isComparable() fix for double describe()

core/generated-sources/src/main/kotlin/org/jetbrains/kotlinx/dataframe/api/DataColumnType.kt

@@ -2,10 +2,13 @@ package org.jetbrains.kotlinx.dataframe.api
 
 import org.jetbrains.kotlinx.dataframe.AnyCol
 import org.jetbrains.kotlinx.dataframe.columns.ColumnKind
+import org.jetbrains.kotlinx.dataframe.impl.isNothing
+import org.jetbrains.kotlinx.dataframe.impl.projectTo
 import org.jetbrains.kotlinx.dataframe.type
 import org.jetbrains.kotlinx.dataframe.typeClass
 import kotlin.reflect.KClass
 import kotlin.reflect.KType
+import kotlin.reflect.KTypeProjection
 import kotlin.reflect.full.isSubclassOf
 import kotlin.reflect.full.isSubtypeOf
 import kotlin.reflect.typeOf
@@ -16,7 +19,8 @@ public fun AnyCol.isFrameColumn(): Boolean = kind() == ColumnKind.Frame
 
 public fun AnyCol.isValueColumn(): Boolean = kind() == ColumnKind.Value
 
-public fun AnyCol.isSubtypeOf(type: KType): Boolean = this.type.isSubtypeOf(type) && (!this.type.isMarkedNullable || type.isMarkedNullable)
+public fun AnyCol.isSubtypeOf(type: KType): Boolean =
+    this.type.isSubtypeOf(type) && (!this.type.isMarkedNullable || type.isMarkedNullable)
 
 public inline fun <reified T> AnyCol.isSubtypeOf(): Boolean = isSubtypeOf(typeOf<T>())
 
@@ -26,9 +30,23 @@ public fun AnyCol.isNumber(): Boolean = isSubtypeOf<Number?>()
 
 public fun AnyCol.isList(): Boolean = typeClass == List::class
 
-public fun AnyCol.isComparable(): Boolean = isSubtypeOf<Comparable<*>?>()
+/**
+ * Returns `true` if [this] column is comparable, i.e. its type is a subtype of [Comparable] and its
+ * type argument is not [Nothing].
+ */
+public fun AnyCol.isComparable(): Boolean =
+    isSubtypeOf<Comparable<*>?>() &&
+        type().projectTo(Comparable::class).arguments[0].let {
+            it != KTypeProjection.STAR &&
+                it.type?.isNothing != true
+        }
 
 @PublishedApi
 internal fun AnyCol.isPrimitive(): Boolean = typeClass.isPrimitive()
 
-internal fun KClass<*>.isPrimitive(): Boolean = isSubclassOf(Number::class) || this == String::class || this == Char::class || this == Array::class || isSubclassOf(Collection::class)
+internal fun KClass<*>.isPrimitive(): Boolean =
+    isSubclassOf(Number::class) ||
+        this == String::class ||
+        this == Char::class ||
+        this == Array::class ||
+        isSubclassOf(Collection::class)

core/generated-sources/src/main/kotlin/org/jetbrains/kotlinx/dataframe/impl/TypeUtils.kt

@@ -12,7 +12,9 @@ import kotlin.reflect.KType
 import kotlin.reflect.KTypeParameter
 import kotlin.reflect.KTypeProjection
 import kotlin.reflect.KVariance
-import kotlin.reflect.KVariance.*
+import kotlin.reflect.KVariance.IN
+import kotlin.reflect.KVariance.INVARIANT
+import kotlin.reflect.KVariance.OUT
 import kotlin.reflect.KVisibility
 import kotlin.reflect.full.allSuperclasses
 import kotlin.reflect.full.createType
@@ -463,6 +465,9 @@ internal fun guessValueType(values: Sequence<Any?>, upperBound: KType? = null, l
     }
 }
 
+internal val KType.isNothing: Boolean
+    get() = classifier == Nothing::class
+
 internal fun nothingType(nullable: Boolean): KType =
     if (nullable) {
         typeOf<List<Nothing?>>()

core/generated-sources/src/test/kotlin/org/jetbrains/kotlinx/dataframe/testSets/person/DataFrameTests.kt

