feat: enhanced search filters (#2398)

* advanced search filters * improve labelId filtering in query * index label ids on typesense * index label ids on typesense * filters on AI search * refactor: detect typesense schema drift from the declared collection schema * feat: show secondary search filters only when applied Created by and Labels now stay hidden until they hold a value; a Filter button at the right end of the bar lists the hidden ones and opens the picked filter's dropdown immediately. * fix: keep applied search filters in the order they were added * feat: add title-only search mode Adds a titleOnly flag to page search: the Postgres driver matches titles via trigram-indexed unaccented LIKE ranked by word_similarity, and a Match filter in the search spotlight switches between everything and title-only matching. * refactor: make title-only search a toggle chip * fix: drop stale results when the search content type changes * feat: add trigram index on attachment file names * feat: extend title-only search to attachments The titleOnly flag now matches attachment file names via the separator-normalized trigram expression, and the toggle chip stays available in attachment mode as File name only. * refactor: keep the title-only label uniform across search modes * feat: index txt attachments for content search * feat: pin the current user at the top of the creator filter * refactor: dim the you suffix in the creator filter * feat: browse label-filtered pages without a query Selecting labels now lists their pages newest-first before any text is typed, on both the Postgres and Typesense drivers. * fix: match any selected label instead of requiring all * fix: use a gray spotlight selection instead of primary blue * feat: include search results in the spotlight tab order * feat: show last updated time on search results * fix: stop empty-state flicker while the search query debounces * feat: browse creator-filtered results without a query Selecting a creator with an empty query now lists their pages (or attachments in attachment mode) newest-first, with the same space and page permission filtering as typed search. * fix: show Untitled for pages without a title in search results * quick page sharing fix * minor search filter fixes --------- Co-authored-by: Philipinho <16838612+Philipinho@users.noreply.github.com>
2026-08-25 15:57:11 +08:00 · 2026-08-25 01:39:33 +01:00
parent cd597f0161
commit 917195b2f2
19 changed files with 740 additions and 85 deletions
@@ -116,8 +116,8 @@ export class AttachmentService {
        });
      }

-      // Only index PDFs and DOCX files
-      if (['.pdf', '.docx'].includes(attachment.fileExt.toLowerCase())) {
+      // Only index PDF, DOCX and TXT files
+      if (['.pdf', '.docx', '.txt'].includes(attachment.fileExt.toLowerCase())) {
        await this.attachmentQueue.add(
          QueueJob.ATTACHMENT_INDEX_CONTENT,
          {
@@ -7,12 +7,15 @@ import { executeTx } from '@docmost/db/utils';
 import { PaginationOptions } from '@docmost/db/pagination/pagination-options';
 import { PagePermissionRepo } from '@docmost/db/repos/page/page-permission.repo';
 import { normalizeLabelName } from './utils';
+import { EventEmitter2 } from "@nestjs/event-emitter";
+import { EventName } from "src/common/events/event.contants";

@Injectable()
 export class LabelService {
  constructor(
    private readonly labelRepo: LabelRepo,
    private readonly pagePermissionRepo: PagePermissionRepo,
+    private readonly eventEmitter: EventEmitter2,
    @InjectKysely() private readonly db: KyselyDB,
  ) {}

@@ -34,6 +37,12 @@ export class LabelService {
        attached.push(label);
      }
    });
+
+    this.eventEmitter.emit(EventName.PAGE_UPDATED, {
+      pageIds: [pageId],
+      workspaceId: workspaceId,
+    });
+    
    return attached;
  }

@@ -64,6 +73,11 @@ export class LabelService {
        await this.labelRepo.deleteLabel(labelId, workspaceId, trx);
      }
    });
+
+    this.eventEmitter.emit(EventName.PAGE_UPDATED, {
+      pageIds: [pageId],
+      workspaceId: workspaceId,
+    });
  }

  async getPageLabels(pageId: string, pagination: PaginationOptions) {
@@ -1,4 +1,5 @@
 import {
+  IsArray,
  IsBoolean,
  IsNotEmpty,
  IsNumber,
@@ -8,9 +9,9 @@ import {
 } from 'class-validator';

 export class SearchDTO {
-  @IsNotEmpty()
+  @IsOptional()
  @IsString()
-  query: string;
+  query?: string;

  @IsOptional()
  @IsUUID()
@@ -24,6 +25,15 @@ export class SearchDTO {
  @IsUUID()
  creatorId?: string;

+  @IsOptional()
+  @IsArray()
+  @IsUUID('all', { each: true })
+  labelIds?: string[];
+
+  @IsOptional()
+  @IsBoolean()
+  titleOnly?: boolean;
+
  @IsOptional()
  @IsNumber()
  limit?: number;
@@ -29,12 +29,36 @@ export class SearchService {
      workspaceId: string;
    },
  ): Promise<{ items: SearchResponseDto[] }> {
-    const { query } = searchParams;
+    const query = searchParams.query?.trim() ?? '';
+    const labelIds = [...new Set(searchParams.labelIds ?? [])];
+    // selected filters (labels, creator) are browsable without a query
+    const browseByFilters =
+      query.length < 1 &&
+      (labelIds.length > 0 || Boolean(searchParams.creatorId));

