Update to Dropwizard 4

.github/workflows/ci-build-manual.yml

@@ -0,0 +1,40 @@
+name: Build and push a development version on docker 
+
+on: 
+  workflow_dispatch: 
+
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v1
+    - name: Set up JDK 17
+      uses: actions/setup-java@v1
+      with:
+        java-version: 1.17
+    - name: Build with Gradle
+      run: ./gradlew build -x test
+
+  docker-build:
+    needs: [ build ]
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Create more disk space
+        run: sudo rm -rf /usr/share/dotnet && sudo rm -rf /opt/ghc && sudo rm -rf "/usr/local/share/boost" && sudo rm -rf "$AGENT_TOOLSDIRECTORY"
+      - uses: actions/checkout@v2
+      - name: Build and push
+        id: docker_build
+        uses: mr-smithers-excellent/docker-build-push@v5
+        with:
+          dockerfile: Dockerfile.local
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+          image: lfoppiano/grobid-quantities
+          registry: docker.io
+          pushImage: true
+          tags: latest-develop
+      - name: Image digest
+        run: echo ${{ steps.docker_build.outputs.digest }}

CHANGELOG.md

@@ -13,9 +13,11 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
 ### Changed
 
-+ Updated to Grobid version 0.8.0 
++ Updated to Grobid version 0.8.0
 + Updated to Dropwizard version 4.x (from version 1.x)
 
+
+
 ## [0.7.3] – 2023-06-26
 
 ### Added

Dockerfile

@@ -50,6 +50,7 @@ WORKDIR /opt
 
 FROM grobid/grobid:0.7.3 as runtime
 
+
 # setting locale is likely useless but to be sure
 ENV LANG C.UTF-8
 

build.gradle

@@ -74,7 +74,7 @@ repositories {
 
 dependencies {
     //Tests
-    testImplementation 'org.junit.vintage:junit-vintage-engine:5.9.3'
+    testRuntimeOnly 'org.junit.vintage:junit-vintage-engine:5.9.3'
     testImplementation(platform('org.junit:junit-bom:5.9.3'))
     testImplementation('org.junit.jupiter:junit-jupiter')
     testImplementation 'org.easymock:easymock:5.1.0'
@@ -84,9 +84,9 @@ dependencies {
     testImplementation 'org.jetbrains.kotlin:kotlin-test'
 
     //GROBID
-    implementation 'org.grobid:grobid-core:0.7.3'
-    implementation 'org.grobid:grobid-trainer:0.7.3'
-    implementation 'org.grobid:grobid-service:0.7.3'
+    implementation 'org.grobid:grobid-core:0.8.0'
+    implementation 'org.grobid:grobid-trainer:0.8.0'
+    implementation 'org.grobid:grobid-service:0.8.0'
     implementation "xerces:xercesImpl:2.12.0"
     implementation "net.arnx:jsonic:1.3.10"
     implementation "net.sf.saxon:Saxon-HE:9.6.0-9"
@@ -104,10 +104,10 @@ dependencies {
     implementation 'commons-pool:commons-pool:1.6'
 
     //Json
-    implementation 'com.fasterxml.jackson.core:jackson-core:2.13.3'
-    implementation 'com.fasterxml.jackson.core:jackson-databind:2.13.3'
-    implementation 'com.fasterxml.jackson.module:jackson-module-afterburner:2.13.3'
-    implementation 'com.fasterxml.jackson.dataformat:jackson-dataformat-yaml:2.13.3'
+    implementation 'com.fasterxml.jackson.core:jackson-core:2.14.3'
+    implementation 'com.fasterxml.jackson.core:jackson-databind:2.14.3'
+    implementation 'com.fasterxml.jackson.module:jackson-module-afterburner:2.14.3'
+    implementation 'com.fasterxml.jackson.dataformat:jackson-dataformat-yaml:2.14.3'
 
     // measurements
 
@@ -122,20 +122,21 @@ dependencies {
     implementation group: 'systems.uom', name: 'systems-unicode', version: '2.1'
 
