Slight changes to services description

.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 build --tag $DOCKER_IMAGE --file $DOCKERFILE $DOCKER_BUILD_PATH
-    - docker push $IMAGE_TAG
+    - docker save $DOCKER_IMAGE > docker_image.tar
+  artifacts:
+    paths:
+      - docker_image.tar
 
-include:
+publish:
-  - template: Security/Container-Scanning.gitlab-ci.yml
+  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
+      when: always
-      variables:
+    # Run the job on tag creation
-        CS_IMAGE: $CI_REGISTRY_IMAGE:latest
     - if: $CI_COMMIT_TAG
-      when: on_success
+      when: always
-      variables:
+    # Don't run the job on all other occasions
-        CS_IMAGE: ${CI_REGISTRY_IMAGE}:${CI_COMMIT_REF_NAME}
     - 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

@@ -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/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']
@@ -973,7 +974,7 @@ class TesseractOCRPipelineModel(FileMixin, HashidMixin, db.Model):
                 model.is_public = True
                 model.title = m['title']
                 model.version = m['version']
-                continue
+            else:
                 model = TesseractOCRPipelineModel(
                     compatible_service_versions=m['compatible_service_versions'],
                     description=m['description'],
@@ -990,6 +991,7 @@ class TesseractOCRPipelineModel(FileMixin, HashidMixin, db.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})',
@@ -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']
@@ -1101,10 +1104,11 @@ class SpaCyNLPPipelineModel(FileMixin, HashidMixin, db.Model):
                 model.title = m['title']
                 model.version = m['version']
                 model.pipeline_name = m['pipeline_name']
-                continue
+            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'],
@@ -1118,7 +1122,7 @@ class SpaCyNLPPipelineModel(FileMixin, HashidMixin, db.Model):
                 db.session.add(model)
                 db.session.flush(objects=[model])
                 db.session.refresh(model)
-            model.filename = m['url'].split('/')[-1]
+            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})',

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/query-builder.js

@@ -7,13 +7,21 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
     this.addEventListenersToNAndMInputSubmit();
 
     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() {
@@ -108,7 +116,7 @@ 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 close chip-action-button" data-chip-action="delete">close</i>'}
         </span>
@@ -152,8 +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);
       }
       });
     });
@@ -292,24 +298,36 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
   }
 
   selectChipElement(attr) {
-    document.querySelectorAll('.chip.teal').forEach(element => {
+    if (attr.classList.contains('teal')) {
-        if (element !== attr) {
+      return;
-          element.classList.remove('teal', 'lighten-2');
-          this.toggleClass(['token-incidence-modifiers'], 'disabled', 'add');
     }
-    });
 
     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.queryChipElements).indexOf(selectedChip);
+    if (nOrNM) {
+      this.unselectChipElement(selectedChip);
+    }
     this.submitQueryChipElement('token-incidence-modifier', incidenceModifierPretty, incidenceModifier, selectedChipIndex);
-    this.selectChipElement(selectedChip);
   }
 
   tokenNMSubmitHandler(modalId) {
@@ -327,7 +345,7 @@ 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);
   }
 
   expertModeQueryBuilderSwitchHandler() {
@@ -368,15 +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'];
     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);
+      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);
+    let input = this.tokenInputCheck(this.elements.tokenBuilderContent);
-    tokenInput.value += '{' + input + '}';
+    this.cursorPositionInputfieldHandler(input, `{${addedInput}}`);
   }
 
