updating from master

Author: Jolanrensen

dataframe-csv/build.gradle.kts

@@ -138,8 +138,10 @@ tasks.withType<Jar> {
 }
 
 // modify all publishing tasks to depend on `changeJarTask` so the sources are swapped out with generated sources
-tasks.named { it.startsWith("publish") }.configureEach {
-    dependsOn(processKDocsMain, changeJarTask)
+tasks.configureEach {
+    if (name.startsWith("publish")) {
+        dependsOn(processKDocsMain, changeJarTask)
+    }
 }
 
 // Exclude the generated/processed sources from the IDE

dataframe-csv/src/main/kotlin/org/jetbrains/kotlinx/dataframe/impl/io/FastDoubleParser.kt

@@ -4,14 +4,20 @@ import io.deephaven.csv.containers.ByteSlice
 import io.deephaven.csv.tokenization.Tokenizer.CustomDoubleParser
 import org.jetbrains.kotlinx.dataframe.api.ParserOptions
 
+/**
+ * Wrapper around [DoubleParser] so we can use it from Deephaven.
+ */
 internal class FastDoubleParser(parserOptions: ParserOptions) : CustomDoubleParser {
 
     private val doubleParser = DoubleParser(parserOptions)
 
     override fun parse(bs: ByteSlice): Double {
         val array = ByteArray(bs.size())
-        bs.copyTo(array, 0)
-
+        try {
+            bs.copyTo(array, 0)
+        } catch (e: Exception) {
+            throw NumberFormatException("Failed to parse double")
+        }
         return doubleParser.parseOrNull(array)
             ?: throw NumberFormatException("Failed to parse double")
     }

dataframe-csv/src/test/kotlin/org/jetbrains/kotlinx/dataframe/io/DelimCsvTsvTests.kt

@@ -4,6 +4,7 @@ import io.kotest.assertions.throwables.shouldNotThrowAny
 import io.kotest.assertions.throwables.shouldThrow
 import io.kotest.matchers.nulls.shouldNotBeNull
 import io.kotest.matchers.shouldBe
+import jdk.nashorn.internal.ir.annotations.Ignore
 import kotlinx.datetime.LocalDate
 import kotlinx.datetime.LocalDateTime
 import org.intellij.lang.annotations.Language
@@ -551,6 +552,30 @@ class DelimCsvTsvTests {
         df["bodywt"].type() shouldBe typeOf<Double?>()
     }
 
+    @Ignore
+    @Test // TODO https://github.com/deephaven/deephaven-csv/issues/212
+    fun `multiple spaces as delimiter`() {
+        @Language("csv")
+        val csv =
+            """
+            NAME                     STATUS   AGE      LABELS
+            argo-events              Active   2y77d    app.kubernetes.io/instance=argo-events,kubernetes.io/metadata.name=argo-events
+            argo-workflows           Active   2y77d    app.kubernetes.io/instance=argo-workflows,kubernetes.io/metadata.name=argo-workflows
+            argocd                   Active   5y18d    kubernetes.io/metadata.name=argocd
+            beta                     Active   4y235d   kubernetes.io/metadata.name=beta
+            """.trimIndent()
+        val df = DataFrame.readCsvStr(
+            text = csv,
+            delimiter = ' ',
+            parserOptions = DEFAULT_PARSER_OPTIONS.copy(
+                nullStrings = DEFAULT_NULL_STRINGS - "",
+            ),
+            ignoreSurroundingSpaces = false,
+        )
+
+        df.print(borders = true, title = true)
+    }
+
     companion object {
         private val simpleCsv = testCsv("testCSV")
         private val simpleCsvZip = testResource("testCSV.zip")