Add max/min eval functions #4333
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,38 @@ | ||
| /* | ||
| * Copyright OpenSearch Contributors | ||
| * SPDX-License-Identifier: Apache-2.0 | ||
| */ | ||
|
|
||
| package org.opensearch.sql.data.utils; | ||
|
|
||
| import java.util.Comparator; | ||
|
|
||
| /** Comparator for mixed-type values. */ | ||
| public class MixedTypeComparator implements Comparator<Object> { | ||
|
|
||
| public static final MixedTypeComparator INSTANCE = new MixedTypeComparator(); | ||
|
|
||
| private MixedTypeComparator() {} | ||
|
|
||
| @Override | ||
| public int compare(Object a, Object b) { | ||
| boolean aIsNumeric = isNumeric(a); | ||
| boolean bIsNumeric = isNumeric(b); | ||
|
|
||
| // For same types compare directly | ||
| if (aIsNumeric == bIsNumeric) { | ||
| if (aIsNumeric) { | ||
| return Double.compare(((Number) a).doubleValue(), ((Number) b).doubleValue()); | ||
| } else { | ||
| return Integer.compare(a.toString().compareTo(b.toString()), 0); | ||
| } | ||
| } | ||
| // For mixed types, strings are considered larger than numbers (non-numeric values are treated | ||
| // as strings) | ||
| return aIsNumeric ? -1 : 1; | ||
| } | ||
|
|
||
| private static boolean isNumeric(Object obj) { | ||
| return obj instanceof Number; | ||
|
Collaborator
There was a problem hiding this comment. Could you confirm whether comparison between "1" and "2" also considered as numerical comparison?
Contributor
Author
There was a problem hiding this comment. No they will be compared as strings so max("9", "21") will return "9" |
||
| } | ||
| } | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,67 @@ | ||
| /* | ||
| * Copyright OpenSearch Contributors | ||
| * SPDX-License-Identifier: Apache-2.0 | ||
| */ | ||
|
|
||
| package org.opensearch.sql.expression.function.udf.math; | ||
|
|
||
| import java.util.Arrays; | ||
| import java.util.List; | ||
| import java.util.Objects; | ||
| import org.apache.calcite.adapter.enumerable.NotNullImplementor; | ||
| import org.apache.calcite.adapter.enumerable.NullPolicy; | ||
| import org.apache.calcite.adapter.enumerable.RexToLixTranslator; | ||
| import org.apache.calcite.linq4j.tree.Expression; | ||
| import org.apache.calcite.linq4j.tree.Expressions; | ||
| import org.apache.calcite.rex.RexCall; | ||
| import org.apache.calcite.sql.type.SqlReturnTypeInference; | ||
| import org.apache.calcite.sql.type.SqlTypeName; | ||
| import org.opensearch.sql.data.utils.MixedTypeComparator; | ||
| import org.opensearch.sql.expression.function.ImplementorUDF; | ||
| import org.opensearch.sql.expression.function.UDFOperandMetadata; | ||
|
|
||
| /** | ||
| * MAX(value1, value2, ...) returns the maximum value from the arguments. For mixed types, strings | ||
| * have higher precedence than numbers. | ||
| */ | ||
| public class MaxFunction extends ImplementorUDF { | ||
|
|
||
| public MaxFunction() { | ||
| super(new MaxImplementor(), NullPolicy.ALL); | ||
| } | ||
|
|
||
| @Override | ||
| public SqlReturnTypeInference getReturnTypeInference() { | ||
| return opBinding -> opBinding.getTypeFactory().createSqlType(SqlTypeName.ANY); | ||
| } | ||
|
|
||
| @Override | ||
| public UDFOperandMetadata getOperandMetadata() { | ||
| return null; | ||
| } | ||
|
|
||
| public static class MaxImplementor implements NotNullImplementor { | ||
|
|
||
| @Override | ||
| public Expression implement( | ||
| RexToLixTranslator translator, RexCall call, List<Expression> translatedOperands) { | ||
| return Expressions.call( | ||
| MaxImplementor.class, "max", Expressions.newArrayInit(Object.class, translatedOperands)); | ||
| } | ||
|
|
||
| public static Object max(Object[] args) { | ||
| return findMax(args); | ||
| } | ||
|
|
||
| private static Object findMax(Object[] args) { | ||
| if (args == null) { | ||
| return null; | ||
| } | ||
|
|
||
| return Arrays.stream(args) | ||
| .filter(Objects::nonNull) | ||
| .max(MixedTypeComparator.INSTANCE) | ||
| .orElse(null); | ||
| } | ||
| } | ||
| } |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,67 @@ | ||
