Prototype new iteration of ImportDataSchema annotation

koperagen · koperagen · commit 9eacca5b458b · 2025-08-29T11:38:38.000+03:00
diff --git a/core/api/core.api b/core/api/core.api
@@ -227,6 +227,11 @@ public abstract interface annotation class org/jetbrains/kotlinx/dataframe/annot
 	public abstract fun isOpen ()Z
 }
 
+public abstract interface annotation class org/jetbrains/kotlinx/dataframe/annotations/DataSchemaSource : java/lang/annotation/Annotation {
+	public abstract fun qualifier ()Ljava/lang/String;
+	public abstract fun source ()Ljava/lang/String;
+}
+
 public final class org/jetbrains/kotlinx/dataframe/annotations/DataSchemaVisibility : java/lang/Enum {
 	public static final field EXPLICIT_PUBLIC Lorg/jetbrains/kotlinx/dataframe/annotations/DataSchemaVisibility;
 	public static final field IMPLICIT_PUBLIC Lorg/jetbrains/kotlinx/dataframe/annotations/DataSchemaVisibility;
@@ -6189,6 +6194,12 @@ public final class org/jetbrains/kotlinx/dataframe/io/DataFrameHtmlData$Companio
 	public static synthetic fun tableDefinitions$default (Lorg/jetbrains/kotlinx/dataframe/io/DataFrameHtmlData$Companion;ZZILjava/lang/Object;)Lorg/jetbrains/kotlinx/dataframe/io/DataFrameHtmlData;
 }
 
+public abstract interface class org/jetbrains/kotlinx/dataframe/io/DataFrameProvider {
+	public abstract fun default ()Lorg/jetbrains/kotlinx/dataframe/DataFrame;
+	public abstract fun getSchemaKType ()Lkotlin/reflect/KType;
+	public abstract fun read (Ljava/lang/String;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
+}
+
 public final class org/jetbrains/kotlinx/dataframe/io/DisplayConfiguration {
 	public static final field Companion Lorg/jetbrains/kotlinx/dataframe/io/DisplayConfiguration$Companion;
 	public synthetic fun <init> (Ljava/lang/Integer;Ljava/lang/Integer;ILkotlin/jvm/functions/Function3;Ljava/lang/String;ZZZZZILkotlin/jvm/internal/DefaultConstructorMarker;)V
@@ -6305,6 +6316,18 @@ public final class org/jetbrains/kotlinx/dataframe/io/RendererDecimalFormat$Comp
 	public final fun of-VVLz-gw (Ljava/lang/String;)Ljava/lang/String;
 }
 
+public abstract interface class org/jetbrains/kotlinx/dataframe/io/SchemaReader {
+	public static final field Companion Lorg/jetbrains/kotlinx/dataframe/io/SchemaReader$Companion;
+	public static final field DEFAULT_QUALIFIER Ljava/lang/String;
+	public fun accepts (Ljava/lang/String;Ljava/lang/String;)Z
+	public fun default (Ljava/lang/String;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
+	public abstract fun read (Ljava/lang/String;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
+}
+
+public final class org/jetbrains/kotlinx/dataframe/io/SchemaReader$Companion {
+	public static final field DEFAULT_QUALIFIER Ljava/lang/String;
+}
+
 public final class org/jetbrains/kotlinx/dataframe/io/StringKt {
 	public static final fun renderToString (Lorg/jetbrains/kotlinx/dataframe/DataFrame;IIZZZZZ)Ljava/lang/String;
 	public static synthetic fun renderToString$default (Lorg/jetbrains/kotlinx/dataframe/DataFrame;IIZZZZZILjava/lang/Object;)Ljava/lang/String;
diff --git a/core/src/main/kotlin/org/jetbrains/kotlinx/dataframe/annotations/ImportDataSchema.kt b/core/src/main/kotlin/org/jetbrains/kotlinx/dataframe/annotations/ImportDataSchema.kt
@@ -5,6 +5,7 @@ import org.jetbrains.kotlinx.dataframe.api.KeyValueProperty
 import org.jetbrains.kotlinx.dataframe.columns.ColumnGroup
 import org.jetbrains.kotlinx.dataframe.columns.FrameColumn
 import org.jetbrains.kotlinx.dataframe.documentation.UnifyingNumbers
+import org.jetbrains.kotlinx.dataframe.io.SchemaReader
 
