Merge remote-tracking branch 'origin' into feat/safe-put

table.go

@@ -1,41 +1,50 @@
 package cuckoo
 
 import (
+	"errors"
 	"fmt"
 	"iter"
 	"math/bits"
 	"strings"
 )
 
-// A Table is hash table that uses cuckoo hashing to resolve collision. Create
-// one with [NewTable]. Or if you want more granularity, use [NewTableBy] or
-// [NewCustomTable].
+// ErrBadHash occurs when the hashes given to a [Table] cause too many key
+// collisions. Try rebuilding the table using:
+//
+//  1. Different hash seeds. Equal seeds produce equal hash functions, which
+//     always cycle.
+//  2. A different [Hash] algorithm.
+var ErrBadHash = errors.New("bad hash")
+
+// A Table which uses cuckoo hashing to resolve collision. Create
+// one with [New]. Or if you want more granularity, use [NewBy] or
+// [NewCustom].
 type Table[K, V any] struct {
-	bucketA, bucketB bucket[K, V]
-	growthFactor     uint64
-	minLoadFactor    float64
+	tableA, tableB *subtable[K, V]
+	growthFactor   uint64
+	minLoadFactor  float64
 }
 
 // TotalCapacity returns the number of slots allocated for the [Table]. To get the
 // number of slots filled, look at [Table.Size].
-func (t Table[K, V]) TotalCapacity() uint64 {
-	return t.bucketA.capacity + t.bucketB.capacity
+func (t *Table[K, V]) TotalCapacity() uint64 {
+	return t.tableA.capacity + t.tableB.capacity
 }
 
 // Size returns how many slots are filled in the [Table].
-func (t Table[K, V]) Size() int {
-	return int(t.bucketA.size + t.bucketB.size)
+func (t *Table[K, V]) Size() int {
+	return int(t.tableA.size + t.tableB.size)
 }
 
 func log2(n uint64) (m int) {
 	return max(0, bits.Len64(n)-1)
 }
 
-func (t Table[K, V]) maxEvictions() int {
+func (t *Table[K, V]) maxEvictions() int {
 	return 3 * log2(t.TotalCapacity())
 }
 
-func (t Table[K, V]) load() float64 {
+func (t *Table[K, V]) load() float64 {
 	// When there are no slots in the table, we still treat the load as 100%.
 	// Every slot in the table is full.
 	if t.TotalCapacity() == 0 {
@@ -49,20 +58,20 @@ func (t Table[K, V]) load() float64 {
 // size of the table. Returns a displaced entry and 'homeless = true' if an
 // entry could not be placed after exhausting evictions.
 func (t *Table[K, V]) insert(entry Entry[K, V]) (displaced Entry[K, V], homeless bool) {
-	if t.bucketA.update(entry.Key, entry.Value) {
+	if t.tableA.update(entry.Key, entry.Value) {
 		return
 	}
 
-	if t.bucketB.update(entry.Key, entry.Value) {
+	if t.tableB.update(entry.Key, entry.Value) {
 		return
 	}
 
 	for range t.maxEvictions() {
-		if entry, homeless = t.bucketA.insert(entry); !homeless {
+		if entry, homeless = t.tableA.insert(entry); !homeless {
 			return
 		}
 
-		if entry, homeless = t.bucketB.insert(entry); !homeless {
+		if entry, homeless = t.tableB.insert(entry); !homeless {
 			return
 		}
 	}
@@ -72,12 +81,12 @@ func (t *Table[K, V]) insert(entry Entry[K, V]) (displaced Entry[K, V], homeless
 
 // resized creates an empty copy of the table, with a new capacity for each
 // bucket.
-func (t Table[K, V]) resized(capacity uint64) Table[K, V] {
-	return Table[K, V]{
+func (t *Table[K, V]) resized(capacity uint64) *Table[K, V] {
+	return &Table[K, V]{
 		growthFactor:  t.growthFactor,
 		minLoadFactor: t.minLoadFactor,
-		bucketA:       t.bucketA.resized(capacity),
-		bucketB:       t.bucketB.resized(capacity),
+		tableA:        t.tableA.resized(capacity),
+		tableB:        t.tableB.resized(capacity),
 	}
 }
 
