Merge remote-tracking branch 'origin' into feat/get-no-error

## Description

Currently, the errors are not sentinel, and so are hard to test for. This PR makes sure hash collision errors are accounted for.

## Changes

- Add `ErrBadHash`. Happens when there are too many collisions for an item to be added.

### Design Decisions

- Chose to name `ErrBadHash` over `ErrCycle` because the feedbach that the user should be given is to evaluate their hash functions. Cycle collision is a bit esoteric.

## Checklist

- [x] Tests pass
- [x] Docs updated

Reviewed-on: #19
Co-authored-by: M.V. Hutz <git@maximhutz.me>
Co-committed-by: M.V. Hutz <git@maximhutz.me>

.gitea/ISSUE_TEMPLATE/BUG_REPORT.yml

@@ -0,0 +1,26 @@
+# yaml-language-server: $schema=https://www.schemastore.org/gitea-issue-forms.json
+name: 🐛 Bug Report
+about: Report a bug in this project
+title: "[BUG]: "
+body:
+  - type: textarea
+    id: context
+    attributes:
+      label: Context
+      placeholder: What circumstances led to the bug?
+    validations:
+      required: true
+  - type: textarea
+    id: expected-behavior
+    attributes:
+      label: Expected Behavior
+      placeholder: What did you expect would happen?
+    validations:
+      required: true
+  - type: textarea
+    id: actual-behavior
+    attributes:
+      label: Actual Behavior
+      placeholder: What happened, and why was it unexpected?
+    validations:
+      required: true

.gitea/ISSUE_TEMPLATE/FEATURE_REQUEST.yml

@@ -0,0 +1,37 @@
+# 'Feature Request Template' By @cheehwatang
+# https://github.com/cheehwatang/.github/blob/master/.github/ISSUE_TEMPLATE/feature_request.yml
+#
+# yaml-language-server: $schema=https://www.schemastore.org/gitea-issue-forms.json
+name: ✨ Feature Request
+about: Suggest an idea for this project
+title: "[FEATURE]: "
+body:
+  - type: dropdown
+    attributes:
+      multiple: false
+      label: Feature Type
+      options:
+        - "✨ New Feature"
+        - "📝 Documentation"
+        - "🎨 Style and UI"
+        - "🔨 Code Refactor"
+        - "⚡ Performance Improvements"
+        - "✅ New Test"
+    validations:
+      required: true
+  - type: textarea
+    id: description
+    attributes:
+      label: Description
+      placeholder: |
+        Give us a brief description of the feature or enhancement you would
+        like!
+    validations:
+      required: true
+  - type: textarea
+    id: additional-information
+    attributes:
+      label: Additional Information
+      placeholder: |
+        Give us some additional information on the feature request like proposed
+        solutions, links, screenshots, etc.

.gitea/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,2 @@
+# yaml-language-server: $schema=https://www.schemastore.org/gitea-issue-config.json
+blank_issues_enabled: false

.gitea/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,17 @@
+---
+name: "New Pull Request"
+about: "Standard PR template"
+title: ""
+ref: "main"
+---
+
+## Description
+
+## Changes
+
+### Design Decisions
+
+## Checklist
+
+- [ ] Tests pass
+- [ ] Docs updated

.gitea/workflows/ci.yml

@@ -6,6 +6,19 @@ on:
   pull_request:
 
 jobs:
+  check-pr-title:
+    name: Check PR Title
+    runs-on: ubuntu-latest
+    if: github.event_name == 'pull_request'
+    env:
+      TITLE: ${{ gitea.event.pull_request.title }}
+    steps:
+      - run: |
+          if ! echo "$TITLE" | grep -qE '^(WIP: )?(feat|fix|docs|chore|ci|test|refactor|perf|build|style|revert)(\(.+\))?(!)?: .+'; then
+            echo "::error::Pull Request title must follow conventional commits"
+            exit 1
+          fi
+
   lint-go:
     name: Go Lint
     runs-on: ubuntu-latest
@@ -39,6 +52,14 @@ jobs:
       - name: Run mutation tests
         run: make lint-makefile
 
+  lint-markdown:
+    name: Markdown Lint
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: DavidAnson/markdownlint-cli2-action@v19
+
   test-unit:
     name: Unit Tests
     runs-on: ubuntu-latest

