after ordering

.gitattributes

@@ -262,3 +262,83 @@ data/politicians/MPs_after1890.csv filter=lfs diff=lfs merge=lfs -text
 data/politicians/lastnames/** filter=lfs diff=lfs merge=lfs -text
 data/train_NER/20190109_train_NER.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/train_NER/20190116_train_NER_french.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1973/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1975/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1976/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1974/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1980/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1981/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1977/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1982/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1983/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1991/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1991/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/lists/dict_overlaps.pickle filter=lfs diff=lfs merge=lfs -text
+data/lists/all_titles.csv filter=lfs diff=lfs merge=lfs -text
+data/AB/1978/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1979/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1975/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1891/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1892/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1893/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1894/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1895/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1896/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1897/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1898/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1899/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1900/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1991/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1901/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1902/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1903/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1904/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1905/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1906/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1907/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1908/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1909/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1910/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1911/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1912/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1913/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1914/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1915/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1916/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1917/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1918/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1919/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1920/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1921/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1922/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1923/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1924/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1925/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1926/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1927/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1928/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1929/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1930/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1931/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1932/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1933/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1934/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1935/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1936/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1937/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1938/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1939/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1940/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1941/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1942/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1943/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1944/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1945/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1946/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1947/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1948/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1949/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1950/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1976/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1977/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1975/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text

.gitlab-ci.yml

@@ -24,8 +24,9 @@ image_build:
 
 dot:
   stage: build
-  image: renku/singleuser:latest
+  image: renku/renku-python:latest
   script:
+    - renku --version
     - renku log --format dot $(git ls-files --no-empty-directory --recurse-submodules) > graph.dot
   artifacts:
     paths:

.renku/workflow/04e7976838dc4d37bb8159375d17fd04_python.cwl

+arguments: []
+baseCommand:
+- python
+class: CommandLineTool
+cwlVersion: v1.0
+hints: []
+inputs:
+  input_1:
+    default:
+      class: File
+      path: ../../src/python/run_extract_discussions.py
+    inputBinding:
+      position: 1
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_2:
+    default:
+      class: File
+      path: ../../data/politicians/lastnames/1900_MPs.pickle
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default:
+      class: File
+      path: ../../data/AB/1900/04_correctedxml.tar.gz
+    inputBinding:
+      position: 3
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_4:
+    default:
+      class: File
+      path: ../../data/AB/1900/03_correctedmeta.tar.gz
+    inputBinding:
+      position: 4
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_5:
+    default:
+      class: File
+      path: ../../data/lists/not_names.txt
+    inputBinding:
+      position: 5
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_6:
+    default:
+      class: File
+      path: ../../data/lists/dict_overlaps.pickle
+    inputBinding:
+      position: 6
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_7:
+    default: data/AB/1900/05_annotatedxml.tar.gz
+    inputBinding:
+      position: 7
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: string
+outputs:
+  output_0:
+    outputBinding:
+      glob: $(inputs.input_7)
+    streamable: false
+    type: File
+permanentFailCodes: []
+requirements:
+- class: InlineJavascriptRequirement
+- class: InitialWorkDirRequirement
+  listing:
+  - entry: '$({"listing": [], "class": "Directory"})'
+    entryname: data/AB/1900
+    writable: true
+successCodes: []
+temporaryFailCodes: []