| /* | ||
| * Copyright OpenSearch Contributors | ||
| * SPDX-License-Identifier: Apache-2.0 | ||
| */ | ||
|
|
||
| package org.opensearch.sql.expression.function.udf.math; | ||
|
|
||
| import java.util.Arrays; | ||
| import java.util.List; | ||
| import java.util.Objects; | ||
| import org.apache.calcite.adapter.enumerable.NotNullImplementor; | ||
| import org.apache.calcite.adapter.enumerable.NullPolicy; | ||
| import org.apache.calcite.adapter.enumerable.RexToLixTranslator; | ||
| import org.apache.calcite.linq4j.tree.Expression; | ||
| import org.apache.calcite.linq4j.tree.Expressions; | ||
| import org.apache.calcite.rex.RexCall; | ||
| import org.apache.calcite.sql.type.SqlReturnTypeInference; | ||
| import org.apache.calcite.sql.type.SqlTypeName; | ||
| import org.opensearch.sql.data.utils.MixedTypeComparator; | ||
| import org.opensearch.sql.expression.function.ImplementorUDF; | ||
| import org.opensearch.sql.expression.function.UDFOperandMetadata; | ||
|
|
||
| /** | ||
| * MIN(value1, value2, ...) returns the minimum value from the arguments. For mixed types, numbers | ||
| * have higher precedence than strings. | ||
| */ | ||
| public class MinFunction extends ImplementorUDF { | ||
|
|
||
| public MinFunction() { | ||
| super(new MinImplementor(), NullPolicy.ALL); | ||
| } | ||
|
|
||
| @Override | ||
| public SqlReturnTypeInference getReturnTypeInference() { | ||
| return opBinding -> opBinding.getTypeFactory().createSqlType(SqlTypeName.ANY); | ||
| } | ||
|
|
||
| @Override | ||
| public UDFOperandMetadata getOperandMetadata() { | ||
| return null; | ||
| } | ||
|
|
||
| public static class MinImplementor implements NotNullImplementor { | ||
|
|
||
| @Override | ||
| public Expression implement( | ||
| RexToLixTranslator translator, RexCall call, List<Expression> translatedOperands) { | ||
| return Expressions.call( | ||
| MinImplementor.class, "min", Expressions.newArrayInit(Object.class, translatedOperands)); | ||
| } | ||
|
|
||
| public static Object min(Object[] args) { | ||
| return findMin(args); | ||
| } | ||
|
|
||
| private static Object findMin(Object[] args) { | ||
| if (args == null) { | ||
| return null; | ||
| } | ||
|
|
||
| return Arrays.stream(args) | ||
| .filter(Objects::nonNull) | ||
| .min(MixedTypeComparator.INSTANCE) | ||
| .orElse(null); | ||
| } | ||
| } | ||
| } |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,48 @@ | ||
| /* | ||
| * Copyright OpenSearch Contributors | ||
| * SPDX-License-Identifier: Apache-2.0 | ||
| */ | ||
|
|
||
| package org.opensearch.sql.data.utils; | ||
|
|
||
| import static org.junit.jupiter.api.Assertions.assertEquals; | ||
|
|
||
| import java.math.BigDecimal; | ||
| import org.junit.jupiter.api.Test; | ||
|
|
||
| class MixedTypeComparatorTest { | ||
|
|
||
| private final MixedTypeComparator comparator = MixedTypeComparator.INSTANCE; | ||
|
|
||
| @Test | ||
| public void testNumericComparison() { | ||
| assertEquals(-1, comparator.compare(1, 2)); | ||
| assertEquals(1, comparator.compare(2, 1)); | ||
| assertEquals(0, comparator.compare(5, 5)); | ||
|
|
||
| // Different numeric types | ||
| assertEquals(-1, comparator.compare(1, 2.5)); | ||
| assertEquals(1, comparator.compare(3.14, 2)); | ||
| assertEquals(0, comparator.compare(4, 4.0)); | ||
| assertEquals(-1, comparator.compare(10L, new BigDecimal("20"))); | ||
| } | ||
|
|
||
| @Test | ||
| public void testStringComparison() { | ||
| assertEquals(-1, comparator.compare("apple", "banana")); | ||
| assertEquals(1, comparator.compare("zebra", "apple")); | ||
| assertEquals(0, comparator.compare("test", "test")); | ||
| assertEquals(-1, comparator.compare("ABC", "abc")); // | ||
| assertEquals(1, comparator.compare("hello", "HELLO")); | ||
| } | ||
|
|
||
| @Test | ||
| public void testMixedTypeComparison() { | ||
| assertEquals(-1, comparator.compare(42, "apple")); | ||
| assertEquals(1, comparator.compare("apple", 42)); | ||
| assertEquals(-1, comparator.compare(3.14, "hello")); | ||
| assertEquals(1, comparator.compare("world", 100L)); | ||
