feat(search): 'why this matched' highlights (ts_headline)

Slice 3 of search-core. Search results now show WHY they matched: a ts_headline body fragment with matched terms highlighted. The API returns U+E000/U+E001 sentinels around matches (NOT HTML); the client tokenises them into escaped <mark> React elements, so untrusted email content can never inject markup (no dangerouslySetInnerHTML). Subtle accent tint. Only when there's a free-text query (browse unchanged); projection branched (no DB function in a ternary) for unambiguous EF translation. Verified: build + all 40 tests; ts_headline output shape in raw Postgres; and the ranked+headline EF query proven to translate + execute against a live Postgres via a throwaway test (removed). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-01 22:14:15 +02:00
parent fcf290a83b
commit 4c43bfed0d
4 changed files with 69 additions and 11 deletions
@@ -77,15 +77,39 @@ public class SearchService : ISearchService
               .ThenByDescending(e => e.SentAtUtc)
            : q.OrderByDescending(e => e.SentAtUtc);

-        var items = await ranked
-            .Skip((r.Page - 1) * r.PageSize)
-            .Take(r.PageSize)
-            .Select(e => new EmailSummaryDto(
-                e.Id, e.GmailMessageId, e.Subject, e.Snippet,
-                e.Sender!.Address, e.Sender.DisplayName, e.SentAtUtc,
-                e.IsUnread, e.IsStarred, e.HasAttachments, e.SizeEstimateBytes, e.Category,
-                e.HasListUnsubscribe, e.SupportsOneClickUnsubscribe))
-            .ToListAsync(ct);
+        var paged = ranked.Skip((r.Page - 1) * r.PageSize).Take(r.PageSize);
+
+        // Two unconditional projections (no DB function inside a C# ternary → no doubt about
+        // EF translation). The browse path never touches ts_headline, so it's byte-for-byte
+        // unchanged AND safe under the InMemory test provider.
+        List<EmailSummaryDto> items;
+        if (hasFreeTextQuery)
+        {
+            // "Why this matched": ts_headline body fragment with matched terms wrapped in
+            // U+E000/U+E001 sentinels (safe, non-HTML — the client renders them as escaped
+            // <mark> spans; see EmailSummaryDto).
+            var headlineOpts =
+                $"StartSel={(char)0xE000},StopSel={(char)0xE001},MaxWords=16,MinWords=5,ShortWord=2,HighlightAll=false";
+            items = await paged
+                .Select(e => new EmailSummaryDto(
+                    e.Id, e.GmailMessageId, e.Subject, e.Snippet,
+                    e.Sender!.Address, e.Sender.DisplayName, e.SentAtUtc,
+                    e.IsUnread, e.IsStarred, e.HasAttachments, e.SizeEstimateBytes, e.Category,
+                    e.HasListUnsubscribe, e.SupportsOneClickUnsubscribe,
+                    EF.Functions.WebSearchToTsQuery("english", term).GetResultHeadline("english", e.BodyText ?? "", headlineOpts)))
+                .ToListAsync(ct);
+        }
+        else
+        {
+            items = await paged
+                .Select(e => new EmailSummaryDto(
+                    e.Id, e.GmailMessageId, e.Subject, e.Snippet,
+                    e.Sender!.Address, e.Sender.DisplayName, e.SentAtUtc,
+                    e.IsUnread, e.IsStarred, e.HasAttachments, e.SizeEstimateBytes, e.Category,
+                    e.HasListUnsubscribe, e.SupportsOneClickUnsubscribe,
+                    null))
+                .ToListAsync(ct);
+        }

        return new PagedResult<EmailSummaryDto>
        {