.renku/workflow/08070d37200f4c08ae0ae5d950b77ede_python.cwl

+arguments: []
+baseCommand:
+- python
+class: CommandLineTool
+cwlVersion: v1.0
+hints: []
+inputs:
+  input_1:
+    default:
+      class: File
+      path: ../../src/python/run_extract_discussions.py
+    inputBinding:
+      position: 1
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_2:
+    default:
+      class: File
+      path: ../../data/politicians/lastnames/1897_MPs.pickle
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default:
+      class: File
+      path: ../../data/AB/1897/04_correctedxml.tar.gz
+    inputBinding:
+      position: 3
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_4:
+    default:
+      class: File
+      path: ../../data/AB/1897/03_correctedmeta.tar.gz
+    inputBinding:
+      position: 4
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_5:
+    default:
+      class: File
+      path: ../../data/lists/not_names.txt
+    inputBinding:
+      position: 5
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_6:
+    default:
+      class: File
+      path: ../../data/lists/dict_overlaps.pickle
+    inputBinding:
+      position: 6
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_7:
+    default: data/AB/1897/05_annotatedxml.tar.gz
+    inputBinding:
+      position: 7
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: string
+outputs:
+  output_0:
+    outputBinding:
+      glob: $(inputs.input_7)
+    streamable: false
+    type: File
+permanentFailCodes: []
+requirements:
+- class: InlineJavascriptRequirement
+- class: InitialWorkDirRequirement
+  listing:
+  - entry: '$({"listing": [], "class": "Directory"})'
+    entryname: data/AB/1897
+    writable: true
+successCodes: []
+temporaryFailCodes: []

.renku/workflow/096cbe6860624be295bb368f984ccf0c_python.cwl

+arguments: []
+baseCommand:
+- python
+class: CommandLineTool
+cwlVersion: v1.0
+hints: []
+inputs:
+  input_1:
+    default:
+      class: File
+      path: ../../src/python/run_extract_discussions.py
+    inputBinding:
+      position: 1
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_2:
+    default:
+      class: File
+      path: ../../data/politicians/lastnames/1943_MPs.pickle
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default:
+      class: File
+      path: ../../data/AB/1943/04_correctedxml.tar.gz
+    inputBinding:
+      position: 3
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_4:
+    default:
+      class: File
+      path: ../../data/AB/1943/03_correctedmeta.tar.gz
+    inputBinding:
+      position: 4
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_5:
+    default:
+      class: File
+      path: ../../data/lists/not_names.txt
+    inputBinding:
+      position: 5
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_6:
+    default:
+      class: File
+      path: ../../data/lists/dict_overlaps.pickle
+    inputBinding:
+      position: 6
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_7:
+    default: data/AB/1943/05_annotatedxml.tar.gz
+    inputBinding:
+      position: 7
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: string
+outputs:
+  output_0:
+    outputBinding:
+      glob: $(inputs.input_7)
+    streamable: false
+    type: File
+permanentFailCodes: []
+requirements:
+- class: InlineJavascriptRequirement
+- class: InitialWorkDirRequirement
+  listing:
+  - entry: '$({"listing": [], "class": "Directory"})'
+    entryname: data/AB/1943
+    writable: true
+successCodes: []
+temporaryFailCodes: []

.renku/workflow/09c91cabdeb84f79b46299ed82540e2b_python.cwl

+arguments: []
+baseCommand:
+- python
+class: CommandLineTool
+cwlVersion: v1.0
+hints: []
+inputs:
+  input_1:
+    default:
+      class: File
+      path: ../../src/python/run_extract_discussions.py
+    inputBinding:
+      position: 1
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_2:
+    default:
+      class: File
+      path: ../../data/politicians/lastnames/1917_MPs.pickle
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default:
+      class: File
+      path: ../../data/AB/1917/04_correctedxml.tar.gz
+    inputBinding:
+      position: 3
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_4:
+    default:
+      class: File
+      path: ../../data/AB/1917/03_correctedmeta.tar.gz
+    inputBinding:
+      position: 4
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_5:
+    default:
+      class: File
+      path: ../../data/lists/not_names.txt
+    inputBinding:
+      position: 5
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_6:
+    default:
+      class: File
+      path: ../../data/lists/dict_overlaps.pickle
+    inputBinding:
+      position: 6
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_7:
+    default: data/AB/1917/05_annotatedxml.tar.gz
+    inputBinding:
+      position: 7
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: string
+outputs:
+  output_0:
+    outputBinding:
+      glob: $(inputs.input_7)
+    streamable: false
+    type: File
+permanentFailCodes: []
+requirements:
+- class: InlineJavascriptRequirement
+- class: InitialWorkDirRequirement
+  listing:
+  - entry: '$({"listing": [], "class": "Directory"})'
+    entryname: data/AB/1917
+    writable: true
+successCodes: []
+temporaryFailCodes: []

