-
Notifications
You must be signed in to change notification settings - Fork 24.9k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
EQL: Add Substring function with Python semantics (#53688)
Does not reuse substring from SQL due to the difference in semantics and the accepted arguments. Currently it is missing full integration tests as, due to the usage of scripting, requires an actual integration test against a proper cluster (and likely its own QA project).
- Loading branch information
Showing
22 changed files
with
704 additions
and
69 deletions.
There are no files selected for viewing
This file contains 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 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 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 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
50 changes: 50 additions & 0 deletions
50
.../main/java/org/elasticsearch/xpack/eql/expression/function/scalar/string/StringUtils.java
This file contains 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 +1,50 @@ | ||
| /* | ||
| * Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one | ||
| * or more contributor license agreements. Licensed under the Elastic License; | ||
| * you may not use this file except in compliance with the Elastic License. | ||
| */ | ||
|
|
||
| package org.elasticsearch.xpack.eql.expression.function.scalar.string; | ||
|
|
||
| import org.elasticsearch.common.Strings; | ||
|
|
||
| import static org.elasticsearch.common.Strings.hasLength; | ||
|
|
||
| final class StringUtils { | ||
|
|
||
| private StringUtils() {} | ||
|
|
||
| /** | ||
| * Returns a substring using the Python slice semantics, meaning | ||
| * start and end can be negative | ||
| */ | ||
| static String substringSlice(String string, int start, int end) { | ||
| if (hasLength(string) == false) { | ||
| return string; | ||
| } | ||
|
|
||
| int length = string.length(); | ||
|
|
||
| // handle first negative values | ||
| if (start < 0) { | ||
| start += length; | ||
| } | ||
| if (start < 0) { | ||
| start = 0; | ||
| } | ||
| if (end < 0) { | ||
| end += length; | ||
| } | ||
| if (end < 0) { | ||
| end = 0; | ||
| } else if (end > length) { | ||
| end = length; | ||
| } | ||
|
|
||
| if (start >= end) { | ||
| return org.elasticsearch.xpack.ql.util.StringUtils.EMPTY; | ||
| } | ||
|
|
||
| return Strings.substring(string, start, end); | ||
| } | ||
| } |
129 changes: 129 additions & 0 deletions
129
...rc/main/java/org/elasticsearch/xpack/eql/expression/function/scalar/string/Substring.java
This file contains 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 +1,129 @@ | ||
| /* | ||
| * Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one | ||
| * or more contributor license agreements. Licensed under the Elastic License; | ||
| * you may not use this file except in compliance with the Elastic License. | ||
| */ | ||
|
|
||
| package org.elasticsearch.xpack.eql.expression.function.scalar.string; | ||
|
|
||
| import org.elasticsearch.xpack.ql.expression.Expression; | ||
| import org.elasticsearch.xpack.ql.expression.Expressions; | ||
| import org.elasticsearch.xpack.ql.expression.Expressions.ParamOrdinal; | ||
| import org.elasticsearch.xpack.ql.expression.FieldAttribute; | ||
| import org.elasticsearch.xpack.ql.expression.Literal; | ||
| import org.elasticsearch.xpack.ql.expression.function.OptionalArgument; | ||
| import org.elasticsearch.xpack.ql.expression.function.scalar.ScalarFunction; | ||
| import org.elasticsearch.xpack.ql.expression.gen.pipeline.Pipe; | ||
| import org.elasticsearch.xpack.ql.expression.gen.script.ScriptTemplate; | ||
| import org.elasticsearch.xpack.ql.tree.NodeInfo; | ||
| import org.elasticsearch.xpack.ql.tree.Source; | ||
| import org.elasticsearch.xpack.ql.type.DataType; | ||
| import org.elasticsearch.xpack.ql.type.DataTypes; | ||
|
|
||
| import java.util.Arrays; | ||
| import java.util.List; | ||
