Compare commits
4 Commits
docs/contr
...
e2ba398a62
| Author | SHA1 | Date | |
|---|---|---|---|
e2ba398a62
|
|||
|
c1314f8a3c
|
|||
|
74ed81761c
|
|||
|
d4acdda95b
|
@@ -1,26 +0,0 @@
|
||||
# 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
|
||||
@@ -1,37 +0,0 @@
|
||||
# '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.
|
||||
@@ -1,2 +0,0 @@
|
||||
# yaml-language-server: $schema=https://www.schemastore.org/gitea-issue-config.json
|
||||
blank_issues_enabled: false
|
||||
@@ -1,17 +0,0 @@
|
||||
---
|
||||
name: "New Pull Request"
|
||||
about: "Standard PR template"
|
||||
title: ""
|
||||
ref: "main"
|
||||
---
|
||||
|
||||
## Description
|
||||
|
||||
## Changes
|
||||
|
||||
### Design Decisions
|
||||
|
||||
## Checklist
|
||||
|
||||
- [ ] Tests pass
|
||||
- [ ] Docs updated
|
||||
@@ -6,19 +6,6 @@ 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
|
||||
@@ -52,14 +39,6 @@ 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
|
||||
|
||||
1
.gitignore
vendored
1
.gitignore
vendored
@@ -24,3 +24,4 @@ go.work.sum
|
||||
|
||||
# env file
|
||||
.env
|
||||
|
||||
|
||||
@@ -114,9 +114,6 @@ linters:
|
||||
# Reports uses of functions with replacement inside the testing package.
|
||||
- usetesting
|
||||
|
||||
# Reports mixed receiver types in structs/interfaces.
|
||||
- recvcheck
|
||||
|
||||
settings:
|
||||
revive:
|
||||
rules:
|
||||
|
||||
@@ -5,5 +5,3 @@ unleash:
|
||||
|
||||
workers: 4
|
||||
dry-run: false
|
||||
threshold:
|
||||
efficacy: 1.0
|
||||
@@ -1,17 +0,0 @@
|
||||
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
|
||||
11
Makefile
11
Makefile
@@ -1,4 +1,4 @@
|
||||
.PHONY: all help install clean test-unit test-mutation test-fuzz test docs lint-go lint-makefile lint-markdown lint
|
||||
.PHONY: all help install clean test-unit test-mutation test-fuzz test docs lint-go lint-makefile lint
|
||||
|
||||
help: ## Show this help
|
||||
@grep -E '^[a-zA-Z_-]+:.*##' $(MAKEFILE_LIST) | awk -F ':.*## ' '{printf " %-15s %s\n", $$1, $$2}'
|
||||
@@ -16,12 +16,10 @@ test-unit: ## Run unit tests with coverage
|
||||
test-mutation: ## Run mutation tests with gremlins
|
||||
gremlins unleash
|
||||
|
||||
FUZZ_TIME ?= 30
|
||||
|
||||
test-fuzz: ## Run all fuzz tests for 30s each
|
||||
@for func in $$(grep -r --include='*_test.go' -oh 'func Fuzz\w*' . | sed 's/func //'); do \
|
||||
echo "Fuzzing $$func..."; \
|
||||
go test ./... -fuzz="^$$func$$" -fuzztime=$(FUZZ_TIME)s; \
|
||||
go test ./... -fuzz="^$$func$$" -fuzztime=30s; \
|
||||
done
|
||||
|
||||
test: test-unit test-mutation test-fuzz ## Run all tests
|
||||
@@ -32,10 +30,7 @@ lint-go: ## Lint Go code
|
||||
lint-makefile: ## Lint the Makefile
|
||||
checkmake Makefile
|
||||
|
||||
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
|
||||
lint: lint-go lint-makefile ## Lint all code
|
||||
|
||||
docs: ## Serve godoc locally
|
||||
@echo ">>> Visit: http://localhost:6060/pkg/$$(go list -m)"
|
||||
|
||||
@@ -1,3 +1,3 @@
|
||||
# <img height="30" src="assets/logo.svg" alt="Go Cuckoo, by `mvhutz`."> Go Cuckoo
|
||||
# go-cuckoo
|
||||
|
||||
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).
|
||||
A hash table that uses cuckoo hashing to achieve a worst-case O(1) lookup time.
|
||||
@@ -1,542 +0,0 @@
|
||||
# Designing an Idiomatic API Interface
|
||||
|
||||
We (the maintainers) built `go-cuckoo`'s API interface without design intent.
|
||||
Up until now, we paid more attention implementing the underlying functionality of the cuckoo hashing.
|
||||
|
||||
With the fundamentals of the algorithm built, we should revisit the interface.
|
||||
It should align closer to the following principles:
|
||||
|
||||
- **Congruency**
|
||||
A `go-cuckoo` table should have the same core functionality as Go's built-in map.
|
||||
|
||||
- **Familiarity**
|
||||
A `go-cuckoo` table should behave similarly to Go's standard map, so users will intuitively know how to use it.
|
||||
In effect, its users will carry less cognitive load.
|
||||
|
||||
## Current State
|
||||
|
||||
### Interface of the built-in Map
|
||||
|
||||
Listed below is every interface provided by Go to the built-in map object.
|
||||
Also included, are the functions from the package `maps` in the standard library.
|
||||
|
||||
<details>
|
||||
<summary>Interfaces</summary>
|
||||
|
||||
| # | built-in Interface | Description |
|
||||
| --- | ---------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| 1 | `m := make(map[K]V)` | Returns an empty map using the built-in `make()` function. |
|
||||
| 2 | `m := make(map[K]V, hint)` | Returns an empty map using `make()`, with a capacity 'hint'. This hint is how many items the map expects to hold, _not_ a measure of how large it is. |
|
||||
| 3 | `m := map[K]V{...}` | Returns a map, which may be filled with entries in the ellipsis (optional). |
|
||||
| 4 | `var m map[K]V` | Defines an empty _variable_ that holds a map. This differs from #1 because `m` is uninitialized (nil) here. |
|
||||
| 5 | `m[k] := v` | Assigns the value of `k` to `v`. |
|
||||
| 6 | `v := m[k]` | Returns the value of `k` if it exists. Otherwise, `v` is uninitialized. |
|
||||
| 7 | `v, ok := m[k]` | Similar to #6, except `ok` is equal to whether `v` is initialized. This is comma-ok notation. |
|
||||
| 8 | `for k, v := range m` | Iterates over every key-value pair in `m`. The order is random. |
|
||||
| 9 | `delete(m, k)` | Unassigns the value `k`. Returns no value. |
|
||||
| 10 | `clear(m)` | Unassigns all keys in `m`. Returns no value. |
|
||||
| 11 | `n := len(m)` | Returns the number of entries in `m`. If nil, `m` returns 0. |
|
||||
| 12 | `m2 := maps.Clone(m)` | Returns a copy of `m`. |
|
||||
| 13 | `maps.Copy(dst, src)` | Assigns every entry of `src` in `dst`. |
|
||||
| 14 | `ok := maps.Equal(m1, m2)` | Returns true iff `m1` and `m2` the same entries. |
|
||||
| 15 | `ok := maps.EqualFunc(m1, m2, fn)` | Like #14, but with a custom comparator for non-comparable values. |
|
||||
| 16 | `maps.DeleteFunc(m, fn)` | Removes every entry in `m` which satisfies `fn`. Returns no value. |
|
||||
| 17 | `it2 := maps.All(m)` | Returns an 2D iterator over every key-value pair. |
|
||||
| 18 | `it := maps.Keys(m)` | Returns an iterator over every key. |
|
||||
| 19 | `it := maps.Values(m)` | Returns an iterator over every value. There can be duplicates. |
|
||||
| 20 | `m := maps.Collect(seq)` | Returns a map, with every entry defined in a 2D iterator over key-value pairs. |
|
||||
| 21 | `maps.Insert(m, seq)` | Assigns to `m` all key-value pairs in 2D iterator `seq`. Returns no value. |
|
||||
|
||||
</details>
|
||||
|
||||
### Interface of `go-cuckoo`
|
||||
|
||||
On the other hand, here is the current contract for `go-cuckoo`.
