mirror of
https://github.com/go-gitea/gitea.git
synced 2026-07-23 17:32:39 +00:00
ee10ae168c
This pull request optimizes `FindEmojiSubmatchIndex` in Gitea's emoji package (`modules/emoji/emoji.go`) by replacing the `strings.Replacer`-based search with a slice-based trie and a constant-time starting-byte check (`isStartingByte`). The new implementation avoids heap allocations during the search and reduces CPU overhead when rendering Markdown, particularly for plain text that does not contain emojis. ### Verification Verified with unit tests: ```sh go test -count=1 ./modules/emoji/... ``` Benchmarks: ```sh go test -bench=. -benchmem ./modules/emoji/... ``` ### Results | Benchmark | Before | After | | ---------- | ------ | ----- | | `BenchmarkFindEmojiSubmatchIndex` | 168.3 ns/op, 2 allocs/op | 85.78 ns/op, 1 alloc/op | | `BenchmarkFindEmojiSubmatchIndexNoMatch` | 239.8 ns/op, 1 alloc/op | 105.1 ns/op, 0 allocs/op | ### Benchmark Output ```text goos: linux goarch: amd64 pkg: gitea.dev/modules/emoji cpu: Intel(R) Core(TM) i5-7400 CPU @ 3.00GHz BenchmarkFindEmojiSubmatchIndex-4 13498539 85.78 ns/op 16 B/op 1 allocs/op BenchmarkFindEmojiSubmatchIndexNoMatch-4 11220450 105.1 ns/op 0 B/op 0 allocs/op BenchmarkFindEmojiSubmatchIndexOld-4 6569360 168.3 ns/op 48 B/op 2 allocs/op BenchmarkFindEmojiSubmatchIndexOldNoMatch-4 5026116 239.8 ns/op 32 B/op 1 allocs/op ``` --------- Signed-off-by: Sudhanshu Singh <sudhanshuwriterblc@gmail.com> Co-authored-by: silverwind <me@silverwind.io> Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
57 lines
1.2 KiB
Go
57 lines
1.2 KiB
Go
// Copyright 2026 The Gitea Authors. All rights reserved.
|
|
// SPDX-License-Identifier: MIT
|
|
|
|
package util
|
|
|
|
type trieEdge struct {
|
|
b byte
|
|
node *TrieNode
|
|
}
|
|
|
|
// TrieNode represents a node in a slice-based Trie for fast byte-sequence prefix matching.
|
|
type TrieNode struct {
|
|
children []trieEdge
|
|
isEnd bool
|
|
}
|
|
|
|
func (t *TrieNode) child(b byte) *TrieNode {
|
|
for _, edge := range t.children {
|
|
if edge.b == b {
|
|
return edge.node
|
|
}
|
|
}
|
|
return nil
|
|
}
|
|
|
|
// Insert adds a string (byte sequence) to the Trie.
|
|
func (t *TrieNode) Insert(val string) {
|
|
curr := t
|
|
for i := 0; i < len(val); i++ {
|
|
next := curr.child(val[i])
|
|
if next == nil {
|
|
next = &TrieNode{}
|
|
curr.children = append(curr.children, trieEdge{b: val[i], node: next})
|
|
}
|
|
curr = next
|
|
}
|
|
curr.isEnd = true
|
|
}
|
|
|
|
// Match returns the length of the longest matching prefix starting at index `start` in string `s`.
|
|
// It returns -1 if no prefix is matched.
|
|
func (t *TrieNode) Match(s string, start int) int {
|
|
curr := t
|
|
matchLen := -1
|
|
for j := start; j < len(s); j++ {
|
|
next := curr.child(s[j])
|
|
if next == nil {
|
|
break
|
|
}
|
|
curr = next
|
|
if curr.isEnd {
|
|
matchLen = j - start + 1
|
|
}
|
|
}
|
|
return matchLen
|
|
}
|