diff --git a/.gitattributes b/.gitattributes
index 5a22723930372f13bd38915ee9986275f3398e7e..222e8b48b0b5180117cdf7edc3465cff6f28b8df 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -91,3 +91,4 @@ data/AB/1942/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1943/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1944/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1945/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1946/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/d1f1a51f0439449aa0e5f6fe6a5835cc_python.cwl b/.renku/workflow/d1f1a51f0439449aa0e5f6fe6a5835cc_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..c111f2d5dc92e17b9466a4e03f7ca27874fbf0d0
--- /dev/null
+++ b/.renku/workflow/d1f1a51f0439449aa0e5f6fe6a5835cc_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/1946/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1946/02_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/1946
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1946/02_extractedxml.tar.gz b/data/AB/1946/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..6a836914f4cf92b77cece97bf3773d0b3c267768
--- /dev/null
+++ b/data/AB/1946/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13da9ee0a93a941f24cc7a07a3471640cb76a8d54b446fbffa307e47ddf1c5f8
+size 136232748