|
||||
|
||||
<details>
|
||||
<summary>Interfaces</summary>
|
||||
|
||||
| # | built-in Interface | Description |
|
||||
| --- | -------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------- |
|
||||
| 1 | `m := New(opts...)` | Creates a table using the default hash and equal function. The options configure its behavior. Confined to comparable keys. |
|
||||
| 2 | `m := NewBy(keyFunc, opts...)` | Like #1, but allows any key type. A `keyFunc` is used to derive a comparable key. |
|
||||
| 3 | `m := NewCustom(hashA, hashB, equalFunc, opts...)` | Like #1, but allows control over the hashes used to allow any key type. An `equalFunc` determines key equality. |
|
||||
| 4 | `seq := m.Entries()` | Returns an unordered 2D iterator of all key-value pairs in the table. |
|
||||
| 5 | `v := m.Find(k)` | Removes the value for `k`. Returns true if `k` existed. |
|
||||
| 6 | `v, ok := m.Get(k)` | Returns the value for `k` in the table. Also, returns true if the `k` exists, otherwise false. When false, `v` is undefined. |
|
||||
| 7 | `ok := m.Has(k)` | Returns true if `k` is in the table. |
|
||||
| 8 | `err := m.Put(k, v)` | Sets value `v` for key `k`. Otherwise, returns error. |
|
||||
| 9 | `n := m.Size()` | Returns the number of items in `m`. |
|
||||
| 10 | `str := m.String()` | Returns `m` as a string in the format "table[k1:v1 k2:v2 ...]". |
|
||||
| 11 | `cap := m.TotalCapacity()` | Returns how many slots `m` has allocated. |
|
||||
| 12 | `ok := m.Drop(k)` | Removes `k` from the table. Returns whether the key had existed. |
|
||||
|
||||
</details>
|
||||
|
||||
### Determining Congruency
|
||||
|
||||
So, how does the core functionality compare?
|
||||
Listed below is an analysis of every interface in Go's standard map.
|
||||
Each is compared against what `go-cuckoo` offers, and categorized into the following groups:
|
||||
|
||||
- ✅ Covered: an analog exists.
|
||||
- ⚠️ Partial: workaround available.
|
||||
- ❌ Gap: no analog yet; addressed in [Target State](#solving-congruency).
|
||||
|
||||
Specifically, here we are checking for functionality.
|
||||
Is there functionality that this offers which `go-cuckoo` does not?
|
||||
We are checking accessibility, but not discoverability.
|
||||
The latter will be considered later.
|
||||
|
||||
<details>
|
||||
<summary>✅ <code>m := make(map[K]V)</code></summary>
|
||||
|
||||
The analog is `m := New()`.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>⚠️ <code>m := make(map[K]V, hint)</code></summary>
|
||||
|
||||
This has no simple analog.
|
||||
|
||||
It is close to `m := New(Capacity(hint))`, but it assigns starting capacity, not expected size.
|
||||
For the built-in map, these are two separate things.
|
||||
|
||||
- Capacity is an internal measure, used to optimize space/speed.
|
||||
It is hidden from the user because it depends on the underlying implementation, which may change.
|
||||
- Expected size requires the map must hold a number of items before resizing.
|
||||
This is tangeable and agnostic to implementation, hence why it is given to the user.
|
||||
|
||||
In short, this interface defines expected size, but `Capacity()` defines capacity.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>❌ <code>m := map[K]V{...}</code></summary>
|
||||
|
||||
This has no simple analog, the closest being:
|
||||
|
||||
```go
|
||||
m := New[K, V]()
|
||||
for k, v := range startingEntries {
|
||||
m.Put(k, v)
|
||||
}
|
||||
```
|
||||
|
||||
It is idiomatic, but far less ergonomic.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>✅ <code>var m map[K]V</code></summary>
|
||||
|
||||
The analog is `var m Table[K, V]`.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>✅ <code>m[k] := v</code></summary>
|
||||
|
||||
The analog is `err := m.Put(k, v)`.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>✅ <code>v := m[k]</code></summary>
|
||||
|
||||
The analog is `v := m.Find(k)`.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>✅ <code>v, ok := m[k]</code></summary>
|
||||
|
||||
The analog is `v, ok := m.Get(k)`.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>✅ <code>for k, v := range m</code></summary>
|
||||
|
||||
The analog is `for k, v := range m.Entries()`.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>✅ <code>delete(m, k)</code></summary>
|
||||
|
||||
The analog is `ok := m.Drop(k)`.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>❌ <code>clear(m)</code></summary>
|
||||
|
||||
There is no analog.
|
||||
|
||||
The easiest may to do this is to delete all items individually:
|
||||
|
||||
```go
|
||||
for k := range m.Entries() {
|
||||
m.Drop(k)
|
||||
}
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>✅ <code>n := len(m)</code></summary>
|
||||
|
||||
The analog is `n := m.Size()`.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>❌ <code>m2 := maps.Clone(m)</code></summary>
|
||||
|
||||
There is no analog.
|
||||
|
||||
The easiest way to do this currently is to make a new map, and manually add the items.
|
||||
|
||||
```go
|
||||
m2 := cuckoo.Table[K, V]()
|
||||
|
||||
for k, v := range m.Entries() {
|
||||
m2.Put(k, v)
|
||||
}
|
||||
```
|
||||
|
||||
This gets complicated by the various options available to the user.
|
||||
Furthermore, any custom `EqualFunc`, `keyFunc` or `Hash` is not transferred.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>❌ <code>maps.Copy(dst, src)</code></summary>
|
||||
|
||||
There is no analog.
|
||||
|
||||
The simplest way to do this is with a for-loop.
|
||||
|
||||
```go
|
||||
for k, v := range src.Entries() {
|
||||
dst.Put(k, v)
|
||||
}
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>❌ <code>ok := maps.Equal(m1, m2)</code></summary>
|
||||
|
||||
There is no analog.
|
||||
|
||||
Users have to manually check the key-value pairs to determine equality.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>❌ <code>ok := maps.EqualFunc(m1, m2, fn)</code></summary>
|
||||
|
||||
There is no analog.
|
||||
|
||||
Users have to manually check the key-value pairs to determine equality.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>❌ <code>maps.DeleteFunc(m, fn)</code></summary>
|
||||
|
||||
There is no analog.
|
||||
|
||||
Users have to manually delete keys.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>✅ <code>it2 := maps.All(m)</code></summary>
|
||||
|
||||
The analog is `it2 := m.Entries()`.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>⚠️ <code>it := maps.Keys(m)</code></summary>
|
||||
|
||||
There is no simple analog.
|
||||
|
||||
A close neighbor is `it2 := m.Entries()`.
|
||||
Users can use this in a for-loop, and pick out just the keys:
|
||||
|
||||
```go
|
||||
for k := range m.Entries() {
|
||||
// ...
|
||||
}
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>⚠️ <code>it := maps.Values(m)</code></summary>
|
||||
|
||||
There is no simple analog.
|
||||
|
||||
A close neighbor is `it2 := m.Entries()`.
