[REST-155] Refactoring type class hierarchy

build.sbt

@@ -100,6 +100,6 @@ lazy val `data-scalaxy-reader` = (project in file("."))
 
 lazy val `reader-text` = (project in file("text"))
   .settings(
-    version := "1.1.0",
+    version := "2.0.0",
     libraryDependencies ++= textDependencies
   )

text/src/main/scala/com/clairvoyant/data/scalaxy/reader/text/TextToDataFrameReader.scala

@@ -1,26 +1,26 @@
 package com.clairvoyant.data.scalaxy.reader.text
 
 import com.clairvoyant.data.scalaxy.reader.text.formats.TextFormat
-import com.clairvoyant.data.scalaxy.reader.text.instances.TextFormatToDataFrameReader
 import org.apache.spark.sql.types.StructType
 import org.apache.spark.sql.{DataFrame, SparkSession}
 
-object TextToDataFrameReader {
+trait TextToDataFrameReader[T]:
 
-  def read[T <: TextFormat](
+  def read(
+      text: Seq[String],
+      textFormat: T,
+      originalSchema: Option[StructType],
+      adaptSchemaColumns: StructType => StructType
+  )(using sparkSession: SparkSession): DataFrame
+
+  def read(
       text: String,
       textFormat: T,
       originalSchema: Option[StructType] = None,
       adaptSchemaColumns: StructType => StructType = identity
-  )(using textFormatToDataFrameReader: TextFormatToDataFrameReader[T], sparkSession: SparkSession): DataFrame =
-    read(Seq(text), textFormat, originalSchema, adaptSchemaColumns)
+  )(using sparkSession: SparkSession): DataFrame = read(Seq(text), textFormat, originalSchema, adaptSchemaColumns)
 
-  def read[T <: TextFormat](
-      text: Seq[String],
-      textFormat: T,
-      originalSchema: Option[StructType],
-      adaptSchemaColumns: StructType => StructType
-  )(using textFormatToDataFrameReader: TextFormatToDataFrameReader[T], sparkSession: SparkSession): DataFrame =
-    textFormatToDataFrameReader.read(text, textFormat, originalSchema, adaptSchemaColumns)
+object TextToDataFrameReader:
 
-}
+  def apply[T <: TextFormat](using textToDataFrameReader: TextToDataFrameReader[T]): TextToDataFrameReader[T] =
+    textToDataFrameReader

text/src/main/scala/com/clairvoyant/data/scalaxy/reader/text/instances/CSVTextToDataFrameReader.scala

@@ -1,11 +1,12 @@
 package com.clairvoyant.data.scalaxy.reader.text.instances
 
+import com.clairvoyant.data.scalaxy.reader.text.TextToDataFrameReader
 import com.clairvoyant.data.scalaxy.reader.text.formats.CSVTextFormat
 import org.apache.spark.sql.catalyst.csv.CSVOptions.*
 import org.apache.spark.sql.types.{StringType, StructType}
 import org.apache.spark.sql.{DataFrame, SparkSession}
 
-implicit object CSVTextToDataFrameReader extends TextFormatToDataFrameReader[CSVTextFormat] {
+implicit object CSVTextToDataFrameReader extends TextToDataFrameReader[CSVTextFormat] {
 
   override def read(
       text: Seq[String],

text/src/main/scala/com/clairvoyant/data/scalaxy/reader/text/instances/HTMLTableTextToDataFrameReader.scala

@@ -11,17 +11,17 @@ import org.jsoup.select.Elements
 import scala.collection.convert.ImplicitConversions.`collection AsScalaIterable`
 import scala.util.Try
 
-implicit object HTMLTableTextToDataFrameReader extends TextFormatToDataFrameReader[HTMLTableTextFormat] {
+implicit object HTMLTableTextToDataFrameReader extends TextToDataFrameReader[HTMLTableTextFormat] {
 
-  val VALUE_SEPARATOR = "~"
+  private val VALUE_SEPARATOR = "~"
 
   override def read(
       text: Seq[String],
       textFormat: HTMLTableTextFormat,
       originalSchema: Option[StructType],
       adaptSchemaColumns: StructType => StructType
   )(using sparkSession: SparkSession): DataFrame =
-    TextToDataFrameReader.read(
+    TextToDataFrameReader[CSVTextFormat].read(
       text = text.map(htmlText => convertHTMLTableToCSV(htmlText, textFormat.tableName)),
       textFormat = CSVTextFormat(
         sep = VALUE_SEPARATOR
@@ -30,7 +30,7 @@ implicit object HTMLTableTextToDataFrameReader extends TextFormatToDataFrameRead
       adaptSchemaColumns = adaptSchemaColumns
     )
 
