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 push $IMAGE_TAG
+    - docker build --tag $DOCKER_IMAGE --file $DOCKERFILE $DOCKER_BUILD_PATH
+    - docker save $DOCKER_IMAGE > docker_image.tar
+  artifacts:
+    paths:
+      - docker_image.tar
 
-include:
-  - template: Security/Container-Scanning.gitlab-ci.yml
+publish:
+  stage: publish
+  before_script:
+    - docker login --username gitlab-ci-token --password $CI_JOB_TOKEN $CI_REGISTRY
+  script:
+    - docker load --input docker_image.tar
+    - docker push $DOCKER_IMAGE
+  after_script:
+    - docker logout $CI_REGISTRY
 
 container_scanning:
+  stage: sca
   rules:
+    # Run the job on commits to the default branch
     - if: $CI_COMMIT_BRANCH == $CI_DEFAULT_BRANCH
-      when: on_success
-      variables:
-        CS_IMAGE: $CI_REGISTRY_IMAGE:latest
+      when: always
+    # Run the job on tag creation
     - if: $CI_COMMIT_TAG
-      when: on_success
-      variables:
-        CS_IMAGE: ${CI_REGISTRY_IMAGE}:${CI_COMMIT_REF_NAME}
+      when: always
+    # Don't run the job on all other occasions
     - when: never
+  variables:
+    CS_IMAGE: $DOCKER_IMAGE

.vscode/extensions.json

@@ -1,7 +1,8 @@
 {
     "recommendations": [
-        "samuelcolvin.jinjahtml",
+        "irongeek.vscode-env",
         "ms-azuretools.vscode-docker",
-        "ms-python.python"
+        "ms-python.python",
+        "samuelcolvin.jinjahtml"
     ]
 }

.vscode/settings.json

@@ -1,13 +1,9 @@
 {
     "editor.rulers": [79],
     "files.insertFinalNewline": true,
-    "python.terminal.activateEnvironment": false,
     "[css]": {
         "editor.tabSize": 2
     },
-    "[scss]": {
-        "editor.tabSize": 2
-    },
     "[html]": {
         "editor.tabSize": 2
     },
@@ -17,7 +13,7 @@
     "[jinja-html]": {
         "editor.tabSize": 2
     },
-    "[jinja-js]": {
+    "[scss]": {
         "editor.tabSize": 2
     }
 }

Dockerfile

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

README.md

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

app/SpaCyNLPPipelineModel.defaults.yml

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

app/TesseractOCRPipelineModel.defaults.yml

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

app/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/main/routes.py

@@ -45,12 +45,6 @@ def dashboard():
     )
 
 
-# @bp.route('/user_manual')
-# @register_breadcrumb(bp, '.user_manual', '<i class="material-icons left">help</i>User manual')
-# def user_manual():
-#     return render_template('main/user_manual.html.j2', title='User manual')
-
-
 @bp.route('/news')
 @register_breadcrumb(bp, '.news', '<i class="material-icons left">email</i>News')
 def news():

app/models.py

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

app/services/services.yml

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

app/static/js/app.js

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

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

@@ -3,16 +3,16 @@ nopaque.corpus_analysis.query_builder.ElementReferences = class ElementReference
     // General Elements
     this.queryInputField = document.querySelector('#corpus-analysis-concordance-query-builder-input-field');
     this.queryChipElements = [];
+    this.queryElementTarget = document.querySelector('.query-element-target')
     this.editingModusOn = false;
     this.editedQueryChipElementIndex = undefined;
+    this.deleteQueryButton = document.querySelector('#corpus-analysis-concordance-delete-query-button');
 
     // Structural Attribute Builder Elements
     this.structuralAttrModal = M.Modal.getInstance(document.querySelector('#corpus-analysis-concordance-structural-attr-modal'));
     this.englishEntTypeSelection = document.querySelector('#corpus-analysis-concordance-english-ent-type-selection');
     this.germanEntTypeSelection = document.querySelector('#corpus-analysis-concordance-german-ent-type-selection');
-    this.textAnnotationSelection = document.querySelector('#corpus-analysis-concordance-text-annotation-options');
-    this.textAnnotationInput = document.querySelector('#corpus-analysis-concordance-text-annotation-input');
-
+    
     // Token Attribute Builder Elements
     this.positionalAttrModal = M.Modal.getInstance(document.querySelector('#corpus-analysis-concordance-positional-attr-modal'));
     this.positionalAttrSelection = document.querySelector('#corpus-analysis-concordance-positional-attr-selection');

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

@@ -2,30 +2,58 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
   constructor() {
     this.elements = new nopaque.corpus_analysis.query_builder.ElementReferences();
 
-    this.incidenceModifierEventListeners();
-    this.nAndMInputSubmitEventListeners();
+    this.addEventListenersToQueryElementTarget();
+    this.addEventListenersToIncidenceModifier();
+    this.addEventListenersToNAndMInputSubmit();
 
-    let queryBuilderDisplay = document.querySelector("#corpus-analysis-concordance-query-builder-display");
-    let expertModeDisplay = document.querySelector("#corpus-analysis-concordance-expert-mode-display");
-    let expertModeSwitch = document.querySelector("#corpus-analysis-concordance-expert-mode-switch");
-    
-    expertModeSwitch.addEventListener("change", () => {
-      const isChecked = expertModeSwitch.checked;
-      if (isChecked) {
-        queryBuilderDisplay.classList.add("hide");
-        expertModeDisplay.classList.remove("hide");
-        this.switchToExpertModeParser();
-      } else {
-        queryBuilderDisplay.classList.remove("hide");
-        expertModeDisplay.classList.add("hide");
-        this.switchToQueryBuilderParser();
-      }
-    });
+    this.elements.deleteQueryButton.addEventListener('click', () => {this.resetQueryInputField()});
+    this.expertModeQueryBuilderSwitchHandler();
 
     this.extensions = {
       structuralAttributeBuilderFunctions: new nopaque.corpus_analysis.query_builder.StructuralAttributeBuilderFunctions(this),
       tokenAttributeBuilderFunctions: new nopaque.corpus_analysis.query_builder.TokenAttributeBuilderFunctions(this),
     };
+
+    this.dropdown = M.Dropdown.init(
+      document.querySelector('.dropdown-trigger[data-toggle-area="token-incidence-modifiers"]'), 
+      {
+        onCloseStart: () => {
+          this.unselectChipElement(this.elements.queryInputField.querySelector('.chip.teal'));
+        }
+      }
+    )
+  }
+
+  addEventListenersToQueryElementTarget() {
+    this.elements.queryElementTarget.addEventListener('click', () => {
+      this.elements.positionalAttrModal.open();
+    });
+    this.elements.queryElementTarget.addEventListener('dragstart', this.handleDragStart.bind(this, this.elements.queryElementTarget));
+    this.elements.queryElementTarget.addEventListener('dragend', this.handleDragEnd);
+  }
+
+  addEventListenersToIncidenceModifier() {
+    // Eventlisteners for the incidence modifiers. There are two different types of incidence modifiers: token and character incidence modifiers.
+    document.querySelectorAll('.incidence-modifier-selection').forEach(button => {
+      let dropdownId = button.parentNode.parentNode.id;
+      if (dropdownId === 'corpus-analysis-concordance-token-incidence-modifiers-dropdown') {
+        button.addEventListener('click', () => this.tokenIncidenceModifierHandler(button.dataset.token, button.innerHTML));
+      } else if (dropdownId === 'corpus-analysis-concordance-character-incidence-modifiers-dropdown') {
+        button.addEventListener('click', () => this.extensions.tokenAttributeBuilderFunctions.characterIncidenceModifierHandler(button));
+      }
+    });
+  }
+
+  addEventListenersToNAndMInputSubmit() {
+    // Eventlisteners for the submit of n- and m-values of the incidence modifier modal for "exactly n" or "between n and m".
+    document.querySelectorAll('.n-m-submit-button').forEach(button => {
+      let modalId = button.dataset.modalId;
+      if (modalId === 'corpus-analysis-concordance-exactly-n-token-modal' || modalId === 'corpus-analysis-concordance-between-nm-token-modal') {
+        button.addEventListener('click', () => this.tokenNMSubmitHandler(modalId));
+      } else if (modalId === 'corpus-analysis-concordance-exactly-n-character-modal' || modalId === 'corpus-analysis-concordance-between-nm-character-modal') {
+        button.addEventListener('click', () => this.extensions.tokenAttributeBuilderFunctions.characterNMSubmitHandler(modalId));
+      }
+    });
   }
 
   toggleClass(elements, className, action) {
@@ -36,26 +64,27 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
 
   resetQueryInputField() {
     this.elements.queryInputField.innerHTML = '';
-    this.addPlaceholder();
+    this.addQueryElementTarget();
     this.updateChipList();
     this.queryPreviewBuilder();
   }
 