|
||||
Users can use this in a for-loop, and pick out just the values:
|
||||
|
||||
```go
|
||||
for _, v := range m.Entries() {
|
||||
// ...
|
||||
}
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>❌ <code>m := maps.Collect(seq)</code></summary>
|
||||
|
||||
There is no analog.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>❌ <code>maps.Insert(m, seq)</code></summary>
|
||||
|
||||
There is no analog.
|
||||
|
||||
</details>
|
||||
|
||||
## Target State
|
||||
|
||||
### Solving Congruency
|
||||
|
||||
We should make the following changes to accomodate for congruency:
|
||||
|
||||
<details>
|
||||
<summary><code>ok := maps.EqualFunc(m1, m2, fn)</code></summary>
|
||||
|
||||
We should implement a new function:
|
||||
|
||||
```go
|
||||
func EqualFunc[K, V1, V2 any](t1 *Table[K, V1], t2 *Table[K, V2], eq func(V1, V2) bool) bool
|
||||
```
|
||||
|
||||
This function is free, and not bound as a receiver function.
|
||||
(It is called `cuckoo.Equal(t1, t2)`, not `t1.Equals(t2)`.)
|
||||
The latter implies `t1` has authority, when in fact neither do.
|
||||
|
||||
We define equality as:
|
||||
|
||||
1. Neither table has a key the other doesn't.
|
||||
2. Each key has the same value in each table.
|
||||
Parameter `eq` determines this equality.
|
||||
|
||||
Custom `EqualFunc`'s complicate this, as they modulate key identity in tables.
|
||||
If two tables may differ on whether two keys are different, this function might break.
|
||||
So, we must assume that:
|
||||
|
||||
- Both tables have `EqualFunc`'s which 'agree' on the identity of the keys present in the tables.
|
||||
Agreement is defined as: if two keys are distinct in one table, they are distinct in the other.
|
||||
|
||||
The name `EqualFunc` is already taken by `EqualFunc[K, V]`: an alias for `func(a, b K) bool`.
|
||||
Inlining `EqualFunc[K, V]` would solve this problem.
|
||||
We will move the documentation attached to it to `DefaultEqualFunc`.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary><code>ok := maps.Equal(m1, m2)</code></summary>
|
||||
|
||||
We should implement a new function, to conform with the standard library:
|
||||
|
||||
```go
|
||||
func Equal[K any, V comparable](t1, t2 *Table[K, V]) bool
|
||||
```
|
||||
|
||||
It uses the same equality check as in `EqualFunc`.
|
||||
Once again, the function is free because it is symmetric.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary><code>maps.Insert(m, seq)</code></summary>
|
||||
|
||||
We should implement a new receiver for the table:
|
||||
|
||||
```go
|
||||
func (t *Table[K, V]) Insert(seq iter.Seq2[K, V]) error
|
||||
```
|
||||
|
||||
A receiver fits better even though `maps.Insert` is a free function, because copying it is asymmetric.
|
||||
Map `dst` receives entries from map `src`.
|
||||
It's only free because Go's standard map is built into the language, and so cannot have receivers.
|
||||
|
||||
In terms of naming, `t.Extend` is more accurate, and has precedent in [Python](docs.python.org/3/tutorial/datastructures.html#more-on-lists) and [Rust](https://doc.rust-lang.org/std/iter/trait.Extend.html).
|
||||
When [adding iterator function](https://github.com/golang/go/issues/61900) to the `maps` package, the Go team chose to frame it as 'sources' and 'sinks'.
|
||||
With this model, `maps.Insert` made more sense than `maps.Extend`.
|
||||
Ultimately, `t.Insert()` is a better choice to be consistent with `maps`.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary><code>maps.Copy(dst, src)</code></summary>
|
||||
|
||||
We should implement a new receiver for the table:
|
||||
|
||||
```go
|
||||
func (t *Table[K, V]) Copy(src *Table[K, V]) error
|
||||
```
|
||||
|
||||
It's functionality should match that of `t.Insert()`.
|
||||
|
||||
A receiver fits better even though `maps.Copy` is a free function, 'copying' it is asymmetric: `dst` is writen into by `src`.
|
||||
It is only free because Go's standard map is built into the language, and so cannot have receivers.
|
||||
|
||||
The name `t.Merge()` might be more accurate, but it does work because:
|
||||
|
||||
- `t.Copy()` matches Go's built-in `copy()`, and `io.Copy()`. The Go team used [the same logic](https://github.com/golang/go/discussions/47330#discussioncomment-1167799) to name `maps.Copy()`.
|
||||
In this case, `t.Merge()` would be an outlier.
|
||||
- `t.Merge()` implies some sort of conflict-resolution, when there is not.
|
||||
It simply overwrites the values.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary><code>maps.DeleteFunc(m, fn)</code></summary>
|
||||
|
||||
We should implement a new receiver for the table:
|
||||
|
||||
```go
|
||||
func (t *Table[K, V]) DeleteFunc(del func(K, V) bool)
|
||||
```
|
||||
|
||||
It would have the same functionality as `maps.DeleteFunc`.
|
||||
|
||||
A free function could work here, but `t` has clear authority over `del`.
|
||||
Other than being consistent with the `maps` package, `t.DeleteFunc` follows the Go convention of appending `Func` to higher-order equivalents of functions.
|
||||
This trumps names like `t.DeleteIf`, which lend more to [Java](https://docs.oracle.com/javase/8/docs/api/java/util/ArrayList.html#removeIf-java.util.function.Predicate-) or [C++](https://en.cppreference.com/cpp/algorithm/remove).
|
||||
The word `Delete` is also convention, tying back to the built-in `delete()`.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary><code>m := maps.Collect(seq)</code></summary>
|
||||
|
||||
We should implement a new constructor.
|
||||
|
||||
```go
|
||||
func Collect[K comparable, V any](seq iter.Seq2[K, V]) (*Table[K, V], error)
|
||||
```
|
||||
|
||||
It would create a `New()` table, and insert all entries in `seq`.
|
||||
|
||||
This reveicer only supports the standard table constructor, with comparable keys.
|
||||
It is tempting to add `CollectBy` or `CollectCustom` to support all table types, but doing so would pollute the public interface.
|
||||
|
||||
It would be just one more line to initialize the table and then call `t.Insert` directly:
|
||||
|
||||
```go
|
||||
t := // ...
|
||||
err := t.Insert(seq)
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary><code>m := map[K]V{...}</code></summary>
|
||||
|
||||
We should make a new constructor, because entries are generic.
|
||||
So, creating an option with inialized entries doesn't work.
|
||||
|
||||
With the previous additions, users have a few options.
|
||||
If they want to use a `New()` table, `t.Collect` matches well:
|
||||
|
||||
```go
|
||||
t, err := cuckoo.Collect(func(yield func(K, V) bool) {
|
||||
yield(key1, val1)
|
||||
yield(key2, val2)
|
||||
})
|
||||
```
|
||||
|
||||
For `NewCustom()` or `NewBy()` tables, users can call `t.Insert` after initialization:
|
||||
|
||||
```go
|
||||
t := // ...
|
||||
err := t.Insert(func(yield func(K, V) bool) {
|
||||
yield(key1, val1)
|
||||
yield(key2, val2)
|
||||
})
|
||||
```
|
||||
|
||||
It is one more line.
