DriveSomethingGreater: guard against empty vin or value

[andig]

No description provided.

[sourcery-ai]

Hey - I've found 1 issue, and left some high level feedback:

• By removing the VIN from parseDataset and the subsequent VIN equality check in update, all datasets are now merged regardless of which vehicle they belong to; if the intent was only to ignore entries with an empty VIN, consider keeping the VIN return and guard while explicitly skipping only when dvin == "".
• The new p.Value == "" filter in parseDataset changes behavior by dropping points that previously would have been included; if this is meant to address a specific case (e.g. bogus VIN entries), consider tightening the condition to that case or documenting why empty values should be ignored across all fields.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- By removing the VIN from `parseDataset` and the subsequent VIN equality check in `update`, all datasets are now merged regardless of which vehicle they belong to; if the intent was only to ignore entries with an empty VIN, consider keeping the VIN return and guard while explicitly skipping only when `dvin == ""`.
- The new `p.Value == ""` filter in `parseDataset` changes behavior by dropping points that previously would have been included; if this is meant to address a specific case (e.g. bogus VIN entries), consider tightening the condition to that case or documenting why empty values should be ignored across all fields.

## Individual Comments

### Comment 1
<location path="vehicle/vw/eudataact/store.go" line_range="118-121" />
<code_context>
 		}

-		dvin, data, err := parseDataset(b)
+		data, err := parseDataset(b)
 		if err != nil {
 			return newest, err
</code_context>
<issue_to_address>
**issue (bug_risk):** Removing VIN filtering may merge data from multiple vehicles into the same store entry.

Previously, `parseDataset` yielded a VIN and `update` skipped datasets whose VIN didn’t match the requested `vin`. Without that check, every dataset from `contentDatasets` is now merged into `v.data`, even if it belongs to another vehicle. If `contentDatasets` can surface multiple or incorrect VINs, this will mix data across vehicles. If the contract now guarantees a single VIN, please enforce it at the boundary (e.g., validate `ds.VIN` in `parseDataset` and fail on mismatch) rather than relying on this implicit behavior.
</issue_to_address>

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}

[sourcery-ai]

issue (bug_risk): Removing VIN filtering may merge data from multiple vehicles into the same store entry.

Previously, parseDataset yielded a VIN and update skipped datasets whose VIN didn’t match the requested vin. Without that check, every dataset from contentDatasets is now merged into v.data, even if it belongs to another vehicle. If contentDatasets can surface multiple or incorrect VINs, this will mix data across vehicles. If the contract now guarantees a single VIN, please enforce it at the boundary (e.g., validate ds.VIN in parseDataset and fail on mismatch) rather than relying on this implicit behavior.