Automatisierung OPUS Siegen

2021-01-14 16:51:39 +01:00 · 2021-01-14 16:51:39 +01:00 · a71e86eba8
parent bd4f9c182a
commit a71e86eba8
21 changed files with 2188 additions and 2 deletions
--- a/.gitignore
+++ b/.gitignore
@ -0,0 +1,3 @@
+data
+openrefine
+.task
--- a/README.md
+++ b/README.md
@ -1,2 +1,123 @@
-# noah
-Harvesting von OAI-PMH-Schnittstellen und Transformation in METS/MODS für das Portal noah.nrw
+# Datenintegration für noah.nrw
+Harvesting von OAI-PMH-Schnittstellen und Transformation in METS/MODS für das Portal [noah.nrw](https://noah.nrw/)
+
+## Datenfluss
+
+![Datenflussdiagramm](/home/felix/git/noah/flowchart.svg)
+
+## Verwendete Tools
+
+* Harvesting (mit Cache): [metha](https://github.com/miku/metha/)
+* Transformation: [OpenRefine](https://github.com/OpenRefine/OpenRefine) und [openrefine-client](https://github.com/opencultureconsulting/openrefine-client)
+* Task Runner: [Task](https://github.com/go-task/task)
+
+## Systemvoraussetzungen
+
+* GNU/Linux (getestet mit Fedora 32)
+* JAVA 8+
+
+## Installation
+
+1. Git Repository klonen
+
+    ```sh
+    git clone https://github.com/opencultureconsulting/noah.git
+    cd noah
+    ```
+
+2. [OpenRefine 3.4.1](https://github.com/OpenRefine/OpenRefine/releases/tag/3.4.1) (benötigt JAVA 8+)
+
+    ```sh
+    # download OpenRefine
+    wget -O openrefine.tar.gz https://github.com/OpenRefine/OpenRefine/releases/download/3.4.1/openrefine-linux-3.4.1.tar.gz
+    # install OpenRefine in subdirectory openrefine
+    mkdir -p openrefine
+    tar -xzf openrefine.tar.gz -C openrefine --strip 1 && rm openrefine.tar.gz
+    # do not try to open OpenRefine in browser
+    sed -i '$ a JAVA_OPTIONS=-Drefine.headless=true' "openrefine/refine.ini"
+    # set autosave period from 5 minutes to 25 hours
+    sed -i 's/#REFINE_AUTOSAVE_PERIOD=60/REFINE_AUTOSAVE_PERIOD=1440/' "openrefine/refine.ini"
+    ```
+    
+3. [openrefine-client 0.3.10](https://github.com/opencultureconsulting/openrefine-client/releases/tag/v0.3.10)
+
+    ```sh
+    # install openrefine-client in subdirectory openrefine
+    mkdir -p openrefine
+    wget -O openrefine/openrefine-client https://github.com/opencultureconsulting/openrefine-client/releases/download/v0.3.10/openrefine-client_0-3-10_linux
+    chmod +x openrefine/openrefine-client
+    ```
+    
+4. [metha 0.2.20](https://github.com/miku/metha/releases/tag/v0.2.20)
+
+	a) RPM-basiert (Fedora, CentOS, SLES, etc.)
+
+    ```sh
+    # download and install rpm package
+    wget https://github.com/miku/metha/releases/download/v0.2.20/metha-0.2.20-0.x86_64.rpm
+    sudo dnf install ./metha-0.2.20-0.x86_64.rpm && rm metha-0.2.20-0.x86_64.rpm
+    ```
+
+	b) DEB-basiert (Debian, Ubuntu etc.)
+
+    ```sh
+    # download and install deb package
+    wget https://github.com/miku/metha/releases/download/v0.2.20/metha_0.2.20_amd64.deb
+    sudo apt install ./metha_0.2.20_amd64.deb && rm metha_0.2.20_amd64.deb
+    ```
+
+5. [Task 3.2.2](https://github.com/go-task/task/releases/tag/v3.2.2)
+
+	a) RPM-basiert (Fedora, CentOS, SLES, etc.)
