Merge pull request #17 from ChinthapallyAkanksha/spark-3.3

Updated Quenya-Dsl to support special characters for spark-3.3 branch

.github/workflows/quneys-dsl-githubactions.yml → .github/workflows/quenya-dsl-githubactions.yml

@@ -28,8 +28,8 @@ jobs:
           cache: sbt
       - name: Build and test scala version
         run: |
-          PGPASSWORD="postgres" psql -c 'create database almaren;' -U postgres -h localhost 
-          PGPASSWORD="postgres" psql -c "ALTER USER postgres PASSWORD 'foo' ;" -U postgres -h localhost 
+          PGPASSWORD="postgres" psql -c 'create database almaren;' -U postgres -h localhost
+          PGPASSWORD="postgres" psql -c "ALTER USER postgres PASSWORD 'postgres' ;" -U postgres -h localhost
           PGPASSWORD="postgres" psql -c 'create role runner;' -U postgres -h localhost
           PGPASSWORD="postgres" psql -c 'ALTER ROLE "runner" WITH  LOGIN SUPERUSER INHERIT CREATEDB CREATEROLE REPLICATION;' -U postgres -h localhost
           sbt ++2.12.10 test

README.md

@@ -1,28 +1,24 @@
-# Quenya DSL
+# Quenya-DSL
 
 [![Build Status](https://github.com/music-of-the-ainur/quenya-dsl/actions/workflows/quneys-dsl-githubactions.yml/badge.svg)](https://github.com/music-of-the-ainur/quenya-dsl/actions/workflows/quneys-dsl-githubactions.yml)
 
-Adding Quenya DSL dependency to your sbt build:
+Adding Quenya-DSL dependency to your sbt build:
 
 ```
-libraryDependencies += "com.github.music-of-the-ainur" %% "quenya-dsl" % "1.2.2-3.3"
+libraryDependencies += "com.github.music-of-the-ainur" %% "quenya-dsl" % "1.2.2-$SPARK_VERSION"
 ```
 
 To run in spark-shell:
 
 ```
-spark-shell --packages "com.github.music-of-the-ainur:quenya-dsl_2.13:1.2.2-3.3"
+spark-shell --packages "com.github.music-of-the-ainur:quenya-dsl_2.12:1.2.0-$SPARK_VERSION"
 ```
 
-### Connector Usage
 
-#### Maven / Ivy Package Usage
-The connector is also available from the
-[Maven Central](https://mvnrepository.com/artifact/com.github.music-of-the-ainur)
-repository. It can be used using the `--packages` option or the
-`spark.jars.packages` configuration property. Use the following value
+Quenya-Dsl is available in [Maven Central](https://mvnrepository.com/artifact/com.github.music-of-the-ainur)
+repository. 
 
-| version                    | Connector Artifact                                        |
+| versions                   | Connector Artifact                                        |
 |----------------------------|-----------------------------------------------------------|
 | Spark 3.3.x and scala 2.13 | `com.github.music-of-the-ainur:quenya-dsl_2.13:1.2.2-3.3` |
 | Spark 3.3.x and scala 2.12 | `com.github.music-of-the-ainur:quenya-dsl_2.12:1.2.2-3.3` |
@@ -32,7 +28,7 @@ repository. It can be used using the `--packages` option or the
 | Spark 2.4.x and scala 2.11 | `com.github.music-of-the-ainur:quenya-dsl_2.11:1.2.2-2.4` |
 
 ## Introduction
-Quenya DSL(Domain Specific Language) is a language that simplifies the task to parser complex semi-structured data.
+Quenya-DSL(Domain Specific Language) is a language that simplifies the task to parser complex semi-structured data.
 
 ```scala
 
@@ -155,7 +151,7 @@ Output:
 
 ## DSL Generator
 
-You can generate a DSL based on a DataFrame:
+You can generate the DSL from an existing DataFrame:
 
 ```scala
 import com.github.music.of.the.ainur.quenya.QuenyaDSL
@@ -165,6 +161,18 @@ val quenyaDsl = QuenyaDSL
 quenyaDsl.printDsl(df)
 ```
 
+### getDsl
+You can generate and asssign a DSL to variable based on a DataFrame:
+
+```scala
+import com.github.music.of.the.ainur.quenya.QuenyaDSL
+
+val df:DataFrame = ...
+val quenyaDsl = QuenyaDSL
+val dsl = quenyaDsl.getDsl(df)
+```
+
+
 json:
 ```
 { 
@@ -201,6 +209,50 @@ weapon@weapon
 
 You can _alias_ using the fully qualified name using ```printDsl(df,true)```, you should turn on in case of name conflict.
 
