feat!: Drop returns bool, Put doesn't stack-overflow (#21)
All checks were successful
CI / Check PR Title (push) Has been skipped
CI / Go Lint (push) Successful in 58s
CI / Makefile Lint (push) Successful in 55s
CI / Markdown Lint (push) Successful in 34s
CI / Unit Tests (push) Successful in 54s
CI / Fuzz Tests (push) Successful in 1m26s
CI / Mutation Tests (push) Successful in 1m11s

## Description

Closes #11.

## Changes

### Design Decisions

## Checklist

- [ ] Tests pass
- [ ] Docs updated

Reviewed-on: #21
Co-authored-by: M.V. Hutz <git@maximhutz.me>
Co-committed-by: M.V. Hutz <git@maximhutz.me>
This commit was merged in pull request #21.
This commit is contained in:
2026-04-17 01:31:01 +00:00
committed by Maxim Hutz
parent 29ba6bfd4d
commit 39548b4332
6 changed files with 107 additions and 65 deletions

124
table.go
View File

@@ -9,7 +9,7 @@ import (
)
// ErrBadHash occurs when the hashes given to a [Table] cause too many key
// collisions. Try rebuilding the table using:
// collisions. Discard the old table, rebuild it from your source data, and try:
//
// 1. Different hash seeds. Equal seeds produce equal hash functions, which
// always cycle.
@@ -20,7 +20,7 @@ var ErrBadHash = errors.New("bad hash")
// one with [New]. Or if you want more granularity, use [NewBy] or
// [NewCustom].
type Table[K, V any] struct {
tableA, tableB subtable[K, V]
tableA, tableB *subtable[K, V]
growthFactor uint64
minLoadFactor float64
}
@@ -54,30 +54,61 @@ func (t *Table[K, V]) load() float64 {
return float64(t.Size()) / float64(t.TotalCapacity())
}
// resize clears all tables, changes the sizes of them to a specific capacity,
// and fills them back up again. It is a helper function for [Table.grow] and
// [Table.shrink]; use them instead.
func (t *Table[K, V]) resize(capacity uint64) error {
entries := make([]entry[K, V], 0, t.Size())
for k, v := range t.Entries() {
entries = append(entries, entry[K, V]{k, v})
// insert attempts to put/update an entry in the table, without modifying the
// 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.tableA.update(entry.key, entry.value) {
return
}
t.tableA.resize(capacity)
t.tableB.resize(capacity)
if t.tableB.update(entry.key, entry.value) {
return
}
for _, entry := range entries {
if err := t.Put(entry.key, entry.value); err != nil {
return err
for range t.maxEvictions() {
if entry, homeless = t.tableA.insert(entry); !homeless {
return
}
if entry, homeless = t.tableB.insert(entry); !homeless {
return
}
}
return nil
return entry, true
}
// 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]{
growthFactor: t.growthFactor,
minLoadFactor: t.minLoadFactor,
tableA: t.tableA.resized(capacity),
tableB: t.tableB.resized(capacity),
}
}
// resize creates a new [Table.resized] with 'capacity', inserts all items into
// the array, and replaces the current table. It is a helper function for
// [Table.grow] and [Table.shrink]; use them instead.
func (t *Table[K, V]) resize(capacity uint64) bool {
updated := t.resized(capacity)
for k, v := range t.Entries() {
if _, failed := updated.insert(entry[K, V]{k, v}); failed {
return false
}
}
*t = *updated
return true
}
// 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() error {
func (t *Table[K, V]) grow() bool {
var newCapacity uint64
if t.TotalCapacity() == 0 {
@@ -91,7 +122,7 @@ func (t *Table[K, V]) grow() error {
// shrink reduces the table's capacity by the growth factor. It may
// reduce it down to 0.
func (t *Table[K, V]) shrink() error {
func (t *Table[K, V]) shrink() bool {
return t.resize(t.tableA.capacity / t.growthFactor)
}
@@ -122,49 +153,48 @@ func (t *Table[K, V]) Has(key K) (exists bool) {
return
}
// Put sets the value for a key. Returns error if its value cannot be set.
// Put sets the value for a key. If it cannot be set, an error is returned.
func (t *Table[K, V]) Put(key K, value V) (err error) {
if t.tableA.update(key, value) {
return nil
}
var (
entry = entry[K, V]{key, value}
homeless bool
)
if t.tableB.update(key, value) {
return nil
}
entry, eviction := entry[K, V]{key, value}, false
for range t.maxEvictions() {
if entry, eviction = t.tableA.evict(entry); !eviction {
return nil
for range defaultGrowthLimit {
if entry, homeless = t.insert(entry); !homeless {
return
}
if entry, eviction = t.tableB.evict(entry); !eviction {
return nil
// Both this and the growth limit are necessary: this catches bad hashes
// early when the table is sparse, while the latter catches cases where
// growing never helps.
if t.load() < t.minLoadFactor {
return fmt.Errorf("hash functions produced a cycle at load %d/%d: %w", t.Size(), t.TotalCapacity(), ErrBadHash)
}
// It is theoretically possible to have a table with a larger capacity
// that is valid. But this chance is astronomically small, so we ignore
// it in this implementation.
if grew := t.grow(); !grew {
return fmt.Errorf("could not redistribute entries into larger table: %w", ErrBadHash)
}
}
if t.load() < t.minLoadFactor {
return fmt.Errorf("hash functions produced a cycle at load %d/%d: %w", t.Size(), t.TotalCapacity(), ErrBadHash)
}
if err := t.grow(); err != nil {
return err
}
return t.Put(entry.key, entry.value)
return fmt.Errorf("could not place entry after %d resizes: %w", defaultGrowthLimit, ErrBadHash)
}
// Drop removes a value for a key in the table. Returns an error if its value
// cannot be removed.
func (t *Table[K, V]) Drop(key K) (err error) {
t.tableA.drop(key)
t.tableB.drop(key)
// 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.tableA.drop(key) || t.tableB.drop(key)
if t.load() < t.minLoadFactor {
return t.shrink()
// The error is not handled here, because table-shrinking is an internal
// optimization.
t.shrink()
}
return nil
return occupied
}
// Entries returns an unordered sequence of all key-value pairs in the table.