+
+    ```sh
+    # download and install rpm package
+    wget https://github.com/go-task/task/releases/download/v3.2.2/task_linux_amd64.rpm
+    sudo dnf install ./task_linux_amd64.rpm && rm task_linux_amd64.rpm
+    ```
+
+	b) DEB-basiert (Debian, Ubuntu etc.)
+
+    ```sh
+    # download and install deb package
+    wget https://github.com/go-task/task/releases/download/v3.2.2/task_linux_amd64.deb
+    sudo apt install ./task_linux_amd64.deb && rm task_linux_amd64.deb
+    ```
+
+## Nutzung
+
+* Alle Datenquellen harvesten und transformieren (parallelisiert)
+
+  ```
+  task default
+  ```
+
+* Eine Datenquelle harvesten und transformieren
+
+  ```
+  task siegen:default
+  ```
+
+* Cache einer Datenquelle löschen
+
+  ```
+  task siegen:delete
+  ```
+
+* Verfügbare Tasks auflisten
+
+  ```
+  task --list
+  ```
+
+## Konfiguration
+
+* Umgebungsvariablen in [Taskfile.yml](Taskfile.yml)
+* Workflow für die Datenquellen in [tasks](tasks)
+  * Beispiel: [tasks/siegen.yml](tasks/siegen.yml)
+* Transformationsregeln in [rules](rules)
+  * Beispiel: [rules/siegen/hbz.json](rules/siegen/hbz.json)
+
+## OAI-PMH Data Provider
+
+Für die Bereitstellung der transformierten Daten wird der dateibasierte OAI-PMH Data Provider [oai_pmh](https://github.com/opencultureconsulting/oai_pmh) genutzt. Installations- und Nutzungshinweise sind dort zu finden.
--- a/Taskfile.yml
+++ b/Taskfile.yml
@ -0,0 +1,35 @@
+# https://taskfile.dev
+
+version: '3'
+
+#silent: true
+output: prefixed
+
+includes:
+  siegen: ./tasks/siegen.yml
+#  wuppertal: ./tasks/wuppertal.yml
+
+vars:
+  DATE: '{{ now | date "2006-01-02"}}'
+
+env:
+  OPENREFINE:
+    sh: readlink -e openrefine/refine
+  OPENREFINE_CLIENT:
+    sh: readlink -e openrefine/openrefine-client
+
+tasks:
+  default:
+    desc: alle Datenquellen harvesten und transformieren (parallel)
+    preconditions:
+      - sh: test -n "$(command -v metha-sync)"
+        msg: "requirement metha missing"
+      - sh: test -n "$(command -v java)"
+        msg: "requirement JAVA runtime environment (jre) missing"
+      - sh: test -x "$OPENREFINE"
+        msg: "requirement OpenRefine missing"
+      - sh: test -x "$OPENREFINE_CLIENT"
+        msg: "requirement openrefine-client missing"
+    deps:
+#      - task: wuppertal:default
+      - task: siegen:default
--- a/flowchart.mmd
+++ b/flowchart.mmd
@ -0,0 +1,19 @@
+graph LR
+wuppertal[elpub.bib.uni-wuppertal.de] --- metha_wuppertal
+click wuppertal "http://elpub.bib.uni-wuppertal.de/servlets/OAIDataProvider?verb=ListRecords&metadataPrefix=oai_dc" _blank
+siegen[dspace.ub.uni-siegen.de] --- metha_siegen
+click siegen "https://dspace.ub.uni-siegen.de/oai/request?verb=ListRecords&metadataPrefix=xMetaDissPlus" _blank
+subgraph Harvesting
+metha_wuppertal["fa:fa-cogs metha"]
+metha_siegen["fa:fa-cogs metha"]
+end
+subgraph Transformation
+metha_wuppertal  -->|Dublin Core| refine_wuppertal[fa:fa-cogs OpenRefine]
+metha_siegen -->|xMetaDissPlus| refine_siegen[fa:fa-cogs OpenRefine]
+end
+subgraph OAI-PMH Data Provider
+refine_wuppertal -->|METS/MODS| oai_wuppertal["noah.opencultureconsulting.com/ubw/"]
+click oai_wuppertal "https://noah.opencultureconsulting.com/ubw/?verb=ListRecords&metadataPrefix=mets" _blank
+refine_siegen -->|METS/MODS| oai_siegen["noah.opencultureconsulting.com/ubs/"]
+click oai_siegen "https://noah.opencultureconsulting.com/ubs/?verb=ListRecords&metadataPrefix=mets" _blank
+end
--- a/flowchart.svg
+++ b/flowchart.svg
--- a/rules/siegen/cc.json
+++ b/rules/siegen/cc.json
@ -0,0 +1,25 @@
+[
+  {
+    "op": "core/column-addition",
+    "engineConfig": {
+      "facets": [
+        {
+          "type": "text",
+          "name": "dc:rights",
+          "columnName": "dc:rights",
+          "query": "creativecommons.org",
+          "mode": "text",
+          "caseSensitive": false,
+          "invert": false
+        }
+      ],
+      "mode": "row-based"
+    },
+    "baseColumnName": "dc:rights",
+    "expression": "grel:value.replace('https://','').replace('http://','').replace('creativecommons.org/licenses/','CC ').replace('/',' ').trim().toUppercase()",
+    "onError": "set-to-blank",
+    "newColumnName": "cc",
+    "columnInsertIndex": 23,
+    "description": "Create column cc at index 23 based on column dc:rights using expression grel:value.replace('https://','').replace('http://','').replace('creativecommons.org/licenses/','CC ').replace('/',' ').trim().toUppercase()"
+  }
+]
--- a/rules/siegen/ddc-topic.json
+++ b/rules/siegen/ddc-topic.json
@ -0,0 +1,74 @@
+[
+  {
+    "op": "core/column-addition",
+    "engineConfig": {
+      "facets": [
+        {
+          "type": "list",
+          "name": "dc:subject/xsi:type",
