Merge branch 'development'

.dockerignore

@@ -8,6 +8,6 @@
 !.flaskenv
 !boot.sh
 !config.py
-!docker-entrypoint.sh
+!docker-nopaque-entrypoint.sh
 !nopaque.py
 !requirements.txt

.gitlab-ci.yml

@@ -1,3 +1,37 @@
+include:
+  - template: Security/Container-Scanning.gitlab-ci.yml
+
+##############################################################################
+# Pipeline stages in order of execution                                      #
+##############################################################################
+stages:
+  - build
+  - publish
+  - sca
+
+##############################################################################
+# Pipeline behavior                                                          #
+##############################################################################
+workflow:
+  rules:
+    # Run the pipeline on commits to the default branch
+    - if: $CI_COMMIT_BRANCH == $CI_DEFAULT_BRANCH
+      variables:
+        # Set the Docker image tag to `latest`
+        DOCKER_IMAGE: $CI_REGISTRY_IMAGE:latest
+      when: always
+    # Run the pipeline on tag creation
+    - if: $CI_COMMIT_TAG
+      variables:
+        # Set the Docker image tag to the Git tag name
+        DOCKER_IMAGE: $CI_REGISTRY_IMAGE:$CI_COMMIT_REF_NAME
+      when: always
+    # Don't run the pipeline on all other occasions
+    - when: never
+
+##############################################################################
+# Default values for pipeline jobs                                           #
+##############################################################################
 default:
   image: docker:24.0.6
   services:
@@ -5,38 +39,46 @@ default:
   tags:
     - docker
 
+##############################################################################
+# CI/CD variables for all jobs in the pipeline                               #
+##############################################################################
 variables:
   DOCKER_TLS_CERTDIR: /certs
+  DOCKER_BUILD_PATH: .
+  DOCKERFILE: Dockerfile
 
-build_image:
+##############################################################################
+# Pipeline jobs                                                              #
+##############################################################################
+build:
   stage: build
-  rules:
-    - if: $CI_COMMIT_BRANCH == $CI_DEFAULT_BRANCH
-      when: on_success
-      variables:
-        IMAGE_TAG: $CI_REGISTRY_IMAGE:latest
-    - if: $CI_COMMIT_TAG
-      when: "on_success"
-      variables:
-        IMAGE_TAG: $CI_REGISTRY_IMAGE:$CI_COMMIT_REF_NAME
-    - when: never
-  before_script:
-    - docker login -u gitlab-ci-token -p $CI_JOB_TOKEN $CI_REGISTRY
   script:
-    - docker build -t $IMAGE_TAG .
-    - docker push $IMAGE_TAG
+    - docker build --tag $DOCKER_IMAGE --file $DOCKERFILE $DOCKER_BUILD_PATH
+    - docker save $DOCKER_IMAGE > docker_image.tar
+  artifacts:
+    paths:
+      - docker_image.tar
 
-include:
-  - template: Security/Container-Scanning.gitlab-ci.yml
+publish:
+  stage: publish
+  before_script:
+    - docker login --username gitlab-ci-token --password $CI_JOB_TOKEN $CI_REGISTRY
+  script:
+    - docker load --input docker_image.tar
+    - docker push $DOCKER_IMAGE
+  after_script:
+    - docker logout $CI_REGISTRY
 
 container_scanning:
+  stage: sca
   rules:
+    # Run the job on commits to the default branch
     - if: $CI_COMMIT_BRANCH == $CI_DEFAULT_BRANCH
-      when: on_success
-      variables:
-        CS_IMAGE: $CI_REGISTRY_IMAGE:latest
+      when: always
+    # Run the job on tag creation
     - if: $CI_COMMIT_TAG
-      when: on_success
-      variables:
-        CS_IMAGE: ${CI_REGISTRY_IMAGE}:${CI_COMMIT_REF_NAME}
+      when: always
+    # Don't run the job on all other occasions
     - when: never
+  variables:
+    CS_IMAGE: $DOCKER_IMAGE

Dockerfile

@@ -17,9 +17,6 @@ RUN apt-get update \
  && rm --recursive /var/lib/apt/lists/*
 
 
-COPY docker-entrypoint.sh /usr/local/bin/
-
-
 RUN useradd --create-home --no-log-init nopaque \
  && groupadd docker \
  && usermod --append --groups docker nopaque
@@ -47,7 +44,10 @@ RUN python3 -m pip install --requirement requirements.txt \
 USER root
 
 
+COPY docker-nopaque-entrypoint.sh /usr/local/bin/
+
+
 EXPOSE 5000
 
 
-ENTRYPOINT ["docker-entrypoint.sh"]
+ENTRYPOINT ["docker-nopaque-entrypoint.sh"]

README.md

@@ -1,5 +1,8 @@
 # nopaque
 
+![release badge](https://gitlab.ub.uni-bielefeld.de/sfb1288inf/nopaque/-/badges/release.svg)
+![pipeline badge](https://gitlab.ub.uni-bielefeld.de/sfb1288inf/nopaque/badges/master/pipeline.svg?ignore_skipped=true)
+
 nopaque bundles various tools and services that provide humanities scholars with DH methods and thus can support their various individual research processes. Using nopaque, researchers can subject digitized sources to Optical Character Recognition (OCR). The resulting text files can then be used as a data basis for Natural Language Processing (NLP). The texts are automatically subjected to various linguistic annotations. The data processed via NLP can then be summarized in the web application as corpora and analyzed by means of an information retrieval system through complex search queries. The range of functions of the web application will be successively extended according to the needs of the researchers.
 
 ## Prerequisites and requirements

app/SpaCyNLPPipelineModel.defaults.yml

@@ -8,7 +8,7 @@
   pipeline_name: 'ca_core_news_md'
   version: '3.2.0'
   compatible_service_versions:
-    - '0.1.0' 
+    - '0.1.0'
 - title: 'German'
   description: 'German pipeline optimized for CPU. Components: tok2vec, tagger, morphologizer, parser, senter, ner, attribute_ruler, lemmatizer.'
   url: 'https://github.com/explosion/spacy-models/releases/download/de_core_news_md-3.2.0/de_core_news_md-3.2.0.tar.gz'
@@ -19,7 +19,7 @@
   pipeline_name: 'de_core_news_md'
   version: '3.2.0'
   compatible_service_versions:
-    - '0.1.0' 
+    - '0.1.0'
 - title: 'Greek'
   description: 'Greek pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, senter, ner, attribute_ruler, lemmatizer.'
   url: 'https://github.com/explosion/spacy-models/releases/download/el_core_news_md-3.2.0/el_core_news_md-3.2.0.tar.gz'
@@ -120,7 +120,6 @@
   version: '3.4.0'
   compatible_service_versions:
     - '0.1.1'
-    - '0.1.2'
 - title: 'German'
   description: 'German pipeline optimized for CPU. Components: tok2vec, tagger, morphologizer, parser, lemmatizer (trainable_lemmatizer), senter, ner.'
   url: 'https://github.com/explosion/spacy-models/releases/download/de_core_news_md-3.4.0/de_core_news_md-3.4.0.tar.gz'
@@ -132,7 +131,6 @@
   version: '3.4.0'
   compatible_service_versions:
     - '0.1.1'
-    - '0.1.2'
 - title: 'Greek'
   description: 'Greek pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, lemmatizer (trainable_lemmatizer), senter, ner, attribute_ruler.'
   url: 'https://github.com/explosion/spacy-models/releases/download/el_core_news_md-3.4.0/el_core_news_md-3.4.0.tar.gz'
@@ -144,7 +142,6 @@
   version: '3.4.0'
   compatible_service_versions:
     - '0.1.1'
-    - '0.1.2'
 - title: 'English'
   description: 'English pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter, ner, attribute_ruler, lemmatizer.'
   url: 'https://github.com/explosion/spacy-models/releases/download/en_core_web_md-3.4.1/en_core_web_md-3.4.1.tar.gz'
@@ -156,7 +153,6 @@
   version: '3.4.1'
   compatible_service_versions:
     - '0.1.1'
-    - '0.1.2'
 - title: 'Spanish'
   description: 'Spanish pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, senter, ner, attribute_ruler, lemmatizer.'
   url: 'https://github.com/explosion/spacy-models/releases/download/es_core_news_md-3.4.0/es_core_news_md-3.4.0.tar.gz'
@@ -168,7 +164,6 @@
   version: '3.4.0'
   compatible_service_versions:
     - '0.1.1'
-    - '0.1.2'
 - title: 'French'
   description: 'French pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, senter, ner, attribute_ruler, lemmatizer.'
   url: 'https://github.com/explosion/spacy-models/releases/download/fr_core_news_md-3.4.0/fr_core_news_md-3.4.0.tar.gz'
@@ -180,7 +175,6 @@
   version: '3.4.0'
   compatible_service_versions:
     - '0.1.1'
-    - '0.1.2' 
 - title: 'Italian'
   description: 'Italian pipeline optimized for CPU. Components: tok2vec, morphologizer, tagger, parser, lemmatizer (trainable_lemmatizer), senter, ner'
   url: 'https://github.com/explosion/spacy-models/releases/download/it_core_news_md-3.4.0/it_core_news_md-3.4.0.tar.gz'
@@ -192,7 +186,6 @@
   version: '3.4.0'
   compatible_service_versions:
     - '0.1.1'
-    - '0.1.2'
 - title: 'Polish'
   description: 'Polish pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, lemmatizer (trainable_lemmatizer), tagger, senter, ner.'
   url: 'https://github.com/explosion/spacy-models/releases/download/pl_core_news_md-3.4.0/pl_core_news_md-3.4.0.tar.gz'
@@ -204,7 +197,6 @@
   version: '3.4.0'
   compatible_service_versions:
     - '0.1.1'
-    - '0.1.2'
 - title: 'Russian'
   description: 'Russian pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, senter, ner, attribute_ruler, lemmatizer.'
   url: 'https://github.com/explosion/spacy-models/releases/download/ru_core_news_md-3.4.0/ru_core_news_md-3.4.0.tar.gz'
@@ -216,7 +208,6 @@
   version: '3.4.0'
   compatible_service_versions:
     - '0.1.1'
-    - '0.1.2'
 - title: 'Chinese'
   description: 'Chinese pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter, ner, attribute_ruler.'
   url: 'https://github.com/explosion/spacy-models/releases/download/zh_core_web_md-3.4.0/zh_core_web_md-3.4.0.tar.gz'
@@ -228,4 +219,3 @@
   version: '3.4.0'
   compatible_service_versions:
     - '0.1.1'
-    - '0.1.2'

app/TesseractOCRPipelineModel.defaults.yml

@@ -9,6 +9,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Amharic'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/amh.traineddata'
@@ -20,6 +21,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 - title: 'Arabic'
   description: ''
   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/ara.traineddata'
@@ -31,6 +33,7 @@
   compatible_service_versions:
     - '0.1.0'
     - '0.1.1'
+    - '0.1.2'
 # - title: 'Assamese'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/asm.traineddata'
@@ -42,6 +45,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Azerbaijani'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/aze.traineddata'
@@ -53,6 +57,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Azerbaijani - Cyrillic'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/aze_cyrl.traineddata'
@@ -64,6 +69,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Belarusian'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/bel.traineddata'
@@ -75,6 +81,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Bengali'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/ben.traineddata'
@@ -86,6 +93,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Tibetan'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/bod.traineddata'
@@ -97,6 +105,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Bosnian'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/bos.traineddata'
@@ -108,6 +117,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Bulgarian'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/bul.traineddata'
@@ -119,6 +129,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Catalan; Valencian'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/cat.traineddata'
@@ -130,6 +141,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Cebuano'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/ceb.traineddata'
@@ -141,6 +153,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Czech'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/ces.traineddata'
@@ -152,6 +165,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Chinese - Simplified'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/chi_sim.traineddata'
@@ -163,6 +177,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 - title: 'Chinese - Traditional'
   description: ''
   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/chi_tra.traineddata'
@@ -174,6 +189,7 @@
   compatible_service_versions:
     - '0.1.0'
     - '0.1.1'
+    - '0.1.2'
 # - title: 'Cherokee'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/chr.traineddata'
@@ -185,6 +201,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Welsh'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/cym.traineddata'
@@ -196,6 +213,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 - title: 'Danish'
   description: ''
   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/dan.traineddata'
@@ -207,6 +225,7 @@
   compatible_service_versions:
     - '0.1.0'
     - '0.1.1'
+    - '0.1.2'
 - title: 'German'
   description: ''
   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/deu.traineddata'
@@ -218,6 +237,7 @@
   compatible_service_versions:
     - '0.1.0'
     - '0.1.1'
+    - '0.1.2'
 # - title: 'Dzongkha'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/dzo.traineddata'
@@ -229,6 +249,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 - title: 'Greek, Modern (1453-)'
   description: ''
   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/ell.traineddata'
@@ -240,6 +261,7 @@
   compatible_service_versions:
     - '0.1.0'
     - '0.1.1'
+    - '0.1.2'
 - title: 'English'
   description: ''
   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/eng.traineddata'
@@ -251,6 +273,7 @@
   compatible_service_versions:
     - '0.1.0'
     - '0.1.1'
+    - '0.1.2'
 - title: 'English, Middle (1100-1500)'
   description: ''
   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/enm.traineddata'
@@ -262,6 +285,7 @@
   compatible_service_versions:
     - '0.1.0'
     - '0.1.1'
+    - '0.1.2'
 # - title: 'Esperanto'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/epo.traineddata'
@@ -273,6 +297,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Estonian'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/est.traineddata'
@@ -284,6 +309,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Basque'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/eus.traineddata'
@@ -295,6 +321,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Persian'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/fas.traineddata'
@@ -306,6 +333,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Finnish'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/fin.traineddata'
@@ -317,6 +345,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 - title: 'French'
   description: ''
   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/fra.traineddata'
@@ -328,6 +357,7 @@
   compatible_service_versions:
     - '0.1.0'
     - '0.1.1'
+    - '0.1.2'
 - title: 'German Fraktur'
   description: ''
   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/frk.traineddata'
@@ -339,6 +369,7 @@
   compatible_service_versions:
     - '0.1.0'
     - '0.1.1'
+    - '0.1.2'
 - title: 'French, Middle (ca. 1400-1600)'
   description: ''
   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/frm.traineddata'
@@ -350,6 +381,7 @@
   compatible_service_versions:
     - '0.1.0'
     - '0.1.1'
+    - '0.1.2'
 # - title: 'Irish'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/gle.traineddata'
@@ -361,6 +393,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Galician'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/glg.traineddata'
@@ -372,6 +405,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 - title: 'Greek, Ancient (-1453)'
   description: ''
   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/grc.traineddata'
@@ -383,6 +417,7 @@
   compatible_service_versions:
     - '0.1.0'
     - '0.1.1'
+    - '0.1.2'
 # - title: 'Gujarati'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/guj.traineddata'
@@ -394,6 +429,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Haitian; Haitian Creole'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/hat.traineddata'
@@ -405,6 +441,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Hebrew'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/heb.traineddata'
@@ -416,6 +453,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Hindi'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/hin.traineddata'
@@ -427,6 +465,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Croatian'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/hrv.traineddata'
@@ -438,6 +477,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Hungarian'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/hun.traineddata'
@@ -449,6 +489,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Inuktitut'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/iku.traineddata'
@@ -460,6 +501,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Indonesian'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/ind.traineddata'
@@ -471,6 +513,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Icelandic'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/isl.traineddata'
@@ -482,6 +525,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 - title: 'Italian'
   description: ''
   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/ita.traineddata'
@@ -493,6 +537,7 @@
   compatible_service_versions:
     - '0.1.0'
     - '0.1.1'
+    - '0.1.2'
 - title: 'Italian - Old'
   description: ''
   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/ita_old.traineddata'
@@ -504,6 +549,7 @@
   compatible_service_versions:
     - '0.1.0'
     - '0.1.1'
+    - '0.1.2'
 # - title: 'Javanese'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/jav.traineddata'
@@ -515,6 +561,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Japanese'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/jpn.traineddata'
@@ -526,6 +573,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Kannada'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/kan.traineddata'
@@ -537,6 +585,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Georgian'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/kat.traineddata'
@@ -548,6 +597,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Georgian - Old'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/kat_old.traineddata'
@@ -559,6 +609,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Kazakh'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/kaz.traineddata'
@@ -570,6 +621,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Central Khmer'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/khm.traineddata'
@@ -581,6 +633,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Kirghiz; Kyrgyz'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/kir.traineddata'
@@ -592,6 +645,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Korean'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/kor.traineddata'
@@ -603,6 +657,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Kurdish'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/kur.traineddata'
@@ -614,6 +669,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Lao'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/lao.traineddata'
@@ -625,6 +681,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Latin'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/lat.traineddata'
@@ -636,6 +693,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Latvian'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/lav.traineddata'
@@ -647,6 +705,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Lithuanian'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/lit.traineddata'
@@ -658,6 +717,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Malayalam'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/mal.traineddata'
@@ -669,6 +729,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Marathi'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/mar.traineddata'
@@ -680,6 +741,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Macedonian'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/mkd.traineddata'
@@ -691,6 +753,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Maltese'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/mlt.traineddata'
@@ -702,6 +765,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Malay'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/msa.traineddata'
@@ -713,6 +777,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Burmese'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/mya.traineddata'
@@ -724,6 +789,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Nepali'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/nep.traineddata'
@@ -735,6 +801,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Dutch; Flemish'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/nld.traineddata'
@@ -746,6 +813,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Norwegian'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/nor.traineddata'
@@ -757,6 +825,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Oriya'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/ori.traineddata'
@@ -768,6 +837,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Panjabi; Punjabi'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/pan.traineddata'
@@ -779,6 +849,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Polish'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/pol.traineddata'
@@ -790,6 +861,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 - title: 'Portuguese'
   description: ''
   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/por.traineddata'
@@ -801,6 +873,7 @@
   compatible_service_versions:
     - '0.1.0'
     - '0.1.1'
+    - '0.1.2'
 # - title: 'Pushto; Pashto'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/pus.traineddata'
@@ -812,6 +885,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Romanian; Moldavian; Moldovan'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/ron.traineddata'
@@ -823,6 +897,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 - title: 'Russian'
   description: ''
   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/rus.traineddata'
@@ -834,6 +909,7 @@
   compatible_service_versions:
     - '0.1.0'
     - '0.1.1'
+    - '0.1.2'
 # - title: 'Sanskrit'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/san.traineddata'
@@ -845,6 +921,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Sinhala; Sinhalese'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/sin.traineddata'
@@ -856,6 +933,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Slovak'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/slk.traineddata'
@@ -867,6 +945,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Slovenian'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/slv.traineddata'
@@ -878,6 +957,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 - title: 'Spanish; Castilian'
   description: ''
   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/spa.traineddata'
@@ -889,6 +969,7 @@
   compatible_service_versions:
     - '0.1.0'
     - '0.1.1'
+    - '0.1.2'
 - title: 'Spanish; Castilian - Old'
   description: ''
   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/spa_old.traineddata'
@@ -900,6 +981,7 @@
   compatible_service_versions:
     - '0.1.0'
     - '0.1.1'
+    - '0.1.2'
 # - title: 'Albanian'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/sqi.traineddata'
@@ -911,6 +993,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Serbian'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/srp.traineddata'
@@ -922,6 +1005,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Serbian - Latin'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/srp_latn.traineddata'
@@ -933,6 +1017,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Swahili'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/swa.traineddata'
@@ -944,6 +1029,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Swedish'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/swe.traineddata'
@@ -955,6 +1041,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Syriac'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/syr.traineddata'
@@ -966,6 +1053,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Tamil'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/tam.traineddata'
@@ -977,6 +1065,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Telugu'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/tel.traineddata'
@@ -988,6 +1077,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Tajik'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/tgk.traineddata'
@@ -999,6 +1089,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Tagalog'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/tgl.traineddata'
@@ -1010,6 +1101,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Thai'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/tha.traineddata'
@@ -1021,6 +1113,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Tigrinya'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/tir.traineddata'
@@ -1032,6 +1125,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Turkish'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/tur.traineddata'
@@ -1043,6 +1137,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Uighur; Uyghur'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/uig.traineddata'
@@ -1054,6 +1149,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Ukrainian'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/ukr.traineddata'
@@ -1065,6 +1161,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Urdu'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/urd.traineddata'
@@ -1076,6 +1173,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Uzbek'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/uzb.traineddata'
@@ -1087,6 +1185,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Uzbek - Cyrillic'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/uzb_cyrl.traineddata'
@@ -1098,6 +1197,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Vietnamese'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/vie.traineddata'
@@ -1109,6 +1209,7 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'
 # - title: 'Yiddish'
 #   description: ''
 #   url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/yid.traineddata'
@@ -1120,3 +1221,4 @@
 #   compatible_service_versions:
 #     - '0.1.0'
 #     - '0.1.1'
+#     - '0.1.2'

