go-ethereum/statediff/indexer/database/file/indexer.go
Elizabeth 3aead03aeb Statediffing geth
* Write state diff to CSV (#2)

* port statediff from 9b7fd9af80/statediff/statediff.go; minor fixes

* integrating state diff extracting, building, and persisting into geth processes

* work towards persisting created statediffs in ipfs; based off github.com/vulcanize/eth-block-extractor

* Add a state diff service

* Remove diff extractor from blockchain

* Update imports

* Move statediff on/off check to geth cmd config

* Update starting state diff service

* Add debugging logs for creating diff

* Add statediff extractor and builder tests and small refactoring

* Start to write statediff to a CSV

* Restructure statediff directory

* Pull CSV publishing methods into their own file

* Reformatting due to go fmt

* Add gomega to vendor dir

* Remove testing focuses

* Update statediff tests to use golang test pkg

instead of ginkgo

- builder_test
- extractor_test
- publisher_test

* Use hexutil.Encode instead of deprecated common.ToHex

* Remove OldValue from DiffBigInt and DiffUint64 fields

* Update builder test

* Remove old storage value from updated accounts

* Remove old values from created/deleted accounts

* Update publisher to account for only storing current account values

* Update service loop and fetching previous block

* Update testing

- remove statediff ginkgo test suite file
- move mocks to their own dir

* Updates per go fmt

* Updates to tests

* Pass statediff mode and path in through cli

* Return filename from publisher

* Remove some duplication in builder

* Remove code field from state diff output

this is the contract byte code, and it can still be obtained by querying
the db by the codeHash

* Consolidate acct diff structs for updated & updated/deleted accts

* Include block number in csv filename

* Clean up error logging

* Cleanup formatting, spelling, etc

* Address PR comments

* Add contract address and storage value to csv

* Refactor accumulating account row in csv publisher

* Add DiffStorage struct

* Add storage key to csv

* Address PR comments

* Fix publisher to include rows for accounts that don't have store updates

* Update builder test after merging in release/1.8

* Update test contract to include storage on contract intialization

- so that we're able to test that storage diffing works for created and
deleted accounts (not just updated accounts).

* Factor out a common trie iterator method in builder

* Apply goimports to statediff

* Apply gosimple changes to statediff

* Gracefully exit geth command(#4)

* Statediff for full node (#6)

* Open a trie from the in-memory database

* Use a node's LeafKey as an identifier instead of the address

It was proving difficult to find look the address up from a given path
with a full node (sometimes the value wouldn't exist in the disk db).
So, instead, for now we are using the node's LeafKey with is a Keccak256
hash of the address, so if we know the address we can figure out which
LeafKey it matches up to.

* Make sure that statediff has been processed before pruning

* Use blockchain stateCache.OpenTrie for storage diffs

* Clean up log lines and remove unnecessary fields from builder

* Apply go fmt changes

* Add a sleep to the blockchain test

* refactoring/reorganizing packages

* refactoring statediff builder and types and adjusted to relay proofs and paths (still need to make this optional)

* refactoring state diff service and adding api which allows for streaming state diff payloads over an rpc websocket subscription

* make proofs and paths optional + compress service loop into single for loop (may be missing something here)

* option to process intermediate nodes

* make state diff rlp serializable

* cli parameter to limit statediffing to select account addresses + test

* review fixes and fixes for issues ran into in integration

* review fixes; proper method signature for api; adjust service so that statediff processing is halted/paused until there is at least one subscriber listening for the results

* adjust buffering to improve stability; doc.go; fix notifier
err handling

* relay receipts with the rest of the data + review fixes/changes

* rpc method to get statediff at specific block; requires archival node or the block be within the pruning range

* fix linter issues

* include total difficulty to the payload

* fix state diff builder: emit actual leaf nodes instead of value nodes; diff on the leaf not on the value; emit correct path for intermediate nodes