+          "expression": "value",
+          "columnName": "dc:subject/xsi:type",
+          "invert": false,
+          "omitBlank": false,
+          "omitError": false,
+          "selection": [
+            {
+              "v": {
+                "v": "xMetaDiss:DDC-SG",
+                "l": "xMetaDiss:DDC-SG"
+              }
+            }
+          ],
+          "selectBlank": false,
+          "selectError": false
+        }
+      ],
+      "mode": "row-based"
+    },
+    "baseColumnName": "dc:subject",
+    "expression": "grel:value",
+    "onError": "set-to-blank",
+    "newColumnName": "ddc",
+    "columnInsertIndex": 2,
+    "description": "Create column ddc at index 2 based on column dc:subject using expression grel:value"
+  },
+  {
+    "op": "core/column-addition",
+    "engineConfig": {
+      "facets": [
+        {
+          "type": "list",
+          "name": "dc:subject/xsi:type",
+          "expression": "value",
+          "columnName": "dc:subject/xsi:type",
+          "invert": false,
+          "omitBlank": false,
+          "omitError": false,
+          "selection": [
+            {
+              "v": {
+                "v": "xMetaDiss:noScheme",
+                "l": "xMetaDiss:noScheme"
+              }
+            },
+            {
+              "v": {
+                "v": "xMetaDiss:SWD",
+                "l": "xMetaDiss:SWD"
+              }
+            }
+          ],
+          "selectBlank": false,
+          "selectError": false
+        }
+      ],
+      "mode": "row-based"
+    },
+    "baseColumnName": "dc:subject",
+    "expression": "grel:value",
+    "onError": "set-to-blank",
+    "newColumnName": "topic",
+    "columnInsertIndex": 2,
+    "description": "Create column topic at index 2 based on column dc:subject using expression grel:value"
+  }
+]
--- a/rules/siegen/dini.json
+++ b/rules/siegen/dini.json
@ -0,0 +1,35 @@
+[
+  {
+    "op": "core/column-addition",
+    "engineConfig": {
+      "facets": [
+        {
+          "type": "list",
+          "name": "dc:type/xsi:type",
+          "expression": "value",
+          "columnName": "dc:type/xsi:type",
+          "invert": false,
+          "omitBlank": false,
+          "omitError": false,
+          "selection": [
+            {
+              "v": {
+                "v": "dini:PublType",
+                "l": "dini:PublType"
+              }
+            }
+          ],
+          "selectBlank": false,
+          "selectError": false
+        }
+      ],
+      "mode": "row-based"
+    },
+    "baseColumnName": "dc:type",
+    "expression": "grel:value",
+    "onError": "set-to-blank",
+    "newColumnName": "dini",
+    "columnInsertIndex": 7,
+    "description": "Create column dini at index 7 based on column dc:type using expression grel:value"
+  }
+]
--- a/rules/siegen/direktlinks.json
+++ b/rules/siegen/direktlinks.json
@ -0,0 +1,127 @@
+[
+  {
+    "op": "core/column-addition-by-fetching-urls",
+    "engineConfig": {
+      "facets": [
+        {
+          "type": "list",
+          "name": "id",
+          "expression": "isBlank(value)",
+          "columnName": "id",
+          "invert": false,
+          "omitBlank": false,
+          "omitError": false,
+          "selection": [
+            {
+              "v": {
+                "v": false,
+                "l": "false"
+              }
+            }
+          ],
+          "selectBlank": false,
+          "selectError": false
+        },
+        {
+          "type": "list",
+          "name": "ddb:transfer",
+          "expression": "isBlank(value)",
+          "columnName": "ddb:transfer",
+          "invert": false,
+          "omitBlank": false,
+          "omitError": false,
+          "selection": [
+            {
+              "v": {
+                "v": true,
+                "l": "true"
+              }
+            }
+          ],
+          "selectBlank": false,
+          "selectError": false
+        }
+      ],
+      "mode": "row-based"
+    },
+    "baseColumnName": "id",
+    "urlExpression": "grel:'https://dspace.ub.uni-siegen.de/oai/request?verb=GetRecord&metadataPrefix=mets&identifier=' + value",
+    "onError": "set-to-blank",
+    "newColumnName": "mets",
+    "columnInsertIndex": 1,
+    "delay": 0,
+    "cacheResponses": true,
+    "httpHeadersJson": [
+      {
+        "name": "authorization",
+        "value": ""
+      },
+      {
+        "name": "user-agent",
+        "value": "OpenRefine 3.4.1 [437dc4d]"
+      },
+      {
+        "name": "accept",
+        "value": "*/*"
+      }
+    ],