+## How to Handle Special Characters
+
+
+
+Use the literal backtick **``**  to handle special characters like space,semicolon,hyphen and colon.
+Example:
+
+
+
+json:
+```
+{
+   "name":{
+      "name One":"Mithrandir",
+      "Last-Name":"Olórin",
+      "nick:Names":[
+         "Gandalf the Grey",
+         "Gandalf the White"
+      ]
+   },
+   "race":"Maiar",
+   "age":"immortal",
+   "weapon;name":[
+      "Glamdring",
+      "Narya",
+      "Wizard Staff"
+   ]
+}
+```
+
+
+
+DSL:
+```
+age$age:StringType
+`name.Last-Name`$`Last-Name`:StringType
+`name.name One`$`name-One`:StringType
+`name.nick:Names`@`nick:Names`
+        `nick:Names`$`nick:Names`:StringType
+race$race:StringType
+`weapon;name`@`weapon;name`
+        `weapon;name`$`weapon_name`:StringType
+```
+
 ## Backus–Naur form
 
 ```
@@ -216,14 +268,6 @@ You can _alias_ using the fully qualified name using ```printDsl(df,true)```, yo
  | DoubleType | FloatType | ByteType | IntegerType | LongType | ShortType
 ```
 
-## Requirements
-
-| Software     | Version   |
-|--------------|-----------|
-| Java         | 8         |
-| Scala        | 2.11/2.12 |
-| Apache Spark | 2.4       |
-
 ## Author
 Daniel Mantovani [[email protected]](mailto:[email protected])
 

build.sbt

@@ -32,6 +32,12 @@ ThisBuild / developers := List(
     name  = "Daniel Mantovani",
     email = "[email protected]",
     url   = url("https://github.com/music-of-the-ainur")
+  ),
+  Developer(
+    id = "ChinthapallyAkanksha",
+    name = "Akanksha Chinthapally",
+    email = "[email protected]",
+    url = url("https://github.com/music-of-the-ainur")
   )
 )
 

src/main/scala/com/github/music/of/the/ainur/quenya/compiler/CombinatorParser.scala

@@ -6,7 +6,6 @@ import scala.util.parsing.combinator._
 
 /*
  Spark DSL Backus-Naur form.
-
  <dsl> ::= \{"[\r\n]*".r <precedence> <col> <operator> \}
  <precedence> ::= "[\s\t]*".r
  <col> ::= "a-zA-Z0-9_.".r  [ element ]
@@ -15,9 +14,8 @@ import scala.util.parsing.combinator._
  <@> ::= @ <alias>
  <$> ::= $ <alias> : <datatype>
  <alias> ::= "0-9a-zA-Z_".r
- <datatype> ::= BinaryType | BooleanType | StringType | TimestampType | DecimalType 
+ <datatype> ::= BinaryType | BooleanType | StringType | TimestampType | DecimalType
  | DoubleType | FloatType | ByteType | IntegerType | LongType | ShortType
-
  */
 private[quenya] trait CombinatorParser {
   val parser = ParserQuenyaDsl
@@ -30,9 +28,16 @@ private[quenya] trait CombinatorParser {
     }
 }
 
