diff --git a/.gitattributes b/.gitattributes
index cb8b447f806535f3d16eeb2fa9b6c48af0b2d26b..874e38a93f8047005c5fab272b3a0e319dbc444e 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -352,3 +352,4 @@ data/AB/1986/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1988/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1989/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1985/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1994/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/c2f614e0e3404b07966c88893244e0ea_python.cwl b/.renku/workflow/c2f614e0e3404b07966c88893244e0ea_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..733dbc3d69af0923b05f44ecfd26f8fb483ad008
--- /dev/null
+++ b/.renku/workflow/c2f614e0e3404b07966c88893244e0ea_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/1994/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1994/02_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/1994
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1994/02_extractedxml.tar.gz b/data/AB/1994/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..4966cc5340261b4671c16d9832ecea7c8ad7f1d3
--- /dev/null
+++ b/data/AB/1994/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:438f3e8c1b5f66db4d80fb5a66d70b80f6cd405b4c7330a199a7befef1c24223
+size 512661912