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"
+  }
+]
--- a/rules/siegen/template.txt
+++ b/rules/siegen/template.txt
@ -0,0 +1,75 @@
+<mets:mets xmlns:mets="http://www.loc.gov/METS/" xmlns:mods="http://www.loc.gov/mods/v3"
+    xmlns:xlink="http://www.w3.org/1999/xlink">
+    <mets:dmdSec ID="DMD_siegen_opus_{{cells['id'].value.split('/').reverse()[0].escape('xml')}}">
+        <mets:mdWrap MIMETYPE="text/xml" MDTYPE="MODS">
+            <mets:xmlData>
+                <mods xmlns="http://www.loc.gov/mods/v3" version="3.7"
+                    xmlns:vl="http://visuallibrary.net/vl">{{forEachIndex(cells['dc:title'].value.split('␞'), i, v, '
+                    <titleInfo' + forNonBlank(cells['dc:title/lang'].value.split('␞')[i], v, ' lang="' + v.escape('xml') + '"', '') + if(and(i != 0, cells['dc:title/ddb:type'].value == 'translated'), ' type="translated"', '') + '>' + forNonBlank(cells['nonsort'].value, z,'
+                        <nonSort>' + z.escape('xml') + '</nonSort>', '') + '
+                        <title>'+v.split('␞')[0].escape('xml')+'</title>'+forNonBlank(cells['dcterms:alternative/lang'].value, v, '
+                        <subTitle lang="' + v.escape('xml') + '"' + '>' + cells['dcterms:alternative'].value.escape('xml') + '</subTitle>', '')+'
+                    </titleInfo>').join('')}}{{forNonBlank(cells['dc:creator/pc:surName'].value,x,with(cells['dc:creator/pc:foreName'].value,y,forEachIndex(x.split('␞'),i,v,'
+                    <name type="personal">
+                        <displayForm>'+ x.split('␞')[i].escape('xml') + ', ' + y.split('␞')[i].escape('xml') +'</displayForm>
+                        <namePart type="family">' + v.escape('xml') + '</namePart>
+                        <namePart type="given">' + y.split('␞')[i].escape('xml') + '</namePart>
+                        <role>
+                            <roleTerm type="code" authority="marcrelator">aut</roleTerm>
+                        </role>
+                    </name>')).join(''),'')}}{{forNonBlank(cells['dc:contributor/pc:surName'].value,x,with(cells['dc:contributor/pc:foreName'].value,y,forEachIndex(x.split('␞'),i,v,'
+                    <name type="personal">
+                        <displayForm>'+ x.split('␞')[i].escape('xml') + ', ' + y.split('␞')[i].escape('xml') +'</displayForm>
+                        <namePart type="family">' + v.escape('xml') + '</namePart>
+                        <namePart type="given">' + y.split('␞')[i].escape('xml') + '</namePart>' + forNonBlank(cells['dc:contributor/thesis:role'].value, v, '
+                        <role>
+                            <roleTerm type="code" authority="marcrelator">' + v.escape('xml').replace('referee', 'ths').replace('editor', 'edt') + '</roleTerm>
+                        </role>', '') + '
+                    </name>')).join(''),'')}}
+                    <typeOfResource>text</typeOfResource>{{forNonBlank(cells['dini'].value, v, '
+                    <genre authority="dini">' + v.escape('xml') + '</genre>', '')}}{{forNonBlank(cells['dcterms:issued'].value,v,'
+                    <originInfo>
+                        <dateIssued encoding="w3cdtf" keyDate="yes">' + v.escape('xml') + '</dateIssued>
+                    </originInfo>','')}}{{forNonBlank(cells['dc:language'].value,v,'
+                    <language>
+                        <languageTerm type="code" authority="iso639-2b">' + v.split('␞')[0].escape('xml') + '</languageTerm>
+                    </language>','')}}{{forNonBlank(cells['dcterms:abstract'].value, x, forEachIndex(x.split('␞'), i, v, '
+                    <abstract type="content"' + forNonBlank(cells['dcterms:abstract/lang'].value.split('␞')[i], z, ' lang="' + z.escape('xml') + '"','') + '>' + v.escape('xml') + '</abstract>').join(''),'')}}{{forNonBlank(cells['topic'].value,x,'
+                    <subject>' + forEach(x.split('␞'),v,'
+                        <topic>' + v.escape('xml') + '</topic>').join('') + '
+                    </subject>','')}}{{forNonBlank(cells['ddc'].value,x,forEach(x.split('␞'),v,'
+                    <classification authority="ddc">' + v.escape('xml') + '</classification>').join(''),'')}}{{forNonBlank(cells['thesis:grantor'].value,x,forEach(x.split('␞'),v,'
+                    <classification authority="ioo" displayLabel="' + v.escape('xml') + '"></classification>').join(''),'')}}{{forNonBlank(cells['dc:identifier'].value,v,'
+                    <identifier type="urn">' + v.escape('xml') + '</identifier>','')}}{{forNonBlank(cells['doi'].value,v,'
+                    <identifier type="doi">' + v.escape('xml') + '</identifier>','')}}{{forNonBlank(cells['hbz'].value,v,'
+                    <identifier type="sys">' + v.escape('xml') + '</identifier>','')}}{{forNonBlank(cells['cc'].value,v,'