   conditionHandler(conditionText) {

app/templates/_base/_modals/_manual/01_introduction.html.j2

@@ -1,9 +1,34 @@
 <h3 class="manual-chapter-title">Introduction</h3>
+<h4>Introduction</h4>
 <p>
-  nopaque is a web-based digital working environment. It implements a
+  Nopaque is a web application that offers different services and tools to support 
-  workflow based on the research process in the humanities and supports its
+  researchers working with image and text-based data. These services are logically 
-  users in processing their data in order to subsequently apply digital
+  connected and build upon each other. They include:
-  analysis methods to them. All processes are implemented in a specially
-  provided cloud environment with established open source software. This
-  always ensures that no personal data of the users is disclosed.
 </p>
+ <ol style="list-style-type:disc; margin-left:2em; padding-bottom:0;">
+  <li><b>File setup</b>, which converts and merges different data  (e.g., books, letters) 
+  for further processing.</li>
+  <li><b>Image-to-text conversion tools:</b></li>
+    <ol style="list-style-type:circle; margin-left:1em; padding-bottom:0;"><li><b>Optical Character Recognition</b> converts photos and 
+    scans into text data, making them machine-readable.</li>
+    <li><b>Transkribus HTR (Handwritten Text Recognition) Pipeline</b> (currently deactivated)* 
+    also converts images into text data, making them machine-readable.</li>
+    </ol>
+  <li><b>Natural Language Processing</b> extracts information from your text via 
+  computational linguistic data processing (tokenization, lemmatization, part-of-speech 
+  tagging and named-entity recognition.</li>
+  <li><b>Corpus analysis</b> makes use of CQP Query Language to search through text 
+  corpora with the aid of metadata and Natural Language Processing tags.</li>
+ </ol>
+
+Nopaque also features a <b>Social Area</b>, where researchers can create a personal profile, connect with other users and share corpora if desired.
+These services can be accessed from the sidebar in nopaque.
+All processes are implemented in a specially provided cloud environment with established open-source software. 
+This always ensures that no personal data of the users is disclosed.
+<p>
+*Note: the Transkribus HTR Pipeline is currently 
+deactivated; we are working on an alternative solution. You can try using Tesseract OCR, 
+though the results will likely be poor.
+</p>
+
+