app/__init__.py

@@ -99,7 +99,7 @@ def create_app(config: Config = Config) -> Flask:
 
     from .users import bp as users_blueprint
     default_breadcrumb_root(users_blueprint, '.users')
-    app.register_blueprint(users_blueprint, url_prefix='/users')
+    app.register_blueprint(users_blueprint, cli_group='user', url_prefix='/users')
 
     from .workshops import bp as workshops_blueprint
     app.register_blueprint(workshops_blueprint, url_prefix='/workshops')

app/corpora/routes.py

@@ -97,14 +97,14 @@ def analysis(corpus_id):
     )
 
 
-# @bp.route('/<hashid:corpus_id>/follow/<token>')
-# def follow_corpus(corpus_id, token):
-#     corpus = Corpus.query.get_or_404(corpus_id)
-#     if current_user.follow_corpus_by_token(token):
-#         db.session.commit()
-#         flash(f'You are following "{corpus.title}" now', category='corpus')
-#         return redirect(url_for('corpora.corpus', corpus_id=corpus_id))
-#     abort(403)
+@bp.route('/<hashid:corpus_id>/follow/<token>')
+def follow_corpus(corpus_id, token):
+    corpus = Corpus.query.get_or_404(corpus_id)
+    if current_user.follow_corpus_by_token(token):
+        db.session.commit()
+        flash(f'You are following "{corpus.title}" now', category='corpus')
+        return redirect(url_for('corpora.corpus', corpus_id=corpus_id))
+    abort(403)
 
 
 @bp.route('/import', methods=['GET', 'POST'])

app/daemon/corpus_utils.py

@@ -45,7 +45,7 @@ def _create_build_corpus_service(corpus):
     ''' ## Constraints ## '''
     constraints = ['node.role==worker']
     ''' ## Image ## '''
-    image = f'{current_app.config["NOPAQUE_DOCKER_IMAGE_PREFIX"]}cwb:r1853'
+    image = f'{current_app.config["NOPAQUE_DOCKER_IMAGE_PREFIX"]}cwb:r1879'
     ''' ## Labels ## '''
     labels = {
         'origin': current_app.config['SERVER_NAME'],
@@ -139,7 +139,7 @@ def _create_cqpserver_container(corpus):
     ''' ## Entrypoint ## '''
     entrypoint = ['bash', '-c']
     ''' ## Image ## '''
-    image = f'{current_app.config["NOPAQUE_DOCKER_IMAGE_PREFIX"]}cwb:r1853'
+    image = f'{current_app.config["NOPAQUE_DOCKER_IMAGE_PREFIX"]}cwb:r1879'
     ''' ## Name ## '''
     name = f'cqpserver_{corpus.id}'
     ''' ## Network ## '''

app/models.py

@@ -953,7 +953,7 @@ class TesseractOCRPipelineModel(FileMixin, HashidMixin, db.Model):
         return self.user.hashid
 
     @staticmethod
-    def insert_defaults():
+    def insert_defaults(force_download=False):
         nopaque_user = User.query.filter_by(username='nopaque').first()
         defaults_file = os.path.join(
             os.path.dirname(os.path.abspath(__file__)),
@@ -966,6 +966,7 @@ class TesseractOCRPipelineModel(FileMixin, HashidMixin, db.Model):
             if model is not None:
                 model.compatible_service_versions = m['compatible_service_versions']
                 model.description = m['description']
+                model.filename = f'{model.id}.traineddata'
                 model.publisher = m['publisher']
                 model.publisher_url = m['publisher_url']
                 model.publishing_url = m['publishing_url']
@@ -973,38 +974,39 @@ class TesseractOCRPipelineModel(FileMixin, HashidMixin, db.Model):
                 model.is_public = True
                 model.title = m['title']
                 model.version = m['version']
-                continue
-            model = TesseractOCRPipelineModel(
-                compatible_service_versions=m['compatible_service_versions'],
-                description=m['description'],
-                publisher=m['publisher'],
-                publisher_url=m['publisher_url'],
-                publishing_url=m['publishing_url'],
-                publishing_year=m['publishing_year'],
-                is_public=True,
-                title=m['title'],
-                user=nopaque_user,
-                version=m['version']
-            )
-            db.session.add(model)
-            db.session.flush(objects=[model])
-            db.session.refresh(model)
-            model.filename = f'{model.id}.traineddata'
-            r = requests.get(m['url'], stream=True)
-            pbar = tqdm(
-                desc=f'{model.title} ({model.filename})',
-                unit="B",
-                unit_scale=True,
-                unit_divisor=1024,
-                total=int(r.headers['Content-Length'])
-            )
-            pbar.clear()
-            with open(model.path, 'wb') as f:
-                for chunk in r.iter_content(chunk_size=1024):
-                    if chunk:  # filter out keep-alive new chunks
-                        pbar.update(len(chunk))
-                        f.write(chunk)
-                pbar.close()
+            else:
+                model = TesseractOCRPipelineModel(
+                    compatible_service_versions=m['compatible_service_versions'],
+                    description=m['description'],
+                    publisher=m['publisher'],
+                    publisher_url=m['publisher_url'],
+                    publishing_url=m['publishing_url'],
+                    publishing_year=m['publishing_year'],
+                    is_public=True,
+                    title=m['title'],
+                    user=nopaque_user,
+                    version=m['version']
+                )
+                db.session.add(model)
+                db.session.flush(objects=[model])
+                db.session.refresh(model)
+                model.filename = f'{model.id}.traineddata'
+            if not os.path.exists(model.path) or force_download:
+                r = requests.get(m['url'], stream=True)
+                pbar = tqdm(
+                    desc=f'{model.title} ({model.filename})',
+                    unit="B",
+                    unit_scale=True,
+                    unit_divisor=1024,
+                    total=int(r.headers['Content-Length'])
+                )
+                pbar.clear()
+                with open(model.path, 'wb') as f:
+                    for chunk in r.iter_content(chunk_size=1024):
+                        if chunk:  # filter out keep-alive new chunks
+                            pbar.update(len(chunk))
+                            f.write(chunk)
+                    pbar.close()
         db.session.commit()
 
     def delete(self):
@@ -1080,7 +1082,7 @@ class SpaCyNLPPipelineModel(FileMixin, HashidMixin, db.Model):
         return self.user.hashid
 
     @staticmethod
-    def insert_defaults():
+    def insert_defaults(force_download=False):
         nopaque_user = User.query.filter_by(username='nopaque').first()
         defaults_file = os.path.join(
             os.path.dirname(os.path.abspath(__file__)),
@@ -1093,6 +1095,7 @@ class SpaCyNLPPipelineModel(FileMixin, HashidMixin, db.Model):
             if model is not None:
                 model.compatible_service_versions = m['compatible_service_versions']
                 model.description = m['description']
+                model.filename = m['url'].split('/')[-1]
                 model.publisher = m['publisher']
                 model.publisher_url = m['publisher_url']
                 model.publishing_url = m['publishing_url']
@@ -1101,39 +1104,40 @@ class SpaCyNLPPipelineModel(FileMixin, HashidMixin, db.Model):
                 model.title = m['title']
                 model.version = m['version']
                 model.pipeline_name = m['pipeline_name']
-                continue
-            model = SpaCyNLPPipelineModel(
-                compatible_service_versions=m['compatible_service_versions'],
-                description=m['description'],
-                publisher=m['publisher'],
-                publisher_url=m['publisher_url'],
-                publishing_url=m['publishing_url'],
-                publishing_year=m['publishing_year'],
-                is_public=True,
-                title=m['title'],
-                user=nopaque_user,
-                version=m['version'],
-                pipeline_name=m['pipeline_name']
-            )
-            db.session.add(model)
-            db.session.flush(objects=[model])
-            db.session.refresh(model)
-            model.filename = m['url'].split('/')[-1]
-            r = requests.get(m['url'], stream=True)
-            pbar = tqdm(
-                desc=f'{model.title} ({model.filename})',
-                unit="B",
-                unit_scale=True,
-                unit_divisor=1024,
-                total=int(r.headers['Content-Length'])
-            )
-            pbar.clear()
-            with open(model.path, 'wb') as f:
-                for chunk in r.iter_content(chunk_size=1024):
-                    if chunk:  # filter out keep-alive new chunks
-                        pbar.update(len(chunk))
-                        f.write(chunk)
-                pbar.close()
+            else:
+                model = SpaCyNLPPipelineModel(
+                    compatible_service_versions=m['compatible_service_versions'],
+                    description=m['description'],
+                    filename=m['url'].split('/')[-1],
+                    publisher=m['publisher'],
+                    publisher_url=m['publisher_url'],
+                    publishing_url=m['publishing_url'],
+                    publishing_year=m['publishing_year'],
+                    is_public=True,
+                    title=m['title'],
+                    user=nopaque_user,
+                    version=m['version'],
+                    pipeline_name=m['pipeline_name']
+                )
+                db.session.add(model)
+                db.session.flush(objects=[model])
+                db.session.refresh(model)
+            if not os.path.exists(model.path) or force_download:
+                r = requests.get(m['url'], stream=True)
+                pbar = tqdm(
+                    desc=f'{model.title} ({model.filename})',
+                    unit="B",
+                    unit_scale=True,
+                    unit_divisor=1024,
+                    total=int(r.headers['Content-Length'])
+                )
+                pbar.clear()
+                with open(model.path, 'wb') as f:
+                    for chunk in r.iter_content(chunk_size=1024):
+                        if chunk:  # filter out keep-alive new chunks
+                            pbar.update(len(chunk))
+                            f.write(chunk)
+                    pbar.close()
         db.session.commit()
     
     def delete(self):

app/services/services.yml

@@ -10,7 +10,7 @@ file-setup-pipeline:
 tesseract-ocr-pipeline:
   name: 'Tesseract OCR Pipeline'
   publisher: 'Bielefeld University - CRC 1288 - INF'
-  latest_version: '0.1.1'
+  latest_version: '0.1.2'
   versions:
     0.1.0:
       methods:
@@ -23,6 +23,12 @@ tesseract-ocr-pipeline:
         - 'ocropus_nlbin_threshold'
       publishing_year: 2022
       url: 'https://gitlab.ub.uni-bielefeld.de/sfb1288inf/tesseract-ocr-pipeline/-/releases/v0.1.1'
+    0.1.2:
+      methods:
+        - 'binarization'
+        - 'ocropus_nlbin_threshold'
+      publishing_year: 2023
+      url: 'https://gitlab.ub.uni-bielefeld.de/sfb1288inf/tesseract-ocr-pipeline/-/releases/v0.1.2'
 transkribus-htr-pipeline:
   name: 'Transkribus HTR Pipeline'
   publisher: 'Bielefeld University - CRC 1288 - INF'
@@ -41,7 +47,7 @@ transkribus-htr-pipeline:
 spacy-nlp-pipeline:
   name: 'SpaCy NLP Pipeline'
   publisher: 'Bielefeld University - CRC 1288 - INF'
-  latest_version: '0.1.2'
+  latest_version: '0.1.1'
   versions:
     0.1.0:
       methods:
@@ -53,8 +59,3 @@ spacy-nlp-pipeline:
         - 'encoding_detection'
       publishing_year: 2022
       url: 'https://gitlab.ub.uni-bielefeld.de/sfb1288inf/spacy-nlp-pipeline/-/releases/v0.1.1'
-    0.1.2:
-      methods:
-        - 'encoding_detection'
-      publishing_year: 2022
-      url: 'https://gitlab.ub.uni-bielefeld.de/sfb1288inf/spacy-nlp-pipeline/-/releases/v0.1.2'

app/static/js/app.js

@@ -168,6 +168,14 @@ nopaque.App = class App {
             let manualModalTocElement = document.querySelector('#manual-modal-toc');
             let manualModalToc = M.Tabs.getInstance(manualModalTocElement);
             manualModalToc.select(modalTriggerElement.dataset.manualModalChapter);
+            // TODO: Make this work.
+            // if ('manualModalChapterAnchor' in modalTriggerElement.dataset) {
+            //   let manualModalChapterAnchor = document.querySelector(`#${modalTriggerElement.dataset.manualModalChapterAnchor}`);
+            //   let xCoord = manualModalChapterAnchor.getBoundingClientRect().left;
+            //   let yCoord = manualModalChapterAnchor.getBoundingClientRect().top;
+            //   let modalContentElement = modalElement.querySelector('.modal-content');
+            //   modalContentElement.scroll(xCoord, yCoord);
+            // }
           }
         }
       }

app/static/js/corpus-analysis/query-builder/element-references.js

@@ -3,8 +3,10 @@ nopaque.corpus_analysis.query_builder.ElementReferences = class ElementReference
     // General Elements
     this.queryInputField = document.querySelector('#corpus-analysis-concordance-query-builder-input-field');
     this.queryChipElements = [];
+    this.queryElementTarget = document.querySelector('.query-element-target')
     this.editingModusOn = false;
     this.editedQueryChipElementIndex = undefined;
+    this.deleteQueryButton = document.querySelector('#corpus-analysis-concordance-delete-query-button');
 
     // Structural Attribute Builder Elements
     this.structuralAttrModal = M.Modal.getInstance(document.querySelector('#corpus-analysis-concordance-structural-attr-modal'));

app/static/js/corpus-analysis/query-builder/query-builder.js

@@ -2,30 +2,58 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
   constructor() {
     this.elements = new nopaque.corpus_analysis.query_builder.ElementReferences();
 
-    this.incidenceModifierEventListeners();
-    this.nAndMInputSubmitEventListeners();
+    this.addEventListenersToQueryElementTarget();
+    this.addEventListenersToIncidenceModifier();
+    this.addEventListenersToNAndMInputSubmit();
 
