Boltdb学习笔记之二--数据结构

type nodes []*node

// inode represents an internal node inside of a node.
// It can be used to point to elements in a page or point
// to an element which hasn't been added to a page yet.
type inode struct {
	flags uint32
	pgid  pgid
	key   []byte
	value []byte
}

type inodes []inode

// node represents an in-memory, deserialized page.
type node struct {
	bucket     *Bucket
	isLeaf     bool
	unbalanced bool
	spilled    bool
	key        []byte
	pgid       pgid
	parent     *node
	children   nodes
	inodes     inodes
}

	for i, item := range n.inodes {
		_assert(len(item.key) > 0, "write: zero-length inode key")

		// Write the page element.
		if n.isLeaf {
			elem := p.leafPageElement(uint16(i))
			elem.pos = uint32(uintptr(unsafe.Pointer(&b[0])) - uintptr(unsafe.Pointer(elem)))
			elem.flags = item.flags
			elem.ksize = uint32(len(item.key))
			elem.vsize = uint32(len(item.value))
		} else {
			elem := p.branchPageElement(uint16(i))
			elem.pos = uint32(uintptr(unsafe.Pointer(&b[0])) - uintptr(unsafe.Pointer(elem)))
			elem.ksize = uint32(len(item.key))
			elem.pgid = item.pgid
			_assert(elem.pgid != p.id, "write: circular dependency occurred")
		}

        // If the length of key+value is larger than the max allocation size
		// then we need to reallocate the byte array pointer.
		//
		// See: https://github.com/boltdb/bolt/pull/335
		klen, vlen := len(item.key), len(item.value)
		if len(b) < klen+vlen {
			b = (*[maxAllocSize]byte)(unsafe.Pointer(&b[0]))[:]
		}

		// Write data for the element to the end of the page.
		copy(b[0:], item.key)
		b = b[klen:]
		copy(b[0:], item.value)
		b = b[vlen:]
	}

// read initializes the node from a page.
func (n *node) read(p *page) {
	n.pgid = p.id
	n.isLeaf = ((p.flags & leafPageFlag) != 0)
	n.inodes = make(inodes, int(p.count))

	for i := 0; i < int(p.count); i++ {
		inode := &n.inodes[i]
		if n.isLeaf {
			elem := p.leafPageElement(uint16(i))
			inode.flags = elem.flags
			inode.key = elem.key()
			inode.value = elem.value()
		} else {
			elem := p.branchPageElement(uint16(i))
			inode.pgid = elem.pgid
			inode.key = elem.key()
		}
		_assert(len(inode.key) > 0, "read: zero-length inode key")
	}

	// Save first key so we can find the node in the parent when we spill.
	if len(n.inodes) > 0 {
		n.key = n.inodes[0].key
		_assert(len(n.key) > 0, "read: zero-length node key")
	} else {
		n.key = nil
	}
}

// put inserts a key/value.
func (n *node) put(oldKey, newKey, value []byte, pgid pgid, flags uint32) {
    ...

	// Find insertion index.
	index := sort.Search(len(n.inodes), func(i int) bool { return bytes.Compare(n.inodes[i].key, oldKey) != -1 })

	// Add capacity and shift nodes if we don't have an exact match and need to insert.
	exact := (len(n.inodes) > 0 && index < len(n.inodes) && bytes.Equal(n.inodes[index].key, oldKey))
	if !exact {
		n.inodes = append(n.inodes, inode{})
		copy(n.inodes[index+1:], n.inodes[index:])
	}

	inode := &n.inodes[index]
	inode.flags = flags
	inode.key = newKey
	inode.value = value
	inode.pgid = pgid
	_assert(len(inode.key) > 0, "put: zero-length inode key")
}

// del removes a key from the node.
func (n *node) del(key []byte) {
	// Find index of key.
	index := sort.Search(len(n.inodes), func(i int) bool { return bytes.Compare(n.inodes[i].key, key) != -1 })

	// Exit if the key isn't found.
	if index >= len(n.inodes) || !bytes.Equal(n.inodes[index].key, key) {
		return
	}

	// Delete inode from the node.
	n.inodes = append(n.inodes[:index], n.inodes[index+1:]...)