.renku/workflow/0c03aec5c51a4c49b79accd91c4537c6_python.cwl

+arguments: []
+baseCommand:
+- python
+class: CommandLineTool
+cwlVersion: v1.0
+hints: []
+inputs:
+  input_1:
+    default:
+      class: File
+      path: ../../src/python/run_extract_discussions.py
+    inputBinding:
+      position: 1
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_2:
+    default:
+      class: File
+      path: ../../data/politicians/lastnames/1913_MPs.pickle
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default:
+      class: File
+      path: ../../data/AB/1913/04_correctedxml.tar.gz
+    inputBinding:
+      position: 3
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_4:
+    default:
+      class: File
+      path: ../../data/AB/1913/03_correctedmeta.tar.gz
+    inputBinding:
+      position: 4
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_5:
+    default:
+      class: File
+      path: ../../data/lists/not_names.txt
+    inputBinding:
+      position: 5
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_6:
+    default:
+      class: File
+      path: ../../data/lists/dict_overlaps.pickle
+    inputBinding:
+      position: 6
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_7:
+    default: data/AB/1913/05_annotatedxml.tar.gz
+    inputBinding:
+      position: 7
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: string
+outputs:
+  output_0:
+    outputBinding:
+      glob: $(inputs.input_7)
+    streamable: false
+    type: File
+permanentFailCodes: []
+requirements:
+- class: InlineJavascriptRequirement
+- class: InitialWorkDirRequirement
+  listing:
+  - entry: '$({"listing": [], "class": "Directory"})'
+    entryname: data/AB/1913
+    writable: true
+successCodes: []
+temporaryFailCodes: []

.renku/workflow/0c251d63a59149b68a93f7ac34a0e4ce_python.cwl

+arguments: []
+baseCommand:
+- python
+class: CommandLineTool
+cwlVersion: v1.0
+hints: []
+inputs:
+  input_1:
+    default:
+      class: File
+      path: ../../src/python/run_extract_discussions.py
+    inputBinding:
+      position: 1
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_2:
+    default:
+      class: File
+      path: ../../data/politicians/lastnames/1901_MPs.pickle
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default:
+      class: File
+      path: ../../data/AB/1901/04_correctedxml.tar.gz
+    inputBinding:
+      position: 3
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_4:
+    default:
+      class: File
+      path: ../../data/AB/1901/03_correctedmeta.tar.gz
+    inputBinding:
+      position: 4
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_5:
+    default:
+      class: File
+      path: ../../data/lists/not_names.txt
+    inputBinding:
+      position: 5
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_6:
+    default:
+      class: File
+      path: ../../data/lists/dict_overlaps.pickle
+    inputBinding:
+      position: 6
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_7:
+    default: data/AB/1901/05_annotatedxml.tar.gz
+    inputBinding:
+      position: 7
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: string
+outputs:
+  output_0:
+    outputBinding:
+      glob: $(inputs.input_7)
+    streamable: false
+    type: File
+permanentFailCodes: []
+requirements:
+- class: InlineJavascriptRequirement
+- class: InitialWorkDirRequirement
+  listing:
+  - entry: '$({"listing": [], "class": "Directory"})'
+    entryname: data/AB/1901
+    writable: true
+successCodes: []
+temporaryFailCodes: []

