Skip to content

Part3 implement function score #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 3 commits into
base: part2-implement-search-and-query-condition-and-sorting
Choose a base branch
from
Open

Part3 implement function score #3

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
25678f6
Finish part 3. Provide util methods to create score function and inte…
ntub46010 Oct 21, 2022
98eb2b3
Merge branch 'part2-implement-query-condition' into part3-implement-f…
ntub46010 Oct 22, 2022
43664a5
Merge branch 'part2-implement-search-and-query-condition-and-sorting'…
ntub46010 Dec 25, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
39 changes: 32 additions & 7 deletions src/main/java/com/vincent/es/util/SearchInfo.java
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,16 +1,22 @@
package com.vincent.es.util;

import co.elastic.clients.elasticsearch._types.SortOptions;
import co.elastic.clients.elasticsearch._types.query_dsl.BoolQuery;
import co.elastic.clients.elasticsearch._types.query_dsl.Query;
import co.elastic.clients.elasticsearch._types.query_dsl.*;
import org.springframework.util.CollectionUtils;

import java.util.List;

public class SearchInfo {
private BoolQuery boolQuery; // 查詢條件
private List<SortOptions> sortOptions = List.of(); // 排序方式
private Integer from; // 資料的跳過數量
private Integer size; // 資料的擷取數量
private BoolQuery boolQuery; // 查詢條件
private List<FunctionScore> functionScores = List.of(); // 計分函數
private List<SortOptions> sortOptions = List.of(); // 排序方式
private Integer from; // 資料的跳過數量
private Integer size; // 資料的擷取數量

public SearchInfo() {
var matchAll = MatchAllQuery.of(b -> b)._toQuery();
this.boolQuery = BoolQuery.of(b -> b.filter(matchAll));
}

public static SearchInfo of(BoolQuery bool) {
var info = new SearchInfo();
Expand All @@ -32,6 +38,14 @@ public void setBoolQuery(BoolQuery boolQuery) {
this.boolQuery = boolQuery;
}

public List<FunctionScore> getFunctionScores() {
return functionScores;
}

public void setFunctionScores(List<FunctionScore> functionScores) {
this.functionScores = functionScores;
}

public List<SortOptions> getSortOptions() {
return sortOptions;
}
Expand All @@ -58,6 +72,17 @@ public void setSize(Integer size) {

// library 使用 Query 類別當作條件的傳遞介面
public Query toQuery() {
return boolQuery._toQuery();
if (CollectionUtils.isEmpty(functionScores)) {
return boolQuery._toQuery();
}

return new FunctionScoreQuery.Builder()
.query(boolQuery._toQuery())
.functions(functionScores)
.scoreMode(FunctionScoreMode.Sum)
.boostMode(FunctionBoostMode.Replace)
.maxBoost(30.0)
.build()
._toQuery();
}
}
109 changes: 107 additions & 2 deletions src/main/java/com/vincent/es/util/SearchUtils.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@ public static Query createTermQuery(String field, Object value) {
.value((int) value); // 此方法接受 long 型態
} else if (value instanceof String){
builder
.field(field + ".keyword")
.field(field)
.value((String) value);
} else {
throw new UnsupportedOperationException("Please implement for other type additionally.");
Expand Down Expand Up @@ -188,4 +188,109 @@ public static SortOptions createSortOption(String field, SortOrder order, SortMo
public static SortOptions createSortOption(String field, SortOrder order) {
return createSortOption(field, order, null);
}
}

/**
* <pre>
* {
* "field_value_factor": {
* "field": {@param field},
* "factor": {@param factor},
* "modifier": {@param modifier},
* "missing": {@param missing}
* }
* }
* </pre>
*/
public static FunctionScore createFieldValueFactor(
String field, Double factor, FieldValueFactorModifier modifier, Double missing) {

return new FieldValueFactorScoreFunction.Builder()
.field(field)
.factor(factor)
.modifier(modifier)
.missing(missing)
.build()
._toFunctionScore();
}

/**
* <pre>
* {
* "filter": {@param query},
* "weight": {@param weight}
* }
* </pre>
*/
public static FunctionScore createConditionalWeightFunctionScore(Query query, Double weight) {
return new FunctionScore.Builder()
.filter(query)
.weight(weight)
.build();
}

/**
* <pre>
* {
* "field_value_factor": {@param function},
* "weight": {@param weight}
* }
* </pre>
*/
public static FunctionScore createWeightedFieldValueFactor(
FieldValueFactorScoreFunction function, Double weight) {

return new FunctionScore.Builder()
.fieldValueFactor(function)
.weight(weight)
.build();
}

/**
* <pre>
* {
* "gauss": {@param placement}
* }
* </pre>
*/
public static FunctionScore createGaussFunction(String field, DecayPlacement placement) {
var decayFunction = new DecayFunction.Builder()
.field(field)
.placement(placement)
.build();
return new FunctionScore.Builder()
.gauss(decayFunction)
.build();
}

