Backport work around

DEVELOPER_GUIDE.rst

@@ -405,7 +405,7 @@ Sample test class:
 Doctest
 >>>>>>>
 
-Python doctest library makes our document executable which keeps it up-to-date to source code. The doc generator aforementioned served as scaffolding and generated many docs in short time. Now the examples inside is changed to doctest gradually. For more details please read `Doctest <./dev/Doctest.md>`_.
+Python doctest library makes our document executable which keeps it up-to-date to source code. The doc generator aforementioned served as scaffolding and generated many docs in short time. Now the examples inside is changed to doctest gradually. For more details please read `testing-doctest <./docs/dev/testing-doctest.md>`_.
 
 
 Backports

benchmarks/build.gradle

@@ -20,4 +20,13 @@ dependencies {
     annotationProcessor group: 'org.openjdk.jmh', name: 'jmh-generator-annprocess', version: '1.36'
 }
 
+spotless {
+    java {
+        target fileTree('.') {
+            include '**/*.java'
+            exclude '**/jmh_generated/**'
+        }
+    }
+}
+
 compileJava.options.compilerArgs.addAll(["-processor", "org.openjdk.jmh.generators.BenchmarkProcessor"])

benchmarks/src/jmh/java/org/opensearch/sql/expression/operator/predicate/PatternsWindowFunctionBenchmark.java

@@ -0,0 +1,98 @@
+/*
+ * Copyright OpenSearch Contributors
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+package org.opensearch.sql.expression.operator.predicate;
+
+import static org.opensearch.sql.data.model.ExprTupleValue.fromExprValueMap;
+import static org.opensearch.sql.data.type.ExprCoreType.STRING;
+
+import com.google.common.collect.ImmutableList;
+import com.google.common.collect.ImmutableMap;
+import com.google.common.collect.Iterators;
+import com.google.common.collect.PeekingIterator;
+import java.util.concurrent.TimeUnit;
+import org.openjdk.jmh.annotations.Benchmark;
+import org.openjdk.jmh.annotations.BenchmarkMode;
+import org.openjdk.jmh.annotations.Fork;
+import org.openjdk.jmh.annotations.Measurement;
+import org.openjdk.jmh.annotations.Mode;
+import org.openjdk.jmh.annotations.OutputTimeUnit;
+import org.openjdk.jmh.annotations.Scope;
+import org.openjdk.jmh.annotations.State;
+import org.openjdk.jmh.annotations.Warmup;
+import org.opensearch.sql.common.patterns.BrainLogParser;
+import org.opensearch.sql.data.model.ExprStringValue;
+import org.opensearch.sql.data.model.ExprValue;
+import org.opensearch.sql.expression.DSL;
+import org.opensearch.sql.expression.Expression;
+import org.opensearch.sql.expression.NamedArgumentExpression;
+import org.opensearch.sql.expression.ReferenceExpression;
+import org.opensearch.sql.expression.window.WindowDefinition;
+import org.opensearch.sql.expression.window.frame.BufferPatternRowsWindowFrame;
+import org.opensearch.sql.expression.window.frame.CurrentRowWindowFrame;
+import org.opensearch.sql.expression.window.frame.WindowFrame;
+
+@Warmup(iterations = 1)
+@Measurement(iterations = 3)
+@BenchmarkMode(Mode.AverageTime)
+@OutputTimeUnit(TimeUnit.MILLISECONDS)
+@State(Scope.Thread)
+@Fork(value = 1)
+public class PatternsWindowFunctionBenchmark {
+
+  private static final String TEST_MESSAGE_1 =
+      "12.132.31.17 - - [2018-07-22T05:36:25.812Z] \\\"GET /opensearch HTTP/1.1\\\" 200 9797"
+          + " \\\"-\\\" \\\"Mozilla/5.0 (X11; Linux x86_64; rv:6.0a1) Gecko/20110421"
+          + " Firefox/6.0a1\\\"";
+  private static final String TEST_MESSAGE_2 =
+      "129.138.185.193 - - [2018-07-22T05:39:39.668Z] \\\"GET /opensearch HTTP/1.1\\\" 404 9920"
+          + " \\\"-\\\" \\\"Mozilla/5.0 (X11; Linux x86_64; rv:6.0a1) Gecko/20110421"
+          + " Firefox/6.0a1\\\"";
+  private static final String TEST_MESSAGE_3 =
+      "240.58.187.246 - - [2018-07-22T06:02:46.006Z] \\\"GET /opensearch HTTP/1.1\\\" 500 6936"
+          + " \\\"-\\\" \\\"Mozilla/5.0 (X11; Linux i686) AppleWebKit/534.24 (KHTML, like Gecko)"
+          + " Chrome/11.0.696.50 Safari/534.24\\\"";
+
+  private PeekingIterator<ExprValue> tuples;
+  private final BufferPatternRowsWindowFrame bufferWindowFrame =
+      new BufferPatternRowsWindowFrame(
+          new WindowDefinition(ImmutableList.of(), ImmutableList.of()),
+          new BrainLogParser(),
+          new NamedArgumentExpression("message", new ReferenceExpression("message", STRING)));
+
+  @Benchmark
+  public void testSimplePattern() {
+    CurrentRowWindowFrame windowFrame =
+        new CurrentRowWindowFrame(new WindowDefinition(ImmutableList.of(), ImmutableList.of()));
+
+    run(windowFrame, DSL.simple_pattern(DSL.ref("message", STRING)));
+  }
+
+  @Benchmark
+  public void testBrain() {
+    BufferPatternRowsWindowFrame windowFrame =
+        new BufferPatternRowsWindowFrame(
+            new WindowDefinition(ImmutableList.of(), ImmutableList.of()),
+            new BrainLogParser(),
+            new NamedArgumentExpression("message", new ReferenceExpression("message", STRING)));
+
+    run(windowFrame, DSL.brain(DSL.ref("message", STRING)));
+  }
+
+  private void run(WindowFrame windowFrame, Expression windowFunction) {
+    tuples =
+        Iterators.peekingIterator(
+            Iterators.forArray(
+                tuple(TEST_MESSAGE_1), tuple(TEST_MESSAGE_2), tuple(TEST_MESSAGE_3)));
+    while (tuples.hasNext() || windowFrame.hasNext()) {
+      windowFrame.load(tuples);
+      windowFunction.valueOf(windowFrame);
+    }
+  }
+
+  private ExprValue tuple(String message) {
+    return fromExprValueMap(ImmutableMap.of("message", new ExprStringValue(message)));
+  }
+}