.gitignore

@@ -24,4 +24,3 @@ go.work.sum
 
 # env file
 .env
-

.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

Makefile

@@ -1,4 +1,4 @@
-.PHONY: all help install clean test-unit test-mutation test-fuzz test docs lint-go lint-makefile lint
+.PHONY: all help install clean test-unit test-mutation test-fuzz test docs lint-go lint-makefile lint-markdown lint
 
 help: ## Show this help
 	@grep -E '^[a-zA-Z_-]+:.*##' $(MAKEFILE_LIST) | awk -F ':.*## ' '{printf "  %-15s %s\n", $$1, $$2}'
@@ -32,7 +32,10 @@ lint-go: ## Lint Go code
 lint-makefile: ## Lint the Makefile
 	checkmake Makefile
 
-lint: lint-go lint-makefile ## Lint all code
+lint-markdown: ## Lint Markdown files
+	docker run --rm -v $(CURDIR):/workdir davidanson/markdownlint-cli2 "**/*.md"
+
+lint: lint-go lint-makefile lint-markdown ## Lint all code
 
 docs: ## Serve godoc locally
 	@echo ">>> Visit: http://localhost:6060/pkg/$$(go list -m)"

README.md

@@ -1,3 +1,3 @@
-# go-cuckoo
+# <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).

assets/logo.svg

@@ -0,0 +1 @@
+<svg width="16" height="16" xmlns="http://www.w3.org/2000/svg" shape-rendering="crispEdges"><path fill="#2a1512" d="M3,6h1v1h-1v-1M2,7h1v1h-1v-1M12,7h1v1h-1v-1M1,8h1v1h-1v-1M4,8h1v2h-1v-2M14,8h1v1h-1v-1M11,9h1v2h-2v-1h1v-1M5,10h1v1h-1v-1M1,13h2v1h1v1h-2v-1h-1v-1M13,13h2v1h-1v1h-1v1h-1v-2h1v-1M4,15h1v1h-1v-1"/><path fill="#38231f" d="M4,6h1v1h-1v-1M11,6h1v1h-1v-1M13,7h1v1h-1v-1M1,9h1v2h-1v-2M14,9h1v1h-1v-1M14,11h1v2h-1v-2M1,12h1v1h-1v-1M5,15h3v1h-3v-1M10,15h2v1h-2v-1"/><path fill="#3f3f74" d="M7,3h2v1h-2v-1M6,4h1v1h-1v-1M9,4h1v1h-1v-1M5,5h1v5h-1v-5M10,5h1v5h-1v-5M6,10h4v1h-4v-1"/><path fill="#6262ab" d="M9,5h1v1h-1v-1M6,9h1v1h-1v-1M9,9h1v1h-1v-1"/><path fill="#663931" d="M11,8h1v1h-1v-1M2,9h1v1h-1v-1M14,10h1v1h-1v-1M1,11h1v1h-1v-1M3,11h2v1h-2v-1M13,11h1v1h-1v-1M2,12h1v1h-1v-1M5,12h1v1h-1v-1M10,12h3v2h-1v-1h-2v-1M3,13h1v1h-1v-1M8,13h2v1h-2v-1M4,14h3v1h-3v-1M10,14h2v1h-2v-1M8,15h2v1h-2v-1"/><path fill="#8d8dcb" d="M9,6h1v3h-1v1h-2v-1h1v-1h1v-2M6,8h1v1h-1v-1"/><path fill="#8f563b" d="M2,8h1v1h-1v-1M12,9h1v1h-1v-1M2,10h1v1h-1v-1M13,10h1v1h-1v-1M7,11h1v1h-1v-1M11,11h2v1h-2v-1M4,12h1v1h1v-1h1v2h-3v-2M13,12h1v1h-1v-1M10,13h2v1h-2v-1M7,14h3v1h-3v-1"/><path fill="#a4a4d5" d="M8,4h1v4h-1v1h-1v-1h-1v-2h1v-1h1v-1"/><path fill="#ab764a" d="M4,7h1v1h-1v-1M3,8h1v2h-1v-2M12,10h1v1h-1v-1M2,11h1v1h-1v-1M8,11h1v1h-1v-1M3,12h1v1h-1v-1M7,12h1v2h-1v-2"/><path fill="#cacaea" d="M7,4h1v1h-1v-1M6,5h1v1h-1v-1"/><path fill="#d9a066" d="M3,7h1v1h-1v-1M11,7h1v1h-1v-1M12,8h2v2h-1v-1h-1v-1M3,10h2v1h-2v-1M5,11h2v1h-2v-1M9,11h2v1h-1v1h-2v-1h1v-1"/></svg>

cuckoo_fuzz_test.go

@@ -1,7 +1,9 @@
 package cuckoo_test
 
 import (
+	"fmt"
 	"maps"
+	"os"
 	"testing"
 
