ipld-eth-statedb/bycid/trie/trie.go

// Package trie implements Merkle Patricia Tries.
package trie

import (
	"bytes"
	"fmt"

	"github.com/ethereum/go-ethereum/common"
	"github.com/ethereum/go-ethereum/crypto"

	"github.com/ethereum/go-ethereum/statediff/indexer/ipld"
)

var (
	// emptyRoot is the known root hash of an empty trie.
	emptyRoot = common.HexToHash("56e81f171bcc55a6ff8345e692c0f86e5b48e01b996cadc001622fb5e363b421")

	// emptyState is the known hash of an empty state trie entry.
	emptyState = crypto.Keccak256Hash(nil)
)

// Trie is a Merkle Patricia Trie. Use New to create a trie that sits on
// top of a database. Whenever trie performs a commit operation, the generated
// nodes will be gathered and returned in a set. Once the trie is committed,
// it's not usable anymore. Callers have to re-create the trie with new root
// based on the updated trie database.
//
// Trie is not safe for concurrent use.
type Trie struct {
	root  node
	owner common.Hash

	// Keep track of the number leaves which have been inserted since the last
	// hashing operation. This number will not directly map to the number of
	// actually unhashed nodes.
	unhashed int

	// db is the handler trie can retrieve nodes from. It's
	// only for reading purpose and not available for writing.
	db *Database

	// Multihash codec for key encoding
	codec uint64
}

// New creates a trie with an existing root node from db and an assigned
// owner for storage proximity.
//
// If root is the zero hash or the sha3 hash of an empty string, the
// trie is initially empty and does not require a database. Otherwise,
// New will panic if db is nil and returns a MissingNodeError if root does
// not exist in the database. Accessing the trie loads nodes from db on demand.
func New(owner common.Hash, root common.Hash, db *Database, codec uint64) (*Trie, error) {
	trie := &Trie{
		owner: owner,
		db:    db,
		codec: codec,
	}
	if root != (common.Hash{}) && root != emptyRoot {
		rootnode, err := trie.resolveHash(root[:], nil)
		if err != nil {
			return nil, err
		}
		trie.root = rootnode
	}
	return trie, nil
}

// NewEmpty is a shortcut to create empty tree. It's mostly used in tests.
func NewEmpty(db *Database) *Trie {
	tr, _ := New(common.Hash{}, common.Hash{}, db, ipld.MEthStateTrie)
	return tr
}

// NodeIterator returns an iterator that returns nodes of the trie. Iteration starts at
// the key after the given start key.
func (t *Trie) NodeIterator(start []byte) NodeIterator {
	return newNodeIterator(t, start)
}

// TryGet returns the value for key stored in the trie.
// The value bytes must not be modified by the caller.
// If a node was not found in the database, a MissingNodeError is returned.
func (t *Trie) TryGet(key []byte) ([]byte, error) {
	value, newroot, didResolve, err := t.tryGet(t.root, keybytesToHex(key), 0)
	if err == nil && didResolve {
		t.root = newroot
	}
	return value, err
}

func (t *Trie) tryGet(origNode node, key []byte, pos int) (value []byte, newnode node, didResolve bool, err error) {
	switch n := (origNode).(type) {
	case nil:
		return nil, nil, false, nil
	case valueNode:
		return n, n, false, nil
	case *shortNode:
		if len(key)-pos < len(n.Key) || !bytes.Equal(n.Key, key[pos:pos+len(n.Key)]) {
			// key not found in trie
			return nil, n, false, nil
		}
		value, newnode, didResolve, err = t.tryGet(n.Val, key, pos+len(n.Key))
		if err == nil && didResolve {
			n = n.copy()
			n.Val = newnode
		}
		return value, n, didResolve, err
	case *fullNode:
		value, newnode, didResolve, err = t.tryGet(n.Children[key[pos]], key, pos+1)
		if err == nil && didResolve {
			n = n.copy()
			n.Children[key[pos]] = newnode
		}
		return value, n, didResolve, err
	case hashNode:
		child, err := t.resolveHash(n, key[:pos])
		if err != nil {
			return nil, n, true, err
		}
		value, newnode, _, err := t.tryGet(child, key, pos)
		return value, newnode, true, err
	default:
		panic(fmt.Sprintf("%T: invalid node: %v", origNode, origNode))
	}
}

// resolveHash loads node from the underlying database with the provided
// node hash and path prefix.
func (t *Trie) resolveHash(n hashNode, prefix []byte) (node, error) {
	cid := ipld.Keccak256ToCid(t.codec, n)
	node, err := t.db.node(cid.Bytes())
	if err != nil {
		return nil, err
	}
	if node != nil {
		return node, nil
	}
	return nil, &MissingNodeError{Owner: t.owner, NodeHash: n, Path: prefix}
}

// resolveHash loads rlp-encoded node blob from the underlying database
// with the provided node hash and path prefix.
func (t *Trie) resolveBlob(n hashNode, prefix []byte) ([]byte, error) {
	cid := ipld.Keccak256ToCid(t.codec, n)
	blob, _ := t.db.Node(cid.Bytes())
	if len(blob) != 0 {
		return blob, nil
	}
	return nil, &MissingNodeError{Owner: t.owner, NodeHash: n, Path: prefix}
}

// Hash returns the root hash of the trie. It does not write to the
// database and can be used even if the trie doesn't have one.
func (t *Trie) Hash() common.Hash {
	hash, cached, _ := t.hashRoot()
	t.root = cached
	return common.BytesToHash(hash.(hashNode))
}

// hashRoot calculates the root hash of the given trie
func (t *Trie) hashRoot() (node, node, error) {
	if t.root == nil {
		return hashNode(emptyRoot.Bytes()), nil, nil
	}
	// If the number of changes is below 100, we let one thread handle it
	h := newHasher(t.unhashed >= 100)
	defer returnHasherToPool(h)
	hashed, cached := h.hash(t.root, true)
	t.unhashed = 0
	return hashed, cached, nil
}