Skip to content

add nulls parse option in readExcel #1247

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

add nulls parse option in readExcel #1247

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7a0a377
add nulls parse option in readExcel
AndreiKingsley Jun 11, 2025
c9f4177
readExcel fixes
AndreiKingsley Jun 12, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 12 additions & 12 deletions dataframe-excel/api/dataframe-excel.api
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,13 +39,13 @@ public final class org/jetbrains/kotlinx/dataframe/io/WorkBookType : java/lang/E

public final class org/jetbrains/kotlinx/dataframe/io/XlsxKt {
public static final synthetic fun readExcel (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Lorg/apache/poi/ss/usermodel/Sheet;Ljava/lang/String;Lorg/jetbrains/kotlinx/dataframe/io/FormattingOptions;ILjava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static final fun readExcel (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Lorg/apache/poi/ss/usermodel/Sheet;Ljava/lang/String;Lorg/jetbrains/kotlinx/dataframe/io/FormattingOptions;ILjava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;Z)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static final fun readExcel (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Lorg/apache/poi/ss/usermodel/Sheet;Ljava/lang/String;Lorg/jetbrains/kotlinx/dataframe/io/FormattingOptions;ILjava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;ZZ)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static final synthetic fun readExcel (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Lorg/apache/poi/ss/usermodel/Workbook;Ljava/lang/String;ILjava/lang/String;Lorg/jetbrains/kotlinx/dataframe/io/FormattingOptions;Ljava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static final fun readExcel (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Lorg/apache/poi/ss/usermodel/Workbook;Ljava/lang/String;ILjava/lang/String;Lorg/jetbrains/kotlinx/dataframe/io/FormattingOptions;Ljava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;Z)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static final fun readExcel (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Lorg/apache/poi/ss/usermodel/Workbook;Ljava/lang/String;ILjava/lang/String;Lorg/jetbrains/kotlinx/dataframe/io/FormattingOptions;Ljava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;ZZ)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static synthetic fun readExcel$default (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Lorg/apache/poi/ss/usermodel/Sheet;Ljava/lang/String;Lorg/jetbrains/kotlinx/dataframe/io/FormattingOptions;ILjava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;ILjava/lang/Object;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static synthetic fun readExcel$default (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Lorg/apache/poi/ss/usermodel/Sheet;Ljava/lang/String;Lorg/jetbrains/kotlinx/dataframe/io/FormattingOptions;ILjava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;ZILjava/lang/Object;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static synthetic fun readExcel$default (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Lorg/apache/poi/ss/usermodel/Sheet;Ljava/lang/String;Lorg/jetbrains/kotlinx/dataframe/io/FormattingOptions;ILjava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;ZZILjava/lang/Object;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static synthetic fun readExcel$default (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Lorg/apache/poi/ss/usermodel/Workbook;Ljava/lang/String;ILjava/lang/String;Lorg/jetbrains/kotlinx/dataframe/io/FormattingOptions;Ljava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;ILjava/lang/Object;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static synthetic fun readExcel$default (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Lorg/apache/poi/ss/usermodel/Workbook;Ljava/lang/String;ILjava/lang/String;Lorg/jetbrains/kotlinx/dataframe/io/FormattingOptions;Ljava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;ZILjava/lang/Object;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static synthetic fun readExcel$default (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Lorg/apache/poi/ss/usermodel/Workbook;Ljava/lang/String;ILjava/lang/String;Lorg/jetbrains/kotlinx/dataframe/io/FormattingOptions;Ljava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;ZZILjava/lang/Object;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static final synthetic fun readExcel-CWg63oo (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Ljava/io/File;Ljava/lang/String;ILjava/lang/String;Ljava/lang/String;Ljava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static final synthetic fun readExcel-CWg63oo (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Ljava/io/InputStream;Ljava/lang/String;ILjava/lang/String;Ljava/lang/String;Ljava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static final synthetic fun readExcel-CWg63oo (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Ljava/lang/String;Ljava/lang/String;ILjava/lang/String;Ljava/lang/String;Ljava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
Expand All @@ -54,14 +54,14 @@ public final class org/jetbrains/kotlinx/dataframe/io/XlsxKt {
public static synthetic fun readExcel-CWg63oo$default (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Ljava/io/InputStream;Ljava/lang/String;ILjava/lang/String;Ljava/lang/String;Ljava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;ILjava/lang/Object;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static synthetic fun readExcel-CWg63oo$default (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Ljava/lang/String;Ljava/lang/String;ILjava/lang/String;Ljava/lang/String;Ljava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;ILjava/lang/Object;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static synthetic fun readExcel-CWg63oo$default (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Ljava/net/URL;Ljava/lang/String;ILjava/lang/String;Ljava/lang/String;Ljava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;ILjava/lang/Object;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static final fun readExcel-ssqQo1E (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Ljava/io/File;Ljava/lang/String;ILjava/lang/String;Ljava/lang/String;Ljava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;Z)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static final fun readExcel-ssqQo1E (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Ljava/io/InputStream;Ljava/lang/String;ILjava/lang/String;Ljava/lang/String;Ljava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;Z)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static final fun readExcel-ssqQo1E (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Ljava/lang/String;Ljava/lang/String;ILjava/lang/String;Ljava/lang/String;Ljava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;Z)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static final fun readExcel-ssqQo1E (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Ljava/net/URL;Ljava/lang/String;ILjava/lang/String;Ljava/lang/String;Ljava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;Z)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static