[SPARK-38225][SQL] Adjust input format of function to_binary

### What changes were proposed in this pull request?
Adjust input `format` of function `to_binary`:
- gracefully fail for the non-string `format` parameter
- remove arguable `base2` format support

### Why are the changes needed?
Currently, function to_binary doesn't deal with the non-string `format` parameter properly.
For example, `spark.sql("select to_binary('abc', 1)")` raises casting error, rather than hint that encoding format is unsupported.

In addition, `base2` format is arguable as discussed [here](#35415 (comment)). We may exclude it following what Snowflake [to_binary](https://docs.snowflake.com/en/sql-reference/functions/to_binary.html) does for now.

### Does this PR introduce _any_ user-facing change?
Yes.

- Better error messages for non-string `format` parameter. For example:

From:
```
scala> spark.sql("select to_binary('abc', 1)")
org.apache.spark.sql.AnalysisException: class java.lang.Integer cannot be cast to class org.apache.spark.unsafe.types.UTF8String (java.lang.Integer is in module java.base of loader 'bootstrap'; org.apache.spark.unsafe.types.UTF8String is in unnamed module of loader 'app'); line 1 pos 7
```

To:
```
scala> spark.sql("select to_binary('abc', 1)")
org.apache.spark.sql.AnalysisException: cannot resolve 'to_binary('abc', 1)' due to data type mismatch: Unsupported encoding format: Some(1). The format has to be a case-insensitive string literal of 'hex', 'utf-8', 'base2', or 'base64'; line 1 pos 7;
```

- Removed `base2` format support
```
scala> spark.sql("select to_binary('abc', 'base2')").show()
org.apache.spark.sql.AnalysisException: cannot resolve 'to_binary('abc', 'base2')' due to data type mismatch: Unsupported encoding format: Some(base2). The format has to be a case-insensitive string literal of 'hex', 'utf-8', or 'base64'; line 1 pos 7;
```

### How was this patch tested?
Unit test.

Closes #35533 from xinrong-databricks/to_binary_followup.

Authored-by: Xinrong Meng <[email protected]>
Signed-off-by: Wenchen Fan <[email protected]>

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

@@ -2545,7 +2545,7 @@ case class Encode(value: Expression, charset: Expression)
 @ExpressionDescription(
   usage = """
     _FUNC_(str[, fmt]) - Converts the input `str` to a binary value based on the supplied `fmt`.
-      `fmt` can be a case-insensitive string literal of "hex", "utf-8", "base2", or "base64".
+      `fmt` can be a case-insensitive string literal of "hex", "utf-8", or "base64".
       By default, the binary format for conversion is "hex" if `fmt` is omitted.
       The function returns NULL if at least one of the input parameters is NULL.
   """,
@@ -2562,15 +2562,14 @@ case class ToBinary(expr: Expression, format: Option[Expression], child: Express
 
   def this(expr: Expression, format: Expression) = this(expr, Option(format),
     format match {
-      case lit if lit.foldable =>
+      case lit if (lit.foldable && Seq(StringType, NullType).contains(lit.dataType)) =>
         val value = lit.eval()
         if (value == null) Literal(null, BinaryType)
         else {
           value.asInstanceOf[UTF8String].toString.toLowerCase(Locale.ROOT) match {
             case "hex" => Unhex(expr)
             case "utf-8" => Encode(expr, Literal("UTF-8"))
             case "base64" => UnBase64(expr)
-            case "base2" => Cast(expr, BinaryType)
             case _ => lit
           }
         }
@@ -2589,10 +2588,11 @@ case class ToBinary(expr: Expression, format: Option[Expression], child: Express
 
   override def checkInputDataTypes(): TypeCheckResult = {
     def checkFormat(lit: Expression) = {
-      if (lit.foldable) {
+      if (lit.foldable && Seq(StringType, NullType).contains(lit.dataType)) {
         val value = lit.eval()
-        value == null || Seq("hex", "utf-8", "base64", "base2").contains(
-          value.asInstanceOf[UTF8String].toString.toLowerCase(Locale.ROOT))
+        value == null ||
+          Seq("hex", "utf-8", "base64").contains(
+            value.asInstanceOf[UTF8String].toString.toLowerCase(Locale.ROOT))
       } else false
     }
 