build.gradle

@@ -50,7 +50,16 @@ buildscript {
             return "https://github.com/prometheus/prometheus/releases/download/v${prometheus_binary_version}/prometheus-${prometheus_binary_version}."+ getOSFamilyType() + "-" + getArchType() + ".tar.gz"
         }
         aws_java_sdk_version = "1.12.651"
-        guava_version = "32.1.3-jre"
+        guava_version = "33.3.0-jre"
+        resilience4j_version = "1.5.0"
+        hamcrest_version = "2.1"
+        mockito_version = "5.7.0"
+        commons_io_version = "2.14.0"
+        commons_text_version = "1.10.0"
+        commons_lang3_version = "3.12.0"
+        // enforce 1.13, https://www.whitesourcesoftware.com/vulnerability-database/WS-2019-0379
+        commons_codec_version = "1.13"
+        commons_logging_version = "1.2"
     }
 
     repositories {
@@ -122,6 +131,23 @@ allprojects {
         resolutionStrategy.force "org.jetbrains.kotlin:kotlin-stdlib-jdk7:1.9.0"
         resolutionStrategy.force "org.jetbrains.kotlin:kotlin-stdlib-jdk8:1.9.0"
         resolutionStrategy.force "net.bytebuddy:byte-buddy:1.14.9"
+        resolutionStrategy.force "org.apache.httpcomponents.client5:httpclient5:5.4.4"
+        resolutionStrategy.force "org.apache.httpcomponents.core5:httpcore5:5.3.4"
+        resolutionStrategy.force "org.apache.httpcomponents.core5:httpcore5-h2:5.3.4"
+        resolutionStrategy.force "com.fasterxml.jackson.core:jackson-annotations:2.18.2"
+        resolutionStrategy.force "com.fasterxml.jackson.core:jackson-core:2.18.2"
+        resolutionStrategy.force "com.fasterxml.jackson.core:jackson-databind:2.18.2"
+        resolutionStrategy.force "com.fasterxml.jackson.dataformat:jackson-dataformat-yaml:2.18.2"
+        resolutionStrategy.force "com.fasterxml.jackson.dataformat:jackson-dataformat-smile:2.18.2"
+        resolutionStrategy.force "com.fasterxml.jackson.dataformat:jackson-dataformat-cbor:2.18.2"
+        resolutionStrategy.force 'com.google.protobuf:protobuf-java:3.25.5'
+        resolutionStrategy.force 'org.locationtech.jts:jts-core:1.19.0'
+        resolutionStrategy.force 'com.google.errorprone:error_prone_annotations:2.28.0'
+        resolutionStrategy.force 'org.checkerframework:checker-qual:3.43.0'
+        resolutionStrategy.force 'org.apache.commons:commons-lang3:3.13.0'
+        resolutionStrategy.force 'org.apache.commons:commons-text:1.11.0'
+        resolutionStrategy.force 'commons-io:commons-io:2.15.0'
+        resolutionStrategy.force 'org.yaml:snakeyaml:2.2'
     }
 }
 

common/src/main/java/org/opensearch/sql/common/grok/GrokCompiler.java

@@ -18,6 +18,7 @@
 import java.time.ZoneId;
 import java.time.ZoneOffset;
 import java.util.HashMap;
+import java.util.Locale;
 import java.util.Map;
 import java.util.Objects;
 import java.util.Set;
@@ -174,9 +175,10 @@ public Grok compile(final String pattern, ZoneId defaultTimeZone, boolean namedO
             throw new IllegalArgumentException(
                 format("No definition for key '%s' found, aborting", group.get("pattern")));
           }
-          String replacement = String.format("(?<name%d>%s)", index, definitionOfPattern);
+          String replacement =
+              String.format(Locale.ROOT, "(?<name%d>%s)", index, definitionOfPattern);
           if (namedOnly && group.get("subname") == null) {
-            replacement = String.format("(?:%s)", definitionOfPattern);
+            replacement = String.format(Locale.ROOT, "(?:%s)", definitionOfPattern);
           }
           namedRegexCollection.put(
               "name" + index,