-    let queryBuilderDisplay = document.querySelector("#corpus-analysis-concordance-query-builder-display");
-    let expertModeDisplay = document.querySelector("#corpus-analysis-concordance-expert-mode-display");
-    let expertModeSwitch = document.querySelector("#corpus-analysis-concordance-expert-mode-switch");
-    
-    expertModeSwitch.addEventListener("change", () => {
-      const isChecked = expertModeSwitch.checked;
-      if (isChecked) {
-        queryBuilderDisplay.classList.add("hide");
-        expertModeDisplay.classList.remove("hide");
-        this.switchToExpertModeParser();
-      } else {
-        queryBuilderDisplay.classList.remove("hide");
-        expertModeDisplay.classList.add("hide");
-        this.switchToQueryBuilderParser();
-      }
-    });
+    this.elements.deleteQueryButton.addEventListener('click', () => {this.resetQueryInputField()});
+    this.expertModeQueryBuilderSwitchHandler();
 
     this.extensions = {
       structuralAttributeBuilderFunctions: new nopaque.corpus_analysis.query_builder.StructuralAttributeBuilderFunctions(this),
       tokenAttributeBuilderFunctions: new nopaque.corpus_analysis.query_builder.TokenAttributeBuilderFunctions(this),
     };
+
+    this.dropdown = M.Dropdown.init(
+      document.querySelector('.dropdown-trigger[data-toggle-area="token-incidence-modifiers"]'), 
+      {
+        onCloseStart: () => {
+          this.unselectChipElement(this.elements.queryInputField.querySelector('.chip.teal'));
+        }
+      }
+    )
+  }
+
+  addEventListenersToQueryElementTarget() {
+    this.elements.queryElementTarget.addEventListener('click', () => {
+      this.elements.positionalAttrModal.open();
+    });
+    this.elements.queryElementTarget.addEventListener('dragstart', this.handleDragStart.bind(this, this.elements.queryElementTarget));
+    this.elements.queryElementTarget.addEventListener('dragend', this.handleDragEnd);
+  }
+
+  addEventListenersToIncidenceModifier() {
+    // Eventlisteners for the incidence modifiers. There are two different types of incidence modifiers: token and character incidence modifiers.
+    document.querySelectorAll('.incidence-modifier-selection').forEach(button => {
+      let dropdownId = button.parentNode.parentNode.id;
+      if (dropdownId === 'corpus-analysis-concordance-token-incidence-modifiers-dropdown') {
+        button.addEventListener('click', () => this.tokenIncidenceModifierHandler(button.dataset.token, button.innerHTML));
+      } else if (dropdownId === 'corpus-analysis-concordance-character-incidence-modifiers-dropdown') {
+        button.addEventListener('click', () => this.extensions.tokenAttributeBuilderFunctions.characterIncidenceModifierHandler(button));
+      }
+    });
+  }
+
+  addEventListenersToNAndMInputSubmit() {
+    // Eventlisteners for the submit of n- and m-values of the incidence modifier modal for "exactly n" or "between n and m".
+    document.querySelectorAll('.n-m-submit-button').forEach(button => {
+      let modalId = button.dataset.modalId;
+      if (modalId === 'corpus-analysis-concordance-exactly-n-token-modal' || modalId === 'corpus-analysis-concordance-between-nm-token-modal') {
+        button.addEventListener('click', () => this.tokenNMSubmitHandler(modalId));
+      } else if (modalId === 'corpus-analysis-concordance-exactly-n-character-modal' || modalId === 'corpus-analysis-concordance-between-nm-character-modal') {
+        button.addEventListener('click', () => this.extensions.tokenAttributeBuilderFunctions.characterNMSubmitHandler(modalId));
+      }
+    });
   }
 
   toggleClass(elements, className, action) {
@@ -36,26 +64,27 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
 
   resetQueryInputField() {
     this.elements.queryInputField.innerHTML = '';
-    this.addPlaceholder();
+    this.addQueryElementTarget();
     this.updateChipList();
     this.queryPreviewBuilder();
   }
 
+  addQueryElementTarget() {
+    let queryElementTarget = nopaque.Utils.HTMLToElement(
+      `
+      <a class="query-element-target btn-floating btn-small blue-grey lighten-4 waves-effect waves-light tooltipped" style="margin-bottom:10px; margin-right:5px;" draggable="true" data-position="bottom" data-tooltip="Add an Element to your query">
+        <i class="material-icons">add</i>
+      </a>
+      `
+    );
+    this.elements.queryInputField.appendChild(queryElementTarget);
+    this.elements.queryElementTarget = queryElementTarget;
+    this.addEventListenersToQueryElementTarget();
+  }
+
   updateChipList() {
     this.elements.queryChipElements = this.elements.queryInputField.querySelectorAll('.query-component');
   }
-
-  removePlaceholder() {
-    let placeholder = this.elements.queryInputField.querySelector('#corpus-analysis-concordance-query-builder-input-field-placeholder');
-    if (placeholder && this.elements.queryInputField !== undefined) {
-      this.elements.queryInputField.innerHTML = '';
-    }
-  }
-
-  addPlaceholder() {
-    let placeholder = nopaque.Utils.HTMLToElement('<span id="corpus-analysis-concordance-query-builder-input-field-placeholder">Click on a button to add a query component</span>');
-    this.elements.queryInputField.appendChild(placeholder);
-  }
   
   resetMaterializeSelection(selectionElements, value = "default") {
     selectionElements.forEach(selectionElement => {
@@ -87,34 +116,34 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
     prettyQueryText = nopaque.Utils.escape(prettyQueryText);
     let queryChipElement = nopaque.Utils.HTMLToElement(
       `
-        <span class="chip query-component" data-type="${dataType}" data-query="${queryText}" draggable="true" data-closing-tag="${isClosingTag}">
+        <span class="chip query-component" data-type="${dataType}" data-query="${queryText}" draggable="true"">
           ${prettyQueryText}${isEditable ? '<i class="material-icons chip-action-button" data-chip-action="edit" style="padding-left:5px; font-size:18px; cursor:pointer;">edit</i>': ''}
-          ${isClosingTag ? '<i class="material-icons chip-action-button" data-chip-action="lock" style="padding-top:5px; font-size:20px; cursor:pointer;">lock_open</i>' : '<i class="material-icons close chip-action-button" data-chip-action="delete">close</i>'}
+          ${isClosingTag ? '' : '<i class="material-icons close chip-action-button" data-chip-action="delete">close</i>'}
         </span>
       `
     );
     this.addActionListeners(queryChipElement);
     queryChipElement.addEventListener('dragstart', this.handleDragStart.bind(this, queryChipElement));
     queryChipElement.addEventListener('dragend', this.handleDragEnd);
-
-    // Ensures that metadata is always at the end of the query and if an index is given, inserts the query chip at the given index and if there is a closing tag, inserts the query chip before the closing tag.
-    this.removePlaceholder();
-    if (!index) {
-      let closingTagElement = this.elements.queryInputField.querySelector('[data-closing-tag="true"]');
-      if (closingTagElement) {
-        index = Array.from(this.elements.queryInputField.children).indexOf(closingTagElement);
-      }
-    }
-    if (index) {
-      this.elements.queryInputField.insertBefore(queryChipElement, this.elements.queryChipElements[index]);
+    // If an index is given, inserts the query chip after the given index (only relevant for Incidence Modifier) and if there is a closing tag, inserts the query chip before the closing tag.
+    if (index !== null) {
+      this.updateChipList();
+      this.elements.queryChipElements[index].after(queryChipElement);
     } else {
-      this.elements.queryInputField.appendChild(queryChipElement);
+      this.elements.queryInputField.insertBefore(queryChipElement, this.elements.queryElementTarget);
+    }
+    if (isClosingTag) {
+      this.moveQueryElementTarget(queryChipElement);
     }
 
     this.updateChipList();
     this.queryPreviewBuilder();
   }
 
+  moveQueryElementTarget(element) {
+    this.elements.queryInputField.insertBefore(this.elements.queryElementTarget, element);
+  }
+
   addActionListeners(queryChipElement) {
     let notQuantifiableDataTypes = ['start-sentence', 'end-sentence', 'start-entity', 'start-empty-entity', 'end-entity', 'token-incidence-modifier'];
     queryChipElement.addEventListener('click', (event) => {
@@ -131,8 +160,6 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
         this.deleteChipElement(queryChipElement);
       } else if (event.target.dataset.chipAction === 'edit') {
         this.editChipElement(queryChipElement);
-      } else if (event.target.dataset.chipAction === 'lock') {
-        this.lockClosingChipElement(queryChipElement);
       }
       });
     });
@@ -154,20 +181,13 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
     }
   }
 
-  lockClosingChipElement(queryChipElement) {
-    queryChipElement.dataset.closingTag = 'false';
-    let lockIcon = queryChipElement.querySelector('[data-chip-action="lock"]');
-    lockIcon.textContent = 'lock';
-    // TODO: Write unlock-Function?
-    lockIcon.dataset.chipAction = 'unlock';
-  }
-
   deleteChipElement(attr) {
     let elementIndex = Array.from(this.elements.queryInputField.children).indexOf(attr);
     switch (attr.dataset.type) {
       case 'start-sentence':
         this.deleteClosingTagHandler(elementIndex, 'end-sentence');
         break;
+      case 'start-empty-entity':
       case 'start-entity':
         this.deleteClosingTagHandler(elementIndex, 'end-entity');
         break;
@@ -180,9 +200,6 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
         break;
     }
     this.elements.queryInputField.removeChild(attr);
-    if (this.elements.queryInputField.children.length === 0) {
-      this.addPlaceholder();
-    }
     this.updateChipList();
     this.queryPreviewBuilder();
   }
@@ -217,13 +234,17 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
 
         let targetChipClone = targetChipElement.cloneNode(true);
         element.insertAdjacentElement('afterend', targetChipClone);
-
+        //TODO: Change to two different functions for drag and drop
         this.addDragDropListeners(targetChipClone, queryChipElement);
       }
     }, 0);
   }
 
-  handleDragEnd() {
+  handleDragEnd(event) {
+    // is called when a query chip is dropped. It removes the dropzones and initializes the tooltips if the dragged element is the query element target.
+    if (event.target.classList.contains('query-element-target')) {
+      M.Tooltip.init(event.target);
+    }
     document.querySelectorAll('.drop-target').forEach(target => target.remove());
   }
 
@@ -277,24 +298,36 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
   }
 
   selectChipElement(attr) {
-    document.querySelectorAll('.chip.teal').forEach(element => {
-        if (element !== attr) {
-          element.classList.remove('teal', 'lighten-2');
-          this.toggleClass(['token-incidence-modifiers'], 'disabled', 'add');
-        }
-    });
+    if (attr.classList.contains('teal')) {
+      return;
+    }
 
     this.toggleClass(['token-incidence-modifiers'], 'disabled', 'toggle');
     attr.classList.toggle('teal');
     attr.classList.toggle('lighten-5');
+
+    M.Dropdown.getInstance(document.querySelector('.dropdown-trigger[data-toggle-area="token-incidence-modifiers"]')).open();
+
   }
 
-  tokenIncidenceModifierHandler(incidenceModifier, incidenceModifierPretty) {
+  unselectChipElement(attr) {
+    let nModalInstance = M.Modal.getInstance(document.querySelector('#corpus-analysis-concordance-exactly-n-token-modal'));
+    let nmModalInstance = M.Modal.getInstance(document.querySelector('#corpus-analysis-concordance-between-nm-token-modal'));
+    if (nModalInstance.isOpen || nmModalInstance.isOpen) {
+      return;
+    }
+    attr.classList.remove('teal', 'lighten-5');
+    this.toggleClass(['token-incidence-modifiers'], 'disabled', 'add');
+  }
+
+  tokenIncidenceModifierHandler(incidenceModifier, incidenceModifierPretty, nOrNM = false) {
     // Adds a token incidence modifier to the query input field.
     let selectedChip = this.elements.queryInputField.querySelector('.chip.teal');
-    let selectedChipIndex = Array.from(this.elements.queryInputField.children).indexOf(selectedChip);
-    this.submitQueryChipElement('token-incidence-modifier', incidenceModifierPretty, incidenceModifier, selectedChipIndex+1);
-    this.selectChipElement(selectedChip);
+    let selectedChipIndex = Array.from(this.elements.queryChipElements).indexOf(selectedChip);
+    if (nOrNM) {
+      this.unselectChipElement(selectedChip);
+    }
+    this.submitQueryChipElement('token-incidence-modifier', incidenceModifierPretty, incidenceModifier, selectedChipIndex);
   }
 
   tokenNMSubmitHandler(modalId) {
@@ -312,29 +345,30 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
     let instance = M.Modal.getInstance(modal);
     instance.close();
 
-    this.tokenIncidenceModifierHandler(input, pretty_input);
+    this.tokenIncidenceModifierHandler(input, pretty_input, true);
   }
 
-  incidenceModifierEventListeners() {
-    // Eventlisteners for the incidence modifiers. There are two different types of incidence modifiers: token and character incidence modifiers.
-    document.querySelectorAll('.incidence-modifier-selection').forEach(button => {
-      let dropdownId = button.parentNode.parentNode.id;
-      if (dropdownId === 'corpus-analysis-concordance-token-incidence-modifiers-dropdown') {
-        button.addEventListener('click', () => this.tokenIncidenceModifierHandler(button.dataset.token, button.innerHTML));
-      } else if (dropdownId === 'corpus-analysis-concordance-character-incidence-modifiers-dropdown') {
-        button.addEventListener('click', () => this.extensions.tokenAttributeBuilderFunctions.characterIncidenceModifierHandler(button));
-      }
+  expertModeQueryBuilderSwitchHandler() {
+    let queryBuilderDisplay = document.querySelector("#corpus-analysis-concordance-query-builder-display");
+    let expertModeDisplay = document.querySelector("#corpus-analysis-concordance-expert-mode-display");
+    let expertModeSwitch = document.querySelector("#corpus-analysis-concordance-expert-mode-switch");
+    let submitModal = M.Modal.getInstance(document.querySelector('#corpus-analysis-concordance-switch-to-query-builder-submit-modal'));
+    
+    let confirmSwitchToQueryBuilderButton = document.querySelector('.switch-action[data-switch-action="confirm"]');
+    confirmSwitchToQueryBuilderButton.addEventListener("click", () => {
+      queryBuilderDisplay.classList.remove("hide");
+      expertModeDisplay.classList.add("hide");
+      this.switchToQueryBuilderParser();
     });
-  }
 
-  nAndMInputSubmitEventListeners() {
-    // Eventlisteners for the submit of n- and m-values of the incidence modifier modal for "exactly n" or "between n and m".
-    document.querySelectorAll('.n-m-submit-button').forEach(button => {
-      let modalId = button.dataset.modalId;
-      if (modalId === 'corpus-analysis-concordance-exactly-n-token-modal' || modalId === 'corpus-analysis-concordance-between-nm-token-modal') {
-        button.addEventListener('click', () => this.tokenNMSubmitHandler(modalId));
-      } else if (modalId === 'corpus-analysis-concordance-exactly-n-character-modal' || modalId === 'corpus-analysis-concordance-between-nm-character-modal') {
-        button.addEventListener('click', () => this.extensions.tokenAttributeBuilderFunctions.characterNMSubmitHandler(modalId));
+    expertModeSwitch.addEventListener("change", () => {
+      const isChecked = expertModeSwitch.checked;
+      if (isChecked) {
+        queryBuilderDisplay.classList.add("hide");
+        expertModeDisplay.classList.remove("hide");
+        this.switchToExpertModeParser();
+      } else {
+        submitModal.open();
       }
     });
   }
@@ -352,18 +386,13 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
     this.resetQueryInputField();
     let expertModeInputFieldValue = document.querySelector('#corpus-analysis-concordance-form-query').value;
     let chipElements = this.parseTextToChip(expertModeInputFieldValue);
-    let closingTagElements = ['end-sentence', 'end-entity'];
-    let editableElements = ['start-entity',  'token'];
+    let editableElements = ['start-entity', 'token'];
     for (let chipElement of chipElements) {
-      let isClosingTag = closingTagElements.includes(chipElement['type']);
       let isEditable = editableElements.includes(chipElement['type']);
       if (chipElement['query'] === '[]'){
         isEditable = false;
       }
-      this.submitQueryChipElement(chipElement['type'], chipElement['pretty'], chipElement['query'], null, isClosingTag, isEditable);
-      if (isClosingTag) {
-        this.lockClosingChipElement(this.elements.queryChipElements[this.elements.queryChipElements.length-1]);
-      }
+      this.submitQueryChipElement(chipElement['type'], chipElement['pretty'], chipElement['query'], null, false, isEditable);
     }
   }
 

app/static/js/corpus-analysis/query-builder/token-attribute-builder-functions.js

@@ -52,14 +52,14 @@ nopaque.corpus_analysis.query_builder.TokenAttributeBuilderFunctions = class Tok
     let input = this.tokenInputCheck(this.elements.tokenBuilderContent);
     switch (elem) {
       case 'option-group':
-        input.value  += '(option1|option2)';
+        this.cursorPositionInputfieldHandler(input, '(option1|option2)');
         let firstIndex = input.value.indexOf('option1');
         let lastIndex = firstIndex + 'option1'.length;
-        input.focus();
         input.setSelectionRange(firstIndex, lastIndex);
         break;
       case 'wildcard-char':
-        input.value += '.';
+        this.cursorPositionInputfieldHandler(input, '.');
+        input.focus();
         break;
       case 'and':
         this.conditionHandler('and');
@@ -73,9 +73,19 @@ nopaque.corpus_analysis.query_builder.TokenAttributeBuilderFunctions = class Tok
     this.optionToggleHandler();
   }
 
