Added tests for the DNB scenario with custom max match and context size.

Change-Id: Ie0a78c79d6f4128c400230f64929c062ffa400f5

.gitignore

@@ -58,4 +58,5 @@ src\main\resources\Kustvakt.conf
 /test-config-icc.xml
 /data/
 /old-jars/
-/data-backup
+/data-backup
+/notes

Changes

@@ -1,5 +1,8 @@
 # version 0.73.2-SNAPSHOT
 
+- Added tests for the DNB scenario with custom max match 
+  and context size. (#745)
+
 # version 0.73.1
 
 - Fixed jakarta validation error.

src/main/java/de/ids_mannheim/korap/config/KustvaktConfiguration.java

@@ -16,6 +16,9 @@
 import java.util.Set;
 import java.util.regex.Pattern;
 
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
 import de.ids_mannheim.korap.util.KrillProperties;
 import de.ids_mannheim.korap.utils.TimeUtils;
 import lombok.Getter;
@@ -41,6 +44,9 @@ public class KustvaktConfiguration {
     public static final Map<String, Object> KUSTVAKT_USER = new HashMap<>();
     public static final String DATA_FOLDER = "data";
 
+    public final static Logger log = LoggerFactory
+            .getLogger(KustvaktConfiguration.class);
+
     private String vcInCaching;
 
     private String indexDir;
@@ -139,6 +145,7 @@ public void loadBasicProperties (Properties properties) {
      */
     protected void load (Properties properties) throws Exception {
         loadBasicProperties(properties);
+        loadKrillProperties(properties);
 
         apiWelcomeMessage = properties.getProperty("api.welcome.message",
                 "Welcome to KorAP API!");
@@ -215,6 +222,26 @@ protected void load (Properties properties) throws Exception {
         networkEndpointURL = properties.getProperty("network.endpoint.url", "");
     }
 
+    private void loadKrillProperties (Properties properties) {
+        try {
+            String maxTokenMatch = properties.getProperty("krill.match.max.token");
+            if (maxTokenMatch != null) {
+                KrillProperties.maxTokenMatchSize = Integer.parseInt(maxTokenMatch);
+            }
+
+            String maxTokenContext = properties
+                    .getProperty("krill.context.max.token");
+            if (maxTokenContext != null) {
+                KrillProperties.maxTokenContextSize = Integer
+                        .parseInt(maxTokenContext);
+            }
+        }
+        catch (NumberFormatException e) {
+            log.error("A Krill property expects numerical values: "
+                    + e.getMessage());
+        };
+    }
+
     @Deprecated
     public void readPipesFile (String filename) throws IOException {
         File file = new File(filename);

src/main/java/de/ids_mannheim/korap/web/SearchKrill.java

@@ -35,7 +35,7 @@ public class SearchKrill {
     private static final boolean DEBUG = false;
 
     public static KrillIndex index;
-
+    
     /**
      * Constructor
      */
@@ -60,7 +60,7 @@ public SearchKrill (String path) {
             jlog.error("Unable to loadSubTypes index:" + e.getMessage());
         };
     };
-
+    
     public KrillIndex getIndex () {
         return index;
     };

src/test/java/de/ids_mannheim/korap/scenario/DNBTest.java

@@ -0,0 +1,78 @@
+package de.ids_mannheim.korap.scenario;
+
+import static org.junit.jupiter.api.Assertions.assertEquals;
+
+import org.junit.jupiter.api.AfterAll;
+import org.junit.jupiter.api.Test;
+import org.springframework.test.context.ContextConfiguration;
+
+import com.fasterxml.jackson.databind.JsonNode;
+
+import de.ids_mannheim.korap.config.SpringJerseyTest;
+import de.ids_mannheim.korap.exceptions.KustvaktException;
+import de.ids_mannheim.korap.util.KrillProperties;
+import de.ids_mannheim.korap.utils.JsonUtils;
+import jakarta.ws.rs.core.Response;
+import jakarta.ws.rs.core.Response.Status;
+
+@ContextConfiguration("classpath:test-config-dnb.xml")
+public class DNBTest extends SpringJerseyTest {
+
+    public final static String API_VERSION = "v1.0";
+
+    private JsonNode sendQuery (String query) throws KustvaktException {
+        Response r = target().path(API_VERSION).path("search")
+                .queryParam("q", query).queryParam("ql", "poliqarp")
+                .queryParam("show-tokens", true).request().get();
+        assertEquals(Status.OK.getStatusCode(), r.getStatus());
+        String entity = r.readEntity(String.class);
+        JsonNode node = JsonUtils.readTree(entity);
+
+        return node;
+
+    }
+
+    @AfterAll
+    public static void resetKrillProperties() {
+        KrillProperties.loadProperties("kustvakt-test.conf");
+    }
+
+    @Test
+    public void testTokenMatchSize () throws KustvaktException {
+        assertEquals(1, KrillProperties.maxTokenMatchSize);
+        assertEquals(25, KrillProperties.maxTokenContextSize);
+
+        JsonNode node = sendQuery("[orth=das]");
+        assertEquals(KrillProperties.maxTokenMatchSize,
+                node.at("/matches/0/tokens/match").size());
+
+        node = sendQuery("[orth=das][orth=Glück]");
+        assertEquals(KrillProperties.maxTokenMatchSize,
+                node.at("/matches/0/tokens/match").size());
+    }
+
+    @Test
+    public void testTokenContextMatchSize () throws KustvaktException {
+        Response r = target().path(API_VERSION).path("search")
+                .queryParam("q", "[orth=das][orth=Glück]")
+                .queryParam("ql", "poliqarp").queryParam("show-tokens", true)
+                .queryParam("context", "30-token,30-token").request().get();
+        assertEquals(Status.OK.getStatusCode(), r.getStatus());
+        String entity = r.readEntity(String.class);
+        JsonNode node = JsonUtils.readTree(entity);
+
+        assertEquals(KrillProperties.maxTokenContextSize,
+                node.at("/meta/context/left/1").asInt());
+        assertEquals(KrillProperties.maxTokenContextSize,
+                node.at("/meta/context/right/1").asInt());
+
+        assertEquals(KrillProperties.maxTokenContextSize,
+                node.at("/matches/0/tokens/left").size());
+
+        // There is a bug in Krill (https://github.com/KorAP/Krill/issues/141)
+        // So the following test fails
+//        assertEquals(KrillProperties.maxTokenContextSize,
+//                node.at("/matches/0/tokens/right").size());
+    }
+
+}

