diff --git a/.gitattributes b/.gitattributes
index f163c1b95f38dfa54f64bf63de2f54f12ef57b6c..3e5952577640d5d596fcc5f130b0526b15e4f27f 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -84,3 +84,4 @@ data/AB/1935/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1936/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1937/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 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
diff --git a/.renku/workflow/4b0272e5c18e4c08926350e08bd05a18_python.cwl b/.renku/workflow/4b0272e5c18e4c08926350e08bd05a18_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..28b59f718299e32409b2bf885295ebe1a629c2b2
--- /dev/null
+++ b/.renku/workflow/4b0272e5c18e4c08926350e08bd05a18_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/1939/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1939/02_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/1939
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1939/02_extractedxml.tar.gz b/data/AB/1939/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..f8985e5fb7ac4888098e461ace6b6976d7680211
--- /dev/null
+++ b/data/AB/1939/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9da4e0dfd6dbdb8b199769785946b788b5696ec7e3ce3c7a3042cf6a142443fd
+size 118051217