Pull request #301: RED-3086: Fixed overlapping rule and dictionary entries

Merge in RED/redaction-service from RED-3086 to release/2.52.x

* commit 'a62c94b34411abff6106c6d9239a1ec40f873d08':
  RED-3086: Fixed overlapping rule and dictionary entries

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/redaction/utils/EntitySearchUtils.java

@@ -159,6 +159,8 @@ public class EntitySearchUtils {
         // HashSet keeps old value but we want the new.
         entities.removeAll(found);
         entities.addAll(found);
+
+        removeEntitiesContainedInLarger(entities);
     }
 
 

redaction-service-v1/redaction-service-server-v1/src/test/java/com/iqser/red/service/redaction/v1/server/RedactionIntegrationTest.java

@@ -673,7 +673,7 @@ public class RedactionIntegrationTest {
     public void redactionTest() throws IOException {
 
         long start = System.currentTimeMillis();
-        ClassPathResource pdfFileResource = new ClassPathResource("files/Metolachlor/S-Metolachlor_RAR_01_Volume_1_2018-09-06.pdf");
+        ClassPathResource pdfFileResource = new ClassPathResource("files/new/just-a-document-20211215.pdf");
         AnalyzeRequest request = prepareStorage(pdfFileResource.getInputStream());
         request.setExcludedPages(Set.of(1));
 

redaction-service-v1/redaction-service-server-v1/src/test/resources/dictionaries/CBI_address.txt

@@ -1655,3 +1655,11 @@ Zyma SA, Nyon, Switzerland
 Mambo-Tox Ltd. Biomedical Sciences Building Bassett Crescent East Southampton SO16 7PX UK
 Syngenta Environmental Sciences Jealott’s Hill International Research Centre Bracknell, Berkshire RG42 6EY UK
 Test Ignored Hint CBI_ADDRESS
+CTL
+CTL - Central Toxicology Laboratory
+CTL/P/3557
+CTL/P/3607
+CTL/P/S 161
+CTL/Pl4333
+CTL/with dictionary entry
+