     //Dropwizard
-    implementation "com.hubspot.dropwizard:dropwizard-guicier:1.3.5.2"
-    implementation "io.dropwizard:dropwizard-core:1.3.29"
-    implementation "io.dropwizard:dropwizard-assets:1.3.29"
-    implementation "io.dropwizard:dropwizard-testing:1.3.29"
-    implementation "io.dropwizard:dropwizard-forms:1.3.29"
-    implementation "io.dropwizard:dropwizard-client:1.3.29"
-    implementation "io.dropwizard:dropwizard-auth:1.3.29"
-    implementation "io.dropwizard.metrics:metrics-core:4.0.0"
-    implementation "io.dropwizard.metrics:metrics-servlets:4.0.0"
-    implementation 'javax.servlet:javax.servlet-api:3.1.0'
+    implementation 'ru.vyarus:dropwizard-guicey:7.0.0'
+
+    implementation 'io.dropwizard:dropwizard-bom:4.0.0'
+    implementation 'io.dropwizard:dropwizard-core:4.0.0'
+    implementation 'io.dropwizard:dropwizard-assets:4.0.0'
+    implementation 'io.dropwizard:dropwizard-testing:4.0.0'
+    implementation 'io.dropwizard:dropwizard-forms:4.0.0'
+    implementation 'io.dropwizard:dropwizard-client:4.0.0'
+    implementation 'io.dropwizard:dropwizard-auth:4.0.0'
+    implementation 'io.dropwizard.metrics:metrics-core:4.2.22'
+    implementation 'io.dropwizard.metrics:metrics-servlets:4.2.22'
 
     //Misc
     implementation group: 'com.googlecode.clearnlp', name: 'clearnlp', version: '1.3.1'
-    implementation 'com.google.guava:guava:30.1.1-jre'
+    implementation 'com.google.guava:guava:31.0.1-jre'
     implementation "net.arnx:jsonic:1.3.10"
 
     // XML

gradle.properties

@@ -1 +1 @@
-version=0.7.4-SNAPSHOT
+version=0.8.0-SNAPSHOT

resources/config/config.yml

@@ -56,29 +56,31 @@ models:
       embeddings_name: "glove-840B"
 
 
-views:
-  .mustache:
-    cache: false
+#views:
+#  .mustache:
+#    cache: false
 
 server:
   type: custom
   applicationConnectors:
     - type: http
       port: 8060
       idleTimeout: 120 seconds
+      acceptQueueSize: 2048
+
   adminConnectors:
     - type: http
       port: 8061
   registerDefaultExceptionMappers: false
   maxThreads: 2048
   maxQueuedRequests: 2048
-  acceptQueueSize: 2048
 
 logging:
   level: INFO
   appenders:
     - type: console
       threshold: INFO
+      timeZone: UTC
 #Docker-ignore-log-start      
     - type: file
       threshold: DEBUG
@@ -89,5 +91,4 @@ logging:
       timeZone: UTC
       maxFileSize: 10MB
 #Docker-ignore-log-end
-timeZone: UTC
 

src/main/java/org/grobid/core/engines/QuantitiesEngine.java

@@ -34,9 +34,9 @@
 import org.xml.sax.InputSource;
 import org.xml.sax.SAXException;
 
-import javax.inject.Inject;
-import javax.inject.Singleton;
-import javax.ws.rs.core.Response;
+import jakarta.inject.Inject;
+import jakarta.inject.Singleton;
+import jakarta.ws.rs.core.Response;
 import javax.xml.parsers.ParserConfigurationException;
 import javax.xml.parsers.SAXParser;
 import javax.xml.parsers.SAXParserFactory;
@@ -129,7 +129,7 @@ public MeasurementsResponse processPdf(InputStream inputStream) {
 
                     BiblioItem resHeader = new BiblioItem();
                     //parsers.getHeaderParser().processingHeaderSection(false, doc, resHeader);
-                    resHeader.generalResultMapping(labeledResult, tokenizationHeader);
+                    resHeader.generalResultMappingHeader(labeledResult, tokenizationHeader);
 
