Merge pull request #2351 from paperless-ngx/feature-comment-search

Feature: include comments in advanced search

src-ui/src/app/components/document-list/document-card-large/document-card-large.component.html

@@ -25,7 +25,13 @@
           </h5>
         </div>
         <p class="card-text">
-          <span *ngIf="document.__search_hit__" [innerHtml]="document.__search_hit__.highlights"></span>
+          <span *ngIf="document.__search_hit__ && document.__search_hit__.highlights" [innerHtml]="document.__search_hit__.highlights"></span>
+          <span *ngIf="document.__search_hit__ && document.__search_hit__.comment_highlights">
+            <svg width="1em" height="1em" fill="currentColor" class="me-2">
+              <use xlink:href="assets/bootstrap-icons.svg#chat-left-text"/>
+            </svg>
+            <span [innerHtml]="document.__search_hit__.comment_highlights"></span>
+          </span>
           <span *ngIf="!document.__search_hit__" class="result-content">{{contentTrimmed}}</span>
         </p>
 

src-ui/src/app/data/paperless-document.ts

@@ -10,6 +10,7 @@ export interface SearchHit {
   rank?: number
 
   highlights?: string
+  comment_highlights?: string
 }
 
 export interface PaperlessDocument extends ObjectWithId {

src/documents/index.py

@@ -5,6 +5,7 @@ from contextlib import contextmanager
 
 from dateutil.parser import isoparse
 from django.conf import settings
+from documents.models import Comment
 from documents.models import Document
 from whoosh import classify
 from whoosh import highlight
@@ -49,6 +50,7 @@ def get_schema():
         path=TEXT(sortable=True),
         path_id=NUMERIC(),
         has_path=BOOLEAN(),
+        comments=TEXT(),
     )
 
 
@@ -90,6 +92,7 @@ def open_index_searcher():
 def update_document(writer, doc):
     tags = ",".join([t.name for t in doc.tags.all()])
     tags_ids = ",".join([str(t.id) for t in doc.tags.all()])
+    comments = ",".join([str(c.comment) for c in Comment.objects.filter(document=doc)])
     writer.update_document(
         id=doc.pk,
         title=doc.title,
@@ -110,6 +113,7 @@ def update_document(writer, doc):
         path=doc.storage_path.name if doc.storage_path else None,
         path_id=doc.storage_path.id if doc.storage_path else None,
         has_path=doc.storage_path is not None,
+        comments=comments,
     )
 
 
@@ -255,7 +259,7 @@ class DelayedFullTextQuery(DelayedQuery):
     def _get_query(self):
         q_str = self.query_params["query"]
         qp = MultifieldParser(
-            ["content", "title", "correspondent", "tag", "type"],
+            ["content", "title", "correspondent", "tag", "type", "comments"],
             self.searcher.ixreader.schema,
         )
         qp.add_plugin(DateParserPlugin())

src/documents/views.py

@@ -458,10 +458,19 @@ class DocumentViewSet(
 class SearchResultSerializer(DocumentSerializer):
     def to_representation(self, instance):
         doc = Document.objects.get(id=instance["id"])
+        commentTerm = instance.results.q.subqueries[0]
+        comments = ",".join(
+            [
+                str(c.comment)
+                for c in Comment.objects.filter(document=instance["id"])
+                if commentTerm.text in c.comment
+            ],
+        )
         r = super().to_representation(doc)
         r["__search_hit__"] = {
             "score": instance.score,
-            "highlights": instance.highlights("content", text=doc.content)
+            "highlights": instance.highlights("content", text=doc.content),
+            "comment_highlights": instance.highlights("content", text=comments)
             if doc
             else None,
             "rank": instance.rank,