+                    <accessCondition type="use and reproduction">' + v.escape('xml') + '</accessCondition>','')}}
+                    <recordInfo>
+                        <recordIdentifier>siegen_opus_{{cells['id'].value.split('/').reverse()[0].escape('xml')}}</recordIdentifier>
+                    </recordInfo>{{forNonBlank(cells['doctype'].value, v,'
+                    <extension>
+                        <vl:doctype>' + v.escape('xml') + '</vl:doctype>' + forNonBlank(cells['dcterms:dateAccepted'].value, x, '
+                        <vl:defenseDate>' + x.escape('xml') + '</vl:defenseDate>', '') + '
+                    </extension>', '')}}
+                </mods>
+            </mets:xmlData>
+        </mets:mdWrap>
+    </mets:dmdSec>
+    <mets:fileSec>{{forEachIndex(cells['ddb:transfer'].value.split('␞'), i, v, '
+        <mets:fileGrp USE="' + if(i == 0, 'pdf upload', 'generic file') + '">
+            <mets:file MIMETYPE="' + cells['mime'].value.split('␞')[i] + '" ID="FILE' + i + '_siegen_opus_' + cells['id'].value.split('/').reverse()[0].escape('xml') + '">
+                <mets:FLocat xlink:href="' + v.escape('xml') + '" LOCTYPE="URL"/>
+            </mets:file>
+        </mets:fileGrp>')}}
+    </mets:fileSec>
+    <mets:structMap TYPE="LOGICAL">
+        <mets:div TYPE="document" ID="siegen_opus_{{cells['id'].value.split('/').reverse()[0].escape('xml')}}"
+            DMDID="DMD_siegen_opus_{{cells['id'].value.split('/').reverse()[0].escape('xml')}}">
+            <mets:fptr FILEID="FILE0_siegen_opus_{{cells['id'].value.split('/').reverse()[0].escape('xml')}}"/>{{forEachIndex(cells['ddb:transfer'].value.split('␞').slice(1), i, v, '
+            <mets:div TYPE="part" ID="PART' + (i+1) + '_siegen_opus_' + cells['id'].value.split('/').reverse()[0].escape('xml') + '"
+                LABEL="' + cells['ddb:fileName'].value.split('␞')[i+1] + '">
+                <mets:fptr FILEID="FILE' + (i+1) + '_siegen_opus_' + cells['id'].value.split('/').reverse()[0].escape('xml') + '"/>
+            </mets:div>').join('')}}
+        </mets:div>
+    </mets:structMap>
+</mets:mets>
--- a/rules/siegen/urn.json
+++ b/rules/siegen/urn.json
@ -0,0 +1,15 @@
+[
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "record-based"
+    },
+    "columnName": "dc:identifier",
+    "expression": "grel:if(isNonBlank(cells['id'].value),row.record.cells[columnName].value.uniques().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.uniques().join('␞'),'')"
+  }
+]
--- a/rules/siegen/vorverarbeitung.json
+++ b/rules/siegen/vorverarbeitung.json
@ -0,0 +1,409 @@
+[
+  {
+    "op": "core/column-move",
+    "columnName": "Record - header - identifier",
+    "index": 0,
+    "description": "Move column Record - header - identifier to position 0"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - xsi:schemaLocation",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - xsi:schemaLocation"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:creator - xsi:type",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - dc:creator - xsi:type"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:creator - pc:person - pc:name - type",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - dc:creator - pc:person - pc:name - type"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:identifier - xsi:type",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - dc:identifier - xsi:type"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - dcterms:abstract - xsi:type",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - dcterms:abstract - xsi:type"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:title - xsi:type",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - dc:title - xsi:type"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:publisher - type",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - dc:publisher - type"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:publisher - xsi:type",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - dc:publisher - xsi:type"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:publisher - countryCode",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - dc:publisher - countryCode"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:publisher - cc:address - cc:Scheme",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - dc:publisher - cc:address - cc:Scheme"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:language - xsi:type",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - dc:language - xsi:type"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:rights - xsi:type",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - dc:rights - xsi:type"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - ddb:rights - ddb:kind",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - ddb:rights - ddb:kind"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - ddb:server",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - ddb:server"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - ddb:contact - ddb:contactID",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - ddb:contact - ddb:contactID"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - dini:version_driver",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - dini:version_driver"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - ddb:identifier - ddb:type",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - ddb:identifier - ddb:type"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - dcterms:issued - xsi:type",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - dcterms:issued - xsi:type"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - ddb:checksum - ddb:type",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - ddb:checksum - ddb:type"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - ddb:transfer - ddb:type",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - ddb:transfer - ddb:type"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - thesis:degree - thesis:grantor - type",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - thesis:degree - thesis:grantor - type"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - thesis:degree - thesis:grantor - xsi:type",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - thesis:degree - thesis:grantor - xsi:type"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - thesis:degree - thesis:grantor - countryCode",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - thesis:degree - thesis:grantor - countryCode"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - thesis:degree - thesis:grantor - cc:universityOrInstitution - cc:name",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - thesis:degree - thesis:grantor - cc:universityOrInstitution - cc:name"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - thesis:degree - thesis:grantor - cc:universityOrInstitution - cc:place",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - thesis:degree - thesis:grantor - cc:universityOrInstitution - cc:place"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - thesis:degree - thesis:grantor - cc:universityOrInstitution - cc:department - cc:place",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - thesis:degree - thesis:grantor - cc:universityOrInstitution - cc:department - cc:place"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - dcterms:dateAccepted - xsi:type",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - dcterms:dateAccepted - xsi:type"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:contributor - xsi:type",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - dc:contributor - xsi:type"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:contributor - pc:person - pc:name - type",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - dc:contributor - pc:person - pc:name - type"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - dcterms:alternative - xsi:type",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - dcterms:alternative - xsi:type"
+  },
+  {
+    "op": "core/column-removal",
+    "columnName": "Record - metadata - xMetaDiss:xMetaDiss - dcterms:hasVersion - xsi:type",
+    "description": "Remove column Record - metadata - xMetaDiss:xMetaDiss - dcterms:hasVersion - xsi:type"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - header - identifier",
+    "newColumnName": "id",
+    "description": "Rename column Record - header - identifier to id"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:subject",
+    "newColumnName": "dc:subject",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - dc:subject to dc:subject"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:subject - xsi:type",
+    "newColumnName": "dc:subject/xsi:type",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - dc:subject - xsi:type to dc:subject/xsi:type"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:type",
+    "newColumnName": "dc:type",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - dc:type to dc:type"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:type - xsi:type",
+    "newColumnName": "dc:type/xsi:type",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - dc:type - xsi:type to dc:type/xsi:type"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:creator - pc:person - pc:name - pc:surName",
+    "newColumnName": "dc:creator/pc:surName",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - dc:creator - pc:person - pc:name - pc:surName to dc:creator/pc:surName"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:creator - pc:person - pc:name - pc:foreName",