+  addQueryElementTarget() {
+    let queryElementTarget = nopaque.Utils.HTMLToElement(
+      `
+      <a class="query-element-target btn-floating btn-small blue-grey lighten-4 waves-effect waves-light tooltipped" style="margin-bottom:10px; margin-right:5px;" draggable="true" data-position="bottom" data-tooltip="Add an Element to your query">
+        <i class="material-icons">add</i>
+      </a>
+      `
+    );
+    this.elements.queryInputField.appendChild(queryElementTarget);
+    this.elements.queryElementTarget = queryElementTarget;
+    this.addEventListenersToQueryElementTarget();
+  }
+
   updateChipList() {
     this.elements.queryChipElements = this.elements.queryInputField.querySelectorAll('.query-component');
   }
-
-  removePlaceholder() {
-    let placeholder = this.elements.queryInputField.querySelector('#corpus-analysis-concordance-query-builder-input-field-placeholder');
-    if (placeholder && this.elements.queryInputField !== undefined) {
-      this.elements.queryInputField.innerHTML = '';
-    }
-  }
-
-  addPlaceholder() {
-    let placeholder = nopaque.Utils.HTMLToElement('<span id="corpus-analysis-concordance-query-builder-input-field-placeholder">Click on a button to add a query component</span>');
-    this.elements.queryInputField.appendChild(placeholder);
-  }
   
   resetMaterializeSelection(selectionElements, value = "default") {
     selectionElements.forEach(selectionElement => {
@@ -68,7 +97,7 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
     })
   }
 
-  submitQueryChipElement(dataType = undefined, prettyQueryText = undefined, queryText = undefined, index = null, isClosingTag = false, isEditable = false) {
+  submitQueryChipElement(dataType=undefined, prettyQueryText=undefined, queryText=undefined, index=null, isClosingTag=false, isEditable=false) {
     if (this.elements.editingModusOn) {
       let editedQueryChipElement = this.elements.queryChipElements[this.elements.editedQueryChipElementIndex];
       editedQueryChipElement.dataset.type = dataType;
@@ -81,45 +110,41 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
     }
   }
 
-  queryChipFactory(dataType, prettyQueryText, queryText, index = null, isClosingTag = false, isEditable = false) {
+  queryChipFactory(dataType, prettyQueryText, queryText, index=null, isClosingTag=false, isEditable=false) {
     // Creates a new query chip element, adds Eventlisteners for selection, deletion and drag and drop and appends it to the query input field.
     queryText = nopaque.Utils.escape(queryText);
     prettyQueryText = nopaque.Utils.escape(prettyQueryText);
     let queryChipElement = nopaque.Utils.HTMLToElement(
       `
-        <span class="chip query-component" data-type="${dataType}" data-query="${queryText}" draggable="true" data-closing-tag="${isClosingTag}">
+        <span class="chip query-component" data-type="${dataType}" data-query="${queryText}" draggable="true"">
           ${prettyQueryText}${isEditable ? '<i class="material-icons chip-action-button" data-chip-action="edit" style="padding-left:5px; font-size:18px; cursor:pointer;">edit</i>': ''}
-          ${isClosingTag ? '<i class="material-icons chip-action-button" data-chip-action="lock" style="padding-top:5px; font-size:20px; cursor:pointer;">lock_open</i>' : '<i class="material-icons close chip-action-button" data-chip-action="delete">close</i>'}
+          ${isClosingTag ? '' : '<i class="material-icons close chip-action-button" data-chip-action="delete">close</i>'}
         </span>
       `
     );
-    this.actionListeners(queryChipElement);
+    this.addActionListeners(queryChipElement);
     queryChipElement.addEventListener('dragstart', this.handleDragStart.bind(this, queryChipElement));
     queryChipElement.addEventListener('dragend', this.handleDragEnd);
-
-    // Ensures that metadata is always at the end of the query and if an index is given, inserts the query chip at the given index and if there is a closing tag, inserts the query chip before the closing tag.
-    this.removePlaceholder();
-    let lastChild = this.elements.queryInputField.lastChild;
-    let isLastChildTextAnnotation = lastChild && lastChild.dataset.type === 'text-annotation';
-    if (!index) {
-      let closingTagElement = this.elements.queryInputField.querySelector('[data-closing-tag="true"]');
-      if (closingTagElement) {
-        index = Array.from(this.elements.queryInputField.children).indexOf(closingTagElement);
-      }
-    }
-    if (dataType !== 'text-annotation' && index) {
-      this.elements.queryInputField.insertBefore(queryChipElement, this.elements.queryChipElements[index]);
-    } else if (dataType !== 'text-annotation' && isLastChildTextAnnotation) {
-      this.elements.queryInputField.insertBefore(queryChipElement, lastChild);
+    // If an index is given, inserts the query chip after the given index (only relevant for Incidence Modifier) and if there is a closing tag, inserts the query chip before the closing tag.
+    if (index !== null) {
+      this.updateChipList();
+      this.elements.queryChipElements[index].after(queryChipElement);
     } else {
-      this.elements.queryInputField.appendChild(queryChipElement);
+      this.elements.queryInputField.insertBefore(queryChipElement, this.elements.queryElementTarget);
+    }
+    if (isClosingTag) {
+      this.moveQueryElementTarget(queryChipElement);
     }
 
     this.updateChipList();
     this.queryPreviewBuilder();
   }
 
-  actionListeners(queryChipElement) {
+  moveQueryElementTarget(element) {
+    this.elements.queryInputField.insertBefore(this.elements.queryElementTarget, element);
+  }
+
+  addActionListeners(queryChipElement) {
     let notQuantifiableDataTypes = ['start-sentence', 'end-sentence', 'start-entity', 'start-empty-entity', 'end-entity', 'token-incidence-modifier'];
     queryChipElement.addEventListener('click', (event) => {
       if (event.target.classList.contains('chip')) {
@@ -129,19 +154,15 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
       }
     });
     let chipActionButtons = queryChipElement.querySelectorAll('.chip-action-button');
-    // chipActionButtons.forEach(button => {
-    for (let button of chipActionButtons) {
+    chipActionButtons.forEach(button => {
       button.addEventListener('click', (event) => {
       if (event.target.dataset.chipAction === 'delete') {
         this.deleteChipElement(queryChipElement);
       } else if (event.target.dataset.chipAction === 'edit') {
         this.editChipElement(queryChipElement);
-      } else if (event.target.dataset.chipAction === 'lock') {
-        this.lockClosingChipElement(queryChipElement);
       }
       });
-    }
-    // });
+    });
   }
 
   editChipElement(queryChipElement) {
@@ -151,9 +172,6 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
       case 'start-entity':
         this.extensions.structuralAttributeBuilderFunctions.editStartEntityChipElement(queryChipElement);
         break;
-      case 'text-annotation':
-        this.extensions.structuralAttributeBuilderFunctions.editTextAnnotationChipElement(queryChipElement);
-        break;
       case 'token':
         let queryElementsContent = this.extensions.tokenAttributeBuilderFunctions.prepareTokenQueryElementsContent(queryChipElement);
         this.extensions.tokenAttributeBuilderFunctions.editTokenChipElement(queryElementsContent);
@@ -163,22 +181,15 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
     }
   }
 
-  lockClosingChipElement(queryChipElement) {
-    queryChipElement.dataset.closingTag = 'false';
-    let lockIcon = queryChipElement.querySelector('[data-chip-action="lock"]');
-    lockIcon.textContent = 'lock';
-    // TODO: Write unlock-Function?
-    lockIcon.dataset.chipAction = 'unlock';
-  }
-
   deleteChipElement(attr) {
     let elementIndex = Array.from(this.elements.queryInputField.children).indexOf(attr);
     switch (attr.dataset.type) {
       case 'start-sentence':
-        this.deletingClosingTagHandler(elementIndex, 'end-sentence');
+        this.deleteClosingTagHandler(elementIndex, 'end-sentence');
         break;
+      case 'start-empty-entity':
       case 'start-entity':
-        this.deletingClosingTagHandler(elementIndex, 'end-entity');
+        this.deleteClosingTagHandler(elementIndex, 'end-entity');
         break;
       case 'token':
         let nextElement = Array.from(this.elements.queryInputField.children)[elementIndex+1];
@@ -189,14 +200,11 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
         break;
     }
     this.elements.queryInputField.removeChild(attr);
-    if (this.elements.queryInputField.children.length === 0) {
-      this.addPlaceholder();
-    }
     this.updateChipList();
     this.queryPreviewBuilder();
   }
 