* adjust statediff builder tests to changes and extend to test intermediate nodes; golint

* add genesis block to test; handle block 0 in StateDiffAt

* rlp files for mainnet blocks 0-3, for tests

* builder test on mainnet blocks

* common.BytesToHash(path) => crypto.Keaccak256(hash) in builder; BytesToHash produces same hash for e.g. []byte{} and []byte{\x00} - prefix \x00 steps are inconsequential to the hash result

* complete tests for early mainnet blocks

* diff type for representing deleted accounts

* fix builder so that we handle account deletions properly and properly diff storage when an account is moved to a new path; update params

* remove cli params; moving them to subscriber defined

* remove unneeded bc methods

* update service and api; statediffing params are now defined by user through api rather than by service provider by cli

* update top level tests

* add ability to watch specific storage slots (leaf keys) only

* comments; explain logic

* update mainnet blocks test

* update api_test.go

* storage leafkey filter test

* cleanup chain maker

* adjust chain maker for tests to add an empty account in block1 and switch to EIP-158 afterwards (now we just need to generate enough accounts until one causes the empty account to be touched and removed post-EIP-158 so we can simulate and test that process...); also added 2 new blocks where more contract storage is set and old slots are set to zero so they are removed so we can test that

* found an account whose creation causes the empty account to be moved to a new path; this should count as 'touching; the empty account and cause it to be removed according to eip-158... but it doesn't

* use new contract in unit tests that has self-destruct ability, so we can test eip-158 since simply moving an account to new path doesn't count as 'touchin' it

* handle storage deletions

* tests for eip-158 account removal and storage value deletions; there is one edge case left to test where we remove 1 account when only two exist such that the remaining account is moved up and replaces the root branch node

* finish testing known edge cases

* add endpoint to fetch all state and storage nodes at a given blockheight; useful for generating a recent atate cache/snapshot that we can diff forward from rather than needing to collect all diffs from genesis

* test for state trie builder

* if statediffing is on, lock tries in triedb until the statediffing service signals they are done using them

* fix mock blockchain; golint; bump patch

* increase maxRequestContentLength; bump patch

* log the sizes of the state objects we are sending

* CI build (#20)

* CI: run build on PR and on push to master

* CI: debug building geth

* CI: fix coping file

* CI: fix coping file v2

* CI: temporary upload file to release asset

* CI: get release upload_url by tag, upload asset to current relase

* CI: fix tag name

* fix ci build on statediff_at_anyblock-1.9.11 branch

* fix publishing assets in release

* use context deadline for timeout in eth_call

* collect and emit codehash=>code mappings for state objects

* subscription endpoint for retrieving all the codehash=>code mappings that exist at provided height

* Implement WriteStateDiffAt

* Writes state diffs directly to postgres

* Adds CLI flags to configure PG

* Refactors builder output with callbacks

* Copies refactored postgres handling code from ipld-eth-indexer

* rename PostgresCIDWriter.{index->upsert}*

* rm unused

* output code & codehash iteratively

* had to rf some types for this

* prometheus metrics output

* duplicate recent eth-indexer changes

* migrations and metrics...

* [wip] prom.Init() here? another CLI flag?

* tidy & DRY

* statediff WriteLoop service + CLI flag

* [wip] update test mocks

* todo - do something meaningful to test write loop

* logging

* use geth log

* port tests to go testing

* drop ginkgo/gomega

* fix and cleanup tests

* fail before defer statement

* delete vendor/ dir

* fixes after rebase onto 1.9.23

* fix API registration

* use golang 1.15.5 version (#34)

* bump version meta; add 0.0.11 branch to actions

* bump version meta; update github actions workflows

* statediff: refactor metrics

* Remove redundant statediff/indexer/prom tooling and use existing
prometheus integration.