+  cursorPositionInputfieldHandler(input, addedInput) {
+    let cursorPosition = input.selectionStart;
+    let textBeforeCursor = input.value.substring(0, cursorPosition);
+    let textAfterCursor = input.value.substring(cursorPosition);
+    let newInputValue = textBeforeCursor + addedInput + textAfterCursor;
+    input.value = newInputValue;
+    let newCursorPosition = cursorPosition + addedInput.length;
+    input.setSelectionRange(newCursorPosition, newCursorPosition);
+  }
+
   characterIncidenceModifierHandler(elem) {
     let input = this.tokenInputCheck(this.elements.tokenBuilderContent);
-    input.value += elem.dataset.token;
+    this.cursorPositionInputfieldHandler(input, elem.dataset.token);
   }
 
   characterNMSubmitHandler(modalId) {
@@ -83,12 +93,12 @@ nopaque.corpus_analysis.query_builder.TokenAttributeBuilderFunctions = class Tok
     let input_n = modal.querySelector('.n-m-input[data-value-type="n"]').value;
     let input_m = modal.querySelector('.n-m-input[data-value-type="m"]') || undefined;
     input_m = input_m !== undefined ? ',' + input_m.value : '';
-    let input = `${input_n}${input_m}`;
+    let addedInput = `${input_n}${input_m}`;
 
     let instance = M.Modal.getInstance(modal);
     instance.close();
-    let tokenInput = this.tokenInputCheck(this.elements.tokenBuilderContent);
-    tokenInput.value += '{' + input + '}';
+    let input = this.tokenInputCheck(this.elements.tokenBuilderContent);
+    this.cursorPositionInputfieldHandler(input, `{${addedInput}}`);
   }
 
   conditionHandler(conditionText) {

app/templates/_base/_modals/_manual/03_dashboard.html.j2

@@ -8,7 +8,7 @@
       The <a href="{{ url_for('main.dashboard') }}">dashboard</a> provides a central overview of all resources assigned to the
       user. These are <a href="{{ url_for('main.dashboard', _anchor='corpora') }}">corpora</a> and created <a href="{{ url_for('main.dashboard', _anchor='jobs') }}">jobs</a>. Corpora are freely composable
       annotated text collections and jobs are the initiated file processing
-      procedures. Both the job and the corpus listings can be searched using
+      procedures. One can search for jobs as well as corpus listings using
       the search field displayed above them.
     </p>
   </div>
@@ -20,10 +20,10 @@
         <p>
           A corpus is a collection of texts that can be analyzed using the
           Corpus Analysis service. All texts must be in the verticalized text
-          file format, which can be obtained via the Natrual Language
-          Processing service. It contains, in addition to the actual text,
+          file format, which can be obtained via the Natural Language
+          Processing service. It contains, in addition to the text,
           further annotations that are searchable in combination with optional
-          addable metadata during your analysis. 
+          metadata that can be added during your analysis. 
         </p>
       </div>
     </div>

app/templates/_base/_modals/_manual/06_services.html.j2

@@ -35,13 +35,13 @@
 </p>
 
 <h4>Optical Character Recognition (OCR)</h4>
-<p>Comming soon...</p>
+<p>Coming soon...</p>
 
 <h4>Handwritten Text Recognition (HTR)</h4>
-<p>Comming soon...</p>
+<p>Coming soon...</p>
 
 <h4>Natural Language Processing (NLP)</h4>
-<p>Comming soon...</p>
+<p>Coming soon...</p>
 
 <h4>Corpus Analysis</h4>
 <p>

app/templates/_base/_modals/_manual/07_a_closer_look_at_the_corpus_analysis.html.j2

@@ -7,7 +7,7 @@
   <div class="col s12 m8">
     <p>
       To <a href="{{ url_for('corpora.create_corpus') }}">create a corpus</a>, you
-      can use the "New Corpus" button, which can be found on both, the Corpus
+      can use the "New Corpus" button, which can be found on both the Corpus
       Analysis Service page and the Dashboard below the corpus list. Fill in the input
       mask to Create a corpus. After you have completed the input mask, you will
       be automatically taken to the corpus overview page (which can be called up
@@ -43,5 +43,5 @@
   the way of how a token is displayed, by using the text style switch. The
   concordance module offers some more options regarding the context size of
   search results. If the context does not provide enough information you can
-  hop into the reader module by using the lupe icon next to a match.
+  hop into the reader module by using the magnifier icon next to a match.
 </p>

app/templates/_base/_modals/_manual/09_query_builder.html.j2

@@ -1,22 +1,30 @@
 <h3 class="manual-chapter-title">Query Builder Tutorial</h3>
-
-<p>The query builder helps you to make a query in the form of the Corpus Query 
-Language (CQL) to your text. You can use the CQL to filter out various types of 
-text parameters, for example, a specific word, a lemma, or you can set part-of-speech 
+<h4>Overview</h4>
+<p>The query builder can be accessed via "My Corpora" or "Corpus Analysis" in the sidebar options. 
+Select the desired corpus and click on the "Analyze" and then "Concordance"
+buttons to open the query builder.</p>
+<p>The query builder uses the Corpus Query Language (CQL) to help you make a query for analyzing your texts. 
+In this way, it is possible to filter out various types of text parameters, for 
+example, a specific word, a lemma, or you can set part-of-speech 
 tags (pos) that indicate the type of word you are looking for (a noun, an 
 adjective, etc.). In addition, you can also search for structural attributes, 
 or specify your query for a token (word, lemma, pos) via entity typing. And of 
-course everything can be combined. You can find examples for different queries 
-under the tab "Examples".</p>
-<p></p>
+course, the different text parameters can be combined.</p>
+<p>Tokens and structural attributes can be added by clicking on the "+" button
+(the "input marker") in the input field or the labeled buttons below it. Elements 
+added are shown as chips. These can be reorganized using drag and drop. The input 
+marker can also be moved in this way. Its position shows where new elements will be added. <br>
+A "translation" of your query into Corpus Query Language (CQL) is shown below.</p>
+<p>Advanced users can make direct use of the Corpus Query Language (CQL) by switching to "expert mode" via the toggle button.</p>
+<p>The entire input field can be cleared using the red trash icon on the right.</p>
 <br>
 
 <div style="border: 1px solid; padding-left: 20px; margin-right: 400px; margin-bottom: 40px;">
   <h5>Content</h5>
   <ol style="list-style-type:disc">
-    <li><a href="#add-new-token-tutorial">Add new token to your query</a></li>
-    <li><a href="#edit-options-tutorial">Options to edit your query</a></li>
-    <li><a href="#add-structural-attribute-tutorial">Add structural Attributes to your query</a></li>
+    <li><a href="#add-new-token-tutorial">Add a new token to your query</a></li>
+    <li><a href="#edit-options-tutorial">Options for editing your query</a></li>
+    <li><a href="#add-structural-attribute-tutorial">Add structural attributes to your query</a></li>
     <li><a href="#general-options-query-builder">General options</a></li>
   </ol>
 </div>
@@ -30,7 +38,7 @@ under the tab "Examples".</p>
   <p>If you are only looking for a specific token, you can click on the left 
   button and select the type of token you are looking for from the drop-down menu. 
   By default "Word" is selected. </p>
-
+  <br>
   <h5>Word and Lemma</h5>
   <p>If you want to search for a specific word or lemma and the respective 
   category is selected in the drop-down menu, you can type in the word or lemma 
@@ -46,13 +54,13 @@ under the tab "Examples".</p>
   "simple_pos" to search for different parts-of-speech. You can find an overview 
   of all tags under the "Tagsets" tab.</p>
   <img src="{{ url_for('static', filename='images/manual/query_builder/pos.gif') }}" alt="part-of-speech-tag explanation" width="100%;" style="margin-bottom:20px;">
+  <br>
 
   <h5>Empty Token</h5>
-  <p>Here you can search for an empty token. This selection should never stand 
-  alone and should always be extended with an incidence modifier or stand in a 
+  <p>Here you can search for a token with unspecified attributes (also called wildcard token). This 
+  selection should never stand alone and should always be extended with an incidence modifier or stand in a 
   larger query, because otherwise all possible tokens would be searched for and 
   the program would crash.</p>
-  <p></p>
   <br>
 </div>
 
@@ -61,8 +69,8 @@ under the tab "Examples".</p>
   <hr>
   <p></p>
   <br>
-  <h4 id="edit-options-tutorial">Options to edit your token</h4> 
-  <p>You have the possibility to extend or specify your searched token with 
+  <h4 id="edit-options-tutorial">Options for editing your query</h4> 
+  <p>You have the possibility to extend or specify the token you are searching for with 
   certain factors. For this the query builder offers some fixed options. You can 
   find more information about the options in the Corpus Query Language Tutorial.</p>
   <br>
@@ -76,7 +84,6 @@ under the tab "Examples".</p>
   variants are not limited, so you can manually enter more options in the same 
   format. "Option1" and "option2" must be replaced accordingly. </p>
   <img src="{{ url_for('static', filename='images/manual/query_builder/option_group.gif') }}" alt="option group explanation" width="100%;" style="margin-bottom:20px;">
-  <p></p>
   <br>
 
   <h5>Incidence Modifiers</h5>
@@ -85,7 +92,7 @@ under the tab "Examples".</p>
   not at all or once: <br> 
   [word = "is"] [word="it"] [word="your"] [word="litte"]? [word = "dog"] <br>
   Here the word "little" should occur either once or not at all. With 
-  [word="dogs?"] the search is for "dog "or "dogs". </p>
+  [word="dogs?"] the search is for "dog "or "dogs".</p>
   <br>
 
   <h5>Ignore Case</h5>
@@ -101,7 +108,10 @@ under the tab "Examples".</p>
   this case. For this you can simply string them together: <br>
   [word="I"] [word="will" & simple_pos="VERB"] [word="go"].</p>
   <img src="{{ url_for('static', filename='images/manual/query_builder/or_and.gif') }}" alt="OR/AND explanation" width="100%;" style="margin-bottom:20px;">
-  <p></p>
+  <p>Tokens that have already been added can also be modified by clicking on the corresponding 
+  pen icon. Click on the "ignore case" box, for example, and the query builder will 
+  not differentiate between upper- and lower- case letters for that respective token. 
+  New conditions added apply to the most recent token information.</p>
   <br>
 </div>
 
@@ -120,26 +130,33 @@ under the tab "Examples".</p>
   This search can of course be specified if you search for particular tokens or 
   entities between the sentence tags (<s></s>). For example, you can search for
   sentences that contain only a noun, verb, and adjective. <br> 
-  After clicking on Sentence you will see a <div class="chip" style="background-color:#FD9720;">Sentence Start</div>.
-  When you are done with your query or the content 
-  between the Sentence tags, you have to click the Sentence button one more time 
-  to close it. The corresponding button is called 
-  <div class="chip" style="background-color:#FD9720;">Sentence End</div>.<br>
+  Click on Sentence to add the sentence chips: <div class="chip" style="background-color:#FD9720;">Sentence Start</div> 
+  and <div class="chip" style="background-color:#FD9720;">Sentence End</div>. 
+  These mark where the sentence starts and ends. Use drag-and-drop to place them accordingly. When 
+  the Sentence attribute is added, the input marker will automatically be 
+  moved between the sentence chips. Use drag-and-drop as needed to continue your query 
+  at a different position.
   <br>
 
   <h5>Entities</h5>
-  <p>With entities, i.e. units of meaning, you search for text sections that 
-  follow a certain code. For example, persons, dates, certain events. You can 
-  select the codes using the drop-down menus. You can find an explanation of 
-  the respective abbreviations under the tab "Tagsets". <br>
+  <p>With entities, i.e. units of meaning, you can search for text sections that 
+  contain more specific information, for example, persons, dates, or events. The 
+  codes for these categories can be selected using the drop-down menus. You can find an explanation of 
+  these abbreviations under the tab "Tagsets". <br>
   You can also search for unspecified entities by selecting "Add entity of any type".</p>
-  To close the entity query you started, you have to click the entity button one more time. This will make the <div class="chip" style="background-color:#A6E22D;">Entity End</div> element appear in your query.
+  Click on the Entity button to add the entity chips <div class="chip" style="background-color:#A6E22D;">Entity Type=</div> and <div class="chip" style="background-color:#A6E22D;">Entity End</div>.
+  <p>The entity type can be changed by clicking on the pen symbol on the chip. When 
+  the Entity attribute is added, the input marker will automatically be 
+  moved between the entity chips. Use drag-and-drop as needed to continue your query 
+  at a different position.</p>
   <img src="{{ url_for('static', filename='images/manual/query_builder/entity.gif') }}" alt="entity explanation" width="100%;" style="margin-bottom:20px;">
   <p></p>
   <br>
 
-  <h5>Meta Data</h5>
-  <p>With the meta data you can annotate your text and add specific conditions. 
+  <h5>Meta Data (currently unavailable)</h5>
+  <p>The meta data function is being worked on and cannot currently be used!
+  <br>
+  With the meta data you can annotate your text and add specific conditions. 
   You can select a category on the left and enter your desired value on the right. 
   The selected metadata will apply to your entire request and will be added at the end.</p>
   <img src="{{ url_for('static', filename='images/manual/query_builder/meta_data.gif') }}" alt="meta data explanation" width="100%;" style="margin-bottom:20px;">
@@ -155,14 +172,39 @@ under the tab "Examples".</p>
   <br>
   <h4 id="general-options-query-builder">General Options of the query builder</h4>
   <p>You have several options to edit your query after adding it to the preview.</p>
+  <br>
+
+  <h5>Editing the elements</h5>
+  <p>You can edit your query chips by clicking on the pen icon.</p>
+  <img src="{{ url_for('static', filename='images/manual/query_builder/editing_chips.gif') }}" alt="editing explanation" width="100%;" style="margin-bottom:20px;">
+  <br>
 
   <h5>Deleting the elements</h5>
   <p>You can delete the added elements from the query by clicking the X behind the respective content.</p>
   <img src="{{ url_for('static', filename='images/manual/query_builder/delete.gif') }}" alt="delete explanation" width="100%;" style="margin-bottom:20px;">
+  <br>
 
   <h5>Move the elements of your query</h5>
   <p>You can drag and drop elements to customize your query.</p>
   <img src="{{ url_for('static', filename='images/manual/query_builder/drag_and_drop.gif') }}" alt="Drag&Drop explanation" width="100%;" style="margin-bottom:20px;">
+  <br>
+
+  <h5>Setting an incidence modifier</h5>
+  <p>With the incidence modifier option, you can specify the amount of 
+  times a token should appear in your query. This is particularly relevant for empty
+  tokens (tokens with unspecified attributes). Click on a token (blue chip) and 
+  select the desired option from the list to add an incidence modifier. To 
+  close the list without adding anything, click on the token again.</p>
+  <img src="{{ url_for('static', filename='images/manual/query_builder/incidence_modifier.gif') }}" alt="incidence modifier explanation" width="100%;" style="margin-bottom:20px;">
+  <br>
+  
+  <h5>Switching between Query Builder and Expert mode</h5>
+  <p>To work with the plain Corpus Query Language instead of using the Query Builder, click on the "expert mode" 
+  switch. Your query can be entered into the input field. All elements previously added will be carried over 
+  into expert mode. Click on the switch again to switch back to the Query Builder if desired. All recognized elements 
+  will be parsed into chips; those not recognized will be deleted from the query.</p>
+  <img src="{{ url_for('static', filename='images/manual/query_builder/expert_mode.gif') }}" alt="expert mode explanation" width="100%;" style="margin-bottom:20px;">
+
 
