Initial commit.
This commit is contained in:
commit
6c22c168a7
19 changed files with 695 additions and 0 deletions
68
src/main/kotlin/net/thauvin/erik/readingtime/ReadingTime.kt
Normal file
68
src/main/kotlin/net/thauvin/erik/readingtime/ReadingTime.kt
Normal file
|
|
@ -0,0 +1,68 @@
|
|||
package net.thauvin.erik.readingtime
|
||||
|
||||
import org.jsoup.Jsoup
|
||||
import java.math.BigDecimal
|
||||
import java.math.RoundingMode
|
||||
|
||||
/**
|
||||
* Calculates the reading time of the given [text].
|
||||
*
|
||||
* Calculation based on this [Medium's Post](https://blog.medium.com/read-time-and-you-bc2048ab620c)
|
||||
*/
|
||||
class ReadingTime(
|
||||
var text: String,
|
||||
var wpm: Int = 275,
|
||||
var postfix: String = "min read",
|
||||
var plural: String = "min read",
|
||||
var excludeImages: Boolean = false
|
||||
) {
|
||||
companion object {
|
||||
@JvmStatic
|
||||
fun wordCount(words: String): Int {
|
||||
val s = Jsoup.parse(words).text().trim()
|
||||
return if (s.isEmpty()) 0 else s.split("\\s+".toRegex()).size
|
||||
}
|
||||
|
||||
@JvmStatic
|
||||
fun imgCount(html: String): Int {
|
||||
return "<img ".toRegex(RegexOption.IGNORE_CASE).findAll(html).count()
|
||||
}
|
||||
}
|
||||
|
||||
fun calcReadingTimeInSec(): Double {
|
||||
var readingTime = 0.0
|
||||
|
||||
if (!excludeImages)
|
||||
readingTime += calcImgReadingTime()
|
||||
|
||||
readingTime += wordCount(text) / (wpm / 60.0)
|
||||
|
||||
return readingTime
|
||||
}
|
||||
|
||||
fun calcReadingTime(): String {
|
||||
val readingTime = BigDecimal((calcReadingTimeInSec() / 60)).setScale(0, RoundingMode.CEILING)
|
||||
return if (readingTime.compareTo(BigDecimal.ONE) == 1) {
|
||||
"$readingTime $plural".trim()
|
||||
} else {
|
||||
"$readingTime $postfix".trim()
|
||||
}
|
||||
}
|
||||
|
||||
private fun calcImgReadingTime(): Int {
|
||||
var imgTime = 0
|
||||
val imgCount = imgCount(text)
|
||||
|
||||
var offset = 12
|
||||
for (i in 1..imgCount) {
|
||||
if (i > 10) {
|
||||
imgTime += 3
|
||||
} else {
|
||||
imgTime += offset
|
||||
offset--
|
||||
}
|
||||
}
|
||||
|
||||
return imgTime
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,52 @@
|
|||
package net.thauvin.erik.readingtime
|
||||
|
||||
import net.thauvin.erik.readingtime.ReadingTime.Companion.imgCount
|
||||
import net.thauvin.erik.readingtime.ReadingTime.Companion.wordCount
|
||||
import java.io.File
|
||||
import kotlin.test.Test
|
||||
import kotlin.test.assertEquals
|
||||
|
||||
class ReadingTimeTest {
|
||||
private val rt = ReadingTime("This is a <b>test</b>.\nWith an image: <img src=\"#\">")
|
||||
private val blogPost = File("src/test/resources/post.html").readText()
|
||||
private val mediumPost = File("src/test/resources/medium.html").readText()
|
||||
|
||||
@Test
|
||||
fun testWordCount() {
|
||||
assertEquals(0, wordCount(" "))
|
||||
assertEquals(3, wordCount("one two three"))
|
||||
assertEquals(2, wordCount(" one two "))
|
||||
assertEquals(7, wordCount(rt.text))
|
||||
assertEquals(210, wordCount(blogPost))
|
||||
}
|
||||
|
||||
@Test
|
||||
fun testImgCount() {
|
||||
assertEquals(1, imgCount(rt.text))
|
||||
assertEquals(4, imgCount(blogPost))
|
||||
assertEquals(3, imgCount(mediumPost))
|
||||
}
|
||||
|
||||
@Test
|
||||
fun testReadingTimeInSec() {
|
||||
assertEquals((wordCount(rt.text) / (rt.wpm / 60.0)) + 12.0, rt.calcReadingTimeInSec())
|
||||
rt.text = "<img src=\"#\"> <IMG src=\"#\">"
|
||||
assertEquals(12.0 + 11.0, rt.calcReadingTimeInSec())
|
||||
rt.text = blogPost
|
||||
assertEquals((wordCount(rt.text) / (rt.wpm / 60.0)) + 12.0 + 11.0 + 10.0 + 9.0, rt.calcReadingTimeInSec())
|
||||
rt.text = mediumPost
|
||||
rt.wpm = 300
|
||||
