Merge pull request #1123 from kermitt2/release-0.8.1

Preparation release 0.8.1

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

@@ -42,6 +42,6 @@ jobs:
           registry: docker.io
           pushImage: true
           tags:  |
-            latest-develop${{ github.event.inputs.suffix != '' && '-' || '' }}${{ github.event.inputs.suffix }}, latest-crf${{ github.event.inputs.suffix != '' && '-' || '' }}${{ github.event.inputs.suffix }}
+            latest-develop, latest-crf${{ github.event.inputs.suffix != '' && '-' || '' }}${{ github.event.inputs.suffix }}
       - name: Image digest
         run: echo ${{ steps.docker_build.outputs.digest }}

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

@@ -13,11 +13,11 @@ jobs:
 
     steps:
       - uses: actions/checkout@v4
-      - name: Set up JDK 17
+      - name: Set up JDK 11
         uses: actions/setup-java@v4
         with:
-          java-version: '17.0.10+7'
-          distribution: 'temurin'
+          java-version: '11'
+          distribution: 'adopt'
           cache: 'gradle'
       - name: Build with Gradle
         run: ./gradlew clean assemble --info --stacktrace --no-daemon

CHANGELOG.md

@@ -4,6 +4,29 @@ All notable changes to this project will be documented in this file.
 
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
+## [0.8.1] - 2024-06-10
+
+### Added
+ - Identified URLs are now added in the TEI output #1099
+ - Added DL models for patent processing #1082
+ - Copyright and licence identification models #1078 
+ - Add research infrastructure recognition for funding processing #1085
+
+### Changed
+ - Improved the recognition of URLs using (when available) PDF annotations, such as clickable links
+ - Updated TEI schema #1084
+ - Review patent process #1082
+ - Add Kotlin language to support development and testing #1096
+
+### Fixed
+ - Sentence segmentation avoids to split sentences with an URL in the middle  #1097
+ - Sentence segmentation is now applied to funding and acknowledgement #1106
+ - Docker image was optimized to reduce the needed space #1088
+ - Fixed OOBE when processing large quantities of notes #1075
+ - Corrected `<title>` coordinate attribute name #1070
+ - Fix missing coordinates in paragraph continuation #1076
+ - Fixed JSON log output
+
 ## [0.8.0] - 2023-11-19
 
 ### Added

Readme.md

@@ -105,11 +105,10 @@ Detailed end-to-end [benchmarking](https://grobid.readthedocs.io/en/latest/Bench
 A series of additional modules have been developed for performing __structure aware__ text mining directly on scholar PDF, reusing GROBID's PDF processing and sequence labelling weaponry:
 
 - [software-mention](https://github.com/ourresearch/software-mentions): recognition of software mentions and associated attributes in scientific literature
-- [datastet](https://github.com/kermitt2/datastet): identification of named and implicit research datasets and associated attributes in scientific articles
+- [datastet](https://github.com/kermitt2/datastet): identification of sections and sentences introducing datasets in a scientific article, identification of dataset names and attributes (implict and named datasets) and classification of the type of datasets
 - [grobid-quantities](https://github.com/kermitt2/grobid-quantities): recognition and normalization of physical quantities/measurements
 - [grobid-superconductors](https://github.com/lfoppiano/grobid-superconductors): recognition of superconductor material and properties in scientific literature
 - [entity-fishing](https://github.com/kermitt2/entity-fishing), a tool for extracting Wikidata entities from text and document, which can also use Grobid to pre-process scientific articles in PDF, leading to more precise and relevant entity extraction and the capacity to annotate the PDF with interactive layout
-- [datastet](https://github.com/kermitt2/datastet): identification of sections and sentences introducing datasets in a scientific article, identification of dataset names (implict and named datasets) and classification of the type of these datasets
 - [grobid-ner](https://github.com/kermitt2/grobid-ner): named entity recognition
 - [grobid-astro](https://github.com/kermitt2/grobid-astro): recognition of astronomical entities in scientific papers
 - [grobid-bio](https://github.com/kermitt2/grobid-bio): a toy bio-entity tagger using BioNLP/NLPBA 2004 dataset

build.gradle

@@ -60,19 +60,29 @@ subprojects {
         }
     }
 
-//    sourceCompatibility = 1.11
-//    targetCompatibility = 1.11
-
-    kotlin {
-        jvmToolchain(17)
-    }
-
-    java {
-        toolchain {
-            languageVersion.set(JavaLanguageVersion.of(17))
+    sourceCompatibility = 1.11
+    targetCompatibility = 1.11
+
+    tasks.withType(KotlinCompile).configureEach {
+        sourceCompatibility = JavaVersion.VERSION_11
+        targetCompatibility = JavaVersion.VERSION_11
+        kotlinOptions {
+            jvmTarget = JavaVersion.VERSION_11
         }
     }
 
+//    kotlin {
+//        jvmToolchain(11)
+//    }
+
+//    java {
+//        toolchain {
+//            languageVersion.set(JavaLanguageVersion.of(11))
+//            vendor.set(JvmVendorSpec.ADOPTIUM)
+//
+//        }
+//    }
+
     repositories {
         mavenCentral()
         maven {
@@ -316,6 +326,7 @@ project("grobid-home") {
 }
 
 import org.apache.tools.ant.taskdefs.condition.Os
+import org.jetbrains.kotlin.gradle.tasks.KotlinCompile
 
 project(":grobid-service") {
     apply plugin: 'application'