core/org.jetbrains.kotlinx.dataframe.io

Package-level declarations

Types

internal interface CellContent

Column types that DataFrame can parse from a String.

internal data class ColumnDataForJs(val column: AnyCol, val nested: List<ColumnDataForJs>, val rightAlign: Boolean, val values: List<CellContent>, val headerStyle: String?)

Compression

fun interface Compression<I : InputStream>

Compression algorithm to use when reading files. We support GZIP and ZIP compression out of the box.

CSV

class ~~CSV~~(delimiter: Char = ',') : SupportedDataFrameFormat

CSVType

enum class ~~CSVType~~ : Enum<CSVType>

DataFrameFormatter

internal class DataFrameFormatter(val formattedClass: String, val nullClass: String, val structuralClass: String, val numberClass: String, val dataFrameClass: String)

DataFrameHtmlData

class DataFrameHtmlData(val style: String = "", val body: String = "", val script: String = "")

Container for HTML data, often containing a dataframe table.

DataFrameReference

internal data class DataFrameReference(val dfId: Int, val size: DataFrameSize) : CellContent

DisplayConfiguration

data class DisplayConfiguration(var rowsLimit: Int? = 20, var nestedRowsLimit: Int? = 5, var cellContentLimit: Int = 40, var cellFormatter: RowColFormatter<*, *>? = null, var headerFormatter: HeaderColFormatter<*>? = null, var decimalFormat: RendererDecimalFormat = RendererDecimalFormat.DEFAULT, var isolatedOutputs: Boolean = flagFromEnv("LETS_PLOT_HTML_ISOLATED_FRAME"), val localTesting: Boolean = flagFromEnv("KOTLIN_DATAFRAME_LOCAL_TESTING"), var useDarkColorScheme: Boolean = false, var enableFallbackStaticTables: Boolean = true, var downsizeBufferedImage: Boolean = true)

A collection of settings for rendering dataframes as HTML tables or native Kotlin Notebook table output.

GeneratedCode

internal data class GeneratedCode(val format: SupportedCodeGenerationFormat, val code: Code)

HtmlContent

internal data class HtmlContent(val html: String, val style: String?) : CellContent

MarkdownAlignment

enum class MarkdownAlignment : Enum<MarkdownAlignment>

MethodArguments

class MethodArguments

NameRepairStrategy

enum class ~~NameRepairStrategy~~ : Enum<NameRepairStrategy>

This strategy defines how the repeatable name column will be handled during the creation new dataframe from the IO sources.

PreparedTable

internal class PreparedTable(val header: List<String>, val types: List<String>?, val values: List<List<String>>, val rowsCount: Int, val totalRows: Int)

ReadAnyFrame

internal data class ReadAnyFrame(val format: SupportedDataFrameFormat, val df: AnyFrame)

RendererDecimalFormat

@JvmInline

value class RendererDecimalFormat

StringBorderStyle

interface StringBorderStyle

SupportedCodeGenerationFormat

interface SupportedCodeGenerationFormat : SupportedFormat

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.

SupportedDataFrameFormat

interface ~~SupportedDataFrameFormat~~ : SupportedFormat

Deprecated: As a result of Issue #450 and the removal of our old Gradle/KSP plugin and DataFrame.read(), the SupportedDataFrameFormat system is deprecated and will be removed in version 1.0.

SupportedFormat

sealed interface SupportedFormat

SupportedFormatSample

sealed interface SupportedFormatSample

TSV

class ~~TSV~~ : SupportedDataFrameFormat

Properties

DEFAULT_PRECISION

internal const val DEFAULT_PRECISION: Int = 6

formatter

internal val formatter: DataFrameFormatter

sessionId

internal var sessionId: Int

supportedFormats

internal val supportedFormats: List<SupportedFormat>

NOTE: Needs to have fully qualified name in resources/META-INF/services/org.jetbrains.kotlinx.dataframe.io.SupportedFormat to be detected here.

tableInSessionId

internal var tableInSessionId: Int

tooltipLimit

internal val tooltipLimit: Int = 1000

VALUE_TO_STRING_LIMIT_DEFAULT

internal const val VALUE_TO_STRING_LIMIT_DEFAULT: Int = 1000

VALUE_TO_STRING_LIMIT_FOR_ROW_AS_TABLE

internal const val VALUE_TO_STRING_LIMIT_FOR_ROW_AS_TABLE: Int = 50

Functions

asFileOrNull

fun asFileOrNull(url: URL): File?

asURL

fun ~~asURL~~(fileOrUrl: String): URL

asUrl

fun asUrl(fileOrUrl: String): URL

Converts a file path or URL String to a URL. If the path is a file path, the file is checked for existence and not being a directory.