.renku/workflow/0dfe13364d3842a389d0a7c0041e58d4_python.cwl

+arguments: []
+baseCommand:
+- python
+class: CommandLineTool
+cwlVersion: v1.0
+hints: []
+inputs:
+  input_1:
+    default:
+      class: File
+      path: ../../src/python/run_extract_discussions.py
+    inputBinding:
+      position: 1
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_2:
+    default:
+      class: File
+      path: ../../data/politicians/lastnames/1920_MPs.pickle
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default:
+      class: File
+      path: ../../data/AB/1920/04_correctedxml.tar.gz
+    inputBinding:
+      position: 3
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_4:
+    default:
+      class: File
+      path: ../../data/AB/1920/03_correctedmeta.tar.gz
+    inputBinding:
+      position: 4
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_5:
+    default:
+      class: File
+      path: ../../data/lists/not_names.txt
+    inputBinding:
+      position: 5
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_6:
+    default:
+      class: File
+      path: ../../data/lists/dict_overlaps.pickle
+    inputBinding:
+      position: 6
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_7:
+    default: data/AB/1920/05_annotatedxml.tar.gz
+    inputBinding:
+      position: 7
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: string
+outputs:
+  output_0:
+    outputBinding:
+      glob: $(inputs.input_7)
+    streamable: false
+    type: File
+permanentFailCodes: []
+requirements:
+- class: InlineJavascriptRequirement
+- class: InitialWorkDirRequirement
+  listing:
+  - entry: '$({"listing": [], "class": "Directory"})'
+    entryname: data/AB/1920
+    writable: true
+successCodes: []
+temporaryFailCodes: []

.renku/workflow/1099d291016a42b88441229dc6f00edb_python.cwl

+arguments: []
+baseCommand:
+- python
+class: CommandLineTool
+cwlVersion: v1.0
+hints: []
+inputs:
+  input_1:
+    default:
+      class: File
+      path: ../../src/python/run_extract_discussions.py
+    inputBinding:
+      position: 1
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_2:
+    default:
+      class: File
+      path: ../../data/politicians/lastnames/1939_MPs.pickle
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default:
+      class: File
+      path: ../../data/AB/1939/04_correctedxml.tar.gz
+    inputBinding:
+      position: 3
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_4:
+    default:
+      class: File
+      path: ../../data/AB/1939/03_correctedmeta.tar.gz
+    inputBinding:
+      position: 4
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_5:
+    default:
+      class: File
+      path: ../../data/lists/not_names.txt
+    inputBinding:
+      position: 5
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_6:
+    default:
+      class: File
+      path: ../../data/lists/dict_overlaps.pickle
+    inputBinding:
+      position: 6
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_7:
+    default: data/AB/1939/05_annotatedxml.tar.gz
+    inputBinding:
+      position: 7
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: string
+outputs:
+  output_0:
+    outputBinding:
+      glob: $(inputs.input_7)
+    streamable: false
+    type: File
+permanentFailCodes: []
+requirements:
+- class: InlineJavascriptRequirement
+- class: InitialWorkDirRequirement
+  listing:
+  - entry: '$({"listing": [], "class": "Directory"})'
+    entryname: data/AB/1939
+    writable: true
+successCodes: []
+temporaryFailCodes: []

