Prefer exact matches in Link Search results sorting (#67367)

* Weight towards exact matches * Add additional test coverage Co-authored-by: getdave <[email protected]> Co-authored-by: draganescu <[email protected]> Co-authored-by: talldan <[email protected]> Co-authored-by: jasmussen <[email protected]> Co-authored-by: kevin940726 <[email protected]> Co-authored-by: ironprogrammer <[email protected]> Co-authored-by: annezazu <[email protected]>
WordPress · Dec 5, 2024 · f6d161d · f6d161d
1 parent d0da94d
commit f6d161d
Show file tree

Hide file tree

Showing 2 changed files with 58 additions and 4 deletions.
diff --git a/packages/core-data/src/fetch/__experimental-fetch-link-suggestions.ts b/packages/core-data/src/fetch/__experimental-fetch-link-suggestions.ts
@@ -270,12 +270,29 @@ export function sortResults( results: SearchResult[], search: string ) {
 	for ( const result of results ) {
 		if ( result.title ) {
 			const titleTokens = tokenize( result.title );
-			const matchingTokens = titleTokens.filter( ( titleToken ) =>
-				searchTokens.some( ( searchToken ) =>
-					titleToken.includes( searchToken )
+			const exactMatchingTokens = titleTokens.filter( ( titleToken ) =>
+				searchTokens.some(
+					( searchToken ) => titleToken === searchToken
 				)
 			);
-			scores[ result.id ] = matchingTokens.length / titleTokens.length;
+			const subMatchingTokens = titleTokens.filter( ( titleToken ) =>
+				searchTokens.some(
+					( searchToken ) =>
+						titleToken !== searchToken &&
+						titleToken.includes( searchToken )
+				)
+			);
+
+			// The score is a combination of exact matches and sub-matches.
+			// More weight is given to exact matches, as they are more relevant (e.g. "cat" vs "caterpillar").
+			// Diving by the total number of tokens in the title normalizes the score and skews
+			// the results towards shorter titles.
+			const exactMatchScore =
+				( exactMatchingTokens.length / titleTokens.length ) * 10;
+
+			const subMatchScore = subMatchingTokens.length / titleTokens.length;
+
+			scores[ result.id ] = exactMatchScore + subMatchScore;
 		} else {
 			scores[ result.id ] = 0;
 		}

diff --git a/packages/core-data/src/fetch/test/__experimental-fetch-link-suggestions.js b/packages/core-data/src/fetch/test/__experimental-fetch-link-suggestions.js
@@ -393,6 +393,43 @@ describe( 'sortResults', () => {
 			6,
 		] );
 	} );
+
+	it( 'orders results to prefer direct matches over sub matches', () => {
+		const results = [
+			{
+				id: 1,
+				title: 'News',
+				url: 'http://wordpress.local/news/',
+				type: 'page',
+				kind: 'post-type',
+			},
+			{
+				id: 2,
+				title: 'Newspaper',
+				url: 'http://wordpress.local/newspaper/',
+				type: 'page',
+				kind: 'post-type',
+			},
+			{
+				id: 3,
+				title: 'News Flash News',
+				url: 'http://wordpress.local/news-flash-news/',
+				type: 'page',
+				kind: 'post-type',
+			},
+			{
+				id: 4,
+				title: 'News',
+				url: 'http://wordpress.local/news-2/',
+				type: 'page',
+				kind: 'post-type',
+			},
+		];
+		const order = sortResults( results, 'News' ).map(
+			( result ) => result.id
+		);
+		expect( order ).toEqual( [ 1, 4, 3, 2 ] );
+	} );
 } );
 
 describe( 'tokenize', () => {