synthetic fun readExcel-ssqQo1E$default (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Ljava/io/File;Ljava/lang/String;ILjava/lang/String;Ljava/lang/String;Ljava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;ZILjava/lang/Object;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static synthetic fun readExcel-ssqQo1E$default (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Ljava/io/InputStream;Ljava/lang/String;ILjava/lang/String;Ljava/lang/String;Ljava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;ZILjava/lang/Object;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static synthetic fun readExcel-ssqQo1E$default (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Ljava/lang/String;Ljava/lang/String;ILjava/lang/String;Ljava/lang/String;Ljava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;ZILjava/lang/Object;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static synthetic fun readExcel-ssqQo1E$default (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Ljava/net/URL;Ljava/lang/String;ILjava/lang/String;Ljava/lang/String;Ljava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;ZILjava/lang/Object;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static final fun readExcel-Q2e6U8A (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Ljava/io/File;Ljava/lang/String;ILjava/lang/String;Ljava/lang/String;Ljava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;ZZ)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static final fun readExcel-Q2e6U8A (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Ljava/io/InputStream;Ljava/lang/String;ILjava/lang/String;Ljava/lang/String;Ljava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;ZZ)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static final fun readExcel-Q2e6U8A (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Ljava/lang/String;Ljava/lang/String;ILjava/lang/String;Ljava/lang/String;Ljava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;ZZ)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static final fun readExcel-Q2e6U8A (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Ljava/net/URL;Ljava/lang/String;ILjava/lang/String;Ljava/lang/String;Ljava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;ZZ)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static synthetic fun readExcel-Q2e6U8A$default (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Ljava/io/File;Ljava/lang/String;ILjava/lang/String;Ljava/lang/String;Ljava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;ZZILjava/lang/Object;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static synthetic fun readExcel-Q2e6U8A$default (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Ljava/io/InputStream;Ljava/lang/String;ILjava/lang/String;Ljava/lang/String;Ljava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;ZZILjava/lang/Object;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static synthetic fun readExcel-Q2e6U8A$default (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Ljava/lang/String;Ljava/lang/String;ILjava/lang/String;Ljava/lang/String;Ljava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;ZZILjava/lang/Object;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static synthetic fun readExcel-Q2e6U8A$default (Lorg/jetbrains/kotlinx/dataframe/DataFrame$Companion;Ljava/net/URL;Ljava/lang/String;ILjava/lang/String;Ljava/lang/String;Ljava/lang/Integer;Lorg/jetbrains/kotlinx/dataframe/io/NameRepairStrategy;ZZILjava/lang/Object;)Lorg/jetbrains/kotlinx/dataframe/DataFrame;
public static final fun toFormattingOptions-lk1XfQA (Ljava/lang/String;Lorg/apache/poi/ss/usermodel/DataFormatter;)Lorg/jetbrains/kotlinx/dataframe/io/FormattingOptions;
public static synthetic fun toFormattingOptions-lk1XfQA$default (Ljava/lang/String;Lorg/apache/poi/ss/usermodel/DataFormatter;ILjava/lang/Object;)Lorg/jetbrains/kotlinx/dataframe/io/FormattingOptions;
public static final fun writeExcel (Lorg/jetbrains/kotlinx/dataframe/DataFrame;Ljava/io/File;Lkotlin/jvm/functions/Function2;Ljava/lang/String;ZLorg/jetbrains/kotlinx/dataframe/io/WorkBookType;Z)V
Expand Down
50 changes: 44 additions & 6 deletions dataframe-excel/src/main/kotlin/org/jetbrains/kotlinx/dataframe/io/xlsx.kt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -98,6 +98,8 @@ private fun setWorkbookTempDirectory() {
* when set to false, it operates as [NameRepairStrategy.MAKE_UNIQUE],
* ensuring unique column names will make the columns be named according to excel columns, like "A", "B", "C" etc.
* for unstructured data.
* @param parseEmptyAsNull when set to true, empty strings in cells are parsed as null (default true).
* These cells are ignored when inferring the column’s type.
*/
public fun DataFrame.Companion.readExcel(
url: URL,
Expand All @@ -108,6 +110,7 @@ public fun DataFrame.Companion.readExcel(
rowsCount: Int? = null,
nameRepairStrategy: NameRepairStrategy = NameRepairStrategy.CHECK_UNIQUE,
firstRowIsHeader: Boolean = true,
parseEmptyAsNull: Boolean = true,
): AnyFrame {
setWorkbookTempDirectory()
val wb = WorkbookFactory.create(url.openStream())
Expand All @@ -121,6 +124,7 @@ public fun DataFrame.Companion.readExcel(
rowsCount,
nameRepairStrategy,
firstRowIsHeader,
parseEmptyAsNull,
)
}
}
Expand All @@ -138,6 +142,8 @@ public fun DataFrame.Companion.readExcel(
* when set to false, it operates as [NameRepairStrategy.MAKE_UNIQUE],
* ensuring unique column names will make the columns be named according to excel columns, like "A", "B", "C" etc.
* for unstructured data.
* @param parseEmptyAsNull when set to true, empty strings in cells are parsed as null (default true).
* These cells are ignored when inferring the column’s type.
*/
public fun DataFrame.Companion.readExcel(
file: File,
Expand All @@ -148,6 +154,7 @@ public fun DataFrame.Companion.readExcel(
rowsCount: Int? = null,
nameRepairStrategy: NameRepairStrategy = NameRepairStrategy.CHECK_UNIQUE,
firstRowIsHeader: Boolean = true,
parseEmptyAsNull: Boolean = true,
): AnyFrame {
setWorkbookTempDirectory()
@Suppress("ktlint:standard:comment-wrapping")
Expand All @@ -162,6 +169,7 @@ public fun DataFrame.Companion.readExcel(
rowsCount,
nameRepairStrategy,
firstRowIsHeader,
parseEmptyAsNull,
)
}
}
Expand All @@ -179,6 +187,8 @@ public fun DataFrame.Companion.readExcel(
* when set to false, it operates as [NameRepairStrategy.MAKE_UNIQUE],
* ensuring unique column names will make the columns be named according to excel columns, like "A", "B", "C" etc.
* for unstructured data.
* @param parseEmptyAsNull when set to true, empty strings in cells are parsed as null (default true).
* These cells are ignored when inferring the column’s type.
*/
public fun DataFrame.Companion.readExcel(
fileOrUrl: String,
Expand All @@ -189,6 +199,7 @@ public fun DataFrame.Companion.readExcel(
rowsCount: Int? = null,
nameRepairStrategy: NameRepairStrategy = NameRepairStrategy.CHECK_UNIQUE,
firstRowIsHeader: Boolean = true,
parseEmptyAsNull: Boolean = true,
): AnyFrame =
readExcel(
asUrl(fileOrUrl),
Expand All @@ -199,6 +210,7 @@ public fun DataFrame.Companion.readExcel(
rowsCount,
nameRepairStrategy,
firstRowIsHeader,
parseEmptyAsNull,
)