 </div>
 

app/templates/_base/_modals/terms_of_use.html.j2

@@ -5,111 +5,28 @@
         <div class="col s12">
           <h1 id="title">Terms of use</h1>
         </div>
-
         <div class="col s12">
-          <p>With the usage of the nopaque platform you declare your acceptance of the General Terms of Use and that you have taken note of the legal framework and the data protection declaration.</p>
-        </div>
-
-        <div class="col s12">
-          <div class="card">
-            <div class="card-content">
-              <span class="card-title">§ 1 Scope</span>
-              <p>The General Terms of Use for the nopaque platform apply to everyone who uses the system as an authorised user in the sense of <b>§ 2</b> (1) of the General Terms of Use. By using the system and with your consent you accept these terms of use.</p>
-            </div>
+          <div class="switch">
+            <label>
+              DE
+              <input type="checkbox" id="terms-of-use-modal-switch">
+              <span class="lever"></span>
+              EN
+            </label>
           </div>
+          <br>
         </div>
-
-        <div class="col s12">
-          <div class="card">
-            <div class="card-content">
-              <span class="card-title">§ 2 Right of use</span>
-              <p>(1) The nopaque platform is available to users exclusively for the purposes of teaching and research. Any other use, especially for business, commercial is not permitted. The following groups shall be entitled to use the nopaque platform:</p>
-              <ul class="browser-default">
-                <li>students, teaching staff and employees at Bielefeld University</li>
-                <li>external researchers from outside the University Bielefeld</li>
-              </ul>
-              <p>&nbsp;</p>
-              <p>(2) The use of the system is free of charge.</p>
-              <p>&nbsp;</p>
-              <p>(3) The duration of the right of use ends with the deletion of the user account by the user (see <b>§ 7</b>)</p>
-            </div>
-          </div>
+        <div class="terms-of-use-modal-content hide">
+          {% include "main/terms_of_use_en.html.j2" %}
         </div>
-
-        <div class="col s12">
-          <div class="card">
-            <div class="card-content">
-              <span class="card-title">§ 3 Purpose of the Services</span>
-              <p>nopaque custom-built web application which serves as a platform for preprocessing and analysing digital copies of various text based research data (books, letters, etc.) in different files and formats. nopaque converts image data – like photos or scans – into text data through OCR making it machine readable. This step enables to proceed with further computational analysis of the documents. By means of computational linguistic data processing (tokenization, lemmatization, part-of-speech tagging and named-entity recognition) nopaque extracts additional information from texts.</p>
-              <p>&nbsp;</p>
-              <p>(1) Change of service</p>
-              <p>The provider of the nopaque platform is entitled to change and supplement the scope of functions of nopaque without prior notice. This could result from a thematic and scientific reorientation of the project.</p>
-              <p>&nbsp;</p>
-              <p>(2) Support</p>
-              <p>On nopaque, a contact form is available. As far as possible the SFB 1288 INF staff will try to provide user support.</p>
-            </div>
-          </div>
+        <div class="terms-of-use-modal-content">
+          {% include "main/terms_of_use_de.html.j2" %}
         </div>
-
-        <div class="col s12">
-          <div class="card">
-            <div class="card-content">
-              <span class="card-title">§ 4 Obligations of the User</span>
-              <p>(1) The system is suitable for normal security requirements. Data with a high need for protection (e.g. health data) may not be stored or processed in the nopaque platform.</p>
-              <p>&nbsp;</p>
-              <p>(2) Users of nopaque are responsible for their own entered contents. The uploading of illegal content, especially content that violates criminal, personal, data protection or copyright regulations (including § 60a) is not permitted.</p>
-              <p>&nbsp;</p>
-              <p>(3) Users undertake to indemnify Bielefeld University from all claims by third parties based on the data they use and to reimburse Bielefeld University for any costs incurred by the latter due to possible infringements of rights. This also includes the costs incurred by Bielefeld University in defending itself against such claims in and out of court.</p>
-              <p>&nbsp;</p>
-              <p>(4) Exclusion from use</p>
-              <p>Bielefeld University is entitled to immediately block access to the service if there are reasonable grounds to suspect that the stored data is unlawful (e.g upload harmful files via file upload) and/or violates the rights of third parties. Other infringements of the provisions of these Terms of Use, in particular the obligations under §6 also entitle Bielefeld University to block the user. Bielefeld University shall immediately notify the user of the block and the reason for the block. The block must be lifted as soon as the suspicion is invalidated.</p>
-              <p>&nbsp;</p>
-              <p>(5) Usage of Data</p>
-              <p>The data stored by the user on the storage space intended for him may be legally protected, the responsibility for the processing of the data from these points of view lies solely with the user. By using nopaque, the user grants Bielefeld the right to process the data with the corresponding tools. At all times during processing in nopaque, data remains in the user's private storage location and will not passed on to third parties.</p>
-              <p>&nbsp;</p>
-              <p>(6) Release of Bielefeld University from Third-Party Claims</p>
-              <p>The user is responsible for the data stored by him/her in nopaque. Furthermore he/she is responsible for entering and maintaining the data and information required to use nopaque.</p>
-              <p>&nbsp;</p>
-              <p>The user is obliged to indemnify Bielefeld University against all claims by third parties based on the data stored by him/her and to reimburse Bielefeld University for any costs incurred as a result of possible legal infringements. This also includes the costs incurred by Bielefeld University for extrajudicial and judicial defense against these claims.</p>
-            </div>
-          </div>
-        </div>
-
-        <div class="col s12">
-          <div class="card">
-            <div class="card-content">
-              <span class="card-title">§ 5 Liability of Bielefeld University</span>
-              <p>Claims for damages against Bielefeld University are excluded irrespective of the legal grounds. Bielefeld University shall not be liable for loss of data and information or other „indirect“ damages, e.g. loss of profit, loss of production, or other indirect damages. Bielefeld University shall not be liable for the loss of data to the extent that the damage is due to the fact that the user has failed to back up the data and thereby ensure that lost data can be restored with justifiable effort.</p>
-              <p>&nbsp;</p>
-              <p>nopaque is available in accordance with normal operational care based on the "Best Effort" practice. No liability is assumed for the consequences of failures or errors of the nopaque platform. Bielefeld University does not guarantee that the systems will run error-free and without interruption at all times. Bielefeld University accepts no responsibility for technical quality. Nor is it liable for the content, in particular for the accuracy, completeness, and timeliness of information to which it merely provides access for use.</p>
-            </div>
-          </div>
-        </div>
-
-        <div class="col s12">
-          <div class="card">
-            <div class="card-content">
-              <span class="card-title">§ 6 Data Protection</span>
-              <p>Information on the handling of personal data during the operation of the service can be found in the separate data protection policy.</p>
-            </div>
-          </div>
-        </div>
-
-        <div class="col s12">
-          <div class="card">
-            <div class="card-content">
-              <span class="card-title">§ 7 Duration and Termination</span>
-              <p>The user may terminate the use nopaque by deleting his/her account at any time without giving reasons. After deletion of the account, all users‘ data will be automatically deleted and access to the service blocked. This does not affect the user's right to delete data under data protection law.</p>
-              <p>&nbsp;</p>
-              <p>Bielefeld University may exclude the user from using the service without notice for an important reason. Important reasons include, in particular, repeated violations of the provisions of these Terms of Use or of applicable laws.</p>
-            </div>
-          </div>
-        </div>
-
       </div>
     </div>
   </div>
   <div class="modal-footer">
-    <a href="#!" class="modal-close waves-effect waves-green btn-flat">Accept</a>
+    <span style="margin-right:20px;">I have taken note of the new GTC and agree to their validity in the context of my further use.</span>
+    <a href="#!" class="modal-close waves-effect waves-green btn">Yes</a>
   </div>
 </div>

app/templates/_base/footer.html.j2

@@ -27,7 +27,10 @@
       <div class="col s12 m3">
         <span>© 2020 Bielefeld University</span>
       </div>
-      <div class="col s12 m9 right-align">
+      <div class="col s12 m2">
+        <span class="right"><b>Version {{ config.NOPAQUE_VERSION }}</b></span>
+      </div>
+      <div class="col s12 m7 right-align">
         <a class="btn-small primary-variant-color waves-effect waves-light" href="{{ url_for('main.faq') }}"><i class="left material-icons">info_outline</i>Frequently Asked Questions</a>
         <a class="btn-small primary-variant-color waves-effect waves-light" href="mailto:{{ config.NOPAQUE_SERVICE_DESK }}"><i class="left material-icons">mail</i>Report an issue</a>
         <a class="btn-small primary-variant-color waves-effect waves-light" href="https://gitlab.ub.uni-bielefeld.de/sfb1288inf/nopaque" target="_blank"><i class="left material-icons">code</i>GitLab</a>

app/templates/_base/navbar.html.j2

@@ -5,7 +5,6 @@
       <a href="#" data-target="sidenav" class="sidenav-trigger"><i class="material-icons">menu</i></a>
       {% endif %}
       <a href="{{ url_for('main.index') }}" class="brand-logo" style="height: 100%; overflow: hidden;">
-        <img class="hide-on-small-only" src="{{ url_for('static', filename='images/nopaque_-_logo_name_slogan.svg') }}" style="height: 128px; margin-top: -32px; margin-left: -32px;">
         <img class="hide-on-med-and-up" src="{{ url_for('static', filename='images/nopaque_-_logo.svg') }}" style="height: 128px; margin-top: -32px; margin-left: -32px;">
       </a>
       <ul class="right hide-on-med-and-down">
@@ -31,14 +30,14 @@
         {% endif %}
         {%- endfor -%}
       </ul>
-      <a class="btn-floating btn-large halfway-fab modal-trigger pink tooltipped waves-effect waves-light" data-tooltip="Manual" href="#manual-modal"><i class="material-icons">help</i></a>
+      <a class="btn-floating btn-large halfway-fab modal-trigger pink tooltipped waves-effect waves-light" data-tooltip="Manual" href="#manual-modal"><i class="material-icons">school</i></a>
     </div>
   </nav>
 </div>
 
 <ul class="dropdown-content" id="nav-more-dropdown">
-  {# <li><a href="{{ url_for('main.user_manual') }}"><i class="material-icons left">help</i>Manual</a></li> #}
   {% if current_user.is_authenticated %}
+  <li><a href="{{ url_for('users.user', user_id=current_user.id) }}"><i class="material-icons left">person</i>My Profile</a></li>
   <li><a href="{{ url_for('settings.settings') }}"><i class="material-icons left">settings</i>Settings</a></li>
   <li class="divider" tabindex="-1"></li>
   <li><a href="{{ url_for('auth.logout') }}">Log out</a></li>

app/templates/_base/scripts.html.j2

@@ -131,3 +131,15 @@
     app.flash(message, message);
   }
 </script>
+
+<script>
+  let languageModalSwitch = document.querySelector('#terms-of-use-modal-switch');
+  let termsOfUseModalContent = document.querySelectorAll('.terms-of-use-modal-content');
+  if (languageModalSwitch) {
+    languageModalSwitch.addEventListener('change', function() {
+      termsOfUseModalContent.forEach(content => {
+        content.classList.toggle('hide');
+      });
+    });
+  }
+</script>

app/templates/_base/sidenav.html.j2

@@ -1,19 +1,18 @@
 <ul class="sidenav sidenav-fixed" id="sidenav">
-  <li>
-    <div class="user-view">
-      <div class="background primary-color"></div>
-    </div>
+  <li class="primary-color hide-on-small-only">
+      <div style="overflow: hidden; height: 64px; width: 250px;">
+        <a href="{{ url_for('main.index') }}">
+          <img class="hide-on-small-only" src="{{ url_for('static', filename='images/nopaque_-_logo_name_slogan.svg') }}" style="height: 128px; margin-top: -32px;">
+        </a>
+      </div>
   </li>
-  {# <li class="primary-color">
-    <div style="overflow: hidden;height: 64px; width: 250px;">
-      <img class="hide-on-small-only" src="{{ url_for('static', filename='images/nopaque_-_logo_name_slogan.svg') }}" style="height: 128px; margin-top: -32px; margin-left: ;">
-    </div>
-  </li> #}
-  <li><a href="{{ url_for('main.index') }}"><i class="material-icons left">home</i>nopaque</a></li>
+  <li class="primary-variant-color center-align hide-on-small-only" style="padding-top: 8px; height:48px;">
+    <img src="{{ url_for('static', filename='images/nopaque_slogan_transparent.png') }}" style="width:85%">
+  </li>
+  <li class="hide-on-med-and-up"><a class="waves-effect" href="{{ url_for('main.index') }}"><i class="material-icons left">home</i>nopaque</a></li>
   <li>
     <a class="waves-effect" href="{{ url_for('main.news') }}"><i class="material-icons left">email</i>News</a>
   </li>
-  {# <li><a href="{{ url_for('main.user_manual') }}"><i class="material-icons">help</i>Manual</a></li> #}
   <li>
     <a class="waves-effect" class="waves-effect" href="{{ url_for('main.dashboard') }}"><i class="material-icons">dashboard</i>Dashboard</a>
     <ul>
@@ -51,12 +50,13 @@
   <li>
     <a class="waves-effect" class="waves-effect" href="{{ url_for('main.social_area') }}"><i class="material-icons">rocket_launch</i>Social Area</a>
     <ul>
-  <li>
-    <a class="waves-effect" href="{{ url_for('main.social_area', _anchor='public-users') }}" style="padding-left: 47px;"><i class="material-icons">person</i>Public Users</a>
-  </li>
-  <li>
-    <a class="waves-effect" href="{{ url_for('main.social_area', _anchor='public-corpora') }}" style="padding-left: 47px;"><i class="nopaque-icons">I</i>Public Corpora</a>
-  </li>
+      <li><a href="{{ url_for('users.user', user_id=current_user.id) }}" style="padding-left: 47px;"><i class="material-icons left">person</i>My Profile</a></li>
+      <li>
+        <a class="waves-effect" href="{{ url_for('main.social_area', _anchor='public-users') }}" style="padding-left: 47px;"><i class="material-icons">group</i>Public Users</a>
+      </li>
+      <li>
+        <a class="waves-effect" href="{{ url_for('main.social_area', _anchor='public-corpora') }}" style="padding-left: 47px;"><i class="nopaque-icons">I</i>Public Corpora</a>
+      </li>
     </ul>
   </li>
   <li class="hide-on-large-only"><div class="divider"></div></li>

app/templates/corpora/_analysis/query_builder/_expert_mode.html.j2

@@ -23,4 +23,15 @@
     </div>
   </form>
 </div>
+
+<div id="corpus-analysis-concordance-switch-to-query-builder-submit-modal" class="modal">
+  <div class="modal-content">
+    <h4>Switch to Query Builder</h4>
+    <p>Switching back to the query builder can cause elements the query builder does not recognize to become lost. Continue?</p>
+  </div>
+  <div class="modal-footer">
+    <a class="btn modal-close waves-effect waves-light">Cancel</a>
+    <a class="btn modal-close red waves-effect waves-light switch-action" data-switch-action="confirm">Switch to Query Builder</a>
+  </div>
+</div>
 {% endmacro %}

app/templates/corpora/_analysis/query_builder/_query_builder.html.j2

@@ -1,11 +1,18 @@
 {% macro card_content(id_prefix) %}
 <form id="corpus-analysis-concordance-query-builder-form">
   <div class="row">
-    <div class="col s9" id="corpus-analysis-concordance-query-builder-input-field-container">
+    <div class="col s8" id="corpus-analysis-concordance-query-builder-input-field-container">
       <div id="corpus-analysis-concordance-query-builder-input-field">
-        <p id="corpus-analysis-concordance-query-builder-input-field-placeholder">Click on the buttons below to build your query.</p>
+        <a class="query-element-target btn-floating btn-small blue-grey lighten-4 waves-effect waves-light tooltipped" style="margin-bottom:10px; margin-right:5px;" draggable="true" data-position="bottom" data-tooltip="Add a token to your query">
+          <i class="material-icons">add</i>
+        </a>
       </div>
     </div>
+    <div class="col s1 center-align">
+      <a class="btn-floating btn waves-effect waves-light red" id="corpus-analysis-concordance-delete-query-button" style="margin-top:18px;">
+        <i class="material-icons">delete</i>
+      </a>
+    </div>
     <div class="input-field col s3">
       <i class="material-icons prefix">arrow_forward</i>
       <input class="validate corpus-analysis-action" id="corpus-analysis-concordance-form-subcorpus-name" name="subcorpus-name" type="text" required pattern="^[A-Z][a-z0-9\-]*" value="Last"></input>
@@ -30,9 +37,10 @@
   <div class="row">
     <div class="col s12">
       <p></p>
-      <a class="btn waves-effect waves-light tooltipped modal-trigger" href="#corpus-analysis-concordance-positional-attr-modal" data-position="bottom" data-tooltip="Search for any token, for example a word, a lemma or a part-of-speech tag">Add new token to your query</a>
-      <a class="btn waves-effect waves-light tooltipped modal-trigger" href="#corpus-analysis-concordance-structural-attr-modal" data-position="bottom" data-tooltip="Structure your query with structural attributes, for example sentences, entities or annotate the text">Add structural attributes to your query</a>
-      <a class="btn waves-effect waves-light tooltipped dropdown-trigger disabled" data-target="corpus-analysis-concordance-token-incidence-modifiers-dropdown" data-toggle-area="token-incidence-modifiers" data-position="top" data-tooltip="Incidence Modifiers are special characters or patterns, <br>which determine how often a character represented previously should occur.">incidence modifiers</a>
+      <a class="btn-small waves-effect waves-light tooltipped modal-trigger" href="#corpus-analysis-concordance-positional-attr-modal" data-position="bottom" data-tooltip="Search for any token, for example a word, a lemma or a part-of-speech tag">Add new token to your query</a>
+      <a class="btn-small waves-effect waves-light tooltipped modal-trigger" href="#corpus-analysis-concordance-structural-attr-modal" data-position="bottom" data-tooltip="Structure your query with structural attributes, for example sentences, entities or annotate the text">Add structural attributes to your query</a>
+      <a class="btn-small waves-effect waves-light tooltipped dropdown-trigger disabled" data-target="corpus-analysis-concordance-token-incidence-modifiers-dropdown" data-toggle-area="token-incidence-modifiers" data-position="top" data-tooltip="Incidence Modifiers are special characters or patterns, <br>which determine how often a character represented previously should occur.">incidence modifiers</a>
+      <a class="modal-trigger" data-manual-modal-chapter="manual-modal-query-builder" href="#manual-modal"><i class="material-icons left" style="color:black">help_outline</i></a>
     </div>
   </div>
   <div class="row">
@@ -59,7 +67,7 @@
 <div id="corpus-analysis-concordance-structural-attr-modal" class="modal">
   <div class="modal-content">
     <div class="attr-modal-header">
-      <h5>Which structural attribute do you want to add to your query?<a class="modal-trigger" data-manual-modal-chapter="manual-modal-query-builder" href="#manual-modal"><i class="material-icons left" id="corpus-analysis-concordance-add-structural-attribute-tutorial-info-icon">help_outline</i></a></h5>
+      <h5>Which structural attribute do you want to add to your query?<a class="modal-trigger" data-manual-modal-chapter="manual-modal-query-builder" data-manual-modal-chapter-anchor="add-structural-attribute-tutorial" href="#manual-modal"><i class="material-icons left" id="corpus-analysis-concordance-add-structural-attribute-tutorial-info-icon">help_outline</i></a></h5>
     </div>
     <p></p>
     <br>
@@ -120,7 +128,7 @@
     <div class="row attr-modal-header">
       <p></p>
       <div class="col s12">
-        <h5>Which kind of token are you looking for? <a class="modal-trigger" data-manual-modal-chapter="manual-modal-query-builder" href="#manual-modal"><i class="material-icons left" id="corpus-analysis-concordance-token-tutorial-info-icon">help_outline</i></a></h5>
+        <h5>Which kind of token are you looking for? <a class="modal-trigger" data-manual-modal-chapter="manual-modal-query-builder" data-manual-modal-chapter-anchor="add-new-token-tutorial" href="#manual-modal"><i class="material-icons left" id="corpus-analysis-concordance-token-tutorial-info-icon">help_outline</i></a></h5>
       </div>
       <div class="input-field col s3" style="margin-left:42px;">
         <select id="corpus-analysis-concordance-positional-attr-selection">
@@ -329,7 +337,7 @@
     </div>
     <div id="corpus-analysis-concordance-token-edit-options" data-toggle-area="input-field-options">
       <div class="row">
-        <h6>Options to edit your token: <a class="modal-trigger" data-manual-modal-chapter="manual-modal-query-builder" href="#manual-modal"><i class="material-icons left" id="corpus-analysis-concordance-edit-options-tutorial-info-icon">help_outline</i></a></h6>
+        <h6>Options to edit your token: <a class="modal-trigger" data-manual-modal-chapter="manual-modal-query-builder" href="#manual-modal" data-manual-modal-chapter-anchor="edit-options-tutorial"><i class="material-icons left" id="corpus-analysis-concordance-edit-options-tutorial-info-icon">help_outline</i></a></h6>
       </div>
       <p></p>
       <div class="row">
@@ -402,9 +410,3 @@
   </div>
 </div>
 {% endmacro %}
-
-{# {% macro scripts(id_prefix) %}
-<script>
-  const concordanceQueryBuilder = new ConcordanceQueryBuilder();
-</script>
-{% endmacro %} #}