 /**
  * Annotation preprocessing will generate a DataSchema interface from the data at `path`.
@@ -43,6 +44,9 @@ public annotation class ImportDataSchema(
     val enableExperimentalOpenApi: Boolean = false,
 )
 
+@Target(AnnotationTarget.CLASS)
+public annotation class DataSchemaSource(val source: String, val qualifier: String = SchemaReader.DEFAULT_QUALIFIER)
+
 public enum class DataSchemaVisibility {
     INTERNAL,
     IMPLICIT_PUBLIC,
diff --git a/core/src/main/kotlin/org/jetbrains/kotlinx/dataframe/io/guess.kt b/core/src/main/kotlin/org/jetbrains/kotlinx/dataframe/io/guess.kt
@@ -59,6 +59,36 @@ public interface SupportedDataFrameFormat : SupportedFormat {
     public fun readDataFrame(file: File, header: List<String> = emptyList()): DataFrame<*>
 }
 
+/**
+ * User-facing API implemented by a companion object of an imported schema [org.jetbrains.kotlinx.dataframe.annotations.DataSchemaSource]
+ * Intended use:
+ * 1. Interact with this API to read dataframe of a desired type
+ * 2. API is used to implement "generic dataframe reader" based on [schemaKType] and other available methods
+ */
+public interface DataFrameProvider<T> {
+    public val schemaKType: KType
+
+    public fun default(): DataFrame<T>
+
+    public fun read(path: String): DataFrame<T>
+}
+
+/**
+ * Handler of classes annotated with [org.jetbrains.kotlinx.dataframe.annotations.DataSchemaSource].
+ * Implementations must have a single zero-argument constructor
+ */
+public interface SchemaReader {
+    public companion object {
+        public const val DEFAULT_QUALIFIER: String = "default"
+    }
+
+    public fun accepts(path: String, qualifier: String): Boolean = qualifier == DEFAULT_QUALIFIER
+
+    public fun read(path: String): DataFrame<*>
+
+    public fun default(path: String): DataFrame<*> = read(path)
+}
+
 /**
  * Implement this interface to provide additional [DataSchema] interface generation formats for DataFrames (such as OpenAPI).
  * Note, this doesn't add functionality to [DataFrame.Companion.read], just [ImportDataSchema] and Gradle plugin.
diff --git a/dataframe-arrow/api/dataframe-arrow.api b/dataframe-arrow/api/dataframe-arrow.api
@@ -47,6 +47,13 @@ public final class org/jetbrains/kotlinx/dataframe/io/ArrowReadingKt {
 	public static synthetic fun toDataFrame$default (Lorg/apache/arrow/vector/ipc/ArrowReader;Lorg/jetbrains/kotlinx/dataframe/api/NullabilityOptions;ILjava/lang/Object;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
 }
 
+public final class org/jetbrains/kotlinx/dataframe/io/ArrowSchemaReader : org/jetbrains/kotlinx/dataframe/io/SchemaReader {
+	public fun <init> ()V
+	public fun accepts (Ljava/lang/String;Ljava/lang/String;)Z
+	public fun default (Ljava/lang/String;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
+	public fun read (Ljava/lang/String;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
+}
+
 public final class org/jetbrains/kotlinx/dataframe/io/ArrowTypesMatchingKt {
 	public static final fun toArrowField (Lorg/jetbrains/kotlinx/dataframe/DataColumn;Lkotlin/jvm/functions/Function1;)Lorg/apache/arrow/vector/types/pojo/Field;
 	public static synthetic fun toArrowField$default (Lorg/jetbrains/kotlinx/dataframe/DataColumn;Lkotlin/jvm/functions/Function1;ILjava/lang/Object;)Lorg/apache/arrow/vector/types/pojo/Field;
diff --git a/dataframe-arrow/src/main/kotlin/org/jetbrains/kotlinx/dataframe/io/arrowReading.kt b/dataframe-arrow/src/main/kotlin/org/jetbrains/kotlinx/dataframe/io/arrowReading.kt
@@ -36,6 +36,13 @@ public class ArrowFeather : SupportedDataFrameFormat {
         DefaultReadArrowMethod(pathRepresentation)
 }
 
