diff --git a/.gitattributes b/.gitattributes
index cacc10aff23362e3a6fb9887ecf4c6a2198a9263..25a2d15ada71d7512e50e09a3b0128b5ca4c5423 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -87,3 +87,4 @@ data/AB/1938/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1939/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1940/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1941/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1942/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/cb63628c2445443dad93dc1af707a812_python.cwl b/.renku/workflow/cb63628c2445443dad93dc1af707a812_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..b063499e3bd45dda1dbf6c57e7172dddc64791e3
--- /dev/null
+++ b/.renku/workflow/cb63628c2445443dad93dc1af707a812_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/1942/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1942/02_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/1942
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1942/02_extractedxml.tar.gz b/data/AB/1942/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..fc2effb152993a1da9c967b23b935ae6e0280cb8
--- /dev/null
+++ b/data/AB/1942/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f45b7b3f443824ea0e4554a6e566907ce09e44542c4dd5f9f73df4e5e1deeae6
+size 52870046