-  def convertHTMLTableToCSV(htmlText: String, tableName: Option[String] = None): String = {
+  private def convertHTMLTableToCSV(htmlText: String, tableName: Option[String] = None): String = {
     Try {
       val parsedDocument = Jsoup.parse(htmlText)
 
@@ -47,7 +47,7 @@ implicit object HTMLTableTextToDataFrameReader extends TextFormatToDataFrameRead
     }.get
   }
 
-  def getTableFromParsedDocument(parsedDocument: Document, tableName: Option[String]): Element =
+  private def getTableFromParsedDocument(parsedDocument: Document, tableName: Option[String]): Element =
     tableName
       .map { tblName =>
         val tables = parsedDocument.select(tblName)
@@ -58,12 +58,12 @@ implicit object HTMLTableTextToDataFrameReader extends TextFormatToDataFrameRead
       }
       .getOrElse(parsedDocument.getElementsByTag("table").first())
 
-  def getTableHeader(rows: Elements): String =
+  private def getTableHeader(rows: Elements): String =
     Seq(rows.select("th").map(_.text)).flatten
       .mkString(VALUE_SEPARATOR)
       .concat("\n")
 
-  def getTableRows(rows: Elements): String =
+  private def getTableRows(rows: Elements): String =
     Seq(
       rows.map { row =>
         val flattenRows = Seq(row.select("td").map(_.text())).flatten

text/src/main/scala/com/clairvoyant/data/scalaxy/reader/text/instances/JSONTextToDataFrameReader.scala

@@ -1,12 +1,13 @@
 package com.clairvoyant.data.scalaxy.reader.text.instances
 
+import com.clairvoyant.data.scalaxy.reader.text.TextToDataFrameReader
 import com.clairvoyant.data.scalaxy.reader.text.formats.JSONTextFormat
 import org.apache.spark.sql.catalyst.json.JSONOptions.*
 import org.apache.spark.sql.functions.{col, explode}
 import org.apache.spark.sql.types.StructType
 import org.apache.spark.sql.{DataFrame, SparkSession}
 
-implicit object JSONTextToDataFrameReader extends TextFormatToDataFrameReader[JSONTextFormat] {
+implicit object JSONTextToDataFrameReader extends TextToDataFrameReader[JSONTextFormat] {
 
   override def read(
       text: Seq[String],

text/src/main/scala/com/clairvoyant/data/scalaxy/reader/text/instances/XMLTextToDataFrameReader.scala

@@ -1,13 +1,14 @@
 package com.clairvoyant.data.scalaxy.reader.text.instances
 
+import com.clairvoyant.data.scalaxy.reader.text.TextToDataFrameReader
 import com.clairvoyant.data.scalaxy.reader.text.formats.XMLTextFormat
 import org.apache.spark.sql.types.StructType
 import org.apache.spark.sql.{DataFrame, SparkSession}
 
 import java.io.{File, PrintWriter}
 import java.util.concurrent.Semaphore
 
-implicit object XMLTextToDataFrameReader extends TextFormatToDataFrameReader[XMLTextFormat] {
+implicit object XMLTextToDataFrameReader extends TextToDataFrameReader[XMLTextFormat] {
 
   override def read(
       text: Seq[String],

text/src/test/scala/com/clairvoyant/data/scalaxy/reader/text/CSVTextToDataFrameReaderSpec.scala

@@ -1,6 +1,5 @@
 package com.clairvoyant.data.scalaxy.reader.text
 
-import com.clairvoyant.data.scalaxy.reader.text.TextToDataFrameReader
 import com.clairvoyant.data.scalaxy.reader.text.formats.CSVTextFormat
 import com.clairvoyant.data.scalaxy.reader.text.instances.CSVTextToDataFrameReader
 import com.clairvoyant.data.scalaxy.test.util.SparkUtil
@@ -9,6 +8,8 @@ import org.apache.spark.sql.types.*
 
 class CSVTextToDataFrameReaderSpec extends SparkUtil {
 
+  val csvTextToDataFrameReader = TextToDataFrameReader[CSVTextFormat]
+
   "read() - with csv text and headers" should "return a dataframe with correct count and schema" in {
     val csvText =
       """|col1,col2
@@ -18,7 +19,7 @@ class CSVTextToDataFrameReaderSpec extends SparkUtil {
 
     val csvTextFormat = CSVTextFormat()
 
