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
|
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.spark.util.collection
import java.util.{Arrays, Comparator}
import com.google.common.hash.Hashing
import org.apache.spark.annotation.DeveloperApi
/**
* :: DeveloperApi ::
* A simple open hash table optimized for the append-only use case, where keys
* are never removed, but the value for each key may be changed.
*
* This implementation uses quadratic probing with a power-of-2 hash table
* size, which is guaranteed to explore all spaces for each key (see
* http://en.wikipedia.org/wiki/Quadratic_probing).
*
* TODO: Cache the hash values of each key? java.util.HashMap does that.
*/
@DeveloperApi
class AppendOnlyMap[K, V](initialCapacity: Int = 64)
extends Iterable[(K, V)] with Serializable {
require(initialCapacity <= (1 << 29), "Can't make capacity bigger than 2^29 elements")
require(initialCapacity >= 1, "Invalid initial capacity")
private var capacity = nextPowerOf2(initialCapacity)
private var mask = capacity - 1
private var curSize = 0
private var growThreshold = (LOAD_FACTOR * capacity).toInt
// Holds keys and values in the same array for memory locality; specifically, the order of
// elements is key0, value0, key1, value1, key2, value2, etc.
private var data = new Array[AnyRef](2 * capacity)
// Treat the null key differently so we can use nulls in "data" to represent empty items.
private var haveNullValue = false
private var nullValue: V = null.asInstanceOf[V]
// Triggered by destructiveSortedIterator; the underlying data array may no longer be used
private var destroyed = false
private val destructionMessage = "Map state is invalid from destructive sorting!"
private val LOAD_FACTOR = 0.7
/** Get the value for a given key */
def apply(key: K): V = {
assert(!destroyed, destructionMessage)
val k = key.asInstanceOf[AnyRef]
if (k.eq(null)) {
return nullValue
}
var pos = rehash(k.hashCode) & mask
var i = 1
while (true) {
val curKey = data(2 * pos)
if (k.eq(curKey) || k.equals(curKey)) {
return data(2 * pos + 1).asInstanceOf[V]
} else if (curKey.eq(null)) {
return null.asInstanceOf[V]
} else {
val delta = i
pos = (pos + delta) & mask
i += 1
}
}
null.asInstanceOf[V]
}
/** Set the value for a key */
def update(key: K, value: V): Unit = {
assert(!destroyed, destructionMessage)
val k = key.asInstanceOf[AnyRef]
if (k.eq(null)) {
if (!haveNullValue) {
incrementSize()
}
nullValue = value
haveNullValue = true
return
}
var pos = rehash(key.hashCode) & mask
var i = 1
while (true) {
val curKey = data(2 * pos)
if (curKey.eq(null)) {
data(2 * pos) = k
data(2 * pos + 1) = value.asInstanceOf[AnyRef]
incrementSize() // Since we added a new key
return
} else if (k.eq(curKey) || k.equals(curKey)) {
data(2 * pos + 1) = value.asInstanceOf[AnyRef]
return
} else {
val delta = i
pos = (pos + delta) & mask
i += 1
}
}
}
/**
* Set the value for key to updateFunc(hadValue, oldValue), where oldValue will be the old value
* for key, if any, or null otherwise. Returns the newly updated value.
