[SPARK-27786][SQL] Fix Sha1, Md5, and Base64 codegen when commons-codec is shaded

## What changes were proposed in this pull request?

When running a custom build of Spark which shades `commons-codec`, the `Sha1` expression generates code which fails to compile:

```
org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator: failed to compile: org.codehaus.commons.compiler.CompileException: File 'generated.java', Line 47, Column 93: A method named "sha1Hex" is not declared in any enclosing class nor any supertype, nor through a static import
```

This is caused by an interaction between Spark's code generator and the shading: the current codegen template includes the string `org.apache.commons.codec.digest.DigestUtils.sha1Hex` as part of a larger string literal, preventing JarJarLinks from being able to replace the class name with the shaded class's name. As a result, the generated code still references the original unshaded class name name, triggering an error in case the original unshaded dependency isn't on the path.

This problem impacts the `Sha1`, `Md5`, and `Base64` expressions.

To fix this problem and allow for proper shading, this PR updates the codegen templates to replace the hardcoded class names with `${classof[<name>].getName}` calls.

## How was this patch tested?

Existing tests.

To ensure that I found all occurrences of this problem, I used IntelliJ's "Find in Path" to search for lines matching the regex `^(?!import|package).*(org|com|net|io)\.(?!apache\.spark)` and then filtered matches to inspect only non-test "Usage in string constants" cases. This isn't _perfect_ but I think it'll catch most cases.

Closes apache#24655 from JoshRosen/fix-shaded-apache-commons.

Authored-by: Josh Rosen <[email protected]>
Signed-off-by: Wenchen Fan <[email protected]>

Author: JoshRosen

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/hash.scala

@@ -63,7 +63,7 @@ case class Md5(child: Expression) extends UnaryExpression with ImplicitCastInput
 
   override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
     defineCodeGen(ctx, ev, c =>
-      s"UTF8String.fromString(org.apache.commons.codec.digest.DigestUtils.md5Hex($c))")
+      s"UTF8String.fromString(${classOf[DigestUtils].getName}.md5Hex($c))")
   }
 }
 
@@ -120,7 +120,7 @@ case class Sha2(left: Expression, right: Expression)
   }
 
   override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
-    val digestUtils = "org.apache.commons.codec.digest.DigestUtils"
+    val digestUtils = classOf[DigestUtils].getName
     nullSafeCodeGen(ctx, ev, (eval1, eval2) => {
       s"""
         if ($eval2 == 224) {
@@ -170,7 +170,7 @@ case class Sha1(child: Expression) extends UnaryExpression with ImplicitCastInpu
 
   override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
     defineCodeGen(ctx, ev, c =>
-      s"UTF8String.fromString(org.apache.commons.codec.digest.DigestUtils.sha1Hex($c))"
+      s"UTF8String.fromString(${classOf[DigestUtils].getName}.sha1Hex($c))"
     )
   }
 }

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringExpressions.scala

@@ -24,6 +24,8 @@ import java.util.regex.Pattern
 
 import scala.collection.mutable.ArrayBuffer
 
+import org.apache.commons.codec.binary.{Base64 => CommonsBase64}
+
 import org.apache.spark.sql.catalyst.InternalRow
 import org.apache.spark.sql.catalyst.analysis.TypeCheckResult
 import org.apache.spark.sql.catalyst.expressions.codegen._
@@ -1829,15 +1831,13 @@ case class Base64(child: Expression) extends UnaryExpression with ImplicitCastIn
   override def inputTypes: Seq[DataType] = Seq(BinaryType)
 
   protected override def nullSafeEval(bytes: Any): Any = {
-    UTF8String.fromBytes(
-      org.apache.commons.codec.binary.Base64.encodeBase64(
-        bytes.asInstanceOf[Array[Byte]]))
+    UTF8String.fromBytes(CommonsBase64.encodeBase64(bytes.asInstanceOf[Array[Byte]]))
   }
 
   override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
     nullSafeCodeGen(ctx, ev, (child) => {
       s"""${ev.value} = UTF8String.fromBytes(
-            org.apache.commons.codec.binary.Base64.encodeBase64($child));
+            ${classOf[CommonsBase64].getName}.encodeBase64($child));
        """})
   }
 }
@@ -1859,12 +1859,12 @@ case class UnBase64(child: Expression) extends UnaryExpression with ImplicitCast
   override def inputTypes: Seq[DataType] = Seq(StringType)
 
   protected override def nullSafeEval(string: Any): Any =
-    org.apache.commons.codec.binary.Base64.decodeBase64(string.asInstanceOf[UTF8String].toString)
+    CommonsBase64.decodeBase64(string.asInstanceOf[UTF8String].toString)
 
   override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
     nullSafeCodeGen(ctx, ev, (child) => {
       s"""
-         ${ev.value} = org.apache.commons.codec.binary.Base64.decodeBase64($child.toString());
+         ${ev.value} = ${classOf[CommonsBase64].getName}.decodeBase64($child.toString());
        """})
   }
 }