-    val df = TextToDataFrameReader.read(
+    val df = csvTextToDataFrameReader.read(
       text = csvText,
       textFormat = csvTextFormat
     )
@@ -38,7 +39,7 @@ class CSVTextToDataFrameReaderSpec extends SparkUtil {
       inferSchema = false
     )
 
-    val df = TextToDataFrameReader.read(
+    val df = csvTextToDataFrameReader.read(
       text = csvText,
       textFormat = csvTextFormat
     )
@@ -57,7 +58,7 @@ class CSVTextToDataFrameReaderSpec extends SparkUtil {
       header = false
     )
 
-    val df = TextToDataFrameReader.read(
+    val df = csvTextToDataFrameReader.read(
       text = csvText,
       textFormat = csvTextFormat
     )
@@ -77,7 +78,7 @@ class CSVTextToDataFrameReaderSpec extends SparkUtil {
       sep = ";"
     )
 
-    val df = TextToDataFrameReader.read(
+    val df = csvTextToDataFrameReader.read(
       text = csvText,
       textFormat = csvTextFormat
     )
@@ -94,7 +95,7 @@ class CSVTextToDataFrameReaderSpec extends SparkUtil {
       recordSep = "#"
     )
 
-    val df = TextToDataFrameReader.read(
+    val df = csvTextToDataFrameReader.read(
       text = csvText,
       textFormat = csvTextFormat
     )
@@ -112,7 +113,7 @@ class CSVTextToDataFrameReaderSpec extends SparkUtil {
       recordSep = "#"
     )
 
-    val df = TextToDataFrameReader.read(
+    val df = csvTextToDataFrameReader.read(
       text = csvText,
       textFormat = csvTextFormat
     )
@@ -132,7 +133,7 @@ class CSVTextToDataFrameReaderSpec extends SparkUtil {
       timestampFormat = "dd-MM-yyyy HH:mm:ss"
     )
 
-    val df = TextToDataFrameReader.read(
+    val df = csvTextToDataFrameReader.read(
       text = csvText,
       textFormat = csvTextFormat
     )
@@ -153,7 +154,7 @@ class CSVTextToDataFrameReaderSpec extends SparkUtil {
       locale = "fr-FR"
     )
 
-    val df = TextToDataFrameReader.read(
+    val df = csvTextToDataFrameReader.read(
       text = csvText,
       textFormat = csvTextFormat
     )
@@ -175,7 +176,7 @@ class CSVTextToDataFrameReaderSpec extends SparkUtil {
       mode = "PERMISSIVE"
     )
 
-    val df = TextToDataFrameReader.read(
+    val df = csvTextToDataFrameReader.read(
       text = csvText,
       textFormat = csvTextFormat
     )
@@ -208,7 +209,7 @@ class CSVTextToDataFrameReaderSpec extends SparkUtil {
       escape = "#"
     )
 
-    val df = TextToDataFrameReader.read(
+    val df = csvTextToDataFrameReader.read(
       text = csvText,
       textFormat = csvTextFormat
     )
@@ -235,7 +236,7 @@ class CSVTextToDataFrameReaderSpec extends SparkUtil {
       nullValue = "Invalid"
     )
 
-    val df = TextToDataFrameReader.read(
+    val df = csvTextToDataFrameReader.read(
       text = csvText,
       textFormat = csvTextFormat
     )
@@ -263,7 +264,7 @@ class CSVTextToDataFrameReaderSpec extends SparkUtil {
       quote = "~"
     )
 
-    val df = TextToDataFrameReader.read(
+    val df = csvTextToDataFrameReader.read(
       text = csvText,
       textFormat = csvTextFormat
     )
@@ -285,7 +286,7 @@ class CSVTextToDataFrameReaderSpec extends SparkUtil {
       enforceSchema = true
     )
 