@@ -93,11 +102,11 @@ func (t *Table[K, V]) resize(capacity uint64) bool {
 		}
 	}
 
-	*t = updated
+	*t = *updated
 	return true
 }
 
-// grow increases the table's capacity by the [Table.growthFactor]. If the
+// grow increases the table's capacity by the growth factor. If the
 // capacity is 0, it increases it to 1.
 func (t *Table[K, V]) grow() bool {
 	var newCapacity uint64
@@ -105,36 +114,43 @@ func (t *Table[K, V]) grow() bool {
 	if t.TotalCapacity() == 0 {
 		newCapacity = 1
 	} else {
-		newCapacity = t.bucketA.capacity * t.growthFactor
+		newCapacity = t.tableA.capacity * t.growthFactor
 	}
 
 	return t.resize(newCapacity)
 }
 
-// shrink reduces the table's capacity by the [Table.growthFactor]. It may
+// shrink reduces the table's capacity by the growth factor. It may
 // reduce it down to 0.
 func (t *Table[K, V]) shrink() bool {
-	return t.resize(t.bucketA.capacity / t.growthFactor)
+	return t.resize(t.tableA.capacity / t.growthFactor)
 }
 
-// Get fetches the value for a key in the [Table]. Returns an error if no value
-// is found.
-func (t Table[K, V]) Get(key K) (value V, err error) {
-	if item, ok := t.bucketA.get(key); ok {
-		return item, nil
+// Get fetches the value for a key in the [Table]. Matches the comma-ok pattern
+// of a builtin map; see [Table.Find] for plain indexing.
+func (t *Table[K, V]) Get(key K) (value V, ok bool) {
+	if item, ok := t.tableA.get(key); ok {
+		return item, true
 	}
 
-	if item, ok := t.bucketB.get(key); ok {
-		return item, nil
+	if item, ok := t.tableB.get(key); ok {
+		return item, true
 	}
 
-	return value, fmt.Errorf("key '%v' not found", key)
+	return
+}
+
+// Find fetches the value of a key. Matches direct indexing of a builtin map;
+// see [Table.Get] for a comma-ok pattern.
+func (t *Table[K, V]) Find(key K) (value V) {
+	value, _ = t.Get(key)
+	return
 }
 
 // Has returns true if a key has a value in the table.
-func (t Table[K, V]) Has(key K) (exists bool) {
-	_, err := t.Get(key)
-	return err == nil
+func (t *Table[K, V]) Has(key K) (exists bool) {
+	_, exists = t.Get(key)
+	return
 }
 
 // Put sets the value for a key. If it cannot be set, an error is returned,
@@ -174,7 +190,7 @@ func (t *Table[K, V]) Put(key K, value V) (displaced Entry[K, V], err error) {
 // Drop removes a value for a key in the table. Returns whether the key had
 // existed.
 func (t *Table[K, V]) Drop(key K) bool {
-	occupied := t.bucketA.drop(key) || t.bucketB.drop(key)
+	occupied := t.tableA.drop(key) || t.tableB.drop(key)
 
 	if t.load() < t.minLoadFactor {
 		// The error is not handled here, because table-shrinking is an internal
@@ -186,9 +202,9 @@ func (t *Table[K, V]) Drop(key K) bool {
 }
 
 // Entries returns an unordered sequence of all key-value pairs in the table.
-func (t Table[K, V]) Entries() iter.Seq2[K, V] {
+func (t *Table[K, V]) Entries() iter.Seq2[K, V] {
 	return func(yield func(K, V) bool) {
-		for _, slot := range t.bucketA.slots {
+		for _, slot := range t.tableA.slots {
 			if slot.occupied {
 				if !yield(slot.Key, slot.Value) {
 					return
@@ -196,7 +212,7 @@ func (t Table[K, V]) Entries() iter.Seq2[K, V] {
 			}
 		}
 