+public class ArrowSchemaReader : SchemaReader {
+    override fun accepts(path: String, qualifier: String): Boolean =
+        super.accepts(path, qualifier) && path.endsWith(".feather")
+
+    override fun read(path: String): DataFrame<*> = DataFrame.readArrowFeather(path)
+}
+
 private const val READ_ARROW_FEATHER = "readArrowFeather"
 
 internal const val ARROW_PARQUET_DEFAULT_BATCH_SIZE = 32768L
diff --git a/dataframe-arrow/src/main/resources/META-INF/services/org.jetbrains.kotlinx.dataframe.io.SchemaReader b/dataframe-arrow/src/main/resources/META-INF/services/org.jetbrains.kotlinx.dataframe.io.SchemaReader
@@ -0,0 +1 @@
+org.jetbrains.kotlinx.dataframe.io.ArrowSchemaReader
diff --git a/dataframe-csv/api/dataframe-csv.api b/dataframe-csv/api/dataframe-csv.api
@@ -10,6 +10,13 @@ public final class org/jetbrains/kotlinx/dataframe/io/CsvDeephaven : org/jetbrai
 	public fun readDataFrame (Ljava/io/InputStream;Ljava/util/List;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
 }
 
+public final class org/jetbrains/kotlinx/dataframe/io/CsvSchemaReader : org/jetbrains/kotlinx/dataframe/io/SchemaReader {
+	public fun <init> ()V
+	public fun accepts (Ljava/lang/String;Ljava/lang/String;)Z
+	public fun default (Ljava/lang/String;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
+	public fun read (Ljava/lang/String;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
+}
+
 public final class org/jetbrains/kotlinx/dataframe/io/QuoteMode : java/lang/Enum {
 	public static final field ALL Lorg/jetbrains/kotlinx/dataframe/io/QuoteMode;
 	public static final field ALL_NON_NULL Lorg/jetbrains/kotlinx/dataframe/io/QuoteMode;
@@ -102,6 +109,13 @@ public final class org/jetbrains/kotlinx/dataframe/io/TsvDeephaven : org/jetbrai
 	public fun readDataFrame (Ljava/io/InputStream;Ljava/util/List;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
 }
 
+public final class org/jetbrains/kotlinx/dataframe/io/TsvSchemaReader : org/jetbrains/kotlinx/dataframe/io/SchemaReader {
+	public fun <init> ()V
+	public fun accepts (Ljava/lang/String;Ljava/lang/String;)Z
+	public fun default (Ljava/lang/String;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
+	public fun read (Ljava/lang/String;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
+}
+
 public final class org/jetbrains/kotlinx/dataframe/io/UtilKt {
 	public static final fun getDEFAULT_DELIM_NULL_STRINGS ()Ljava/util/Set;
 }
diff --git a/dataframe-csv/src/main/kotlin/org/jetbrains/kotlinx/dataframe/io/csv.kt b/dataframe-csv/src/main/kotlin/org/jetbrains/kotlinx/dataframe/io/csv.kt
@@ -29,6 +29,20 @@ public class CsvDeephaven(private val delimiter: Char = DelimParams.CSV_DELIMITE
     }
 }
 
+public class CsvSchemaReader : SchemaReader {
+    override fun accepts(path: String, qualifier: String): Boolean =
+        super.accepts(path, qualifier) && path.endsWith(".csv")
+
+    override fun read(path: String): DataFrame<*> = DataFrame.readCsv(path)
+}
+
+public class TsvSchemaReader : SchemaReader {
+    override fun accepts(path: String, qualifier: String): Boolean =
+        super.accepts(path, qualifier) && path.endsWith(".tsv")
+
+    override fun read(path: String): DataFrame<*> = DataFrame.readTsv(path)
+}
+
 private const val READ_CSV = "readCsv"
 
 internal class DefaultReadCsvMethod(path: String?, arguments: MethodArguments) :
diff --git a/dataframe-csv/src/main/resources/META-INF/services/org.jetbrains.kotlinx.dataframe.io.SchemaReader b/dataframe-csv/src/main/resources/META-INF/services/org.jetbrains.kotlinx.dataframe.io.SchemaReader
@@ -0,0 +1,2 @@
+org.jetbrains.kotlinx.dataframe.io.CsvSchemaReader
+org.jetbrains.kotlinx.dataframe.io.TsvSchemaReader
diff --git a/dataframe-excel/api/dataframe-excel.api b/dataframe-excel/api/dataframe-excel.api
@@ -8,6 +8,13 @@ public final class org/jetbrains/kotlinx/dataframe/io/Excel : org/jetbrains/kotl
 	public fun readDataFrame (Ljava/io/InputStream;Ljava/util/List;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
 }
 
