Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Change Ngram to value class to reduce memory indirection #126

Closed
wants to merge 2 commits into from
Closed

Change Ngram to value class to reduce memory indirection #126

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9c5e8b5
Use "merge" in incrementCounter to reduce map lookup
fvasco Apr 1, 2022
dff1c84
Change Ngram to value class to reduce memory indirection
fvasco Apr 1, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 7 additions & 12 deletions src/main/kotlin/com/github/pemistahl/lingua/internal/Ngram.kt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,8 +23,9 @@ import kotlinx.serialization.descriptors.PrimitiveSerialDescriptor
import kotlinx.serialization.encoding.Decoder
import kotlinx.serialization.encoding.Encoder

@JvmInline
@Serializable(with = NgramSerializer::class)
internal data class Ngram(val value: String) : Comparable<Ngram> {
internal value class Ngram(val value: String) : Comparable<Ngram> {
init {
require(value.length in 0..5) {
"length of ngram '$value' is not in range 0..5"
Expand All @@ -33,20 +34,14 @@ internal data class Ngram(val value: String) : Comparable<Ngram> {

override fun toString() = value

override fun compareTo(other: Ngram) = when {
this.value.length > other.value.length -> 1
this.value.length < other.value.length -> -1
else -> 0
}
override fun compareTo(other: Ngram) = value.length.compareTo(other.value.length)

fun rangeOfLowerOrderNgrams() = NgramRange(this, Ngram(this.value[0].toString()))

operator fun dec(): Ngram = when {
this.value.length > 1 -> Ngram(this.value.substring(0, this.value.length - 1))
this.value.length == 1 -> Ngram("")
else -> throw IllegalStateException(
"Zerogram is ngram type of lowest order and can not be decremented"
)
operator fun dec(): Ngram = when(value.length) {
0 -> error("Zerogram is ngram type of lowest order and can not be decremented")
1 -> Ngram("")
else -> Ngram(this.value.substring(0, this.value.length - 1))
}

companion object {
Expand Down
4 changes: 1 addition & 3 deletions src/main/kotlin/com/github/pemistahl/lingua/internal/util/extension/MapExtensions.kt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,4 @@

package com.github.pemistahl.lingua.internal.util.extension

internal fun <T> MutableMap<T, Int>.incrementCounter(key: T) {
this[key] = this.getOrDefault(key, 0) + 1
}
internal fun <T> MutableMap<T, Int>.incrementCounter(key: T) = this.merge(key, 1, Int::plus)
22 changes: 11 additions & 11 deletions src/test/kotlin/com/github/pemistahl/lingua/api/LanguageDetectorTest.kt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -212,17 +212,17 @@ class LanguageDetectorTest {
// ngram probability lookup

private fun ngramProbabilityProvider() = listOf(
arguments(ENGLISH, Ngram("a"), 0.01),
arguments(ENGLISH, Ngram("lt"), 0.12),
arguments(ENGLISH, Ngram("ter"), 0.21),
arguments(ENGLISH, Ngram("alte"), 0.25),
arguments(ENGLISH, Ngram("alter"), 0.29),

arguments(GERMAN, Ngram("t"), 0.08),
arguments(GERMAN, Ngram("er"), 0.18),
arguments(GERMAN, Ngram("alt"), 0.22),
arguments(GERMAN, Ngram("lter"), 0.28),
arguments(GERMAN, Ngram("alter"), 0.30)
arguments(ENGLISH, "a", 0.01),
arguments(ENGLISH, "lt", 0.12),
arguments(ENGLISH, "ter", 0.21),
arguments(ENGLISH, "alte", 0.25),
arguments(ENGLISH, "alter", 0.29),

arguments(GERMAN, "t", 0.08),
arguments(GERMAN, "er", 0.18),
arguments(GERMAN, "alt", 0.22),
arguments(GERMAN, "lter", 0.28),
arguments(GERMAN, "alter", 0.30)
)

@ParameterizedTest
Expand Down