|
||||
But, the alternative is polluting the public interface with corresponding `*WithEntries` constuctors.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary><code>m := make(map[K]V, hint)</code></summary>
|
||||
|
||||
We should add a new option:
|
||||
|
||||
```go
|
||||
func ExpectedSize(n int) Option
|
||||
```
|
||||
|
||||
When fed to a table, it will allocate enough space to hold `n` entries without a resize.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary><code>clear(m)</code></summary>
|
||||
|
||||
We should implement a new receiver:
|
||||
|
||||
```go
|
||||
func (t *Table[K, V]) Clear()
|
||||
```
|
||||
|
||||
It will remove all entries from the table.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary><code>m2 := maps.Clone(m)</code></summary>
|
||||
|
||||
We should implement a matching function:
|
||||
|
||||
```go
|
||||
func (t *Table[K, V]) Clone() *Table[K, V]
|
||||
```
|
||||
|
||||
Also, it will copy the hash, equality function, and options used in the table.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary><code>it := maps.Keys(m)</code></summary>
|
||||
|
||||
We should implement a matching function:
|
||||
|
||||
```go
|
||||
func (t *Table[K, V]) Keys() iter.Seq[K]
|
||||
```
|
||||
|
||||
It is tempting to just have `All()`, but it returns a `Seq2`, not a `Seq`.
|
||||
There is no iterator adaptor between `Seq` and `Seq2`, and will not be for the foreseeable future.
|
||||
This function, while it feels superfluous, is required.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary><code>it := maps.Values(m)</code></summary>
|
||||
|
||||
We should implement a matching function:
|
||||
|
||||
```go
|
||||
func (t *Table[K, V]) Values() iter.Seq[V]
|
||||
```
|
||||
|
||||
For the same reason we need `Keys()`, we also need `Values()`.
|
||||
|
||||
</details>
|
||||
@@ -1 +0,0 @@
|
||||
<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>
|
||||
|
Before Width: | Height: | Size: 1.5 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 963 B |
Binary file not shown.
|
Before Width: | Height: | Size: 418 B |
85
bucket.go
Normal file
85
bucket.go
Normal file
@@ -0,0 +1,85 @@
|
||||
package cuckoo
|
||||
|
||||
type entry[K, V any] struct {
|
||||
key K
|
||||
value V
|
||||
}
|
||||
|
||||
type slot[K, V any] struct {
|
||||
entry[K, V]
|
||||
occupied bool
|
||||
}
|
||||
|
||||
type bucket[K, V any] struct {
|
||||
hash Hash[K]
|
||||
slots []slot[K, V]
|
||||
capacity, size uint64
|
||||
compare EqualFunc[K]
|
||||
}
|
||||
|
||||
func (b bucket[K, V]) location(key K) uint64 {
|
||||
return b.hash(key) % b.capacity
|
||||
}
|
||||
|
||||
func (b bucket[K, V]) get(key K) (value V, found bool) {
|
||||
slot := b.slots[b.location(key)]
|
||||
return slot.value, slot.occupied && b.compare(slot.key, key)
|
||||
}
|
||||
|
||||
func (b *bucket[K, V]) drop(key K) (occupied bool) {
|
||||
slot := &b.slots[b.location(key)]
|
||||
|
||||
if slot.occupied && b.compare(slot.key, key) {
|
||||
slot.occupied = false
|
||||
b.size--
|
||||
return true
|
||||
}
|
||||
|
||||
return false
|
||||
}
|
||||
|
||||
func (b *bucket[K, V]) resize(capacity uint64) {
|
||||
b.slots = make([]slot[K, V], capacity)
|
||||
b.capacity = capacity
|
||||
b.size = 0
|
||||
}
|
||||
|
||||
func (b bucket[K, V]) update(key K, value V) (updated bool) {
|
||||
slot := &b.slots[b.location(key)]
|
||||
|
||||
if slot.occupied && b.compare(slot.key, key) {
|
||||
slot.value = value
|
||||
return true
|
||||
}
|
||||
|
||||
return false
|
||||
}
|
||||
|
||||
func (b *bucket[K, V]) evict(insertion entry[K, V]) (evicted entry[K, V], eviction bool) {
|
||||
slot := &b.slots[b.location(insertion.key)]
|
||||
|
||||
if !slot.occupied {
|
||||
slot.entry = insertion
|
||||
slot.occupied = true
|
||||
b.size++
|
||||
return
|
||||
}
|
||||
|
||||
if b.compare(slot.key, insertion.key) {
|
||||
slot.value = insertion.value
|
||||
return
|
||||
}
|
||||
|
||||
insertion, slot.entry = slot.entry, insertion
|
||||
return insertion, true
|
||||
}
|
||||
|
||||
func newBucket[K, V any](capacity uint64, hash Hash[K], compare EqualFunc[K]) bucket[K, V] {
|
||||
return bucket[K, V]{
|
||||
hash: hash,
|
||||
capacity: capacity,
|
||||
compare: compare,
|
||||
size: 0,
|
||||
slots: make([]slot[K, V], capacity),
|
||||
}
|
||||
}
|
||||
@@ -2,7 +2,7 @@ package cuckoo
|
||||
|
||||
// An EqualFunc determines whethers two keys are 'equal'. Keys that are 'equal'
|
||||
// are teated as the same by the [Table]. A good EqualFunc is pure,
|
||||
// deterministic, and fast. By default, [New] uses [DefaultEqualFunc].
|
||||
// deterministic, and fast. By default, [NewTable] uses [DefaultEqualFunc].
|
||||
//
|
||||
// This function MUST NOT return true if the [Hash] digest of two keys
|
||||
// are different: the [Table] will not work.
|
||||
|
||||
@@ -28,7 +28,7 @@ func ExampleEqualFunc_badEqualFunc() {
|
||||
// Two users with the same ID are equal.
