paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-04-09 09:58:20 -05:00
Code Issues Packages Projects Releases Wiki Activity

fixes to the search index

Browse Source
This commit is contained in:
jonaswinkler 2020-11-28 11:49:46 +01:00
parent a1f5ddede8
commit 52b3057640
2 changed files with 7 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/documents/tasks.py
View File

@ -12,7 +12,9 @@ from documents.sanity_checker import SanityFailedError
def index_optimize(): def index_optimize():
index.open_index().optimize() ix = index.open_index()
with AsyncWriter(ix) as writer:
writer.commit(optimize=True)
def index_reindex(): def index_reindex():

7
src/documents/tests/test_api.py
View File

@ -5,6 +5,7 @@ from unittest import mock
from django.contrib.auth.models import User from django.contrib.auth.models import User
from pathvalidate import ValidationError from pathvalidate import ValidationError
from rest_framework.test import APITestCase from rest_framework.test import APITestCase
from whoosh.writing import AsyncWriter
from documents import index from documents import index
from documents.models import Document, Correspondent, DocumentType, Tag from documents.models import Document, Correspondent, DocumentType, Tag
@ -173,7 +174,7 @@ class DocumentApiTest(DirectoriesMixin, APITestCase):
d1=Document.objects.create(title="invoice", content="the thing i bought at a shop and paid with bank account", checksum="A", pk=1) d1=Document.objects.create(title="invoice", content="the thing i bought at a shop and paid with bank account", checksum="A", pk=1)
d2=Document.objects.create(title="bank statement 1", content="things i paid for in august", pk=2, checksum="B") d2=Document.objects.create(title="bank statement 1", content="things i paid for in august", pk=2, checksum="B")
d3=Document.objects.create(title="bank statement 3", content="things i paid for in september", pk=3, checksum="C") d3=Document.objects.create(title="bank statement 3", content="things i paid for in september", pk=3, checksum="C")
with index.open_index(False).writer() as writer: with AsyncWriter(index.open_index()) as writer:
# Note to future self: there is a reason we dont use a model signal handler to update the index: some operations edit many documents at once # Note to future self: there is a reason we dont use a model signal handler to update the index: some operations edit many documents at once
# (retagger, renamer) and we don't want to open a writer for each of these, but rather perform the entire operation with one writer. # (retagger, renamer) and we don't want to open a writer for each of these, but rather perform the entire operation with one writer.
# That's why we cant open the writer in a model on_save handler or something. # That's why we cant open the writer in a model on_save handler or something.
@ -209,7 +210,7 @@ class DocumentApiTest(DirectoriesMixin, APITestCase):
self.assertEqual(len(results), 0) self.assertEqual(len(results), 0)
def test_search_multi_page(self): def test_search_multi_page(self):
with index.open_index(False).writer() as writer: with AsyncWriter(index.open_index()) as writer:
for i in range(55): for i in range(55):
doc = Document.objects.create(checksum=str(i), pk=i+1, title=f"Document {i+1}", content="content") doc = Document.objects.create(checksum=str(i), pk=i+1, title=f"Document {i+1}", content="content")
index.update_document(writer, doc) index.update_document(writer, doc)
@ -248,7 +249,7 @@ class DocumentApiTest(DirectoriesMixin, APITestCase):
self.assertEqual(len(results), 5) self.assertEqual(len(results), 5)
def test_search_invalid_page(self): def test_search_invalid_page(self):
with index.open_index(False).writer() as writer: with AsyncWriter(index.open_index()) as writer:
for i in range(15): for i in range(15):
doc = Document.objects.create(checksum=str(i), pk=i+1, title=f"Document {i+1}", content="content") doc = Document.objects.create(checksum=str(i), pk=i+1, title=f"Document {i+1}", content="content")
index.update_document(writer, doc) index.update_document(writer, doc)