-object ParserQuenyaDsl extends JavaTokenParsers {
+trait ParserUtil {
+  def removeLiteral(content: String, literal: String): String = {
+    if (content.head.toString == literal && content.last.toString == literal)
+      content.substring(1, content.length - 1)
+    else content
+  }
+}
+object ParserQuenyaDsl extends JavaTokenParsers with ParserUtil {
   override val skipWhitespace = false
- 
+
   def dsl: Parser[List[Statement]] = repsep(expression,"""[\n\r]*""".r) ^^ (List() ++ _ )
   def expression: Parser[Statement] = precedence ~ col ~ operator ^^ {
     case prec ~ cl ~ op =>
@@ -45,16 +50,21 @@ object ParserQuenyaDsl extends JavaTokenParsers {
         case al:String => Statement(prec,cl,AT,al)
       }
   }
-  def precedence: Parser[Int] = """[\t\s]*""".r ^^ (prec => prec.replaceAll(" ","\t").count(_ == '\t'))
-  def col: Parser[StateSelect] = """[0-9A-Za-z._]+""".r ~ opt(element) ^^ {
-    case a ~ Some(b) => StateSelect(a,b)
-    case a ~ None => StateSelect(a,None)
+  def precedence: Parser[Int] = """^[\t\s]*""".r ^^ (prec => prec.replaceAll(" ","\t").count(_ == '\t'))
+  def col: Parser[StateSelect] = """[\w.]+|`[\w. \-:;$]+`""".r ~ opt(element) ^^ {
+    case a ~ Some(b) => createStateSelect(a,b)
+    case a ~ None => createStateSelect(a,None)
   }
+  private def createStateSelect(name: String, element: Option[String]): StateSelect =
+    StateSelect(removeLiteral(name,"`"),element)
+
   def element: Parser[Option[String]] = "[" ~> opt("""\d+""".r) <~ "]"
   def operator: Parser[Any] = at | dollar
   def at: Parser[String] = "@" ~> alias
   def dollar : Parser[Any] = "$" ~> alias ~ opt(":") ~ datatype
-  def alias : Parser[String] = "[0-9a-zA-Z_]+".r
+  def alias : Parser[String] = """\w+|`[\w \-:;$]+`""".r ^^ {
+    alias => removeLiteral(alias,"`")
+  }
   def datatype : Parser[Option[DataType]] = ("BinaryType" ^^ (dt => Some(BinaryType))
     | "FloatType" ^^ (dt => Some(FloatType))
     | "ByteType" ^^ (dt => Some(ByteType))
@@ -67,4 +77,4 @@ object ParserQuenyaDsl extends JavaTokenParsers {
     | "DoubleType" ^^ (dt => Some(DoubleType))
     | "ShortType" ^^ (dt => Some(ShortType))
     | "" ^^ (dt => None))
-}
+}

src/test/resources/data.csv

@@ -1,10 +1,10 @@
 age,LastName,nameOne,nickNames,race,weapon
-3500,Olórin,Mithrandir,Gandalf the Grey,Maiar,Glamdring
-3500,Olórin,Mithrandir,Gandalf the Grey,Maiar,Narya
-3500,Olórin,Mithrandir,Gandalf the Grey,Maiar,Wizard Staff
+3500,Olórin,Mithrandir,Gandalf the Grey,Maiar,Glamdring
+3500,Olórin,Mithrandir,Gandalf the Grey,Maiar,Narya
+3500,Olórin,Mithrandir,Gandalf the Grey,Maiar,Wizard Staff
 4500,"",Ilmarë,"",Ainur,Powers of the Ainur
 3500,"",Morgoth,Bauglir,Ainur,Powers of the Ainur
 3500,"",Morgoth,Bauglir,Ainur,Grond
 3500,"",Morgoth,Bauglir,Ainur,Mace
 3500,"",Morgoth,Bauglir,Ainur,Sword
-3500,"",Manwë,"King of Arda,",Ainur,Powers of the Ainur
+3500,"",Manwë,"King of Arda,",Ainur,Powers of the Ainur

src/test/resources/data.json

@@ -0,0 +1,50 @@
+{
+  "Coffee": {
+    "sub region": [
+      {
+        "id": 1,
+        "full name": "John Doe"
+      },
+      {
+        "id": 2,
+        "name": "Don Joeh"
+      }
+    ],
+    "country": {
+      "id": 2,
+      "company": "ACME"
+    }
+  },
+  "brewing": {
+    "sub-region": [
+      {
+        "id": 1,
+        "name": "John Doe"
+      },
+      {
+        "id": 2,
+        "name": "Don Joeh"
+      }
+    ],
+    "world:country": {
+      "id": 2,
+      "company": "ACME"
+    }
+  },
+  "brewing2": {
+    "sub;region": [
+      {
+        "id": 1,
+        "name": "John Doe"
+      },
+      {
+        "id": 2,
+        "name": "Don Joeh"
+      }
+    ],
+    "world;country": {
+      "id": 2,
+      "company": "ACME"
+    }
+  }
+}