maint(zenodo): bring update_zenodo.py script from Nipype and run it [skip ci]

Author: oesteban

.mailmap

@@ -0,0 +1,9 @@
+Anisha Keshavan <[email protected]> <[email protected]>
+Anisha Keshavan <[email protected]> <[email protected]>
+Ariel Rokem <[email protected]>
+Ariel Rokem <[email protected]> <[email protected]>
+Garikoitz Lerma-Usabiaga <[email protected]> garikoitz <[email protected]>
+Michael Joseph <[email protected]> mjoseph <[email protected]>
+Oscar Esteban <[email protected]>
+Oscar Esteban <[email protected]> <[email protected]>
+Oscar Esteban <[email protected]> oesteban <[email protected]>

.maintenance/update_zenodo.py

@@ -0,0 +1,74 @@
+#!/usr/bin/env python3
+"""Update and sort the creators list of the zenodo record."""
+import sys
+import shutil
+from pathlib import Path
+import json
+from fuzzywuzzy import fuzz, process
+import subprocess as sp
+
+# These ORCIDs should go last
+CREATORS_LAST = ['Rokem, Ariel', 'Esteban, Oscar']
+# for entries not found in line-contributions
+MISSING_ENTRIES = [
+]
+
+if __name__ == '__main__':
+    contrib_file = Path('line-contributors.txt')
+    lines = []
+    if contrib_file.exists():
+        print('WARNING: Reusing existing line-contributors.txt file.', file=sys.stderr)
+        lines = contrib_file.read_text().splitlines()
+
+    git_line_summary_path = shutil.which('git-line-summary')
+    if not lines and git_line_summary_path:
+        print("Running git-line-summary on nipype repo")
+        lines = sp.check_output([git_line_summary_path]).decode().splitlines()
+        contrib_file.write_text('\n'.join(lines))
+
+    if not lines:
+        raise RuntimeError("""\
+Could not find line-contributors from git repository.%s""" % """ \
+git-line-summary not found, please install git-extras. """ * (git_line_summary_path is None))
+
+    data = [' '.join(line.strip().split()[1:-1]) for line in lines if '%' in line]
+
+    # load zenodo from master
+    zenodo_file = Path('.zenodo.json')
+    zenodo = json.loads(zenodo_file.read_text())
+    zen_names = [' '.join(val['name'].split(',')[::-1]).strip()
+                 for val in zenodo['creators']]
+    total_names = len(zen_names) + len(MISSING_ENTRIES)
+
+    name_matches = []
+    position = 1
+    for ele in data:
+        matches = process.extract(ele, zen_names, scorer=fuzz.token_sort_ratio,
+                                  limit=2)
+        # matches is a list [('First match', % Match), ('Second match', % Match)]
+        if matches[0][1] > 80:
+            val = zenodo['creators'][zen_names.index(matches[0][0])]
+        else:
+            # skip unmatched names
+            print("No entry to sort:", ele)
+            continue
+
+        if val not in name_matches:
+            if val['name'] not in CREATORS_LAST:
+                val['position'] = position
+                position += 1
+            else:
+                val['position'] = total_names + CREATORS_LAST.index(val['name'])
+            name_matches.append(val)
+
+    for missing in MISSING_ENTRIES:
+        missing['position'] = position
+        position += 1
+        name_matches.append(missing)
+
+    zenodo['creators'] = sorted(name_matches, key=lambda k: k['position'])
+    # Remove position
+    for creator in zenodo['creators']:
+        del creator['position']
+
+    zenodo_file.write_text('%s\n' % json.dumps(zenodo, indent=2, sort_keys=True))

.zenodo.json

@@ -1,18 +1,33 @@
-
 {
-  "title": "dMRIPrep: a robust preprocessing pipeline for diffusion MRI",
-  "description": "<p>dMRIPrep is a robust and easy-to-use pipeline for preprocessing of diverse dMRI data. The transparent workflow dispenses of manual intervention, thereby ensuring the reproducibility of the results.</p>",
-  "creators": [
+  "contributors": [
     {
-      "affiliation": "The University of Washington eScience Institute",
-      "name": "Keshavan, Anisha",
-      "orcid": "0000-0003-3554-043X"
+      "affiliation": "Department of Psychology, Stanford University, CA, USA",
+      "name": "Lerma-Usabiaga, Garikoitz",
+      "orcid": "0000-0001-9800-4816",
+      "type": "Researcher"
+    },
+    {
+      "name": "nrajamani3",
+      "type": "Researcher"
     },
+    {
+      "affiliation": "Department of Psychology, Stanford University",
+      "name": "Poldrack, Russell A.",
+      "orcid": "0000-0001-6755-0259",
+      "type": "Researcher"
+    }
+  ],
+  "creators": [
     {
       "affiliation": "The University of Washington eScience Institute",
       "name": "Richie-Halford, Adam",
       "orcid": "0000-0001-9276-9084"
     },
+    {
+      "affiliation": "The University of Washington eScience Institute",
+      "name": "Keshavan, Anisha",
+      "orcid": "0000-0003-3554-043X"
+    },
     {
       "affiliation": "The Centre for Addiction and Mental Health",
       "name": "Joseph, Michael",
@@ -29,24 +44,7 @@
       "orcid": "0000-0001-8435-6191"
     }
   ],
-  "contributors": [
-    {
-      "affiliation": "Department of Psychology, Stanford University, CA, USA",
-      "name": "Lerma-Usabiaga, Garikoitz",
-      "orcid": "0000-0001-9800-4816",
-      "type": "Researcher"
-    },
-    {
-      "name": "nrajamani3",
-      "type": "Researcher"
-    },
-    {
-      "name": "Poldrack, Russell A.",
-      "affiliation": "Department of Psychology, Stanford University",
-      "orcid": "0000-0001-6755-0259",
-      "type": "Researcher"
-    },
-  ],
+  "description": "<p>dMRIPrep is a robust and easy-to-use pipeline for preprocessing of diverse dMRI data. The transparent workflow dispenses of manual intervention, thereby ensuring the reproducibility of the results.</p>",
   "keywords": [
     "neuroimaging",
     "workflow",
@@ -68,5 +66,6 @@
       "scheme": "doi"
     }
   ],
+  "title": "dMRIPrep: a robust preprocessing pipeline for diffusion MRI",
   "upload_type": "software"
 }