	// Mark the node as needing rebalancing.
	n.unbalanced = true
}

// bucket represents the on-file representation of a bucket.
// This is stored as the "value" of a bucket key. If the bucket is small enough,
// then its root page can be stored inline in the "value", after the bucket
// header. In the case of inline buckets, the "root" will be 0.
type bucket struct {
    root     pgid   // page id of the bucket's root-level page
    sequence uint64 // monotonically incrementing, used by NextSequence()
}

// Bucket represents a collection of key/value pairs inside the database.
type Bucket struct {
    *bucket
    tx       *Tx                // the associated transaction
    buckets  map[string]*Bucket // subbucket cache
    page     *page              // inline page reference
    rootNode *node              // materialized node for the root page.
    nodes    map[pgid]*node     // node cache

    // Sets the threshold for filling nodes when they split. By default,
    // the bucket will fill to 50% but it can be useful to increase this
    // amount if you know that your write workloads are mostly append-only.
    //
    // This is non-persisted across transactions so it must be set in every Tx.
    FillPercent float64
}

// Get retrieves the value for a key in the bucket.
// Returns a nil value if the key does not exist or if the key is a nested bucket.
// The returned value is only valid for the life of the transaction.
func (b *Bucket) Get(key []byte) []byte {
	k, v, flags := b.Cursor().seek(key)

	// Return nil if this is a bucket.
	if (flags & bucketLeafFlag) != 0 {
		return nil
	}

	// If our target node isn't the same key as what's passed in then return nil.
	if !bytes.Equal(key, k) {
		return nil
	}
	return v
}

// seek moves the cursor to a given key and returns it.
// If the key does not exist then the next key is used.
func (c *Cursor) seek(seek []byte) (key []byte, value []byte, flags uint32) {
	_assert(c.bucket.tx.db != nil, "tx closed")

	// Start from root page/node and traverse to correct page.
	c.stack = c.stack[:0]
	c.search(seek, c.bucket.root)
	ref := &c.stack[len(c.stack)-1]

	// If the cursor is pointing to the end of page/node then return nil.
	if ref.index >= ref.count() {
		return nil, nil, 0
	}

	// If this is a bucket then return a nil value.
	return c.keyValue()
}

// search recursively performs a binary search against a given page/node until it finds a given key.
func (c *Cursor) search(key []byte, pgid pgid) {
	p, n := c.bucket.pageNode(pgid)
	if p != nil && (p.flags&(branchPageFlag|leafPageFlag)) == 0 {
		panic(fmt.Sprintf("invalid page type: %d: %x", p.id, p.flags))
	}
	e := elemRef{page: p, node: n}
	c.stack = append(c.stack, e)

	// If we're on a leaf page/node then find the specific node.
	if e.isLeaf() {
		c.nsearch(key)
		return
	}

	if n != nil {
		c.searchNode(key, n)
		return
	}
	c.searchPage(key, p)
}

func (c *Cursor) searchNode(key []byte, n *node) {
	var exact bool
	index := sort.Search(len(n.inodes), func(i int) bool {
		// TODO(benbjohnson): Optimize this range search. It's a bit hacky right now.
		// sort.Search() finds the lowest index where f() != -1 but we need the highest index.
		ret := bytes.Compare(n.inodes[i].key, key)
		if ret == 0 {
			exact = true
		}
		return ret != -1
	})
	if !exact && index > 0 {
		index--
	}
	c.stack[len(c.stack)-1].index = index

	// Recursively search to the next page.
	c.search(key, n.inodes[index].pgid)
}

// Put sets the value for a key in the bucket.
// If the key exist then its previous value will be overwritten.
// Supplied value must remain valid for the life of the transaction.
// Returns an error if the bucket was created from a read-only transaction, if the key is blank, if the key is too large, or if the value is too large.
func (b *Bucket) Put(key []byte, value []byte) error {
	if b.tx.db == nil {
		return ErrTxClosed
	} else if !b.Writable() {
		return ErrTxNotWritable
	} else if len(key) == 0 {
		return ErrKeyRequired
	} else if len(key) > MaxKeySize {
		return ErrKeyTooLarge
	} else if int64(len(value)) > MaxValueSize {
		return ErrValueTooLarge
	}

	// Move cursor to correct position.
	c := b.Cursor()
	k, _, flags := c.seek(key)

	// Return an error if there is an existing key with a bucket value.
	if bytes.Equal(key, k) && (flags&bucketLeafFlag) != 0 {
		return ErrIncompatibleValue
	}

	// Insert into node.
	key = cloneBytes(key)
	c.node().put(key, key, value, 0, 0)

	return nil
}

// Delete removes a key from the bucket.
// If the key does not exist then nothing is done and a nil error is returned.
// Returns an error if the bucket was created from a read-only transaction.
func (b *Bucket) Delete(key []byte) error {
	if b.tx.db == nil {
		return ErrTxClosed
	} else if !b.Writable() {
		return ErrTxNotWritable
	}

