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

.markdownlint-cli2.jsonc

@@ -1,14 +0,0 @@
-{
-  "customRules": [".markdownlint-rules/one-sentence-per-line.mjs"],
-  "config": {
-    "default": true,
-    "heading-style": { "style": "atx" },
-    "ul-indent": { "indent": 2 },
-    "line-length": false,
-    "no-duplicate-heading": { "siblings_only": true },
-    "no-inline-html": {
-      "allowed_elements": ["br", "code", "details", "summary", "img", "picture", "source"]
-    },
-    "first-line-heading": true
-  }
-}

.markdownlint-rules/one-sentence-per-line.mjs

@@ -1,48 +0,0 @@
-// @ts-check
-
-/**
- * @typedef {object} ErrorInfo
- * @property {number} lineNumber
- * @property {string} [context]
- * @property {string} [detail]
- * @property {[number, number]} [range]
- */
-
-/**
- * @typedef {object} Params
- * @property {string[]} lines
- */
-
-/** @typedef {(error: ErrorInfo) => void} OnError */
-
-/**
- * @typedef {object} Rule
- * @property {string[]} names
- * @property {string} description
- * @property {string[]} tags
- * @property {(params: Params, onError: OnError) => void} function
- */
-
-/** @type {Rule} */
-export default {
-  names: ["one-sentence-per-line"],
-  description: "Each sentence must be on its own line",
-  tags: ["sentences"],
-  function: function (params, onError) {
-    let inFence = false;
-    params.lines.forEach((line, index) => {
-      if (/^```/.test(line)) {
-        inFence = !inFence;
-        return;
-      }
-      if (inFence) return;
-      // Skip headings, blank lines, HTML, table rows
-      if (/^(#|\s*[|<]|>|\s*$)/.test(line)) return;
-      // Strip list marker before checking
-      const text = line.replace(/^\s*(?:[-*+]|\d+\.)\s+/, "");
-      if (/[.!?]\s+[A-Z]/.test(text)) {
-        onError({ lineNumber: index + 1, context: text.trim() });
-      }
-    });
-  },
-};

.markdownlint.yml

@@ -0,0 +1,17 @@
+default: true
+heading-style:
+  style: atx
+ul-indent:
+  indent: 2
+line-length: false
+no-duplicate-heading:
+  siblings_only: true
+no-inline-html:
+  allowed_elements:
+    - br
+    - details
+    - summary
+    - img
+    - picture
+    - source
+first-line-heading: true

README.md

@@ -1,6 +1,3 @@
 # <img height="30" src="assets/logo.svg" alt="Go Cuckoo, by `mvhutz`."> Go Cuckoo
 
-A hash table that uses cuckoo hashing to achieve a worst-case O(1) lookup time.
+A hash table that uses cuckoo hashing to achieve a worst-case O(1) lookup time. Read more about it in [the package documentation](https://pkg.go.dev/git.maximhutz.com/tools/go-cuckoo).
-Read more about it in [the package documentation][docs].
-
-[docs]: https://pkg.go.dev/git.maximhutz.com/tools/go-cuckoo

cuckoo_fuzz_test.go

@@ -75,9 +75,9 @@ func FuzzInsertLookup(f *testing.F) {
 				delete(expected, step.key)
 
 				_, ok = actual.Get(step.key)
-				assert.False(ok)
+				assert.True(ok)
 			} else {
-				err := actual.Put(step.key, step.value)
+				_, err := actual.Put(step.key, step.value)
 				assert.NoError(err)
 
 				expected[step.key] = step.value

cuckoo_internal_test.go

@@ -23,7 +23,7 @@ func TestLoad(t *testing.T) {
 	table := New[int, bool](Capacity(8))
 
 	for i := range 16 {
-		err := table.Put(i, true)
+		_, err := table.Put(i, true)
 		assert.NoError(err)
 		assert.Equal(float64(table.Size())/float64(table.TotalCapacity()), table.load())
 	}

cuckoo_test.go

@@ -25,7 +25,7 @@ func TestAddItem(t *testing.T) {
 	key, value := 0, true
 	table := cuckoo.New[int, bool]()
 
