[SPARK-30292][SQL][FOLLOWUP] ansi cast from strings to integral numbers (byte/short/int/long) should fail with fraction

### What changes were proposed in this pull request?

This is a followup of #26933

Fraction string like "1.23" is definitely not a valid integral format and we should fail to do the cast under the ANSI mode.

### Why are the changes needed?

correct the ANSI cast behavior from string to integral

### Does this PR introduce any user-facing change?

Yes under ANSI mode, but ANSI mode is off by default.

### How was this patch tested?

new test

Closes #27957 from cloud-fan/ansi.

Authored-by: Wenchen Fan <[email protected]>
Signed-off-by: Takeshi Yamamuro <[email protected]>

Author: cloud-fan

common/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java

@@ -1105,6 +1105,10 @@ public static class IntWrapper implements Serializable {
    * @return true if the parsing was successful else false
    */
   public boolean toLong(LongWrapper toLongResult) {
+    return toLong(toLongResult, true);
+  }
+
+  private boolean toLong(LongWrapper toLongResult, boolean allowDecimal) {
     int offset = 0;
     while (offset < this.numBytes && getByte(offset) <= ' ') offset++;
     if (offset == this.numBytes) return false;
@@ -1129,7 +1133,7 @@ public boolean toLong(LongWrapper toLongResult) {
     while (offset <= end) {
       b = getByte(offset);
       offset++;
-      if (b == separator) {
+      if (b == separator && allowDecimal) {
         // We allow decimals and will return a truncated integral in that case.
         // Therefore we won't throw an exception here (checking the fractional
         // part happens below.)
@@ -1198,6 +1202,10 @@ public boolean toLong(LongWrapper toLongResult) {
    * @return true if the parsing was successful else false
    */
   public boolean toInt(IntWrapper intWrapper) {
+    return toInt(intWrapper, true);
+  }
+
+  private boolean toInt(IntWrapper intWrapper, boolean allowDecimal) {
     int offset = 0;
     while (offset < this.numBytes && getByte(offset) <= ' ') offset++;
     if (offset == this.numBytes) return false;
@@ -1222,7 +1230,7 @@ public boolean toInt(IntWrapper intWrapper) {
     while (offset <= end) {
       b = getByte(offset);
       offset++;
-      if (b == separator) {
+      if (b == separator && allowDecimal) {
         // We allow decimals and will return a truncated integral in that case.
         // Therefore we won't throw an exception here (checking the fractional
         // part happens below.)
@@ -1276,9 +1284,7 @@ public boolean toShort(IntWrapper intWrapper) {
     if (toInt(intWrapper)) {
       int intValue = intWrapper.value;
       short result = (short) intValue;
-      if (result == intValue) {
-        return true;
-      }
+      return result == intValue;
     }
     return false;
   }
@@ -1287,9 +1293,7 @@ public boolean toByte(IntWrapper intWrapper) {
     if (toInt(intWrapper)) {
       int intValue = intWrapper.value;
       byte result = (byte) intValue;
-      if (result == intValue) {
-        return true;
-      }
+      return result == intValue;
     }
     return false;
   }
@@ -1302,7 +1306,7 @@ public boolean toByte(IntWrapper intWrapper) {
    */
   public long toLongExact() {
     LongWrapper result = new LongWrapper();
-    if (toLong(result)) {
+    if (toLong(result, false)) {
       return result.value;
     }
     throw new NumberFormatException("invalid input syntax for type numeric: " + this);
@@ -1316,7 +1320,7 @@ public long toLongExact() {
    */
   public int toIntExact() {
     IntWrapper result = new IntWrapper();
-    if (toInt(result)) {
+    if (toInt(result, false)) {
       return result.value;
     }
     throw new NumberFormatException("invalid input syntax for type numeric: " + this);

sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/CastSuite.scala

@@ -1287,6 +1287,8 @@ class AnsiCastSuite extends CastSuiteBase {
         cast("123-string", dataType), "invalid input")
       checkExceptionInExpression[NumberFormatException](
         cast("2020-07-19", dataType), "invalid input")
+      checkExceptionInExpression[NumberFormatException](
+        cast("1.23", dataType), "invalid input")
     }
 
     Seq(DoubleType, FloatType, DecimalType.USER_DEFAULT).foreach { dataType =>