build.gradle.kts

@@ -5,7 +5,7 @@ plugins {
 }
 
 group = "com.marvinelsen"
-version = "1.0.1"
+version = "2.0.0"
 
 repositories {
     mavenCentral()

src/main/kotlin/com/marvinelsen/cedict/api/CedictParser.kt

@@ -1,12 +1,12 @@
 package com.marvinelsen.cedict.api
 
-import com.marvinelsen.cedict.internal.CedictParserImpl
+import com.marvinelsen.cedict.internal.RegexCedictParser
 import java.io.InputStream
 
 interface CedictParser {
-    fun parseCedict(inputStream: InputStream): List<CedictEntry>
+    fun parseCedict(inputStream: InputStream): Sequence<CedictEntry>
 
     companion object {
-        val instance: CedictParser by lazy { CedictParserImpl() }
+        val instance: CedictParser by lazy { RegexCedictParser() }
     }
 }

src/main/kotlin/com/marvinelsen/cedict/internal/RegexCedictParser.kt

@@ -6,7 +6,7 @@ import com.marvinelsen.cedict.api.CedictParser
 import com.marvinelsen.chinese.transliteration.Syllable
 import java.io.InputStream
 
-internal class CedictParserImpl : CedictParser {
+internal class RegexCedictParser : CedictParser {
     companion object {
         private const val DEFINITION_SEPARATOR = '/'
         private const val GLOSS_SEPARATOR = ';'
@@ -20,11 +20,11 @@ internal class CedictParserImpl : CedictParser {
     }
 
     override fun parseCedict(inputStream: InputStream) =
-        inputStream.bufferedReader().useLines { lines ->
-            lines.filterNot(::isComment)
+        inputStream
+            .bufferedReader()
+            .lineSequence()
+            .filterNot(::isComment)
             .map(::toCedictEntry)
-                .toList()
-        }
 
     private fun isComment(line: String) = line[0] == COMMENT_MARKER
 
@@ -48,9 +48,5 @@ internal class CedictParserImpl : CedictParser {
 
     private fun toCedictDefinitions(definitions: String) = definitions
         .split(DEFINITION_SEPARATOR)
-        .map {
-            CedictDefinition(
-                glosses = it.split(GLOSS_SEPARATOR).map(String::trim)
-            )
-        }
+        .map { CedictDefinition(it.split(GLOSS_SEPARATOR).map(String::trim)) }
 }

src/test/kotlin/com/marvinelsen/cedict/internal/RegexCedictParserTest.kt

@@ -7,9 +7,9 @@ import io.kotest.core.spec.style.ShouldSpec
 import io.kotest.matchers.shouldBe
 import java.util.zip.GZIPInputStream
 
-class CedictParserImplTest : ShouldSpec({
+class RegexCedictParserTest : ShouldSpec({
     should("parse lines correctly") {
-        val cedictParser = CedictParserImpl()
+        val cedictParser = RegexCedictParser()
         val cedictEntry =
             cedictParser.toCedictEntry("皮實 皮实 [pi2 shi5] /(of things) durable/(of people) sturdy; tough/")
 
@@ -29,9 +29,12 @@ class CedictParserImplTest : ShouldSpec({
         val cedictFilePath = "/cedict_1_0_ts_utf-8_mdbg.txt.gz"
         val cedictFileStream = GZIPInputStream(javaClass.getResourceAsStream(cedictFilePath))
 
-        val cedictParser = CedictParserImpl()
+        val cedictParser = RegexCedictParser()
+
+        cedictFileStream.use {
             val cedictEntries = cedictParser.parseCedict(cedictFileStream)
 
-        cedictEntries.size shouldBe 122_508
+            cedictEntries.toList().size shouldBe 122_508
+        }
     }
 })