+    "description": "Create column mets at index 1 by fetching URLs based on column id using expression grel:'https://dspace.ub.uni-siegen.de/oai/request?verb=GetRecord&metadataPrefix=mets&identifier=' + value"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [
+        {
+          "type": "list",
+          "name": "id",
+          "expression": "isBlank(value)",
+          "columnName": "id",
+          "invert": false,
+          "omitBlank": false,
+          "omitError": false,
+          "selection": [
+            {
+              "v": {
+                "v": false,
+                "l": "false"
+              }
+            }
+          ],
+          "selectBlank": false,
+          "selectError": false
+        },
+        {
+          "type": "list",
+          "name": "ddb:transfer",
+          "expression": "isBlank(value)",
+          "columnName": "ddb:transfer",
+          "invert": false,
+          "omitBlank": false,
+          "omitError": false,
+          "selection": [
+            {
+              "v": {
+                "v": true,
+                "l": "true"
+              }
+            }
+          ],
+          "selectBlank": false,
+          "selectError": false
+        }
+      ],
+      "mode": "row-based"
+    },
+    "columnName": "ddb:transfer",
+    "expression": "grel:forEach(cells['mets'].value.parseXml().select('FLocat'),v,v.xmlAttr('xlink:href')).join('␞')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column ddb:transfer using expression grel:forEach(cells['mets'].value.parseXml().select('FLocat'),v,v.xmlAttr('xlink:href')).join('␞')"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "mets",
+    "description": "Remove column mets"
+  }
+]
--- a/rules/siegen/doctype.json
+++ b/rules/siegen/doctype.json
@ -0,0 +1,68 @@
+[
+  {
+    "op": "core/column-addition",
+    "engineConfig": {
+      "facets": [
+        {
+          "type": "list",
+          "name": "dc:type/xsi:type",
+          "expression": "value",
+          "columnName": "dc:type/xsi:type",
+          "invert": false,
+          "omitBlank": false,
+          "omitError": false,
+          "selection": [
+            {
+              "v": {
+                "v": "dini:PublType",
+                "l": "dini:PublType"
+              }
+            }
+          ],
+          "selectBlank": false,
+          "selectError": false
+        }
+      ],
+      "mode": "row-based"
+    },
+    "baseColumnName": "dc:type",
+    "expression": "grel:with([ ['article','oaArticle'], ['bachelorThesis','oaBachelorThesis'], ['book','oaBook'], ['bookPart','oaBookPart'], ['conferenceObject','conferenceObject'], ['doctoralThesis','oaDoctoralThesis'], ['masterThesis','oaMasterThesis'], ['PeriodicalPart','journal issue'], ['StudyThesis','oaStudyThesis'], ['Other','oaBdOther'] ], x, forEach(x, v, if(value == v[0], v[1], null)).join(''))",
+    "onError": "set-to-blank",
+    "newColumnName": "doctype",
+    "columnInsertIndex": 7,
+    "description": "Create column doctype at index 7 based on column dc:type using expression grel:with([ ['article','oaArticle'], ['bachelorThesis','oaBachelorThesis'], ['book','oaBook'], ['bookPart','oaBookPart'], ['conferenceObject','conferenceObject'], ['doctoralThesis','oaDoctoralThesis'], ['masterThesis','oaMasterThesis'], ['StudyThesis','oaStudyThesis'], ['Other','oaBdOther'] ], x, forEach(x, v, if(value == v[0], v[1], null)).join(''))"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [
+        {
+          "type": "list",
+          "name": "thesis:level",
+          "expression": "value",
+          "columnName": "thesis:level",
+          "invert": false,
+          "omitBlank": false,
+          "omitError": false,
+          "selection": [
+            {
+              "v": {
+                "v": "thesis.habilitation",
+                "l": "thesis.habilitation"
+              }
+            }
+          ],
+          "selectBlank": false,
+          "selectError": false
+        }
+      ],
+      "mode": "row-based"
+    },
+    "columnName": "doctype",
+    "expression": "grel:'oaHabil'",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column doctype using expression grel:'oaHabil'"
+  }
+]
--- a/rules/siegen/doi.json
+++ b/rules/siegen/doi.json
@ -0,0 +1,84 @@
+[
+  {
+    "op": "core/column-addition-by-fetching-urls",
+    "engineConfig": {
+      "facets": [
+        {
+          "type": "list",
+          "name": "id",
+          "expression": "isBlank(value)",
+          "columnName": "id",
+          "invert": false,
+          "omitBlank": false,
+          "omitError": false,
+          "selection": [
+            {
+              "v": {
+                "v": false,
+                "l": "false"
+              }
+            }
+          ],
+          "selectBlank": false,