-    if (query.length < 1) {
+    if (query.length < 1 && !browseByFilters) {
      return { items: [] };
    }
-    const searchQuery = tsquery(query.trim() + '*');
+    const searchQuery = tsquery(query + '*');
+    const titleOnly = searchParams.titleOnly === true;
+    const titleQuery = query;
+    // escape LIKE wildcards; ranking keeps the raw query
+    const titleLikeQuery = query.replace(/[\\%_]/g, '\\$&');
+
+    const rankColumn = browseByFilters
+      ? sql<number>`0`.as('rank')
+      : titleOnly
+        ? sql<number>`word_similarity(lower(f_unaccent(${titleQuery})), lower(f_unaccent(pages.title)))`.as(
+            'rank',
+          )
+        : sql<number>`ts_rank(tsv, to_tsquery('english', f_unaccent(${searchQuery})))`.as(
+            'rank',
+          );
+    const highlightColumn = browseByFilters || titleOnly
+      ? sql<string>`''`.as('highlight')
+      : sql<string>`ts_headline('english', text_content, to_tsquery('english', f_unaccent(${searchQuery})),'MinWords=9, MaxWords=10, MaxFragments=3')`.as(
+          'highlight',
+        );

    let queryResults = this.db
      .selectFrom('pages')
@@ -47,23 +71,41 @@ export class SearchService {
        'creatorId',
        'createdAt',
        'updatedAt',
-        sql<number>`ts_rank(tsv, to_tsquery('english', f_unaccent(${searchQuery})))`.as(
-          'rank',
-        ),
-        sql<string>`ts_headline('english', text_content, to_tsquery('english', f_unaccent(${searchQuery})),'MinWords=9, MaxWords=10, MaxFragments=3')`.as(
-          'highlight',
-        ),
+        rankColumn,
+        highlightColumn,
      ])
-      .where(
-        'tsv',
-        '@@',
-        sql<string>`to_tsquery('english', f_unaccent(${searchQuery}))`,
+      .$if(!browseByFilters && !titleOnly, (qb) =>
+        qb.where(
+          'tsv',
+          '@@',
+          sql<string>`to_tsquery('english', f_unaccent(${searchQuery}))`,
+        ),
+      )
+      .$if(!browseByFilters && titleOnly, (qb) =>
+        qb.where((eb) =>
+          eb(
+            sql`lower(f_unaccent(pages.title))`,
+            'like',
+            sql`lower(f_unaccent(${`%${titleLikeQuery}%`}))`,
+          ),
+        ),
      )
      .$if(Boolean(searchParams.creatorId), (qb) =>
        qb.where('creatorId', '=', searchParams.creatorId),
      )
+      .$if(labelIds?.length > 0, (qb) =>
+        qb.where(
+          'id',
+          'in',
+          this.db
+            .selectFrom('pageLabels')
+            .select('pageId')
+            .where('labelId', 'in', labelIds),
+        ),
+      )
      .where('deletedAt', 'is', null)
-      .orderBy('rank', 'desc')
+      .$if(browseByFilters, (qb) => qb.orderBy('updatedAt', 'desc'))
+      .$if(!browseByFilters, (qb) => qb.orderBy('rank', 'desc'))
      .limit(searchParams.limit || 25)
      .offset(searchParams.offset || 0);

@@ -71,8 +113,7 @@ export class SearchService {
      queryResults = queryResults.select((eb) => this.pageRepo.withSpace(eb));
    }

-    if (searchParams.spaceId) {
-      // search by spaceId
+    if (searchParams.spaceId && opts.userId) {
      queryResults = queryResults.where('spaceId', '=', searchParams.spaceId);
    } else if (opts.userId && !searchParams.spaceId) {
      // only search spaces the user is a member of
@@ -46,8 +46,9 @@ export class ShareService {
      throw new NotFoundException('Share not found');
    }

-    const isRestricted =
-      await this.pagePermissionRepo.hasRestrictedAncestor(share.pageId);
+    const isRestricted = await this.pagePermissionRepo.hasRestrictedAncestor(
+      share.pageId,
+    );
    if (isRestricted) {
      throw new NotFoundException('Share not found');
    }
@@ -110,6 +111,9 @@ export class ShareService {
  }

  async getSharedPage(dto: ShareInfoDto, workspaceId: string) {
+    //TODO: we should resolve the page from the share id
+    if (!dto.pageId) throw new NotFoundException('Shared page not found');
+
    const share = await this.getShareForPage(dto.pageId, workspaceId);

    if (!share) {
@@ -126,8 +130,9 @@ export class ShareService {
    }

    // Block access to restricted pages
-    const isRestricted =
-      await this.pagePermissionRepo.hasRestrictedAncestor(page.id);
+    const isRestricted = await this.pagePermissionRepo.hasRestrictedAncestor(
+      page.id,
+    );
    if (isRestricted) {
      throw new NotFoundException('Shared page not found');
    }
@@ -0,0 +1,17 @@
+import { type Kysely, sql } from 'kysely';
+
+export async function up(db: Kysely<any>): Promise<void> {
+  await sql`CREATE INDEX IF NOT EXISTS pages_title_trgm_idx ON pages USING gin (lower(f_unaccent(title)) gin_trgm_ops)`.execute(
+    db,
+  );
+
+  // separators normalized to spaces so space-typed queries match How_to_export.pdf
+  await sql`CREATE INDEX IF NOT EXISTS attachments_file_name_trgm_idx ON attachments USING gin (lower(f_unaccent(translate(file_name, '_.-', '   '))) gin_trgm_ops)`.execute(
+    db,
+  );
+}
+
+export async function down(db: Kysely<any>): Promise<void> {
+  await sql`DROP INDEX IF EXISTS attachments_file_name_trgm_idx`.execute(db);
+  await sql`DROP INDEX IF EXISTS pages_title_trgm_idx`.execute(db);
+}