 	"github.com/stretchr/testify/assert"
@@ -25,8 +27,9 @@ type fuzzStep struct {
 }
 
 type fuzzScenario struct {
-	seedA, seedB uint32
+	seedA, seedB           uint32
-	steps        []fuzzStep
+	capacity, growthFactor uint8
+	steps                  []fuzzStep
 }
 
 func FuzzInsertLookup(f *testing.F) {
@@ -40,14 +43,25 @@ func FuzzInsertLookup(f *testing.F) {
 			return
 		}
 
-		if scenario.seedA == scenario.seedB {
+		seedA, seedB := scenario.seedA, scenario.seedB
-			return
+		growthFactor := max(2, int(scenario.growthFactor))
+		capacity := int(scenario.capacity)
+
+		// If they are the same number, the hashes will clash, always causing an
+		// error.
+		if seedA == seedB {
+			t.Skip()
 		}
 
+		fmt.Fprintf(os.Stderr, "seedA=%d seedB=%d capacity=%d growthFactor=%d\n",
+			seedA, seedB, capacity, growthFactor)
+
 		actual := cuckoo.NewCustomTable[uint32, uint32](
-			offsetHash(scenario.seedA),
+			offsetHash(seedA),
-			offsetHash(scenario.seedB),
+			offsetHash(seedB),
 			func(a, b uint32) bool { return a == b },
+			cuckoo.Capacity(capacity),
+			cuckoo.GrowthFactor(growthFactor),
 		)
 
 		expected := map[uint32]uint32{}
@@ -59,16 +73,16 @@ func FuzzInsertLookup(f *testing.F) {
 
 				delete(expected, step.key)
 
-				_, err = actual.Get(step.key)
+				_, ok := actual.Get(step.key)
-				assert.Error(err)
+				assert.False(ok)
 			} else {
 				err := actual.Put(step.key, step.value)
 				assert.NoError(err)
 
 				expected[step.key] = step.value
 
-				found, err := actual.Get(step.key)
+				found, ok := actual.Get(step.key)
-				assert.NoError(err)
+				assert.True(ok)
 				assert.Equal(step.value, found)
 			}
 

cuckoo_test.go

@@ -108,28 +108,16 @@ func TestGetMany(t *testing.T) {
 	}
 
 	for i := range 2_000 {
-		value, err := table.Get(i)
+		value, ok := table.Get(i)
 		if i < 1_000 {
-			assert.NoError(err)
+			assert.True(ok)
 			assert.Equal(value, true)
 		} else {
-			assert.Error(err)
+			assert.False(ok)
 		}
 	}
 }
 
-func TestRemove(t *testing.T) {
-	assert := assert.New(t)
-	table := cuckoo.NewTable[int, bool]()
-
-	assert.False(table.Has(0))
-
-	err := table.Put(0, true)
-	assert.NoError(err)
-
-	assert.True(table.Has(0))
-}
-
 func TestDropExistingItem(t *testing.T) {
 	assert := assert.New(t)
 	key, value := 0, true

doc_example_test.go

@@ -14,19 +14,19 @@ func Example_basic() {
 		fmt.Println("Put error:", err)
 	}
 
-	if item, err := table.Get(1); err != nil {
+	if item, ok := table.Get(1); !ok {
-		fmt.Println("Error:", err)
+		fmt.Println("Not Found 1!")
 	} else {
 		fmt.Println("Found 1:", item)
 	}
 
-	if item, err := table.Get(0); err != nil {
+	if item, ok := table.Get(0); !ok {
-		fmt.Println("Error:", err)
+		fmt.Println("Not Found 0!")
 	} else {
 		fmt.Println("Found 0:", item)
 	}
 
 	// Output:
 	// Found 1: Hello, World!
-	// Error: key '0' not found
+	// Not Found 0!
 }

settings.go

@@ -1,5 +1,7 @@
 package cuckoo
 
+import "fmt"
+
 // DefaultCapacity is the initial capacity of a [Table]. It is inspired from
 // Java's [HashMap] implementation, which also uses 16.
 //
@@ -10,11 +12,12 @@ const DefaultCapacity uint64 = 16
 // hash table implementations use 2.
 const DefaultGrowthFactor uint64 = 2
 