+public final class org/jetbrains/kotlinx/dataframe/io/ExcelSchemaReader : org/jetbrains/kotlinx/dataframe/io/SchemaReader {
+	public fun <init> ()V
+	public fun accepts (Ljava/lang/String;Ljava/lang/String;)Z
+	public fun default (Ljava/lang/String;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
+	public fun read (Ljava/lang/String;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
+}
+
 public final class org/jetbrains/kotlinx/dataframe/io/FormattingOptions {
 	public fun <init> (Ljava/lang/String;Lorg/apache/poi/ss/usermodel/DataFormatter;)V
 	public synthetic fun <init> (Ljava/lang/String;Lorg/apache/poi/ss/usermodel/DataFormatter;ILkotlin/jvm/internal/DefaultConstructorMarker;)V
diff --git a/dataframe-excel/src/main/kotlin/org/jetbrains/kotlinx/dataframe/io/xlsx.kt b/dataframe-excel/src/main/kotlin/org/jetbrains/kotlinx/dataframe/io/xlsx.kt
@@ -59,6 +59,13 @@ public class Excel : SupportedDataFrameFormat {
         DefaultReadExcelMethod(pathRepresentation)
 }
 
+public class ExcelSchemaReader : SchemaReader {
+    override fun accepts(path: String, qualifier: String): Boolean =
+        super.accepts(path, qualifier) && path.endsWith(".xlsx") || path.endsWith(".xls")
+
+    override fun read(path: String): DataFrame<*> = DataFrame.readExcel(path)
+}
+
 private const val MESSAGE_REMOVE_1_1 = "Will be removed in 1.1."
 internal const val READ_EXCEL_OLD = "This function is only here for binary compatibility. $MESSAGE_REMOVE_1_1"
 
diff --git a/dataframe-excel/src/main/resources/META-INF/services/org.jetbrains.kotlinx.dataframe.io.SchemaReader b/dataframe-excel/src/main/resources/META-INF/services/org.jetbrains.kotlinx.dataframe.io.SchemaReader
@@ -0,0 +1 @@
+org.jetbrains.kotlinx.dataframe.io.ExcelSchemaReader
diff --git a/dataframe-jdbc/api/dataframe-jdbc.api b/dataframe-jdbc/api/dataframe-jdbc.api
@@ -1,3 +1,11 @@
+public abstract class org/jetbrains/kotlinx/dataframe/io/AbstractJdbcSchemaReader : org/jetbrains/kotlinx/dataframe/io/SchemaReader {
+	public fun <init> ()V
+	public fun accepts (Ljava/lang/String;Ljava/lang/String;)Z
+	public abstract fun config ()Lorg/jetbrains/kotlinx/dataframe/io/DbConnectionConfig;
+	public fun default (Ljava/lang/String;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
+	public fun read (Ljava/lang/String;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
+}
+
 public final class org/jetbrains/kotlinx/dataframe/io/DbConnectionConfig {
 	public fun <init> (Ljava/lang/String;Ljava/lang/String;Ljava/lang/String;Z)V
 	public synthetic fun <init> (Ljava/lang/String;Ljava/lang/String;Ljava/lang/String;ZILkotlin/jvm/internal/DefaultConstructorMarker;)V
diff --git a/dataframe-jdbc/src/main/kotlin/org/jetbrains/kotlinx/dataframe/io/Jdbc.kt b/dataframe-jdbc/src/main/kotlin/org/jetbrains/kotlinx/dataframe/io/Jdbc.kt
@@ -38,6 +38,14 @@ public class Jdbc :
         DefaultReadJdbcMethod(pathRepresentation)
 }
 
+public abstract class AbstractJdbcSchemaReader : SchemaReader {
+    override fun accepts(path: String, qualifier: String): Boolean = qualifier == "jdbc"
+
+    public abstract fun config(): DbConnectionConfig
+
+    override fun read(path: String): DataFrame<*> = config().readDataFrame(path)
+}
+
 private fun DataFrame.Companion.readJDBC(stream: File): DataFrame<*> {
     TODO("Not yet implemented")
 }
diff --git a/dataframe-json/api/dataframe-json.api b/dataframe-json/api/dataframe-json.api
@@ -80,3 +80,10 @@ public final class org/jetbrains/kotlinx/dataframe/io/JsonKt {
 	public static synthetic fun writeJson$default (Lorg/jetbrains/kotlinx/dataframe/DataRow;Ljava/lang/String;ZILjava/lang/Object;)V
 }
 