@@ -7,6 +7,7 @@ import io.kotest.matchers.shouldBe
 import io.kotest.matchers.shouldNotBe
 import org.jetbrains.kotlinx.dataframe.AnyFrame
 import org.jetbrains.kotlinx.dataframe.AnyRow
+import org.jetbrains.kotlinx.dataframe.DataColumn
 import org.jetbrains.kotlinx.dataframe.DataFrame
 import org.jetbrains.kotlinx.dataframe.DataRow
 import org.jetbrains.kotlinx.dataframe.RowExpression
@@ -79,6 +80,7 @@ import org.jetbrains.kotlinx.dataframe.api.intoColumns
 import org.jetbrains.kotlinx.dataframe.api.intoList
 import org.jetbrains.kotlinx.dataframe.api.intoRows
 import org.jetbrains.kotlinx.dataframe.api.isColumnGroup
+import org.jetbrains.kotlinx.dataframe.api.isComparable
 import org.jetbrains.kotlinx.dataframe.api.isEmpty
 import org.jetbrains.kotlinx.dataframe.api.isFrameColumn
 import org.jetbrains.kotlinx.dataframe.api.isNA
@@ -119,6 +121,7 @@ import org.jetbrains.kotlinx.dataframe.api.rename
 import org.jetbrains.kotlinx.dataframe.api.reorderColumnsByName
 import org.jetbrains.kotlinx.dataframe.api.replace
 import org.jetbrains.kotlinx.dataframe.api.rows
+import org.jetbrains.kotlinx.dataframe.api.schema
 import org.jetbrains.kotlinx.dataframe.api.select
 import org.jetbrains.kotlinx.dataframe.api.single
 import org.jetbrains.kotlinx.dataframe.api.sortBy
@@ -165,18 +168,22 @@ import org.jetbrains.kotlinx.dataframe.exceptions.ExcessiveColumnsException
 import org.jetbrains.kotlinx.dataframe.exceptions.TypeConversionException
 import org.jetbrains.kotlinx.dataframe.get
 import org.jetbrains.kotlinx.dataframe.hasNulls
+import org.jetbrains.kotlinx.dataframe.impl.DataFrameImpl
 import org.jetbrains.kotlinx.dataframe.impl.DataFrameSize
 import org.jetbrains.kotlinx.dataframe.impl.api.convertToImpl
 import org.jetbrains.kotlinx.dataframe.impl.between
 import org.jetbrains.kotlinx.dataframe.impl.columns.isMissingColumn
 import org.jetbrains.kotlinx.dataframe.impl.emptyPath
 import org.jetbrains.kotlinx.dataframe.impl.getColumnsImpl
+import org.jetbrains.kotlinx.dataframe.impl.isNothing
 import org.jetbrains.kotlinx.dataframe.impl.nothingType
+import org.jetbrains.kotlinx.dataframe.impl.projectTo
 import org.jetbrains.kotlinx.dataframe.impl.trackColumnAccess
 import org.jetbrains.kotlinx.dataframe.index
 import org.jetbrains.kotlinx.dataframe.io.renderValueForStdout
 import org.jetbrains.kotlinx.dataframe.kind
 import org.jetbrains.kotlinx.dataframe.math.mean
+import org.jetbrains.kotlinx.dataframe.name
 import org.jetbrains.kotlinx.dataframe.ncol
 import org.jetbrains.kotlinx.dataframe.nrow
 import org.jetbrains.kotlinx.dataframe.size
@@ -2358,6 +2365,47 @@ class DataFrameTests : BaseTest() {
         desc.print()
     }
 
+    @DataSchema
+    data class ComparableTest(
+        val int: Int,
+        val comparableInt: Comparable<Int>,
+        val string: String,
+        val comparableString: Comparable<String>,
+        val comparableStar: Comparable<*>,
+        val comparableNothing: Comparable<Nothing>,
+    )
+
+    @Test
+    fun `is comparable`() {
+        val df = listOf(
+            ComparableTest(1, 1, "a", "a", 1, 1),
+            ComparableTest(2, 2, "b", "b", "2", "2"),
+        ).toDataFrame()
+
+        df.int.isComparable() shouldBe true
+        df.comparableInt.isComparable() shouldBe true
+        df.string.isComparable() shouldBe true
+        df.comparableString.isComparable() shouldBe true
+        df.comparableStar.isComparable() shouldBe false
+        df.comparableNothing.isComparable() shouldBe false
+    }
+
+    @Test
+    fun `describe twice minimal`() {
+        val df = dataFrameOf("a", "b")(1, "foo", 3, "bar")
+        val desc1 = df.describe()
+        val desc2 = desc1.describe()
+        desc2::class shouldBe DataFrameImpl::class
+    }
+
+    @Test
+    fun `describe twice`() {
+        val df = typed.group { age and weight }.into("info").groupBy { city }.toDataFrame()
+        val desc1 = df.describe()
+        val desc2 = desc1.describe()
+        desc2::class shouldBe DataFrameImpl::class
+    }
+
     @Test
     fun `index by column accessor`() {
         val col = listOf(1, 2, 3, 4, 5).toColumn("name")

