feat(web): add .codepointLength field for SearchQuotientNode types

Build-bot: skip build:web
Skip-bot: skip

web/src/engine/predictive-text/worker-thread/src/main/correction/legacy-quotient-spur.ts

@@ -9,6 +9,7 @@
  */
 
 import { LexicalModelTypes } from '@keymanapp/common-types';
+import { KMWString } from '@keymanapp/web-utils';
 
 import { SearchNode } from './distance-modeler.js';
 import { PathResult, SearchQuotientNode, PathInputProperties } from './search-quotient-node.js';
@@ -21,6 +22,9 @@ import Transform = LexicalModelTypes.Transform;
 // The set of search spaces corresponding to the same 'context' for search.
 // Whenever a wordbreak boundary is crossed, a new instance should be made.
 export class LegacyQuotientSpur extends SearchQuotientSpur {
+  protected readonly insertLength: number;
+  protected readonly leftDeleteLength: number;
+
   /**
    * Constructs a fresh SearchQuotientNode instance for use in predictive-text
    * correction and suggestion searches.
@@ -31,6 +35,12 @@ export class LegacyQuotientSpur extends SearchQuotientSpur {
   constructor(space: SearchQuotientNode, inputs: Distribution<Transform>, inputSource: PathInputProperties | ProbabilityMass<Transform>) {
     super(space, inputs, inputSource);
     this.queueNodes(this.buildEdgesForNodes(space.previousResults.map(r => r.node)));
+
+    // Compute this SearchPath's codepoint length & edge length.
+    const insert = this.inputs?.[0].sample.insert ?? '';
+    this.insertLength = KMWString.length(insert);
+
+    this.leftDeleteLength = this.inputs?.[0].sample.deleteLeft ?? 0;
     return;
   }
 

web/src/engine/predictive-text/worker-thread/src/main/correction/search-quotient-node.ts

@@ -168,6 +168,12 @@ export interface SearchQuotientNode {
    */
   readonly inputSequence: Distribution<Transform>[];
 
+  /**
+   * Reports the length in codepoints of corrected text represented by completed
+   * paths from this instance.
+   */
+  readonly codepointLength: number;
+
   /**
    * Determines the best example text representable by this batcher's portion of
    * the correction-search graph and its paths.

web/src/engine/predictive-text/worker-thread/src/main/correction/search-quotient-root.ts

@@ -15,6 +15,7 @@ export class SearchQuotientRoot implements SearchQuotientNode {
   readonly lowestPossibleSingleCost: number = 0;
 
   readonly inputCount: number = 0;
+  readonly codepointLength: number = 0;
   readonly correctionsEnabled: boolean = false;
 
   private hasBeenProcessed: boolean = false;

web/src/engine/predictive-text/worker-thread/src/main/correction/search-quotient-spur.ts

@@ -34,6 +34,9 @@ export abstract class SearchQuotientSpur implements SearchQuotientNode {
   readonly spaceId: number;
 
   readonly inputCount: number;
+  private _codepointLength: number;
+  protected abstract readonly insertLength: number;
+  protected abstract readonly leftDeleteLength: number
 
   /**
    * Marks all results that have already been returned from this instance of SearchPath.
@@ -102,6 +105,14 @@ export abstract class SearchQuotientSpur implements SearchQuotientNode {
     return parentInputs.concat(localInputs);
   }
 
+  get codepointLength(): number {
+    if(this._codepointLength === undefined) {
+      this._codepointLength = this.parentNode.codepointLength + this.insertLength - this.leftDeleteLength;
+    }
+
+    return this._codepointLength;
+  }
+
   public get lastInput(): Distribution<Readonly<Transform>> {
     // Shallow-copies the array to prevent external modification; the Transforms
     // are marked Readonly to prevent their modification as well.
@@ -113,7 +124,7 @@ export abstract class SearchQuotientSpur implements SearchQuotientNode {
     const bestLocalInput = this.inputs?.reduce((max, curr) => max.p < curr.p ? curr : max) ?? { sample: { insert: '', deleteLeft: 0 }, p: 1};
 
     return {
-      text: KMWString.substring(bestPrefix.text, 0, KMWString.length(bestPrefix.text) - bestLocalInput.sample.deleteLeft) + bestLocalInput.sample.insert,
+      text: KMWString.substring(bestPrefix.text, 0, (this.parentNode?.codepointLength ?? 0) - bestLocalInput.sample.deleteLeft) + bestLocalInput.sample.insert,
       p: bestPrefix.p * bestLocalInput.p
     }
   }

web/src/test/auto/headless/engine/predictive-text/worker-thread/correction-search/search-quotient-spur.tests.ts