app/templates/_base/_modals/_manual/02_getting_started.html.j2

@@ -0,0 +1,104 @@
+<h3 class="manual-chapter-title">Getting Started</h3>
+<h4>Getting Started</h4>
+<p>
+In this section, we will take you through all the steps you need to start analyzing your data with nopaque.
+</p>
+
+<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="#registration-and-login">Registration and login</a></li>
+    <li><a href="#preparing-files">Preparing files for analysis</a></li>
+    <li><a href="#converting-a-pdf-into-text">Converting a PDF into text data</a></li>
+    <li><a href="#extracting-linguistic-data">Extracting linguistic data from text</a></li>
+    <li><a href="#creating-a-corpus">Creating a corpus</a></li>
+    <li><a href="#analyzing-a-corpus">Analyzing a corpus</a></li>
+  </ol>
+</div>
+
+<p></p>
+
+<h5 id="registration-and-login">Registration and login</h5>
+<p>Before you can begin using nopaque, you will need to create a personal user account. 
+Open the menu (three dots) at the top right of the screen and choose “Register.” Enter 
+the required details listed on the registration page (username, password, email address). 
+After verifying your account via the link sent to your email, you can log in.</p>
+
+<h5 id="preparing-files">Preparing files for analysis</h5>
+<p>A few steps need to be taken before images, scans, or other text data are ready for 
+analysis in nopaque. The SpaCy NLP Pipeline service can only extract linguistic data 
+from texts in plain text (.txt) format. If your text is already in this format, you 
+can skip the next steps and go directly to <b>Extracting linguistic data from text</b>. 
+Otherwise, the next steps assume that you are starting off with image data.</p>
+<p>
+First, all data needs to be converted into PDF format. Using the <b>File Setup</b> service, 
+you can bundle images together – even of different formats – and convert them all into 
+one PDF file. Note that the File Setup service will sort the images based on their file 
+name in ascending order. It is thus recommended to name them accordingly, for example: 
+page-01.png, page-02.jpg, page-03.tiff.
+</p>
+<p>
+Add a title and description to your job and select the File Setup version* you want to use.
+After uploading the images and completing the File Setup job, the list of files added 
+can be seen under “Inputs.” Further below, under “Results,” you can find and download 
+the PDF output.</p>
+
+<h5 id="converting-a-pdf-into-text">Converting a PDF into text data</h5>
+<p>Select an image-to-text conversion tool depending on whether your PDF is primarily 
+composed of handwritten text or printed text. For printed text, select the <b>Tesseract OCR 
+Pipeline</b>. For handwritten text, select the <b>Transkribus HTR Pipeline</b>. Select the desired 
+language model or upload your own. Select the version* of Tesseract OCR you want to use 
+and click on submit to start the conversion. When the job is finished, various output 
+files can be seen and downloaded further below, under “Results.” You may want to review 
+the text output for errors and coherence. (Note: the Transkribus HTR Pipeline is currently 
+deactivated; we are working on an alternative solution. You can try using Tesseract OCR, 
+though the results will likely be poor.)
+</p>
+
+<h5 id="extracting-linguistic-data">Extracting linguistic data from text</h5>
+<p>The <b>SpaCy NLP Pipeline</b> service extracts linguistic information from plain text files 
+(in .txt format). Select the corresponding .txt file, the language model, and the 
+version* you want to use. When the job is finished, find and download the files in 
+<b>.json</b> and <b>.vrt</b> format under “Results.”</p>
+
+<h5 id="creating-a-corpus">Creating a corpus</h5>
+<p>Now, using the files in .vrt format, you can create a corpus. This can be done 
+in the <a href="{{ url_for('main.dashboard') }}">Dashboard</a> or 
+<a href="{{ url_for('services.corpus_analysis') }}">Corpus Analysis</a> sections under “My Corpora.” Click on “Create corpus” 
+and add a title and description for your corpus. After submitting, you will automatically 
+be taken to the corpus overview page (which can be called up again via the corpus lists) 
+of your new, still empty corpus. </p>
+<p>
+Further down in the “Corpus files” section, you can add texts in .vrt format 
+(results of the NLP service) to your new corpus. To do this, use the "Add Corpus File" 
+button and fill in the form that appears. Here, you can add 
+metadata to each text. After adding all texts to the corpus, it must 
+be prepared for analysis. This process can be initiated by clicking on the 
+"Build" button under "Actions". 
+On the corpus overview page, you can see information about the current status of 
+the corpus in the upper right corner. After the build process, the status "built" should be shown here.
+Now, your corpus is ready for analysis.</p>
+
+<h5 id="analyzing-a-corpus">Analyzing a corpus</h5>
+<p>Navigate to the corpus you would like to analyze and click on the Analyze button. 
+This will take you to an analysis overview page for your corpus. Here, you can find a 
+visualization of general linguistic information of your corpus, including tokens, 
+sentences, unique words, unique lemmas, unique parts of speech and unique simple parts 
+of speech. You will also find a pie chart of the proportional textual makeup of your 
+corpus and can view the linguistic information for each individual text file. A more 
+detailed visualization of token frequencies with a search option is also on this page.</p>
+<p>From the corpus analysis overview page, you can navigate to other analysis modules: 
+the <b>Query Builder</b> (under <b>Concordance</b>) and the <b>Reader</b>. With the Reader, you can read 
+your corpus texts tokenized with the associated linguistic information. The tokens can 
+be shown as lemmas, parts of speech, words, and can be displayed in different ways: 
+visually as plain text with the option of highlighted entities or as chips.</p>
+<p>The <b>Concordance</b> module allows for more specific, query-oriented text analyses. 
+Here, you can filter out text parameters and structural attributes in different 
+combinations. This is explained in more detail in the Query Builder section of the 
+manual.</p>
+
+<br>
+<br>
+*For all services, it is recommended to use the latest version unless you need a model 
+only available in an earlier version or are looking to reproduce data that was originally generated 
+using an older version.

