aboutsummaryrefslogtreecommitdiff
path: root/vendor/github.com/etcd-io/bbolt/cursor.go
blob: 3000aced6c4c1d38661f54f415c466440f66e987 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
package bbolt

import (
	"bytes"
	"fmt"
	"sort"
)

// Cursor represents an iterator that can traverse over all key/value pairs in a bucket in sorted order.
// Cursors see nested buckets with value == nil.
// Cursors can be obtained from a transaction and are valid as long as the transaction is open.
//
// Keys and values returned from the cursor are only valid for the life of the transaction.
//
// Changing data while traversing with a cursor may cause it to be invalidated
// and return unexpected keys and/or values. You must reposition your cursor
// after mutating data.
type Cursor struct {
	bucket *Bucket
	stack  []elemRef
}

// Bucket returns the bucket that this cursor was created from.
func (c *Cursor) Bucket() *Bucket {
	return c.bucket
}

// First moves the cursor to the first item in the bucket and returns its key and value.
// If the bucket is empty then a nil key and value are returned.
// The returned key and value are only valid for the life of the transaction.
func (c *Cursor) First() (key []byte, value []byte) {
	_assert(c.bucket.tx.db != nil, "tx closed")
	c.stack = c.stack[:0]
	p, n := c.bucket.pageNode(c.bucket.root)
	c.stack = append(c.stack, elemRef{page: p, node: n, index: 0})
	c.first()

	// If we land on an empty page then move to the next value.
	// https://github.com/boltdb/bolt/issues/450
	if c.stack[len(c.stack)-1].count() == 0 {
		c.next()
	}

	k, v, flags := c.keyValue()
	if (flags & uint32(bucketLeafFlag)) != 0 {
		return k, nil
	}
	return k, v

}

// Last moves the cursor to the last item in the bucket and returns its key and value.
// If the bucket is empty then a nil key and value are returned.
// The returned key and value are only valid for the life of the transaction.
func (c *Cursor) Last() (key []byte, value []byte) {
	_assert(c.bucket.tx.db != nil, "tx closed")
	c.stack = c.stack[:0]
	p, n := c.bucket.pageNode(c.bucket.root)
	ref := elemRef{page: p, node: n}
	ref.index = ref.count() - 1
	c.stack = append(c.stack, ref)
	c.last()
	k, v, flags := c.keyValue()
	if (flags & uint32(bucketLeafFlag)) != 0 {
		return k, nil
	}
	return k, v
}

// Next moves the cursor to the next item in the bucket and returns its key and value.
// If the cursor is at the end of the bucket then a nil key and value are returned.
// The returned key and value are only valid for the life of the transaction.
func (c *Cursor) Next() (key []byte, value []byte) {
	_assert(c.bucket.tx.db != nil, "tx closed")
	k, v, flags := c.next()
	if (flags & uint32(bucketLeafFlag)) != 0 {
		return k, nil
	}
	return k, v
}

// Prev moves the cursor to the previous item in the bucket and returns its key and value.
// If the cursor is at the beginning of the bucket then a nil key and value are returned.
// The returned key and value are only valid for the life of the transaction.
func (c *Cursor) Prev() (key []byte, value []byte) {
	_assert(c.bucket.tx.db != nil, "tx closed")

	// Attempt to move back one element until we're successful.
	// Move up the stack as we hit the beginning of each page in our stack.
	for i := len(c.stack) - 1; i >= 0; i-- {
		elem := &c.stack[i]
		if elem.index > 0 {
			elem.index--
			break
		}
		c.stack = c.stack[:i]
	}

	// If we've hit the end then return nil.
	if len(c.stack) == 0 {
		return nil, nil
	}

	// Move down the stack to find the last element of the last leaf under this branch.
	c.last()
	k, v, flags := c.keyValue()
	if (flags & uint32(bucketLeafFlag)) != 0 {
		return k, nil
	}
	return k, v
}

// Seek moves the cursor to a given key and returns it.
// If the key does not exist then the next key is used. If no keys
// follow, a nil key is returned.
// The returned key and value are only valid for the life of the transaction.
func (c *Cursor) Seek(seek []byte) (key []byte, value []byte) {
	k, v, flags := c.seek(seek)

	// If we ended up after the last element of a page then move to the next one.
	if ref := &c.stack[len(c.stack)-1]; ref.index >= ref.count() {
		k, v, flags = c.next()
	}

	if k == nil {
		return nil, nil
	} else if (flags & uint32(bucketLeafFlag)) != 0 {
		return k, nil
	}
	return k, v
}

// Delete removes the current key/value under the cursor from the bucket.
// Delete fails if current key/value is a bucket or if the transaction is not writable.
func (c *Cursor) Delete() error {
	if c.bucket.tx.db == nil {
		return ErrTxClosed
	} else if !c.bucket.Writable() {
		return ErrTxNotWritable
	}

	key, _, flags := c.keyValue()
	// Return an error if current value is a bucket.
	if (flags & bucketLeafFlag) != 0 {
		return ErrIncompatibleValue
	}
	c.node().del(key)

	return nil
}

// 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)