+    "newColumnName": "dc:creator/pc:foreName",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - dc:creator - pc:person - pc:name - pc:foreName to dc:creator/pc:foreName"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:identifier",
+    "newColumnName": "dc:identifier",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - dc:identifier to dc:identifier"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - dcterms:abstract",
+    "newColumnName": "dcterms:abstract",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - dcterms:abstract to dcterms:abstract"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - dcterms:abstract - lang",
+    "newColumnName": "dcterms:abstract/lang",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - dcterms:abstract - lang to dcterms:abstract/lang"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:title",
+    "newColumnName": "dc:title",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - dc:title to dc:title"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:title - lang",
+    "newColumnName": "dc:title/lang",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - dc:title - lang to dc:title/lang"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:title - ddb:type",
+    "newColumnName": "dc:title/ddb:type",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - dc:title - ddb:type to dc:title/ddb:type"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - ddb:fileProperties - ddb:fileName",
+    "newColumnName": "ddb:fileName",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - ddb:fileProperties - ddb:fileName to ddb:fileName"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - ddb:fileProperties - ddb:fileSize",
+    "newColumnName": "ddb:fileSize",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - ddb:fileProperties - ddb:fileSize to ddb:fileSize"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:publisher - cc:address",
+    "newColumnName": "dc:publisher/cc:address",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - dc:publisher - cc:address to dc:publisher/cc:address"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:publisher - cc:universityOrInstitution - cc:GKD-Nr",
+    "newColumnName": "dc:publisher/cc:GKD-Nr",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - dc:publisher - cc:universityOrInstitution - cc:GKD-Nr to dc:publisher/cc:GKD-Nr"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:publisher - cc:universityOrInstitution - cc:name",
+    "newColumnName": "dc:publisher/cc:name",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - dc:publisher - cc:universityOrInstitution - cc:name to dc:publisher/cc:name"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:publisher - cc:universityOrInstitution - cc:place",
+    "newColumnName": "dc:publisher/cc:place",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - dc:publisher - cc:universityOrInstitution - cc:place to dc:publisher/cc:place"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:language",
+    "newColumnName": "dc:language",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - dc:language to dc:language"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:rights",
+    "newColumnName": "dc:rights",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - dc:rights to dc:rights"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - ddb:fileNumber",
+    "newColumnName": "ddb:fileNumber",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - ddb:fileNumber to ddb:fileNumber"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - ddb:identifier",
+    "newColumnName": "ddb:identifier",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - ddb:identifier to ddb:identifier"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - dcterms:issued",
+    "newColumnName": "dcterms:issued",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - dcterms:issued to dcterms:issued"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - ddb:checksum",
+    "newColumnName": "ddb:checksum",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - ddb:checksum to ddb:checksum"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - ddb:transfer",
+    "newColumnName": "ddb:transfer",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - ddb:transfer to ddb:transfer"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - thesis:degree - thesis:level",
+    "newColumnName": "thesis:level",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - thesis:degree - thesis:level to thesis:level"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - thesis:degree - thesis:grantor - cc:universityOrInstitution - cc:department - cc:name",
