diff --git a/.gitattributes b/.gitattributes
index aa493d6d6b344605c6c49f8ffbceef145e8631a2..ee9a59a77d286d83100c812858b9cc4595b7d78e 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -137,3 +137,4 @@ data/AB/1970/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1971/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1972/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1973/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1974/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/80240e7b708342cba4d51f98dc694707_python.cwl b/.renku/workflow/80240e7b708342cba4d51f98dc694707_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..074df1e5048d9ddf183a4e86153de405e252fb3d
--- /dev/null
+++ b/.renku/workflow/80240e7b708342cba4d51f98dc694707_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/1974/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1974/02_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/1974
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1974/02_extractedxml.tar.gz b/data/AB/1974/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..00f7f04744cd1c2f73d43eb5e37f9efd2eeea40b
--- /dev/null
+++ b/data/AB/1974/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f93d1164e5feacd1ea5f0ffa187ad44cb48c2e19c1ed515efc58f542c5aa11e5
+size 316579148