-  deletingClosingTagHandler(elementIndex, closingTagType) {
+  deleteClosingTagHandler(elementIndex, closingTagType) {
     let closingTags = this.elements.queryInputField.querySelectorAll(`[data-type="${closingTagType}"]`);
     for (let i = 0; i < closingTags.length; i++) {
       let closingTag = closingTags[i];
@@ -208,7 +216,7 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
     }
   }
 
-  handleDragStart(queryChipElement, event) {
+  handleDragStart(queryChipElement) {
     // is called when a query chip is dragged. It creates a dropzone (in form of a chip) for the dragged chip and adds it to the query input field.
     let queryChips = this.elements.queryInputField.querySelectorAll('.query-component');
     if (queryChipElement.dataset.type === 'token-incidence-modifier') {
@@ -226,13 +234,17 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
 
         let targetChipClone = targetChipElement.cloneNode(true);
         element.insertAdjacentElement('afterend', targetChipClone);
-
+        //TODO: Change to two different functions for drag and drop
         this.addDragDropListeners(targetChipClone, queryChipElement);
       }
     }, 0);
   }
 
   handleDragEnd(event) {
+    // is called when a query chip is dropped. It removes the dropzones and initializes the tooltips if the dragged element is the query element target.
+    if (event.target.classList.contains('query-element-target')) {
+      M.Tooltip.init(event.target);
+    }
     document.querySelectorAll('.drop-target').forEach(target => target.remove());
   }
 
@@ -286,24 +298,36 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
   }
 
   selectChipElement(attr) {
-    document.querySelectorAll('.chip.teal').forEach(element => {
-        if (element !== attr) {
-          element.classList.remove('teal', 'lighten-2');
-          this.toggleClass(['token-incidence-modifiers'], 'disabled', 'add');
-        }
-    });
+    if (attr.classList.contains('teal')) {
+      return;
+    }
 
     this.toggleClass(['token-incidence-modifiers'], 'disabled', 'toggle');
     attr.classList.toggle('teal');
     attr.classList.toggle('lighten-5');
+
+    M.Dropdown.getInstance(document.querySelector('.dropdown-trigger[data-toggle-area="token-incidence-modifiers"]')).open();
+
   }
 
-  tokenIncidenceModifierHandler(incidenceModifier, incidenceModifierPretty) {
+  unselectChipElement(attr) {
+    let nModalInstance = M.Modal.getInstance(document.querySelector('#corpus-analysis-concordance-exactly-n-token-modal'));
+    let nmModalInstance = M.Modal.getInstance(document.querySelector('#corpus-analysis-concordance-between-nm-token-modal'));
+    if (nModalInstance.isOpen || nmModalInstance.isOpen) {
+      return;
+    }
+    attr.classList.remove('teal', 'lighten-5');
+    this.toggleClass(['token-incidence-modifiers'], 'disabled', 'add');
+  }
+
+  tokenIncidenceModifierHandler(incidenceModifier, incidenceModifierPretty, nOrNM = false) {
     // Adds a token incidence modifier to the query input field.
     let selectedChip = this.elements.queryInputField.querySelector('.chip.teal');
-    let selectedChipIndex = Array.from(this.elements.queryInputField.children).indexOf(selectedChip);
-    this.submitQueryChipElement('token-incidence-modifier', incidenceModifierPretty, incidenceModifier, selectedChipIndex+1);
-    this.selectChipElement(selectedChip);
+    let selectedChipIndex = Array.from(this.elements.queryChipElements).indexOf(selectedChip);
+    if (nOrNM) {
+      this.unselectChipElement(selectedChip);
+    }
+    this.submitQueryChipElement('token-incidence-modifier', incidenceModifierPretty, incidenceModifier, selectedChipIndex);
   }
 
   tokenNMSubmitHandler(modalId) {
@@ -321,29 +345,30 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
     let instance = M.Modal.getInstance(modal);
     instance.close();
 
-    this.tokenIncidenceModifierHandler(input, pretty_input);
+    this.tokenIncidenceModifierHandler(input, pretty_input, true);
   }
 
-  incidenceModifierEventListeners() {
-    // Eventlisteners for the incidence modifiers. There are two different types of incidence modifiers: token and character incidence modifiers.
-    document.querySelectorAll('.incidence-modifier-selection').forEach(button => {
-      let dropdownId = button.parentNode.parentNode.id;
-      if (dropdownId === 'corpus-analysis-concordance-token-incidence-modifiers-dropdown') {
-        button.addEventListener('click', () => this.tokenIncidenceModifierHandler(button.dataset.token, button.innerHTML));
-      } else if (dropdownId === 'corpus-analysis-concordance-character-incidence-modifiers-dropdown') {
-        button.addEventListener('click', () => this.characterIncidenceModifierHandler(button));
-      }
+  expertModeQueryBuilderSwitchHandler() {
+    let queryBuilderDisplay = document.querySelector("#corpus-analysis-concordance-query-builder-display");
+    let expertModeDisplay = document.querySelector("#corpus-analysis-concordance-expert-mode-display");
+    let expertModeSwitch = document.querySelector("#corpus-analysis-concordance-expert-mode-switch");
+    let submitModal = M.Modal.getInstance(document.querySelector('#corpus-analysis-concordance-switch-to-query-builder-submit-modal'));
+    
+    let confirmSwitchToQueryBuilderButton = document.querySelector('.switch-action[data-switch-action="confirm"]');
+    confirmSwitchToQueryBuilderButton.addEventListener("click", () => {
+      queryBuilderDisplay.classList.remove("hide");
+      expertModeDisplay.classList.add("hide");
+      this.switchToQueryBuilderParser();
     });
-  }
 
-  nAndMInputSubmitEventListeners() {
-    // Eventlisteners for the submit of n- and m-values of the incidence modifier modal for "exactly n" or "between n and m".
-    document.querySelectorAll('.n-m-submit-button').forEach(button => {
-      let modalId = button.dataset.modalId;
-      if (modalId === 'corpus-analysis-concordance-exactly-n-token-modal' || modalId === 'corpus-analysis-concordance-between-nm-token-modal') {
-        button.addEventListener('click', () => this.tokenNMSubmitHandler(modalId));
-      } else if (modalId === 'corpus-analysis-concordance-exactly-n-character-modal' || modalId === 'corpus-analysis-concordance-between-nm-character-modal') {
-        button.addEventListener('click', () => this.extensions.tokenAttributeBuilderFunctions.characterNMSubmitHandler(modalId));
+    expertModeSwitch.addEventListener("change", () => {
+      const isChecked = expertModeSwitch.checked;
+      if (isChecked) {
+        queryBuilderDisplay.classList.add("hide");
+        expertModeDisplay.classList.remove("hide");
+        this.switchToExpertModeParser();
+      } else {
+        submitModal.open();
       }
     });
   }
@@ -361,15 +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', 'text-annotation', 'token'];
+    let editableElements = ['start-entity', 'token'];
     for (let chipElement of chipElements) {
-      let isClosingTag = closingTagElements.includes(chipElement['type']);
       let isEditable = editableElements.includes(chipElement['type']);
       if (chipElement['query'] === '[]'){
         isEditable = false;
       }
-      this.submitQueryChipElement(chipElement['type'], chipElement['pretty'], chipElement['query'], null, isClosingTag, isEditable);
+      this.submitQueryChipElement(chipElement['type'], chipElement['pretty'], chipElement['query'], null, false, isEditable);
     }
   }
 