                     // title
                     List<LayoutToken> titleTokens = resHeader.getLayoutTokens(TaggingLabels.HEADER_TITLE);

src/main/java/org/grobid/core/engines/QuantityParser.java

@@ -1,10 +1,10 @@
 package org.grobid.core.engines;
 
 import com.google.common.collect.Iterables;
+import jakarta.inject.Inject;
 import org.apache.commons.collections4.CollectionUtils;
 import org.apache.commons.lang3.StringUtils;
 import org.apache.commons.lang3.tuple.Pair;
-import org.apache.log4j.Layout;
 import org.grobid.core.GrobidModel;
 import org.grobid.core.analyzers.QuantityAnalyzer;
 import org.grobid.core.data.Measurement;
@@ -18,8 +18,6 @@
 import org.grobid.core.engines.label.TaggingLabel;
 import org.grobid.core.exceptions.GrobidException;
 import org.grobid.core.features.FeaturesVectorQuantities;
-import org.grobid.core.lang.SentenceDetector;
-import org.grobid.core.lang.impl.OpenNLPSentenceDetector;
 import org.grobid.core.layout.BoundingBox;
 import org.grobid.core.layout.LayoutToken;
 import org.grobid.core.lexicon.QuantityLexicon;
@@ -29,7 +27,6 @@
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 
-import javax.inject.Inject;
 import java.math.BigDecimal;
 import java.util.ArrayList;
 import java.util.Arrays;
@@ -182,9 +179,10 @@ public List<Measurement> process(List<LayoutToken> layoutTokens) {
     }
 
     protected List<OffsetPosition> getSentencesOffsets(List<LayoutToken> tokens) {
-        SentenceDetector segmenter = new OpenNLPSentenceDetector();
+        SentenceUtilities segmenter = SentenceUtilities.getInstance();
+
         String text = LayoutTokensUtil.toText(tokens);
-        List<OffsetPosition> results = segmenter.detect(text);
+        List<OffsetPosition> results = segmenter.runSentenceDetection(text);
 
         if (CollectionUtils.isEmpty(results)) {
             results = Arrays.asList(new OffsetPosition(0, text.length()));

src/main/java/org/grobid/core/utilities/TextParser.java

@@ -57,7 +57,7 @@ public class TextParser {
     private AbstractPredIdentifier predicater = null;
     private AbstractSRLabeler labeler = null;
     private DEPReader depReader = null;
-    private SentenceDetector segmenter;
+    private SentenceUtilities segmenter;
 
     // this is for version 1.3.0 of ClearNLP
     private CRolesetClassifier roleClassifier = null;
@@ -120,7 +120,7 @@ private void init(String dictionaryFile, String posModelFile, String depModelFil
 
         depReader = new DEPReader(0, 1, 2, 3, 4, 5, 6);
 
-        segmenter = new OpenNLPSentenceDetector();
+        segmenter = SentenceUtilities.getInstance();
     }
 
     /**
@@ -177,7 +177,7 @@ public synchronized List<Sentence> parseText(String text) throws GrobidException
         }
 
         List<Sentence> results = new ArrayList<>();
-        List<OffsetPosition> sentences = this.segmenter.detect(text);
+        List<OffsetPosition> sentences = this.segmenter.runSentenceDetection(text);
 
         if (CollectionUtils.isEmpty(sentences)) {
             // there is some text but not in a state so that a sentence at least can be
@@ -219,7 +219,7 @@ public List<Sentence> parse(BufferedReader reader) throws GrobidException {
 
         String text = reader.lines().collect(Collectors.joining());
 
-        List<OffsetPosition> sentences = segmenter.detect(text);
+        List<OffsetPosition> sentences = segmenter.runSentenceDetection(text);
 
         for (OffsetPosition sentencePosition : sentences) {
             String sentence = text.substring(sentencePosition.start, sentencePosition.end);

src/main/java/org/grobid/service/GrobidEngineInitialiser.java

@@ -1,15 +1,15 @@
 package org.grobid.service;
 
 import com.google.common.collect.ImmutableList;
+import jakarta.inject.Inject;
+import jakarta.inject.Singleton;
 import org.grobid.core.main.GrobidHomeFinder;
 import org.grobid.core.main.LibraryLoader;
 import org.grobid.core.utilities.GrobidProperties;
 import org.grobid.service.configuration.GrobidQuantitiesConfiguration;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 
-import javax.inject.Inject;
-import javax.inject.Singleton;
 