/**
Expand All @@ -214,6 +226,8 @@ public fun DataFrame.Companion.readExcel(
* when set to false, it operates as [NameRepairStrategy.MAKE_UNIQUE],
* ensuring unique column names will make the columns be named according to excel columns, like "A", "B", "C" etc.
* for unstructured data.
* @param parseEmptyAsNull when set to true, empty strings in cells are parsed as null (default true).
* These cells are ignored when inferring the column’s type.
*/
public fun DataFrame.Companion.readExcel(
inputStream: InputStream,
Expand All @@ -224,6 +238,7 @@ public fun DataFrame.Companion.readExcel(
rowsCount: Int? = null,
nameRepairStrategy: NameRepairStrategy = NameRepairStrategy.CHECK_UNIQUE,
firstRowIsHeader: Boolean = true,
parseEmptyAsNull: Boolean = true,
): AnyFrame {
setWorkbookTempDirectory()
val wb = WorkbookFactory.create(inputStream)
Expand All @@ -237,6 +252,7 @@ public fun DataFrame.Companion.readExcel(
rowsCount,
nameRepairStrategy,
firstRowIsHeader,
parseEmptyAsNull,
)
}
}
Expand All @@ -255,6 +271,8 @@ public fun DataFrame.Companion.readExcel(
* when set to false, it operates as [NameRepairStrategy.MAKE_UNIQUE],
* ensuring unique column names will make the columns be named according to excel columns, like "A", "B", "C" etc.
* for unstructured data.
* @param parseEmptyAsNull when set to true, empty strings in cells are parsed as null (default true).
Copy link
Collaborator