.renku/workflow/10b263baa6cb4a1995a435bbf58f2dd8_python.cwl

+arguments: []
+baseCommand:
+- python
+class: CommandLineTool
+cwlVersion: v1.0
+hints: []
+inputs:
+  input_1:
+    default:
+      class: File
+      path: ../../src/python/run_extract_discussions.py
+    inputBinding:
+      position: 1
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_2:
+    default:
+      class: File
+      path: ../../data/politicians/lastnames/1924_MPs.pickle
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default:
+      class: File
+      path: ../../data/AB/1924/04_correctedxml.tar.gz
+    inputBinding:
+      position: 3
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_4:
+    default:
+      class: File
+      path: ../../data/AB/1924/03_correctedmeta.tar.gz
+    inputBinding:
+      position: 4
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_5:
+    default:
+      class: File
+      path: ../../data/lists/not_names.txt
+    inputBinding:
+      position: 5
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_6:
+    default:
+      class: File
+      path: ../../data/lists/dict_overlaps.pickle
+    inputBinding:
+      position: 6
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_7:
+    default: data/AB/1924/05_annotatedxml.tar.gz
+    inputBinding:
+      position: 7
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: string
+outputs:
+  output_0:
+    outputBinding:
+      glob: $(inputs.input_7)
+    streamable: false
+    type: File
+permanentFailCodes: []
+requirements:
+- class: InlineJavascriptRequirement
+- class: InitialWorkDirRequirement
+  listing:
+  - entry: '$({"listing": [], "class": "Directory"})'
+    entryname: data/AB/1924
+    writable: true
+successCodes: []
+temporaryFailCodes: []

.renku/workflow/2866929d184b4145abd4ff60a5b17ac6_python.cwl

+arguments: []
+baseCommand:
+- python
+class: CommandLineTool
+cwlVersion: v1.0
+hints: []
+inputs:
+  input_1:
+    default:
+      class: File
+      path: ../../src/python/run_extract_discussions.py
+    inputBinding:
+      position: 1
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_2:
+    default:
+      class: File
+      path: ../../data/politicians/lastnames/1991_MPs.pickle
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default:
+      class: File
+      path: ../../data/AB/1991/04_correctedxml.tar.gz
+    inputBinding:
+      position: 3
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_4:
+    default:
+      class: File
+      path: ../../data/AB/1991/03_correctedmeta.tar.gz
+    inputBinding:
+      position: 4
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_5:
+    default:
+      class: File
+      path: ../../data/lists/not_names.txt
+    inputBinding:
+      position: 5
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_6:
+    default:
+      class: File
+      path: ../../data/lists/dict_overlaps.pickle
+    inputBinding:
+      position: 6
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_7:
+    default: data/AB/1991/05_annotatedxml.tar.gz
+    inputBinding:
+      position: 7
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: string
+outputs:
+  output_0:
+    outputBinding:
+      glob: $(inputs.input_7)
+    streamable: false
+    type: File
+permanentFailCodes: []
+requirements:
+- class: InlineJavascriptRequirement
+- class: InitialWorkDirRequirement
+  listing:
+  - entry: '$({"listing": [], "class": "Directory"})'
+    entryname: data/AB/1991
+    writable: true
+successCodes: []
+temporaryFailCodes: []

.renku/workflow/2bf80c15eb374f1392a44cbe715d8b75_python.cwl

+arguments: []
+baseCommand:
+- python
+class: CommandLineTool
+cwlVersion: v1.0
+hints: []
+inputs:
+  input_1:
+    default:
+      class: File
+      path: ../../src/python/run_extract_discussions.py
+    inputBinding:
+      position: 1
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_2:
+    default:
+      class: File
+      path: ../../data/politicians/lastnames/1948_MPs.pickle
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default:
+      class: File
+      path: ../../data/AB/1948/04_correctedxml.tar.gz
+    inputBinding:
+      position: 3
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_4:
+    default:
+      class: File
+      path: ../../data/AB/1948/03_correctedmeta.tar.gz
+    inputBinding:
+      position: 4
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_5:
+    default:
+      class: File
+      path: ../../data/lists/not_names.txt
+    inputBinding:
+      position: 5
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_6:
+    default:
+      class: File
+      path: ../../data/lists/dict_overlaps.pickle
+    inputBinding:
+      position: 6
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_7:
+    default: data/AB/1948/05_annotatedxml.tar.gz
+    inputBinding:
+      position: 7
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: string
+outputs:
+  output_0:
+    outputBinding:
+      glob: $(inputs.input_7)
+    streamable: false
+    type: File
+permanentFailCodes: []
+requirements:
+- class: InlineJavascriptRequirement
+- class: InitialWorkDirRequirement
+  listing:
+  - entry: '$({"listing": [], "class": "Directory"})'
+    entryname: data/AB/1948
+    writable: true
+successCodes: []
+temporaryFailCodes: []

