diff --git a/.gitattributes b/.gitattributes
index 62433ae1bd8609689a48b3843ed0df97aeb37dbb..e4651eee28cb66f2dd7cf8e7a5951159f8889d09 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -79,3 +79,4 @@ data/AB/1930/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1931/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1932/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1933/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1934/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/e1a550de644e4ac98f0a5d7c9055c74c_python.cwl b/.renku/workflow/e1a550de644e4ac98f0a5d7c9055c74c_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..05f925da60dddf48e99dfeba110752dde3095f2d
--- /dev/null
+++ b/.renku/workflow/e1a550de644e4ac98f0a5d7c9055c74c_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/1934/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1934/02_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/1934
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1934/02_extractedxml.tar.gz b/data/AB/1934/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..8c5610692c29e349f202351174b2c5adfc75bed4
--- /dev/null
+++ b/data/AB/1934/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4739cf075e59b98025b7ca8229d5ec03dc19f6b84d67faac0accecbf000e08c
+size 142548370