*/
def changeValue(key: K, updateFunc: (Boolean, V) => V): V = {
assert(!destroyed, destructionMessage)
val k = key.asInstanceOf[AnyRef]
if (k.eq(null)) {
if (!haveNullValue) {
incrementSize()
}
nullValue = updateFunc(haveNullValue, nullValue)
haveNullValue = true
return nullValue
}
var pos = rehash(k.hashCode) & mask
var i = 1
while (true) {
val curKey = data(2 * pos)
if (k.eq(curKey) || k.equals(curKey)) {
val newValue = updateFunc(true, data(2 * pos + 1).asInstanceOf[V])
data(2 * pos + 1) = newValue.asInstanceOf[AnyRef]
return newValue
} else if (curKey.eq(null)) {
val newValue = updateFunc(false, null.asInstanceOf[V])
data(2 * pos) = k
data(2 * pos + 1) = newValue.asInstanceOf[AnyRef]
incrementSize()
return newValue
} else {
val delta = i
pos = (pos + delta) & mask
i += 1
}
}
null.asInstanceOf[V] // Never reached but needed to keep compiler happy
}
/** Iterator method from Iterable */
override def iterator: Iterator[(K, V)] = {
assert(!destroyed, destructionMessage)
new Iterator[(K, V)] {
var pos = -1
/** Get the next value we should return from next(), or null if we're finished iterating */
def nextValue(): (K, V) = {
if (pos == -1) { // Treat position -1 as looking at the null value
if (haveNullValue) {
return (null.asInstanceOf[K], nullValue)
}
pos += 1
}
while (pos < capacity) {
if (!data(2 * pos).eq(null)) {
return (data(2 * pos).asInstanceOf[K], data(2 * pos + 1).asInstanceOf[V])
}
pos += 1
}
null
}
override def hasNext: Boolean = nextValue() != null
override def next(): (K, V) = {
val value = nextValue()
if (value == null) {
throw new NoSuchElementException("End of iterator")
}
pos += 1
value
}
}
}
override def size: Int = curSize
/** Increase table size by 1, rehashing if necessary */
private def incrementSize() {
curSize += 1
if (curSize > growThreshold) {
growTable()
}
}
/**
* Re-hash a value to deal better with hash functions that don't differ in the lower bits.
*/
private def rehash(h: Int): Int = Hashing.murmur3_32().hashInt(h).asInt()
/** Double the table's size and re-hash everything */
protected def growTable() {
val newCapacity = capacity * 2
if (newCapacity >= (1 << 30)) {
// We can't make the table this big because we want an array of 2x
// that size for our data, but array sizes are at most Int.MaxValue
throw new Exception("Can't make capacity bigger than 2^29 elements")
}
val newData = new Array[AnyRef](2 * newCapacity)
val newMask = newCapacity - 1
// Insert all our old values into the new array. Note that because our old keys are
// unique, there's no need to check for equality here when we insert.
var oldPos = 0
while (oldPos < capacity) {
if (!data(2 * oldPos).eq(null)) {
val key = data(2 * oldPos)
val value = data(2 * oldPos + 1)
var newPos = rehash(key.hashCode) & newMask
var i = 1
var keepGoing = true
while (keepGoing) {
val curKey = newData(2 * newPos)
if (curKey.eq(null)) {
newData(2 * newPos) = key
newData(2 * newPos + 1) = value
keepGoing = false
} else {
val delta = i
newPos = (newPos + delta) & newMask
i += 1
}
}
}
oldPos += 1
}
data = newData
capacity = newCapacity
mask = newMask
growThreshold = (LOAD_FACTOR * newCapacity).toInt
}
private def nextPowerOf2(n: Int): Int = {
val highBit = Integer.highestOneBit(n)
if (highBit == n) n else highBit << 1
}
/**
* Return an iterator of the map in sorted order. This provides a way to sort the map without
* using additional memory, at the expense of destroying the validity of the map.
*/
def destructiveSortedIterator(cmp: Comparator[(K, V)]): Iterator[(K, V)] = {
destroyed = true
// Pack KV pairs into the front of the underlying array
var keyIndex, newIndex = 0
while (keyIndex < capacity) {
if (data(2 * keyIndex) != null) {
data(newIndex) = (data(2 * keyIndex), data(2 * keyIndex + 1))
newIndex += 1
}
keyIndex += 1
}
assert(curSize == newIndex + (if (haveNullValue) 1 else 0))
// Sort by the given ordering
val rawOrdering = new Comparator[AnyRef] {
def compare(x: AnyRef, y: AnyRef): Int = {
cmp.compare(x.asInstanceOf[(K, V)], y.asInstanceOf[(K, V)])
}
}
Arrays.sort(data, 0, newIndex, rawOrdering)
new Iterator[(K, V)] {
var i = 0
var nullValueReady = haveNullValue
def hasNext: Boolean = (i < newIndex || nullValueReady)
def next(): (K, V) = {
if (nullValueReady) {
nullValueReady = false
(null.asInstanceOf[K], nullValue)
} else {
val item = data(i).asInstanceOf[(K, V)]
i += 1
item
}
}
}
}
/**
* Return whether the next insert will cause the map to grow
*/
def atGrowThreshold: Boolean = curSize == growThreshold
}
|