* "indexer" namespace for metrics

* add reporting loop for db metrics

* doc

* metrics for statediff stats

* metrics namespace/subsystem = statediff/{indexer,service}

* statediff: use a worker pool (for direct writes)

* fix test

* fix chain event subscription

* log tweaks

* func name

* unused import

* intermediate chain event channel for metrics

* update github actions; linting

* add poststate and status to receipt ipld indexes

* stateDiffFor endpoints for fetching or writing statediff object by blockhash; bump statediff version

* fixes after rebase on to v1.10.1

* update github actions and version meta; go fmt

* add leaf key to removed 'nodes'

* include Postgres migrations and schema

* service documentation

* touching up

* update github actions after rebase

* fix connection leak (misplaced defer) and perform proper rollback on errs

* improve error logging; handle PushBlock internal err

* build docker image and publish it to Docker Hub on release

* add access list tx to unit tests

* MarshalBinary and UnmarshalBinary methods for receipt

* fix error caused by 2718 by using MarshalBinary instead of EncodeRLP methods

* ipld encoding/decoding tests

* update TxModel; add AccessListElementModel

* index tx type and access lists

* add access list metrics

* unit tests for tx_type and access list table

* unit tests for receipt marshal/unmarshal binary methods

* improve documentation of the encoding methods

* fix issue identified in linting

* update github actions and version meta after rebase

* unit test that fails undeterministically on eip2930 txs, giving same error we are seeing in prod

* Include genesis block state diff.

* documentation on versioning, rebasing, releasing; bump version meta

* Add geth and statediff unit test to CI.

* Set pgpassword in env.

* Added comments.

* Add new major branch to github action.

* Add support for Dynamic txn(EIP-1559).

* Update version meta to 0.0.24

* Verify block base fee in test.

* Fix base_fee type and add backward compatible test.

* Remove type definition for AccessListElementModel

* Change basefee to int64/bigint.

* block and uncle reward in PoA network = 0  (#87)

* in PoA networks there is no block and uncle rewards

* bump meta version

* (cherry picked from commit b64ca14689)

* Use Ropsten to test block reward.

* Add Makefile target to build static linux binaries.

* Strip symbol tables from static binaries.

* Fix block_fee to support NULL values.

* bump version meta.

* Add new major branch to github action.

* rename doc.go to README.md

* Create a seperate table for storing logs

* Bump statediff version to 0.0.26.

* add btree index to state/storage_cids.node_type; updated schema

* Dedup receipt data.

* Fix linter errors.

* Address comments.

* Bump statediff version to 0.0.27.

* new cli flag for initializing db first time service is ran

* only write Removed node ipld block (on db init) and reuse constant cid and mhkey

* test new handling of Removed nodes; don't require init flag

* log metrics

* Add new major branch to github action.

* Fix build.

* Update golang version in CI.

* Use ipld-eth-db in testing.

* Remove migration from repo.

* Add new major branch to github action.

*Use `GetTd` instead of `GetTdByHash`
6289137827

* Add new major branch to github action.

* Report DB metrics

* batch inserts to public.blocks

* v2 => v3  major refactor

* fixes and cli integration for new options

* update example command in readme

* ashwin's fix for failing pgx unit test

* update to use new schema; fix pgx driver

* indexer that writes sql stmts out to a file

* cli integration

* fix unit tests

* use node_id as PK/FK

* misc fixes/adjustments

* update README

* cleanup; more unit tests

* basefee is big.Int, it won't always fit in int64

* adjust for schema updates

* finish unit tests

* test harnest for arbitrary mainnet blocks and receipts

* cache problematic block locally for quicker testing/easier CI testing

* fix issue with log/logTrie processing

* remove some unecessary hashing operations

* handle edge case

* add more 'bad blocks' to mainnet_tests

* increase file write buffer size

* increase buffer further

* fix rct trie multicodec type

* extend testing

* log trie fk fix

* bump statediff meta version; use db v0.3.0 in compose

* skip file writing tests in CI, for now

* prevent parallel execution of tests in different pkgs (suspect this is what causes our deadlock to show up only in CI test env)
adjust write buffering