app/templates/_base/_modals/_manual/02_registration_and_log_in.html.j2

@@ -1,18 +0,0 @@
-<h3 class="manual-chapter-title">Registration and Log in</h3>
-<div class="row">
-  <div class="col s12 m4">
-    <img alt="Registration and Log in" class="materialboxed responsive-img" src="{{ url_for('static', filename='images/manual/registration-and-log-in.png') }}">
-  </div>
-  <div class="col s12 m8">
-    <p>
-      Before you can start using the web platform, you need to create a user
-      account. This requires only a few details: just a user name, an e-mail
-      address and a password are needed. In order to register yourself, fill out
-      the form on the <a href="{{ url_for('auth.register') }}">registration page</a>. After successful registration, the
-      created account must be verified. To do this, follow the instructions
-      given in the automatically sent e-mail. Afterwards, you can log in as
-      usual with your username/email address and password in the log-in form
-      located next to the registration button.
-    </p>
-  </div>
-</div>

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

@@ -1,15 +1,22 @@
 <h3 class="manual-chapter-title">Dashboard</h3>
+<h4>About the dashboard</h4>
+<br>
 <div class="row">
   <div class="col s12 m4">
     <img alt="Dashboard" class="materialboxed responsive-img" src="{{ url_for('static', filename='images/manual/dashboard.png') }}">
   </div>
   <div class="col s12 m8">
     <p>
-      The <a href="{{ url_for('main.dashboard') }}">dashboard</a> provides a central overview of all resources assigned to the
+      The <a href="{{ url_for('main.dashboard') }}">dashboard</a> provides a central 
-      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
+      overview of all user-specific resources.
-      annotated text collections and jobs are the initiated file processing
+      These are <a href="{{ url_for('main.dashboard', _anchor='corpora') }}">corpora</a>, 
-      procedures. Both the job and the corpus listings can be searched using
+      created <a href="{{ url_for('main.dashboard', _anchor='jobs') }}">jobs</a>, and 
-      the search field displayed above them.
+      model <a href="{{ url_for('main.dashboard', _anchor='contributions') }}"">contributions</a>. 
+      A <b>corpus</b> is a freely composable annotated text collection. 
+      A <b>job</b> is an initiated file processing procedure. 
+      A <b>model</b> is a mathematical system for pattern recognition based on data examples that have been processed by AI. One can search for jobs as 
+      well as corpus listings using the search field displayed above them on the dashboard. 
+      Uploaded models can be found and edited by clicking on the corresponding service under <b>My Contributions</b>.      
     </p>
   </div>
   <div class="col s12">&nbsp;</div>
@@ -20,10 +27,10 @@
         <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
+          file format, which can be obtained via the Natural Language
-          Processing service. It contains, in addition to the actual text,
+          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

@@ -1,52 +1,107 @@
 <h3 class="manual-chapter-title">Services</h5>
+<h4>Services</h4>
+<p>
+In this section, we will describe the different services nopaque has to offer.
+</p>
+
 <div class="row">
   <div class="col s12 m4">
     <img alt="Services" class="materialboxed responsive-img" src="{{ url_for('static', filename='images/manual/services.png') }}">
   </div>
   <div class="col s12 m8">
     <p>
-      nopaque was designed from the ground up to be modular. This modularity
+      Nopaque was designed to be modular. Its modules are implemented in 
-      means that the offered workflow provides variable entry and exit points,
+      self-contained <b>services</b>, each of which represents a step in the 
-      so that different starting points and goals can be flexibly addressed.
+      workflow. The typical workflow involves using services one after another, 
-      Each of these modules are implemented in a self-contained service, each of
+      consecutively.
-      which represents a step in the workflow. The services are coordinated in
+      The typical workflow order can be taken from the listing of the 
-      such a way that they can be used consecutively. The order can either be
+      services in the left sidebar or from the nopaque manual (accessible via the pink 
-      taken from the listing of the services in the left sidebar or from the
+      button in the upper right corner). 
-      roadmap (accessible via the pink compass in the upper right corner). All
+      The services can also be applied at different starting and ending points, 
-      services are versioned, so the data generated with nopaque is always
+      which allows you to conduct your work flexibly.
+      All services are versioned, so the data generated with nopaque is always
       reproducible.
+      
+      <p>For all services, it is recommended to use the latest version (selected 
+      in the drop-down menu on the service page) unless you need a model 
+      only available in an earlier version or are looking to reproduce data that was originally generated 
+      using an older version.</p>
     </p>
   </div>
 </div>
 
