tea/browsertrix
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
9f32aa697b
browsertrix/backend/test/test_collections.py
Ilya Kreymer 00eb62214d
Uploads API: BaseCrawl refactor + Initial support for /uploads endpoint (#937) 
* basecrawl refactor: make crawls db more generic, supporting different types of 'base crawls': crawls, uploads, manual archives
- move shared functionality to basecrawl.py
- create a base BaseCrawl object, which contains start / finish time, metadata and files array
- create BaseCrawlOps, base class for CrawlOps, which supports base crawl deletion, querying and collection add/remove

* uploads api: (part of #929)
- new UploadCrawl object which extends BaseCrawl, has name and description
- support multipart form data data upload to /uploads/formdata
- support streaming upload of a single file via /uploads/stream, using botocore multipart upload to upload to s3-endpoint in parts
- require 'filename' param to set upload filename for streaming uploads (otherwise use form data names)
- sanitize filename, place uploads in /uploads/<uuid>/<sanitized-filename>-<random>.wacz
- uploads have internal id 'upload-<uuid>'
- create UploadedCrawl object with CrawlFiles pointing to the newly uploaded files, set state to 'complete'
- handle upload failures, abort multipart upload
- ensure uploads added within org bucket path
- return id / added when adding new UploadedCrawl
- support listing, deleting, and patch /uploads
- support upload details via /replay.json to support for replay
- add support for 'replaceId=<id>', which would remove all previous files in upload after new upload succeeds. if replaceId doesn't exist, create new upload. (only for stream endpoint so far).
- support patching upload metadata: notes, tags and name on uploads (UpdateUpload extends UpdateCrawl and adds 'name')

* base crawls api: Add /all-crawls list and delete endpoints for all crawl types (without resources)
- support all-crawls/<id>/replay.json with resources
- Use ListCrawlOut model for /all-crawls list endpoint
- Extend BaseCrawlOut from ListCrawlOut, add type
- use 'type: crawl' for crawls and 'type: upload' for uploads
- migration: ensure all previous crawl objects / missing type are set to 'type: crawl'
- indexes: add db indices on 'type' field and with 'type' field and oid, cid, finished, state

* tests: add test for multipart and streaming upload, listing uploads, deleting upload
- add sample WACZ for upload testing: 'example.wacz' and 'example-2.wacz'

* collections: support adding and remove both crawls and uploads via base crawl
- include collection_ids in /all-crawls list
- collections replay.json can include both crawls and uploads

bump version to 1.6.0-beta.2
---------

Co-authored-by: Tessa Walsh <tessa@bitarchivist.net>
2023-07-07 09:13:26 -07:00

539 lines
16 KiB
Python
Raw Blame History

import requests
import os
from .conftest import API_PREFIX
from .utils import read_in_chunks
COLLECTION_NAME = "Test collection"
UPDATED_NAME = "Updated tést cöllection"
SECOND_COLLECTION_NAME = "second-collection"
DESCRIPTION = "Test description"
_coll_id = None
_second_coll_id = None
upload_id = None
modified = None
curr_dir = os.path.dirname(os.path.realpath(__file__))
def test_create_collection(
crawler_auth_headers, default_org_id, crawler_crawl_id, admin_crawl_id
):
r = requests.post(
f"{API_PREFIX}/orgs/{default_org_id}/collections",
headers=crawler_auth_headers,