catchHttpResponse

fun catchHttpResponse(url: URL, body: (InputStream) -> AnyFrame): AnyFrame

Opens a stream to url to create a DataFrame from it. If the URL is a file URL, the file is read directly. If the URL is an HTTP URL, it's also read directly, but if the server returns an error code, the error response is read and parsed as DataFrame too.

escapeForHtmlInJs

internal fun String.escapeForHtmlInJs(): String

escapeHTML

internal fun String.escapeHTML(): String

escapeNewLines

internal fun String.escapeNewLines(): String

format

internal fun BigDecimal.format(decimalFormat: RendererDecimalFormat): String

internal fun Double.format(decimalFormat: RendererDecimalFormat): String

internal fun Float.format(decimalFormat: RendererDecimalFormat): String

getResources

internal fun getResources(vararg resource: String): String

getResourceText

internal fun getResourceText(resource: String, vararg replacement: Pair<String, Any>): String

getVisibleValues

internal fun AnyRow.getVisibleValues(): List<Pair<String, Any?>>

guessFormat

internal fun guessFormat(url: URL, formats: List<SupportedFormat> = supportedFormats, sample: SupportedFormatSample.DataUrl? = SupportedFormatSample.DataUrl(url)): SupportedFormat?

internal fun guessFormat(path: Path, formats: List<SupportedFormat> = supportedFormats, sample: SupportedFormatSample.DataPath? = SupportedFormatSample.DataPath(path)): SupportedFormat?

internal fun guessFormat(path: String, formats: List<SupportedFormat> = supportedFormats, sample: SupportedFormatSample.PathString? = SupportedFormatSample.PathString(path)): SupportedFormat?

guessFormatForExtension

internal fun guessFormatForExtension(ext: String, formats: List<SupportedFormat> = supportedFormats, sample: SupportedFormatSample? = null): SupportedFormat?

isCompressed

internal fun ~~isCompressed~~(file: File): Boolean

internal fun ~~isCompressed~~(url: URL): Boolean

internal fun ~~isCompressed~~(fileOrUrl: String): Boolean

isFile

fun isFile(url: URL): Boolean

isProtocolSupported

fun isProtocolSupported(url: URL): Boolean

isURL

fun ~~isURL~~(path: String): Boolean

isUrl

fun isUrl(path: String): Boolean

maxDepth

internal fun AnyFrame.maxDepth(startingAt: Int = 0): Int

Returns the depth of the most-nested column in this df/group, starting at 0

maxWidth

internal fun BaseColumn<*>.maxWidth(): Int

Returns the max number of columns needed to display this column flattened

nextTableId

internal fun nextTableId(): Int

prepareTable

internal fun AnyFrame.prepareTable(rowsLimit: Int?, valueLimit: Int?, columnTypes: Boolean, rowIndex: Boolean, escapeValue: (String) -> String = { it }): PreparedTable

internal fun DataFrameHtmlData.print()

read

fun DataFrame.Companion.~~read~~(file: File, header: List<String> = emptyList()): AnyFrame

fun DataFrame.Companion.~~read~~(url: URL, header: List<String> = emptyList()): AnyFrame

fun DataFrame.Companion.~~read~~(path: Path, header: List<String> = emptyList()): AnyFrame

fun DataFrame.Companion.~~read~~(path: String, header: List<String> = emptyList()): AnyFrame

fun DataRow.Companion.~~read~~(file: File, header: List<String> = emptyList()): AnyRow

fun DataRow.Companion.~~read~~(url: URL, header: List<String> = emptyList()): AnyRow

fun DataRow.Companion.~~read~~(path: Path, header: List<String> = emptyList()): AnyRow

fun DataRow.Companion.~~read~~(path: String, header: List<String> = emptyList()): AnyRow

internal fun DataFrame.Companion.read(stream: InputStream, format: SupportedDataFrameFormat? = null, header: List<String> = emptyList(), formats: List<SupportedDataFrameFormat> = supportedFormats.filterIsInstance<SupportedDataFrameFormat>()): ReadAnyFrame

internal fun DataFrame.Companion.read(path: Path, format: SupportedDataFrameFormat? = null, header: List<String> = emptyList(), formats: List<SupportedDataFrameFormat> = supportedFormats.filterIsInstance<SupportedDataFrameFormat>()): ReadAnyFrame

fun DataFrame.Companion.~~read~~(fileOrUrl: String, delimiter: Char, header: List<String> = listOf(), colTypes: Map<String, ColType> = mapOf(), skipLines: Int = 0, readLines: Int? = null, duplicate: Boolean = true, charset: Charset = Charsets.UTF_8): DataFrame<*>

readCodeForGeneration

internal fun readCodeForGeneration(stream: InputStream, name: String, format: SupportedCodeGenerationFormat? = null, generateHelperCompanionObject: Boolean = false, formats: List<SupportedCodeGenerationFormat> = supportedFormats.filterIsInstance<SupportedCodeGenerationFormat>()): GeneratedCode