-<h4 class="manual-chapter-title">File Setup</h4>
+
+
+<h4>File Setup</h4>
 <p>
   The <a href="{{ url_for('services.file_setup_pipeline') }}">File Setup Service</a> bundles image data, such as scans and photos,
   together in a handy PDF file. To use this service, use the job form to
   select the images to be bundled, choose the desired service version, and
-  specify a title and description. Please note that the service sorts the
+  specify a title and description.
-  images into the resulting PDF file based on the file names. So naming the
+  Note that the File Setup service will sort the images based on their file name in 
-  images correctly is of great importance. It has proven to be a good practice
+  ascending order. It is thus important and highly recommended to name 
-  to name the files according to the following scheme:
+  them accordingly, for example: 
-  page-01.png, page-02.jpg, page-03.tiff, etc. In general, you can assume
+  page-01.png, page-02.jpg, page-03.tiff. Generally, you can assume
   that the images will be sorted in the order in which the file explorer of
   your operating system lists them when you view the files in a folder
   sorted in ascending order by file name.
 </p>
 
 <h4>Optical Character Recognition (OCR)</h4>
-<p>Comming soon...</p>
+<p>
+  The <a href="{{ url_for('services.tesseract_ocr_pipeline') }}">Tesseract OCR Pipeline</a> 
+  converts image data - like photos and scans - into text data, making them machine-readable. 
+  This step enables you to proceed with the computational analysis of your documents. 
+  To use this service, use the job form to select the file you want to convert into text data. 
+  Then, choose the language model and service version you would like to use. Enter a title and description for your file and then 
+  submit your job. Once the job is finished, the results can be found and downloaded further below on the page, under 
+  the section labeled "Inputs."
+
+</p>
 
 <h4>Handwritten Text Recognition (HTR)</h4>
-<p>Comming soon...</p>
+<p>The Transkribus HTR Pipeline is currently 
+deactivated. We are working on an alternative solution. In the meantime, you can 
+try using Tesseract OCR, though the results will likely be poor.</p>
 
 <h4>Natural Language Processing (NLP)</h4>
-<p>Comming soon...</p>
+<p>The <a href="{{ url_for('services.spacy_nlp_pipeline') }}">SpaCy NLP Pipeline</a> extracts 
+information from plain text files (.txt format) via computational linguistic data processing 
+(tokenization, lemmatization, part-of-speech tagging and named-entity recognition). 
+To use this service, select the .txt file that you want to extract this information from. 
+Then select the language model and the version you want to use. Once the job is finished, you can find and download the files in 
+<b>.json</b> and <b>.vrt</b> format under the section labeled “Results.”</p>
 
 <h4>Corpus Analysis</h4>
 <p>
-  With the corpus analysis service, it is possible to create a text corpus
+  With the <a href="{{ url_for('services.corpus_analysis') }}">Corpus Analysis</a> 
-  and then explore it in an analysis session. The analysis session is realized
+  service, it is possible to create a text corpus
+  and then explore through it with analytical tools. The analysis session is realized
   on the server side by the Open Corpus Workbench software, which enables
-  efficient and complex searches with the help of the CQP Query Language.
+  efficient and complex searches with the help of the CQP Query Language.</p>
+  <p>
+  To use this service, navigate to the corpus you would like to analyze and click on the Analyze button. 
+  This will take you to an analysis overview page for your corpus. Here, you can find 
+  a visualization of general linguistic information of your corpus, including tokens, 
+  sentences, unique words, unique lemmas, unique parts of speech and unique simple 
+  parts of speech. You will also find a pie chart of the proportional textual makeup 
+  of your corpus and can view the linguistic information for each individual text file. 
+  A more detailed visualization of token frequencies with a search option is also on 
+  this page.
+  </p>
+  <p>
+  From the corpus analysis overview page, you can navigate to other analysis modules: 
+  the Query Builder (under Concordance) and the Reader. 
+  </p>
+  <p>
+  With the <b>Reader</b>, you can read your corpus texts tokenized with the associated linguistic information. The tokens 
+  can be shown as lemmas, parts of speech, words, and can be displayed in different 
+  ways: visually as plain text with the option of highlighted entities or as chips.
+  </p>
+  <p>
+  The Concordance module allows for more specific, query-oriented text analyses. 
+  Here, you can filter out text parameters and structural attributes in different 
+  combinations. This is explained in more detail in the <b>Query Builder</b> section of the 
+  manual.
+  </p>
 </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/08_cqp_query_language.html.j2