json={
"crawlIds": [crawler_crawl_id],
"name": COLLECTION_NAME,
},
)
assert r.status_code == 200
data = r.json()
assert data["added"]
assert data["name"] == COLLECTION_NAME
global _coll_id
_coll_id = data["id"]
# Verify crawl in collection
r = requests.get(
f"{API_PREFIX}/orgs/{default_org_id}/crawls/{crawler_crawl_id}/replay.json",
headers=crawler_auth_headers,
)
assert _coll_id in r.json()["collections"]
def test_create_collection_taken_name(
crawler_auth_headers, default_org_id, crawler_crawl_id, admin_crawl_id
):
r = requests.post(
f"{API_PREFIX}/orgs/{default_org_id}/collections",
headers=crawler_auth_headers,
json={
"crawlIds": [crawler_crawl_id],
"name": COLLECTION_NAME,
},
)
assert r.status_code == 400
assert r.json()["detail"] == "collection_name_taken"
def test_create_collection_empty_name(
crawler_auth_headers, default_org_id, crawler_crawl_id, admin_crawl_id
):
r = requests.post(
f"{API_PREFIX}/orgs/{default_org_id}/collections",
headers=crawler_auth_headers,
json={
"crawlIds": [crawler_crawl_id],
"name": "",
},
)
assert r.status_code == 422
def test_update_collection(
crawler_auth_headers, default_org_id, crawler_crawl_id, admin_crawl_id
):
r = requests.patch(
f"{API_PREFIX}/orgs/{default_org_id}/collections/{_coll_id}",
headers=crawler_auth_headers,
json={
"description": DESCRIPTION,
},
)
assert r.status_code == 200
assert r.json()["updated"]
r = requests.get(
f"{API_PREFIX}/orgs/{default_org_id}/collections/{_coll_id}",
headers=crawler_auth_headers,
)
assert r.status_code == 200
data = r.json()
assert data["id"] == _coll_id
assert data["name"] == COLLECTION_NAME
assert data["description"] == DESCRIPTION
assert data["crawlCount"] == 1
assert data["pageCount"] > 0
global modified
modified = data["modified"]
assert modified
def test_rename_collection(
crawler_auth_headers, default_org_id, crawler_crawl_id, admin_crawl_id
):
r = requests.patch(
f"{API_PREFIX}/orgs/{default_org_id}/collections/{_coll_id}",
headers=crawler_auth_headers,
json={
"name": UPDATED_NAME,
},
)
assert r.status_code == 200
assert r.json()["updated"]
r = requests.get(
f"{API_PREFIX}/orgs/{default_org_id}/collections/{_coll_id}",
headers=crawler_auth_headers,
)
assert r.status_code == 200
data = r.json()
assert data["id"] == _coll_id
assert data["name"] == UPDATED_NAME
assert data["modified"] >= modified
def test_rename_collection_taken_name(
crawler_auth_headers, default_org_id, crawler_crawl_id, admin_crawl_id
):
# Add second collection
r = requests.post(
f"{API_PREFIX}/orgs/{default_org_id}/collections",
headers=crawler_auth_headers,
json={
"crawlIds": [crawler_crawl_id],
"name": SECOND_COLLECTION_NAME,
},
)
assert r.status_code == 200
data = r.json()
assert data["added"]
assert data["name"] == SECOND_COLLECTION_NAME
global _second_coll_id
_second_coll_id = data["id"]
# Try to rename first coll to second collection's name
r = requests.patch(
f"{API_PREFIX}/orgs/{default_org_id}/collections/{_coll_id}",
headers=crawler_auth_headers,
json={"name": SECOND_COLLECTION_NAME},
)
assert r.status_code == 400
assert r.json()["detail"] == "collection_name_taken"
def test_add_remove_crawl_from_collection(
crawler_auth_headers, default_org_id, crawler_crawl_id, admin_crawl_id
):
# Add crawl
r = requests.post(
f"{API_PREFIX}/orgs/{default_org_id}/collections/{_coll_id}/add",
json={"crawlIds": [admin_crawl_id]},
headers=crawler_auth_headers,
)
assert r.status_code == 200
data = r.json()
