Merge pull request #157 from LeandroC89/ExcelWriteNewSheet

Excel add new sheet without overwriting the file

Author: koperagen

dataframe-excel/src/main/kotlin/org/jetbrains/kotlinx/dataframe/io/xlsx.kt

@@ -306,8 +306,9 @@ public fun <T> DataFrame<T>.writeExcel(
     sheetName: String? = null,
     writeHeader: Boolean = true,
     workBookType: WorkBookType = WorkBookType.XLSX,
+    keepFile: Boolean = false,
 ) {
-    return writeExcel(File(path), columnsSelector, sheetName, writeHeader, workBookType)
+    return writeExcel(File(path), columnsSelector, sheetName, writeHeader, workBookType, keepFile)
 }
 
 public enum class WorkBookType {
@@ -320,16 +321,22 @@ public fun <T> DataFrame<T>.writeExcel(
     sheetName: String? = null,
     writeHeader: Boolean = true,
     workBookType: WorkBookType = WorkBookType.XLSX,
+    keepFile: Boolean = false,
 ) {
-    val factory = when (workBookType) {
-        WorkBookType.XLS -> {
-            { HSSFWorkbook() }
-        }
 
-        WorkBookType.XLSX -> {
-            { XSSFWorkbook() }
+    val factory =
+        if (keepFile){
+            when (workBookType) {
+                WorkBookType.XLS -> HSSFWorkbook(file.inputStream())
+                WorkBookType.XLSX ->  XSSFWorkbook(file.inputStream())
+            }
+        }
+        else {
+            when (workBookType) {
+                WorkBookType.XLS ->  HSSFWorkbook()
+                WorkBookType.XLSX ->  XSSFWorkbook()
+            }
         }
-    }
     return file.outputStream().use {
         writeExcel(it, columnsSelector, sheetName, writeHeader, factory)
     }
@@ -340,9 +347,9 @@ public fun <T> DataFrame<T>.writeExcel(
     columnsSelector: ColumnsSelector<T, *> = { all() },
     sheetName: String? = null,
     writeHeader: Boolean = true,
-    factory: () -> Workbook,
+    factory: Workbook
 ) {
-    val wb: Workbook = factory()
+    val wb: Workbook = factory
     writeExcel(wb, columnsSelector, sheetName, writeHeader)
     wb.write(outputStream)
     wb.close()

dataframe-excel/src/test/kotlin/org/jetbrains/kotlinx/dataframe/io/XlsxTest.kt

@@ -133,6 +133,21 @@ class XlsxTest {
         }
     }
 
+    @Test
+    fun `write to new sheet when keepFile is true`() {
+        val names = (1..5).map { "column$it" }
+        val df = dataFrameOf(names).randomDouble(7)
+        val fileLoc = Files.createTempFile("generated_wb", ".xlsx").toFile()
+
+        df.writeExcel(fileLoc, sheetName = "TestSheet1")
+        df.writeExcel(fileLoc, sheetName = "TestSheet2", keepFile = true)
+
+        val testSheet1Df = DataFrame.readExcel(fileLoc, sheetName = "TestSheet1")
+        val testSheet2Df = DataFrame.readExcel(fileLoc, sheetName = "TestSheet2")
+
+        testSheet1Df.columnNames() shouldBe testSheet2Df.columnNames()
+    }
+
     @Test
     fun `read xlsx file with duplicated columns and repair column names`() {
         shouldThrow<DuplicateColumnNamesException> {

docs/StardustDocs/topics/write.md

@@ -117,6 +117,21 @@ wb.close()
 
 <!---END-->
 
+Add new sheets without using Apache POI directly by using a parameter to keep using the same file if it already exists
+
+<!---FUN writeXlsWithMultipleSheets-->
+
+```kotlin
+// Create a new Excel workbook with a single sheet called "allPersons", replacing the file if it already exists -> Current sheets: allPersons
+df.writeExcel(file, sheetName = "allPersons")
+// Add a new sheet to the previous file without replacing it, by setting keepFile = true -> Current sheets: allPersons, happyPersons
+df.filter { person -> person.isHappy }.remove("isHappy").writeExcel(file, sheetName = "happyPersons", keepFile = true)
+// Add a new sheet to the previous file without replacing it, by setting keepFile = true -> Current sheets: allPersons, happyPersons, unhappyPersons
+df.filter { person -> !person.isHappy }.remove("isHappy").writeExcel(file, sheetName = "unhappyPersons", keepFile = true)
+```
+
+<!---END-->
+
 ### Writing to Apache Arrow formats
 
 Add dependency:

tests/src/test/kotlin/org/jetbrains/kotlinx/dataframe/samples/api/Write.kt

@@ -219,6 +219,20 @@ class Write : TestBase() {
         }
     }
 
+    @Test
+    fun writeXlsWithMultipleSheets() {
+        useTempFile { file ->
+            // SampleStart
+            // Create a new Excel workbook with a single sheet called "allPersons", replacing the file if it already exists -> Current sheets: allPersons
+            df.writeExcel(file, sheetName = "allPersons")
+            // Add a new sheet to the previous file without replacing it, by setting keepFile = true -> Current sheets: allPersons, happyPersons
+            df.filter { person -> person.isHappy }.remove("isHappy").writeExcel(file, sheetName = "happyPersons", keepFile = true)
+            // Add a new sheet to the previous file without replacing it, by setting keepFile = true -> Current sheets: allPersons, happyPersons, unhappyPersons
+            df.filter { person -> !person.isHappy }.remove("isHappy").writeExcel(file, sheetName = "unhappyPersons", keepFile = true)
+            // SampleEnd
+        }
+    }
+
     companion object {
         private fun String.rejoinWithSystemLineSeparator() = rejoinWithLineSeparator(System.lineSeparator())