==h})}
|
||||
window.addEventListener('hashchange',show);show()})()"""
|
||||
|
||||
|
||||
def g(chosen, i):
|
||||
return next((c["gloss"] for c in chosen if c["id"] == i), "?")
|
||||
|
||||
|
||||
def val(v):
|
||||
(k, x), = v.items()
|
||||
return f"{x}‰" if k == "Grade" else str(x)
|
||||
|
||||
|
||||
def slots_html(fx):
|
||||
s, ch = fx["slots"], fx["chosen"]
|
||||
rows = []
|
||||
for r in s["meaning"]["referents"]:
|
||||
ent = f" · entity <code>{e(r['entity'])}</code>" if r["entity"] else ""
|
||||
rows.append(f"<tr><td><code>{e(r['id'])}</code></td><td>referent</td><td>{e(g(ch, r['kind']))} / {e(g(ch, r['concept']))}{ent}</td></tr>")
|
||||
for p in s["meaning"]["predications"]:
|
||||
roles = ", ".join(f"{e(g(ch, x['role']))}=<code>{e(x['filler'])}</code>" for x in p["roles"])
|
||||
rows.append(f"<tr><td><code>{e(p['id'])}</code></td><td>predication</td><td>{e(g(ch, p['concept']))} in frame {e(g(ch, p['frame']))}: {roles}</td></tr>")
|
||||
for r in s["meaning"]["relations"]:
|
||||
rows.append(f"<tr><td></td><td>relation</td><td>{e(g(ch, r['relation']))}: <code>{e(r['from'])}</code> → <code>{e(r['to'])}</code></td></tr>")
|
||||
meaning = "<table><tr><th>node</th><th>kind</th><th>content</th></tr>" + "".join(rows) + "</table>"
|
||||
d = s["discourse"]
|
||||
drows = []
|
||||
if d["speech_act"]:
|
||||
drows.append(f"<tr><td>speech act</td><td>{e(g(ch, d['speech_act']))}</td></tr>")
|
||||
if d["addressee"]:
|
||||
drows.append(f"<tr><td>addressee</td><td><code>{e(d['addressee'])}</code></td></tr>")
|
||||
if d["addressee_consent"]:
|
||||
drows.append(f"<tr><td>addressee consent</td><td>predication <code>{e(d['addressee_consent'])}</code> (what the addressee asked for)</td></tr>")
|
||||
drows.append(f"<tr><td>source</td><td>{e(s['provenance']['source'])}, kind {e(s['kind'])}</td></tr>")
|
||||
return (f"<h3>Slot: meaning</h3>{meaning}<h3>Slot: discourse</h3><table>{''.join(drows)}</table>"
|
||||
+ stance_register(fx))
|
||||
|
||||
|
||||
def stance_register(fx):
|
||||
s = fx["slots"]
|
||||
eff = fx["outcome"].get("feature_effects") or []
|
||||
rows = []
|
||||
for i, f in enumerate(s["features"]):
|
||||
note = eff[i] if i < len(eff) else ""
|
||||
cls = "read" if "read it" in note else "unread" if "did not read" in note else "refuse" if "refus" in note else ""
|
||||
rows.append(f"<tr><td>{e(f['gloss'])} <span class='meta'>{e(f['id'])}</span></td><td>{e(f['slot'])} @ {e(f['at'])}</td><td>{e(val(f['value']))}</td><td><span class='tag {cls}'>{e(note)}</span></td></tr>")
|
||||
feats = ("<table><tr><th>feature</th><th>slot</th><th>value</th><th>measured effect on the lowerer</th></tr>" + "".join(rows) + "</table>") if rows else "<p class='meta'>No features: no hedge, certainty, polarity, irony or stance set.</p>"
|
||||
return ("<h3>Slot: stance, hedge, certainty, restraint (features)</h3>" + feats
|
||||
+ "<p class='meta'>Register: the packet has no register slot. Register and address belong to a target-language profile, not to the packet; this lowerer reads none.</p>")
|
||||
|
||||
|
||||
def outcome_html(fx):
|
||||
o = fx["outcome"]
|
||||
if o["kind"] == "lowered":
|
||||
ipa = o["ipa"]
|
||||
ipa_s = ("IPA of cited entities: <span class='mono'>" + e(" ".join(ipa["ok"])) + "</span>") if "ok" in ipa else f"IPA refused: {e(ipa['error']['reason'])} <code>{e(ipa['error']['variant'])}</code>"
|
||||
sc = []
|
||||
for s in o["scores"]:
|
||||
ref = corpus[s["item"]]["text"]
|
||||
sc.append(f"<div class='ref'>{'Target' if s['target'] else 'Other reference'} <code>{e(s['item'])}</code>: <q>{e(ref)}</q></div>"
|
||||
f"<table><tr><td width=110>chrF {s['chrf']:.1f}</td><td><div class='bar'><i style='width:{min(s['chrf'],100):.0f}%'></i></div></td>"