-	err := table.Put(key, value)
+	_, err := table.Put(key, value)
 
 	assert.NoError(err)
 	assert.Equal(1, table.Size())
@@ -38,7 +38,7 @@ func TestPutOverwrite(t *testing.T) {
 	table := cuckoo.New[int, int]()
 	(table.Put(key, value))
 
-	err := table.Put(key, newValue)
+	_, err := table.Put(key, newValue)
 
 	assert.NoError(err)
 	assert.Equal(1, table.Size())
@@ -52,9 +52,9 @@ func TestSameHash(t *testing.T) {
 	hash := func(int) uint64 { return 0 }
 	table := cuckoo.NewCustom[int, bool](hash, hash, cuckoo.DefaultEqualFunc[int])
 
-	errA := table.Put(0, true)
+	_, errA := table.Put(0, true)
-	errB := table.Put(1, true)
+	_, errB := table.Put(1, true)
-	errC := table.Put(2, true)
+	_, errC := table.Put(2, true)
 
 	assert.NoError(errA)
 	assert.NoError(errB)
@@ -76,7 +76,7 @@ func TestResizeCapacity(t *testing.T) {
 	)
 
 	for table.TotalCapacity() == 16 {
-		err := table.Put(rand.Int(), true)
+		_, err := table.Put(rand.Int(), true)
 		assert.NoError(err)
 	}
 
@@ -89,7 +89,7 @@ func TestPutMany(t *testing.T) {
 
 	for i := range 1_000 {
 		expected[i] = true
-		err := actual.Put(i, true)
+		_, err := actual.Put(i, true)
 
 		assert.NoError(err)
 	}
@@ -103,7 +103,7 @@ func TestGetMany(t *testing.T) {
 	table := cuckoo.New[int, bool]()
 
 	for i := range 1_000 {
-		err := table.Put(i, true)
+		_, err := table.Put(i, true)
 		assert.NoError(err)
 	}
 
@@ -167,7 +167,7 @@ func TestPutNoCapacity(t *testing.T) {
 		cuckoo.Capacity(0),
 	)
 
-	err := table.Put(key, value)
+	_, err := table.Put(key, value)
 
 	assert.NoError(err)
 	assert.Equal(1, table.Size())
@@ -183,9 +183,9 @@ func TestBadHashCapacity(t *testing.T) {
 		cuckoo.Capacity(20),
 	)
 
-	err1 := table.Put(0, true)
+	_, err1 := table.Put(0, true)
-	err2 := table.Put(1, true)
+	_, err2 := table.Put(1, true)
-	err3 := table.Put(2, true)
+	_, err3 := table.Put(2, true)
 
 	assert.NoError(err1)
 	assert.NoError(err2)
@@ -200,8 +200,8 @@ func TestDropResizeCapacity(t *testing.T) {
 		cuckoo.Capacity(10),
 	)
 
-	err1 := table.Put(0, true)
+	_, err1 := table.Put(0, true)
-	err2 := table.Put(1, true)
+	_, err2 := table.Put(1, true)
 	table.Drop(1)
 
 	assert.NoError(errors.Join(err1, err2))
@@ -218,7 +218,7 @@ func TestNewTableBy(t *testing.T) {
 	assert := assert.New(t)
 	table := cuckoo.NewBy[User, bool](func(u User) string { return u.id })
 