assert data["id"] == _coll_id
assert data["crawlCount"] == 2
assert data["pageCount"] > 0
assert data["modified"] >= modified
assert data["tags"] == ["wr-test-2", "wr-test-1"]
# Verify it was added
r = requests.get(
f"{API_PREFIX}/orgs/{default_org_id}/crawls/{admin_crawl_id}/replay.json",
headers=crawler_auth_headers,
)
assert _coll_id in r.json()["collections"]
# Remove crawls
r = requests.post(
f"{API_PREFIX}/orgs/{default_org_id}/collections/{_coll_id}/remove",
json={"crawlIds": [admin_crawl_id, crawler_crawl_id]},
headers=crawler_auth_headers,
)
assert r.status_code == 200
data = r.json()
assert data["id"] == _coll_id
assert data["crawlCount"] == 0
assert data["pageCount"] == 0
assert data["modified"] >= modified
assert data.get("tags", []) == []
# Verify they were removed
r = requests.get(
f"{API_PREFIX}/orgs/{default_org_id}/crawls/{admin_crawl_id}/replay.json",
headers=crawler_auth_headers,
)
assert _coll_id not in r.json()["collections"]
r = requests.get(
f"{API_PREFIX}/orgs/{default_org_id}/crawls/{crawler_crawl_id}/replay.json",
headers=crawler_auth_headers,
)
assert _coll_id not in r.json()["collections"]
# Add crawls back for further tests
r = requests.post(
f"{API_PREFIX}/orgs/{default_org_id}/collections/{_coll_id}/add",
json={"crawlIds": [admin_crawl_id, crawler_crawl_id]},
headers=crawler_auth_headers,
)
assert r.status_code == 200
data = r.json()
assert data["id"] == _coll_id
assert data["crawlCount"] == 2
assert data["pageCount"] > 0
assert data["modified"] >= modified
assert data["tags"] == ["wr-test-2", "wr-test-1"]
def test_get_collection(crawler_auth_headers, default_org_id):
r = requests.get(
f"{API_PREFIX}/orgs/{default_org_id}/collections/{_coll_id}",
headers=crawler_auth_headers,
)
assert r.status_code == 200
data = r.json()
assert data["id"] == _coll_id
assert data["name"] == UPDATED_NAME
assert data["oid"] == default_org_id
assert data["description"] == DESCRIPTION
assert data["crawlCount"] == 2
assert data["pageCount"] > 0
assert data["modified"] >= modified
assert data["tags"] == ["wr-test-2", "wr-test-1"]
def test_get_collection_replay(
crawler_auth_headers, default_org_id, crawler_crawl_id, admin_crawl_id
):
r = requests.get(
f"{API_PREFIX}/orgs/{default_org_id}/collections/{_coll_id}/replay.json",
headers=crawler_auth_headers,
)
assert r.status_code == 200
data = r.json()
assert data["id"] == _coll_id
assert data["name"] == UPDATED_NAME
assert data["oid"] == default_org_id
assert data["description"] == DESCRIPTION
assert data["crawlCount"] == 2
assert data["pageCount"] > 0
assert data["modified"] >= modified
assert data["tags"] == ["wr-test-2", "wr-test-1"]
resources = data["resources"]
assert resources
for resource in resources:
assert resource["name"]
assert resource["path"]
assert resource["size"]
def test_add_upload_to_collection(crawler_auth_headers, default_org_id):
with open(os.path.join(curr_dir, "data", "example.wacz"), "rb") as fh:
r = requests.put(
f"{API_PREFIX}/orgs/{default_org_id}/uploads/stream?filename=test-upload.wacz",
headers=crawler_auth_headers,
data=read_in_chunks(fh),
)
assert r.status_code == 200
assert r.json()["added"]
global upload_id
upload_id = r.json()["id"]
# Add upload
r = requests.post(
f"{API_PREFIX}/orgs/{default_org_id}/collections/{_coll_id}/add",
json={"crawlIds": [upload_id]},
headers=crawler_auth_headers,
)
assert r.status_code == 200
data = r.json()
assert data["id"] == _coll_id