* fix rct unit tests

* fix README formatting

* port retry on deadlock detection feature

* new workflow on-'master' targets

* update version meta

* improve test coverage for logs

* fix possible race condition

* fix CI

* check tx pool state at end of unit tests

* better logging of rollbacks and dead lock retries
2022-02-16 14:40:08 -06:00

481 lines
16 KiB
Go

// VulcanizeDB
// Copyright © 2021 Vulcanize
// This program is free software: you can redistribute it and/or modify
// it under the terms of the GNU Affero General Public License as published by
// the Free Software Foundation, either version 3 of the License, or
// (at your option) any later version.
// This program is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU Affero General Public License for more details.
// You should have received a copy of the GNU Affero General Public License
// along with this program. If not, see <http://www.gnu.org/licenses/>.
package file
import (
"context"
"errors"
"fmt"
"math/big"
"os"
"sync"
"time"
"github.com/ipfs/go-cid"
node "github.com/ipfs/go-ipld-format"
"github.com/multiformats/go-multihash"
"github.com/ethereum/go-ethereum/common"
"github.com/ethereum/go-ethereum/core/types"
"github.com/ethereum/go-ethereum/crypto"
"github.com/ethereum/go-ethereum/log"
"github.com/ethereum/go-ethereum/metrics"
"github.com/ethereum/go-ethereum/params"
"github.com/ethereum/go-ethereum/rlp"
"github.com/ethereum/go-ethereum/statediff/indexer/interfaces"
ipld2 "github.com/ethereum/go-ethereum/statediff/indexer/ipld"
"github.com/ethereum/go-ethereum/statediff/indexer/models"
"github.com/ethereum/go-ethereum/statediff/indexer/shared"
sdtypes "github.com/ethereum/go-ethereum/statediff/types"
)
const defaultFilePath = "./statediff.sql"
var _ interfaces.StateDiffIndexer = &StateDiffIndexer{}
var (
indexerMetrics = RegisterIndexerMetrics(metrics.DefaultRegistry)
)
// StateDiffIndexer satisfies the indexer.StateDiffIndexer interface for ethereum statediff objects on top of a void
type StateDiffIndexer struct {
fileWriter *SQLWriter
chainConfig *params.ChainConfig
nodeID string
wg *sync.WaitGroup
}
// NewStateDiffIndexer creates a void implementation of interfaces.StateDiffIndexer
func NewStateDiffIndexer(ctx context.Context, chainConfig *params.ChainConfig, config Config) (*StateDiffIndexer, error) {
filePath := config.FilePath
if filePath == "" {
filePath = defaultFilePath
}
if _, err := os.Stat(filePath); !errors.Is(err, os.ErrNotExist) {
return nil, fmt.Errorf("cannot create file, file (%s) already exists", filePath)
}
file, err := os.Create(filePath)
if err != nil {
return nil, fmt.Errorf("unable to create file (%s), err: %v", filePath, err)
}
log.Info("Writing statediff SQL statements to file", "file", filePath)
w := NewSQLWriter(file)
wg := new(sync.WaitGroup)
w.Loop()
w.upsertNode(config.NodeInfo)
w.upsertIPLDDirect(shared.RemovedNodeMhKey, []byte{})
return &StateDiffIndexer{
fileWriter: w,
chainConfig: chainConfig,
nodeID: config.NodeInfo.ID,
wg: wg,
}, nil
}
// ReportDBMetrics has nothing to report for dump
func (sdi *StateDiffIndexer) ReportDBMetrics(time.Duration, <-chan bool) {}
