diff --git a/.gitattributes b/.gitattributes
index ecdead894ef79dc2859e08c68ffd1760d8fa7b30..64c7457aa29330cd6f2a11f809f27ec774c0a9eb 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -15,3 +15,4 @@ 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
 data/AB/1902/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1903/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1904/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/113abe1329c848b8a140aa344d36dcca_python.cwl b/.renku/workflow/113abe1329c848b8a140aa344d36dcca_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..b7be8aeb9b76e8477eb1b91f6badfdc4a1ad8d15
--- /dev/null
+++ b/.renku/workflow/113abe1329c848b8a140aa344d36dcca_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/1904/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1904/02_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/1904
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1904/02_extractedxml.tar.gz b/data/AB/1904/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..ae6cfbad9ddb91d9506531947fe9611015ef78c8
--- /dev/null
+++ b/data/AB/1904/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2caf2bd818f28c03cde6fb9a304aa2a0f028b2e6a3ec2669337fa1f2e50d4e66
+size 40694830