readCSV

fun DataFrame.Companion.~~readCSV~~(file: File, delimiter: Char = ',', header: List<String> = listOf(), colTypes: Map<String, ColType> = mapOf(), skipLines: Int = 0, readLines: Int? = null, duplicate: Boolean = true, charset: Charset = Charsets.UTF_8, parserOptions: ParserOptions? = null): DataFrame<*>

fun DataFrame.Companion.~~readCSV~~(url: URL, delimiter: Char = ',', header: List<String> = listOf(), colTypes: Map<String, ColType> = mapOf(), skipLines: Int = 0, readLines: Int? = null, duplicate: Boolean = true, charset: Charset = Charsets.UTF_8, parserOptions: ParserOptions? = null): DataFrame<*>

fun DataFrame.Companion.~~readCSV~~(fileOrUrl: String, delimiter: Char = ',', header: List<String> = listOf(), colTypes: Map<String, ColType> = mapOf(), skipLines: Int = 0, readLines: Int? = null, duplicate: Boolean = true, charset: Charset = Charsets.UTF_8, parserOptions: ParserOptions? = null): DataFrame<*>

fun DataFrame.Companion.~~readCSV~~(stream: InputStream, delimiter: Char = ',', header: List<String> = listOf(), isCompressed: Boolean = false, colTypes: Map<String, ColType> = mapOf(), skipLines: Int = 0, readLines: Int? = null, duplicate: Boolean = true, charset: Charset = Charsets.UTF_8, parserOptions: ParserOptions? = null): DataFrame<*>

readDataFrame

fun File.~~readDataFrame~~(header: List<String> = emptyList()): AnyFrame

fun URL.~~readDataFrame~~(header: List<String> = emptyList()): AnyFrame

fun Path.~~readDataFrame~~(header: List<String> = emptyList()): AnyFrame

readDataRow

fun File.~~readDataRow~~(header: List<String> = emptyList()): AnyRow

fun URL.~~readDataRow~~(header: List<String> = emptyList()): AnyRow

fun Path.~~readDataRow~~(header: List<String> = emptyList()): AnyRow

readDelim

fun DataFrame.Companion.~~readDelim~~(reader: Reader, format: CSVFormat = CSVFormat.DEFAULT.builder() .setHeader() .build(), colTypes: Map<String, ColType> = mapOf(), skipLines: Int = 0, readLines: Int? = null, parserOptions: ParserOptions? = null): AnyFrame

fun DataFrame.Companion.~~readDelim~~(inStream: InputStream, delimiter: Char = ',', header: List<String> = listOf(), isCompressed: Boolean = false, csvType: CSVType, colTypes: Map<String, ColType> = mapOf(), skipLines: Int = 0, readLines: Int? = null, duplicate: Boolean = true, charset: Charset = defaultCharset, parserOptions: ParserOptions? = null): AnyFrame

readTSV

fun DataFrame.Companion.~~readTSV~~(file: File, header: List<String> = listOf(), colTypes: Map<String, ColType> = mapOf(), skipLines: Int = 0, readLines: Int? = null, duplicate: Boolean = true, charset: Charset = Charsets.UTF_8): DataFrame<*>

fun DataFrame.Companion.~~readTSV~~(url: URL, header: List<String> = listOf(), colTypes: Map<String, ColType> = mapOf(), skipLines: Int = 0, readLines: Int? = null, duplicate: Boolean = true, charset: Charset = Charsets.UTF_8, parserOptions: ParserOptions? = null): DataFrame<*>

fun DataFrame.Companion.~~readTSV~~(fileOrUrl: String, header: List<String> = listOf(), colTypes: Map<String, ColType> = mapOf(), skipLines: Int = 0, readLines: Int? = null, duplicate: Boolean = true, charset: Charset = Charsets.UTF_8, parserOptions: ParserOptions? = null): DataFrame<*>

fun DataFrame.Companion.~~readTSV~~(stream: InputStream, header: List<String> = listOf(), isCompressed: Boolean = false, colTypes: Map<String, ColType> = mapOf(), skipLines: Int = 0, readLines: Int? = null, duplicate: Boolean = true, charset: Charset = Charsets.UTF_8, parserOptions: ParserOptions? = null): DataFrame<*>

renderCollectionName

internal fun renderCollectionName(value: Collection<*>): String?