@@ -2601,7 +2601,7 @@ case class ToBinary(expr: Expression, format: Option[Expression], child: Express
     } else {
       TypeCheckResult.TypeCheckFailure(
         s"Unsupported encoding format: $format. The format has to be " +
-          s"a case-insensitive string literal of 'hex', 'utf-8', 'base2', or 'base64'")
+          s"a case-insensitive string literal of 'hex', 'utf-8', or 'base64'")
     }
   }
 

sql/core/src/test/resources/sql-tests/inputs/string-functions.sql

@@ -140,7 +140,6 @@ select to_number('00,454.8-', '00,000.9-');
 select to_binary('abc');
 select to_binary('abc', 'utf-8');
 select to_binary('abc', 'base64');
-select to_binary('abc', 'base2');
 select to_binary('abc', 'hex');
 select to_binary('abc', concat('utf', '-8'));
 select to_binary('abc', concat('base', '64'));
@@ -150,4 +149,6 @@ select to_binary('abc', null);
 select to_binary(null, 'utf-8');
 select to_binary(null, null);
 select to_binary(null, cast(null as string));
+select to_binary(null, cast(null as int));
 select to_binary('abc', 'invalidFormat');
+select to_binary('abc', 1);

sql/core/src/test/resources/sql-tests/results/ansi/string-functions.sql.out

@@ -1,5 +1,5 @@
 -- Automatically generated by SQLQueryTestSuite
--- Number of queries: 116
+-- Number of queries: 117
 
 
 -- !query
@@ -850,14 +850,6 @@ struct<to_binary(abc, base64):binary>
 i�
 
 
--- !query
-select to_binary('abc', 'base2')
--- !query schema
-struct<to_binary(abc, base2):binary>
--- !query output
-abc
-
-
 -- !query
 select to_binary('abc', 'hex')
 -- !query schema
@@ -930,10 +922,28 @@ struct<to_binary(NULL, CAST(NULL AS STRING)):binary>
 NULL
 
 
+-- !query
+select to_binary(null, cast(null as int))
+-- !query schema
+struct<>
+-- !query output
+org.apache.spark.sql.AnalysisException
+cannot resolve 'to_binary(NULL, CAST(NULL AS INT))' due to data type mismatch: Unsupported encoding format: Some(ansi_cast(null as int)). The format has to be a case-insensitive string literal of 'hex', 'utf-8', or 'base64'; line 1 pos 7
+
+
 -- !query
 select to_binary('abc', 'invalidFormat')
 -- !query schema
 struct<>
 -- !query output
 org.apache.spark.sql.AnalysisException
-cannot resolve 'to_binary('abc', 'invalidFormat')' due to data type mismatch: Unsupported encoding format: Some(invalidFormat). The format has to be a case-insensitive string literal of 'hex', 'utf-8', 'base2', or 'base64'; line 1 pos 7
+cannot resolve 'to_binary('abc', 'invalidFormat')' due to data type mismatch: Unsupported encoding format: Some(invalidFormat). The format has to be a case-insensitive string literal of 'hex', 'utf-8', or 'base64'; line 1 pos 7
+
+
+-- !query
+select to_binary('abc', 1)
+-- !query schema
+struct<>
+-- !query output
+org.apache.spark.sql.AnalysisException
+cannot resolve 'to_binary('abc', 1)' due to data type mismatch: Unsupported encoding format: Some(1). The format has to be a case-insensitive string literal of 'hex', 'utf-8', or 'base64'; line 1 pos 7

sql/core/src/test/resources/sql-tests/results/string-functions.sql.out

@@ -1,5 +1,5 @@
 -- Automatically generated by SQLQueryTestSuite
--- Number of queries: 116
+-- Number of queries: 117
 
 
 -- !query
@@ -846,14 +846,6 @@ struct<to_binary(abc, base64):binary>
 i�
 
 
--- !query
-select to_binary('abc', 'base2')
--- !query schema
-struct<to_binary(abc, base2):binary>
--- !query output
-abc
-
-
 -- !query
 select to_binary('abc', 'hex')
 -- !query schema
@@ -926,10 +918,28 @@ struct<to_binary(NULL, CAST(NULL AS STRING)):binary>
 NULL
 
 
+-- !query
+select to_binary(null, cast(null as int))
+-- !query schema
+struct<>
+-- !query output
+org.apache.spark.sql.AnalysisException
+cannot resolve 'to_binary(NULL, CAST(NULL AS INT))' due to data type mismatch: Unsupported encoding format: Some(cast(null as int)). The format has to be a case-insensitive string literal of 'hex', 'utf-8', or 'base64'; line 1 pos 7
+
+
 -- !query
 select to_binary('abc', 'invalidFormat')
 -- !query schema
 struct<>
 -- !query output
 org.apache.spark.sql.AnalysisException
-cannot resolve 'to_binary('abc', 'invalidFormat')' due to data type mismatch: Unsupported encoding format: Some(invalidFormat). The format has to be a case-insensitive string literal of 'hex', 'utf-8', 'base2', or 'base64'; line 1 pos 7
+cannot resolve 'to_binary('abc', 'invalidFormat')' due to data type mismatch: Unsupported encoding format: Some(invalidFormat). The format has to be a case-insensitive string literal of 'hex', 'utf-8', or 'base64'; line 1 pos 7
+
+
+-- !query
+select to_binary('abc', 1)
+-- !query schema
+struct<>
+-- !query output
+org.apache.spark.sql.AnalysisException
+cannot resolve 'to_binary('abc', 1)' due to data type mismatch: Unsupported encoding format: Some(1). The format has to be a case-insensitive string literal of 'hex', 'utf-8', or 'base64'; line 1 pos 7