@@ -1,5 +1,22 @@
 <h3 class="manual-chapter-title">CQP Query Language</h3>
-<p>Within the Corpus Query Language, a distinction is made between two types of annotations: positional attributes and structural attributes. Positional attributes refer to a token, e.g. the word "book" is assigned the part-of-speech tag "NN", the lemma "book" and the simplified part-of-speech tag "NOUN" within the token structure. Structural attributes refer to text structure-giving elements such as sentence and entity markup. For example, the markup of a sentence is represented in the background as follows:</p>
+<h4 id="cqp-query-language">CQP Query Language</h4>
+<p>In this section, we will provide some functional explanations of the properties of the Corpus Query Language. This includes 
+the types of linguistic attributes one can work with and how to use them in your query.</p>
+
+<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="#overview-annotations">Overview of annotation types</a></li>
+    <li><a href="#positional-attributes">Positional attributes</a></li>
+    <li><a href="#searching-positional-attributes">How to search for positional attributes</a></li>
+    <li><a href="#structural-attributes">Structural attributes</a></li>
+    <li><a href="#searching-structural-attributes">How to search for structural attributes</a></li>
+
+  </ol>
+</div>
+
+<h4 id="overview-annotations">Overview of annotation types</h4>
+<p>Within the Corpus Query Language, a distinction is made between two types of annotations: <b>positional attributes</b> and <b>structural attributes</b>. Positional attributes refer to a token, e.g. the word "book" is assigned the part-of-speech tag "NN", the lemma "book" and the simplified part-of-speech tag "NOUN" within the token structure. Structural attributes refer to text structure-giving elements such as sentence and entity markup. For example, the markup of a sentence is represented in the background as follows:</p>
 <pre>
   <code>
     <span class="green-text">&lt;s&gt;                                     structural attribute</span>
@@ -13,7 +30,7 @@
   </code>
 </pre>
 
-<h4>Positional attributes</h4>
+<h4 id="positional-attributes">Positional attributes</h4>
 <p>Before you can start searching for positional attributes (also called tokens), it is necessary to know what properties they contain.</p>
 <ol>
   <li><span class="blue-text"><b>word</b></span>: The string as it is also found in the original text</li>
@@ -33,7 +50,7 @@
   </li>
 </ol>
 
-<h5>Searching for positional attributes</h5>
+<h5 id="searching-positional-attributes">How to search for positional attributes</h5>
 <div>
   <p>
     <b>Token with no condition on any property (also called <span class="blue-text">wildcard token</span>)</b><br>
@@ -118,7 +135,7 @@
   <pre style="margin-top: 0;"   ><code>         ^             ^ the braces indicate the start and end of an option group</code></pre>
 </div>
 
-<h4>Structural attributes</h4>
+<h4 id="structural-attributes">Structural attributes</h4>
 <p>nopaque provides several structural attributes for query. A distinction is made between attributes with and without value.</p>
 <ol>
   <li><span class="green-text"><b>s</b></span>: Annotates a sentence</li>
@@ -153,7 +170,7 @@
   </li>
 </ol>
 
-<h5>Searching for structural attributes</h5>
+<h5 id="searching-structural-attributes">How to search for structural attributes</h5>
 <pre><code>&lt;ent&gt; [] &lt;/ent&gt;;                       A one token long entity of any type</code></pre>
 <pre><code>&lt;ent_type="PERSON"&gt; [] &lt;/ent_type&gt;;     A one token long entity of type PERSON</code></pre>
 <pre><code>&lt;ent_type="PERSON"&gt; []* &lt;/ent_type&gt;;    Entity of any length of type PERSON</code></pre>