+public final class org/jetbrains/kotlinx/dataframe/io/JsonSchemaReader : org/jetbrains/kotlinx/dataframe/io/SchemaReader {
+	public fun <init> ()V
+	public fun accepts (Ljava/lang/String;Ljava/lang/String;)Z
+	public fun default (Ljava/lang/String;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
+	public fun read (Ljava/lang/String;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
+}
+
diff --git a/dataframe-json/src/main/kotlin/org/jetbrains/kotlinx/dataframe/io/json.kt b/dataframe-json/src/main/kotlin/org/jetbrains/kotlinx/dataframe/io/json.kt
@@ -127,6 +127,13 @@ public class JSON(
     }
 }
 
+public class JsonSchemaReader : SchemaReader {
+    override fun accepts(path: String, qualifier: String): Boolean =
+        qualifier == SchemaReader.DEFAULT_QUALIFIER && path.endsWith(".json")
+
+    override fun read(path: String): DataFrame<*> = DataFrame.readJson(path)
+}
+
 internal const val ARRAY_COLUMN_NAME: String = "array"
 internal const val VALUE_COLUMN_NAME: String = "value"
 
diff --git a/dataframe-json/src/main/resources/META-INF/services/org.jetbrains.kotlinx.dataframe.io.SchemaReader b/dataframe-json/src/main/resources/META-INF/services/org.jetbrains.kotlinx.dataframe.io.SchemaReader
@@ -0,0 +1 @@
+org.jetbrains.kotlinx.dataframe.io.JsonSchemaReader
diff --git a/plugins/symbol-processor/build.gradle.kts b/plugins/symbol-processor/build.gradle.kts
@@ -22,6 +22,7 @@ dependencies {
     implementation(projects.dataframe)
     // experimental
     implementation(projects.dataframeOpenapiGenerator)
+    implementation(libs.serialization.json)
 
     implementation(libs.ksp.api)
     implementation(libs.kotlin.reflect)
diff --git a/plugins/symbol-processor/src/main/kotlin/org/jetbrains/dataframe/ksp/DataFrameSymbolProcessor.kt b/plugins/symbol-processor/src/main/kotlin/org/jetbrains/dataframe/ksp/DataFrameSymbolProcessor.kt
@@ -1,32 +1,103 @@
 package org.jetbrains.dataframe.ksp
 
+import com.google.devtools.ksp.KspExperimental
+import com.google.devtools.ksp.getAnnotationsByType
+import com.google.devtools.ksp.processing.CodeGenerator
 import com.google.devtools.ksp.processing.KSPLogger
 import com.google.devtools.ksp.processing.Resolver
 import com.google.devtools.ksp.processing.SymbolProcessor
 import com.google.devtools.ksp.symbol.KSAnnotated
+import com.google.devtools.ksp.symbol.KSClassDeclaration
+import com.google.devtools.ksp.validate
+import kotlinx.serialization.json.JsonPrimitive
+import org.jetbrains.kotlinx.dataframe.annotations.DataSchemaSource
+import org.jetbrains.kotlinx.dataframe.api.schema
+import org.jetbrains.kotlinx.dataframe.io.SchemaReader
+import java.io.File
+import java.util.ServiceLoader
 
 class DataFrameSymbolProcessor(
-    private val codeGenerator: com.google.devtools.ksp.processing.CodeGenerator,
+    private val codeGenerator: CodeGenerator,
     private val logger: KSPLogger,
-    private val resolutionDir: String?,
+    private val configuration: DataFrameConfiguration,
 ) : SymbolProcessor {
 
+    @OptIn(KspExperimental::class)
     override fun process(resolver: Resolver): List<KSAnnotated> {
-        val extensionsGenerator = ExtensionsGenerator(resolver, codeGenerator, logger)
-        val (validDataSchemas, invalidDataSchemas) = extensionsGenerator.resolveDataSchemaDeclarations()
-        validDataSchemas.forEach {
-            val file = it.origin.containingFile ?: return@forEach
-            extensionsGenerator.generateExtensions(file, it.origin, it.properties)
+        if (!configuration.experimentalImportSchema) {
+            val extensionsGenerator = ExtensionsGenerator(resolver, codeGenerator, logger)
+            val (validDataSchemas, invalidDataSchemas) = extensionsGenerator.resolveDataSchemaDeclarations()
+            validDataSchemas.forEach {
+                val file = it.origin.containingFile ?: return@forEach
+                extensionsGenerator.generateExtensions(file, it.origin, it.properties)
+            }
+
+            val dataSchemaGenerator = DataSchemaGenerator(resolver, configuration.resolutionDir, logger, codeGenerator)
+            val importStatements = dataSchemaGenerator.resolveImportStatements()
+            importStatements.forEach { importStatement ->
+                dataSchemaGenerator.generateDataSchema(importStatement)
+            }
+            // by returning invalidDataSchemas we defer the processing of incomplete DataSchema declarations
+            // for example when DataSchema declaration references another one generated by @file:ImportDataSchema
+            return invalidDataSchemas
+        }
+
+        val serviceLoader = ServiceLoader.load(SchemaReader::class.java, SchemaReader::class.java.classLoader)
+        val providers = serviceLoader.toList()
+
+        if (configuration.debug) {
+            logger.warn("Service path: " + System.getProperty("java.class.path"))
+            logger.warn("Found providers: " + providers.joinToString())
+            logger.warn(
+                "Service URLs: " +
+                    SchemaReader::class.java.classLoader?.getResources(
+                        "META-INF/services/${SchemaReader::class.java.name}",
+                    )
+                        ?.toList()?.joinToString(),
+            )
         }
 