assertEquals(wordCount(rt.text) / (rt.wpm / 60.0) + 12.0 + 11.0 + 10.0, rt.calcReadingTimeInSec())
|
||||
}
|
||||
|
||||
@Test
|
||||
fun testReadingTime() {
|
||||
rt.text = blogPost
|
||||
assertEquals("2 min read", rt.calcReadingTime())
|
||||
rt.plural = "mins read"
|
||||
assertEquals("2 mins read", rt.calcReadingTime())
|
||||
rt.text = mediumPost
|
||||
rt.plural = ""
|
||||
assertEquals("2", rt.calcReadingTime())
|
||||
}
|
||||
}
|
||||
46
src/test/resources/medium.html
Normal file
46
src/test/resources/medium.html
Normal file
|
|
@ -0,0 +1,46 @@
|
|||
Eons ago, a couple of Medium engineers got fed up. They were sick of having to scroll all the way down the page to see how long a story was. It was wearing out their trackpad, it was making their fingers sore, and they figured there must be a better way. So they sat down and devised a simple formula, and the Medium read time was born.</p>
|
||||
<figure class="ij ik il im in io da db paragraph-image">
|
||||
<div class="ip iq ir is ai">
|
||||
<div class="da db ii">
|
||||
<div class="iy r ir iz">
|
||||
<div class="ja jb r">
|
||||
<div class="it iu s t u iv ai br iw ix"><img alt="Image for post" class="s t u iv ai jc jd je"
|
||||
src="https://miro.medium.com/max/60/1*wju0JzgNZVpPzZDgfchajg.png?q=20"
|
||||
width="180" height="58"/></div>
|
||||
<img alt="Image for post" class="it iu s t u iv ai jf" width="180" height="58"/>
|
||||
<noscript><img alt="Image for post" class="s t u iv ai"
|
||||
src="https://miro.medium.com/max/360/1*wju0JzgNZVpPzZDgfchajg.png" width="180"
|
||||
height="58"/></noscript>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</figure>
|
||||
<p id="8a5b" class="ht hu as hv b fa hw hx fd hy hz ia ib fi ic id fl ie if fo ig di ih">With the widespread
|
||||
adoption of this feature across the internet, we decided to shed some light on exactly what goes in to our read time
|
||||
calculation.</p>
|
||||
<blockquote class="jg"><p id="13d1" class="jh ji as eh b jj jk jl jm jn jo ig aw">Read time is based on the average
|
||||
reading speed of an adult (roughly 275 WPM). We take the total word count of a post and translate it into minutes.
|
||||
Then, we add 12 seconds for each inline image. <strong class="be">Boom, read time.</strong></p></blockquote>
|
||||
<p id="17fc" class="ht hu as hv b fa jp hx fd jq hz ia jr fi ic js fl ie jt fo ig di ih">Lately, we have seen more and
|
||||
more long form stories containing a ton of images. With our release of <a
|
||||
href="https://medium.com/the-story/introducing-image-grids-c592e5bc16d8" class="co he ju jv jw jx"
|
||||
target="_blank" rel="noopener">image grids</a>, we expect even more of these types of essays.</p>
|
||||
<p id="c072" class="ht hu as hv b fa hw hx fd hy hz ia ib fi ic id fl ie if fo ig di ih">Our original read time
|
||||
calculation was geared toward “slow” images, like comics, where you would really want to sit down and invest in the
|
||||
image. This resulted in articles with crazy big read times. For instance, this <a
|
||||
href="https://medium.com/@dahul/inside-medium-94931f66eebd" class="co he ju jv jw jx" target="_blank"
|
||||
rel="noopener">article</a> containing 140 images was clocking in at a whopping 87 minute read. So we amended
|
||||
our read time calculation to count 12 seconds for the first image, 11 for the second, and minus an additional second
|
||||
for each subsequent image. Any images after the tenth image are counted at three seconds.</p>
|
||||
<p id="fbc9" class="ht hu as hv b fa hw hx fd hy hz ia ib fi ic id fl ie if fo ig di ih">You might see this change
|
||||
reflected across the site. Keep in mind that our estimated read time is just that: <em class="jy">an estimation</em>.
