diff --git a/.gitattributes b/.gitattributes
index 172f4a79ac9ca359e570d7d9449d7206200c2560..165eff579c67dd2ba185bfd74e81e8f21c4d5346 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -115,3 +115,4 @@ data/AB/1939/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 src/python/def_classes.py filter=lfs diff=lfs merge=lfs -text
 data/AB/1940/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1951/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1952/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/ac5a84577f084ca0b184c53583169045_python.cwl b/.renku/workflow/ac5a84577f084ca0b184c53583169045_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..81e3a74f7844ae8f5202d7390820fed740359554
--- /dev/null
+++ b/.renku/workflow/ac5a84577f084ca0b184c53583169045_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/1952/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1952/02_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/1952
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1952/02_extractedxml.tar.gz b/data/AB/1952/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..507f6d4ea16769e50d434ba06954e82c88b580ff
--- /dev/null
+++ b/data/AB/1952/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:778aeedd48c457b6aee93a03d711e6bc592abd4c9278eea993f22de060bb9398
+size 87526334