@Jolanrensen Jolanrensen Jun 12, 2025 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

There may be more representations in strings that can refer to null. maybe it might be better to follow readCsv and other parsing options for this. It will be overkill to add the full ParserOptions as argument (since datetime and locales are already handled by excel), but csv, for instance uses nullStrings: Set<String>= setOf("", "NA", "N/A", "null", "NULL", "None", "none", "NIL", "nil"), so it might make sense to add a nullStrings argument here as well, probably with fewer defaults

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Created an issue:
#1248

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I don't think is a good idea to introduce a new non-trivial logic just before release, need more time for implementation and testing.

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

okay sure, makes sense

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

speaking off, this is a binary-breaking change. Since we released a beta already, we cannot break the API like that without a fallback mechanism. Could you add the old function signatures back with @Deprecated() at level HIDDEN? That way, we won't break libraries calling the old function :)

* These cells are ignored when inferring the column’s type.
*/
public fun DataFrame.Companion.readExcel(
wb: Workbook,
Expand All @@ -265,11 +283,21 @@ public fun DataFrame.Companion.readExcel(
rowsCount: Int? = null,
nameRepairStrategy: NameRepairStrategy = NameRepairStrategy.CHECK_UNIQUE,
firstRowIsHeader: Boolean = true,
parseEmptyAsNull: Boolean = true,
): AnyFrame {
val sheet: Sheet = sheetName
?.let { wb.getSheet(it) ?: error("Sheet with name $sheetName not found") }
?: wb.getSheetAt(0)
return readExcel(sheet, columns, formattingOptions, skipRows, rowsCount, nameRepairStrategy, firstRowIsHeader)
return readExcel(
sheet,
columns,
formattingOptions,
skipRows,
rowsCount,
nameRepairStrategy,
firstRowIsHeader,
parseEmptyAsNull,
)
}

/**
Expand Down Expand Up @@ -312,6 +340,7 @@ public fun DataFrame.Companion.readExcel(
rowsCount: Int? = null,
nameRepairStrategy: NameRepairStrategy = NameRepairStrategy.CHECK_UNIQUE,
firstRowIsHeader: Boolean = true,
parseEmptyAsNull: Boolean = true,
): AnyFrame {
val columnIndexes: Iterable<Int> = when {
columns != null -> getColumnIndices(columns)
Expand Down Expand Up @@ -364,12 +393,21 @@ public fun DataFrame.Companion.readExcel(
)
columnNameCounters[nameFromCell] =
columnNameCounters.getOrDefault(nameFromCell, 0) + 1 // increase the counter for specific column name
val getCellValue: (Cell?) -> Any? = when {
formattingOptions != null && index in formattingOptions.columnIndices -> { cell: Cell? ->
formattingOptions.formatter.formatCellValue(cell)
val getCellValue: (Cell?) -> Any? = { cell ->
if (cell == null) {
null
} else {
val rawValue: Any? = if (formattingOptions != null && index in formattingOptions.columnIndices) {
formattingOptions.formatter.formatCellValue(cell)
} else {
cell.cellValue(sheet.sheetName)
}
if (parseEmptyAsNull && rawValue is String && rawValue.isEmpty()) {
null
} else {
rawValue
}
}

else -> { cell -> cell.cellValue(sheet.sheetName) }
}
val values: List<Any?> = valueRowsRange.map {
val row: Row? = sheet.getRow(it)
Expand Down
Loading