|
||||
isEqual := func(a, b User) bool { return a.ID == b.ID }
|
||||
|
||||
userbase := cuckoo.NewCustom[User, bool](makeHash(1), makeHash(2), isEqual)
|
||||
userbase := cuckoo.NewCustomTable[User, bool](makeHash(1), makeHash(2), isEqual)
|
||||
|
||||
(userbase.Put(User{"1", "Robert Doe"}, true))
|
||||
|
||||
|
||||
@@ -1,13 +1,11 @@
|
||||
package cuckoo_test
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"maps"
|
||||
"os"
|
||||
"bytes"
|
||||
"encoding/binary"
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
go_fuzz_utils "github.com/trailofbits/go-fuzz-utils"
|
||||
|
||||
"git.maximhutz.com/tools/go-cuckoo"
|
||||
)
|
||||
@@ -21,73 +19,31 @@ func offsetHash(seed uint32) cuckoo.Hash[uint32] {
|
||||
}
|
||||
}
|
||||
|
||||
type fuzzStep struct {
|
||||
drop bool
|
||||
key, value uint32
|
||||
}
|
||||
|
||||
type fuzzScenario struct {
|
||||
seedA, seedB uint32
|
||||
capacity, growthFactor uint8
|
||||
steps []fuzzStep
|
||||
}
|
||||
|
||||
func FuzzInsertLookup(f *testing.F) {
|
||||
f.Fuzz(func(t *testing.T, data []byte) {
|
||||
var scenario fuzzScenario
|
||||
f.Fuzz(func(t *testing.T, data []byte, seedA, seedB uint32) {
|
||||
assert := assert.New(t)
|
||||
|
||||
if tp, err := go_fuzz_utils.NewTypeProvider(data); err != nil {
|
||||
return
|
||||
} else if err := tp.Fill(&scenario); err != nil {
|
||||
return
|
||||
}
|
||||
|
||||
seedA, seedB := scenario.seedA, scenario.seedB
|
||||
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.NewCustom[uint32, uint32](
|
||||
table := cuckoo.NewCustomTable[uint32, uint32](
|
||||
offsetHash(seedA),
|
||||
offsetHash(seedB),
|
||||
func(a, b uint32) bool { return a == b },
|
||||
cuckoo.Capacity(capacity),
|
||||
cuckoo.GrowthFactor(growthFactor),
|
||||
)
|
||||
|
||||
expected := map[uint32]uint32{}
|
||||
|
||||
for _, step := range scenario.steps {
|
||||
if step.drop {
|
||||
ok := actual.Drop(step.key)
|
||||
_, has := expected[step.key]
|
||||
assert.Equal(ok, has)
|
||||
|
||||
delete(expected, step.key)
|
||||
|
||||
_, ok = actual.Get(step.key)
|
||||
assert.False(ok)
|
||||
} else {
|
||||
err := actual.Put(step.key, step.value)
|
||||
assert.NoError(err)
|
||||
|
||||
expected[step.key] = step.value
|
||||
|
||||
found, ok := actual.Get(step.key)
|
||||
assert.True(ok)
|
||||
assert.Equal(step.value, found)
|
||||
if seedA == seedB {
|
||||
return
|
||||
}
|
||||
|
||||
assert.Equal(expected, maps.Collect(actual.Entries()))
|
||||
r := bytes.NewReader(data)
|
||||
var key, value uint32
|
||||
for binary.Read(r, binary.LittleEndian, &key) == nil &&
|
||||
binary.Read(r, binary.LittleEndian, &value) == nil {
|
||||
|
||||
err := table.Put(key, value)
|
||||
assert.NoError(err)
|
||||
|
||||
found, err := table.Get(key)
|
||||
assert.NoError(err)
|
||||
assert.Equal(value, found)
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
@@ -11,7 +11,7 @@ func TestMaxEvictions(t *testing.T) {
|
||||
assert := assert.New(t)
|
||||
|
||||
for i := 16; i < 116; i++ {
|
||||
table := New[int, bool](Capacity(i / 2))
|
||||
table := NewTable[int, bool](Capacity(i / 2))
|
||||
expectedEvictions := 3 * math.Floor(math.Log2(float64(i)))
|
||||
|
||||
assert.Equal(table.maxEvictions(), int(expectedEvictions))
|
||||
@@ -20,7 +20,7 @@ func TestMaxEvictions(t *testing.T) {
|
||||
|
||||
func TestLoad(t *testing.T) {
|
||||
assert := assert.New(t)
|
||||
table := New[int, bool](Capacity(8))
|
||||
table := NewTable[int, bool](Capacity(8))
|
||||
|
||||
for i := range 16 {
|
||||
err := table.Put(i, true)
|
||||
|
||||
137
cuckoo_test.go
137
cuckoo_test.go
@@ -1,7 +1,6 @@
|
||||
package cuckoo_test
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"maps"
|
||||
"math/rand/v2"
|
||||
"testing"
|
||||
@@ -14,7 +13,7 @@ import (
|
||||
func TestNewTable(t *testing.T) {
|
||||
assert := assert.New(t)
|
||||
|
||||
table := cuckoo.New[int, bool]()
|
||||
table := cuckoo.NewTable[int, bool]()
|
||||
|
||||
assert.NotNil(table)
|
||||
assert.Zero(table.Size())
|
||||
@@ -23,7 +22,7 @@ func TestNewTable(t *testing.T) {
|
||||
func TestAddItem(t *testing.T) {
|
||||
assert := assert.New(t)
|
||||
key, value := 0, true
|
||||
table := cuckoo.New[int, bool]()
|
||||
table := cuckoo.NewTable[int, bool]()
|
||||
|
||||
err := table.Put(key, value)
|
||||
|
||||
@@ -35,7 +34,7 @@ func TestAddItem(t *testing.T) {
|
||||
func TestPutOverwrite(t *testing.T) {
|
||||
assert := assert.New(t)
|
||||
key, value, newValue := 0, 1, 2
|
||||
table := cuckoo.New[int, int]()
|
||||
table := cuckoo.NewTable[int, int]()
|
||||
(table.Put(key, value))
|
||||
|
||||
err := table.Put(key, newValue)
|
||||
@@ -50,7 +49,7 @@ func TestPutOverwrite(t *testing.T) {
|
||||
func TestSameHash(t *testing.T) {
|
||||
assert := assert.New(t)
|
||||
hash := func(int) uint64 { return 0 }
|
||||
table := cuckoo.NewCustom[int, bool](hash, hash, cuckoo.DefaultEqualFunc[int])
|
||||
table := cuckoo.NewCustomTable[int, bool](hash, hash, cuckoo.DefaultEqualFunc[int])
|
||||
|
||||
errA := table.Put(0, true)
|
||||
errB := table.Put(1, true)
|
||||
@@ -63,14 +62,14 @@ func TestSameHash(t *testing.T) {
|
||||
|
||||
func TestStartingCapacity(t *testing.T) {
|
||||
assert := assert.New(t)
|
||||
table := cuckoo.New[int, bool](cuckoo.Capacity(64))
|
||||
table := cuckoo.NewTable[int, bool](cuckoo.Capacity(64))
|
||||
|
||||
assert.Equal(uint64(128), table.TotalCapacity())
|
||||
}
|
||||
|
||||
func TestResizeCapacity(t *testing.T) {
|
||||
assert := assert.New(t)
|
||||
table := cuckoo.New[int, bool](
|
||||
table := cuckoo.NewTable[int, bool](
|
||||
cuckoo.Capacity(8),
|
||||
cuckoo.GrowthFactor(2),
|
||||
)
|
||||
@@ -85,7 +84,7 @@ func TestResizeCapacity(t *testing.T) {
|
||||
|
||||
func TestPutMany(t *testing.T) {
|
||||
assert := assert.New(t)
|
||||
expected, actual := map[int]bool{}, cuckoo.New[int, bool]()
|
||||
expected, actual := map[int]bool{}, cuckoo.NewTable[int, bool]()
|
||||
|
||||
for i := range 1_000 {
|
||||
expected[i] = true
|
||||
@@ -100,7 +99,7 @@ func TestPutMany(t *testing.T) {
|
||||
|
||||
func TestGetMany(t *testing.T) {
|
||||
assert := assert.New(t)
|
||||
table := cuckoo.New[int, bool]()
|
||||
table := cuckoo.NewTable[int, bool]()
|
||||
|
||||
for i := range 1_000 {
|
||||
err := table.Put(i, true)
|
||||
@@ -108,119 +107,37 @@ func TestGetMany(t *testing.T) {
|
||||
}
|
||||
|
||||
for i := range 2_000 {
|
||||
value, ok := table.Get(i)
|
||||
value, err := table.Get(i)
|
||||
if i < 1_000 {
|
||||
assert.True(ok)
|
||||
assert.NoError(err)
|
||||
assert.Equal(value, true)
|
||||
} else {
|
||||
assert.False(ok)
|
||||
assert.Error(err)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestDropExistingItem(t *testing.T) {
|
||||
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 TestDropItem(t *testing.T) {