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

@@ -1,26 +1,46 @@
 <h3 class="manual-chapter-title">Query Builder Tutorial</h3>
-
+<h4>Query Builder</h4>
-<p>The query builder helps you to make a query in the form of the Corpus Query 
+<p>In this section, we will provide you with more detailed instructions on how to use the Query Builder - 
-Language (CQL) to your text. You can use the CQL to filter out various types of 
+nopaque's main user-friendly tool for finding and analyzing different linguistic elements of your texts.</p>
-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>
-<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="#general-overview">General Overview</a></li>
-    <li><a href="#edit-options-tutorial">Options to edit your query</a></li>
+    <li><a href="#add-new-token-tutorial">Add a new token to your query</a></li>
-    <li><a href="#add-structural-attribute-tutorial">Add structural Attributes 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>
 
+<h4 id="general-overview">General Overview</h4>
+<p>The Query Builder can be accessed via <a href=" {{ url_for('main.dashboard') }}">My Corpora</a> or <a href=" {{ url_for('services.corpus_analysis') }}">Corpus Analysis</a> in the sidebar options. 
+Click on the corpus you wish to analyze. You will be sent to its corpus overview page.
+Here, click on <b>Analyze</b> to reach the analysis page.
+The analysis page features different options for analyzing your corpus, including 
+visualizations and a <b>Reader</b> module. In this case, we want to open the query builder. 
+To do so, click on the <b>Concordance</b> button on the top of the page.</p>
+<p>The query builder uses the <b>Corpus Query Language (CQL)</b> 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, the different text parameters can be combined.</p>
+<p>Tokens and structural attributes can be added by clicking on the <b>"+"</b> button
+(what we call 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) will be displayed underneath the query field.</p>
+<p>For more information, see our <b>manual section for the Corpus Query Language.</b>
+<br>
+Advanced users can make direct use of CQL by switching to <b>expert mode</b> via the toggle button.
+</p>
+<p>The entire input field can be cleared using the red trash icon on the right.</p>
+<br>
+
+
 {# Add Token Tutorial #}
 <div>
   <hr>
@@ -29,7 +49,7 @@ under the tab "Examples".</p>
   <h4 id="add-new-token-tutorial">Add new token to your Query</h4>
   <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>
+  "Word" is selected by default. </p>
   
   <h5>Word and Lemma</h5>
   <p>If you want to search for a specific word or lemma and the respective 
@@ -46,13 +66,13 @@ 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 
+  <p>Here you can search for a token with unspecified attributes (also called wildcard token). This 
-  alone and should always be extended with an incidence modifier or stand in a 
+  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 +81,8 @@ under the tab "Examples".</p>
   <hr>
   <p></p>
   <br>
-  <h4 id="edit-options-tutorial">Options to edit your token</h4> 
+  <h4 id="edit-options-tutorial">Options for editing your query</h4> 
-  <p>You have the possibility to extend or specify your searched token with 
+  <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 +96,6 @@ 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 +104,7 @@ 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 +120,10 @@ 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 +142,33 @@ 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>.
+  Click on Sentence to add the sentence chips: <div class="chip" style="background-color:#FD9720;">Sentence Start</div> 
-  When you are done with your query or the content 
+  and <div class="chip" style="background-color:#FD9720;">Sentence End</div>. 
-  between the Sentence tags, you have to click the Sentence button one more time 
+  These mark where the sentence starts and ends. Use drag-and-drop to place them accordingly. When 
-  to close it. The corresponding button is called 
+  the Sentence attribute is added, the input marker will automatically be 
-  <div class="chip" style="background-color:#FD9720;">Sentence End</div>.<br>
+  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 
+  <p>With entities, i.e. units of meaning, you can search for text sections that 
-  follow a certain code. For example, persons, dates, certain events. You can 
+  contain more specific information, for example, persons, dates, or events. The 
-  select the codes using the drop-down menus. You can find an explanation of 
+  codes for these categories can be selected using the drop-down menus. You can find an explanation of 
-  the respective abbreviations under the tab "Tagsets". <br>
+  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>
+  <h5>Meta Data (currently unavailable)</h5>
-  <p>With the meta data you can annotate your text and add specific conditions. 
+  <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 +184,39 @@ 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/manual.html.j2