.renku/workflow/2e32c26de8824d6a9ed0d03f7de081a0_python.cwl

+arguments: []
+baseCommand:
+- python
+class: CommandLineTool
+cwlVersion: v1.0
+hints: []
+inputs:
+  input_1:
+    default:
+      class: File
+      path: ../../src/python/run_extract_discussions.py
+    inputBinding:
+      position: 1
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_2:
+    default:
+      class: File
+      path: ../../data/politicians/lastnames/1906_MPs.pickle
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default:
+      class: File
+      path: ../../data/AB/1906/04_correctedxml.tar.gz
+    inputBinding:
+      position: 3
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_4:
+    default:
+      class: File
+      path: ../../data/AB/1906/03_correctedmeta.tar.gz
+    inputBinding:
+      position: 4
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_5:
+    default:
+      class: File
+      path: ../../data/lists/not_names.txt
+    inputBinding:
+      position: 5
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_6:
+    default:
+      class: File
+      path: ../../data/lists/dict_overlaps.pickle
+    inputBinding:
+      position: 6
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_7:
+    default: data/AB/1906/05_annotatedxml.tar.gz
+    inputBinding:
+      position: 7
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: string
+outputs:
+  output_0:
+    outputBinding:
+      glob: $(inputs.input_7)
+    streamable: false
+    type: File
+permanentFailCodes: []
+requirements:
+- class: InlineJavascriptRequirement
+- class: InitialWorkDirRequirement
+  listing:
+  - entry: '$({"listing": [], "class": "Directory"})'
+    entryname: data/AB/1906
+    writable: true
+successCodes: []
+temporaryFailCodes: []

.renku/workflow/315b709bc82a4f42aecb6028053eb45c_python.cwl

+arguments: []
+baseCommand:
+- python
+class: CommandLineTool
+cwlVersion: v1.0
+hints: []
+inputs:
+  input_1:
+    default:
+      class: File
+      path: ../../src/python/run_extract_discussions.py
+    inputBinding:
+      position: 1
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_2:
+    default:
+      class: File
+      path: ../../data/politicians/lastnames/1923_MPs.pickle
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default:
+      class: File
+      path: ../../data/AB/1923/04_correctedxml.tar.gz
+    inputBinding:
+      position: 3
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_4:
+    default:
+      class: File
+      path: ../../data/AB/1923/03_correctedmeta.tar.gz
+    inputBinding:
+      position: 4
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_5:
+    default:
+      class: File
+      path: ../../data/lists/not_names.txt
+    inputBinding:
+      position: 5
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_6:
+    default:
+      class: File
+      path: ../../data/lists/dict_overlaps.pickle
+    inputBinding:
+      position: 6
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_7:
+    default: data/AB/1923/05_annotatedxml.tar.gz
+    inputBinding:
+      position: 7
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: string
+outputs:
+  output_0:
+    outputBinding:
+      glob: $(inputs.input_7)
+    streamable: false
+    type: File
+permanentFailCodes: []
+requirements:
+- class: InlineJavascriptRequirement
+- class: InitialWorkDirRequirement
+  listing:
+  - entry: '$({"listing": [], "class": "Directory"})'
+    entryname: data/AB/1923
+    writable: true
+successCodes: []
+temporaryFailCodes: []