app/templates/corpora/public_corpus.html.j2

@@ -273,7 +273,7 @@ publicCorpusFollowerList.add(
 {% if cfr.has_permission('MANAGE_FILES') %}
 let followerBuildRequest = document.querySelector('#follower-build-request');
 followerBuildRequest.addEventListener('click', () => {
-  requests.corpora.entity.build({{ corpus.hashid|tojson }})
+  nopaque.requests.corpora.entity.build({{ corpus.hashid|tojson }})
     .then((response) => {
       window.location.reload();
     });
@@ -285,7 +285,7 @@ followerBuildRequest.addEventListener('click', () => {
 {% if current_user.is_following_corpus(corpus) %}
   let unfollowRequestElement = document.querySelector('.action-button[data-action="unfollow-request"]');
   unfollowRequestElement.addEventListener('click', () => {
-    requests.corpora.entity.followers.entity.delete({{ corpus.hashid|tojson }}, {{ current_user.hashid|tojson }})
+    nopaque.requests.corpora.entity.followers.entity.delete({{ corpus.hashid|tojson }}, {{ current_user.hashid|tojson }})
       .then((response) => {
         window.location.reload();
       });
@@ -335,7 +335,7 @@ M.Modal.init(
 
 inviteUserModalInviteButtonElement.addEventListener('click', (event) => {
   let usernames = inviteUserModalSearch.chipsData.map((chipData) => chipData.tag);
-  requests.corpora.entity.followers.add({{ corpus.hashid|tojson }}, usernames)
+  nopaque.requests.corpora.entity.followers.add({{ corpus.hashid|tojson }}, usernames)
     .then((response) => {
       window.location.reload();
     });
@@ -383,7 +383,7 @@ M.Modal.init(
 shareLinkModalCreateButtonElement.addEventListener('click', (event) => {
   let role = shareLinkModalCorpusFollowerRoleSelectElement.value;
   let expiration = shareLinkModalExpirationDateDatepickerElement.value
-  requests.corpora.entity.generateShareLink({{ corpus.hashid|tojson }}, role, expiration)
+  nopaque.requests.corpora.entity.generateShareLink({{ corpus.hashid|tojson }}, role, expiration)
     .then((response) => {
       response.json()
         .then((json) => {

app/templates/jobs/job.html.j2

@@ -153,16 +153,16 @@
   let deleteJobRequestElement = document.querySelector('#delete-job-request');
   let restartJobRequestElement = document.querySelector('#restart-job-request');
   deleteJobRequestElement.addEventListener('click', (event) => {
-       requests.jobs.entity.delete({{ job.hashid|tojson }});
+       nopaque.requests.jobs.entity.delete({{ job.hashid|tojson }});
     });
   restartJobRequestElement.addEventListener('click', (event) => {
-      requests.jobs.entity.restart({{ job.hashid|tojson }});
+      nopaque.requests.jobs.entity.restart({{ job.hashid|tojson }});
   });
 
   if ({{ current_user.is_administrator()|tojson }}) {
     let jobLogButtonElement = document.querySelector('#job-log-button');
     jobLogButtonElement.addEventListener('click', (event) => {
-      requests.jobs.entity.log({{ job.hashid|tojson }})
+      nopaque.requests.jobs.entity.log({{ job.hashid|tojson }})
       .then(
         (response) => {
           response.json()

app/templates/main/privacy_policy.html.j2

@@ -8,14 +8,14 @@
     </div>
 
     <div class="col s12">
-      <p>With these data protection notices, Bielefeld University fulfils its obligation to provide information in accordance with Articles 13 & 14 of the EU General Data Protection Regulation (GDPR) on the above-mentioned processing of personal data. Terms such as "personal data", "processing", "data controller", "third party", etc. are used as defined in Article 4 GDPR.</p>
+      <p>With these data protection notices, Bielefeld University fulfils its obligation to provide information in accordance with Articles 13 & 14 of the <b>EU General Data Protection Regulation (GDPR)</b> on the above-mentioned processing of personal data. Terms such as "personal data", "processing", "data controller", "third party", etc. are used as defined in <b>Article 4 GDPR</b>.</p>
     </div>
 
     <div class="col s12">
       <div class="card">
         <div class="card-content">
           <span class="card-title">§ 1 Contact Details</span>
-          <p>Bielefeld University, a legal entity under public law established by the state of North Rhine-Westphalia (NRW), is responsible for processing the data. It is represented by its rector, Prof. Dr. Ing. Gerhard Sagerer.</p>
+          <p>Bielefeld University, a legal entity under public law established by the state of North Rhine-Westphalia (NRW), is responsible for processing the data. It is represented by its rector, Prof. Dr. Angelika Epple.</p>
           <h6>§ 1.1. Contact details of the data controller</h6>
           <ul class="browser-default">
             <li>Data protection officer of the Faculty of History</li>
@@ -34,10 +34,10 @@
           <ul class="browser-default">
             <li>Dr. Johanna Vompras</li>
             <li>Email:
-              <a href="mailto:johanna.vompras@uni-bielefeld.de">johanna.vompras@uni-bielefeld.de</a>
+              <a href="mailto:nopaque@uni-bielefeld.de">nopaque@uni-bielefeld.de</a>
             </li>
             <li>Web.:
-              <a href="https://www.uni-bielefeld.de/(en)/sfb1288/projekte/inf.html">https://www.uni-bielefeld.de/(en)/sfb1288/projekte/inf.html</a>
+              <a href="https://www.uni-bielefeld.de/sfb/sfb1288/projektbereiche/inf/">https://www.uni-bielefeld.de/sfb/sfb1288/projektbereiche/inf/</a>
             </li>
           </ul>
           <h6>§ 1.2. Contact details of the data protection officer</h6>
@@ -56,40 +56,55 @@
       <div class="card">
         <div class="card-content">
           <span class="card-title">§ 2 General information on data processing and its purpose</span>
-          <p>We process the personal data of our users only to the extent necessary to provide a functioning website and its functionalities.</p>
-          <p>The following personal data is collected and stored within the system:</p>
+          <p>We process the personal data of our users only to the extent necessary to provide a functioning website and its functionalities. Collecting this information enables us to better diagnose problems with the application, provide support more effectively as well as ensure the continuous functionality of the service.</p>
+          <p> The following (personal) data is collected and stored within the system:</p>
+          
           <h6>Master Data</h6>
-          <p>Within the scope of user authentication the following personal data is collected and processed:</p>
+          <p>Within the scope of user authentication, the following personal data is collected and processed: </p>
           <ul class="browser-default">
             <li>User name</li>
             <li>E-Mail</li>
           </ul>
-          <p>Registration of the user is required for the provision of certain content and services within nopaque.</p>
-          <h6>Protocol Data</h6>
+          <p>The registration of users is required for the provision of access to services within NOPAQUE. The freely selectable username and the corresponding email address is used to persistently identify you in NOPAQUE. The provided email address might be used to contact you in case we noticed some malfunction, to announce maintenance, or to spread important information regarding Nopaque. If you reset your password, Nopaque will use your email address to send you reset instructions via email. Nopaque does not show your email address and the username to other Nopaque users per default – except, if user gave the permission to do so, according to <b>§ 7 paragraph 1</b> of the General Terms of Use for the use of NOPAQUE.</p>
+          
+          <h6>Protocol and administrative data</h6>
           <p>In general, when a website is visited, for technical reasons information is automatically sent from the browser to the server and stored there in access protocols. When using a web application, additional protocol data is also generated, which is necessary for tracking technical errors. This information includes:</p>
           <ul class="browser-default">
             <li>IP address</li>
-            <li>User account</li>
             <li>Complete HTTP request URL</li>
             <li>HTTP action (e.g. GET: call up a page, POST: send form data)</li>
             <li>Access status (HTTP status code)</li>
-            <li>data volume retrieved</li>
             <li>Date and time of the action</li>
-            <li>User-Agent string</li>
           </ul>
-          <p>Locally logged data will be used by the development team in order to debug and improve tools. This data can only be viewed by the technical administration and by the employees responsible for the nopaque platform. Data is stored for seven days to ensure proper technical operation and to find the cause of errors and is deleted <u>afterwards</u>.</p>
-          <p>Logged data may be used to understand how researchers are using the nopaque platform. To be able to use the data for research purposes, we reserve the right to store it in an anonymous and aggregated form for a longer period of time (up to two years after completion of the SFB 1288 INF project).</p>
-          <h6>Cookies</h6>
-          <p>Browsers store so-called cookies. Cookies are files that can be stored by the provider of a website in the directory of the browser program on the user's computer. These files contain text information and can be read again by the provider when the page is called up again. The provider can use these cookies, for example, to always deliver pages in the theme selected by the user.</p>
-          <p>The storage of cookies can be switched off in the browser settings or provided with an expiry time. By deactivating cookies, however, some functions that are controlled by cookies can then only be used to a limited extent or not at all.</p>
-          <p>NOPAQUE uses cookies for the following purposes:</p>
+          <br>
+          <p>Protocol data will be used by the development team in order to debug and improve the included tools. This data can only be viewed by the technical administration and by the employees responsible for the NOPAQUE platform. Protocol data is not directly associated with a user account. NOPAQUE deletes all this information when it gets more than six months old.</p>
+          <br>
+          <p>Further administrative data, which is essentially needed – to enable a proper user registration and user management functionalities:</p>
           <ul class="browser-default">
-            <li>Recognition of a user during a session in order to assign personal content and other user-defined settings.</li>
-            <li>Login Script with ‘Remember Me’ feature allows the user to preserve their logged in status. When the user checks the Remember Me option, then the logged in status is serialized in the session and stored in cookies in an encrypted way.</li>
+            <li>Attributes <b>member_since</b> and <b>last_seen</b>: for system cleaning purposes and detection of fake accounts</li>
+            <li>Attribute <b>confirmed</b>: This attribute indicates whether the account has been activated via e-mail. This type of activation ensures that the stored e-mail address actually exists.</li>
+            <li>Attribute <b>terms_of_use_accepted</b>: To verify that the terms of use have been accepted by the user. This attribute is set to false when the terms of use has changed. After the user has logged in again, the user is asked to accept the new terms of use.</li>
           </ul>
+
+          <h6>Cookies</h6>
+          <p>Cookies: Browsers store so-called cookies. Cookies are files that can be stored by the provider of a website in the directory of the browser program on the user's computer. These files contain text information and can be read again by the provider when the page is called up again. The provider can use these cookies, for example, to always deliver pages in the theme selected by the user.</p>
+          <p>The storage of cookies can be switched off in the browser settings or provided with an expiry time. By deactivating cookies, however, some functions that are controlled by cookies can then only be used to a limited extent or not at all.</p>
+          <br>
+          <p>NOPAQUE uses <b>functionality cookies</b> which deliver certain functions and allow to remember important information and user’s preferences:</p>
+          <ul class="browser-default">
+            <li><b>session</b>: Recognition of a user during a session in order to assign personal content and other user-defined settings. The session cookie is deleted after closing the browser session.</li>
+            <li><b>remember_token</b>: Login script with ‘remember me’ feature allowing the user to preserve their logged in status. When the user checks the Remember Me option, then the logged in status is serialized in the session and stored in cookies in an encrypted way.</li>
+          </ul>
+          <p>Cookies collected by NOPAQUE do not collect personal information of the users.</p>
+          
           <h6>Content Data</h6>
-          <p>The content data includes all data that is entered or created by users themselves in the system. This data is listed here because it is assigned to individual authors and may contain personal data. This may include: uploaded files, images, texts or other media files. Please note that files and scans submitted to NOPAQUE are stored in order to allow persistent access during a work session and between work sessions.</p>
-          <p>According to § 4 paragraph 2 of the General Terms of Use for the use of NOPAQUE at Bielefeld University, the users themselves are responsible for the content they post and must comply with the legal provisions of data protection. This includes in particular the deletion of personal data that may no longer be processed.</p>
+          <p>The content data includes all data that is entered or created by users themselves in the system. This data is listed here because it is assigned to individual authors and may contain personal data. This may include: <b>uploaded files, images, text documents, other media files</b> and <b>(interim) results</b> after data processing and computations. Please note that files and scans submitted to NOPAQUE are safely stored on the NOPAQUE server in order to allow persistent access during a work session and between work sessions.</p>
+          <br>
+          <p>According to <b>§ 4 paragraph 1 - 3</b> of the General Terms of Use for the use of NOPAQUE at Bielefeld University, the users themselves are responsible for the content they upload and must comply with the legal provisions of data protection and copyright law. This includes in particular the deletion of personal data that may no longer be processed.</p>
+          
+          <h6>User-added Information (optional)</h6>
+          <p>NOPAQUE also stores optionally user-added personal information, like user’s profile information (full name, affiliation) and user’s added profile photo (avatar).</p>
+        
         </div>
       </div>
     </div>
@@ -107,9 +122,14 @@
     <div class="col s12">
       <div class="card">
         <div class="card-content">
-          <span class="card-title">§ 4 Data transmissions</span>
-          <p>Your personal data, which are processed by Bielefeld University for the purposes mentioned under 2. will not be transferred to third parties.</p>
+          <span class="card-title">§ 4 Data transmissions and sharing of your data</span>
+          <p>Your personal data, which are processed by Bielefeld University for the purposes mentioned under <b>2 A - D</b> will not be transferred to third parties.</p>
+          <br>
           <p>In individual cases, data may also be legally transmitted to third parties, for example, to law enforcement authorities for the investigation of criminal offences within the framework of the <b>Code of Criminal Procedure (StPO)</b>. If technical service providers are given access to personal data, this is done on the basis of a contract in accordance with <b>Article 28 GDPR</b>.</p>
+          <br>
+          <p>NOPAQUE centrally bundles sophisticated data processing functionalities related to Digital Humanities (for example: pattern recognition or text mining) on its platform which are offered by third parties on external platforms. No personal data is passed on to third parties - only content data which is sent anonymously to the APIs of the third-party tools. The results of the calculations are then sent back to NOPAQUE and saved as results in user’s account.</p>
+          <br>
+          <p>For personal data mentioned under <b>2 E</b> the following applies: we do not share your personal data with third parties unless you have given your consent. This consent is given if the user actively makes his profile public in NOPAQUE. As consequence, user-added information (as listed under point 2E of this declaration) and, if applicable, a listing of public corpora with metadata is then made visible to other NOPAQUE users.</p>
         </div>
       </div>
     </div>
@@ -117,8 +137,8 @@
     <div class="col s12">
       <div class="card">
         <div class="card-content">
-          <span class="card-title">§ 5 Duration of processing / data deletion</span>
-          <p>Data processed for user authentication are deleted immediately after account deletion.</p>
+          <span class="card-title">§ 5 Duration of processing of your data and data retention</span>
+          <p>Data processed for user authentication, all personal data and contents uploaded by the user (listed in <b>2</b>) are deleted immediately after account deletion.</p>
         </div>
       </div>
     </div>
@@ -126,7 +146,7 @@
     <div class="col s12">
       <div class="card">
         <div class="card-content">
-          <span class="card-title">§ 6 Your rights as a data subject</span>
+          <span class="card-title">§ 6 Your data protection rights and choices as NOPAQUE user</span>
           <p>As a data subject, you have certain rights under <b>GDPR</b> that you may assert at any time:</p>
           <ul class="browser-default">
             <li>the right to access information about whether or not personal data concerning you is processed, and if so, what categories of data are being processed (<b>Article 15 GDPR</b>),</li>