@@ -54,6 +54,7 @@ describe('SearchQuotientSpur', () => {
     it('initializes from a lexical model', () => {
       const path = new LegacyQuotientRoot(testModel);
       assert.equal(path.inputCount, 0);
+      assert.equal(path.codepointLength, 0);
       assert.isNumber(path.spaceId);
       assert.deepEqual(path.bestExample, {text: '', p: 1});
       assert.deepEqual(path.parents, []);
@@ -71,6 +72,7 @@ describe('SearchQuotientSpur', () => {
       const extendedPath = new LegacyQuotientSpur(rootPath, leadEdgeDistribution, leadEdgeDistribution[0]);
 
       assert.equal(extendedPath.inputCount, 1);
+      assert.equal(extendedPath.codepointLength, 1);
       assert.isNumber(extendedPath.spaceId);
       assert.notEqual(extendedPath.spaceId, rootPath.spaceId);
       assert.deepEqual(extendedPath.bestExample, {text: 't', p: 0.5});
@@ -96,7 +98,7 @@ describe('SearchQuotientSpur', () => {
       assert.deepEqual(rootPath.parents, []);
     });
 
-    it('may be built from arbitrary prior SearchPath', () => {
+    it('may be built from arbitrary prior SearchQuotientSpur', () => {
       const rootPath = new LegacyQuotientRoot(testModel);
 
       const leadEdgeDistribution = [
@@ -128,6 +130,7 @@ describe('SearchQuotientSpur', () => {
       assert.deepEqual(leadEdgeDistribution, inputClone);
 
       assert.equal(length2Path.inputCount, 2);
+      assert.equal(length2Path.codepointLength, 2);
       assert.isNumber(length2Path.spaceId);
       assert.notEqual(length2Path.spaceId, length1Path.spaceId);
       assert.deepEqual(length2Path.bestExample, {text: 'tr', p: leadEdgeDistribution[0].p * tailEdgeDistribution[0].p});
@@ -156,6 +159,7 @@ describe('SearchQuotientSpur', () => {
       ]);
 
       assert.equal(length1Path.inputCount, 1);
+      assert.equal(length1Path.codepointLength, 1);
       assert.isNumber(length1Path.spaceId);
       assert.notEqual(length1Path.spaceId, rootPath.spaceId);
       assert.deepEqual(length1Path.bestExample, {text: 't', p: 0.5});
@@ -210,6 +214,7 @@ describe('SearchQuotientSpur', () => {
       assert.deepEqual(leadEdgeDistribution, inputClone);
 
       assert.equal(length2Path.inputCount, 2);
+      assert.equal(length2Path.codepointLength, 3);
       assert.isNumber(length2Path.spaceId);
       assert.notEqual(length2Path.spaceId, length1Path.spaceId);
       assert.deepEqual(length2Path.bestExample, {text: 'tri', p: leadEdgeDistribution[0].p * tailEdgeDistribution[0].p});
@@ -238,6 +243,7 @@ describe('SearchQuotientSpur', () => {
       ]);
 
       assert.equal(length1Path.inputCount, 1);
+      assert.equal(length1Path.codepointLength, 1);
       assert.isNumber(length1Path.spaceId);
       assert.notEqual(length1Path.spaceId, rootPath.spaceId);
       assert.deepEqual(length1Path.bestExample, {text: 't', p: 0.5});
@@ -253,6 +259,7 @@ describe('SearchQuotientSpur', () => {
 
       assert.equal(pathToSplit.inputCount, 4);
       assert.equal(distributions.length, pathToSplit.inputCount);
+      assert.equal(pathToSplit.codepointLength, 4); // one char per input, no deletions anywhere
       // Per assertions documented in the setup above.
       assert.deepEqual(pathToSplit.bestExample, distributions.reduce(
         (constructing, current) => ({text: constructing.text + current[0].sample.insert, p: constructing.p * current[0].p}),