// PushBlock pushes and indexes block data in sql, except state & storage nodes (includes header, uncles, transactions & receipts)
// Returns an initiated DB transaction which must be Closed via defer to commit or rollback
func (sdi *StateDiffIndexer) PushBlock(block *types.Block, receipts types.Receipts, totalDifficulty *big.Int) (interfaces.Batch, error) {
start, t := time.Now(), time.Now()
blockHash := block.Hash()
blockHashStr := blockHash.String()
height := block.NumberU64()
traceMsg := fmt.Sprintf("indexer stats for statediff at %d with hash %s:\r\n", height, blockHashStr)
transactions := block.Transactions()
// Derive any missing fields
if err := receipts.DeriveFields(sdi.chainConfig, blockHash, height, transactions); err != nil {
return nil, err
}
// Generate the block iplds
headerNode, uncleNodes, txNodes, txTrieNodes, rctNodes, rctTrieNodes, logTrieNodes, logLeafNodeCIDs, rctLeafNodeCIDs, err := ipld2.FromBlockAndReceipts(block, receipts)
if err != nil {
return nil, fmt.Errorf("error creating IPLD nodes from block and receipts: %v", err)
}
if len(txNodes) != len(rctNodes) || len(rctNodes) != len(rctLeafNodeCIDs) {
return nil, fmt.Errorf("expected number of transactions (%d), receipts (%d), and receipt trie leaf nodes (%d) to be equal", len(txNodes), len(rctNodes), len(rctLeafNodeCIDs))
}
if len(txTrieNodes) != len(rctTrieNodes) {
return nil, fmt.Errorf("expected number of tx trie (%d) and rct trie (%d) nodes to be equal", len(txTrieNodes), len(rctTrieNodes))
}
// Calculate reward
var reward *big.Int
// in PoA networks block reward is 0
if sdi.chainConfig.Clique != nil {
reward = big.NewInt(0)
} else {
reward = shared.CalcEthBlockReward(block.Header(), block.Uncles(), block.Transactions(), receipts)
}
t = time.Now()
blockTx := &BatchTx{
BlockNumber: height,
submit: func(self *BatchTx, err error) error {
tDiff := time.Since(t)
indexerMetrics.tStateStoreCodeProcessing.Update(tDiff)
traceMsg += fmt.Sprintf("state, storage, and code storage processing time: %s\r\n", tDiff.String())
t = time.Now()
sdi.fileWriter.Flush()
tDiff = time.Since(t)
indexerMetrics.tPostgresCommit.Update(tDiff)
traceMsg += fmt.Sprintf("postgres transaction commit duration: %s\r\n", tDiff.String())
traceMsg += fmt.Sprintf(" TOTAL PROCESSING DURATION: %s\r\n", time.Since(start).String())
log.Debug(traceMsg)
return err
},
}
tDiff := time.Since(t)
indexerMetrics.tFreePostgres.Update(tDiff)
traceMsg += fmt.Sprintf("time spent waiting for free postgres tx: %s:\r\n", tDiff.String())
t = time.Now()
// write header, collect headerID
headerID := sdi.processHeader(block.Header(), headerNode, reward, totalDifficulty)
tDiff = time.Since(t)
indexerMetrics.tHeaderProcessing.Update(tDiff)
traceMsg += fmt.Sprintf("header processing time: %s\r\n", tDiff.String())
t = time.Now()
// write uncles
sdi.processUncles(headerID, height, uncleNodes)
tDiff = time.Since(t)
indexerMetrics.tUncleProcessing.Update(tDiff)
traceMsg += fmt.Sprintf("uncle processing time: %s\r\n", tDiff.String())
t = time.Now()
// write receipts and txs
err = sdi.processReceiptsAndTxs(processArgs{
headerID: headerID,
blockNumber: block.Number(),
receipts: receipts,
txs: transactions,
rctNodes: rctNodes,
rctTrieNodes: rctTrieNodes,
