docs: Fix proof query example errors

[CryptoKass]

Overview

This PR fixes two errors/typos in the "Proof Queries" example code, making it easier to for readers to follow.

1. toRowProofs missing return statement. This code cannot compile.
2. Incorrect handling of dataRoot in submitFraudProof always leading to a slice bounds out of range error.
   • The example provides blockRes.Block.DataHash – which is always 32 bytes long, as the dataRoot to the submitFraudProof function. The submitFraudProof function then attempts to get slice that is out of bounds for i, b := range dataRoot[58:].

Missing return statement:

The function signature for toRowProofs claims it should return []client.BinaryMerkleProof, but there is no return statement.

func toRowProofs(proofs []*merkle.Proof) []client.BinaryMerkleProof {
	rowProofs := make([]client.BinaryMerkleProof, len(proofs))
	for i, proof := range proofs {
		sideNodes := make( [][32]byte, len(proof.Aunts))
		for j, sideNode :=  range proof.Aunts {
			var bzSideNode [32]byte
			for k, b := range sideNode {
				bzSideNode[k] = b
			}
			sideNodes[j] = bzSideNode
		}
 		rowProofs[i] = client.BinaryMerkleProof{
			SideNodes: sideNodes,
			Key:       big.NewInt(proof.Index),
			NumLeaves: big.NewInt(proof.Total),
		}
	}
	// missing return statement. 
	// this function must return type []client.BinaryMerkleProof
}

DataRoot slice bounds out of range

The example calls submitFraudProof, providing a 32 byte dataHash as the dataRoot, the called function then attempts to create a slice starting at the 58th byte, which is out of bounds.

func verify() error {
        // ...
	err = submitFraudProof(
		ctx,
		simpleRollupWrapper,
		sharesProof,
		event.ProofNonce.Uint64(),
		uint64(tx.Height),
		dcProof.Proof,
		blockRes.Block.DataHash, // DataHash is always 32 bytes
	)

	return nil
}

func submitFraudProof(
	ctx context.Context,
	simpleRollup *client.Wrappers,
	sharesProof types.ShareProof,
	nonce uint64,
	height uint64,
	dataRootInclusionProof merkle.Proof,
	dataRoot []byte,
) error {
	var blockDataRoot [32]byte
	for i, b := range dataRoot[58:] {  // slice out of bounds as dataRoot/dataHash is always 32 bytes
		blockDataRoot[i] = b
	}

Checklist

• New and updated code has appropriate documentation
• New and updated code has new and/or updated testing
• Required CI checks are passing
• Visual proof for any user facing features like CLI or documentation updates
• Linked issues closed with keywords

Summary by CodeRabbit

• New Features
  • Introduced a copy operation for more efficient data handling in fraud proof submissions.
• Refactor
  • Improved clarity in the fraud proof process by explicitly returning rowProofs from a function.

[coderabbitai]

Walkthrough

The recent update introduces enhancements to the blockchain's fraud proof mechanisms. A notable addition is the copy operation, which streamlines the process of copying dataRoot into blockDataRoot within the submitFraudProof function. Furthermore, the toRowProofs function has been refined to explicitly return rowProofs, improving clarity and functionality in handling fraud proofs.

Changes

Files	Change Summaries
developers/.../proof-queries.md	- Added copy operation in submitFraudProof. - toRowProofs now explicitly returns rowProofs.

🐇✨
In the realm of code, where proofs doth lie,
A rabbit hopped, beneath the digital sky.
With a copy and return, it made its mark,
Lighting up the blockchain, with a spark.
"To secure and to verify," it sang with glee,
A whimsical ode, to data integrity.
🌟🐾

Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media?

Share

• X
• Mastodon
• Reddit
• LinkedIn

---

Tips

Chat

There are 3 ways to chat with CodeRabbit:

• Review comments: Directly reply to a review comment made by CodeRabbit. Example:
  • I pushed a fix in commit <commit_id>.
  • Generate unit testing code for this file.
  • Open a follow-up GitHub issue for this discussion.
• Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
  • @coderabbitai generate unit testing code for this file.
  • @coderabbitai modularize this function.
• PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
  • @coderabbitai generate interesting stats about this repository and render them as a table.
  • @coderabbitai show all the console.log statements in this repository.
  • @coderabbitai read src/utils.ts and generate unit testing code.
  • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (invoked as PR comments)

• @coderabbitai pause to pause the reviews on a PR.
• @coderabbitai resume to resume the paused reviews.
• @coderabbitai review to trigger a review. This is useful when automatic reviews are disabled for the repository.
• @coderabbitai resolve resolve all the CodeRabbit review comments.
• @coderabbitai help to get help.

Additionally, you can add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.

CodeRabbit Configration File (.coderabbit.yaml)

• You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
• The JSON schema for the configuration file is available here.
• If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/coderabbit-overrides.v2.json

CodeRabbit Discord Community

Join our Discord Community to get help, request features, and share feedback.

[coderabbitai]

Actionable comments posted: 2

Review Status

Configuration used: CodeRabbit UI

Commits

Files that changed from the base of the PR and between d809af6 and cdc151f.

Files selected for processing (1)

• developers/blobstream-proof-queries.md (3 hunks)

Additional Context Used

Additional comments not posted (1)

developers/blobstream-proof-queries.md (1)

1003-1003: The copy operation in the submitFraudProof function is correctly implemented, but it's important to ensure that the source slice (dataRoot) is not shorter than the destination array (blockDataRoot). This is crucial to avoid runtime panics due to slice bounds out of range.

Verification successful

To verify the length of dataRoot before the copy operation, we need to examine the code more closely around the copy operation for any length checks or assignments ensuring dataRoot has at least 32 bytes. Let's proceed with a new script to gather this information.

---

The verification process has confirmed that there's no explicit length check or assignment ensuring dataRoot has at least 32 bytes before the copy operation in the provided context. This aligns with the concern raised in the review comment about the potential risk of runtime panics if dataRoot is shorter than the destination array blockDataRoot. Therefore, the review comment is accurate.

Scripts Executed

The following scripts were executed for the analysis:

---

Script:

#!/bin/bash
# Verify that dataRoot slice has a length of at least 32 bytes before the copy operation.
grep -B 5 "copy(blockDataRoot\[:\], dataRoot)" developers/blobstream-proof-queries.md | grep "dataRoot \[\]byte"

Length of output: 132

---

---

Script:

#!/bin/bash
# Look for any length checks or assignments to `dataRoot` ensuring it has at least 32 bytes before the copy operation.
grep -B 10 "copy(blockDataRoot\[:\], dataRoot)" developers/blobstream-proof-queries.md

Length of output: 355

[CryptoKass]

DataRoot slice bounds out of range fixed

missing return fixed

[jcstein]

thank you for fixing this and for the PR @CryptoKass

[rach-id]

We can use the data root directly without making a copy. For some reason, I thought that the data root would also contain the min-max namespace. Good catch 🙏