@@ -395,11 +418,7 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
         pretty: 'Entity End',
         type: 'end-entity'
       },
-      ':: ?match\\.text_[A-Za-z]+="[^"]+"': {
-        pretty: '',
-        type: 'text-annotation'
-      },
-      '\\[(word|lemma|pos|simple_pos)=(("[^"]+")|(\\u0027[^\\u0027]+\\u0027)) ?(%c)? ?((\\&|\\|) ?(word|lemma|pos|simple_pos)=(("[^"]+")|(\\u0027[^\\u0027]+\\u0027)) ?(%c)? ?)*\\]': {
+      '\\[(word|lemma|pos|simple_pos)=("(?:[^"\\\\]|\\\\")*") ?(%c)? ?((\\&|\\|) ?(word|lemma|pos|simple_pos)=("(?:[^"\\\\]|\\\\")*") ?(%c)? ?)*\\]': {
         pretty: '',
         type: 'token'
       },
@@ -452,14 +471,8 @@ nopaque.corpus_analysis.query_builder.QueryBuilder = class QueryBuilder {
             case ':: ?match\\.text_[A-Za-z]+="[^"]+"':
               prettyText = stringElement.replace(/:: ?match\.text_|"|"/g, '');
               break;
-            case '\\[(word|lemma|pos|simple_pos)=(("[^"]+")|(\\u0027[^\\u0027]+\\u0027)) ?(%c)? ?((\\&|\\|) ?(word|lemma|pos|simple_pos)=(("[^"]+")|(\\u0027[^\\u0027]+\\u0027)) ?(%c)? ?)*\\]':
-              let doubleQuotes = /(word|lemma|pos|simple_pos)="[^"]+"/gi;
-              let singleQuotes = /(word|lemma|pos|simple_pos)='[^']+'/gi;
-              if (doubleQuotes.exec(stringElement)) {
-                prettyText = stringElement.replace(/^\[|\]$|"/g, '');
-              } else if (singleQuotes.exec(stringElement)) {
-                prettyText = stringElement.replace(/^\[|\]$|'/g, '');
-              }
+            case '\\[(word|lemma|pos|simple_pos)=("(?:[^"\\\\]|\\\\")*") ?(%c)? ?((\\&|\\|) ?(word|lemma|pos|simple_pos)=("(?:[^"\\\\]|\\\\")*") ?(%c)? ?)*\\]':
+              prettyText = stringElement.replace(/^\[|\]$|(?<!\\)"/g, '');
               prettyText = prettyText.replace(/\&/g, ' and ').replace(/\|/g, ' or ');
               break;
             case '(?<!\\[) ?\\{[0-9]+} ?(?![^\\]]\\])':

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

@@ -5,8 +5,6 @@ nopaque.corpus_analysis.query_builder.StructuralAttributeBuilderFunctions = clas
 
     this.structuralAttrModalEventlisteners();
 
-    document.querySelector('#corpus-analysis-concordance-text-annotation-submit').addEventListener('click', () => this.textAnnotationSubmitHandler());
-
     this.elements.structuralAttrModal = M.Modal.init(
       document.querySelector('#corpus-analysis-concordance-structural-attr-modal'), 
       {
@@ -46,10 +44,7 @@ nopaque.corpus_analysis.query_builder.StructuralAttributeBuilderFunctions = clas
 
   resetStructuralAttrModal() {
     this.app.resetMaterializeSelection([this.elements.englishEntTypeSelection, this.elements.germanEntTypeSelection]);
-    this.app.resetMaterializeSelection([this.elements.textAnnotationSelection], 'address');
-    this.elements.textAnnotationInput.value = '';
-
-    this.app.toggleClass(['entity-builder', 'text-annotation-builder'], 'hide', 'add');
+    this.app.toggleClass(['entity-builder'], 'hide', 'add');
     this.toggleEditingAreaStructuralAttrModal('remove');
     this.elements.editingModusOn = false;
     this.elements.editedQueryChipElementIndex = undefined;
@@ -64,11 +59,6 @@ nopaque.corpus_analysis.query_builder.StructuralAttributeBuilderFunctions = clas
         break;
       case 'entity':
         this.app.toggleClass(['entity-builder'], 'hide', 'toggle');
-        this.app.toggleClass(['text-annotation-builder'], 'hide', 'add');
-        break;
-      case 'meta-data':
-        this.app.toggleClass(['text-annotation-builder'], 'hide', 'toggle');
-        this.app.toggleClass(['entity-builder'], 'hide', 'add');
         break;
       default:
         break;
@@ -77,29 +67,7 @@ nopaque.corpus_analysis.query_builder.StructuralAttributeBuilderFunctions = clas
 
   toggleEditingAreaStructuralAttrModal(action) {
     // If the user edits a query chip element, the corresponding editing area is displayed and the other areas are hidden or disabled.
-    this.app.toggleClass(['sentence-button', 'entity-button', 'text-annotation-button', 'any-type-entity-button'], 'disabled', action);
-  }
-
-  textAnnotationSubmitHandler() {
-    let noValueMetadataMessage = document.querySelector('#corpus-analysis-concordance-no-value-metadata-message');
-    let textAnnotationSubmit = document.querySelector('#corpus-analysis-concordance-text-annotation-submit');
-    let textAnnotationInput = document.querySelector('#corpus-analysis-concordance-text-annotation-input');
-    let textAnnotationOptions = document.querySelector('#corpus-analysis-concordance-text-annotation-options');
-
-    if (textAnnotationInput.value === '') {
-      textAnnotationSubmit.classList.add('red');
-      noValueMetadataMessage.classList.remove('hide');
-      setTimeout(() => {
-        textAnnotationSubmit.classList.remove('red');
-      }, 500);
-      setTimeout(() => {
-        noValueMetadataMessage.classList.add('hide');
-      }, 3000);
-    } else {
-      let queryText = `:: match.text_${textAnnotationOptions.value}="${textAnnotationInput.value}"`;
-      this.app.submitQueryChipElement('text-annotation', `${textAnnotationOptions.value}=${textAnnotationInput.value}`, queryText, null, false, true);
-      this.elements.structuralAttrModal.close();
-    }
+    this.app.toggleClass(['sentence-button', 'entity-button', 'any-type-entity-button'], 'disabled', action);
   }
 
   editStartEntityChipElement(queryChipElement) {
@@ -111,15 +79,4 @@ nopaque.corpus_analysis.query_builder.StructuralAttributeBuilderFunctions = clas
     let selection = isEnglishEntType ? this.elements.englishEntTypeSelection : this.elements.germanEntTypeSelection;
     this.app.resetMaterializeSelection([selection], entType);
   }
-
-  editTextAnnotationChipElement(queryChipElement) {
-    this.elements.structuralAttrModal.open();
-    this.app.toggleClass(['text-annotation-builder'], 'hide', 'remove');
-    this.toggleEditingAreaStructuralAttrModal('add');
-    let [textAnnotationSelection, textAnnotationContent] = queryChipElement.dataset.query
-      .replace(/:: ?match\.text_|"|"/g, '')
-      .split('=');
-    this.app.resetMaterializeSelection([this.elements.textAnnotationSelection], textAnnotationSelection);
-    this.elements.textAnnotationInput.value = textAnnotationContent;
-  }
 }

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

@@ -52,14 +52,14 @@ nopaque.corpus_analysis.query_builder.TokenAttributeBuilderFunctions = class Tok
     let input = this.tokenInputCheck(this.elements.tokenBuilderContent);
     switch (elem) {
       case 'option-group':
-        input.value  += '(option1|option2)';
+        this.cursorPositionInputfieldHandler(input, '(option1|option2)');
         let firstIndex = input.value.indexOf('option1');
         let lastIndex = firstIndex + 'option1'.length;
-        input.focus();
         input.setSelectionRange(firstIndex, lastIndex);
         break;
       case 'wildcard-char':
-        input.value += '.';
+        this.cursorPositionInputfieldHandler(input, '.');
+        input.focus();
         break;
       case 'and':
         this.conditionHandler('and');
@@ -73,9 +73,19 @@ nopaque.corpus_analysis.query_builder.TokenAttributeBuilderFunctions = class Tok
     this.optionToggleHandler();
   }
 