+    "newColumnName": "thesis:grantor",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - thesis:degree - thesis:grantor - cc:universityOrInstitution - cc:department - cc:name to thesis:grantor"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - dcterms:dateAccepted",
+    "newColumnName": "dcterms:dateAccepted",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - dcterms:dateAccepted to dcterms:dateAccepted"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - dcterms:isPartOf - xsi:type",
+    "newColumnName": "dcterms:isPartOf/xsi:type",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - dcterms:isPartOf - xsi:type to dcterms:isPartOf/xsi:type"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - dcterms:isPartOf",
+    "newColumnName": "dcterms:isPartOf",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - dcterms:isPartOf to dcterms:isPartOf"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:source",
+    "newColumnName": "dc:source",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - dc:source to dc:source"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:source - xsi:type",
+    "newColumnName": "dc:source/xsi:type",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - dc:source - xsi:type to dc:source/xsi:type"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:contributor - thesis:role",
+    "newColumnName": "dc:contributor/thesis:role",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - dc:contributor - thesis:role to dc:contributor/thesis:role"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:contributor - pc:person - pc:name - pc:surName",
+    "newColumnName": "dc:contributor/pc:surName",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - dc:contributor - pc:person - pc:name - pc:surName to dc:contributor/pc:surName"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - dc:contributor - pc:person - pc:name - pc:foreName",
+    "newColumnName": "dc:contributor/pc:foreName",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - dc:contributor - pc:person - pc:name - pc:foreName to dc:contributor/pc:foreName"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - dcterms:alternative",
+    "newColumnName": "dcterms:alternative",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - dcterms:alternative to dcterms:alternative"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - dcterms:alternative - lang",
+    "newColumnName": "dcterms:alternative/lang",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - dcterms:alternative - lang to dcterms:alternative/lang"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - metadata - xMetaDiss:xMetaDiss - dcterms:hasVersion",
+    "newColumnName": "dcterms:hasVersion",
+    "description": "Rename column Record - metadata - xMetaDiss:xMetaDiss - dcterms:hasVersion to dcterms:hasVersion"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - header - setSpec",
+    "newColumnName": "setSpec",
+    "description": "Rename column Record - header - setSpec to setSpec"
+  },
+  {
+    "op": "core/column-rename",
+    "oldColumnName": "Record - header - datestamp",
+    "newColumnName": "datestamp",
+    "description": "Rename column Record - header - datestamp to datestamp"
+  }
+]
--- a/tasks/siegen.yml
+++ b/tasks/siegen.yml
@ -0,0 +1,131 @@
+# https://taskfile.dev
+
+version: '3'
+
+tasks:
+  default:
+    desc: harvesten und transformieren
+    deps: [harvest]
+    cmds:
+      - ulimit -n 10000 # prevent "too many open files" exit
+      - task: refine
+      - task: check
+      - task: split
+      - task: validate
+      - task: zip
+
+  harvest:
+    desc: nur harvesten
+    dir: data/siegen/harvest
+    cmds:
+      - METHA_DIR=$PWD metha-sync --format xMetaDissPlus https://dspace.ub.uni-siegen.de/oai/request
+      - METHA_DIR=$PWD metha-cat --format xMetaDissPlus https://dspace.ub.uni-siegen.de/oai/request > siegen.xml
+
+  refine:
+    dir: data/siegen/refine
+    ignore_error: true # Bei Exit würde java-Prozess verwaisen https://github.com/go-task/task/issues/141 
+    env:
+      PORT: 3334
+      RAM: 8G
+      PROJECT: siegen
+    cmds:
+      # start OpenRefine
+      - $OPENREFINE -v warn -p $PORT -m $RAM -d $PWD > openrefine.log 2>&1 &
+      - timeout 30s bash -c "until curl -s http://localhost:$PORT | cat | grep -q -o OpenRefine ; do sleep 1; done"
+      # Import (erfordert absoluten Pfad zur XML-Datei)
+      - $OPENREFINE_CLIENT -P $PORT --create "$(readlink -e ../harvest/siegen.xml)" --recordPath Records --recordPath Record --storeEmptyStrings false --trimStrings true --projectName $PROJECT
+      # Vorverarbeitung: Spalte mit Identifier nach Vorne; Nicht benötigte Spalten (ohne differenzierende Merkmale) löschen; verbleibende Spalten umbenennen (Pfad entfernen)
+      - $OPENREFINE_CLIENT -P $PORT --apply ../../../rules/siegen/vorverarbeitung.json $PROJECT
