diff --git a/.gitattributes b/.gitattributes
index 990b12677901a4eb23ad7953c9dba95d259c7b78..92e0f33100f22f0abc9c5069fd6f3c27852aa492 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -242,3 +242,4 @@ data/AB/1994/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1995/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1973/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1974/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1980/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/7b69fad35c574cbfb28b966576580e0d_python.cwl b/.renku/workflow/7b69fad35c574cbfb28b966576580e0d_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..bfd6aa94e19ac1e78ad7275032beb77935681205
--- /dev/null
+++ b/.renku/workflow/7b69fad35c574cbfb28b966576580e0d_python.cwl
@@ -0,0 +1,51 @@
+arguments: []
+baseCommand:
+- python
+class: CommandLineTool
+cwlVersion: v1.0
+hints: []
+inputs:
+  input_1:
+    default:
+      class: File
+      path: ../../src/python/run_extract_origxml.py
+    inputBinding:
+      position: 1
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_2:
+    default:
+      class: File
+      path: ../../data/AB/1980/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1980/02_extractedxml.tar.gz
+    inputBinding:
+      position: 3
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: string
+outputs:
+  output_0:
+    outputBinding:
+      glob: $(inputs.input_3)
+    streamable: false
+    type: File
+permanentFailCodes: []
+requirements:
+- class: InlineJavascriptRequirement
+- class: InitialWorkDirRequirement
+  listing:
+  - entry: '$({"listing": [], "class": "Directory"})'
+    entryname: data/AB/1980
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1980/02_extractedxml.tar.gz b/data/AB/1980/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..9a49a4f352da8f831afa549a7ab7bfdfb699bba1
--- /dev/null
+++ b/data/AB/1980/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0baf515b60277460abe248e29981e2fb35cb335b5bcd8fe6efcb8d325738f59
+size 325333041