From 6dfc10859f4647bbd3b00de1d30d3fe507dead07 Mon Sep 17 00:00:00 2001
From: Andrea Cavalli <andrea@cavallium.it>
Date: Mon, 30 May 2022 01:08:46 +0200
Subject: [PATCH] Implement term fields

---
 src/main/data-generator/lucene-query.yaml     |  1 +
 .../dbengine/client/query/NoOpAnalyzer.java   | 12 +++++++++++
 .../dbengine/client/query/QueryParser.java    | 21 +++++++++++++++++++
 3 files changed, 34 insertions(+)
 create mode 100644 src/main/java/it/cavallium/dbengine/client/query/NoOpAnalyzer.java

diff --git a/src/main/data-generator/lucene-query.yaml b/src/main/data-generator/lucene-query.yaml
index 731597b..678cea7 100644
--- a/src/main/data-generator/lucene-query.yaml
+++ b/src/main/data-generator/lucene-query.yaml
@@ -69,6 +69,7 @@ versions:
           # Should be at least one field!
           defaultFields: String[]
           pointsConfig: PointConfig[]
+          termFields: String[]
       PointConfig:
         data:
           field: String
diff --git a/src/main/java/it/cavallium/dbengine/client/query/NoOpAnalyzer.java b/src/main/java/it/cavallium/dbengine/client/query/NoOpAnalyzer.java
new file mode 100644
index 0000000..9f328de
--- /dev/null
+++ b/src/main/java/it/cavallium/dbengine/client/query/NoOpAnalyzer.java
@@ -0,0 +1,12 @@
+package it.cavallium.dbengine.client.query;
+
+import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.analysis.core.KeywordTokenizer;
+
+public class NoOpAnalyzer extends Analyzer {
+
+	@Override
+	protected TokenStreamComponents createComponents(String fieldName) {
+		return new TokenStreamComponents(new KeywordTokenizer());
+	}
+}
diff --git a/src/main/java/it/cavallium/dbengine/client/query/QueryParser.java b/src/main/java/it/cavallium/dbengine/client/query/QueryParser.java
index b93507e..f850d17 100644
--- a/src/main/java/it/cavallium/dbengine/client/query/QueryParser.java
+++ b/src/main/java/it/cavallium/dbengine/client/query/QueryParser.java
@@ -46,8 +46,20 @@ import it.cavallium.dbengine.client.query.current.data.WildcardQuery;
 import it.cavallium.dbengine.lucene.RandomSortField;
 import java.text.DecimalFormat;
 import java.text.NumberFormat;
+import java.util.Map;
+import java.util.function.Function;
 import java.util.stream.Collectors;
 import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.analysis.LowerCaseFilter;
+import org.apache.lucene.analysis.StopFilter;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.Tokenizer;
+import org.apache.lucene.analysis.core.KeywordTokenizer;
+import org.apache.lucene.analysis.en.EnglishPossessiveFilter;
+import org.apache.lucene.analysis.en.PorterStemFilter;
+import org.apache.lucene.analysis.miscellaneous.PerFieldAnalyzerWrapper;
+import org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter;
+import org.apache.lucene.analysis.standard.StandardTokenizer;
 import org.apache.lucene.document.DoublePoint;
 import org.apache.lucene.document.FloatPoint;
 import org.apache.lucene.document.IntPoint;
@@ -78,7 +90,16 @@ public class QueryParser {
 		switch (query.getBasicType$()) {
 			case StandardQuery:
 				var standardQuery = (it.cavallium.dbengine.client.query.current.data.StandardQuery) query;
+
+				// Fix the analyzer
+				Map<String, Analyzer> customAnalyzers = standardQuery
+						.termFields()
+						.stream()
+						.collect(Collectors.toMap(Function.identity(), term -> new NoOpAnalyzer()));
+				analyzer = new PerFieldAnalyzerWrapper(analyzer, customAnalyzers);
+
 				var standardQueryParser = new StandardQueryParser(analyzer);
+
 				standardQueryParser.setPointsConfigMap(standardQuery
 						.pointsConfig()
 						.stream()