+          "selectError": false
+        }
+      ],
+      "mode": "row-based"
+    },
+    "baseColumnName": "id",
+    "urlExpression": "grel:'https://dspace.ub.uni-siegen.de/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=' + value",
+    "onError": "set-to-blank",
+    "newColumnName": "doi",
+    "columnInsertIndex": 1,
+    "delay": 0,
+    "cacheResponses": true,
+    "httpHeadersJson": [
+      {
+        "name": "authorization",
+        "value": ""
+      },
+      {
+        "name": "user-agent",
+        "value": "OpenRefine 3.4.1 [437dc4d]"
+      },
+      {
+        "name": "accept",
+        "value": "*/*"
+      }
+    ],
+    "description": "Create column doi at index 1 by fetching URLs based on column id using expression grel:'https://dspace.ub.uni-siegen.de/oai/request?verb=GetRecord&metadataPrefix=oai_dc&identifier=' + value"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [
+        {
+          "type": "list",
+          "name": "id",
+          "expression": "isBlank(value)",
+          "columnName": "id",
+          "invert": false,
+          "omitBlank": false,
+          "omitError": false,
+          "selection": [
+            {
+              "v": {
+                "v": false,
+                "l": "false"
+              }
+            }
+          ],
+          "selectBlank": false,
+          "selectError": false
+        }
+      ],
+      "mode": "row-based"
+    },
+    "columnName": "doi",
+    "expression": "grel:forNonBlank(filter(value.parseXml().select('dc|identifier'),v,v.xmlAttr('xsi:type') == 'doi:doi')[0].ownText(),v,v,null)",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dc using expression grel:forNonBlank(filter(value.parseXml().select('dc|identifier'),v,v.xmlAttr('xsi:type') == 'doi:doi')[0].ownText(),v,v,null)"
+  }
+]
--- a/rules/siegen/hbz.json
+++ b/rules/siegen/hbz.json
@ -0,0 +1,84 @@
+[
+  {
+    "op": "core/column-addition-by-fetching-urls",
+    "engineConfig": {
+      "facets": [
+        {
+          "type": "list",
+          "name": "dc:identifier",
+          "expression": "isBlank(value)",
+          "columnName": "dc:identifier",
+          "invert": false,
+          "omitBlank": false,
+          "omitError": false,
+          "selection": [
+            {
+              "v": {
+                "v": false,
+                "l": "false"
+              }
+            }
+          ],
+          "selectBlank": false,
+          "selectError": false
+        }
+      ],
+      "mode": "row-based"
+    },
+    "baseColumnName": "dc:identifier",
+    "urlExpression": "grel:'https://lobid.org/resources/search?q=' + forEach(value.split('␞'),v,'urn:\"'+v+'\"').join('+OR+')",
+    "onError": "set-to-blank",
+    "newColumnName": "hbz",
+    "columnInsertIndex": 11,
+    "delay": 0,
+    "cacheResponses": true,
+    "httpHeadersJson": [
+      {
+        "name": "authorization",
+        "value": ""
+      },
+      {
+        "name": "user-agent",
+        "value": "OpenRefine 3.4.1 [437dc4d]"
+      },
+      {
+        "name": "accept",
+        "value": "*/*"
+      }
+    ],
+    "description": "Create column hbz at index 11 by fetching URLs based on column dc:identifier using expression grel:'https://lobid.org/resources/search?q=' + forEach(value.split('␞'),v,'urn:\"'+v+'\"').join('+OR+')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [
+        {
+          "type": "list",
+          "name": "dc:identifier",
+          "expression": "isBlank(value)",
+          "columnName": "dc:identifier",
+          "invert": false,
+          "omitBlank": false,
+          "omitError": false,
+          "selection": [
+            {
+              "v": {
+                "v": false,
+                "l": "false"
+              }
+            }
+          ],
+          "selectBlank": false,
+          "selectError": false
+        }
+      ],
+      "mode": "row-based"
+    },
+    "columnName": "hbz",
+    "expression": "grel:forNonBlank(value.parseJson().member[0].hbzId,v,v,null)",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column lobid using expression grel:forNonBlank(value.parseJson().member[0].hbzId,v,v,null)"
+  }
+]
--- a/rules/siegen/join.json
+++ b/rules/siegen/join.json
@ -0,0 +1,693 @@
+[
