diff --git a/.gitattributes b/.gitattributes
index 01440337e67ea186f55fd20e3f42ae4b09b21714..26293c8ba8da4244cd2b57550a2ec4e04d2b8bd9 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -93,3 +93,4 @@ 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
 data/AB/1947/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1948/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/d2e1210db92d4dc2bee57f3c369f6c01_python.cwl b/.renku/workflow/d2e1210db92d4dc2bee57f3c369f6c01_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..261bd80c4e4f058e156107436b980d99db0364d8
--- /dev/null
+++ b/.renku/workflow/d2e1210db92d4dc2bee57f3c369f6c01_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/1948/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1948/02_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/1948
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1948/02_extractedxml.tar.gz b/data/AB/1948/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..8c4a4d4a47d7bba5854603e298de76dba972e07f
--- /dev/null
+++ b/data/AB/1948/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:292470297cb066d92dede8df8d58cfb092e6e1dd22d354e6ce6946244e6520ff
+size 103347668