From 4f782d83bc3fda504e500486b37d613c8c12ed64 Mon Sep 17 00:00:00 2001
From: Bogdan Abaev <bogdan@zotero.org>
Date: Tue, 18 Aug 2026 17:25:27 -0700
Subject: [PATCH] temp: pref to select hybrid/semantic/lexical mode

To make it easier to experiment
---
 .../preferences/preferences_advanced.xhtml    | 17 ++++++++++
 chrome/content/zotero/xpcom/bestMatch.js      | 31 ++++++++++++++++---
 chrome/locale/en-US/zotero/preferences.ftl    |  7 +++++
 defaults/preferences/zotero.js                |  3 ++
 4 files changed, 53 insertions(+), 5 deletions(-)

diff --git a/chrome/content/zotero/preferences/preferences_advanced.xhtml b/chrome/content/zotero/preferences/preferences_advanced.xhtml
index cd4bb487a6..17e1afcdfd 100644
--- a/chrome/content/zotero/preferences/preferences_advanced.xhtml
+++ b/chrome/content/zotero/preferences/preferences_advanced.xhtml
@@ -311,6 +311,23 @@
 			</hbox>
 			<description id="semantic-search-model-description"
 				data-l10n-id="preferences-advanced-semantic-search-model-description"/>
+			<!-- Temporary, for testing: pin best-match search to one engine -->
+			<hbox align="center">
+				<label data-l10n-id="preferences-advanced-best-match-engine"
+					control="best-match-engine"/>
+				<menulist id="best-match-engine"
+						preference="extensions.zotero.search.bestMatchEngine"
+						native="true">
+					<menupopup>
+						<menuitem value="hybrid"
+							data-l10n-id="preferences-advanced-best-match-engine-hybrid"/>
+						<menuitem value="lexical"
+							data-l10n-id="preferences-advanced-best-match-engine-lexical"/>
+						<menuitem value="semantic"
+							data-l10n-id="preferences-advanced-best-match-engine-semantic"/>
+					</menupopup>
+				</menulist>
+			</hbox>
 			<checkbox id="semantic-search-index-fulltext"
 				data-l10n-id="preferences-advanced-semantic-search-index-fulltext"
 				preference="extensions.zotero.embeddings.indexFulltext"
diff --git a/chrome/content/zotero/xpcom/bestMatch.js b/chrome/content/zotero/xpcom/bestMatch.js
index afeeef417d..e67467c927 100644
--- a/chrome/content/zotero/xpcom/bestMatch.js
+++ b/chrome/content/zotero/xpcom/bestMatch.js
@@ -99,8 +99,20 @@ Zotero.BestMatch = new function () {
 	 */
 	this.scoreItemIDs = async function (queryText, itemIDs, options = {}) {
 		try {
+			// Temporary, for testing: the bestMatchEngine pref pins scoring to
+			// one engine instead of the hybrid default
+			let engine = Zotero.Prefs.get('search.bestMatchEngine');
+			if (engine == 'semantic') {
+				let semantic = await Zotero.Embeddings.scoreItemIDs(queryText, itemIDs, options);
+				// On the model's display band, so scores are 0-1 like the
+				// other modes'
+				return new Map([...semantic].map(
+					([itemID, score]) => [itemID, Zotero.Embeddings.getScoreFraction(score)]
+				));
+			}
 			// A query the semantic engine can't embed ranks lexically alone
-			if (!_useSemantic() || !Zotero.Embeddings.normalizeQuery(queryText || '')) {
+			if (engine == 'lexical' || !_useSemantic()
+					|| !Zotero.Embeddings.normalizeQuery(queryText || '')) {
 				return await Zotero.Lexical.scoreItemIDs(queryText, itemIDs, options);
 			}
 			// Both engines score the same candidates concurrently. allSettled
@@ -160,9 +172,16 @@ Zotero.BestMatch = new function () {
 	 *     `strength`, plus chunk location fields or a lexical `source`
 	 */
 	this.getMatchingExcerpts = async function (queryText, itemID, options = {}) {
+		// Temporary, for testing: the bestMatchEngine pref keeps the pinned
+		// engine's excerpts alone -- no lexical excerpts or highlights when
+		// pinned semantic, no chunks when pinned lexical
+		let engine = Zotero.Prefs.get('search.bestMatchEngine');
 		let limit = options.limit ?? 5;
-		let excerpts = await Zotero.Lexical.getMatchingExcerpts(queryText, itemID, options);
-		if (!_useSemantic() || !Zotero.Embeddings.normalizeQuery(queryText || '')) {
+		let excerpts = engine == 'semantic'
+			? []
+			: await Zotero.Lexical.getMatchingExcerpts(queryText, itemID, options);
+		if (engine == 'lexical' || !_useSemantic()
+				|| !Zotero.Embeddings.normalizeQuery(queryText || '')) {
 			return excerpts;
 		}
 		let chunks = [];
@@ -180,8 +199,10 @@ Zotero.BestMatch = new function () {
 		if (!chunks.length) {
 			return excerpts;
 		}
-		let ranges = await Zotero.Lexical.findMatchRanges(
-			queryText, chunks.map(chunk => chunk.text));
+		let ranges = engine == 'semantic'
+			? chunks.map(() => [])
+			: await Zotero.Lexical.findMatchRanges(
+				queryText, chunks.map(chunk => chunk.text));
 		chunks = chunks.map((chunk, i) => ({
 			...chunk,
 			ranges: ranges[i],
diff --git a/chrome/locale/en-US/zotero/preferences.ftl b/chrome/locale/en-US/zotero/preferences.ftl
index dfdab9942d..db8a03d7a3 100644
--- a/chrome/locale/en-US/zotero/preferences.ftl
+++ b/chrome/locale/en-US/zotero/preferences.ftl
@@ -105,6 +105,13 @@ preferences-advanced-semantic-search-multilingual =
 preferences-advanced-semantic-search-model-description = “{ preferences-advanced-semantic-search-english.label }” and “{ preferences-advanced-semantic-search-chinese.label }” give the best results for libraries in those languages. “{ preferences-advanced-semantic-search-multilingual.label }” supports searching in and across many languages.
 preferences-advanced-semantic-search-index-fulltext =
     .label = Search full text of attachment files
+preferences-advanced-best-match-engine = Engine (temporary, for testing):
+preferences-advanced-best-match-engine-hybrid =
+    .label = Hybrid
+preferences-advanced-best-match-engine-lexical =
+    .label = Lexical
+preferences-advanced-best-match-engine-semantic =
+    .label = Semantic
 preferences-advanced-semantic-search-downloading = Downloading…
 preferences-advanced-semantic-search-downloading-progress = Downloading… { $percent }%
 preferences-advanced-semantic-search-indexing = Indexing…
diff --git a/defaults/preferences/zotero.js b/defaults/preferences/zotero.js
index 8d6f9f671e..6f3e78478e 100644
--- a/defaults/preferences/zotero.js
+++ b/defaults/preferences/zotero.js
@@ -108,6 +108,9 @@ pref("extensions.zotero.keys.toggleRead", "`");
 pref("extensions.zotero.keys.showTabsMenu", ";");
 
 pref("extensions.zotero.search.quicksearch-mode", "fields");
+// Temporary, for testing: which engine best-match search runs -- 'lexical',
+// 'semantic', or 'hybrid' (both, fused)
+pref("extensions.zotero.search.bestMatchEngine", "hybrid");
 
 // Fulltext indexing
 pref("extensions.zotero.fulltext.textMaxLength", 500000);