txNodes: txNodes,
txTrieNodes: txTrieNodes,
logTrieNodes: logTrieNodes,
logLeafNodeCIDs: logLeafNodeCIDs,
rctLeafNodeCIDs: rctLeafNodeCIDs,
})
if err != nil {
return nil, err
}
tDiff = time.Since(t)
indexerMetrics.tTxAndRecProcessing.Update(tDiff)
traceMsg += fmt.Sprintf("tx and receipt processing time: %s\r\n", tDiff.String())
t = time.Now()
return blockTx, err
}
// processHeader write a header IPLD insert SQL stmt to a file
// it returns the headerID
func (sdi *StateDiffIndexer) processHeader(header *types.Header, headerNode node.Node, reward, td *big.Int) string {
sdi.fileWriter.upsertIPLDNode(headerNode)
var baseFee *string
if header.BaseFee != nil {
baseFee = new(string)
*baseFee = header.BaseFee.String()
}
headerID := header.Hash().String()
sdi.fileWriter.upsertHeaderCID(models.HeaderModel{
NodeID: sdi.nodeID,
CID: headerNode.Cid().String(),
MhKey: shared.MultihashKeyFromCID(headerNode.Cid()),
ParentHash: header.ParentHash.String(),
BlockNumber: header.Number.String(),
BlockHash: headerID,
TotalDifficulty: td.String(),
Reward: reward.String(),
Bloom: header.Bloom.Bytes(),
StateRoot: header.Root.String(),
RctRoot: header.ReceiptHash.String(),
TxRoot: header.TxHash.String(),
UncleRoot: header.UncleHash.String(),
Timestamp: header.Time,
Coinbase: header.Coinbase.String(),
})
return headerID
}
// processUncles writes uncle IPLD insert SQL stmts to a file
func (sdi *StateDiffIndexer) processUncles(headerID string, blockNumber uint64, uncleNodes []*ipld2.EthHeader) {
// publish and index uncles
for _, uncleNode := range uncleNodes {
sdi.fileWriter.upsertIPLDNode(uncleNode)
var uncleReward *big.Int
// in PoA networks uncle reward is 0
if sdi.chainConfig.Clique != nil {
uncleReward = big.NewInt(0)
} else {
uncleReward = shared.CalcUncleMinerReward(blockNumber, uncleNode.Number.Uint64())
}
sdi.fileWriter.upsertUncleCID(models.UncleModel{
HeaderID: headerID,
CID: uncleNode.Cid().String(),
MhKey: shared.MultihashKeyFromCID(uncleNode.Cid()),
ParentHash: uncleNode.ParentHash.String(),
BlockHash: uncleNode.Hash().String(),
Reward: uncleReward.String(),
})
}
}
// processArgs bundles arguments to processReceiptsAndTxs
type processArgs struct {
headerID string
blockNumber *big.Int
receipts types.Receipts
txs types.Transactions
rctNodes []*ipld2.EthReceipt
rctTrieNodes []*ipld2.EthRctTrie
txNodes []*ipld2.EthTx
txTrieNodes []*ipld2.EthTxTrie
logTrieNodes [][]node.Node
logLeafNodeCIDs [][]cid.Cid
rctLeafNodeCIDs []cid.Cid
}
// processReceiptsAndTxs writes receipt and tx IPLD insert SQL stmts to a file
func (sdi *StateDiffIndexer) processReceiptsAndTxs(args processArgs) error {
// Process receipts and txs
signer := types.MakeSigner(sdi.chainConfig, args.blockNumber)
for i, receipt := range args.receipts {
for _, logTrieNode := range args.logTrieNodes[i] {
sdi.fileWriter.upsertIPLDNode(logTrieNode)
}
txNode := args.txNodes[i]
sdi.fileWriter.upsertIPLDNode(txNode)
// index tx
trx := args.txs[i]
txID := trx.Hash().String()
var val string
if trx.Value() != nil {
val = trx.Value().String()
}
// derive sender for the tx that corresponds with this receipt
from, err := types.Sender(signer, trx)
if err != nil {