core/src/main/kotlin/org/jetbrains/kotlinx/dataframe/api/DataColumnType.kt

@@ -2,10 +2,13 @@ package org.jetbrains.kotlinx.dataframe.api
 
 import org.jetbrains.kotlinx.dataframe.AnyCol
 import org.jetbrains.kotlinx.dataframe.columns.ColumnKind
+import org.jetbrains.kotlinx.dataframe.impl.isNothing
+import org.jetbrains.kotlinx.dataframe.impl.projectTo
 import org.jetbrains.kotlinx.dataframe.type
 import org.jetbrains.kotlinx.dataframe.typeClass
 import kotlin.reflect.KClass
 import kotlin.reflect.KType
+import kotlin.reflect.KTypeProjection
 import kotlin.reflect.full.isSubclassOf
 import kotlin.reflect.full.isSubtypeOf
 import kotlin.reflect.typeOf
@@ -16,7 +19,8 @@ public fun AnyCol.isFrameColumn(): Boolean = kind() == ColumnKind.Frame
 
 public fun AnyCol.isValueColumn(): Boolean = kind() == ColumnKind.Value
 
-public fun AnyCol.isSubtypeOf(type: KType): Boolean = this.type.isSubtypeOf(type) && (!this.type.isMarkedNullable || type.isMarkedNullable)
+public fun AnyCol.isSubtypeOf(type: KType): Boolean =
+    this.type.isSubtypeOf(type) && (!this.type.isMarkedNullable || type.isMarkedNullable)
 
 public inline fun <reified T> AnyCol.isSubtypeOf(): Boolean = isSubtypeOf(typeOf<T>())
 
@@ -26,9 +30,23 @@ public fun AnyCol.isNumber(): Boolean = isSubtypeOf<Number?>()
 
 public fun AnyCol.isList(): Boolean = typeClass == List::class
 
-public fun AnyCol.isComparable(): Boolean = isSubtypeOf<Comparable<*>?>()
+/**
+ * Returns `true` if [this] column is comparable, i.e. its type is a subtype of [Comparable] and its
+ * type argument is not [Nothing].
+ */
+public fun AnyCol.isComparable(): Boolean =
+    isSubtypeOf<Comparable<*>?>() &&
+        type().projectTo(Comparable::class).arguments[0].let {
+            it != KTypeProjection.STAR &&
+                it.type?.isNothing != true
+        }
 
 @PublishedApi
 internal fun AnyCol.isPrimitive(): Boolean = typeClass.isPrimitive()
 
-internal fun KClass<*>.isPrimitive(): Boolean = isSubclassOf(Number::class) || this == String::class || this == Char::class || this == Array::class || isSubclassOf(Collection::class)
+internal fun KClass<*>.isPrimitive(): Boolean =
+    isSubclassOf(Number::class) ||
+        this == String::class ||
+        this == Char::class ||
+        this == Array::class ||
+        isSubclassOf(Collection::class)

core/src/main/kotlin/org/jetbrains/kotlinx/dataframe/impl/TypeUtils.kt

@@ -12,7 +12,9 @@ import kotlin.reflect.KType
 import kotlin.reflect.KTypeParameter
 import kotlin.reflect.KTypeProjection
 import kotlin.reflect.KVariance
-import kotlin.reflect.KVariance.*
+import kotlin.reflect.KVariance.IN
+import kotlin.reflect.KVariance.INVARIANT
+import kotlin.reflect.KVariance.OUT
 import kotlin.reflect.KVisibility
 import kotlin.reflect.full.allSuperclasses
 import kotlin.reflect.full.createType
@@ -463,6 +465,9 @@ internal fun guessValueType(values: Sequence<Any?>, upperBound: KType? = null, l
     }
 }
 
+internal val KType.isNothing: Boolean
+    get() = classifier == Nothing::class
+
 internal fun nothingType(nullable: Boolean): KType =
     if (nullable) {
         typeOf<List<Nothing?>>()

core/src/test/kotlin/org/jetbrains/kotlinx/dataframe/testSets/person/DataFrameTests.kt