-	err := table.Put(User{nil, "1", "Robert"}, true)
+	_, err := table.Put(User{nil, "1", "Robert"}, true)
 
 	assert.NoError(err)
 	assert.Equal(1, table.Size())

doc.go

@@ -5,8 +5,5 @@
 // a table with any key type using [NewCustom]. Custom [Hash] functions and
 // key comparison are also supported.
 //
-// NOTE: The [Table] is a look-up structure, and not a source of truth. If
-// [ErrBadHash] occurs, the data cannot be restored.
-//
 // See more: https://en.wikipedia.org/wiki/Cuckoo_hashing
 package cuckoo

doc_example_test.go

@@ -10,7 +10,7 @@ import (
 func Example_basic() {
 	table := cuckoo.New[int, string]()
 
-	if err := table.Put(1, "Hello, World!"); err != nil {
+	if _, err := table.Put(1, "Hello, World!"); err != nil {
 		fmt.Println("Put error:", err)
 	}
 

subtable.go

@@ -1,13 +1,13 @@
 package cuckoo
 
-// An entry is a key-value pair.
+// An Entry is a key-value pair.
-type entry[K, V any] struct {
+type Entry[K, V any] struct {
-	key   K
+	Key   K
-	value V
+	Value V
 }
 
 type slot[K, V any] struct {
-	entry[K, V]
+	Entry[K, V]
 	occupied bool
 }
 
@@ -18,81 +18,81 @@ type subtable[K, V any] struct {
 	compare        EqualFunc[K]
 }
 
-// location determines where in the subtable a certain key would be placed. If
+// location determines where in the bucket a certain key would be placed. If the
-// the capacity is 0, this will panic.
+// capacity is 0, this will panic.
-func (t *subtable[K, V]) location(key K) uint64 {
+func (b *subtable[K, V]) location(key K) uint64 {
-	return t.hash(key) % t.capacity
+	return b.hash(key) % b.capacity
 }
 
-func (t *subtable[K, V]) get(key K) (value V, found bool) {
+func (b *subtable[K, V]) get(key K) (value V, found bool) {
-	if t.capacity == 0 {
+	if b.capacity == 0 {
 		return
 	}
 
-	slot := t.slots[t.location(key)]
+	slot := b.slots[b.location(key)]
-	return slot.value, slot.occupied && t.compare(slot.key, key)
+	return slot.Value, slot.occupied && b.compare(slot.Key, key)
 }
 
-func (t *subtable[K, V]) drop(key K) (occupied bool) {
+func (b *subtable[K, V]) drop(key K) (occupied bool) {
-	if t.capacity == 0 {
+	if b.capacity == 0 {
 		return
 	}
 
-	slot := &t.slots[t.location(key)]
+	slot := &b.slots[b.location(key)]
 
-	if slot.occupied && t.compare(slot.key, key) {
+	if slot.occupied && b.compare(slot.Key, key) {
 		slot.occupied = false
-		t.size--
+		b.size--
 		return true
 	}
 
 	return false
 }
 
-func (t *subtable[K, V]) resized(capacity uint64) *subtable[K, V] {
+func (b *subtable[K, V]) resized(capacity uint64) *subtable[K, V] {
 	return &subtable[K, V]{
 		slots:    make([]slot[K, V], capacity),
 		capacity: capacity,
-		hash:     t.hash,
+		hash:     b.hash,
-		compare:  t.compare,
+		compare:  b.compare,
 	}
 }
 
-func (t *subtable[K, V]) update(key K, value V) (updated bool) {
+func (b *subtable[K, V]) update(key K, value V) (updated bool) {
-	if t.capacity == 0 {
+	if b.capacity == 0 {
 		return
 	}
 
-	slot := &t.slots[t.location(key)]
+	slot := &b.slots[b.location(key)]
 
-	if slot.occupied && t.compare(slot.key, key) {
+	if slot.occupied && b.compare(slot.Key, key) {
-		slot.value = value
+		slot.Value = value
 		return true
 	}
 
 	return false
 }
 
-func (t *subtable[K, V]) insert(insertion entry[K, V]) (evicted entry[K, V], eviction bool) {
+func (b *subtable[K, V]) insert(insertion Entry[K, V]) (evicted Entry[K, V], eviction bool) {
-	if t.capacity == 0 {
+	if b.capacity == 0 {
 		return insertion, true
 	}
 
