Feature/#7 prologue

closes #7 (closed) #6 (closed) #4 (closed)

.gitlab-ci.yml

 stages:
   - load
+  - preprocess
+  - process
+  - test
   - deploy
 
+before_script:
+  - source functions.sh
+
 load:
-  image: docker.gitlab.gwdg.de/fontane-notizbuecher/build:latest
+  image: docker.gitlab.gwdg.de/mgoebel/swiss_knife/fedora:latest
   stage: load
   services:
     - name: existdb/existdb:release
       alias: exist
+  cache:
+    paths:
+      - data/*.xml
   script:
-    - ./load.sh -e exist:8080 -f load.xq
+    - if [[ ! -d data/ ]]; then ./load.sh -e exist:8080 -f load.xq; fi
   artifacts:
     paths:
       - load.txt
       - list.txt
       - data/
 
-# when a git flow release is made, a tag will be pushed starting this job. it
-# will keep the resulting artifact from job number one and it will set up a
-# Gitlab release at the repo. therefore the merge message starting at the release
-# branch should be written in markdown.
-release:
-  stage: deploy
-  only:
-    - tags
+replacements:
+  image: docker.gitlab.gwdg.de/mgoebel/swiss_knife/fedora:latest
+  stage: preprocess
+  script:
+    - cd data
+# prologue
+    - sed --in-place --expression '1i<?xml version="1.0" encoding="UTF-8"?>' *.xml
+    - sed --in-place --expression '2i<?xml-stylesheet type="text/css" href="../css/tei.css"?>' *.xml
+# fix TEI.2
+    - sed --in-place --expression 's*TEI.2*TEI*g' *.xml
+# namespace (when missing)
+    - sed --in-place --expression 's*<TEI*<TEI xmlns="http://www.tei-c.org/ns/1.0"*g' $(grep --files-without-match "xmlns" *.xml)
+# misspelled elemets
+    - sed --in-place --expression 's*SourceDesc*sourceDesc*g' *.xml
+    - cd ..
+  artifacts:
+    paths:
+      - data/
+
+validation:
+  image: docker.gitlab.gwdg.de/mgoebel/swiss_knife/fedora:latest
+  stage: test
   script:
-    # get number of first job in pipeline (assuming that this will create the needed artifact)
-    # it is also possible to query for a job name by altering the jq filter
-    - 'curl --output jobs.json --header "PRIVATE-TOKEN: $GITLAB_TOKEN" "$CI_API_V4_URL/projects/$CI_PROJECT_ID/pipelines/$CI_PIPELINE_ID/jobs"'
-    - CI_JOB_TARGET=$(jq ".[0].id" < jobs.json)
-    - echo $CI_JOB_TARGET
-    # keep artifact (release will link there)
-    - 'curl --request POST --header "PRIVATE-TOKEN: $GITLAB_TOKEN" "$CI_API_V4_URL/projects/$CI_PROJECT_ID/jobs/$CI_JOB_TARGET/artifacts/keep"'
-    # create release data
-    # parse commit message (markdown, lines starting with “\”)
-    - MARKDOWN=$(echo "$CI_COMMIT_MESSAGE" | sed 's=^\\==g')
-    # prepare the json file
-    - 'jq
-      ".name = \"$CI_PROJECT_PATH $CI_COMMIT_TAG\" |
-      .tag_name = \"$CI_COMMIT_TAG\" |
-      .description = \"$MARKDOWN\" |
-      .assets.links[0].name = \"package\" |
-      .assets.links[0].url = \"https://gitlab.gwdg.de/$CI_PROJECT_PATH/-/jobs/$CI_JOB_TARGET/artifacts/download\"
-      " < .gitlab/gitlab-release.json.tmpl > gitlab-release.json'
-    - 'curl --header "Content-Type: application/json" --header "PRIVATE-TOKEN: $GITLAB_TOKEN" --data @gitlab-release.json --request POST $CI_API_V4_URL/projects/$CI_PROJECT_ID/releases'
+    - curl https://repo1.maven.org/maven2/com/thaiopensource/jing/20091111/jing-20091111.jar --output jing.jar
+    - curl https://tei-c.org/release/xml/tei/custom/schema/relaxng/tei_all.rng --output tei_all.rng
+    - java -jar jing.jar tei_all.rng tei/*.xml > validation-report.log || true
+    - grep "error" validation-report.log --count
   artifacts:
     paths:
-      - gitlab-release.json
\ No newline at end of file
+      - validation-report.log
+    when: always