diff --git a/.gitattributes b/.gitattributes
index 3472d227405cd0ff46955f4d5fa0a2d85b86a0f7..006a96b58f02b3edb52503f1b46fd041fe3d37a5 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -20,3 +20,4 @@ data/AB/1905/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1906/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1907/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1908/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1909/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/963b3f1319b5444096f8321b5e2ef1d6_python.cwl b/.renku/workflow/963b3f1319b5444096f8321b5e2ef1d6_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..e922b5bd4db873ecf8a707d36f34fe8c65bd742d
--- /dev/null
+++ b/.renku/workflow/963b3f1319b5444096f8321b5e2ef1d6_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/1909/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1909/02_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/1909
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1909/02_extractedxml.tar.gz b/data/AB/1909/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..963abe268c13f81c79a266827d824f368db353cd
--- /dev/null
+++ b/data/AB/1909/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:418ea8c78b133e7480f83162118199291e5d19a1bd8d53088f95b6cf7cb7e08a
+size 80056573