hugo/helpers/emoji.go
Bjørn Erik Pedersen 9cd54cab20 Move the emoji parsing to pageparser
This avoids double parsing the page content when `enableEmoji=true`.

This commit also adds some general improvements to the parser, making it in general much faster:

```bash
benchmark                     old ns/op     new ns/op     delta
BenchmarkShortcodeLexer-4     90258         101730        +12.71%
BenchmarkParse-4              148940        15037         -89.90%

benchmark                     old allocs     new allocs     delta
BenchmarkShortcodeLexer-4     456            700            +53.51%
BenchmarkParse-4              28             33             +17.86%

benchmark                     old bytes     new bytes     delta
BenchmarkShortcodeLexer-4     69875         81014         +15.94%
BenchmarkParse-4              8128          8304          +2.17%
```

Running some site benchmarks with Emoji support turned on:

```bash
benchmark                                                                                     old ns/op     new ns/op     delta
BenchmarkSiteBuilding/TOML,num_langs=3,num_pages=5000,tags_per_page=5,shortcodes,render-4     924556797     818115620     -11.51%

benchmark                                                                                     old allocs     new allocs     delta
BenchmarkSiteBuilding/TOML,num_langs=3,num_pages=5000,tags_per_page=5,shortcodes,render-4     4112613        4133787        +0.51%

benchmark                                                                                     old bytes     new bytes     delta
BenchmarkSiteBuilding/TOML,num_langs=3,num_pages=5000,tags_per_page=5,shortcodes,render-4     426982864     424363832     -0.61%
```

Fixes #5534
2018-12-20 20:08:01 +01:00

97 lines
2.1 KiB
Go

// Copyright 2016 The Hugo Authors. All rights reserved.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
package helpers
import (
"bytes"
"sync"
"github.com/kyokomi/emoji"
)
var (
emojiInit sync.Once
emojis = make(map[string][]byte)
emojiDelim = []byte(":")
emojiWordDelim = []byte(" ")
emojiMaxSize int
)
// Emoji returns the emojy given a key, e.g. ":smile:", nil if not found.
func Emoji(key string) []byte {
emojiInit.Do(initEmoji)
return emojis[key]
}
// Emojify "emojifies" the input source.
// Note that the input byte slice will be modified if needed.
// See http://www.emoji-cheat-sheet.com/
func Emojify(source []byte) []byte {
emojiInit.Do(initEmoji)
start := 0
k := bytes.Index(source[start:], emojiDelim)
for k != -1 {
j := start + k
upper := j + emojiMaxSize
if upper > len(source) {
upper = len(source)
}
endEmoji := bytes.Index(source[j+1:upper], emojiDelim)
nextWordDelim := bytes.Index(source[j:upper], emojiWordDelim)
if endEmoji < 0 {
start++
} else if endEmoji == 0 || (nextWordDelim != -1 && nextWordDelim < endEmoji) {
start += endEmoji + 1
} else {
endKey := endEmoji + j + 2
emojiKey := source[j:endKey]
if emoji, ok := emojis[string(emojiKey)]; ok {
source = append(source[:j], append(emoji, source[endKey:]...)...)
}
start += endEmoji
}
if start >= len(source) {
break
}
k = bytes.Index(source[start:], emojiDelim)
}
return source
}
func initEmoji() {
emojiMap := emoji.CodeMap()
for k, v := range emojiMap {
emojis[k] = []byte(v)
if len(k) > emojiMaxSize {
emojiMaxSize = len(k)
}
}
}