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "doi",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column doi using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "id",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column id using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dc:subject",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dc:subject using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "topic",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column topic using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dc:subject/xsi:type",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dc:subject/xsi:type using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "ddc",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column ddc using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dc:identifier",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dc:identifier using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dc:creator/pc:foreName",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dc:creator/pc:foreName using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dc:creator/pc:surName",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dc:creator/pc:surName using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dc:type/xsi:type",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dc:type/xsi:type using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dc:type",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dc:type using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "nonsort",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column nonsort using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dc:title",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dc:title using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dcterms:abstract/lang",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dcterms:abstract/lang using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dcterms:abstract",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dcterms:abstract using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "hbz",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column hbz using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dc:publisher/cc:address",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dc:publisher/cc:address using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "ddb:fileSize",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column ddb:fileSize using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "ddb:fileName",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column ddb:fileName using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dc:title/ddb:type",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dc:title/ddb:type using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dc:title/lang",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dc:title/lang using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dc:rights",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dc:rights using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dc:language",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dc:language using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dc:publisher/cc:place",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dc:publisher/cc:place using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dc:publisher/cc:name",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dc:publisher/cc:name using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dc:publisher/cc:GKD-Nr",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dc:publisher/cc:GKD-Nr using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "ddb:checksum",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column ddb:checksum using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dcterms:issued",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dcterms:issued using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "ddb:identifier",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column ddb:identifier using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "ddb:fileNumber",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column ddb:fileNumber using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "cc",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column cc using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dcterms:dateAccepted",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dcterms:dateAccepted using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "thesis:grantor",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column thesis:grantor using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "thesis:level",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column thesis:level using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "mime",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column mime using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "ddb:transfer",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column ddb:transfer