@@ -7,6 +7,7 @@ import io.kotest.matchers.shouldBe
 import io.kotest.matchers.shouldNotBe
 import org.jetbrains.kotlinx.dataframe.AnyFrame
 import org.jetbrains.kotlinx.dataframe.AnyRow
+import org.jetbrains.kotlinx.dataframe.DataColumn
 import org.jetbrains.kotlinx.dataframe.DataFrame
 import org.jetbrains.kotlinx.dataframe.DataRow
 import org.jetbrains.kotlinx.dataframe.RowExpression
@@ -79,6 +80,7 @@ import org.jetbrains.kotlinx.dataframe.api.intoColumns
 import org.jetbrains.kotlinx.dataframe.api.intoList
 import org.jetbrains.kotlinx.dataframe.api.intoRows
 import org.jetbrains.kotlinx.dataframe.api.isColumnGroup
+import org.jetbrains.kotlinx.dataframe.api.isComparable
 import org.jetbrains.kotlinx.dataframe.api.isEmpty
 import org.jetbrains.kotlinx.dataframe.api.isFrameColumn
 import org.jetbrains.kotlinx.dataframe.api.isNA
@@ -119,6 +121,7 @@ import org.jetbrains.kotlinx.dataframe.api.rename
 import org.jetbrains.kotlinx.dataframe.api.reorderColumnsByName
 import org.jetbrains.kotlinx.dataframe.api.replace
 import org.jetbrains.kotlinx.dataframe.api.rows
+import org.jetbrains.kotlinx.dataframe.api.schema
 import org.jetbrains.kotlinx.dataframe.api.select
 import org.jetbrains.kotlinx.dataframe.api.single
 import org.jetbrains.kotlinx.dataframe.api.sortBy
@@ -165,18 +168,22 @@ import org.jetbrains.kotlinx.dataframe.exceptions.ExcessiveColumnsException
 import org.jetbrains.kotlinx.dataframe.exceptions.TypeConversionException
 import org.jetbrains.kotlinx.dataframe.get
 import org.jetbrains.kotlinx.dataframe.hasNulls
+import org.jetbrains.kotlinx.dataframe.impl.DataFrameImpl
 import org.jetbrains.kotlinx.dataframe.impl.DataFrameSize
 import org.jetbrains.kotlinx.dataframe.impl.api.convertToImpl
 import org.jetbrains.kotlinx.dataframe.impl.between
 import org.jetbrains.kotlinx.dataframe.impl.columns.isMissingColumn
 import org.jetbrains.kotlinx.dataframe.impl.emptyPath
 import org.jetbrains.kotlinx.dataframe.impl.getColumnsImpl
+import org.jetbrains.kotlinx.dataframe.impl.isNothing
 import org.jetbrains.kotlinx.dataframe.impl.nothingType
+import org.jetbrains.kotlinx.dataframe.impl.projectTo
 import org.jetbrains.kotlinx.dataframe.impl.trackColumnAccess
 import org.jetbrains.kotlinx.dataframe.index
 import org.jetbrains.kotlinx.dataframe.io.renderValueForStdout
 import org.jetbrains.kotlinx.dataframe.kind
 import org.jetbrains.kotlinx.dataframe.math.mean
+import org.jetbrains.kotlinx.dataframe.name
 import org.jetbrains.kotlinx.dataframe.ncol
 import org.jetbrains.kotlinx.dataframe.nrow
 import org.jetbrains.kotlinx.dataframe.size
@@ -2358,6 +2365,47 @@ class DataFrameTests : BaseTest() {
         desc.print()
     }
 
+    @DataSchema
+    data class ComparableTest(
+        val int: Int,
+        val comparableInt: Comparable<Int>,
+        val string: String,
+        val comparableString: Comparable<String>,
+        val comparableStar: Comparable<*>,
+        val comparableNothing: Comparable<Nothing>,
+    )
+
+    @Test
+    fun `is comparable`() {
+        val df = listOf(
+            ComparableTest(1, 1, "a", "a", 1, 1),
+            ComparableTest(2, 2, "b", "b", "2", "2"),
+        ).toDataFrame()
+
+        df.int.isComparable() shouldBe true
+        df.comparableInt.isComparable() shouldBe true
+        df.string.isComparable() shouldBe true
+        df.comparableString.isComparable() shouldBe true
+        df.comparableStar.isComparable() shouldBe false
+        df.comparableNothing.isComparable() shouldBe false
+    }
+
+    @Test
+    fun `describe twice minimal`() {
+        val df = dataFrameOf("a", "b")(1, "foo", 3, "bar")
+        val desc1 = df.describe()
+        val desc2 = desc1.describe()
+        desc2::class shouldBe DataFrameImpl::class
+    }
+
+    @Test
+    fun `describe twice`() {
+        val df = typed.group { age and weight }.into("info").groupBy { city }.toDataFrame()
+        val desc1 = df.describe()
+        val desc2 = desc1.describe()
+        desc2::class shouldBe DataFrameImpl::class
+    }
+
     @Test
     fun `index by column accessor`() {
         val col = listOf(1, 2, 3, 4, 5).toColumn("name")