	// Move cursor to correct position.
	c := b.Cursor()
	_, _, flags := c.seek(key)

	// Return an error if there is already existing bucket value.
	if (flags & bucketLeafFlag) != 0 {
		return ErrIncompatibleValue
	}

	// Delete the node if we have a matching key.
	c.node().del(key)

	return nil
}

// spill writes all the nodes for this bucket to dirty pages.
func (b *Bucket) spill() error {
	// Spill all child buckets first.
	for name, child := range b.buckets {
		// If the child bucket is small enough and it has no child buckets then
		// write it inline into the parent bucket's page. Otherwise spill it
		// like a normal bucket and make the parent value a pointer to the page.
		var value []byte
		if child.inlineable() {
			child.free()
			value = child.write()
		} else {
			if err := child.spill(); err != nil {
				return err
			}

			// Update the child bucket header in this bucket.
			value = make([]byte, unsafe.Sizeof(bucket{}))
			var bucket = (*bucket)(unsafe.Pointer(&value[0]))
			*bucket = *child.bucket
		}

		// Skip writing the bucket if there are no materialized nodes.
		if child.rootNode == nil {
			continue
		}

		// Update parent node.
		var c = b.Cursor()
		k, _, flags := c.seek([]byte(name))
		if !bytes.Equal([]byte(name), k) {
			panic(fmt.Sprintf("misplaced bucket header: %x -> %x", []byte(name), k))
		}
		if flags&bucketLeafFlag == 0 {
			panic(fmt.Sprintf("unexpected bucket header flag: %x", flags))
		}
		c.node().put([]byte(name), []byte(name), value, 0, bucketLeafFlag)
	}

	// Ignore if there's not a materialized root node.
	if b.rootNode == nil {
		return nil
	}

	// Spill nodes.
	if err := b.rootNode.spill(); err != nil {
		return err
	}
	b.rootNode = b.rootNode.root()

	// Update the root node for this bucket.
	if b.rootNode.pgid >= b.tx.meta.pgid {
		panic(fmt.Sprintf("pgid (%d) above high water mark (%d)", b.rootNode.pgid, b.tx.meta.pgid))
	}
	b.root = b.rootNode.pgid

	return nil
}

// rebalance attempts to balance all nodes.
func (b *Bucket) rebalance() {
	for _, n := range b.nodes {
		n.rebalance()
	}
	for _, child := range b.buckets {
		child.rebalance()
	}
}

// CreateBucket creates a new bucket at the given key and returns the new bucket.
// Returns an error if the key already exists, if the bucket name is blank, or if the bucket name is too long.
// The bucket instance is only valid for the lifetime of the transaction.
func (b *Bucket) CreateBucket(key []byte) (*Bucket, error) {
	if b.tx.db == nil {
		return nil, ErrTxClosed
	} else if !b.tx.writable {
		return nil, ErrTxNotWritable
	} else if len(key) == 0 {
		return nil, ErrBucketNameRequired
	}

	// Move cursor to correct position.
	c := b.Cursor()
	k, _, flags := c.seek(key)

	// Return an error if there is an existing key.
	if bytes.Equal(key, k) {
		if (flags & bucketLeafFlag) != 0 {
			return nil, ErrBucketExists
		}
		return nil, ErrIncompatibleValue
	}

	// Create empty, inline bucket.
	var bucket = Bucket{
		bucket:      &bucket{},
		rootNode:    &node{isLeaf: true},
		FillPercent: DefaultFillPercent,
	}
	var value = bucket.write()

	// Insert into node.
	key = cloneBytes(key)
	c.node().put(key, key, value, 0, bucketLeafFlag)

	// Since subbuckets are not allowed on inline buckets, we need to
	// dereference the inline page, if it exists. This will cause the bucket
	// to be treated as a regular, non-inline bucket for the rest of the tx.
	b.page = nil

	return b.Bucket(key), nil
}

// Bucket retrieves a nested bucket by name.
// Returns nil if the bucket does not exist.
// The bucket instance is only valid for the lifetime of the transaction.
func (b *Bucket) Bucket(name []byte) *Bucket {
	if b.buckets != nil {
		if child := b.buckets[string(name)]; child != nil {
			return child
		}
	}

	// Move cursor to key.
	c := b.Cursor()
	k, v, flags := c.seek(name)

	// Return nil if the key doesn't exist or it is not a bucket.
	if !bytes.Equal(name, k) || (flags&bucketLeafFlag) == 0 {
		return nil
	}

	// Otherwise create a bucket and cache it.
	var child = b.openBucket(v)
	if b.buckets != nil {
		b.buckets[string(name)] = child
	}

	return child
}