+  cursorPositionInputfieldHandler(input, addedInput) {
+    let cursorPosition = input.selectionStart;
+    let textBeforeCursor = input.value.substring(0, cursorPosition);
+    let textAfterCursor = input.value.substring(cursorPosition);
+    let newInputValue = textBeforeCursor + addedInput + textAfterCursor;
+    input.value = newInputValue;
+    let newCursorPosition = cursorPosition + addedInput.length;
+    input.setSelectionRange(newCursorPosition, newCursorPosition);
+  }
+
   characterIncidenceModifierHandler(elem) {
     let input = this.tokenInputCheck(this.elements.tokenBuilderContent);
-    input.value += elem.dataset.token;
+    this.cursorPositionInputfieldHandler(input, elem.dataset.token);
   }
 
   characterNMSubmitHandler(modalId) {
@@ -83,12 +93,12 @@ nopaque.corpus_analysis.query_builder.TokenAttributeBuilderFunctions = class Tok
     let input_n = modal.querySelector('.n-m-input[data-value-type="n"]').value;
     let input_m = modal.querySelector('.n-m-input[data-value-type="m"]') || undefined;
     input_m = input_m !== undefined ? ',' + input_m.value : '';
-    let input = `${input_n}${input_m}`;
+    let addedInput = `${input_n}${input_m}`;
 
     let instance = M.Modal.getInstance(modal);
     instance.close();
-    let tokenInput = this.tokenInputCheck(this.elements.tokenBuilderContent);
-    tokenInput.value += '{' + input + '}';
+    let input = this.tokenInputCheck(this.elements.tokenBuilderContent);
+    this.cursorPositionInputfieldHandler(input, `{${addedInput}}`);
   }
 
   conditionHandler(conditionText) {
@@ -102,36 +112,12 @@ nopaque.corpus_analysis.query_builder.TokenAttributeBuilderFunctions = class Tok
     notSelectedButton.parentNode.removeChild(notSelectedButton);
     this.elements.tokenQuery.appendChild(tokenQueryTemplateClone);
 
-    // Deleting the options which do not make sense in the context of the condition like "word" AND "word". Also sets selection default.
-    let selectionDefault = "word";
-    let optionDeleteList = ['empty-token'];
-    if (conditionText === 'and') {
-      switch (this.elements.positionalAttrSelection.value) {
-        case 'english-pos' || 'german-pos':
-          optionDeleteList.push('english-pos', 'german-pos');
-          break;
-        default:
-          optionDeleteList.push(this.elements.positionalAttrSelection.value);
-          break;
-      }
-    } else {
-      let originalSelectionList = 
-      `
-        <option value="word" selected>word</option>
-        <option value="lemma" >lemma</option>
-        <option value="english-pos">english pos</option>
-        <option value="german-pos">german pos</option>
-        <option value="simple_pos">simple_pos</option>
-      `;
-      this.elements.positionalAttrSelection.innerHTML = originalSelectionList;
-      M.FormSelect.init(this.elements.positionalAttrSelection);
-    }
     let lastTokenQueryRow = this.elements.tokenQuery.lastElementChild;
     if(lastTokenQueryRow.querySelector('[data-kind-of-token="word"]') || lastTokenQueryRow.querySelector('[data-kind-of-token="lemma"]')) {
       this.appendIgnoreCaseCheckbox(lastTokenQueryRow.querySelector('.token-query-template-content'), this.elements.ignoreCaseCheckbox.checked);
     }
     this.elements.ignoreCaseCheckbox.checked = false;
-    this.setTokenSelection(selectionDefault, optionDeleteList);
+    this.setTokenSelection();
   }
 
   deleteTokenQueryRow(deleteButton) {
@@ -160,7 +146,7 @@ nopaque.corpus_analysis.query_builder.TokenAttributeBuilderFunctions = class Tok
     this.elements.positionalAttrSelection.appendChild(option);
   }
 
-  appendIgnoreCaseCheckbox(parentElement, checked = false) {
+  appendIgnoreCaseCheckbox(parentElement, checked=false) {
     let ignoreCaseCheckboxClone = document.querySelector('#ignore-case-checkbox-template').content.cloneNode(true);
     parentElement.appendChild(ignoreCaseCheckboxClone);
     M.Tooltip.init(parentElement.querySelectorAll('.tooltipped'));
@@ -169,7 +155,7 @@ nopaque.corpus_analysis.query_builder.TokenAttributeBuilderFunctions = class Tok
     }
   }
 
-  setTokenSelection(selection, optionDeleteList) {
+  setTokenSelection(selection="word", optionDeleteList=['empty-token']) {
     optionDeleteList.forEach(option => {
       if (this.elements.positionalAttrSelection.querySelector(`option[value=${option}]`) !== null) {
         this.elements.positionalAttrSelection.querySelector(`option[value=${option}]`).remove();
@@ -309,8 +295,8 @@ nopaque.corpus_analysis.query_builder.TokenAttributeBuilderFunctions = class Tok
   }
 
   prepareTokenQueryElementsContent(queryChipElement) {
-    //this regex searches for word or lemma or pos or simple_pos="any string within single or double quotes" followed by one or no ignore case markers, followed by one or no condition characters.
-    let regex = new RegExp('(word|lemma|pos|simple_pos)=(("[^"]+")|(\\\\u0027[^\\\\u0027]+\\\\u0027)) ?(%c)? ?(\\&|\\|)?', 'gm');
+    //this regex searches for word or lemma or pos or simple_pos="any string (also quotation marks escaped by backslash) within double quotes" followed by one or no ignore case markers, followed by one or no condition characters.
+    let regex = new RegExp('(word|lemma|pos|simple_pos)=("(?:[^"\\\\]|\\\\")*") ?(%c)? ?(\\&|\\|)?', 'gm');
     let m;
     let queryElementsContent = [];
     while ((m = regex.exec(queryChipElement.dataset.query)) !== null) {
@@ -323,7 +309,7 @@ nopaque.corpus_analysis.query_builder.TokenAttributeBuilderFunctions = class Tok
       if (tokenAttr === 'pos') {
         tokenAttr = 'english-pos';
       }
-      let tokenValue = m[2].replace(/"|'/g, '');
+      let tokenValue = m[2].replace(/(?<!\\)"/g, '');
       let ignoreCase = false;
       let condition = undefined;
       m.forEach((match) => {

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

@@ -0,0 +1,34 @@
+<h3 class="manual-chapter-title">Introduction</h3>
+<h4>Introduction</h4>
+<p>
+  Nopaque is a web application that offers different services and tools to support 
+  researchers working with image and text-based data. These services are logically 
+  connected and build upon each other. They include:
+</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/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
-      user. These are <a href="{{ url_for('main.dashboard', _anchor='corpora') }}">corpora</a> and created <a href="{{ url_for('main.dashboard', _anchor='jobs') }}">jobs</a>. Corpora are freely composable
-      annotated text collections and jobs are the initiated file processing
-      procedures. Both the job and the corpus listings can be searched using
-      the search field displayed above them.
+      The <a href="{{ url_for('main.dashboard') }}">dashboard</a> provides a central 
+      overview of all user-specific resources.
+      These are <a href="{{ url_for('main.dashboard', _anchor='corpora') }}">corpora</a>, 
+      created <a href="{{ url_for('main.dashboard', _anchor='jobs') }}">jobs</a>, and 
+      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
-          Processing service. It contains, in addition to the actual text,
+          file format, which can be obtained via the Natural Language
+          Processing service. It contains, in addition to the text,
           further annotations that are searchable in combination with optional
-          addable metadata during your analysis. 
+          metadata that can be added during your analysis. 
         </p>
       </div>
     </div>

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

@@ -0,0 +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 to be modular. Its modules are implemented in 
+      self-contained <b>services</b>, each of which represents a step in the 
+      workflow. The typical workflow involves using services one after another, 
+      consecutively.
+      The typical workflow order can be taken from the listing of the 
+      services in the left sidebar or from the nopaque manual (accessible via the pink 
+      button in the upper right corner). 
+      The services can also be applied at different starting and ending points, 
+      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>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.
+  Note that the File Setup service will sort the images based on their file name in 
+  ascending order. It is thus important and highly recommended to name 
+  them accordingly, for example: 
+  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>
+  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>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>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 <a href="{{ url_for('services.corpus_analysis') }}">Corpus Analysis</a> 
+  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.</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>
-
-<p>The query builder helps you to make a query in the form of the Corpus Query 
-Language (CQL) to your text. You can use the CQL to filter out various types of 
-text parameters, for example, a specific word, a lemma, or you can set part-of-speech 
-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>
+<h4>Query Builder</h4>
+<p>In this section, we will provide you with more detailed instructions on how to use the Query Builder - 
+nopaque's main user-friendly tool for finding and analyzing different linguistic elements of your texts.</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="#add-new-token-tutorial">Add new token to your query</a></li>
-    <li><a href="#edit-options-tutorial">Options to edit your query</a></li>
-    <li><a href="#add-structural-attribute-tutorial">Add structural Attributes to your query</a></li>
+    <li><a href="#general-overview">General Overview</a></li>
+    <li><a href="#add-new-token-tutorial">Add a new token to your query</a></li>
+    <li><a href="#edit-options-tutorial">Options for editing your query</a></li>
+    <li><a href="#add-structural-attribute-tutorial">Add structural attributes to your query</a></li>
     <li><a href="#general-options-query-builder">General options</a></li>
   </ol>
 </div>
 