assert data["crawlCount"] == 3
assert data["pageCount"] > 0
assert data["modified"]
assert data["tags"] == ["wr-test-2", "wr-test-1"]
# Verify it was added
r = requests.get(
f"{API_PREFIX}/orgs/{default_org_id}/uploads/{upload_id}/replay.json",
headers=crawler_auth_headers,
)
assert _coll_id in r.json()["collections"]
def test_list_collections(
crawler_auth_headers, default_org_id, crawler_crawl_id, admin_crawl_id
):
r = requests.get(
f"{API_PREFIX}/orgs/{default_org_id}/collections", headers=crawler_auth_headers
)
assert r.status_code == 200
data = r.json()
assert data["total"] == 2
items = data["items"]
assert len(items) == 2
first_coll = [coll for coll in items if coll["name"] == UPDATED_NAME][0]
assert first_coll["id"]
assert first_coll["name"] == UPDATED_NAME
assert first_coll["oid"] == default_org_id
assert first_coll["description"] == DESCRIPTION
assert first_coll["crawlCount"] == 3
assert first_coll["pageCount"] > 0
assert first_coll["modified"]
assert first_coll["tags"] == ["wr-test-2", "wr-test-1"]
second_coll = [coll for coll in items if coll["name"] == SECOND_COLLECTION_NAME][0]
assert second_coll["id"]
assert second_coll["name"] == SECOND_COLLECTION_NAME
assert second_coll["oid"] == default_org_id
assert second_coll.get("description") is None
assert second_coll["crawlCount"] == 1
assert second_coll["pageCount"] > 0
assert second_coll["modified"]
assert second_coll["tags"] == ["wr-test-2"]
def test_remove_upload_from_collection(crawler_auth_headers, default_org_id):
# Remove upload
r = requests.post(
f"{API_PREFIX}/orgs/{default_org_id}/collections/{_coll_id}/remove",
json={"crawlIds": [upload_id]},
headers=crawler_auth_headers,
)
assert r.status_code == 200
data = r.json()
assert data["id"] == _coll_id
assert data["crawlCount"] == 2
assert data["pageCount"] > 0
assert data["modified"] >= modified
assert data.get("tags") == ["wr-test-2", "wr-test-1"]
# Verify it was removed
r = requests.get(
f"{API_PREFIX}/orgs/{default_org_id}/uploads/{upload_id}/replay.json",
headers=crawler_auth_headers,
)
assert _coll_id not in r.json()["collections"]
def test_filter_sort_collections(
crawler_auth_headers, default_org_id, crawler_crawl_id, admin_crawl_id
):
# Test filtering by name
r = requests.get(
f"{API_PREFIX}/orgs/{default_org_id}/collections?name={SECOND_COLLECTION_NAME}",
headers=crawler_auth_headers,
)
assert r.status_code == 200
data = r.json()
assert data["total"] == 1
items = data["items"]
assert len(items) == 1
coll = items[0]
assert coll["id"]
assert coll["name"] == SECOND_COLLECTION_NAME
assert coll["oid"] == default_org_id
assert coll.get("description") is None
# Test filtering by name prefix
name_prefix = SECOND_COLLECTION_NAME[0:4]
r = requests.get(
f"{API_PREFIX}/orgs/{default_org_id}/collections?namePrefix={name_prefix}",
headers=crawler_auth_headers,
)
assert r.status_code == 200
data = r.json()
assert data["total"] == 1
items = data["items"]
assert len(items) == 1
coll = items[0]
assert coll["id"]
assert coll["name"] == SECOND_COLLECTION_NAME
assert coll["oid"] == default_org_id
assert coll.get("description") is None
# Test filtering by name prefix (case insensitive)
name_prefix = name_prefix.upper()
r = requests.get(
f"{API_PREFIX}/orgs/{default_org_id}/collections?namePrefix={name_prefix}",
headers=crawler_auth_headers,
)
assert r.status_code == 200
data = r.json()
assert data["total"] == 1
items = data["items"]
assert len(items) == 1