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

// first moves the cursor to the first leaf element under the last page in the stack.
func (c *Cursor) first() {
	for {
		// Exit when we hit a leaf page.
		var ref = &c.stack[len(c.stack)-1]
		if ref.isLeaf() {
			break
		}

		// Keep adding pages pointing to the first element to the stack.
		var pgid pgid
		if ref.node != nil {
			pgid = ref.node.inodes[ref.index].pgid
		} else {
			pgid = ref.page.branchPageElement(uint16(ref.index)).pgid
		}
		p, n := c.bucket.pageNode(pgid)
		c.stack = append(c.stack, elemRef{page: p, node: n, index: 0})
	}
}

// last moves the cursor to the last leaf element under the last page in the stack.
func (c *Cursor) last() {
	for {
		// Exit when we hit a leaf page.
		ref := &c.stack[len(c.stack)-1]
		if ref.isLeaf() {
			break
		}

		// Keep adding pages pointing to the last element in the stack.
		var pgid pgid
		if ref.node != nil {
			pgid = ref.node.inodes[ref.index].pgid
		} else {
			pgid = ref.page.branchPageElement(uint16(ref.index)).pgid
		}
		p, n := c.bucket.pageNode(pgid)

		var nextRef = elemRef{page: p, node: n}
		nextRef.index = nextRef.count() - 1
		c.stack = append(c.stack, nextRef)
	}
}

// next moves to the next leaf element and returns the key and value.
// If the cursor is at the last leaf element then it stays there and returns nil.
func (c *Cursor) next() (key []byte, value []byte, flags uint32) {
	for {
		// Attempt to move over one element until we're successful.
		// Move up the stack as we hit the end of each page in our stack.
		var i int
		for i = len(c.stack) - 1; i >= 0; i-- {
			elem := &c.stack[i]
			if elem.index < elem.count()-1 {
				elem.index++
				break
			}
		}

		// If we've hit the root page then stop and return. This will leave the
		// cursor on the last element of the last page.
		if i == -1 {
			return nil, nil, 0
		}

		// Otherwise start from where we left off in the stack and find the
		// first element of the first leaf page.
		c.stack = c.stack[:i+1]
		c.first()

		// If this is an empty page then restart and move back up the stack.
		// https://github.com/boltdb/bolt/issues/450
		if c.stack[len(c.stack)-1].count() == 0 {
			continue
		}

		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)
}

func (c *Cursor) searchPage(key []byte, p *page) {
	// Binary search for the correct range.
	inodes := p.branchPageElements()

	var exact bool
	index := sort.Search(int(p.count), 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(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, inodes[index].pgid)
}

// nsearch searches the leaf node on the top of the stack for a key.
func (c *Cursor) nsearch(key []byte) {
	e := &c.stack[len(c.stack)-1]
	p, n := e.page, e.node

	// If we have a node then search its inodes.
	if n != nil {
		index := sort.Search(len(n.inodes), func(i int) bool {
			return bytes.Compare(n.inodes[i].key, key) != -1
		})
		e.index = index
		return
	}

	// If we have a page then search its leaf elements.
	inodes := p.leafPageElements()
	index := sort.Search(int(p.count), func(i int) bool {
		return bytes.Compare(inodes[i].key(), key) != -1
	})
	e.index = index
}

// keyValue returns the key and value of the current leaf element.
func (c *Cursor) keyValue() ([]byte, []byte, uint32) {
	ref := &c.stack[len(c.stack)-1]

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

	// Retrieve value from node.
	if ref.node != nil {
		inode := &ref.node.inodes[ref.index]
		return inode.key, inode.value, inode.flags
	}

	// Or retrieve value from page.
	elem := ref.page.leafPageElement(uint16(ref.index))
	return elem.key(), elem.value(), elem.flags
}

// node returns the node that the cursor is currently positioned on.
func (c *Cursor) node() *node {
	_assert(len(c.stack) > 0, "accessing a node with a zero-length cursor stack")

	// If the top of the stack is a leaf node then just return it.
	if ref := &c.stack[len(c.stack)-1]; ref.node != nil && ref.isLeaf() {
		return ref.node
	}

	// Start from root and traverse down the hierarchy.
	var n = c.stack[0].node
	if n == nil {
		n = c.bucket.node(c.stack[0].page.id, nil)
	}
	for _, ref := range c.stack[:len(c.stack)-1] {
		_assert(!n.isLeaf, "expected branch node")
		n = n.childAt(int(ref.index))
	}
	_assert(n.isLeaf, "expected leaf node")
	return n
}

// elemRef represents a reference to an element on a given page/node.
type elemRef struct {
	page  *page
	node  *node
	index int
}

// isLeaf returns whether the ref is pointing at a leaf page/node.
func (r *elemRef) isLeaf() bool {
	if r.node != nil {
		return r.node.isLeaf
	}
	return (r.page.flags & leafPageFlag) != 0
}

// count returns the number of inodes or page elements.
func (r *elemRef) count() int {
	if r.node != nil {
		return len(r.node.inodes)
	}
	return int(r.page.count)
}