src/test/resources/kustvakt-dnb.conf

@@ -0,0 +1,126 @@
+# Krill settings
+#
+# A sample configuration for the DNB instance
+
+krill.match.max.token=1
+krill.context.max.token=25
+
+krill.indexDir = sample-index
+
+krill.index.commit.count = 134217000
+krill.index.commit.log = log/krill.commit.log
+krill.index.commit.auto = 500
+krill.index.relations.max = 100
+# Directory path of virtual corpora to cache
+krill.namedVC = vc
+krill.test = true
+
+# LDAP configuration file
+#
+ldap.config = src/test/resources/test-ldap.conf
+
+# Kustvakt versions
+#
+# multiple versions separated by space
+current.api.version = v1.0
+supported.api.version = v0.1 v1.0
+
+# Server
+#
+server.port=8089
+server.host=localhost
+
+# Mail settings
+#
+mail.enabled = false
+mail.receiver = test@localhost
+mail.sender = [email protected]
+mail.address.retrieval = test
+
+# Mail.templates
+#
+template.group.invitation = notification.vm
+
+# Default foundries for specific layers (optional)
+#
+default.foundry.partOfSpeech = tt
+default.foundry.lemma = tt
+default.foundry.orthography = opennlp
+default.foundry.dependency = malt
+default.foundry.constituent = corenlp
+default.foundry.morphology = marmot
+default.foundry.surface = base
+
+# Delete configuration (default hard)
+#
+# delete.auto.group = hard
+delete.group = soft
+delete.group.member = soft
+
+# Virtual corpus and queries
+max.user.persistent.queries = 5
+
+# Availability regex only support |
+# It should be removed/commented when the data doesn't contain availability field.
+# 
+availability.regex.free = CC-BY.*
+availability.regex.public = ACA.*|QAO-NC
+availability.regex.all = QAO.*
+
+
+# Define resource filters for search and match info API
+# AuthenticationFilter activates authentication using OAuth2 tokens
+# DemoUserFilter allows access to API without login
+# 
+# Default values: AuthenticationFilter,DemoUserFilter
+#
+search.resource.filters=AuthenticationFilter,DemoUserFilter
+
+
+# options referring to the security module!
+
+# OAuth
+# (see de.ids_mannheim.korap.constant.AuthenticationMethod for possible 
+# oauth.password.authentication values)
+#
+oauth2.password.authentication = TEST
+oauth2.native.client.host = korap.ids-mannheim.de
+oauth2.max.attempts = 2
+# expiry in seconds (S), minutes (M), hours (H), days (D)
+oauth2.access.token.expiry = 3M
+oauth2.refresh.token.expiry = 90D
+oauth2.authorization.code.expiry = 10M
+# -- scopes separated by space
+oauth2.default.scopes = search match_info
+oauth2.client.credentials.scopes = client_info
+
+oauth2.initial.super.client=true
+
+
+# see SecureRandom Number Generation Algorithms
+# optional
+security.secure.random.algorithm=SHA1PRNG
+
+# see MessageDigest Algorithms
+# default MD5
+security.md.algoritm = SHA-256  
+
+# secure hash support: BCRYPT
+security.secure.hash.algorithm=BCRYPT
+security.encryption.loadFactor = 10
+
+# DEPRECATED
+# JWT
+security.jwt.issuer=https://korap.ids-mannheim.de
+security.sharedSecret=this-is-shared-secret-code-for-JWT-Signing.It-must-contains-minimum-256-bits
+
+# token expiration time
+security.longTokenTTL = 1D
+security.tokenTTL = 2S
+security.shortTokenTTL = 1S
+
+# Session authentication
+security.idleTimeoutDuration = 25M
+security.multipleLogIn = true
+security.loginAttemptNum = 3
+security.authAttemptTTL = 45M

src/test/resources/kustvakt-test.conf

@@ -10,6 +10,9 @@ krill.index.relations.max = 100
 krill.namedVC = vc
 krill.test = true
 
+krill.match.max.token=50
+krill.context.max.token=60
+
 # LDAP configuration file
 #
 ldap.config = src/test/resources/test-ldap.conf