Import dedup transparency + override; bulk transaction actions

Paste-import now returns each skipped duplicate WITH the matched
existing row (id, merchant, date, amount, source) instead of a bare
count, and accepts allow_duplicates to force-import false positives —
the practical fix for same-day identical purchases hashing together
(UX-20; supersedes the BE-08 hash change, which would have orphaned
every existing hash). POST /transactions/bulk applies
delete/set_category/set_deferred to up to 500 ids atomically. 82 tests.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Carlos Escalante
2026-06-10 20:46:23 -06:00
parent 5612f69f11
commit ce3cc69846
3 changed files with 215 additions and 8 deletions

View File

@@ -26,12 +26,29 @@ class PasteImportRequest(BaseModel):
text: str = Field(max_length=1_000_000)
bank: Bank = Bank.BAC
source: TransactionSource = TransactionSource.CREDIT_CARD
# Override for false-positive dedup (legitimate same-day, same-amount
# repeat purchases hash identically) — review UX-20/BE-08.
allow_duplicates: bool = False
class SkippedDuplicate(BaseModel):
line: int
merchant: str
date: str
amount: float
currency: str
existing_id: int
existing_merchant: str
existing_date: str
existing_amount: float
existing_source: str
class PasteImportResult(BaseModel):
imported: int
duplicates: int
errors: list[str]
skipped: list[SkippedDuplicate] = []
def make_reference_hash(date: datetime, merchant: str, amount: float, currency: str) -> str:
@@ -103,6 +120,7 @@ def paste_import(
imported = 0
duplicates = 0
errors: list[str] = []
skipped: list[SkippedDuplicate] = []
lines = req.text.strip().splitlines()
@@ -120,12 +138,28 @@ def paste_import(
parsed["date"], parsed["merchant"], parsed["amount"], parsed["currency"]
)
# Check for duplicates
# Check for duplicates — and SHOW the user what matched instead of
# silently dropping the line (UX-20).
if not req.allow_duplicates:
existing = session.exec(
select(Transaction).where(Transaction.reference == ref_hash)
).first()
if existing:
duplicates += 1
skipped.append(
SkippedDuplicate(
line=i,
merchant=parsed["merchant"],
date=parsed["date"].isoformat(),
amount=parsed["amount"],
currency=parsed["currency"],
existing_id=existing.id or 0,
existing_merchant=existing.merchant,
existing_date=existing.date.isoformat(),
existing_amount=float(existing.amount),
existing_source=existing.source.value,
)
)
continue
tx = Transaction(
@@ -147,4 +181,6 @@ def paste_import(
if imported > 0:
session.commit()
return PasteImportResult(imported=imported, duplicates=duplicates, errors=errors)
return PasteImportResult(
imported=imported, duplicates=duplicates, errors=errors, skipped=skipped
)

View File

@@ -99,6 +99,46 @@ def list_transactions(
return session.exec(query).all()
class BulkActionRequest(BaseModel):
ids: list[int]
action: str # 'delete' | 'set_category' | 'set_deferred'
category_id: Optional[int] = None # for set_category (None clears)
deferred: Optional[bool] = None # for set_deferred
@router.post("/bulk")
def bulk_action(
req: BulkActionRequest,
session: Session = Depends(get_session),
_user: str = Depends(get_current_user),
):
"""Apply one action to many transactions atomically (review 4.4)."""
if not req.ids or len(req.ids) > 500:
raise HTTPException(status_code=400, detail="ids must contain 1-500 entries")
if req.action not in ("delete", "set_category", "set_deferred"):
raise HTTPException(status_code=400, detail=f"Unknown action: {req.action}")
if req.action == "set_deferred" and req.deferred is None:
raise HTTPException(status_code=400, detail="deferred is required for set_deferred")
if req.action == "set_category" and req.category_id is not None:
if session.get(Category, req.category_id) is None:
raise HTTPException(status_code=404, detail="Category not found")
txs = session.exec(
select(Transaction).where(col(Transaction.id).in_(req.ids))
).all()
for tx in txs:
if req.action == "delete":
session.delete(tx)
elif req.action == "set_category":
tx.category_id = req.category_id
session.add(tx)
elif req.action == "set_deferred":
tx.deferred_to_next_cycle = bool(req.deferred)
session.add(tx)
session.commit()
return {"affected": len(txs)}
@router.get("/export")
def export_transactions_csv(
source: Optional[TransactionSource] = None,