|
||||
assert := assert.New(t)
|
||||
key, value := 0, true
|
||||
table := cuckoo.New[int, bool]()
|
||||
table := cuckoo.NewTable[int, bool]()
|
||||
(table.Put(key, value))
|
||||
|
||||
had := table.Drop(key)
|
||||
err := table.Drop(key)
|
||||
|
||||
assert.True(had)
|
||||
assert.NoError(err)
|
||||
assert.Equal(0, table.Size())
|
||||
assert.False(table.Has(key))
|
||||
}
|
||||
|
||||
func TestDropNoItem(t *testing.T) {
|
||||
assert := assert.New(t)
|
||||
key := 0
|
||||
table := cuckoo.New[int, bool]()
|
||||
|
||||
had := table.Drop(key)
|
||||
|
||||
assert.False(had)
|
||||
assert.Equal(0, table.Size())
|
||||
assert.False(table.Has(key))
|
||||
}
|
||||
|
||||
func TestDropItemCapacity(t *testing.T) {
|
||||
assert := assert.New(t)
|
||||
key := 0
|
||||
table := cuckoo.New[int, bool](
|
||||
cuckoo.Capacity(64),
|
||||
cuckoo.GrowthFactor(2),
|
||||
)
|
||||
|
||||
startingCapacity := table.TotalCapacity()
|
||||
table.Drop(key)
|
||||
endingCapacity := table.TotalCapacity()
|
||||
|
||||
assert.Equal(0, table.Size())
|
||||
assert.Equal(uint64(128), startingCapacity)
|
||||
assert.Equal(uint64(64), endingCapacity)
|
||||
}
|
||||
|
||||
func TestPutNoCapacity(t *testing.T) {
|
||||
assert := assert.New(t)
|
||||
key, value := 0, true
|
||||
table := cuckoo.New[int, bool](
|
||||
cuckoo.Capacity(0),
|
||||
)
|
||||
|
||||
err := table.Put(key, value)
|
||||
|
||||
assert.NoError(err)
|
||||
assert.Equal(1, table.Size())
|
||||
assert.True(table.Has(key))
|
||||
}
|
||||
|
||||
func TestBadHashCapacity(t *testing.T) {
|
||||
assert := assert.New(t)
|
||||
table := cuckoo.NewCustom[int, bool](
|
||||
func(int) uint64 { return 0 },
|
||||
func(int) uint64 { return 0 },
|
||||
func(a, b int) bool { return a == b },
|
||||
cuckoo.Capacity(20),
|
||||
)
|
||||
|
||||
err1 := table.Put(0, true)
|
||||
err2 := table.Put(1, true)
|
||||
err3 := table.Put(2, true)
|
||||
|
||||
assert.NoError(err1)
|
||||
assert.NoError(err2)
|
||||
assert.Error(err3)
|
||||
|
||||
assert.Equal(uint64(80), table.TotalCapacity())
|
||||
}
|
||||
|
||||
func TestDropResizeCapacity(t *testing.T) {
|
||||
assert := assert.New(t)
|
||||
table := cuckoo.New[int, bool](
|
||||
cuckoo.Capacity(10),
|
||||
)
|
||||
|
||||
err1 := table.Put(0, true)
|
||||
err2 := table.Put(1, true)
|
||||
table.Drop(1)
|
||||
|
||||
assert.NoError(errors.Join(err1, err2))
|
||||
assert.Equal(uint64(20), table.TotalCapacity())
|
||||
}
|
||||
|
||||
func TestNewTableBy(t *testing.T) {
|
||||
type User struct {
|
||||
_ func()
|
||||
id string
|
||||
name string
|
||||
}
|
||||
|
||||
assert := assert.New(t)
|
||||
table := cuckoo.NewBy[User, bool](func(u User) string { return u.id })
|
||||
|
||||
err := table.Put(User{nil, "1", "Robert"}, true)
|
||||
|
||||
assert.NoError(err)
|
||||
assert.Equal(1, table.Size())
|
||||
assert.True(table.Has(User{nil, "1", "Robbie"}))
|
||||
}
|
||||
|
||||
7
doc.go
7
doc.go
@@ -1,12 +1,9 @@
|
||||
// Package cuckoo provides a hash table that uses cuckoo hashing to achieve
|
||||
// a worst-case O(1) lookup time.
|
||||
//
|
||||
// While a [New] only supports comparable keys by default, you can create
|
||||
// a table with any key type using [NewCustom]. Custom [Hash] functions and
|
||||
// While a [NewTable] only supports comparable keys by default, you can create
|
||||
// a table with any key type using [NewCustomTable]. 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
|
||||
|
||||
@@ -8,25 +8,25 @@ import (
|
||||
)
|
||||
|
||||
func Example_basic() {
|
||||
table := cuckoo.New[int, string]()
|
||||
table := cuckoo.NewTable[int, string]()
|
||||
|
||||
if err := table.Put(1, "Hello, World!"); err != nil {
|
||||
fmt.Println("Put error:", err)
|
||||
}
|
||||
|
||||
if item, ok := table.Get(1); !ok {
|
||||
fmt.Println("Not Found 1!")
|
||||
if item, err := table.Get(1); err != nil {
|
||||
fmt.Println("Error:", err)
|
||||
} else {
|
||||
fmt.Println("Found 1:", item)
|
||||
}
|
||||
|
||||
if item, ok := table.Get(0); !ok {
|
||||
fmt.Println("Not Found 0!")
|
||||
if item, err := table.Get(0); err != nil {
|
||||
fmt.Println("Error:", err)
|
||||
} else {
|
||||
fmt.Println("Found 0:", item)
|
||||
}
|
||||
|
||||
// Output:
|
||||
// Found 1: Hello, World!
|
||||
// Not Found 0!
|
||||
// Error: key '0' not found
|
||||
}
|
||||
|
||||
3
go.mod
3
go.mod
@@ -4,11 +4,8 @@ go 1.25.6
|
||||
|
||||
require github.com/stretchr/testify v1.11.1
|
||||
|
||||
require github.com/kr/pretty v0.3.1 // indirect
|
||||
|
||||
require (
|
||||
github.com/davecgh/go-spew v1.1.1 // indirect
|
||||
github.com/pmezard/go-difflib v1.0.0 // indirect
|
||||
github.com/trailofbits/go-fuzz-utils v0.0.0-20260318143407-0907cafe7589
|
||||
gopkg.in/yaml.v3 v3.0.1 // indirect
|
||||
)
|
||||
|
||||
13
go.sum
13
go.sum
@@ -1,21 +1,10 @@
|
||||
github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
|
||||
github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
|
||||
github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
|
||||
github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
|
||||
github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
|
||||
github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
|
||||
github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
|
||||
github.com/pkg/diff v0.0.0-20210226163009-20ebb0f2a09e/go.mod h1:pJLUxLENpZxwdsKMEsNbx1VGcRFpLqf3715MtcvvzbA=
|
||||
github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
|
||||
github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
|
||||
github.com/rogpeppe/go-internal v1.9.0 h1:73kH8U+JUqXU8lRuOHeVHaa/SZPifC7BkcraZVejAe8=
|
||||
github.com/rogpeppe/go-internal v1.9.0/go.mod h1:WtVeX8xhTBvf0smdhujwtBcq4Qrzq/fJaraNFVN+nFs=
|
||||
github.com/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu7U=
|
||||
github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U=
|
||||
github.com/trailofbits/go-fuzz-utils v0.0.0-20260318143407-0907cafe7589 h1:UmBZCTPdDYore2IEHN+U4eIqEaRq6METh9pKiPumkqc=
|
||||
github.com/trailofbits/go-fuzz-utils v0.0.0-20260318143407-0907cafe7589/go.mod h1:zh+T+w9XT/3o4E0WLEGCdmLJ8Yqx/zY3o538tQY3OjY=
|
||||
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=
|
||||
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
|
||||
gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
|
||||
gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=
|
||||
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
|
||||
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
|
||||
|
||||
36
settings.go
36
settings.go
@@ -1,7 +1,5 @@
|
||||
package cuckoo
|
||||
|
||||
import "fmt"
|
||||
|
||||
// DefaultCapacity is the initial capacity of a [Table]. It is inspired from
|
||||
// Java's [HashMap] implementation, which also uses 16.