|
||||
f"<td width=150>meaning cosine {s['meaning']:.3f}</td><td><div class='bar'><i style='width:{max(s['meaning'],0)*100:.0f}%'></i></div></td></tr></table>")
|
||||
return (f"<h3>Lowered English</h3><div class='out'>{e(o['text'])}</div><p class='meta'>{ipa_s}</p>"
|
||||
f"<h3>Closeness to the corpus ({e(data['build']['embedder'])})</h3>{''.join(sc)}")
|
||||
if o["kind"] == "lower_error":
|
||||
er = o["error"]
|
||||
return f"<h3>Refused by the lowerer</h3><div class='refusal'><b>LowerError::{e(er['variant'])}</b>: {e(er['reason'])}</div><p class='meta'>No text, so no score: nothing was invented to score.</p>"
|
||||
items = "".join(f"<li><b>{e(r['rule'])}</b> <span class='mono'>{e(r['detail'])}</span></li>" for r in o["refusals"])
|
||||
return f"<h3>Refused at admission</h3><div class='refusal'><ul>{items}</ul></div><p class='meta'>The packet never became a lowering input, so the lowerer never saw it.</p>"
|
||||
|
||||
|
||||
def card(fx):
|
||||
o = fx["outcome"]
|
||||
ch = "".join(f"<tr><td><code>{e(c['id'])}</code></td><td>{e(c['gloss'] or '(unresolved)')}</td></tr>" for c in fx["chosen"])
|
||||
steps = [("1 Typed slots", "meaning, stance, discourse"), ("2 Inventory entries", f"{len(fx['chosen'])} ids, rev {fx['slots']['inventory_rev']}"),
|
||||
("3 Lowered English", {"lowered": "text", "lower_error": "refused", "admission_refused": "never reached"}[o["kind"]]),
|
||||
("4 Closeness", "scored" if o["kind"] == "lowered" else "no text, no score")]
|
||||
chain = "".join(f"<div><b>{e(a)}</b>{e(b)}</div>" for a, b in steps)
|
||||
return (f"<article id='{e(fx['id'])}' data-fx><h2>{e(fx['title'])}</h2><p>{e(fx['note'])}</p>"
|
||||
f"<p class='meta'>Packet <code>{e(fx['packet_id'])}</code> for <code>{e(fx['corpus_item'])}</code>. Made from: {e(fx['source'])}.</p>"
|
||||
f"<div class='chain'>{chain}</div>{slots_html(fx)}"
|
||||
f"<details><summary>Inventory entries chosen ({len(fx['chosen'])})</summary><table><tr><th>id</th><th>gloss at this revision</th></tr>{ch}</table></details>"
|
||||
f"{outcome_html(fx)}</article>")
|
||||
|
||||
|
||||
nav = "".join(f"<a class='{'lowered' if f['outcome']['kind']=='lowered' else 'refused'}' href='#{e(f['id'])}'>{e(f['title'])}</a>" for f in data["fixtures"])
|
||||
b = data["build"]
|
||||
page = f"""<!doctype html><html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1">
|
||||
<title>Weksa: show her working</title><style>{CSS}</style></head><body>
|
||||
<h1>Show her working</h1>
|
||||
<p class="lede">A meaning packet goes in. The English lowerer picks inventory entries, writes a sentence, and a scorer measures how close that sentence is to a human-written target. Every number and sentence below was produced by running the real Rust lowerer and scorer when this page was built. The refusals are results too: when the lowerer cannot say a meaning without changing it, it says so instead of dropping the part it cannot say.</p>
|
||||
<p class="meta">Built from <code>{e(b['commit'][:10])}</code>, embedder <code>{e(b['embedder'])}</code>. English only. Fixtures are the committed <code>nibu-proof-001</code> packet and variants of it, each variant described in its own card. Scores are against the committed corpus: chrF (0-100) and embedding cosine. Raw data: <a href="data.json">data.json</a>.</p>
|
||||
<nav class="pick">{nav}</nav>
|
||||
{''.join(card(f) for f in data['fixtures'])}
|
||||
<script>{PICK_JS}</script></body></html>"""
|
||||
(out_dir / "index.html").write_text(page, encoding="utf-8")
|
||||
print(f"wrote {out_dir}/index.html and data.json ({len(data['fixtures'])} fixtures)")
|
||||
Loading…
Reference in a new issue