/**
* <pre>
* {
* "origin": {@param origin},
* "offset": {@param offset},
* "scale": {@param scale},
* "decay": {@param decay}
* }
* </pre>
*/
public static DecayPlacement createDecayPlacement(
Number origin, Number offset, Number scale, Double decay) {

return new DecayPlacement.Builder()
.origin(JsonData.of(origin))
.offset(JsonData.of(offset))
.scale(JsonData.of(scale))
.decay(decay)
.build();
}

public static DecayPlacement createDecayPlacement(
String originExp, String offsetExp, String scaleExp, Double decay) {

return new DecayPlacement.Builder()
.origin(JsonData.of(originExp))
.offset(JsonData.of(offsetExp))
.scale(JsonData.of(scaleExp))
.decay(decay)
.build();
}
}
100 changes: 94 additions & 6 deletions src/test/java/com/vincent/es/SearchTests.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,7 @@
import co.elastic.clients.elasticsearch._types.SortMode;
import co.elastic.clients.elasticsearch._types.SortOrder;
import co.elastic.clients.elasticsearch._types.query_dsl.BoolQuery;
import co.elastic.clients.elasticsearch._types.query_dsl.FieldValueFactorModifier;
import co.elastic.clients.elasticsearch._types.query_dsl.MatchAllQuery;
import com.vincent.es.entity.Student;
import com.vincent.es.repository.StudentEsRepository;
Expand Down Expand Up @@ -162,17 +163,104 @@ public void testPaging() {
assertDocumentIds(false, students, "101", "102");
}

@Test
public void testFunctionScore_FieldValueFactor() {
var fieldValueFactorScore = SearchUtils
.createFieldValueFactor("grade", 0.5, FieldValueFactorModifier.Square, 0.0);

var searchInfo = new SearchInfo();
searchInfo.setFunctionScores(List.of(fieldValueFactorScore));

var students = repository.find(searchInfo);

// Dora (4.0) -> Mario (2.25) -> Vincent (1.0) -> Winnie (0.25)
assertDocumentIds(students, "101", "102", "103", "104");
}

@Test
public void testFunctionScore_ConditionalWeight() {
var departmentQuery = SearchUtils
.createTermQuery("departments.keyword", "財務金融");
var departmentScore = SearchUtils
.createConditionalWeightFunctionScore(departmentQuery, 3.0);

var courseQuery = SearchUtils
.createTermQuery("courses.name.keyword", "程式設計");
var courseScore = SearchUtils
.createConditionalWeightFunctionScore(courseQuery, 1.5);

var fieldValueFactorScore = SearchUtils
.createFieldValueFactor("grade", 1.0, FieldValueFactorModifier.None, 0.0);
var gradeScore = SearchUtils
.createWeightedFieldValueFactor(fieldValueFactorScore.fieldValueFactor(), 0.5);

var searchInfo = new SearchInfo();
searchInfo.setFunctionScores(List.of(
departmentScore,
courseScore,
gradeScore
));

var students = repository.find(searchInfo);

// Vincent (5.5) -> Dora (5.0) -> Mario (1.5) -> Winnie (0.5)
assertDocumentIds(students, "103", "101", "102", "104");
}

@Test
public void testFunctionScore_DecayFunction_Number() {
var placement = SearchUtils
.createDecayPlacement(100, 15, 10, 0.5);
var decayFunctionScore = SearchUtils
.createGaussFunction("conductScore", placement);

var searchInfo = new SearchInfo();
searchInfo.setFunctionScores(List.of(decayFunctionScore));

var students = repository.find(searchInfo);

// Vincent (1.0) -> Mario (0.9726) -> Dora (0.4322) -> Winnie (0.2570)
assertDocumentIds(students, "103", "102", "101", "104");
}

@Test
public void testFunctionScore_DecayFunction_Date() {
var placement = SearchUtils
.createDecayPlacement("now", "90d", "270d", 0.5);
var decayFunctionScore = SearchUtils
.createGaussFunction("englishIssuedDate", placement);

var searchInfo = new SearchInfo();
searchInfo.setFunctionScores(List.of(decayFunctionScore));

var students = repository.find(searchInfo);

// Mario -> Winnie -> Dora -> Vincent
assertDocumentIds(students, "102", "104", "101", "103");
}

private void assertDocumentIds(boolean ignoreOrder, List<Student> actualDocs, String... expectedIdArray) {
if (!ignoreOrder) {
assertDocumentIds(actualDocs, expectedIdArray);
return;
}

var expectedIds = List.of(expectedIdArray);
var actualIds = actualDocs.stream()
.map(Student::getId)
.collect(Collectors.toList());

if (ignoreOrder) {
assertTrue(expectedIds.containsAll(actualIds));
assertTrue(actualIds.containsAll(expectedIds));
} else {
assertEquals(expectedIds, actualIds);
}
assertTrue(expectedIds.containsAll(actualIds));
assertTrue(actualIds.containsAll(expectedIds));
}

private void assertDocumentIds(List<Student> actualDocs, String... expectedIdArray) {
var expectedIds = List.of(expectedIdArray);
var actualIds = actualDocs.stream()
.map(Student::getId)
.collect(Collectors.toList());

assertEquals(expectedIds, actualIds);
}

}