| assertEquals(-1, comparator.compare(0, "0")); | ||
| assertEquals(1, comparator.compare("123", 456)); | ||
| } | ||
| } |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,109 @@ | ||
| ====================== | ||
| Statistical Functions | ||
| ====================== | ||
|
|
||
| .. rubric:: Table of contents | ||
|
|
||
| .. contents:: | ||
| :local: | ||
| :depth: 1 | ||
|
|
||
|
|
||
| MAX | ||
| --- | ||
|
|
||
| Description | ||
| >>>>>>>>>>> | ||
|
|
||
| Usage: max(x, y, ...) returns the maximum value from all provided arguments. Strings are treated as greater than numbers, so if provided both strings and numbers, it will return the maximum string value (lexicographically ordered) | ||
|
|
||
| Note: This function is only available in the eval command context and requires Calcite engine to be enabled. | ||
|
|
||
| Argument type: Variable number of INTEGER/LONG/FLOAT/DOUBLE/STRING arguments | ||
|
|
||
| Return type: Type of the selected argument | ||
|
|
||
| Example:: | ||
|
|
||
| os> source=accounts | eval max_val = MAX(age, 30) | fields age, max_val | ||
| fetched rows / total rows = 4/4 | ||
| +-----+---------+ | ||
| | age | max_val | | ||
| |-----+---------| | ||
| | 32 | 32 | | ||
| | 36 | 36 | | ||
| | 28 | 30 | | ||
| | 33 | 33 | | ||
| +-----+---------+ | ||
|
|
||
| os> source=accounts | eval result = MAX(firstname, 'John') | fields firstname, result | ||
| fetched rows / total rows = 4/4 | ||
| +-----------+---------+ | ||
| | firstname | result | | ||
| |-----------+---------| | ||
| | Amber | John | | ||
| | Hattie | John | | ||
| | Nanette | Nanette | | ||
| | Dale | John | | ||
| +-----------+---------+ | ||
|
|
||
| os> source=accounts | eval result = MAX(age, 35, 'John', firstname) | fields age, firstname, result | ||
| fetched rows / total rows = 4/4 | ||
| +-----+-----------+---------+ | ||
| | age | firstname | result | | ||
| |-----+-----------+---------| | ||
| | 32 | Amber | John | | ||
| | 36 | Hattie | John | | ||
| | 28 | Nanette | Nanette | | ||
| | 33 | Dale | John | | ||
| +-----+-----------+---------+ | ||
|
|
||
|
|
||
| MIN | ||
| --- | ||
|
|
||
| Description | ||
| >>>>>>>>>>> | ||
|
|
||
| Usage: min(x, y, ...) returns the minimum value from all provided arguments. Strings are treated as greater than numbers, so if provided both strings and numbers, it will return the minimum numeric value. | ||
|
|
||
| Note: This function is only available in the eval command context and requires Calcite engine to be enabled. | ||
|
|
||
| Argument type: Variable number of INTEGER/LONG/FLOAT/DOUBLE/STRING arguments | ||
|
|
||
| Return type: Type of the selected argument | ||
|
|
||
| Example:: | ||
|
|
||
| os> source=accounts | eval min_val = MIN(age, 30) | fields age, min_val | ||
| fetched rows / total rows = 4/4 | ||
| +-----+---------+ | ||
| | age | min_val | | ||
| |-----+---------| | ||
| | 32 | 30 | | ||
| | 36 | 30 | | ||
| | 28 | 28 | | ||
| | 33 | 30 | | ||
| +-----+---------+ | ||
|
|
||
| os> source=accounts | eval result = MIN(firstname, 'John') | fields firstname, result | ||
| fetched rows / total rows = 4/4 | ||
| +-----------+--------+ | ||
| | firstname | result | | ||
| |-----------+--------| | ||
| | Amber | Amber | | ||
| | Hattie | Hattie | | ||
| | Nanette | John | | ||
| | Dale | Dale | | ||
| +-----------+--------+ | ||
|
|
||
| os> source=accounts | eval result = MIN(age, 35, firstname) | fields age, firstname, result | ||
| fetched rows / total rows = 4/4 | ||
| +-----+-----------+--------+ | ||
| | age | firstname | result | | ||
| |-----+-----------+--------| | ||
| | 32 | Amber | 32 | | ||
| | 36 | Hattie | 35 | | ||
| | 28 | Nanette | 28 | | ||
| | 33 | Dale | 33 | | ||
| +-----+-----------+--------+ |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
what does this Integer.compare with 0 meaning?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
It will normalize it so if the string comparison returns a negative it will make it -1 and if it returns a positive it will be 1. Don't think that is necessary, can remove and just leave the string comparison