bellingcat/auto-archiver-api
1
0
Fork 0
mirror of https://github.com/bellingcat/auto-archiver-api.git synced 2026-06-11 13:08:34 +03:00
Code Issues Packages Projects Releases Wiki Activity

switching from optional response_model to mandatory return type

Browse Source
This commit is contained in:
msramalho
2024-10-29 16:17:40 +00:00
parent aaada7d83f
commit 8c658cdf52
7 changed files with 35 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
src/db/crud.py
View File

@@ -87,10 +87,10 @@ def count_by_user_since(db: Session, seconds_delta: int = 15):
def base_query(db: Session):
# TODO: allow only some fields to be returned, for example author should remain hidden
#NOTE: load_only is for optimization and not obfuscation, use .with_entities() if needed
return db.query(models.Archive)\
.options(load_only(models.Archive.id, models.Archive.created_at, models.Archive.url, models.Archive.result))\
.filter(models.Archive.deleted == False)
.filter(models.Archive.deleted == False)\
.options(load_only(models.Archive.id, models.Archive.created_at, models.Archive.url, models.Archive.result))
# --------------- TAG

7
src/db/schemas.py
View File

@@ -45,6 +45,13 @@ class SubmitManual(BaseModel):
group_id: str | None = None
tags: set[str] | None = set()
# API RESPONSES BELOW
class ArchiveResult(BaseModel):
id: str
url: str
result: dict
created_at: datetime
class Task(BaseModel):
id: str

8
src/endpoints/default.py
View File

@@ -30,13 +30,13 @@ async def health():
return JSONResponse({"status": "ok"})
@default_router.get("/user/active", summary="Check if the user is active and can use the tool.", response_model=schemas.ActiveUser)
async def active(db: Session = Depends(get_db_dependency), email=Depends(get_user_auth)):
@default_router.get("/user/active", summary="Check if the user is active and can use the tool.")
async def active(db: Session = Depends(get_db_dependency), email=Depends(get_user_auth)) -> schemas.ActiveUser:
return {"active": crud.is_active_user(db, email)}
@default_router.get("/groups", response_model=list[str])
def get_user_groups(db: Session = Depends(get_db_dependency), email=Depends(get_user_auth)):
@default_router.get("/groups")
def get_user_groups(db: Session = Depends(get_db_dependency), email=Depends(get_user_auth)) -> list[str]:
return crud.get_user_groups(db, email)

4
src/endpoints/sheet.py
View File

@@ -12,8 +12,8 @@ from worker.main import create_sheet_task
sheet_router = APIRouter(prefix="/sheet", tags=["Google Spreadsheet operations"])
@sheet_router.post("/archive", status_code=201, summary="Submit a Google Sheet archive request, starts a sheet archiving task.", response_model=schemas.Task, response_description="task_id for the archiving task.")
def archive_sheet(sheet:schemas.SubmitSheet, email = Depends(get_token_or_user_auth)):
@sheet_router.post("/archive", status_code=201, summary="Submit a Google Sheet archive request, starts a sheet archiving task.", response_description="task_id for the archiving task.")
def archive_sheet(sheet:schemas.SubmitSheet, email = Depends(get_token_or_user_auth)) -> schemas.Task:
logger.info(f"SHEET TASK for {sheet=}")
if email == ALLOW_ANY_EMAIL:
email = sheet.author_id or "api-endpoint"

4
src/endpoints/task.py
View File

@@ -14,8 +14,8 @@ from worker.main import celery
task_router = APIRouter(prefix="/task", tags=["Async task operations"])
@task_router.get("/{task_id}", response_model=schemas.TaskResult, summary="Check the status of an async task by its id, works for URLs and Sheet tasks.")
def get_status(task_id, email=Depends(get_token_or_user_auth)):
@task_router.get("/{task_id}", summary="Check the status of an async task by its id, works for URLs and Sheet tasks.")
def get_status(task_id, email=Depends(get_token_or_user_auth)) -> schemas.TaskResult:
logger.info(f"status check for user {email} task {task_id}")
task = AsyncResult(task_id, app=celery)
try:

21
src/endpoints/url.py
View File

@@ -15,8 +15,8 @@ from worker.main import create_archive_task
url_router = APIRouter(prefix="/url", tags=["Single URL operations"])
@url_router.post("/archive", status_code=201, summary="Submit a single URL archive request, starts an archiving task.", response_model=schemas.Task, response_description="task_id for the archiving task, will match the archive id.")
def archive_url(archive: schemas.ArchiveCreate, email=Depends(get_token_or_user_auth)):
@url_router.post("/archive", status_code=201, summary="Submit a single URL archive request, starts an archiving task.", response_description="task_id for the archiving task, will match the archive id.")
def archive_url(archive: schemas.ArchiveCreate, email=Depends(get_token_or_user_auth)) -> schemas.Task:
archive.author_id = email
url = archive.url
logger.info(f"new {archive.public=} task for {email=} and {archive.group_id=}: {url}")
@@ -28,30 +28,31 @@ def archive_url(archive: schemas.ArchiveCreate, email=Depends(get_token_or_user_
return JSONResponse(task_response.model_dump(), status_code=201)
@url_router.get("/search", response_model=list[schemas.Archive], summary="Search for archive entries by URL.")
@url_router.get("/search", summary="Search for archive entries by URL.")
def search_by_url(
url: str, skip: int = 0, limit: int = 25,
archived_after: datetime = None, archived_before: datetime = None,
db: Session = Depends(get_db_dependency),
email=Depends(get_token_or_user_auth)):
email=Depends(get_token_or_user_auth)
) -> list[schemas.ArchiveResult]:
return crud.search_archives_by_url(db, url.strip(), email, skip=skip, limit=limit, archived_after=archived_after, archived_before=archived_before)
@url_router.get("/latest", response_model=list[schemas.Archive], summary="Fetch latest URL archives for the authenticated user.")
def latest(skip: int = 0, limit: int = 25, db: Session = Depends(get_db_dependency), email=Depends(get_user_auth)):
@url_router.get("/latest", summary="Fetch latest URL archives for the authenticated user.")
def latest(skip: int = 0, limit: int = 25, db: Session = Depends(get_db_dependency), email=Depends(get_user_auth)) -> list[schemas.ArchiveResult]:
return crud.search_archives_by_email(db, email, skip=skip, limit=limit)
@url_router.get("/{id}", response_model=schemas.Archive, summary="Fetch a single URL archive by the associated id.")
def lookup(id, db: Session = Depends(get_db_dependency), email=Depends(get_token_or_user_auth)):
@url_router.get("/{id}", summary="Fetch a single URL archive by the associated id.")
def lookup(id, db: Session = Depends(get_db_dependency), email=Depends(get_token_or_user_auth)) -> schemas.ArchiveResult:
archive = crud.get_archive(db, id, email)
if archive is None:
raise HTTPException(status_code=404, detail="Archive not found")
return archive
@url_router.delete("/{id}", response_model=schemas.TaskDelete, summary="Delete a single URL archive by id.")
def delete_task(id, db: Session = Depends(get_db_dependency), email=Depends(get_user_auth)):
@url_router.delete("/{id}", summary="Delete a single URL archive by id.")
def delete_task(id, db: Session = Depends(get_db_dependency), email=Depends(get_user_auth)) -> schemas.TaskDelete:
logger.info(f"deleting url archive task {id} request by {email}")
return JSONResponse({
"id": id,

15
src/tests/endpoints/test_url.py
View File

@@ -38,7 +38,7 @@ def test_search_by_url(client_with_auth, db_session):
assert response.status_code == 200
assert response.json() == []
from db import crud
from db import crud, schemas
for i in range(11):
crud.create_task(db_session, ArchiveCreate(id=f"url-456-{i}", url="https://example.com" if i < 10 else "https://something-else.com", result={}, public=True, author_id="rick@example.com", group_id=None), [], [])
#NB: this insertion is too fast for the ordering to be correct as they are within the same second
@@ -49,6 +49,7 @@ def test_search_by_url(client_with_auth, db_session):
assert "url-456-0" in [i["id"] for i in j]
assert "url-456-9" in [i["id"] for i in j]
assert "url-456-10" not in [i["id"] for i in j]
assert j[0].keys() == schemas.ArchiveResult.model_fields.keys()
response = client_with_auth.get("/url/search?url=https://example.com&limit=5")
assert response.status_code == 200
@@ -76,7 +77,7 @@ def test_latest(client_with_auth, db_session):
assert response.status_code == 200
assert response.json() == []
from db import crud
from db import crud, schemas
for i in range(11):
crud.create_task(db_session, ArchiveCreate(id=f"latest-456-{i}", url="https://example.com", result={}, public=True, author_id="morty@example.com" if i < 10 else "rick@example.com", group_id=None), [], [])
#NB: this insertion is too fast for the ordering to be correct as they are within the same second
@@ -90,6 +91,7 @@ def test_latest(client_with_auth, db_session):
assert "latest-456-0" in [i["id"] for i in j]
assert "latest-456-9" in [i["id"] for i in j]
assert "latest-456-10" not in [i["id"] for i in j]
assert j[0].keys() == schemas.ArchiveResult.model_fields.keys()
response = client_with_auth.get("/url/latest?limit=5")
assert response.status_code == 200
@@ -109,21 +111,16 @@ def test_lookup(client_with_auth, db_session):
assert response.status_code == 404
assert response.json() == {"detail": "Archive not found"}
from db import crud
from db import crud, schemas
crud.create_task(db_session, ArchiveCreate(id="lookup-123-456-789", url="https://example.com", result={}, public=True, author_id="rick@example.com", group_id=None), [], [])
response = client_with_auth.get("/url/lookup-123-456-789")
assert response.status_code == 200
j = response.json()
assert j.keys() == schemas.ArchiveResult.model_fields.keys()
assert j["id"] == "lookup-123-456-789"
assert j["url"] == "https://example.com"
assert j["result"] == {}
assert j["public"] == True
assert j["author_id"] == "rick@example.com"
assert j["group_id"] == None
assert j["tags"] == []
assert j["updated_at"] == None
assert j["rearchive"] == True
def test_delete_task_unauthenticated(client, test_no_auth):