.renku/workflow/38c064f35e1c43e6a9f3a2162c4db230_python.cwl

+arguments: []
+baseCommand:
+- python
+class: CommandLineTool
+cwlVersion: v1.0
+hints: []
+inputs:
+  input_1:
+    default:
+      class: File
+      path: ../../src/python/run_extract_discussions.py
+    inputBinding:
+      position: 1
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_2:
+    default:
+      class: File
+      path: ../../data/politicians/lastnames/1932_MPs.pickle
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default:
+      class: File
+      path: ../../data/AB/1932/04_correctedxml.tar.gz
+    inputBinding:
+      position: 3
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_4:
+    default:
+      class: File
+      path: ../../data/AB/1932/03_correctedmeta.tar.gz
+    inputBinding:
+      position: 4
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_5:
+    default:
+      class: File
+      path: ../../data/lists/not_names.txt
+    inputBinding:
+      position: 5
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_6:
+    default:
+      class: File
+      path: ../../data/lists/dict_overlaps.pickle
+    inputBinding:
+      position: 6
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_7:
+    default: data/AB/1932/05_annotatedxml.tar.gz
+    inputBinding:
+      position: 7
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: string
+outputs:
+  output_0:
+    outputBinding:
+      glob: $(inputs.input_7)
+    streamable: false
+    type: File
+permanentFailCodes: []
+requirements:
+- class: InlineJavascriptRequirement
+- class: InitialWorkDirRequirement
+  listing:
+  - entry: '$({"listing": [], "class": "Directory"})'
+    entryname: data/AB/1932
+    writable: true
+successCodes: []
+temporaryFailCodes: []

.renku/workflow/3de19e9765574c0699ba7f649ecc100a_python.cwl

+arguments: []
+baseCommand:
+- python
+class: CommandLineTool
+cwlVersion: v1.0
+hints: []
+inputs:
+  input_1:
+    default:
+      class: File
+      path: ../../src/python/run_extract_discussions.py
+    inputBinding:
+      position: 1
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_2:
+    default:
+      class: File
+      path: ../../data/politicians/lastnames/1946_MPs.pickle
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default:
+      class: File
+      path: ../../data/AB/1946/04_correctedxml.tar.gz
+    inputBinding:
+      position: 3
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_4:
+    default:
+      class: File
+      path: ../../data/AB/1946/03_correctedmeta.tar.gz
+    inputBinding:
+      position: 4
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_5:
+    default:
+      class: File
+      path: ../../data/lists/not_names.txt
+    inputBinding:
+      position: 5
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_6:
+    default:
+      class: File
+      path: ../../data/lists/dict_overlaps.pickle
+    inputBinding:
+      position: 6
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_7:
+    default: data/AB/1946/05_annotatedxml.tar.gz
+    inputBinding:
+      position: 7
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: string
+outputs:
+  output_0:
+    outputBinding:
+      glob: $(inputs.input_7)
+    streamable: false
+    type: File
+permanentFailCodes: []
+requirements:
+- class: InlineJavascriptRequirement
+- class: InitialWorkDirRequirement
+  listing:
+  - entry: '$({"listing": [], "class": "Directory"})'
+    entryname: data/AB/1946
+    writable: true
+successCodes: []
+temporaryFailCodes: []

.renku/workflow/3f1cd56ab2304ed884ea4ed07f583f40_python.cwl

+arguments: []
+baseCommand:
+- python
+class: CommandLineTool
+cwlVersion: v1.0
+hints: []
+inputs:
+  input_1:
+    default:
+      class: File
+      path: ../../src/python/run_extract_discussions.py
+    inputBinding:
+      position: 1
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_2:
+    default:
+      class: File
+      path: ../../data/politicians/lastnames/1916_MPs.pickle
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default:
+      class: File
+      path: ../../data/AB/1916/04_correctedxml.tar.gz
+    inputBinding:
+      position: 3
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_4:
+    default:
+      class: File
+      path: ../../data/AB/1916/03_correctedmeta.tar.gz
+    inputBinding:
+      position: 4
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_5:
+    default:
+      class: File
+      path: ../../data/lists/not_names.txt
+    inputBinding:
+      position: 5
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_6:
+    default:
+      class: File
+      path: ../../data/lists/dict_overlaps.pickle
+    inputBinding:
+      position: 6
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_7:
+    default: data/AB/1916/05_annotatedxml.tar.gz
+    inputBinding:
+      position: 7
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: string
+outputs:
+  output_0:
+    outputBinding:
+      glob: $(inputs.input_7)
+    streamable: false
+    type: File
+permanentFailCodes: []
+requirements:
+- class: InlineJavascriptRequirement
+- class: InitialWorkDirRequirement
+  listing:
+  - entry: '$({"listing": [], "class": "Directory"})'
+    entryname: data/AB/1916
+    writable: true
+successCodes: []
+temporaryFailCodes: []