| import java.util.Locale; | ||
|
|
||
| import static java.lang.String.format; | ||
| import static org.elasticsearch.xpack.eql.expression.function.scalar.string.SubstringFunctionProcessor.doProcess; | ||
| import static org.elasticsearch.xpack.ql.expression.TypeResolutions.isInteger; | ||
| import static org.elasticsearch.xpack.ql.expression.TypeResolutions.isStringAndExact; | ||
| import static org.elasticsearch.xpack.ql.expression.gen.script.ParamsBuilder.paramsBuilder; | ||
|
|
||
| /** | ||
| * EQL specific substring function - similar to the one in Python. | ||
| * Note this is different than the one in SQL. | ||
| */ | ||
| public class Substring extends ScalarFunction implements OptionalArgument { | ||
|
|
||
| private final Expression source, start, end; | ||
|
|
||
| public Substring(Source source, Expression src, Expression start, Expression end) { | ||
| super(source, Arrays.asList(src, start, end != null ? end : new Literal(source, null, DataTypes.NULL))); | ||
| this.source = src; | ||
| this.start = start; | ||
| this.end = arguments().get(2); | ||
| } | ||
|
|
||
| @Override | ||
| protected TypeResolution resolveType() { | ||
| if (!childrenResolved()) { | ||
| return new TypeResolution("Unresolved children"); | ||
| } | ||
|
|
||
| TypeResolution sourceResolution = isStringAndExact(source, sourceText(), ParamOrdinal.FIRST); | ||
| if (sourceResolution.unresolved()) { | ||
| return sourceResolution; | ||
| } | ||
|
|
||
| TypeResolution startResolution = isInteger(start, sourceText(), ParamOrdinal.SECOND); | ||
| if (startResolution.unresolved()) { | ||
| return startResolution; | ||
| } | ||
|
|
||
| return isInteger(end, sourceText(), ParamOrdinal.THIRD); | ||
| } | ||
|
|
||
| @Override | ||
| protected Pipe makePipe() { | ||
| return new SubstringFunctionPipe(source(), this, Expressions.pipe(source), Expressions.pipe(start), Expressions.pipe(end)); | ||
| } | ||
|
|
||
| @Override | ||
| public boolean foldable() { | ||
| return source.foldable() && start.foldable() && end.foldable(); | ||
| } | ||
|
|
||
| @Override | ||
| public Object fold() { | ||
| return doProcess(source.fold(), start.fold(), end.fold()); | ||
| } | ||
|
|
||
| @Override | ||
| protected NodeInfo<? extends Expression> info() { | ||
| return NodeInfo.create(this, Substring::new, source, start, end); | ||
| } | ||
|
|
||
| @Override | ||
| public ScriptTemplate asScript() { | ||
| ScriptTemplate sourceScript = asScript(source); | ||
| ScriptTemplate startScript = asScript(start); | ||
| ScriptTemplate endScript = asScript(end); | ||
|
|
||
| return asScriptFrom(sourceScript, startScript, endScript); | ||
| } | ||
|
|
||
| protected ScriptTemplate asScriptFrom(ScriptTemplate sourceScript, ScriptTemplate startScript, ScriptTemplate endScript) { | ||
| return new ScriptTemplate(format(Locale.ROOT, formatTemplate("{eql}.%s(%s,%s,%s)"), | ||
| "substring", | ||
| sourceScript.template(), | ||
| startScript.template(), | ||
| endScript.template()), | ||
| paramsBuilder() | ||
| .script(sourceScript.params()) | ||
| .script(startScript.params()) | ||
| .script(endScript.params()) | ||
| .build(), dataType()); | ||
| } | ||
|
|
||
| @Override | ||
| public ScriptTemplate scriptWithField(FieldAttribute field) { | ||
| return new ScriptTemplate(processScript("doc[{}].value"), | ||
| paramsBuilder().variable(field.exactAttribute().name()).build(), | ||
| dataType()); | ||
| } | ||
|
|
||
| @Override | ||
| public DataType dataType() { | ||
| return DataTypes.KEYWORD; | ||
| } | ||
|
|
||
| @Override | ||
| public Expression replaceChildren(List<Expression> newChildren) { | ||
| if (newChildren.size() != 3) { | ||
| throw new IllegalArgumentException("expected [3] children but received [" + newChildren.size() + "]"); | ||
| } | ||
|
|
||
| return new Substring(source(), newChildren.get(0), newChildren.get(1), newChildren.get(2)); | ||
| } | ||
| } |
Oops, something went wrong.