-// DefaultMinimumLoad is the default lowest acceptable occupancy of a [Table].
+// defaultMinimumLoad is the default lowest acceptable occupancy of a [Table].
-// The value of 5% is taken from [libcuckoo].
+// The higher the minimum load, the more likely that a [Table.Put] will not
+// succeed. The value of 5% is taken from [libcuckoo].
 //
 // [libcuckoo]: https://github.com/efficient/libcuckoo/blob/656714705a055df2b7a605eb3c71586d9da1e119/libcuckoo/cuckoohash_config.hh#L21
-const DefaultMinimumLoad float64 = 0.05
+const defaultMinimumLoad float64 = 0.05
 
 type settings struct {
 	growthFactor  uint64
@@ -27,19 +30,21 @@ type settings struct {
 type Option func(*settings)
 
 // Capacity modifies the starting capacity of each bucket of the [Table]. The
-// value must be greater than 0.
+// value must be non-negative.
 func Capacity(value int) Option {
-	return func(s *settings) { s.bucketSize = uint64(value) }
+	if value < 0 {
-}
+		panic(fmt.Sprintf("go-cuckoo: Capacity must be non-negative, got %d", value))
+	}
 
-// MinimumLoad modifies the [DefaultMinimumLoad] of the [Table]. The value must
+	return func(s *settings) { s.bucketSize = uint64(value) }
-// be between 0.00 and 1.00.
-func MinimumLoad(value float64) Option {
-	return func(s *settings) { s.minLoadFactor = value }
 }
 
 // GrowthFactor controls how much the capacity of the [Table] multiplies when
 // it must resize. The value must be greater than 1.
 func GrowthFactor(value int) Option {
+	if value < 2 {
+		panic(fmt.Sprintf("go-cuckoo: GrowthFactor must be greater than 1, got %d", value))
+	}
+
 	return func(s *settings) { s.growthFactor = uint64(value) }
 }

table.go

@@ -1,12 +1,21 @@
 package cuckoo
 
 import (
+	"errors"
 	"fmt"
 	"iter"
 	"math/bits"
 	"strings"
 )
 
+// 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 is hash table that uses cuckoo hashing to resolve collision. Create
 // one with [NewTable]. Or if you want more granularity, use [NewTableBy] or
 // [NewCustomTable].
@@ -86,24 +95,23 @@ func (t *Table[K, V]) shrink() error {
 	return t.resize(t.bucketA.capacity / t.growthFactor)
 }
 
-// Get fetches the value for a key in the [Table]. Returns an error if no value
+// Get fetches the value for a key in the [Table].
-// is found.
+func (t Table[K, V]) Get(key K) (value V, ok bool) {
-func (t Table[K, V]) Get(key K) (value V, err error) {
 	if item, ok := t.bucketA.get(key); ok {
-		return item, nil
+		return item, true
 	}
 
 	if item, ok := t.bucketB.get(key); ok {
-		return item, nil
+		return item, true
 	}
 
-	return value, fmt.Errorf("key '%v' not found", 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)
+	_, exists = t.Get(key)
-	return err == nil
+	return
 }
 
 // Put sets the value for a key. Returns error if its value cannot be set.
@@ -128,7 +136,7 @@ func (t *Table[K, V]) Put(key K, value V) (err error) {
 	}
 
 	if t.load() < t.minLoadFactor {
-		return fmt.Errorf("bad hash: resize on load %d/%d = %f", t.Size(), t.TotalCapacity(), t.load())
+		return fmt.Errorf("hash functions produced a cycle at load %d/%d: %w", t.Size(), t.TotalCapacity(), ErrBadHash)
 	}
 
 	if err := t.grow(); err != nil {
@@ -198,7 +206,7 @@ func NewCustomTable[K, V any](hashA, hashB Hash[K], compare EqualFunc[K], option
 	settings := &settings{
 		growthFactor:  DefaultGrowthFactor,
 		bucketSize:    DefaultCapacity,
-		minLoadFactor: DefaultMinimumLoad,
+		minLoadFactor: defaultMinimumLoad,
 	}
 
 	for _, option := range options {