@@ -3,21 +3,22 @@
     <h2>Manual</h2>
     <ul class="tabs" id="manual-modal-toc">
       <li class="tab"><a href="#manual-modal-introduction">Introduction</a></li>
-      <li class="tab"><a href="#manual-modal-registration-and-log-in">Registration and Log in</a></li>
+      <li class="tab"><a href="#manual-modal-getting-started">Getting Started</a></li>
       <li class="tab"><a href="#manual-modal-dashboard">Dashboard</a></li>
       <li class="tab"><a href="#manual-modal-services">Services</a></li>
-      <li class="tab"><a href="#manual-modal-a-closer-look-at-the-corpus-analysis">A closer look at the Corpus Analysis</a></li>
+      <!-- <li class="tab"><a href="#manual-modal-a-closer-look-at-the-corpus-analysis">A closer look at the Corpus Analysis</a></li> -->
-      <li class="tab"><a href="#manual-modal-cqp-query-language">CQP Query Language</a></li>
       <li class="tab"><a href="#manual-modal-query-builder">Query Builder</a></li>
+      <li class="tab"><a href="#manual-modal-cqp-query-language">CQP Query Language</a></li>
+
       <li class="tab"><a href="#manual-modal-tagsets">Tagsets</a></li>
     </ul>
     <div id="manual-modal-introduction">
       <br>
       {% include "_base/_modals/_manual/01_introduction.html.j2" %}
     </div>
-    <div id="manual-modal-registration-and-log-in">
+    <div id="manual-modal-getting-started">
       <br>
-      {% include "_base/_modals/_manual/02_registration_and_log_in.html.j2" %}
+      {% include "_base/_modals/_manual/02_getting_started.html.j2" %}
     </div>
     <div id="manual-modal-dashboard">
       <br>
@@ -27,10 +28,10 @@
       <br>
       {% include "_base/_modals/_manual/06_services.html.j2" %}
     </div>
-    <div id="manual-modal-a-closer-look-at-the-corpus-analysis">
+    <!-- <div id="manual-modal-a-closer-look-at-the-corpus-analysis">
       <br>
       {% include "_base/_modals/_manual/07_a_closer_look_at_the_corpus_analysis.html.j2" %}
-    </div>
+    </div> -->
     <div id="manual-modal-cqp-query-language">
       <br>
       {% include "_base/_modals/_manual/08_cqp_query_language.html.j2" %}

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/sidenav.html.j2

@@ -1,19 +1,18 @@
 <ul class="sidenav sidenav-fixed" id="sidenav">
-  <li>
+  <li class="primary-color hide-on-small-only">
-    <div class="user-view">
+      <div style="overflow: hidden; height: 64px; width: 250px;">
-      <div class="background primary-color"></div>
+        <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">
+  <li class="primary-variant-color center-align hide-on-small-only" style="padding-top: 8px; height:48px;">
-    <div style="overflow: hidden;height: 64px; width: 250px;">
+    <img src="{{ url_for('static', filename='images/nopaque_slogan_transparent.png') }}" style="width:85%">
-      <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: ;">
+  </li>
-    </div>
+  <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> #}
-  <li><a 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>
@@ -51,8 +50,9 @@
   <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 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">person</i>Public Users</a>
+        <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>

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

@@ -40,6 +40,7 @@
       <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">
@@ -66,7 +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>
@@ -127,7 +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">
@@ -336,7 +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">
@@ -409,9 +410,3 @@
   </div>
 </div>
 {% endmacro %}
-
-{# {% macro scripts(id_prefix) %}
-<script>
-  const concordanceQueryBuilder = new ConcordanceQueryBuilder();
-</script>
-{% endmacro %} #}

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()

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_*)