diff options
author | Bryan Newbold <bnewbold@robocracy.org> | 2018-09-22 17:30:21 -0700 |
---|---|---|
committer | Bryan Newbold <bnewbold@robocracy.org> | 2018-09-22 17:30:21 -0700 |
commit | 2eedc871a71e83b126f98ca5915a463a8cd50ccc (patch) | |
tree | 4864e3aeca4673ff2bbea53e157d9de853e33e98 /extra/elasticsearch/transform_release.py | |
parent | 526fe297375b8e5efaffdcb936e6d1f0217d5b1a (diff) | |
download | fatcat-2eedc871a71e83b126f98ca5915a463a8cd50ccc.tar.gz fatcat-2eedc871a71e83b126f98ca5915a463a8cd50ccc.zip |
update elastic schema and transform
Diffstat (limited to 'extra/elasticsearch/transform_release.py')
-rwxr-xr-x | extra/elasticsearch/transform_release.py | 19 |
1 files changed, 12 insertions, 7 deletions
diff --git a/extra/elasticsearch/transform_release.py b/extra/elasticsearch/transform_release.py index 30449e18..2f67977e 100755 --- a/extra/elasticsearch/transform_release.py +++ b/extra/elasticsearch/transform_release.py @@ -26,18 +26,19 @@ def transform(m): ) container = m.get('container') + container_is_kept = False if container: t['publisher'] = countainer.get('publisher') - t['container_title'] = countainer.get('title') + t['container_name'] = countainer.get('name') t['container_issnl'] = countainer.get('issnl') container_extra = container.get('extra') if container_extra: t['container_is_oa'] = container_extra.get('is_oa') - t['container_is_kept'] = container_extra.get('is_kept') + container_is_kept = container_extra.get('is_kept', False) t['container_is_longtail_oa'] = container_extra.get('is_longtail_oa') else: t['publisher'] = m.get('publisher') - t['container_title'] = m.get('container_title') + t['container_name'] = m.get('container_name') files = m.get('files', []) t['file_count'] = len(files) @@ -62,11 +63,15 @@ def transform(m): if extra: t['in_shadow'] = extra.get('in_shadow') t['any_abstract'] = bool(t.get('abstracts')) + t['is_kept'] = container_is_kept or extra.get('is_kept', False) - author_names = [] - for contrib in m.get('contribs', []): - if contrib.get('raw_name'): - author_names.append(contrib.get('raw_name')) + t['ref_count'] = len(m.get('refs', [])) + t['contrib_count'] = len(m.get('contribs', [])) + contrib_names = [] + for c in m.get('contribs', []): + if c.get('raw_name'): + contrib_names.append(c.get('raw_name')) + t['contrib_names'] = contrib_names return t def run(): |