-		for _, slot := range t.bucketB.slots {
+		for _, slot := range t.tableB.slots {
 			if slot.occupied {
 				if !yield(slot.Key, slot.Value) {
 					return
@@ -207,8 +223,8 @@ func (t Table[K, V]) Entries() iter.Seq2[K, V] {
 }
 
 // String returns the entries of the table as a string in the format:
-// "table[k1:v1 h2:v2 ...]".
-func (t Table[K, V]) String() string {
+// "table[k1:v1 k2:v2 ...]".
+func (t *Table[K, V]) String() string {
 	var sb strings.Builder
 	sb.WriteString("table[")
 
@@ -226,9 +242,9 @@ func (t Table[K, V]) String() string {
 	return sb.String()
 }
 
-// NewCustomTable creates a [Table] with custom [Hash] and [EqualFunc]
+// NewCustom creates a [Table] with custom [Hash] and [EqualFunc]
 // functions, along with any [Option] the user provides.
-func NewCustomTable[K, V any](hashA, hashB Hash[K], compare EqualFunc[K], options ...Option) *Table[K, V] {
+func NewCustom[K, V any](hashA, hashB Hash[K], compare EqualFunc[K], options ...Option) *Table[K, V] {
 	settings := &settings{
 		growthFactor:  DefaultGrowthFactor,
 		bucketSize:    DefaultCapacity,
@@ -242,8 +258,8 @@ func NewCustomTable[K, V any](hashA, hashB Hash[K], compare EqualFunc[K], option
 	return &Table[K, V]{
 		growthFactor:  settings.growthFactor,
 		minLoadFactor: settings.minLoadFactor,
-		bucketA:       newBucket[K, V](settings.bucketSize, hashA, compare),
-		bucketB:       newBucket[K, V](settings.bucketSize, hashB, compare),
+		tableA:        newSubtable[K, V](settings.bucketSize, hashA, compare),
+		tableB:        newSubtable[K, V](settings.bucketSize, hashB, compare),
 	}
 }
 
@@ -251,10 +267,10 @@ func pipe[X, Y, Z any](a func(X) Y, b func(Y) Z) func(X) Z {
 	return func(x X) Z { return b(a(x)) }
 }
 
-// NewTableBy creates a [Table] for any key type by using keyFunc to derive a
+// NewBy creates a [Table] for any key type by using keyFunc to derive a
 // comparable key. Two keys with the same derived key are treated as equal.
-func NewTableBy[K, V any, C comparable](keyFunc func(K) C, options ...Option) *Table[K, V] {
-	return NewCustomTable[K, V](
+func NewBy[K, V any, C comparable](keyFunc func(K) C, options ...Option) *Table[K, V] {
+	return NewCustom[K, V](
 		pipe(keyFunc, NewDefaultHash[C]()),
 		pipe(keyFunc, NewDefaultHash[C]()),
 		func(a, b K) bool { return keyFunc(a) == keyFunc(b) },
@@ -262,10 +278,10 @@ func NewTableBy[K, V any, C comparable](keyFunc func(K) C, options ...Option) *T
 	)
 }
 
-// NewTable creates a [Table] using the default [Hash] and [EqualFunc]. Use
+// New creates a [Table] using the default [Hash] and [EqualFunc]. Use
 // the [Option] functions to configure its behavior. Note that this constructor
 // is only provided for comparable keys. For arbitrary keys, consider
-// [NewTableBy] or [NewCustomTable].
-func NewTable[K comparable, V any](options ...Option) *Table[K, V] {
-	return NewCustomTable[K, V](NewDefaultHash[K](), NewDefaultHash[K](), DefaultEqualFunc[K], options...)
+// [NewBy] or [NewCustom].
+func New[K comparable, V any](options ...Option) *Table[K, V] {
+	return NewCustom[K, V](NewDefaultHash[K](), NewDefaultHash[K](), DefaultEqualFunc[K], options...)
 }