-    val df = TextToDataFrameReader.read(
+    val df = csvTextToDataFrameReader.read(
       text = csvText,
       textFormat = csvTextFormat,
       originalSchema = Some(
@@ -315,7 +316,7 @@ class CSVTextToDataFrameReaderSpec extends SparkUtil {
       ignoreLeadingWhiteSpace = true
     )
 
-    val df = TextToDataFrameReader.read(
+    val df = csvTextToDataFrameReader.read(
       text = csvText,
       textFormat = csvTextFormat
     )
@@ -343,7 +344,7 @@ class CSVTextToDataFrameReaderSpec extends SparkUtil {
       ignoreTrailingWhiteSpace = true
     )
 
-    val df = TextToDataFrameReader.read(
+    val df = csvTextToDataFrameReader.read(
       text = csvText,
       textFormat = csvTextFormat
     )
@@ -372,7 +373,7 @@ class CSVTextToDataFrameReaderSpec extends SparkUtil {
       nanValue = "NA"
     )
 
-    val df = TextToDataFrameReader.read(
+    val df = csvTextToDataFrameReader.read(
       text = csvText,
       textFormat = csvTextFormat
     )
@@ -392,7 +393,7 @@ class CSVTextToDataFrameReaderSpec extends SparkUtil {
       positiveInf = "PositiveInfiniteValue"
     )
 
-    val df = TextToDataFrameReader.read(
+    val df = csvTextToDataFrameReader.read(
       text = csvText,
       textFormat = csvTextFormat
     )
@@ -417,7 +418,7 @@ class CSVTextToDataFrameReaderSpec extends SparkUtil {
       negativeInf = "NegativeInfiniteValue"
     )
 
-    val df = TextToDataFrameReader.read(
+    val df = csvTextToDataFrameReader.read(
       text = csvText,
       textFormat = csvTextFormat
     )
@@ -444,7 +445,7 @@ class CSVTextToDataFrameReaderSpec extends SparkUtil {
       comment = "*"
     )
 
-    val df = TextToDataFrameReader.read(
+    val df = csvTextToDataFrameReader.read(
       text = csvText,
       textFormat = csvTextFormat
     )
@@ -462,7 +463,7 @@ class CSVTextToDataFrameReaderSpec extends SparkUtil {
 
     val csvTextFormat = CSVTextFormat()
 
-    val df = TextToDataFrameReader.read(
+    val df = csvTextToDataFrameReader.read(
       text = csvText,
       textFormat = csvTextFormat,
       adaptSchemaColumns =

text/src/test/scala/com/clairvoyant/data/scalaxy/reader/text/HTMLTableTextToDataFrameReaderSpec.scala

@@ -1,16 +1,14 @@
 package com.clairvoyant.data.scalaxy.reader.text
 
-import com.clairvoyant.data.scalaxy.reader.text.TextToDataFrameReader
-import com.clairvoyant.data.scalaxy.reader.text.formats.{CSVTextFormat, HTMLTableTextFormat}
+import com.clairvoyant.data.scalaxy.reader.text.formats.HTMLTableTextFormat
 import com.clairvoyant.data.scalaxy.reader.text.instances.HTMLTableTextToDataFrameReader
-import com.clairvoyant.data.scalaxy.test.util.SparkUtil
 import com.clairvoyant.data.scalaxy.test.util.matchers.DataFrameMatcher
 import com.clairvoyant.data.scalaxy.test.util.readers.DataFrameReader
-import org.apache.spark.sql.functions.col
-import org.apache.spark.sql.types.*
 
 class HTMLTableTextToDataFrameReaderSpec extends DataFrameReader with DataFrameMatcher {
 
+  val htmlTableTextToDataFrameReader = TextToDataFrameReader[HTMLTableTextFormat]
+
   "read() - with html text" should "return a dataframe with correct count and schema" in {
     val htmlText =
       """
@@ -98,7 +96,7 @@ class HTMLTableTextToDataFrameReaderSpec extends DataFrameReader with DataFrameM
 
     val htmlTableTextFormat = HTMLTableTextFormat()
 
-    val actualDF = TextToDataFrameReader.read(
+    val actualDF = htmlTableTextToDataFrameReader.read(
       text = htmlText,
       textFormat = htmlTableTextFormat
     )