chore: copy zenodo/papers update scripts [skip ci]

Author: oesteban

.maint/contributors.json

@@ -0,0 +1,20 @@
+[
+  {
+    "affiliation": "Perelman School of Medicine, University of Pennsylvania, PA, USA",
+    "name": "Cieslak, Matthew",
+    "orcid": "0000-0002-1931-4734",
+    "type": "Researcher"
+  },
+  {
+    "affiliation": "Neuroscience Program, University of Iowa",
+    "name": "Kent, James D.",
+    "orcid": "0000-0002-4892-2659",
+    "type": "Researcher"
+  },
+  {
+    "affiliation": "Department of Psychology, Stanford University",
+    "name": "Poldrack, Russell A.",
+    "orcid": "0000-0001-6755-0259",
+    "type": "Researcher"
+  }
+]

.maint/developers.json

@@ -0,0 +1,37 @@
+[
+  {
+    "affiliation": "Dep. of Radiology, Lausanne University Hospital and University of Lausanne",
+    "name": "Esteban, Oscar",
+    "orcid": "0000-0001-8435-6191"
+  },
+  {
+    "affiliation": "The Centre for Addiction and Mental Health",
+    "name": "Joseph, Michael",
+    "orcid": "0000-0002-0068-230X"
+  },
+  {
+    "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"
+  },
+  {
+    "affiliation": "Department of Psychology, University of Texas at Austin, TX, USA",
+    "name": "Pisner, Derek",
+    "orcid": "0000-0002-1228-0201"
+  },
+  {
+    "affiliation": "The University of Washington, eScience Institute",
+    "name": "Richie-Halford, Adam",
+    "orcid": "0000-0001-9276-9084"
+  },
+  {
+    "affiliation": "The University of Washington eScience Institute",
+    "name": "Rokem, Ariel",
+    "orcid": "0000-0003-0679-1985"
+  }
+]

.maint/former.json

@@ -0,0 +1,5 @@
+[
+  {
+    "name": "nrajamani3"
+  }
+]

.maint/paper_author_list.py

@@ -0,0 +1,49 @@
+#!/usr/bin/env python3
+"""Generate an author list for a new paper or abstract."""
+import sys
+from pathlib import Path
+import json
+from update_zenodo import get_git_lines, sort_contributors
+
+
+# These authors should go last
+AUTHORS_LAST = ['Rokem, Ariel', 'Esteban, Oscar']
+
+
+def _aslist(inlist):
+    if not isinstance(inlist, list):
+        return [inlist]
+    return inlist
+
+
+if __name__ == '__main__':
+    devs = json.loads(Path('.maint/developers.json').read_text())
+    contribs = json.loads(Path('.maint/contributors.json').read_text())
+
+    author_matches, unmatched = sort_contributors(
+        devs + contribs, get_git_lines(),
+        exclude=json.loads(Path('.maint/former.json').read_text()),
+        last=AUTHORS_LAST)
+    # Remove position
+    affiliations = []
+    for item in author_matches:
+        del item['position']
+        for a in _aslist(item.get('affiliation', 'Unaffiliated')):
+            if a not in affiliations:
+                affiliations.append(a)
+
+    aff_indexes = [', '.join(['%d' % (affiliations.index(a) + 1)
+                              for a in _aslist(author.get('affiliation', 'Unaffiliated'))])
+                   for author in author_matches]
+
+    print("Some people made commits, but are missing in .maint/ "
+          "files: %s." % ', '.join(unmatched), file=sys.stderr)
+
+    print('Authors (%d):' % len(author_matches))
+    print("%s." % '; '.join([
+        '%s \\ :sup:`%s`\\ ' % (i['name'], idx)
+        for i, idx in zip(author_matches, aff_indexes)
+    ]))
+
+    print('\n\nAffiliations:\n%s' % '\n'.join(['{0: >2}. {1}'.format(i + 1, a)
+                                               for i, a in enumerate(affiliations)]))