View File

@@ -0,0 +1,131 @@
"""Paste-import dedup transparency + override (UX-20) and bulk actions (4.4).
These exercise the endpoint functions directly with a session — no HTTP
stack needed.
"""
from datetime import datetime
from decimal import Decimal
import pytest
from fastapi import HTTPException
from app.api.v1.endpoints.import_transactions import (
PasteImportRequest,
paste_import,
)
from app.api.v1.endpoints.transactions import BulkActionRequest, bulk_action
from app.models.models import Category, Transaction, TransactionSource
LINE = "15/04/2026\tWALMART\\SAN JOSE\\CR\t25,000.50 CRC"
def do_import(session, text=LINE, **kw):
return paste_import(
PasteImportRequest(text=text, **kw), session=session, _user="t"
)
class TestImportReview:
def test_duplicate_is_reported_with_matched_row(self, session):
first = do_import(session)
assert first.imported == 1 and first.duplicates == 0
second = do_import(session)
assert second.imported == 0
assert second.duplicates == 1
assert len(second.skipped) == 1
skip = second.skipped[0]
assert skip.merchant == "WALMART"
assert skip.amount == 25000.50
assert skip.existing_merchant == "WALMART"
assert skip.existing_amount == 25000.50
assert skip.existing_id > 0
def test_allow_duplicates_overrides_dedup(self, session):
do_import(session)
forced = do_import(session, allow_duplicates=True)
assert forced.imported == 1
assert forced.duplicates == 0
assert forced.skipped == []
def make_tx(session, merchant="M", category_id=None):
tx = Transaction(
amount=Decimal("10"),
merchant=merchant,
date=datetime(2026, 4, 1),
category_id=category_id,
source=TransactionSource.CREDIT_CARD,
)
session.add(tx)
session.commit()
session.refresh(tx)
return tx
class TestBulkActions:
def test_bulk_set_category(self, session):
cat = Category(name="Bulk")
session.add(cat)
session.commit()
session.refresh(cat)
txs = [make_tx(session, f"m{i}") for i in range(3)]
result = bulk_action(
BulkActionRequest(
ids=[t.id for t in txs], action="set_category", category_id=cat.id
),
session=session,
_user="t",
)
assert result["affected"] == 3
for t in txs:
session.refresh(t)
assert t.category_id == cat.id
def test_bulk_set_deferred_and_clear_category(self, session):
cat = Category(name="X")
session.add(cat)
session.commit()
session.refresh(cat)
tx = make_tx(session, category_id=cat.id)
bulk_action(
BulkActionRequest(ids=[tx.id], action="set_deferred", deferred=True),
session=session,
_user="t",
)
session.refresh(tx)
assert tx.deferred_to_next_cycle is True
bulk_action(
BulkActionRequest(ids=[tx.id], action="set_category", category_id=None),
session=session,
_user="t",
)
session.refresh(tx)
assert tx.category_id is None
def test_bulk_delete(self, session):
txs = [make_tx(session, f"d{i}") for i in range(2)]
result = bulk_action(
BulkActionRequest(ids=[t.id for t in txs], action="delete"),
session=session,
_user="t",
)
assert result["affected"] == 2
assert session.get(Transaction, txs[0].id) is None
@pytest.mark.parametrize(
"req",
[
BulkActionRequest(ids=[], action="delete"),
BulkActionRequest(ids=[1], action="explode"),
BulkActionRequest(ids=[1], action="set_deferred"), # missing flag
BulkActionRequest(ids=[1], action="set_category", category_id=99999),
],
)
def test_invalid_requests_rejected(self, session, req):
with pytest.raises(HTTPException):
bulk_action(req, session=session, _user="t")