-	slot := &t.slots[t.location(insertion.key)]
+	slot := &b.slots[b.location(insertion.Key)]
 
 	if !slot.occupied {
-		slot.entry = insertion
+		slot.Entry = insertion
 		slot.occupied = true
-		t.size++
+		b.size++
 		return
 	}
 
-	if t.compare(slot.key, insertion.key) {
+	if b.compare(slot.Key, insertion.Key) {
-		slot.value = insertion.value
+		slot.Value = insertion.Value
 		return
 	}
 
-	insertion, slot.entry = slot.entry, insertion
+	insertion, slot.Entry = slot.Entry, insertion
 	return insertion, true
 }
 

table.go

@@ -9,7 +9,7 @@ import (
 )
 
 // ErrBadHash occurs when the hashes given to a [Table] cause too many key
-// collisions. Discard the old table, rebuild it from your source data, and try:
+// collisions. Try rebuilding the table using:
 //
 //  1. Different hash seeds. Equal seeds produce equal hash functions, which
 //     always cycle.
@@ -57,12 +57,12 @@ func (t *Table[K, V]) load() float64 {
 // 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) {
+func (t *Table[K, V]) insert(entry Entry[K, V]) (displaced Entry[K, V], homeless bool) {
-	if t.tableA.update(entry.key, entry.value) {
+	if t.tableA.update(entry.Key, entry.Value) {
 		return
 	}
 
-	if t.tableB.update(entry.key, entry.value) {
+	if t.tableB.update(entry.Key, entry.Value) {
 		return
 	}
 
@@ -97,7 +97,7 @@ 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 {
+		if _, failed := updated.insert(Entry[K, V]{k, v}); failed {
 			return false
 		}
 	}
@@ -153,10 +153,14 @@ func (t *Table[K, V]) Has(key K) (exists bool) {
 	return
 }
 
-// Put sets the value for a key. If it cannot be set, an error is returned.
+// 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) {
+// along with the last displaced entry.
+//
+// On failure, the returned entry and the current table contents together
+// preserve all previously inserted entries and the attempted entry.
+func (t *Table[K, V]) Put(key K, value V) (displaced Entry[K, V], err error) {
 	var (
-		entry    = entry[K, V]{key, value}
+		entry    = Entry[K, V]{key, value}
 		homeless bool
 	)
 
@@ -169,18 +173,18 @@ func (t *Table[K, V]) Put(key K, value V) (err error) {
 		// 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)
+			return entry, fmt.Errorf("bad hash: resize on load %d/%d", t.Size(), t.TotalCapacity())
 		}
 
 		// 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)
+			return entry, fmt.Errorf("bad hash: could not redistribute entries into larger table")
 		}
 	}
 
-	return fmt.Errorf("could not place entry after %d resizes: %w", defaultGrowthLimit, ErrBadHash)
+	return entry, fmt.Errorf("bad hash: could not place entry after %d resizes", defaultGrowthLimit)
 }
 
 // Drop removes a value for a key in the table. Returns whether the key had
@@ -202,7 +206,7 @@ func (t *Table[K, V]) Entries() iter.Seq2[K, V] {
 	return func(yield func(K, V) bool) {
 		for _, slot := range t.tableA.slots {
 			if slot.occupied {
-				if !yield(slot.key, slot.value) {
+				if !yield(slot.Key, slot.Value) {
 					return
 				}
 			}
@@ -210,7 +214,7 @@ func (t *Table[K, V]) Entries() iter.Seq2[K, V] {
 
 		for _, slot := range t.tableB.slots {
 			if slot.occupied {
-				if !yield(slot.key, slot.value) {
+				if !yield(slot.Key, slot.Value) {
 					return
 				}
 			}