.maintenance/update_changes.sh renamed to .maint/update_changes.sh

@@ -0,0 +1,121 @@
+#!/usr/bin/env python3
+"""Update and sort the creators list of the zenodo record."""
+import sys
+from pathlib import Path
+import json
+from fuzzywuzzy import fuzz, process
+
+# These ORCIDs should go last
+CREATORS_LAST = ['Rokem, Ariel', 'Esteban, Oscar']
+CONTRIBUTORS_LAST = ['Poldrack, Russell A.']
+
+
+def sort_contributors(entries, git_lines, exclude=None, last=None):
+    """Return a list of author dictionaries, ordered by contribution."""
+    last = last or []
+    sorted_authors = sorted(entries, key=lambda i: i['name'])
+
+    first_last = [' '.join(val['name'].split(',')[::-1]).strip()
+                  for val in sorted_authors]
+    first_last_excl = [' '.join(val['name'].split(',')[::-1]).strip()
+                       for val in exclude or []]
+
+    unmatched = []
+    author_matches = []
+    position = 1
+    for ele in git_lines:
+        matches = process.extract(ele, first_last, scorer=fuzz.token_sort_ratio,
+                                  limit=2)
+        # matches is a list [('First match', % Match), ('Second match', % Match)]
+        if matches[0][1] > 80:
+            val = sorted_authors[first_last.index(matches[0][0])]
+        else:
+            # skip unmatched names
+            if ele not in first_last_excl:
+                unmatched.append(ele)
+            continue
+
+        if val not in author_matches:
+            val['position'] = position
+            author_matches.append(val)
+            position += 1
+
+    names = {' '.join(val['name'].split(',')[::-1]).strip() for val in author_matches}
+    for missing_name in first_last:
+        if missing_name not in names:
+            missing = sorted_authors[first_last.index(missing_name)]
+            missing['position'] = position
+            author_matches.append(missing)
+            position += 1
+
+    all_names = [val['name'] for val in author_matches]
+    for last_author in last:
+        author_matches[all_names.index(last_author)]['position'] = position
+        position += 1
+
+    author_matches = sorted(author_matches, key=lambda k: k['position'])
+
+    return author_matches, unmatched
+
+
+def get_git_lines(fname='line-contributors.txt'):
+    """Run git-line-summary."""
+    import shutil
+    import subprocess as sp
+    contrib_file = Path(fname)
+
+    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 repo")
+        lines = sp.check_output([git_line_summary_path]).decode().splitlines()
+        lines = [l for l in lines if "Not Committed Yet" not in l]
+        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))
+    return [' '.join(line.strip().split()[1:-1]) for line in lines if '%' in line]
+
+
+if __name__ == '__main__':
+    data = get_git_lines()
+
+    zenodo_file = Path('.zenodo.json')
+    zenodo = json.loads(zenodo_file.read_text())
+
+    creators = json.loads(Path('.maint/developers.json').read_text())
+    zen_creators, miss_creators = sort_contributors(
+        creators, data,
+        exclude=json.loads(Path('.maint/former.json').read_text()),
+        last=CREATORS_LAST)
+    contributors = json.loads(Path('.maint/contributors.json').read_text())
+    zen_contributors, miss_contributors = sort_contributors(
+        contributors, data,
+        exclude=json.loads(Path('.maint/former.json').read_text()),
+        last=CONTRIBUTORS_LAST)
+    zenodo['creators'] = zen_creators
+    zenodo['contributors'] = zen_contributors
+
+    print("Some people made commits, but are missing in .maint/ "
+          "files: %s." % ', '.join(set(miss_creators).intersection(miss_contributors)),
+          file=sys.stderr)
+
+    # Remove position
+    for creator in zenodo['creators']:
+        del creator['position']
+        if isinstance(creator['affiliation'], list):
+            creator['affiliation'] = creator['affiliation'][0]
+
+    for creator in zenodo['contributors']:
+        creator['type'] = 'Researcher'
+        del creator['position']
+        if isinstance(creator['affiliation'], list):
+            creator['affiliation'] = creator['affiliation'][0]
+
+    zenodo_file.write_text('%s\n' % json.dumps(zenodo, indent=2))