From 5371cc48b8888fc857d77542cce00402db1fa3f0 Mon Sep 17 00:00:00 2001 From: Lilian Gasser <gasserli@ethz.ch> Date: Tue, 5 Feb 2019 20:01:52 +0100 Subject: [PATCH] renku run python src/python/extract_document_titles.py data/AB/ 03_correctedmeta data/lists/all_titles.csv --- .gitattributes | 1 + ...7f5834807064a1f8ed8026be247a3be_python.cwl | 60 +++++++++++++++++++ data/lists/all_titles.csv | 3 + 3 files changed, 64 insertions(+) create mode 100644 .renku/workflow/d7f5834807064a1f8ed8026be247a3be_python.cwl create mode 100644 data/lists/all_titles.csv diff --git a/.gitattributes b/.gitattributes index 239462ba..25caffd4 100644 --- a/.gitattributes +++ b/.gitattributes @@ -254,3 +254,4 @@ 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 diff --git a/.renku/workflow/d7f5834807064a1f8ed8026be247a3be_python.cwl b/.renku/workflow/d7f5834807064a1f8ed8026be247a3be_python.cwl new file mode 100644 index 00000000..1226793d --- /dev/null +++ b/.renku/workflow/d7f5834807064a1f8ed8026be247a3be_python.cwl @@ -0,0 +1,60 @@ +arguments: [] +baseCommand: +- python +class: CommandLineTool +cwlVersion: v1.0 +hints: [] +inputs: + input_1: + default: + class: File + path: ../../src/python/extract_document_titles.py + inputBinding: + position: 1 + separate: true + shellQuote: true + streamable: false + type: File + input_2: + default: + class: Directory + listing: [] + path: ../../data/AB + inputBinding: + position: 2 + separate: true + shellQuote: true + streamable: false + type: Directory + input_3: + default: 03_correctedmeta + inputBinding: + position: 3 + separate: true + shellQuote: true + streamable: false + type: string + input_4: + default: data/lists/all_titles.csv + inputBinding: + position: 4 + separate: true + shellQuote: true + streamable: false + type: string +outputs: + output_0: + outputBinding: + glob: $(inputs.input_4) + streamable: false + type: File +permanentFailCodes: [] +requirements: +- class: InlineJavascriptRequirement +- class: InitialWorkDirRequirement + listing: + - entry: '$({"listing": [], "class": "Directory"})' + entryname: data/lists + writable: true +successCodes: [] +temporaryFailCodes: [] diff --git a/data/lists/all_titles.csv b/data/lists/all_titles.csv new file mode 100644 index 00000000..812c19fa --- /dev/null +++ b/data/lists/all_titles.csv @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45fbfbadcb22dcb849344764815b91ba6a54e092f392f5ea6b84d04d8e90c9cd +size 5867681 -- GitLab