-        val dataSchemaGenerator = DataSchemaGenerator(resolver, resolutionDir, logger, codeGenerator)
-        val importStatements = dataSchemaGenerator.resolveImportStatements()
-        importStatements.forEach { importStatement ->
-            dataSchemaGenerator.generateDataSchema(importStatement)
+        if (configuration.importedSchemasOutput == null) {
+            logger.warn(
+                """
+                Provide KSP argument:
+                ksp {
+                  arg("$DATAFRAME_IMPORTED_SCHEMAS_OUTPUT", layout.projectDirectory.dir("src/schemas"))
+                }
+                """.trimIndent(),
+            )
+            return emptyList()
         }
 
-        // by returning invalidDataSchemas we defer the processing of incomplete DataSchema declarations
-        // for example when DataSchema declaration references another one generated by @file:ImportDataSchema
-        return invalidDataSchemas
+        val (validDeclarations, invalidDeclarations) = resolver
+            .getSymbolsWithAnnotation(DataSchemaSource::class.qualifiedName!!)
+            .filterIsInstance<KSClassDeclaration>()
+            .flatMap { classDeclaration ->
+                classDeclaration.getAnnotationsByType(DataSchemaSource::class).map { classDeclaration to it }
+            }
+            .partition { it.first.validate() }
+
+        validDeclarations
+            .forEach { (classDeclaration, annotation) ->
+                val reader = providers.firstOrNull { it.accepts(annotation.source, annotation.qualifier) }
+                if (reader != null) {
+                    val metadata = mapOf(
+                        "format" to JsonPrimitive(reader::class.qualifiedName!!),
+                        "data" to JsonPrimitive(annotation.source),
+                    )
+                    val df = reader.default(annotation.source)
+                    File(
+                        File(configuration.importedSchemasOutput),
+                        "${classDeclaration.simpleName.asString()}.json",
+                    ).writeText(df.schema().toJsonString(metadata = metadata))
+                } else {
+                    val availableReaders = providers.joinToString { it::class.qualifiedName!! }
+                    val message =
+                        "No reader found for ${classDeclaration.simpleName.asString()}. Available readers: $availableReaders"
+                    logger.warn(message)
+                }
+            }
+
+        return invalidDeclarations.map { it.first }
     }
 }
diff --git a/plugins/symbol-processor/src/main/kotlin/org/jetbrains/dataframe/ksp/DataFrameSymbolProcessorProvider.kt b/plugins/symbol-processor/src/main/kotlin/org/jetbrains/dataframe/ksp/DataFrameSymbolProcessorProvider.kt
diff --git a/plugins/symbol-processor/src/main/kotlin/org/jetbrains/dataframe/ksp/toJsonElement.kt b/plugins/symbol-processor/src/main/kotlin/org/jetbrains/dataframe/ksp/toJsonElement.kt
diff --git a/plugins/symbol-processor/src/test/kotlin/org/jetbrains/dataframe/ksp/ImportedSchemaSerializationTests.kt b/plugins/symbol-processor/src/test/kotlin/org/jetbrains/dataframe/ksp/ImportedSchemaSerializationTests.kt

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1 @@`
	`1`	`+org.jetbrains.kotlinx.dataframe.io.ArrowSchemaReader`
Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,2 @@`
	`1`	`+org.jetbrains.kotlinx.dataframe.io.CsvSchemaReader`
	`2`	`+org.jetbrains.kotlinx.dataframe.io.TsvSchemaReader`