return fmt.Errorf("error deriving tx sender: %v", err)
}
txModel := models.TxModel{
HeaderID: args.headerID,
Dst: shared.HandleZeroAddrPointer(trx.To()),
Src: shared.HandleZeroAddr(from),
TxHash: txID,
Index: int64(i),
Data: trx.Data(),
CID: txNode.Cid().String(),
MhKey: shared.MultihashKeyFromCID(txNode.Cid()),
Type: trx.Type(),
Value: val,
}
sdi.fileWriter.upsertTransactionCID(txModel)
// index access list if this is one
for j, accessListElement := range trx.AccessList() {
storageKeys := make([]string, len(accessListElement.StorageKeys))
for k, storageKey := range accessListElement.StorageKeys {
storageKeys[k] = storageKey.Hex()
}
accessListElementModel := models.AccessListElementModel{
TxID: txID,
Index: int64(j),
Address: accessListElement.Address.Hex(),
StorageKeys: storageKeys,
}
sdi.fileWriter.upsertAccessListElement(accessListElementModel)
}
// this is the contract address if this receipt is for a contract creation tx
contract := shared.HandleZeroAddr(receipt.ContractAddress)
var contractHash string
if contract != "" {
contractHash = crypto.Keccak256Hash(common.HexToAddress(contract).Bytes()).String()
}
// index receipt
if !args.rctLeafNodeCIDs[i].Defined() {
return fmt.Errorf("invalid receipt leaf node cid")
}
rctModel := &models.ReceiptModel{
TxID: txID,
Contract: contract,
ContractHash: contractHash,
LeafCID: args.rctLeafNodeCIDs[i].String(),
LeafMhKey: shared.MultihashKeyFromCID(args.rctLeafNodeCIDs[i]),
LogRoot: args.rctNodes[i].LogRoot.String(),
}
if len(receipt.PostState) == 0 {
rctModel.PostStatus = receipt.Status
} else {
rctModel.PostState = common.Bytes2Hex(receipt.PostState)
}
sdi.fileWriter.upsertReceiptCID(rctModel)
// index logs
logDataSet := make([]*models.LogsModel, len(receipt.Logs))
for idx, l := range receipt.Logs {
topicSet := make([]string, 4)
for ti, topic := range l.Topics {
topicSet[ti] = topic.Hex()
}
if !args.logLeafNodeCIDs[i][idx].Defined() {
return fmt.Errorf("invalid log cid")
}
logDataSet[idx] = &models.LogsModel{
ReceiptID: txID,
Address: l.Address.String(),
Index: int64(l.Index),
Data: l.Data,
LeafCID: args.logLeafNodeCIDs[i][idx].String(),
LeafMhKey: shared.MultihashKeyFromCID(args.logLeafNodeCIDs[i][idx]),
Topic0: topicSet[0],
Topic1: topicSet[1],
Topic2: topicSet[2],
Topic3: topicSet[3],
}
}
sdi.fileWriter.upsertLogCID(logDataSet)
}
// publish trie nodes, these aren't indexed directly
for i, n := range args.txTrieNodes {
sdi.fileWriter.upsertIPLDNode(n)
sdi.fileWriter.upsertIPLDNode(args.rctTrieNodes[i])
}
return nil
}
// PushStateNode writes a state diff node object (including any child storage nodes) IPLD insert SQL stmt to a file
func (sdi *StateDiffIndexer) PushStateNode(batch interfaces.Batch, stateNode sdtypes.StateNode, headerID string) error {
// publish the state node
if stateNode.NodeType == sdtypes.Removed {
// short circuit if it is a Removed node
// this assumes the db has been initialized and a public.blocks entry for the Removed node is present
stateModel := models.StateNodeModel{
HeaderID: headerID,
Path: stateNode.Path,
StateKey: common.BytesToHash(stateNode.LeafKey).String(),
CID: shared.RemovedNodeStateCID,
MhKey: shared.RemovedNodeMhKey,
NodeType: stateNode.NodeType.Int(),