renderHeader

internal fun ColumnDataForJs.renderHeader(): String

renderToMarkdown

fun AnyFrame.renderToMarkdown(rowsLimit: Int? = 20, valueLimit: Int? = 40, alignment: MarkdownAlignment = MarkdownAlignment.UNSPECIFIED, columnTypes: Boolean = false, title: Boolean = false, rowIndex: Boolean = true): String

renderToString

internal fun AnyRow.renderToString(decimalFormat: RendererDecimalFormat = RendererDecimalFormat.DEFAULT): String

fun AnyFrame.renderToString(rowsLimit: Int? = 20, valueLimit: Int? = 40, borders: Boolean = false, alignLeft: Boolean = false, columnTypes: Boolean = true, title: Boolean = false, rowIndex: Boolean = true, borderStyle: StringBorderStyle = StringBorderStyle.DottedLineWithRounderCorners): String

renderToStringTable

internal fun AnyRow.renderToStringTable(forHtml: Boolean = false): String

renderValueForHtml

internal fun renderValueForHtml(value: Any?, truncate: Int, format: RendererDecimalFormat): RenderedContent

renderValueForRowTable

internal fun renderValueForRowTable(value: Any?, forHtml: Boolean): RenderedContent

renderValueForStdout

internal fun renderValueForStdout(value: Any?, limit: Int = VALUE_TO_STRING_LIMIT_DEFAULT, decimalFormat: RendererDecimalFormat = RendererDecimalFormat.DEFAULT): RenderedContent

renderValueToString

internal fun renderValueToString(value: Any?, decimalFormat: RendererDecimalFormat): String

skippingBomCharacters

fun InputStream.skippingBomCharacters(): InputStream

Skips BOM characters if present.

tableJs

internal fun tableJs(columns: List<ColumnDataForJs>, id: Int, rootId: Int, nrow: Int): String

internal infix fun SupportedCodeGenerationFormat.to(code: Code): GeneratedCode

internal infix fun SupportedDataFrameFormat.to(df: AnyFrame): ReadAnyFrame

toCsv

fun AnyFrame.~~toCsv~~(format: CSVFormat = CSVFormat.DEFAULT): String

toDataFrame

fun <T> List<List<T>>.~~toDataFrame~~(containsColumns: Boolean = false): AnyFrame

toHTML

fun <T> DataFrame<T>.~~toHTML~~(configuration: DisplayConfiguration = DisplayConfiguration.DEFAULT, cellRenderer: CellRenderer = DefaultCellRenderer, getFooter: (DataFrame<T>) -> String? = { "DataFrame [${it.size}]" }): DataFrameHtmlData

toHtml

fun <T> DataFrame<T>.toHtml(configuration: DisplayConfiguration = DisplayConfiguration.DEFAULT, cellRenderer: CellRenderer = DefaultCellRenderer, getFooter: (DataFrame<T>) -> String? = { "DataFrame [${it.size}]" }): DataFrameHtmlData

Returns a DataFrameHtmlData without additional definitions. Can be rendered in Jupyter kernel (Kotlin Notebook) environments or other environments that already have CSS- and script definitions for DataFrame.

toHtmlData

internal fun AnyFrame.toHtmlData(defaultConfiguration: DisplayConfiguration = DisplayConfiguration.DEFAULT, cellRenderer: CellRenderer): DataFrameHtmlData

toKType

fun ColType.toKType(): KType

toStandaloneHTML

fun <T> DataFrame<T>.~~toStandaloneHTML~~(configuration: DisplayConfiguration = DisplayConfiguration.DEFAULT, cellRenderer: CellRenderer = DefaultCellRenderer, getFooter: (DataFrame<T>) -> String? = { "DataFrame [${it.size}]" }): DataFrameHtmlData

toStandaloneHtml

fun <T> DataFrame<T>.toStandaloneHtml(configuration: DisplayConfiguration = DisplayConfiguration.DEFAULT, cellRenderer: CellRenderer = DefaultCellRenderer, getFooter: (DataFrame<T>) -> String? = { "DataFrame [${it.size}]" }): DataFrameHtmlData

Returns a DataFrameHtmlData with CSS- and script definitions for DataFrame.

toStaticHtml

fun AnyFrame.toStaticHtml(configuration: DisplayConfiguration = DisplayConfiguration.DEFAULT, cellRenderer: CellRenderer = DefaultCellRenderer, includeCss: Boolean = true, openNestedDfs: Boolean = false): DataFrameHtmlData

Renders this DataFrame as static HTML (meaning no JS is used). CSS rendering is enabled by default but can be turned off using includeCss

toType

fun ColType.toType(): KClass<*>

urlAsFile

fun urlAsFile(url: URL): File

useDecompressed

inline fun <T, I : InputStream> InputStream.useDecompressed(compression: Compression<I>, block: (InputStream) -> T): T

Decompresses the input stream with the given compression algorithm.

writeCSV

fun AnyFrame.~~writeCSV~~(file: File, format: CSVFormat = CSVFormat.DEFAULT)

fun AnyFrame.~~writeCSV~~(writer: Appendable, format: CSVFormat = CSVFormat.DEFAULT)

fun AnyFrame.~~writeCSV~~(path: String, format: CSVFormat = CSVFormat.DEFAULT)