app/templates/main/terms_of_use.html.j2

@@ -6,106 +6,36 @@
     <div class="col s12">
       <h1 id="title">{{ title }}</h1>
     </div>
-
     <div class="col s12">
-      <p>With the usage of the nopaque platform you declare your acceptance of the General Terms of Use and that you have taken note of the legal framework and the data protection declaration.</p>
-    </div>
-
-    <div class="col s12">
-      <div class="card">
-        <div class="card-content">
-          <span class="card-title">§ 1 Scope</span>
-          <p>The General Terms of Use for the nopaque platform apply to everyone who uses the system as an authorised user in the sense of <b>§ 2</b> (1) of the General Terms of Use. By using the system and with your consent you accept these terms of use.</p>
-        </div>
+      <div class="switch">
+        <label>
+          DE
+          <input type="checkbox" id="terms-of-use-page-switch">
+          <span class="lever"></span>
+          EN
+        </label>
       </div>
+      <br>
     </div>
-
-    <div class="col s12">
-      <div class="card">
-        <div class="card-content">
-          <span class="card-title">§ 2 Right of use</span>
-          <p>(1) The nopaque platform is available to users exclusively for the purposes of teaching and research. Any other use, especially for business, commercial is not permitted. The following groups shall be entitled to use the nopaque platform:</p>
-          <ul class="browser-default">
-            <li>students, teaching staff and employees at Bielefeld University</li>
-            <li>external researchers from outside the University Bielefeld</li>
-          </ul>
-          <p>&nbsp;</p>
-          <p>(2) The use of the system is free of charge.</p>
-          <p>&nbsp;</p>
-          <p>(3) The duration of the right of use ends with the deletion of the user account by the user (see <b>§ 7</b>)</p>
-        </div>
-      </div>
+    <div class="terms-of-use-page-content hide">
+      {% include "main/terms_of_use_en.html.j2" %}
     </div>
-
-    <div class="col s12">
-      <div class="card">
-        <div class="card-content">
-          <span class="card-title">§ 3 Purpose of the Services</span>
-          <p>nopaque custom-built web application which serves as a platform for preprocessing and analysing digital copies of various text based research data (books, letters, etc.) in different files and formats. nopaque converts image data – like photos or scans – into text data through OCR making it machine readable. This step enables to proceed with further computational analysis of the documents. By means of computational linguistic data processing (tokenization, lemmatization, part-of-speech tagging and named-entity recognition) nopaque extracts additional information from texts.</p>
-          <p>&nbsp;</p>
-          <p>(1) Change of service</p>
-          <p>The provider of the nopaque platform is entitled to change and supplement the scope of functions of nopaque without prior notice. This could result from a thematic and scientific reorientation of the project.</p>
-          <p>&nbsp;</p>
-          <p>(2) Support</p>
-          <p>On nopaque, a contact form is available. As far as possible the SFB 1288 INF staff will try to provide user support.</p>
-        </div>
-      </div>
-    </div>
-
-    <div class="col s12">
-      <div class="card">
-        <div class="card-content">
-          <span class="card-title">§ 4 Obligations of the User</span>
-          <p>(1) The system is suitable for normal security requirements. Data with a high need for protection (e.g. health data) may not be stored or processed in the nopaque platform.</p>
-          <p>&nbsp;</p>
-          <p>(2) Users of nopaque are responsible for their own entered contents. The uploading of illegal content, especially content that violates criminal, personal, data protection or copyright regulations (including § 60a) is not permitted.</p>
-          <p>&nbsp;</p>
-          <p>(3) Users undertake to indemnify Bielefeld University from all claims by third parties based on the data they use and to reimburse Bielefeld University for any costs incurred by the latter due to possible infringements of rights. This also includes the costs incurred by Bielefeld University in defending itself against such claims in and out of court.</p>
-          <p>&nbsp;</p>
-          <p>(4) Exclusion from use</p>
-          <p>Bielefeld University is entitled to immediately block access to the service if there are reasonable grounds to suspect that the stored data is unlawful (e.g upload harmful files via file upload) and/or violates the rights of third parties. Other infringements of the provisions of these Terms of Use, in particular the obligations under §6 also entitle Bielefeld University to block the user. Bielefeld University shall immediately notify the user of the block and the reason for the block. The block must be lifted as soon as the suspicion is invalidated.</p>
-          <p>&nbsp;</p>
-          <p>(5) Usage of Data</p>
-          <p>The data stored by the user on the storage space intended for him may be legally protected, the responsibility for the processing of the data from these points of view lies solely with the user. By using nopaque, the user grants Bielefeld the right to process the data with the corresponding tools. At all times during processing in nopaque, data remains in the user's private storage location and will not passed on to third parties.</p>
-          <p>&nbsp;</p>
-          <p>(6) Release of Bielefeld University from Third-Party Claims</p>
-          <p>The user is responsible for the data stored by him/her in nopaque. Furthermore he/she is responsible for entering and maintaining the data and information required to use nopaque.</p>
-          <p>&nbsp;</p>
-          <p>The user is obliged to indemnify Bielefeld University against all claims by third parties based on the data stored by him/her and to reimburse Bielefeld University for any costs incurred as a result of possible legal infringements. This also includes the costs incurred by Bielefeld University for extrajudicial and judicial defense against these claims.</p>
-        </div>
-      </div>
-    </div>
-
-    <div class="col s12">
-      <div class="card">
-        <div class="card-content">
-          <span class="card-title">§ 5 Liability of Bielefeld University</span>
-          <p>Claims for damages against Bielefeld University are excluded irrespective of the legal grounds. Bielefeld University shall not be liable for loss of data and information or other „indirect“ damages, e.g. loss of profit, loss of production, or other indirect damages. Bielefeld University shall not be liable for the loss of data to the extent that the damage is due to the fact that the user has failed to back up the data and thereby ensure that lost data can be restored with justifiable effort.</p>
-          <p>&nbsp;</p>
-          <p>nopaque is available in accordance with normal operational care based on the "Best Effort" practice. No liability is assumed for the consequences of failures or errors of the nopaque platform. Bielefeld University does not guarantee that the systems will run error-free and without interruption at all times. Bielefeld University accepts no responsibility for technical quality. Nor is it liable for the content, in particular for the accuracy, completeness, and timeliness of information to which it merely provides access for use.</p>
-        </div>
-      </div>
-    </div>
-
-    <div class="col s12">
-      <div class="card">
-        <div class="card-content">
-          <span class="card-title">§ 6 Data Protection</span>
-          <p>Information on the handling of personal data during the operation of the service can be found in the separate data protection policy.</p>
-        </div>
-      </div>
-    </div>
-
-    <div class="col s12">
-      <div class="card">
-        <div class="card-content">
-          <span class="card-title">§ 7 Duration and Termination</span>
-          <p>The user may terminate the use nopaque by deleting his/her account at any time without giving reasons. After deletion of the account, all users‘ data will be automatically deleted and access to the service blocked. This does not affect the user's right to delete data under data protection law.</p>
-          <p>&nbsp;</p>
-          <p>Bielefeld University may exclude the user from using the service without notice for an important reason. Important reasons include, in particular, repeated violations of the provisions of these Terms of Use or of applicable laws.</p>
-        </div>
-      </div>
+    <div class="terms-of-use-page-content">
+      {% include "main/terms_of_use_de.html.j2" %}
     </div>
   </div>
 </div>
 {% endblock page_content %}
+
+{% block scripts %}
+{{ super() }}
+<script>
+  let languagePageSwitch = document.querySelector('#terms-of-use-page-switch');
+  let termsOfUsePageContent = document.querySelectorAll('.terms-of-use-page-content');
+  languagePageSwitch.addEventListener('change', function() {
+    termsOfUsePageContent.forEach(content => {
+      content.classList.toggle('hide');
+    });
+  });
+</script>
+{% endblock scripts %}

app/templates/main/terms_of_use_de.html.j2

@@ -0,0 +1,141 @@
+<div class="col s12">
+  <p>Mit Nutzung der Plattform nopaque stimmen Sie den Allgemeinen Geschäftsbedingungen sowie der Zurkenntnisnahme des rechtlichen Rahmens und der Datenschutzerklärung.</p>
+</div>
+
+<div class="col s12">
+  <div class="card">
+    <div class="card-content">
+      <span class="card-title">§ 1 Inhalt und Umfang des Serviceangebots</span>
+      <p>(1)	Diese Allgemeinen Geschäftsbedingungen gelten für die Nutzung der Angebote des browserbasierten Datenverarbeitungs- und Textanalysetools „nopaque“ (nachfolgend „Serviceangebot“), der Universität Bielefeld (nachfolgend Universität), das von berechtigten Nutzern kostenlos über die Internetseite www.nopaque.uni-bielefeld.de verwendet werden kann.</p>
+      <p>(2)	berechtigt zur Nutzung des Serviceangebotes sind lediglich</p>
+      <ol type="a">
+        <li>Studierende, Lehrende und Beschäftigte der Universität Bielefeld</li>
+        <li>Externe Wissenschaftler*innen  im Rahmen nichtkommerzieller Forschung</li>
+      </ol>
+    </div>
+  </div>
+</div>
+
+<div class="col s12">
+  <div class="card">
+    <div class="card-content">
+      <span class="card-title">§ 2 Serviceangebot</span>
+      <p>(1)	Im Rahmen des Serviceangebots können von den Nutzern hochzuladende Daten automatisiert verarbeitet und analysiert werden.  Dies ist in Form von folgenden, einzeln ansteuerbaren, Services umgesetzt:</p>
+      <ol type="a">
+        <li><b>File Setup</b>: Digitale Kopien von textbasierten Forschungsdaten (Bücher, Briefe usw.) bestehen oft aus verschiedenen Dateien und Formaten. Nopaque konvertiert und führt diese Dateien zusammen, um die Weiterverarbeitung und die Anwendung anderer Dienste zu erleichtern.</li>
+        <li><b>Optical Character Recognition</b> (OCR): nopaque wandelt Ihre Bilddaten - wie Fotos oder Scans - durch OCR in Textdaten um und macht sie maschinenlesbar. Dieser Schritt ermöglicht es Ihnen, mit der weiteren rechnerischen Analyse Ihrer Dokumente fortzufahren.</li>
+        <li><b>Handwritten Text Recognition</b> (HTR): nopaque wandelt Ihre Bilddaten von handschriftlichen Texten - wie Fotos oder Scans - mittels HTR in Textdaten um und macht sie maschinenlesbar. Dieser Schritt ermöglicht es Ihnen, mit der weiteren rechnerischen Analyse Ihrer Dokumente fortzufahren.</li>
+        <li><b>Natural Language Processing</b> (NLP): Mittels computergestützter linguistischer Datenverarbeitung (Tokenisierung, Lemmatisierung, Part-of-Speech-Tagging und Named-Entity-Erkennung) extrahiert nopaque zusätzliche Informationen aus Ihrem Text.</li>
+        <li><b>Corpus analysis</b>: Mit nopaque können Sie so viele Textkorpora erstellen und hochladen, wie Sie möchten. Es nutzt die CQP Query Language, die komplexe Suchanfragen mit Hilfe von Metadaten und NLP-Tags ermöglicht.</li>
+      </ol>
+      <p>(2)	Der Nutzer ist auch berechtigt, im Rahmen des Serviceangebots erstellte Textaufbereitungen (Corpora) innerhalb der Nutzerplattform des Serviceangebots durch die „Teilen“-Funktionen mit anderen registrierten Nutzern zu teilen. Ein Zugang zu fremden Corpora kann jeweils mit Leserechten (Viewer), mit Lese-und Bearbeitungsrechten (Contributor) oder Co-Administratorrechten (Administrator) eingeräumt werden.</p>
+      <p>(3)	Die Nutzer können im Rahmen Ihres Nutzerkontos eigene Sprachmodelle hochladen und diese zur Analyse hochgeladener Dateien verwenden. Nach Freischaltung durch einen Administrator können Nutzer ihre hochgeladenen Sprachmodelle auch öffentlich im Rahmen der Plattform zur Verfügung stellen.</p>
+    </div>
+  </div>
+</div>
+
+<div class="col s12">
+  <div class="card">
+    <div class="card-content">
+      <span class="card-title">§ 3 Zugang zum Serviceangebot</span>
+      <p>(1) Die Nutzer registrieren sich über die Eingabe der abgefragten Daten in der Anmeldemaske. Danach muss der Nutzer einen von ihm gewählten Benutzernamen und ein Passwort bestimmen und eingeben.</p>
+      <p>(2) Der Nutzer ist für die Geheimhaltung des Benutzernamens sowie des Passwortes selbst verantwortlich.</p>
+      <p>(3) Nach Freischaltung durch einen Administrator können Nutzer durch eine API-Schnittstelle auch persönliche Zugangstoken erstellen und auf alle Daten zugreifen kann, auf die der Nutzer selbst zugreifen kann.</p>
+    </div>
+  </div>
+</div>
+
+<div class="col s12">
+  <div class="card">
+    <div class="card-content">
+      <span class="card-title">§ 4 Allgemeine Pflichten der Nutzer</span>
+      <p>(1)	Mit der Registrierung erklären die Nutzer Ihre Zustimmung zu den Nutzungsbedingungen. Das rechtswidrige Hochladen, Verarbeiten und Teilen von Inhalten insbesondere entgegen strafrechtlicher, persönlichkeitsrechtlicher, datenschutzrechtlicher oder urheberrechtlicher Regelungen ist nicht gestattet. Durch das Hochladen, bearbeiten und/oder Teilen entsprechender Texte, Corpora und/oder Analyseergebnisse erklärt der jeweilige Nutzer, Inhaber aller dazu jeweils erforderlichen Rechte zu sein.</p>
+      <p>(2)	Die Nutzer verpflichten sich, auch im Rahmen der Gestaltung des persönlichen Nutzerprofils und der Nutzung von Foren der Plattform, Medien und Texte nur auf gesetzlich erlaubte Art und Weise zu verwenden und illegale Äußerungen zu unterlassen.</p>
+      <p>(3)	Das Serviceangebot ist lediglich zur Verarbeitung von Daten ohne erhöhte Schutzbedürfnisse geeignet. Daten, welche besonderen datenschutzrechtlichen Anforderungen unterliegen (bspw. Gesundheitsdaten, siehe Art. 9 DSGVO) dürfen nicht gespeichert oder verarbeitet werden.</p>
+    </div>
+  </div>
+</div>
+
+<div class="col s12">
+  <div class="card">
+    <div class="card-content">
+      <span class="card-title">§ 5 Haftung der Nutzer</span>
+      <p>(1)	Sofern aufgrund der Nutzung eines nicht berechtigten Nutzers (siehe hierzu § 1 Abs. 2) oder aufgrund einer unerlaubten Nutzung (siehe hierzu § 4 Abs. 1, 2) von Texten, Analyseergebnissen oder sonstigen Medien (bspw. einem hochgeladenen Profilbild) im Rahmen des Serviceangebots Ansprüche Dritter gegen die Universität Bielefeld geltend gemacht werden, stellt der für die Rechtsverletzung verantwortliche Nutzer die Universität von diesen Ansprüchen frei.</p>
+      <p>(2)	Die Nutzer haften bezgl. der Geheimhaltung und Weitergabe von Zugangsdaten für jegliche Schäden, die Ihnen entstehen.  Sofern aufgrund einer unerlaubten Verwendung von Zugangsdaten/Token Ansprüche Dritter gegen die Universität Bielefeld geltend gemacht werden, stellt der für die Rechtsverletzung verantwortliche Nutzer die Universität von diesen Ansprüchen frei.</p>
+    </div>
+  </div>
+</div>
+
+<div class="col s12">
+  <div class="card">
+    <div class="card-content">
+      <span class="card-title">§ 6 Nutzungsrechte des Nutzers bzgl. erstellter Corpora und Analyseberichte</span>
+      <p>(1)	Der Nutzer ist in den Grenzen des § 4 berechtigt, Texte mit der Webanwendung aufzubereiten, im Rahmen der Webanwendung einzusehen und herunterzuladen. Regelungen zum Teilen der so erstellten Corpora ergeben sich nach § 7 dieser AGB.</p>
+      <p>(2)	Der Nutzer ist auch berechtigt, den jeweils auf Grundlage der aufbereiteten Texte zur Verfügung gestellten Analysebericht zu Zwecken von Forschung und Lehre in den Grenzen des § 4 im Rahmen der Online-Anwendung zu lesen, herunterzuladen, zu vervielfältigen und zu veröffentlichen. Die Berechtigung steht nur denjenigen Nutzern zu, welche die entsprechenden Analyseberichte generieren. Die Berechtigung steht unter der auflösenden Bedingung, dass im Rahmen entsprechender Vervielfältigungen/Veröffentlichungen von Analyseberichten oder deren Ausschnitten als Quellenangabe vermerkt wird: nopaque [Software]. (2020). SFB 1288 – Teilprojekt INF, Universität Bielefeld. https://nopaque.uni-bielefeld.de/</p>
+    </div>
+  </div>
+</div>
+
+<div class="col s12">
+  <div class="card">
+    <div class="card-content">
+      <span class="card-title">§ 7 Teilen von zuvor erstellten Corpora</span>
+      <p>(1)	Das Teilen von Corpora wird auf folgende Art und Weise ermöglicht:</p>
+      <ol type="a"> 
+        <li>Es kann ein Link generiert werden, welcher anderen angemeldeten Nutzern Zugang zu den auf den Servern des Serviceangebots gespeicherten Corpora eines Nutzers ermöglicht.</li>
+        <li>Corpora können in eine durch alle Nutzer einsehbare Liste eingefügt werden, in deren Rahmen sich andere Nutzer über den vorhandene Bestand informieren und durch Kontaktierung des jeweiligen Erstellers einen Zugang erbitten können. Der Ersteller entscheidet dann in eigener Verantwortung über die Zulässigkeit des erbetenen Zugangs und ermöglicht bis zum Widerruf den Zugriff auf die Corpora durch die jeweiligen anderen Nutzer durch das Teilen eines Links im obigen Sinne.</li>
+      </ol>
+      <p>(2)	In Bezug auf das Teilen von Corpora, welche urheberrechtlich geschützte Medien enthalten, ist insb. § 60d UrhG einzuhalten. Es sind durch den hochladenden Nutzer insb. die dort genannten Löschfristen einzuhalten. Es wird ausdrücklich darauf hingewiesen, dass das regelwidrige Verbreiten von Corpora oder Ausgangstexten zu Pflichtverletzungen nach § 4 führen kann, deren finanzieller Schaden von den jeweiligen Nutzern zu tragen ist.</p>
+    </div>
+  </div>
+</div>
+
+<div class="col s12">
+  <div class="card">
+    <div class="card-content">
+      <span class="card-title">§ 8 Verfügbarkeit und Support</span>
+      <p>(1)	Die Universität ist berechtigt, soweit es im Interesse des Nutzers erforderlich ist, Wartungsarbeiten  auch während der Betriebszeit vorzunehmen. Hierbei kann es zu Störungen des Datenabrufs kommen, die die Universität möglichst geringhalten wird.</p>
+      <p>(2)	Die Universität ist berechtigt, den Funktionsumfang des Serviceangebots zu ändern und/oder zu modifizieren ohne die Nutzer zuvor zu benachrichtigen. Die Universität kann, ohne hierzu verpflichtet zu sein, die Software jederzeit aktualisieren oder weiterentwickeln und insbesondere aufgrund geänderter Rechtslage, technischer Entwicklungen, aufgrund einer wissenschaftlichen oder thematischen Umstrukturierung des Projekts oder zur Verbesserung der IT-Sicherheit anpassen.</p>
+      <p>(3)  Nutzern wird im Rahmen des Webauftritts ein Supportformular zur Verfügung gestellt.</p>
+    </div>
+  </div>
+</div>
+
+<div class="col s12">
+  <div class="card">
+    <div class="card-content">
+      <span class="card-title">§ 9 Mängelrechte, Haftung der Universität</span>
+      <p>(1)  Die Universität übernimmt keine Gewähr dafür, dass die durch das Serviceangebot zur Verfügung gestellten Informationen inhaltlich richtig, aktuell oder brauchbar sind oder zu einem gewünschten Erfolg führen. Insoweit ist jegliche Haftung der Universität ausgeschlossen.</p>
+      <p>(2)  Das Serviceangebot wird auf Basis der Praxis „Best Effort“ nach betriebsüblicher Sorgfalt zur Verfügung gestellt. Die Universität Bielefeld übernimmt keine Garantie dafür, dass die Systeme fehlerfrei und ohne Unterbrechung laufen. Eventuelle Datenverluste infolge technischer Störungen können nicht ausgeschlossen werden. Für den Verlust von Daten haftet die Universität Bielefeld insoweit nicht, als der Schaden darauf beruht, dass es die Nutzer*innen unterlassen haben, Datensicherungen durchzuführen und dadurch sicherzustellen, dass verloren gegangene Daten mit vertretbarem Aufwand wiederhergestellt werden können.</p>
+      <p>(3)  Im Übrigen haftet die Universität nur bei Vorsatz oder grober Fahrlässigkeit ihrer Mitarbeiter*innen, es sei denn, dass eine schuldhafte Verletzung wesentlicher Pflichten im Sinne dieser Nutzungsbedingungen vorliegt.  In diesem Fall ist die Haftung auf typische, bei Begründung des Nutzungsverhältnisses vorhersehbare Schäden begrenzt; die Universität haftet nicht für andere Schäden, z.B. für entgangenen Gewinn, für Produktionsausfall, für sonstige mittelbare Schäden oder für Verlust von Daten und Informationen. Die Haftung für Schäden aus der Verletzung des Lebens, des Körpers oder der Gesundheit bleibt unberührt.</p>
+      <p>(4)  Mögliche Amtshaftungsansprüche gegen die Hochschule bleiben von den vorstehenden Regelungen unberührt.</p>
+    </div>
+  </div>
+</div>
+
+<div class="col s12">
+  <div class="card">
+    <div class="card-content">
+      <span class="card-title">§ 10 Missbräuchliche Nutzung</span>
+      <p>Die Universität behält sich vor, bei Verdacht einer missbräuchlichen Nutzung oder wesentlicher Verletzungen dieser Nutzungsbedingungen diesen Vorgängen nachzugehen, entsprechende Vorkehrungen zu treffen und bei einem begründeten Verdacht gegebenenfalls den Zugang des Nutzers zum Serviceangebot – mindestens bis zu einer Verdachtsausräumung seitens des Nutzers – zu sperren und/oder gegebenenfalls bei besonders schwerwiegenden Verstößen auch das Nutzerkonto zu löschen. Soweit der Nutzer den Verdacht ausräumt, wird die Sperrung aufgehoben. Hinweise auf eine missbräuchliche Nutzung des Serviceangebotes hat jeder Nutzer der Universität unverzüglich mitzuteilen.</p>
+    </div>
+  </div>
+</div>
+
+<div class="col s12">
+  <div class="card">
+    <div class="card-content">
+      <span class="card-title">§ 11 Anwendbares Recht</span>
+      <p>Es gilt ausschließlich das Recht der Bundesrepublik Deutschland. Unberührt davon bleiben die zwingenden Bestimmungen des Staates, in dem Sie Ihren gewöhnlichen Aufenthalt haben.</p>
+    </div>
+  </div>
+</div>
+
+<div class="col s12">
+  <div class="card">
+    <div class="card-content">
+      <span class="card-title">§ 12 Gerichtsstand</span>
+      <p>Sofern Sie keinen Wohnsitz in der Bundesrepublik Deutschland haben oder nach Anmeldung Ihren Wohnsitz ins Ausland verlegen oder Ihr Wohnsitz zum Zeitpunkt der Klageerhebung nicht bekannt ist, ist Gerichtsstand für alle Streitigkeiten aus und im Zusammenhang mit dem Nutzungsverhältnis das Amts- oder Landgericht Bielefeld.</p>
+    </div>
+  </div>
+</div>