|
||||
//
|
||||
@@ -9,20 +7,14 @@ import "fmt"
|
||||
const DefaultCapacity uint64 = 16
|
||||
|
||||
// DefaultGrowthFactor is the standard resize multiplier for a [Table]. Most
|
||||
// implementations use 2.
|
||||
// hash table implementations use 2.
|
||||
const DefaultGrowthFactor uint64 = 2
|
||||
|
||||
// defaultMinimumLoad is the default lowest acceptable occupancy of a [Table].
|
||||
// The higher the minimum load, the more likely that a [Table.Put] will not
|
||||
// succeed. The value of 5% is taken from [libcuckoo].
|
||||
// DefaultMinimumLoad is the default lowest acceptable occupancy of a [Table].
|
||||
// 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
|
||||
|
||||
// defaultGrowthLimit is the maximum number of times a [Table] can grow in a
|
||||
// single [Table.Put], before the library infers it will lead to a stack
|
||||
// overflow. The value of '64' was chosen arbirarily.
|
||||
const defaultGrowthLimit uint64 = 64
|
||||
const DefaultMinimumLoad float64 = 0.05
|
||||
|
||||
type settings struct {
|
||||
growthFactor uint64
|
||||
@@ -31,25 +23,23 @@ type settings struct {
|
||||
}
|
||||
|
||||
// An Option modifies the settings of a [Table]. It is used in its constructors
|
||||
// like [New], for example.
|
||||
// like [NewTable], for example.
|
||||
type Option func(*settings)
|
||||
|
||||
// Capacity modifies the starting capacity of each subtable of the [Table]. The
|
||||
// value must be non-negative.
|
||||
// Capacity modifies the starting capacity of each bucket of the [Table]. The
|
||||
// value must be greater than 0.
|
||||
func Capacity(value int) Option {
|
||||
if value < 0 {
|
||||
panic(fmt.Sprintf("go-cuckoo: Capacity must be non-negative, got %d", value))
|
||||
}
|
||||
|
||||
return func(s *settings) { s.bucketSize = uint64(value) }
|
||||
}
|
||||
|
||||
// MinimumLoad modifies the [DefaultMinimumLoad] of the [Table]. The value must
|
||||
// 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) }
|
||||
}
|
||||
|
||||
107
subtable.go
107
subtable.go
@@ -1,107 +0,0 @@
|
||||
package cuckoo
|
||||
|
||||
// An entry is a key-value pair.
|
||||
type entry[K, V any] struct {
|
||||
key K
|
||||
value V
|
||||
}
|
||||
|
||||
type slot[K, V any] struct {
|
||||
entry[K, V]
|
||||
occupied bool
|
||||
}
|
||||
|
||||
type subtable[K, V any] struct {
|
||||
hash Hash[K]
|
||||
slots []slot[K, V]
|
||||
capacity, size uint64
|
||||
compare EqualFunc[K]
|
||||
}
|
||||
|
||||
// location determines where in the subtable a certain key would be placed. If
|
||||
// the capacity is 0, this will panic.
|
||||
func (t *subtable[K, V]) location(key K) uint64 {
|
||||
return t.hash(key) % t.capacity
|
||||
}
|
||||
|
||||
func (t *subtable[K, V]) get(key K) (value V, found bool) {
|
||||
if t.capacity == 0 {
|
||||
return
|
||||
}
|
||||
|
||||
slot := t.slots[t.location(key)]
|
||||
return slot.value, slot.occupied && t.compare(slot.key, key)
|
||||
}
|
||||
|
||||
func (t *subtable[K, V]) drop(key K) (occupied bool) {
|
||||
if t.capacity == 0 {
|
||||
return
|
||||
}
|
||||
|
||||
slot := &t.slots[t.location(key)]
|
||||
|
||||
if slot.occupied && t.compare(slot.key, key) {
|
||||
slot.occupied = false
|
||||
t.size--
|
||||
return true
|
||||
}
|
||||
|
||||
return false
|
||||
}
|
||||
|
||||
func (t *subtable[K, V]) resized(capacity uint64) *subtable[K, V] {
|
||||
return &subtable[K, V]{
|
||||
slots: make([]slot[K, V], capacity),
|
||||
capacity: capacity,
|
||||
hash: t.hash,
|
||||
compare: t.compare,
|
||||
}
|
||||
}
|
||||
|
||||
func (t *subtable[K, V]) update(key K, value V) (updated bool) {
|
||||
if t.capacity == 0 {
|
||||
return
|
||||
}
|
||||
|
||||
slot := &t.slots[t.location(key)]
|
||||
|
||||
if slot.occupied && t.compare(slot.key, key) {
|
||||
slot.value = value
|
||||
return true
|
||||
}
|
||||
|
||||
return false
|
||||
}
|
||||
|
||||
func (t *subtable[K, V]) insert(insertion entry[K, V]) (evicted entry[K, V], eviction bool) {
|
||||
if t.capacity == 0 {
|
||||
return insertion, true
|
||||
}
|
||||
|
||||
slot := &t.slots[t.location(insertion.key)]
|
||||
|
||||
if !slot.occupied {
|
||||
slot.entry = insertion
|
||||
slot.occupied = true
|
||||
t.size++
|
||||
return
|
||||
}
|
||||
|
||||
if t.compare(slot.key, insertion.key) {
|
||||
slot.value = insertion.value
|
||||
return
|
||||
}
|
||||
|
||||
insertion, slot.entry = slot.entry, insertion
|
||||
return insertion, true
|
||||
}
|
||||
|
||||
func newSubtable[K, V any](capacity uint64, hash Hash[K], compare EqualFunc[K]) *subtable[K, V] {
|
||||
return &subtable[K, V]{
|
||||
hash: hash,
|
||||
capacity: capacity,
|
||||
compare: compare,
|
||||
size: 0,
|
||||
slots: make([]slot[K, V], capacity),
|
||||
}
|
||||
}
|
||||
235
table.go
235
table.go
@@ -1,206 +1,131 @@
|
||||
package cuckoo
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"iter"
|
||||
"math/bits"
|
||||
"strings"
|
||||
)
|
||||
|
||||
// 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:
|
||||
//
|
||||
// 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].
|
||||
// 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].
|
||||
type Table[K, V any] struct {
|
||||
tableA, tableB *subtable[K, V]
|
||||
bucketA, bucketB bucket[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.tableA.capacity + t.tableB.capacity
|
||||
func (t Table[K, V]) TotalCapacity() uint64 {
|
||||
return t.bucketA.capacity + t.bucketB.capacity
|
||||
}
|
||||
|
||||
// Size returns how many slots are filled in the [Table].