 @Singleton
 public class GrobidEngineInitialiser {

src/main/java/org/grobid/service/QuantitiesServiceModule.java

@@ -2,9 +2,11 @@
 
 import com.codahale.metrics.MetricRegistry;
 import com.fasterxml.jackson.databind.ObjectMapper;
+import com.google.inject.AbstractModule;
 import com.google.inject.Binder;
 import com.google.inject.Provides;
-import com.hubspot.dropwizard.guicier.DropwizardAwareModule;
+import jakarta.ws.rs.client.Client;
+import jakarta.ws.rs.client.ClientBuilder;
 import org.grobid.core.engines.QuantitiesEngine;
 import org.grobid.core.engines.QuantityParser;
 import org.grobid.service.configuration.GrobidQuantitiesConfiguration;
@@ -14,34 +16,32 @@
 import org.grobid.service.exceptions.mapper.GrobidExceptionsTranslationUtility;
 import org.grobid.service.exceptions.mapper.GrobidServiceExceptionMapper;
 import org.grobid.service.exceptions.mapper.WebApplicationExceptionMapper;
-
-import javax.ws.rs.client.Client;
-import javax.ws.rs.client.ClientBuilder;
+import ru.vyarus.dropwizard.guice.module.support.DropwizardAwareModule;
 
 
 public class QuantitiesServiceModule extends DropwizardAwareModule<GrobidQuantitiesConfiguration> {
 
     @Override
-    public void configure(Binder binder) {
+    public void configure() {
         // -- Generic modules --
-        binder.bind(GrobidEngineInitialiser.class);
-        binder.bind(HealthCheck.class);
+        bind(GrobidEngineInitialiser.class);
+        bind(HealthCheck.class);
 
         //Services
-        binder.bind(QuantityParser.class);
-        binder.bind(QuantitiesEngine.class);
+        bind(QuantityParser.class);
+        bind(QuantitiesEngine.class);
 
         //REST
-        binder.bind(AnnotationController.class);
+        bind(AnnotationController.class);
 
         //Exception Mappers - directly imported from Grobid
-        binder.bind(GrobidServiceExceptionMapper.class);
-        binder.bind(GrobidExceptionsTranslationUtility.class);
-        binder.bind(GrobidExceptionMapper.class);
-        binder.bind(WebApplicationExceptionMapper.class);
+        bind(GrobidServiceExceptionMapper.class);
+        bind(GrobidExceptionsTranslationUtility.class);
+        bind(GrobidExceptionMapper.class);
+        bind(WebApplicationExceptionMapper.class);
     }
 
-    @Provides
+    /*@Provides
     protected ObjectMapper getObjectMapper() {
         return getEnvironment().getObjectMapper();
     }
@@ -54,7 +54,7 @@ protected MetricRegistry provideMetricRegistry() {
     //for unit tests
     protected MetricRegistry getMetricRegistry() {
         return getEnvironment().metrics();
-    }
+    }*/
 
     @Provides
     Client provideClient() {

src/main/java/org/grobid/service/command/PrepareDelftTrainingCommand.java

@@ -1,7 +1,7 @@
 package org.grobid.service.command;
 
-import io.dropwizard.cli.ConfiguredCommand;
-import io.dropwizard.setup.Bootstrap;
+import io.dropwizard.core.cli.ConfiguredCommand;
+import io.dropwizard.core.setup.Bootstrap;
 import net.sourceforge.argparse4j.impl.Arguments;
 import net.sourceforge.argparse4j.inf.MutuallyExclusiveGroup;
 import net.sourceforge.argparse4j.inf.Namespace;

src/main/java/org/grobid/service/command/RunTrainingCommand.java

@@ -1,7 +1,7 @@
 package org.grobid.service.command;
 
-import io.dropwizard.cli.ConfiguredCommand;
-import io.dropwizard.setup.Bootstrap;
+import io.dropwizard.core.cli.ConfiguredCommand;
+import io.dropwizard.core.setup.Bootstrap;
 import net.sourceforge.argparse4j.impl.Arguments;
 import net.sourceforge.argparse4j.inf.Namespace;
 import net.sourceforge.argparse4j.inf.Subparser;