ab85d4d678
- Refactorise the tests and add some - Use 250 signs instead of the whole text - Only check for Korean, Chinese and Japanese script - Add a benchmark - Use a more idiomatic control flow ```console $ # main branch $ go test -bench=. goos: linux goarch: amd64 pkg: miniflux.app/v2/internal/reader/readingtime BenchmarkEstimateReadingTime-12 267 4821268 ns/op PASS ok miniflux.app/v2/internal/reader/readingtime 1.754s $ # speed_up_reading_time branch $ go test -bench=. goos: linux goarch: amd64 pkg: miniflux.app/v2/internal/reader/readingtime cpu: 12th Gen Intel(R) Core(TM) i7-1265U BenchmarkEstimateReadingTime-12 1941 653312 ns/op PASS ok miniflux.app/v2/internal/reader/readingtime 1.342s $ ```
39 lines
1.3 KiB
Go
39 lines
1.3 KiB
Go
// SPDX-FileCopyrightText: Copyright The Miniflux Authors. All rights reserved.
|
|
// SPDX-License-Identifier: Apache-2.0
|
|
|
|
// Package readtime provides a function to estimate the reading time of an article.
|
|
package readingtime
|
|
|
|
import (
|
|
"math"
|
|
"strings"
|
|
"unicode/utf8"
|
|
|
|
"miniflux.app/v2/internal/reader/sanitizer"
|
|
|
|
"github.com/abadojack/whatlanggo"
|
|
)
|
|
|
|
// EstimateReadingTime returns the estimated reading time of an article in minute.
|
|
func EstimateReadingTime(content string, defaultReadingSpeed, cjkReadingSpeed int) int {
|
|
sanitizedContent := sanitizer.StripTags(content)
|
|
|
|
// Litterature on language detection says that around 100 signes is enough, we're safe here.
|
|
truncationPoint := int(math.Min(float64(len(sanitizedContent)), 250))
|
|
|
|
// We're only interested in identifying Japanse/Chinese/Korean
|
|
options := whatlanggo.Options{
|
|
Whitelist: map[whatlanggo.Lang]bool{
|
|
whatlanggo.Jpn: true,
|
|
whatlanggo.Cmn: true,
|
|
whatlanggo.Kor: true,
|
|
},
|
|
}
|
|
langInfo := whatlanggo.DetectWithOptions(sanitizedContent[:truncationPoint], options)
|
|
|
|
if langInfo.IsReliable() {
|
|
return int(math.Ceil(float64(utf8.RuneCountInString(sanitizedContent)) / float64(cjkReadingSpeed)))
|
|
}
|
|
nbOfWords := len(strings.Fields(sanitizedContent))
|
|
return int(math.Ceil(float64(nbOfWords) / float64(defaultReadingSpeed)))
|
|
}
|