}
sdi.fileWriter.upsertStateCID(stateModel)
return nil
}
stateCIDStr, stateMhKey, err := sdi.fileWriter.upsertIPLDRaw(ipld2.MEthStateTrie, multihash.KECCAK_256, stateNode.NodeValue)
if err != nil {
return fmt.Errorf("error generating and cacheing state node IPLD: %v", err)
}
stateModel := models.StateNodeModel{
HeaderID: headerID,
Path: stateNode.Path,
StateKey: common.BytesToHash(stateNode.LeafKey).String(),
CID: stateCIDStr,
MhKey: stateMhKey,
NodeType: stateNode.NodeType.Int(),
}
// index the state node
sdi.fileWriter.upsertStateCID(stateModel)
// if we have a leaf, decode and index the account data
if stateNode.NodeType == sdtypes.Leaf {
var i []interface{}
if err := rlp.DecodeBytes(stateNode.NodeValue, &i); err != nil {
return fmt.Errorf("error decoding state leaf node rlp: %s", err.Error())
}
if len(i) != 2 {
return fmt.Errorf("eth IPLDPublisher expected state leaf node rlp to decode into two elements")
}
var account types.StateAccount
if err := rlp.DecodeBytes(i[1].([]byte), &account); err != nil {
return fmt.Errorf("error decoding state account rlp: %s", err.Error())
}
accountModel := models.StateAccountModel{
HeaderID: headerID,
StatePath: stateNode.Path,
Balance: account.Balance.String(),
Nonce: account.Nonce,
CodeHash: account.CodeHash,
StorageRoot: account.Root.String(),
}
sdi.fileWriter.upsertStateAccount(accountModel)
}
// if there are any storage nodes associated with this node, publish and index them
for _, storageNode := range stateNode.StorageNodes {
if storageNode.NodeType == sdtypes.Removed {
// short circuit if it is a Removed node
// this assumes the db has been initialized and a public.blocks entry for the Removed node is present
storageModel := models.StorageNodeModel{
HeaderID: headerID,
StatePath: stateNode.Path,
Path: storageNode.Path,
StorageKey: common.BytesToHash(storageNode.LeafKey).String(),
CID: shared.RemovedNodeStorageCID,
MhKey: shared.RemovedNodeMhKey,
NodeType: storageNode.NodeType.Int(),
}
sdi.fileWriter.upsertStorageCID(storageModel)
continue
}
storageCIDStr, storageMhKey, err := sdi.fileWriter.upsertIPLDRaw(ipld2.MEthStorageTrie, multihash.KECCAK_256, storageNode.NodeValue)
if err != nil {
return fmt.Errorf("error generating and cacheing storage node IPLD: %v", err)
}
storageModel := models.StorageNodeModel{
HeaderID: headerID,
StatePath: stateNode.Path,
Path: storageNode.Path,
StorageKey: common.BytesToHash(storageNode.LeafKey).String(),
CID: storageCIDStr,
MhKey: storageMhKey,
NodeType: storageNode.NodeType.Int(),
}
sdi.fileWriter.upsertStorageCID(storageModel)
}
return nil
}
// PushCodeAndCodeHash writes code and codehash pairs insert SQL stmts to a file
func (sdi *StateDiffIndexer) PushCodeAndCodeHash(batch interfaces.Batch, codeAndCodeHash sdtypes.CodeAndCodeHash) error {
// codec doesn't matter since db key is multihash-based
mhKey, err := shared.MultihashKeyFromKeccak256(codeAndCodeHash.Hash)
if err != nil {
return fmt.Errorf("error deriving multihash key from codehash: %v", err)
}
sdi.fileWriter.upsertIPLDDirect(mhKey, codeAndCodeHash.Code)
return nil
}
// Close satisfies io.Closer
func (sdi *StateDiffIndexer) Close() error {
return sdi.fileWriter.Close()
}