coll = items[0]
assert coll["id"]
assert coll["name"] == SECOND_COLLECTION_NAME
assert coll["oid"] == default_org_id
assert coll.get("description") is None
# Test sorting by name, ascending (default)
r = requests.get(
f"{API_PREFIX}/orgs/{default_org_id}/collections?sortBy=name",
headers=crawler_auth_headers,
)
assert r.status_code == 200
data = r.json()
assert data["total"] == 2
items = data["items"]
assert items[0]["name"] == SECOND_COLLECTION_NAME
assert items[1]["name"] == UPDATED_NAME
# Test sorting by name, descending
r = requests.get(
f"{API_PREFIX}/orgs/{default_org_id}/collections?sortBy=name&sortDirection=-1",
headers=crawler_auth_headers,
)
assert r.status_code == 200
data = r.json()
assert data["total"] == 2
items = data["items"]
assert items[0]["name"] == UPDATED_NAME
assert items[1]["name"] == SECOND_COLLECTION_NAME
# Test sorting by description, ascending (default)
r = requests.get(
f"{API_PREFIX}/orgs/{default_org_id}/collections?sortBy=description",
headers=crawler_auth_headers,
)
assert r.status_code == 200
data = r.json()
assert data["total"] == 2
items = data["items"]
assert items[0]["name"] == SECOND_COLLECTION_NAME
assert items[0].get("description") is None
assert items[1]["name"] == UPDATED_NAME
assert items[1]["description"] == DESCRIPTION
# Test sorting by description, descending
r = requests.get(
f"{API_PREFIX}/orgs/{default_org_id}/collections?sortBy=description&sortDirection=-1",
headers=crawler_auth_headers,
)
assert r.status_code == 200
data = r.json()
assert data["total"] == 2
items = data["items"]
assert items[0]["name"] == UPDATED_NAME
assert items[0]["description"] == DESCRIPTION
assert items[1]["name"] == SECOND_COLLECTION_NAME
assert items[1].get("description") is None
# Test sorting by modified, ascending
r = requests.get(
f"{API_PREFIX}/orgs/{default_org_id}/collections?sortBy=modified",
headers=crawler_auth_headers,
)
assert r.status_code == 200
data = r.json()
assert data["total"] == 2
items = data["items"]
assert items[0]["modified"] <= items[1]["modified"]
# Test sorting by modified, descending
r = requests.get(
f"{API_PREFIX}/orgs/{default_org_id}/collections?sortBy=modified&sortDirection=-1",
headers=crawler_auth_headers,
)
assert r.status_code == 200
data = r.json()
assert data["total"] == 2
items = data["items"]
assert items[0]["modified"] >= items[1]["modified"]
def test_delete_collection(crawler_auth_headers, default_org_id, crawler_crawl_id):
# Delete second collection
r = requests.delete(
f"{API_PREFIX}/orgs/{default_org_id}/collections/{_second_coll_id}",
headers=crawler_auth_headers,
)
assert r.status_code == 200
assert r.json()["success"]
# Verify collection id was removed from crawl
r = requests.get(
f"{API_PREFIX}/orgs/{default_org_id}/crawls/{crawler_crawl_id}/replay.json",
headers=crawler_auth_headers,
)
assert _second_coll_id not in r.json()["collections"]
# Make a new empty (no crawls) collection and delete it
r = requests.post(
f"{API_PREFIX}/orgs/{default_org_id}/collections",
headers=crawler_auth_headers,
json={
"name": "To delete",
"description": "Deleting a collection with no crawls should work.",
},
)
assert r.status_code == 200
data = r.json()
assert data["added"]
coll_id = data["id"]
r = requests.delete(
f"{API_PREFIX}/orgs/{default_org_id}/collections/{coll_id}",
headers=crawler_auth_headers,
)
assert r.status_code == 200
assert r.json()["success"]
Reference in New Issue View Git Blame Copy Permalink