using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dc:contributor/thesis:role",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dc:contributor/thesis:role using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dc:source/xsi:type",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dc:source/xsi:type using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dc:source",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dc:source using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dcterms:isPartOf",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dcterms:isPartOf using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dcterms:isPartOf/xsi:type",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dcterms:isPartOf/xsi:type using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dcterms:hasVersion",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dcterms:hasVersion using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dcterms:alternative/lang",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dcterms:alternative/lang using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dcterms:alternative",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dcterms:alternative using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dc:contributor/pc:foreName",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dc:contributor/pc:foreName using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dc:contributor/pc:surName",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dc:contributor/pc:surName using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "datestamp",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column datestamp using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "setSpec",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column setSpec using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "dini",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dini using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "doctype",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column doctype using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "linkcheck",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column linkcheck using expression grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.join('␞'),'')"
+  },
+  {
+    "op": "core/row-removal",
+    "engineConfig": {
+      "facets": [
+        {
+          "type": "list",
+          "name": "Blank Rows",
+          "expression": "(filter(row.columnNames,cn,isNonBlank(cells[cn].value)).length()==0).toString()",
+          "columnName": "",
+          "invert": false,
+          "omitBlank": false,
+          "omitError": false,
+          "selection": [
+            {
+              "v": {
+                "v": "true",
+                "l": "true"
+              }
+            }
+          ],
+          "selectBlank": false,
+          "selectError": false
+        }
+      ],
+      "mode": "row-based"
+    },
+    "description": "Remove rows"
+  }
+]
--- a/rules/siegen/linkcheck.json
+++ b/rules/siegen/linkcheck.json
@ -0,0 +1,35 @@
+[
+  {
+    "op": "core/column-addition",
+    "engineConfig": {
+      "facets": [
+        {
+          "type": "list",
+          "name": "ddb:transfer",
+          "expression": "isBlank(value)",
+          "columnName": "ddb:transfer",
+          "invert": false,
+          "omitBlank": false,
+          "omitError": false,
+          "selection": [
+            {
+              "v": {
+                "v": false,
+                "l": "false"
+              }
+            }
+          ],
+          "selectBlank": false,
+          "selectError": false
+        }
+      ],
+      "mode": "row-based"
+    },
+    "baseColumnName": "ddb:transfer",
+    "expression": "jython:import httplib\nimport urlparse\nstatus = []\nfor x in value.split(u'\\u241e'):\n    url = urlparse.urlparse(x)\n    conn = httplib.HTTPConnection(url[1])\n    conn.request(\"HEAD\", url[2])\n    res = conn.getresponse()\n    status.append(str(res.status))\nreturn ','.join(status)",
+    "onError": "set-to-blank",
+    "newColumnName": "linkcheck",
+    "columnInsertIndex": 34,
+    "description": "Create column linkcheck at index 34 based on column ddb:transfer using expression jython:import httplib\nimport urlparse\nstatus = []\nfor x in value.split(u'\\u241e'):\n    url = urlparse.urlparse(x)\n    conn = httplib.HTTPConnection(url[1])\n    conn.request(\"HEAD\", url[2])\n    res = conn.getresponse()\n    status.append(str(res.status))\nreturn ','.join(status)"
+  }
+]
--- a/rules/siegen/mime.json
+++ b/rules/siegen/mime.json
@ -0,0 +1,35 @@
+[
+  {
+    "op": "core/column-addition",
+    "engineConfig": {