app/templates/main/terms_of_use_en.html.j2

@@ -0,0 +1,150 @@
+<div class="col s12">
+  <div class="card red darken-2">
+    <div class="card-content white-text">
+      <span class="card-title">Notice</span>
+      <p>This page is translated for the understanding of English-speaking users. However, only the version of the German Terms of Use in accordance with German law applies. </p>
+    </div>
+  </div>
+</div>
+
+<div class="col s12">
+  <p>With the usage of the nopaque platform you declare your acceptance of the General Terms of Use and that you have taken note of the legal framework and the data protection declaration.</p>
+</div>
+
+<div class="col s12">
+  <div class="card">
+    <div class="card-content">
+      <span class="card-title">§ 1 Content and scope of the Services offered</span>
+      <p>(1)	These General Terms and Conditions apply to the use of the Services offered in the browser-based data processing and text analysis tool "nopaque" (hereinafter "Services") by Bielefeld University (hereinafter "University"), which can be used free of charge by authorized Users via the website www.nopaque.uni-bielefeld.de.</p>
+      <p>(2)	The authorized use of these services is exclusively granted to:</p>
+      <ol type="a">
+        <li>Students, teaching staff, and employees of Bielefeld University</li>
+        <li>External researchers for use in non-commercial research</li>
+      </ol>
+    </div>
+  </div>
+</div>
+
+<div class="col s12">
+  <div class="card">
+    <div class="card-content">
+      <span class="card-title">§ 2 Services</span>
+      <p>(1)	As part of the Services offered, user-uploaded data can be processed and analyzed automatically. This is implemented in the form of the following Services, each of which can be executed individually:</p>
+      <ol type="a">
+        <li><b>File Setup</b>: Digital copies of text-based research data (books, letters, etc.) often consist of different files and formats. nopaque converts and merges these files to facilitate further processing and the use of other services.</li>
+        <li><b>Optical Character Recognition</b> (OCR): nopaque converts image data - such as photos or scans - into text data using OCR and makes it machine-readable. This step enables the further computational analysis of documents.</li>
+        <li><b>Handwritten Text Recognition</b> (HTR): nopaque converts image data from handwritten text - such as photos or scans - into text data using HTR and makes it machine-readable. This step enables further computational analysis of documents.</li>
+        <li><b>Natural Language Processing</b> (NLP): Using computer-aided linguistic data processing (tokenization, lemmatization, part-of-speech tagging and named entity recognition), nopaque extracts additional information from text.</li>
+        <li><b>Corpus analysis</b>: With nopaque, one can create and upload as many text corpora as desired. It uses the CQP Query Language, which enables complex search queries using metadata and NLP tags.</li>
+      </ol>
+      <p>(2)	The User is also entitled to share text edits (corpora) created as part of the Services offered with other registered Users within the Service’s user platform using the "Share" functions. Access to third-party corpora can be granted with reading rights (viewer), reading and editing rights (contributor) or co-administrator rights (administrator).</p>
+      <p>(3)	Users can upload their own language models as part of their user account and use them to analyze uploaded files. After activation by an administrator, Users can also make their uploaded language models publicly available on the platform.</p>
+    </div>
+  </div>
+</div>
+
+<div class="col s12">
+  <div class="card">
+    <div class="card-content">
+      <span class="card-title">§ 3 Access to the Services</span>
+      <p>(1)  Users register by entering the requested data in the login screen. The User must then select and enter a username and password of their choice.</p>
+      <p>(2) Users are responsible for keeping their username and password confidential.</p>
+      <p>(3) After activation by an administrator, Users can create personal access tokens via an application programming interface (API) and access all user-accessible data. </p>
+    </div>
+  </div>
+</div>
+
+<div class="col s12">
+  <div class="card">
+    <div class="card-content">
+      <span class="card-title">§ 4 General User Obligations</span>
+      <p>(1)	By registering, Users declare their consent to the terms of use. The unlawful uploading, processing, and sharing of content, in particular contrary to criminal law, personal rights regulations, data protection law or copyright regulations, is not permitted. By uploading, editing and/or sharing corresponding texts, corpora and/or analysis results, the respective User declares to be the owner of all rights required in each case.</p>
+      <p>(2)	Users are required to use media and texts only in a legally permitted manner and refrain from making illegal statements. This includes the design of their personal user profile and when using the forums on the nopaque platform.</p>
+      <p>(3)	The Services offered are only suitable for the processing of data without heightened security requirements. Data that is subject to special data protection requirements (e.g. health data, see Art. 9 GDPR) may not be stored or processed.</p>
+    </div>
+  </div>
+</div>
+
+<div class="col s12">
+  <div class="card">
+    <div class="card-content">
+      <span class="card-title">§ 5 User liability</span>
+      <p>(1)	If claims are asserted against Bielefeld University by third parties due to the use of an unauthorized User (see § 1 para. 2) or due to unauthorized use (see § 4 para. 1, 2) of texts, analysis results or other media (e.g. an uploaded profile picture) within the scope of the services offered, the User responsible for the infringement shall indemnify Bielefeld University against these claims.</p>
+      <p>(2)	Users are liable for any damage they incur regarding the confidentiality and disclosure of access data. If claims are asserted against Bielefeld University by third parties due to unauthorized use of access data/tokens, the User responsible for the infringement shall indemnify Bielefeld University against these claims.</p>
+    </div>
+  </div>
+</div>
+
+<div class="col s12">
+  <div class="card">
+    <div class="card-content">
+      <span class="card-title">§ 6 User rights of use regarding generated corpora and analysis reports</span>
+      <p>(1)	Within the limits of § 4, the User is entitled to prepare texts with the web application, to view them within the web application and to download them. Regulations on sharing the corpora created in this way are set out in § 7 of these GTC</p>
+      <p>(2)	The User is also entitled to display, download, reproduce, and publish analysis reports generated based on the prepared texts for the purposes of teaching and research within the limits of § 4. These rights are only granted to the Users that generate the corresponding analysis reports. The authorization is subject to the resolutive condition that in the context of corresponding reproductions/publications of analysis reports or their excerpts, the following is noted as the source: nopaque [Software]. (2020). SFB 1288 - Subproject INF, Bielefeld University. https://nopaque.uni-bielefeld.de/.</p>
+    </div>
+  </div>
+</div>
+
+<div class="col s12">
+  <div class="card">
+    <div class="card-content">
+      <span class="card-title">§ 7 Sharing previously created corpora</span>
+      <p>(1)	Sharing of corpora is possible in the following ways:</p>
+      <ol type="a"> 
+        <li>A link can be generated allowing other registered Users to access another User’s corpora stored on the servers of the Service.</li>
+        <li>Corpora can be added to a list visible to all other Users. In the context of this list, other Users can find information about the available content and request access by contacting the relevant creator. The creator can then decide, on their own responsibility, whether the requested access is permissible and can allow the requesting User to access the corpora – until this access is revoked – by sharing a link as described above.</li>
+      </ol>
+      <p>(2)	With regard to the sharing of corpora containing copyright-protected media, § 60d UrhG must be observed most particularly. The User is required to comply with the deletion periods stated therein. It is expressly pointed out that the improper distribution of corpora or source texts can lead to breaches of duty in accordance with § 4, the financial loss of which is to be borne by the respective users.</p>
+    </div>
+  </div>
+</div>
+
+<div class="col s12">
+  <div class="card">
+    <div class="card-content">
+      <span class="card-title">§ 8 Availability and support</span>
+      <p>(1)	The University has the right to conduct maintenance during operating times as far as it is in user interest. Disruption of data access may occur during maintenance, which the University will minimize as much as possible. </p>
+      <p>(2)	The University has the right to change and/or modify the range of functions of the Services without prior notification of its Users. The University can, without being required to do so, update or develop the software at any time, especially due to changed laws and regulations, technical developments, scientific or thematic restructuring of the project or for IT security improvements.</p>
+      <p>(3)  Users are provided with a support contact form on the website.</p>
+    </div>
+  </div>
+</div>
+
+<div class="col s12">
+  <div class="card">
+    <div class="card-content">
+      <span class="card-title">§ 9 Defect rights and liability of the University</span>
+      <p>(1)  The University does not guarantee that the information provided by the service is correct, up-to-date or usable or that it will lead to the desired results. In this respect, the University accepts no liability whatsoever.</p>
+      <p>(2)  The Services are provided based on “best effort” practices according to customary operational diligence. The University does not guarantee uninterrupted, error-free system operation. Possible data loss due to technical disruptions cannot be ruled out. The University is not liable for data loss based on user neglect to create data backups and to ensure that lost data can be restored with reasonable expense and effort.</p>
+      <p>(3)  Otherwise, the University shall only be liable in the event of wrongful intent or gross negligence on the part of its employees, unless there is a culpable breach of material obligations within the scope of these Terms and Conditions of use.  In this case, liability is limited to typical damages foreseeable at the time the user relationship was established; the University is not liable for other damages, e.g. for loss of profit, for loss of production, for other indirect damages or for loss of data and information. Liability for damage resulting from injury to life, body or health remains unaffected.</p>
+      <p>(4)  Possible official liability claims against the university remain unaffected by the above provisions.</p>
+    </div>
+  </div>
+</div>
+
+<div class="col s12">
+  <div class="card">
+    <div class="card-content">
+      <span class="card-title">§ 10 Wrongful use</span>
+      <p>The University reserves the right to investigate suspected misuse or significant violations of these Terms and Conditions, to take appropriate precautions and, in the event of reasonable suspicion, to block the User's access to the Services – at least until the user has cleared up the suspicion – and/or, if necessary, to delete the user account in the event of particularly serious violations. If the User clears up the suspicion, the block will be lifted. Every User must notify the University immediately of any indications of misuse of the service.</p>
+    </div>
+  </div>
+</div>
+
+<div class="col s12">
+  <div class="card">
+    <div class="card-content">
+      <span class="card-title">§ 11 Applicable law</span>
+      <p>The law of the Federal Republic of Germany shall apply exclusively. The mandatory provisions of the country in which you have your habitual residence remain unaffected</p>
+    </div>
+  </div>
+</div>
+
+<div class="col s12">
+  <div class="card">
+    <div class="card-content">
+      <span class="card-title">§ 12 Place of jurisdiction</span>
+      <p>If you do not have a place of residence in the Federal Republic of Germany, if you move your place of residence abroad after registration, or if your place of residence is not known at the time the action is filed, the place of jurisdiction for all disputes arising from and in connection with the user relationship shall be the local ("Amtsgericht") or regional ("Landgericht") court of Bielefeld.</p>
+    </div>
+  </div>
+</div>

app/users/__init__.py

@@ -15,4 +15,4 @@ def before_request():
     pass
 
 
-from . import events, json_routes, routes, settings
+from . import cli, events, json_routes, routes, settings

app/users/cli.py

@@ -0,0 +1,14 @@
+from app.models import User
+import os
+import shutil
+from app import db
+from . import bp
+
+
+@bp.cli.command('reset')
+def reset():
+    ''' Reset terms of use accept '''
+    for user in [x for x in User.query.all() if x.terms_of_use_accepted]:
+        print(f'Resetting user {user.username}')
+        user.terms_of_use_accepted = False
+    db.session.commit()

config.py

@@ -115,6 +115,8 @@ class Config:
     NOPAQUE_READCOOP_USERNAME = os.environ.get('NOPAQUE_READCOOP_USERNAME')
     NOPAQUE_READCOOP_PASSWORD = os.environ.get('NOPAQUE_READCOOP_PASSWORD')
 
+    NOPAQUE_VERSION='1.0.0'
+
     @staticmethod
     def init_app(app: Flask):
         # Set up logging according to the corresponding (NOPAQUE_LOG_*)