.renku/workflow/4523613056de4b73aca81c156aa1aa08_python.cwl

+arguments: []
+baseCommand:
+- python
+class: CommandLineTool
+cwlVersion: v1.0
+hints: []
+inputs:
+  input_1:
+    default:
+      class: File
+      path: ../../src/python/run_extract_discussions.py
+    inputBinding:
+      position: 1
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_2:
+    default:
+      class: File
+      path: ../../data/politicians/lastnames/1933_MPs.pickle
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default:
+      class: File
+      path: ../../data/AB/1933/04_correctedxml.tar.gz
+    inputBinding:
+      position: 3
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_4:
+    default:
+      class: File
+      path: ../../data/AB/1933/03_correctedmeta.tar.gz
+    inputBinding:
+      position: 4
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_5:
+    default:
+      class: File
+      path: ../../data/lists/not_names.txt
+    inputBinding:
+      position: 5
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_6:
+    default:
+      class: File
+      path: ../../data/lists/dict_overlaps.pickle
+    inputBinding:
+      position: 6
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_7:
+    default: data/AB/1933/05_annotatedxml.tar.gz
+    inputBinding:
+      position: 7
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: string
+outputs:
+  output_0:
+    outputBinding:
+      glob: $(inputs.input_7)
+    streamable: false
+    type: File
+permanentFailCodes: []
+requirements:
+- class: InlineJavascriptRequirement
+- class: InitialWorkDirRequirement
+  listing:
+  - entry: '$({"listing": [], "class": "Directory"})'
+    entryname: data/AB/1933
+    writable: true
+successCodes: []
+temporaryFailCodes: []

.renku/workflow/46541a4c28944396b841a1fef102d0f0_python.cwl

+arguments: []
+baseCommand:
+- python
+class: CommandLineTool
+cwlVersion: v1.0
+hints: []
+inputs:
+  input_1:
+    default:
+      class: File
+      path: ../../src/python/run_extract_discussions.py
+    inputBinding:
+      position: 1
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_2:
+    default:
+      class: File
+      path: ../../data/politicians/lastnames/1898_MPs.pickle
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default:
+      class: File
+      path: ../../data/AB/1898/04_correctedxml.tar.gz
+    inputBinding:
+      position: 3
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_4:
+    default:
+      class: File
+      path: ../../data/AB/1898/03_correctedmeta.tar.gz
+    inputBinding:
+      position: 4
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_5:
+    default:
+      class: File
+      path: ../../data/lists/not_names.txt
+    inputBinding:
+      position: 5
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_6:
+    default:
+      class: File
+      path: ../../data/lists/dict_overlaps.pickle
+    inputBinding:
+      position: 6
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_7:
+    default: data/AB/1898/05_annotatedxml.tar.gz
+    inputBinding:
+      position: 7
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: string
+outputs:
+  output_0:
+    outputBinding:
+      glob: $(inputs.input_7)
+    streamable: false
+    type: File
+permanentFailCodes: []
+requirements:
+- class: InlineJavascriptRequirement
+- class: InitialWorkDirRequirement
+  listing:
+  - entry: '$({"listing": [], "class": "Directory"})'
+    entryname: data/AB/1898
+    writable: true
+successCodes: []
+temporaryFailCodes: []