+<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>
@@ -29,8 +49,8 @@ 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 
   category is selected in the drop-down menu, you can type in the word or lemma 
@@ -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 
-  alone and should always be extended with an incidence modifier or stand in a 
+  <p>Here you can search for a token with unspecified attributes (also called wildcard token). This 
+  selection should never stand alone and should always be extended with an incidence modifier or stand in a 
   larger query, because otherwise all possible tokens would be searched for and 
   the program would crash.</p>
-  <p></p>
   <br>
 </div>
 
@@ -61,8 +81,8 @@ under the tab "Examples".</p>
   <hr>
   <p></p>
   <br>
-  <h4 id="edit-options-tutorial">Options to edit your token</h4> 
-  <p>You have the possibility to extend or specify your searched token with 
+  <h4 id="edit-options-tutorial">Options for editing your query</h4> 
+  <p>You have the possibility to extend or specify the token you are searching for with 
   certain factors. For this the query builder offers some fixed options. You can 
   find more information about the options in the Corpus Query Language Tutorial.</p>
   <br>
@@ -76,7 +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>.
-  When you are done with your query or the content 
-  between the Sentence tags, you have to click the Sentence button one more time 
-  to close it. The corresponding button is called 
-  <div class="chip" style="background-color:#FD9720;">Sentence End</div>.<br>
+  Click on Sentence to add the sentence chips: <div class="chip" style="background-color:#FD9720;">Sentence Start</div> 
+  and <div class="chip" style="background-color:#FD9720;">Sentence End</div>. 
+  These mark where the sentence starts and ends. Use drag-and-drop to place them accordingly. When 
+  the Sentence attribute is added, the input marker will automatically be 
+  moved between the sentence chips. Use drag-and-drop as needed to continue your query 
+  at a different position.
   <br>
 
   <h5>Entities</h5>
-  <p>With entities, i.e. units of meaning, you search for text sections that 
-  follow a certain code. For example, persons, dates, certain events. You can 
-  select the codes using the drop-down menus. You can find an explanation of 
-  the respective abbreviations under the tab "Tagsets". <br>
+  <p>With entities, i.e. units of meaning, you can search for text sections that 
+  contain more specific information, for example, persons, dates, or events. The 
+  codes for these categories can be selected using the drop-down menus. You can find an explanation of 
+  these abbreviations under the tab "Tagsets". <br>
   You can also search for unspecified entities by selecting "Add entity of any type".</p>
-  To close the entity query you started, you have to click the entity button one more time. This will make the <div class="chip" style="background-color:#A6E22D;">Entity End</div> element appear in your query.
+  Click on the Entity button to add the entity chips <div class="chip" style="background-color:#A6E22D;">Entity Type=</div> and <div class="chip" style="background-color:#A6E22D;">Entity End</div>.
+  <p>The entity type can be changed by clicking on the pen symbol on the chip. When 
+  the Entity attribute is added, the input marker will automatically be 
+  moved between the entity chips. Use drag-and-drop as needed to continue your query 
+  at a different position.</p>
   <img src="{{ url_for('static', filename='images/manual/query_builder/entity.gif') }}" alt="entity explanation" width="100%;" style="margin-bottom:20px;">
   <p></p>
   <br>
 
-  <h5>Meta Data</h5>
-  <p>With the meta data you can annotate your text and add specific conditions. 
+  <h5>Meta Data (currently unavailable)</h5>
+  <p>The meta data function is being worked on and cannot currently be used!
+  <br>
+  With the meta data you can annotate your text and add specific conditions. 
   You can select a category on the left and enter your desired value on the right. 
   The selected metadata will apply to your entire request and will be added at the end.</p>
   <img src="{{ url_for('static', filename='images/manual/query_builder/meta_data.gif') }}" alt="meta data explanation" width="100%;" style="margin-bottom:20px;">
@@ -155,14 +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

@@ -3,45 +3,46 @@
     <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-cqp-query-language">CQP Query Language</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-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 "main/_manual_modal/_01_introduction.html.j2" %}
+      {% 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 "main/_manual_modal/_02_registration_and_log_in.html.j2" %}
+      {% include "_base/_modals/_manual/02_getting_started.html.j2" %}
     </div>
     <div id="manual-modal-dashboard">
       <br>
-      {% include "main/_manual_modal/_03_dashboard.html.j2" %}
+      {% include "_base/_modals/_manual/03_dashboard.html.j2" %}
     </div>
     <div id="manual-modal-services">
       <br>
-      {% include "main/_manual_modal/_06_services.html.j2" %}
+      {% 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 "main/_manual_modal/_07_a_closer_look_at_the_corpus_analysis.html.j2" %}
-    </div>
+      {% include "_base/_modals/_manual/07_a_closer_look_at_the_corpus_analysis.html.j2" %}
+    </div> -->
     <div id="manual-modal-cqp-query-language">
       <br>
-      {% include "main/_manual_modal/_08_cqp_query_language.html.j2" %}
+      {% include "_base/_modals/_manual/08_cqp_query_language.html.j2" %}
     </div>
     <div id="manual-modal-query-builder">
       <br>
-      {% include "main/_manual_modal/_09_query_builder.html.j2" %}
+      {% include "_base/_modals/_manual/09_query_builder.html.j2" %}
     </div>
     <div id="manual-modal-tagsets">
       <br>
-      {% include "main/_manual_modal/_10_tagsets.html.j2" %}
+      {% include "_base/_modals/_manual/10_tagsets.html.j2" %}
     </div>
   </div>
   <div class="modal-footer">

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/modals.html.j2

@@ -0,0 +1,5 @@
+{% include "_base/_modals/manual.html.j2" %}
+
+{% if current_user.is_authenticated and not current_user.terms_of_use_accepted %}
+{% include "_base/_modals/terms_of_use.html.j2" %}
+{% endif %}

app/templates/_base/navbar.html.j2

@@ -5,12 +5,20 @@
       <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">
         <li><a href="{{ url_for('main.news') }}"><i class="material-icons left">email</i>News</a></li>
-        <li><a class="dropdown-trigger no-autoinit" data-target="nav-more-dropdown" href="#!" id="nav-more-dropdown-trigger"><i class="material-icons">more_vert</i></a></li>
+        <li>
+          <a class="dropdown-trigger no-autoinit" data-target="nav-more-dropdown" href="#!" id="nav-more-dropdown-trigger">
+            {% if current_user.is_authenticated %}
+            <img src="{{ url_for('users.user_avatar', user_id=current_user.id) }}" alt="avatar" class="circle left" style="height: 54px; padding: 10px 10px 0 0;">
+            {{ current_user.username }} ({{ current_user.email }})
+            {% else %}
+            <i class="material-icons left">more_vert</i>
+            {% endif %}
+          </a>
+        </li>
       </ul>
     </div>
     <div class="nav-content primary-variant-color">
@@ -22,17 +30,14 @@
         {% endif %}
         {%- endfor -%}
       </ul>
-      {# {% if current_user.is_authenticated %}
-      <a class="btn-floating btn-large halfway-fab modal-trigger pink tooltipped waves-effect waves-light" data-tooltip="Roadmap" href="#roadmap-modal"><i class="material-icons">explore</i></a>
-      {% endif %} #}
-      <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