|
||||
func (t *Table[K, V]) Size() int {
|
||||
return int(t.tableA.size + t.tableB.size)
|
||||
func (t Table[K, V]) Size() int {
|
||||
return int(t.bucketA.size + t.bucketB.size)
|
||||
}
|
||||
|
||||
func log2(n uint64) (m int) {
|
||||
return max(0, bits.Len64(n)-1)
|
||||
return 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 {
|
||||
// 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 {
|
||||
return 1.0
|
||||
}
|
||||
|
||||
func (t Table[K, V]) load() float64 {
|
||||
return float64(t.Size()) / float64(t.TotalCapacity())
|
||||
}
|
||||
|
||||
// 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
|
||||
}
|
||||
|
||||
if t.tableB.update(entry.key, entry.value) {
|
||||
return
|
||||
}
|
||||
|
||||
for range t.maxEvictions() {
|
||||
if entry, homeless = t.tableA.insert(entry); !homeless {
|
||||
return
|
||||
}
|
||||
|
||||
if entry, homeless = t.tableB.insert(entry); !homeless {
|
||||
return
|
||||
}
|
||||
}
|
||||
|
||||
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)
|
||||
|
||||
func (t *Table[K, V]) resize(capacity uint64) error {
|
||||
entries := make([]entry[K, V], 0, t.Size())
|
||||
for k, v := range t.Entries() {
|
||||
if _, failed := updated.insert(entry[K, V]{k, v}); failed {
|
||||
return false
|
||||
entries = append(entries, entry[K, V]{k, v})
|
||||
}
|
||||
|
||||
t.bucketA.resize(capacity)
|
||||
t.bucketB.resize(capacity)
|
||||
|
||||
for _, entry := range entries {
|
||||
if err := t.Put(entry.key, entry.value); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
|
||||
*t = *updated
|
||||
return true
|
||||
return nil
|
||||
}
|
||||
|
||||
// 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
|
||||
|
||||
if t.TotalCapacity() == 0 {
|
||||
newCapacity = 1
|
||||
} else {
|
||||
newCapacity = 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
|
||||
}
|
||||
|
||||
return t.resize(newCapacity)
|
||||
}
|
||||
|
||||
// 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.tableA.capacity / t.growthFactor)
|
||||
}
|
||||
|
||||
// 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
|
||||
}
|
||||
|
||||
// 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
|
||||
return value, fmt.Errorf("key '%v' not found", key)
|
||||
}
|
||||
|
||||
// Has returns true if a key has a value in the table.
|
||||
func (t *Table[K, V]) Has(key K) (exists bool) {
|
||||
_, exists = t.Get(key)
|
||||
return
|
||||
func (t Table[K, V]) Has(key K) (exists bool) {
|
||||
_, err := t.Get(key)
|
||||
return err == nil
|
||||
}
|
||||
|
||||
// Put sets the value for a key. If it cannot be set, an error is returned.
|
||||
// Put sets the value for a key. Returns error if its value cannot be set.
|
||||
func (t *Table[K, V]) Put(key K, value V) (err error) {
|
||||
var (
|
||||
entry = entry[K, V]{key, value}
|
||||
homeless bool
|
||||
)
|
||||
|
||||
for range defaultGrowthLimit {
|
||||
if entry, homeless = t.insert(entry); !homeless {
|
||||
return
|
||||
if t.bucketA.update(key, value) {
|
||||
return nil
|
||||
}
|
||||
|
||||
if t.bucketB.update(key, value) {
|
||||
return nil
|
||||
}
|
||||
|
||||
entry, eviction := entry[K, V]{key, value}, false
|
||||
for range t.maxEvictions() {
|
||||
if entry, eviction = t.bucketA.evict(entry); !eviction {
|
||||
return nil
|
||||
}
|
||||
|
||||
if entry, eviction = t.bucketB.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)
|
||||
return fmt.Errorf("bad hash: resize on load %d/%d = %f", t.Size(), t.TotalCapacity(), t.load())
|
||||
}
|
||||
|
||||
// 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 err := t.resize(t.growthFactor * t.bucketA.capacity); err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
return fmt.Errorf("could not place entry after %d resizes: %w", defaultGrowthLimit, ErrBadHash)
|
||||
return t.Put(entry.key, entry.value)
|
||||
}
|
||||
|
||||
// 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)
|
||||
// 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.bucketA.drop(key)
|
||||
t.bucketB.drop(key)
|
||||
|
||||
if t.load() < t.minLoadFactor {
|
||||
// The error is not handled here, because table-shrinking is an internal
|
||||
// optimization.
|
||||
t.shrink()
|
||||
return t.resize(t.bucketA.capacity / t.growthFactor)
|
||||
}
|
||||
|
||||
return occupied
|
||||
return nil
|
||||
}
|
||||
|
||||
// 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.tableA.slots {
|
||||
for _, slot := range t.bucketA.slots {
|
||||
if slot.occupied {
|
||||
if !yield(slot.key, slot.value) {
|
||||
return
|
||||
@@ -208,7 +133,7 @@ func (t *Table[K, V]) Entries() iter.Seq2[K, V] {
|
||||
}
|
||||
}
|
||||
|
||||
for _, slot := range t.tableB.slots {
|
||||
for _, slot := range t.bucketB.slots {
|
||||
if slot.occupied {
|
||||
if !yield(slot.key, slot.value) {
|
||||
return
|
||||
@@ -219,8 +144,8 @@ 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 k2:v2 ...]".
|
||||
func (t *Table[K, V]) String() string {
|
||||
// "table[k1:v1 h2:v2 ...]".
|
||||
func (t Table[K, V]) String() string {
|
||||
var sb strings.Builder
|
||||
sb.WriteString("table[")
|
||||
|
||||
@@ -238,13 +163,13 @@ func (t *Table[K, V]) String() string {
|
||||
return sb.String()
|
||||
}
|
||||
|
||||
// NewCustom creates a [Table] with custom [Hash] and [EqualFunc]
|
||||
// NewCustomTable creates a [Table] with custom [Hash] and [EqualFunc]
|
||||
// functions, along with any [Option] the user provides.
|
||||
func NewCustom[K, V any](hashA, hashB Hash[K], compare EqualFunc[K], options ...Option) *Table[K, V] {
|
||||
func NewCustomTable[K, V any](hashA, hashB Hash[K], compare EqualFunc[K], options ...Option) *Table[K, V] {
|
||||
settings := &settings{
|
||||
growthFactor: DefaultGrowthFactor,
|
||||
bucketSize: DefaultCapacity,
|
||||
minLoadFactor: defaultMinimumLoad,
|
||||
minLoadFactor: DefaultMinimumLoad,
|
||||
}
|
||||
|
||||
for _, option := range options {
|
||||
@@ -254,8 +179,8 @@ func NewCustom[K, V any](hashA, hashB Hash[K], compare EqualFunc[K], options ...
|
||||
return &Table[K, V]{
|
||||
growthFactor: settings.growthFactor,
|
||||
minLoadFactor: settings.minLoadFactor,
|
||||
tableA: newSubtable[K, V](settings.bucketSize, hashA, compare),
|
||||
tableB: newSubtable[K, V](settings.bucketSize, hashB, compare),
|
||||
bucketA: newBucket[K, V](settings.bucketSize, hashA, compare),
|
||||
bucketB: newBucket[K, V](settings.bucketSize, hashB, compare),
|
||||
}
|
||||
}
|
||||
|
||||
@@ -263,10 +188,10 @@ 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)) }
|
||||
}
|
||||
|
||||
// NewBy creates a [Table] for any key type by using keyFunc to derive a
|
||||
// NewTableBy 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 NewBy[K, V any, C comparable](keyFunc func(K) C, options ...Option) *Table[K, V] {
|
||||
return NewCustom[K, V](
|
||||
func NewTableBy[K, V any, C comparable](keyFunc func(K) C, options ...Option) *Table[K, V] {
|
||||
return NewCustomTable[K, V](
|
||||
pipe(keyFunc, NewDefaultHash[C]()),
|
||||
pipe(keyFunc, NewDefaultHash[C]()),
|
||||
func(a, b K) bool { return keyFunc(a) == keyFunc(b) },
|
||||
@@ -274,10 +199,10 @@ func NewBy[K, V any, C comparable](keyFunc func(K) C, options ...Option) *Table[
|
||||
)
|
||||
}
|
||||
|
||||
// New creates a [Table] using the default [Hash] and [EqualFunc]. Use
|
||||
// NewTable 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
|
||||
// [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...)
|
||||
// [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...)
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user