|
||||
You might finish a story faster or slower depending on various factors such as how many children or cats you have,
|
||||
your caffeine/alcohol intake, or if you’re a time-traveler from the future and already read that story. We just want
|
||||
to give you a ballpark figure so you can decide whether you have time to read one more story before the bus comes,
|
||||
or if you should bookmark it for later.</p>
|
||||
<p id="369b" class="ht hu as hv b fa hw hx fd hy hz ia ib fi ic id fl ie if fo ig di ih">We aren’t done with read time
|
||||
yet. In the future, we’d like to tailor it to your reading speed, account for the <a
|
||||
href="https://medium.com/@fchimero/this-should-only-take-a-minute-or-four-probably-e38bb7bf2adf"
|
||||
class="co he ju jv jw jx" target="_blank" rel="noopener">complexity of an article</a>, and add support for
|
||||
other languages. We’ll be sure to let you know about these changes as they happen.</p>
|
||||
45
src/test/resources/post.html
Normal file
45
src/test/resources/post.html
Normal file
|
|
@ -0,0 +1,45 @@
|
|||
<h1>HTML Ipsum Presents</h1>
|
||||
|
||||
<p><strong>Pellentesque habitant morbi tristique</strong> senectus et netus et malesuada fames ac turpis egestas. Vestibulum tortor quam, feugiat vitae, ultricies eget, tempor sit amet, ante. Donec eu libero sit amet quam egestas semper. <em>Aenean ultricies mi vitae est.</em> Mauris placerat eleifend leo. Quisque sit amet est et sapien ullamcorper pharetra. Vestibulum erat wisi, condimentum sed, <code>commodo vitae</code>, ornare sit amet, wisi. Aenean fermentum, elit eget tincidunt condimentum, eros ipsum rutrum orci, sagittis tempus lacus enim ac dui. <a href="#">Donec non enim</a> in turpis pulvinar facilisis. Ut felis.</p>
|
||||
|
||||
<h2>Header Level 2</h2>
|
||||
|
||||
<ol>
|
||||
<li>Lorem ipsum dolor sit amet, consectetuer adipiscing elit.</li>
|
||||
<li>Aliquam tincidunt mauris eu risus.</li>
|
||||
<li><img src="#"></li>
|
||||
</ol>
|
||||
|
||||
<blockquote><p>Lorem ipsum dolor sit amet, consectetur adipiscing elit. Vivamus magna. Cras in mi at felis aliquet congue. Ut a est eget ligula molestie gravida. Curabitur massa. Donec eleifend, libero at sagittis mollis, tellus est malesuada tellus, at luctus turpis elit sit amet quam. Vivamus pretium ornare est.</p></blockquote>
|
||||
|
||||
<h3>Header Level 3</h3>
|
||||
|
||||
<ul>
|
||||
<li>Lorem ipsum dolor sit amet, consectetuer adipiscing elit.</li>
|
||||
<li>Aliquam tincidunt mauris eu risus.</li>
|
||||
<li><img src="#"></li>
|
||||
</ul>
|
||||
|
||||
<h3>Header Level 4</h3>
|
||||
|
||||
<ul>
|
||||
<li>Lorem ipsum dolor sit amet, consectetuer adipiscing elit.</li>
|
||||
<li>Aliquam tincidunt mauris eu risus.</li>
|
||||
<li><img src="#"></li>
|
||||
</ul>
|
||||
|
||||
<h3>Header Level 5</h3>
|
||||
|
||||
<ul>
|
||||
<li>Lorem ipsum dolor sit amet, consectetuer adipiscing elit.</li>
|
||||
<li>Aliquam tincidunt mauris eu risus.</li>
|
||||
<li><img src="#"></li>
|
||||
</ul>
|
||||
|
||||
<pre><code>
|
||||
#header h1 a {
|
||||
display: block;
|
||||
width: 300px;
|
||||
height: 80px;
|
||||
}
|
||||
</code></pre>
|
||||
Loading…
Add table
Add a link
Reference in a new issue