@@ -1,34 +1,18 @@
 <ul class="sidenav sidenav-fixed" id="sidenav">
-  <li>
-    <div class="user-view">
-      <div class="background primary-color"></div>
-        <span class="white-text name">
-          {% if current_user.username|length > 32 %}
-          {{ current_user.username[:29] + '...' }}
-          {% else %}
-          {{ current_user.username }}
-          {% endif %}
-        </span>
-        <span class="white-text email">
-          {% if current_user.email|length > 32 %}
-            {{ current_user.email[:29] + '...' }}
-          {% else %}
-            {{ current_user.email }}
-          {% endif %}
-        </span>
+  <li class="primary-color hide-on-small-only">
+      <div style="overflow: hidden; height: 64px; width: 250px;">
+        <a href="{{ url_for('main.index') }}">
+          <img class="hide-on-small-only" src="{{ url_for('static', filename='images/nopaque_-_logo_name_slogan.svg') }}" style="height: 128px; margin-top: -32px;">
+        </a>
       </div>
-    </div>
   </li>
-  {# <li class="primary-color">
-    <div style="overflow: hidden;height: 64px; width: 250px;">
-      <img class="hide-on-small-only" src="{{ url_for('static', filename='images/nopaque_-_logo_name_slogan.svg') }}" style="height: 128px; margin-top: -32px; margin-left: ;">
-    </div>
-  </li> #}
-  {# <li><a href="{{ url_for('main.index') }}">nopaque</a></li> #}
-  <li class="hide-on-large-only">
+  <li class="primary-variant-color center-align hide-on-small-only" style="padding-top: 8px; height:48px;">
+    <img src="{{ url_for('static', filename='images/nopaque_slogan_transparent.png') }}" style="width:85%">
+  </li>
+  <li class="hide-on-med-and-up"><a class="waves-effect" href="{{ url_for('main.index') }}"><i class="material-icons left">home</i>nopaque</a></li>
+  <li>
     <a class="waves-effect" href="{{ url_for('main.news') }}"><i class="material-icons left">email</i>News</a>
   </li>
-  {# <li><a href="{{ url_for('main.user_manual') }}"><i class="material-icons">help</i>Manual</a></li> #}
   <li>
     <a class="waves-effect" class="waves-effect" href="{{ url_for('main.dashboard') }}"><i class="material-icons">dashboard</i>Dashboard</a>
     <ul>
@@ -66,12 +50,13 @@
   <li>
     <a class="waves-effect" class="waves-effect" href="{{ url_for('main.social_area') }}"><i class="material-icons">rocket_launch</i>Social Area</a>
     <ul>
-  <li>
-    <a class="waves-effect" href="{{ url_for('main.social_area', _anchor='public-users') }}" style="padding-left: 47px;"><i class="material-icons">person</i>Public Users</a>
-  </li>
-  <li>
-    <a class="waves-effect" href="{{ url_for('main.social_area', _anchor='public-corpora') }}" style="padding-left: 47px;"><i class="nopaque-icons">I</i>Public Corpora</a>
-  </li>
+      <li><a href="{{ url_for('users.user', user_id=current_user.id) }}" style="padding-left: 47px;"><i class="material-icons left">person</i>My Profile</a></li>
+      <li>
+        <a class="waves-effect" href="{{ url_for('main.social_area', _anchor='public-users') }}" style="padding-left: 47px;"><i class="material-icons">group</i>Public Users</a>
+      </li>
+      <li>
+        <a class="waves-effect" href="{{ url_for('main.social_area', _anchor='public-corpora') }}" style="padding-left: 47px;"><i class="nopaque-icons">I</i>Public Corpora</a>
+      </li>
     </ul>
   </li>
   <li class="hide-on-large-only"><div class="divider"></div></li>

app/templates/base.html.j2

@@ -16,16 +16,16 @@
 
 {% block styles %}
 {{ super() }}
-{% include "_styles.html.j2" %}
+{% include "_base/styles.html.j2" %}
 {% endblock styles %}
 
 {% block navbar %}
-{% include "_navbar.html.j2" %}
+{% include "_base/navbar.html.j2" %}
 {% endblock navbar %}
 
 {% block sidenav %}
 {% if current_user.is_authenticated %}
-{% include "_sidenav.html.j2" %}
+{% include "_base/sidenav.html.j2" %}
 {% endif %}
 {% endblock sidenav %}
 
@@ -34,23 +34,17 @@
 {% block page_content %}{% endblock page_content %}
 <div id="modals">
   {% block modals %}
-  {% include "main/_manual_modal.html.j2" %}
-  {# {% if current_user.is_authenticated %}
-  {% include "_roadmap.html.j2" %}
-  {% endif %} #}
-  {% if current_user.is_authenticated and not current_user.terms_of_use_accepted %}
-    {% include "_terms_of_use_modal.html.j2" %}
-  {% endif %}
+  {% include "_base/modals.html.j2" %}
   {% endblock modals %}
 </div>
 {% endblock main %}
 
 {% block footer_attribs %} class="page-footer primary-variant-color"{% endblock footer_attribs %}
 {% block footer %}
-{% include "_footer.html.j2" %}
+{% include "_base/footer.html.j2" %}
 {% endblock footer %}
 
 {% block scripts %}
 {{ super() }}
-{% include "_scripts.html.j2" %}
+{% include "_base/scripts.html.j2" %}
 {% endblock scripts %}

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

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

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

@@ -1,11 +1,18 @@
 {% macro card_content(id_prefix) %}
 <form id="corpus-analysis-concordance-query-builder-form">
   <div class="row">
-    <div class="col s9" id="corpus-analysis-concordance-query-builder-input-field-container">
+    <div class="col s8" id="corpus-analysis-concordance-query-builder-input-field-container">
       <div id="corpus-analysis-concordance-query-builder-input-field">
-        <p id="corpus-analysis-concordance-query-builder-input-field-placeholder">Click on the buttons below to build your query.</p>
+        <a class="query-element-target btn-floating btn-small blue-grey lighten-4 waves-effect waves-light tooltipped" style="margin-bottom:10px; margin-right:5px;" draggable="true" data-position="bottom" data-tooltip="Add a token to your query">
+          <i class="material-icons">add</i>
+        </a>
       </div>
     </div>
+    <div class="col s1 center-align">
+      <a class="btn-floating btn waves-effect waves-light red" id="corpus-analysis-concordance-delete-query-button" style="margin-top:18px;">
+        <i class="material-icons">delete</i>
+      </a>
+    </div>
     <div class="input-field col s3">
       <i class="material-icons prefix">arrow_forward</i>
       <input class="validate corpus-analysis-action" id="corpus-analysis-concordance-form-subcorpus-name" name="subcorpus-name" type="text" required pattern="^[A-Z][a-z0-9\-]*" value="Last"></input>
@@ -30,9 +37,10 @@
   <div class="row">
     <div class="col s12">
       <p></p>
-      <a class="btn waves-effect waves-light tooltipped modal-trigger" href="#corpus-analysis-concordance-positional-attr-modal" data-position="bottom" data-tooltip="Search for any token, for example a word, a lemma or a part-of-speech tag">Add new token to your query</a>
-      <a class="btn waves-effect waves-light tooltipped modal-trigger" href="#corpus-analysis-concordance-structural-attr-modal" data-position="bottom" data-tooltip="Structure your query with structural attributes, for example sentences, entities or annotate the text">Add structural attributes to your query</a>
-      <a class="btn waves-effect waves-light tooltipped dropdown-trigger disabled" data-target="corpus-analysis-concordance-token-incidence-modifiers-dropdown" data-toggle-area="token-incidence-modifiers" data-position="top" data-tooltip="Incidence Modifiers are special characters or patterns, <br>which determine how often a character represented previously should occur.">incidence modifiers</a>
+      <a class="btn-small waves-effect waves-light tooltipped modal-trigger" href="#corpus-analysis-concordance-positional-attr-modal" data-position="bottom" data-tooltip="Search for any token, for example a word, a lemma or a part-of-speech tag">Add new token to your query</a>
+      <a class="btn-small waves-effect waves-light tooltipped modal-trigger" href="#corpus-analysis-concordance-structural-attr-modal" data-position="bottom" data-tooltip="Structure your query with structural attributes, for example sentences, entities or annotate the text">Add structural attributes to your query</a>
+      <a class="btn-small waves-effect waves-light tooltipped dropdown-trigger disabled" data-target="corpus-analysis-concordance-token-incidence-modifiers-dropdown" data-toggle-area="token-incidence-modifiers" data-position="top" data-tooltip="Incidence Modifiers are special characters or patterns, <br>which determine how often a character represented previously should occur.">incidence modifiers</a>
+      <a class="modal-trigger" data-manual-modal-chapter="manual-modal-query-builder" href="#manual-modal"><i class="material-icons left" style="color:black">help_outline</i></a>
     </div>
   </div>
   <div class="row">
@@ -59,7 +67,7 @@
 <div id="corpus-analysis-concordance-structural-attr-modal" class="modal">
   <div class="modal-content">
     <div class="attr-modal-header">
-      <h5>Which structural attribute do you want to add to your query?<a class="modal-trigger" data-manual-modal-chapter="manual-modal-query-builder" href="#manual-modal"><i class="material-icons left" id="corpus-analysis-concordance-add-structural-attribute-tutorial-info-icon">help_outline</i></a></h5>
+      <h5>Which structural attribute do you want to add to your query?<a class="modal-trigger" data-manual-modal-chapter="manual-modal-query-builder" data-manual-modal-chapter-anchor="add-structural-attribute-tutorial" href="#manual-modal"><i class="material-icons left" id="corpus-analysis-concordance-add-structural-attribute-tutorial-info-icon">help_outline</i></a></h5>
     </div>
     <p></p>
     <br>
@@ -67,7 +75,6 @@
       <div class="col s12">
         <a class="btn-small waves-effect waves-light" data-structural-attr-modal-action-button="sentence" data-toggle-area="sentence-button">sentence</a>
         <a class="btn-small waves-effect waves-light" data-structural-attr-modal-action-button="entity" data-toggle-area="entity-button">entity</a>
-        <a class="btn-small waves-effect waves-light" data-structural-attr-modal-action-button="meta-data" data-toggle-area="text-annotation-button">Meta Data</a>
       </div>
     </div>
     <div id="corpus-analysis-concordance-entity-builder" data-toggle-area="entity-builder" class="hide">
@@ -111,39 +118,6 @@
         </div>
       </div>
     </div>
-    <div id="corpus-analysis-concordance-text-annotation-builder" data-toggle-area="text-annotation-builder" class="hide">
-      <p></p>
-      <br>
-      <div class="row">
-        <div class= "input-field col s4 l3">
-          <select name="text-annotation-options" id="corpus-analysis-concordance-text-annotation-options">
-            <option class="btn-small waves-effect waves-light" value="address">address</option>
-            <option class="btn-small waves-effect waves-light" value="author">author</option>
-            <option class="btn-small waves-effect waves-light" value="booktitle">booktitle</option>
-            <option class="btn-small waves-effect waves-light" value="chapter">chapter</option>
-            <option class="btn-small waves-effect waves-light" value="editor">editor</option>
-            <option class="btn-small waves-effect waves-light" value="institution">institution</option>
-            <option class="btn-small waves-effect waves-light" value="journal">journal</option>
-            <option class="btn-small waves-effect waves-light" value="pages">pages</option>
-            <option class="btn-small waves-effect waves-light" value="publisher">publisher</option>
-            <option class="btn-small waves-effect waves-light" value="publishing_year">publishing year</option>
-            <option class="btn-small waves-effect waves-light" value="school">school</option>
-            <option class="btn-small waves-effect waves-light" value="title">title</option>
-          </select>
-          <label>Meta data</label>
-        </div>
-        <div class= "input-field col s7 l5">
-          <i class="material-icons prefix">mode_edit</i>
-          <input placeholder="Type in your text annotation" type="text" id="corpus-analysis-concordance-text-annotation-input">
-        </div>
-        <div class="col s1 l1 center-align">
-          <p class="btn-floating waves-effect waves-light" id="corpus-analysis-concordance-text-annotation-submit">
-            <i class="material-icons right">send</i>
-          </p>
-        </div>
-        <div class="hide" id="corpus-analysis-concordance-no-value-metadata-message"><i>No value entered!</i></div>
-      </div>
-    </div>
   </div>
 </div>
 {% endmacro %}
@@ -154,7 +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">
@@ -363,7 +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">
@@ -436,9 +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()

