diff --git a/.gitattributes b/.gitattributes
index 88ca6adb1f7e6adac26593dadccd4ee5bc74ea5d..94ff0f66050a4e70e5f901f43f6d8a1961e21312 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -12,3 +12,4 @@ data/AB/1897/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1898/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1899/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1900/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1901/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/5a0017a638b443959606d67aa04b7fbd_python.cwl b/.renku/workflow/5a0017a638b443959606d67aa04b7fbd_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..431b870be923936f6f2bd6b56270713633447d6e
--- /dev/null
+++ b/.renku/workflow/5a0017a638b443959606d67aa04b7fbd_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/1901/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1901/02_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/1901
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1901/02_extractedxml.tar.gz b/data/AB/1901/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..7fb6854159b749b4de4c49a36a6b4f0e0c3872ad
--- /dev/null
+++ b/data/AB/1901/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f70a672ce6ca37f4a19fccd0dfe81df8ad0d44e4c59f463b273ce463e5092cc8
+size 52036679