+      # URNs extrahieren: Dubletten entfernen und verschiedene URNs zusammenführen
+      - $OPENREFINE_CLIENT -P $PORT --apply ../../../rules/siegen/urn.json $PROJECT
+      # Fehlende Direktlinks ergänzen: Wenn keine Angabe in ddb:transfer, dann zusätzlich METS Format abfragen; aus METS Flocat extrahieren und die URLs in ddb:transfer ablegen
+      - $OPENREFINE_CLIENT -P $PORT --apply ../../../rules/siegen/direktlinks.json $PROJECT
+      # Datensätze ohne Direktlink auf ein PDF löschen
+      - $OPENREFINE_CLIENT -P $PORT --apply ../../../rules/siegen/nur-mit-pdf.json $PROJECT
+      # Aufteilung dc:subject in ddc und topic
+      - $OPENREFINE_CLIENT -P $PORT --apply ../../../rules/siegen/ddc-topic.json $PROJECT
+      # Standardisierte Rechteangaben (Canonical Name aus CC Links in dc:rights)
+      - $OPENREFINE_CLIENT -P $PORT --apply ../../../rules/siegen/cc.json $PROJECT
+      # Internet Media Type aus ddb:transfer ableiten: Mapping manuell nach Apache: http://svn.apache.org/viewvc/httpd/httpd/trunk/docs/conf/mime.types?view=markup
+      - $OPENREFINE_CLIENT -P $PORT --apply ../../../rules/siegen/mime.json $PROJECT
+      # DOIs aus Format OAI_DC ergänzen: Für alle Datensätze zusätzlich DC Format abfragen; Aus DC dc:identifier mit xsi:type doi:doi extrahieren
+      - $OPENREFINE_CLIENT -P $PORT --apply ../../../rules/siegen/doi.json $PROJECT
+      # Abgleich mit lobid resources für HT-Nummer: teilweise mehrere URNs: wir machen dann eine ODER-Suche bei lobid; teilweise mehrere Treffer für eine URN: wir nehmen hier immer den ersten Treffer bei lobid
+      - $OPENREFINE_CLIENT -P $PORT --apply ../../../rules/siegen/hbz.json $PROJECT
+      # Für die Sortierung mods:nonSort: nur für das erste Element in dc:title je Datensatz
+      - $OPENREFINE_CLIENT -P $PORT --apply ../../../rules/siegen/nonsort.json $PROJECT
+      # DINI Publikationstypen aus dc:type extrahieren
+      - $OPENREFINE_CLIENT -P $PORT --apply ../../../rules/siegen/dini.json $PROJECT
+      # Visual Library doctype aus dc:type: Wenn thesis:level == thesis.habiliation dann oaHabil
+      - $OPENREFINE_CLIENT -P $PORT --apply ../../../rules/siegen/doctype.json $PROJECT
+      # Links auf Verfügbarkeit prüfen: ermittelt HTTP status code (z.B. 200)
+      - $OPENREFINE_CLIENT -P $PORT --apply ../../../rules/siegen/linkcheck.json $PROJECT
+      # Pro Zeile ein Datensatz und anschließend leere Zeilen löschen
+      - $OPENREFINE_CLIENT -P $PORT --apply ../../../rules/siegen/join.json $PROJECT
+      # Export mit Templating
+      - |
+        $OPENREFINE_CLIENT -P $PORT --export --template "$(< ../../../rules/siegen/template.txt)" --rowSeparator "
+        <!-- SPLIT -->
+        " --output siegen.txt $PROJECT
+      # Export für Debugging
+      - $OPENREFINE_CLIENT -P $PORT --export --output siegen-debug.tsv $PROJECT
+      # stop OpenRefine
+      - ps -o start,etime,%mem,%cpu,rss -p $(lsof -t -i:$PORT) # print server load
+      - kill -9 $(lsof -t -i:$PORT) # SIGKILL prevents saving projects
+      - rm -rf ./*.project* && rm -f workspace.json # delete temporary OpenRefine files
+    sources:
+      - ../harvest/siegen.xml
+      - ../../../rules/siegen/*.json
+      - ../../../rules/siegen/template.txt
+#     - ../../../rules/common/*.json
+    generates:
+      - siegen.txt
+      - siegen-debug.tsv
+
+  check:
+    dir: data/siegen/refine
+    cmds:
+      # check OpenRefine log for any warnings
+      - if grep -i 'exception\|error' openrefine.log; then echo 1>&2 "log contains warnings!" && exit 1; fi
+      # TODO: Prüfung, ob Mindestmenge an Datensätzen vorhanden ist (z.B. mit wc -l)
+      # TODO: Linkcheck-Ergebnis aus siegen-debug.tsv mit grep auf nicht 200 prüfen
+
+  split:
+    dir: data/siegen/split
+    cmds:
+      # in Einzeldateien aufteilen
+      - csplit -q ../refine/siegen.txt --suppress-matched '/<!-- SPLIT -->/' "{*}"
+      # ggf. vorhandene XML-Dateien löschen
+      - rm -f *.xml
+      # Identifier als Dateinamen
+      - for f in xx*; do mv "$f" "$(xmllint --xpath "//*[local-name(.) = 'recordIdentifier']/text()" "$f").xml"; done
+    sources:
+      - ../refine/siegen.txt
+    generates:
+      - ./*.xml
+
+  validate:
+    dir: data/siegen/
+    cmds:
+      # Validierung gegen METS Schema
+      - wget -q -nc https://www.loc.gov/standards/mets/mets.xsd
+      - xmllint --schema mets.xsd --noout split/*.xml > validate.log 2>&1
+    sources:
+      - split/*.xml
+    generates:
+      - validate.log
+
+  zip:
+    dir: data/siegen/
+    cmds:
+      # ZIP-Archiv mit Zeitstempel erstellen
+      - zip -q -FS -j siegen_{{.DATE}}.zip split/*.xml
+    sources:
+      - split/*.xml
+    generates:
+      - siegen_{{.DATE}}.zip      
+
+  delete:
+    desc: cache löschen
+    cmds:
+      - rm -rf data/siegen