app/templates/main/_manual_modal/_01_introduction.html.j2

@@ -1,9 +0,0 @@
-<h3 class="manual-chapter-title">Introduction</h3>
-<p>
-  nopaque is a web-based digital working environment. It implements a
-  workflow based on the research process in the humanities and supports its
-  users in processing their data in order to subsequently apply digital
-  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>

app/templates/main/_manual_modal/_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/main/_manual_modal/_06_services.html.j2

@@ -1,52 +0,0 @@
-<h3 class="manual-chapter-title">Services</h5>
-<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
-      means that the offered workflow provides variable entry and exit points,
-      so that different starting points and goals can be flexibly addressed.
-      Each of these modules are implemented in a self-contained service, each of
-      which represents a step in the workflow. The services are coordinated in
-      such a way that they can be used consecutively. The order can either be
-      taken from the listing of the services in the left sidebar or from the
-      roadmap (accessible via the pink compass in the upper right corner). All
-      services are versioned, so the data generated with nopaque is always
-      reproducible.
-    </p>
-  </div>
-</div>
-
-<h4 class="manual-chapter-title">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
-  images into the resulting PDF file based on the file names. So naming the
-  images correctly is of great importance. It has proven to be a good practice
-  to name the files according to the following scheme:
-  page-01.png, page-02.jpg, page-03.tiff, etc. In general, 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>
-
-<h4>Handwritten Text Recognition (HTR)</h4>
-<p>Comming soon...</p>
-
-<h4>Natural Language Processing (NLP)</h4>
-<p>Comming soon...</p>
-
-<h4>Corpus Analysis</h4>
-<p>
-  With the corpus analysis service, it is possible to create a text corpus
-  and then explore it in an analysis session. 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.
-</p>

app/templates/main/user_manual.html.j2

@@ -1,43 +0,0 @@
-{% extends "base.html.j2" %}
-
-{% block page_content %}
-<div class="container">
-  <div class="row">
-    <div class="col s12">
-      <h1 id="title">{{ title }}</h1>
-    </div>
-
-    <div class="col s12 m10">
-      <div class="section scrollspy" id="introduction">
-        {% include "main/manual/_01_introduction.html.j2" %}
-      </div>
-      <div class="section scrollspy" id="registration-and-log-in">
-        {% include "main/manual/_02_registration_and_log_in.html.j2" %}
-      </div>
-      <div class="section scrollspy" id="dashboard">
-        {% include "main/manual/_03_dashboard.html.j2" %}
-      </div>
-      <div class="section scrollspy" id="services">
-        {% include "main/manual/_06_services.html.j2" %}
-      </div>
-      <div class="section scrollspy" id="a-closer-look-at-the-corpus-analysis">
-        {% include "main/manual/_07_a_closer_look_at_the_corpus_analysis.html.j2" %}
-      </div>
-      <div class="section scrollspy" id="cqp-query-language">
-        {% include "main/manual/_08_cqp_query_language.html.j2" %}
-      </div>
-    </div>
-
-    <div class="col m2 hide-on-small-only">
-      <ul class="section table-of-contents" style="position: fixed !important;">
-        <li><a href="#introduction">Introduction</a></li>
-        <li><a href="#registration-and-log-in">Registration and Log in</a></li>
-        <li><a href="#dashboard">Dashboard</a></li>
-        <li><a href="#services">Services</a></li>
-        <li><a href="#a-closer-look-at-the-corpus-analysis">A closer look at the Corpus Analysis</a></li>
-        <li><a href="#cqp-query-language">CQP Query Language</a></li>
-      </ul>
-    </div>
-  </div>
-</div>
-{% endblock page_content %}

app/templates/workshops/fgho_sommerschule_2023.html.j2

@@ -12,11 +12,11 @@
     </div>
 
     <div class="col s12" id="fgho-sommerschule-2023-vorbereitungen">
-      {% include "workshops/_fgho_sommerschule_2023/_vorbereitungen.html.j2" %}
+      {% include "workshops/_fgho_sommerschule_2023/vorbereitungen.html.j2" %}
     </div>
 
     <div class="col s12" id="fgho-sommerschule-2023-workshop-aufgaben">
-      {% include "workshops/_fgho_sommerschule_2023/_aufgaben.html.j2" %}
+      {% include "workshops/_fgho_sommerschule_2023/aufgaben.html.j2" %}
     </div>
   </div>
 </div>

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_*)

db.env.tpl

@@ -4,7 +4,6 @@
 # More information about the environment variables can be found here:        #
 # https://hub.docker.com/_/postgres                                          #
 ##############################################################################
-
 POSTGRES_DB=
 
 POSTGRES_USER=

migrations/versions/31dd42e5ea6f_.py

@@ -20,6 +20,7 @@ depends_on = None
 
 
 def upgrade():
+    # TODO: Add error handling for sqlalchemy.exc.ProgrammingError
     for user in User.query.all():
         spacy_nlp_pipeline_models_dir = os.path.join(user.path, 'spacy_nlp_pipeline_models')
         if os.path.exists(spacy_nlp_pipeline_models_dir):

migrations/versions/63b2cc26a01f_.py

@@ -17,6 +17,7 @@ depends_on = None
 
 
 def upgrade():
+    # TODO: Add error handling for sqlalchemy.exc.ProgrammingError
     for user in User.query.all():
         old_tesseract_ocr_pipeline_model_path = os.path.join(user.path, 'tesseract_ocr_models')
         new_tesseract_ocr_pipeline_model_path = os.path.join(user.path, 'tesseract_ocr_pipeline_models')