+      "facets": [
+        {
+          "type": "list",
+          "name": "ddb:transfer",
+          "expression": "isBlank(value)",
+          "columnName": "ddb:transfer",
+          "invert": false,
+          "omitBlank": false,
+          "omitError": false,
+          "selection": [
+            {
+              "v": {
+                "v": false,
+                "l": "false"
+              }
+            }
+          ],
+          "selectBlank": false,
+          "selectError": false
+        }
+      ],
+      "mode": "row-based"
+    },
+    "baseColumnName": "ddb:transfer",
+    "expression": "grel:with([ ['pdf','application/pdf'], ['exe','application/x-msdownload'], ['zip','application/zip'] ], x, forEach(value.split('␞'), v, forEach(x, z, if(v.endsWith(z[0]), z[1], null)).join('')).join('␞'))",
+    "onError": "set-to-blank",
+    "newColumnName": "mime",
+    "columnInsertIndex": 29,
+    "description": "Create column mime at index 29 based on column ddb:transfer using expression grel:with([ ['pdf','application/pdf'], ['exe','application/x-msdownload'], ['zip','application/zip'] ], x, forEach(value.split('␞'), v, forEach(x, z, if(v.endsWith(z[0]), z[1], null)).join('')).join('␞'))"
+  }
+]
--- a/rules/siegen/nonsort.json
+++ b/rules/siegen/nonsort.json
@ -0,0 +1,87 @@
+[
+  {
+    "op": "core/column-addition",
+    "engineConfig": {
+      "facets": [
+        {
+          "type": "list",
+          "name": "id",
+          "expression": "isBlank(value)",
+          "columnName": "id",
+          "invert": false,
+          "omitBlank": false,
+          "omitError": false,
+          "selection": [
+            {
+              "v": {
+                "v": false,
+                "l": "false"
+              }
+            }
+          ],
+          "selectBlank": false,
+          "selectError": false
+        }
+      ],
+      "mode": "row-based"
+    },
+    "baseColumnName": "dc:title",
+    "expression": "grel:with(['a', 'das', 'dem', 'den', 'der', 'des', 'die', 'ein', 'eine', 'einem', 'einen', 'einer', 'eines', 'the'],x,if(inArray(x,value.split(' ')[0].toLowercase()),value.split(' ')[0] + ' ',''))",
+    "onError": "set-to-blank",
+    "newColumnName": "nonsort",
+    "columnInsertIndex": 15,
+    "description": "Create column nonsort at index 15 based on column dc:title using expression grel:with(['a', 'das', 'dem', 'den', 'der', 'des', 'die', 'ein', 'eine', 'einem', 'einen', 'einer', 'eines', 'the'],x,if(inArray(x,value.split(' ')[0].toLowercase()),value.split(' ')[0] + ' ',''))"
+  },
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [
+        {
+          "type": "list",
+          "name": "id",
+          "expression": "isBlank(value)",
+          "columnName": "id",
+          "invert": false,
+          "omitBlank": false,
+          "omitError": false,
+          "selection": [
+            {
+              "v": {
+                "v": false,
+                "l": "false"
+              }
+            }
+          ],
+          "selectBlank": false,
+          "selectError": false
+        },
+        {
+          "type": "list",
+          "name": "nonsort",
+          "expression": "isBlank(value)",
+          "columnName": "nonsort",
+          "invert": false,
+          "omitBlank": false,
+          "omitError": false,
+          "selection": [
+            {
+              "v": {
+                "v": false,
+                "l": "false"
+              }
+            }
+          ],
+          "selectBlank": false,
+          "selectError": false
+        }
+      ],
+      "mode": "row-based"
+    },
+    "columnName": "dc:title",
+    "expression": "grel:value.split(' ').slice(1).join(' ')",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10,
+    "description": "Text transform on cells in column dc:title using expression grel:value.split(' ').slice(1).join(' ')"
+  }
+]
--- a/rules/siegen/nur-mit-pdf.json
+++ b/rules/siegen/nur-mit-pdf.json
@ -0,0 +1,30 @@
+[
+  {
+    "op": "core/row-removal",
+    "engineConfig": {
+      "facets": [
+        {
+          "type": "list",
+          "name": "ddb:transfer",
+          "expression": "grel:row.record.cells['ddb:transfer'].value.join('').contains('.pdf')",
+          "columnName": "ddb:transfer",
+          "invert": false,
+          "omitBlank": false,
+          "omitError": false,
+          "selection": [
+            {
+              "v": {
+                "v": false,
+                "l": "false"
+              }
+            }
+          ],
+          "selectBlank": false,
+          "selectError": false
+        }
+      ],
+      "mode": "record-based"
+    },
+    "description": "Remove rows"
+  }