diff options
| author | Bryan Newbold <bnewbold@robocracy.org> | 2019-01-28 18:11:13 -0800 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@robocracy.org> | 2019-01-28 18:11:13 -0800 |
| commit | 1aa68e94508559d88891d44182e61aba07f828f5 (patch) | |
| tree | 265fc101686f3b80c37d388ec707c0a5188b202e | |
| parent | 0a427dae89357bef0c45830b22b5f18e894747ba (diff) | |
| download | fatcat-1aa68e94508559d88891d44182e61aba07f828f5.tar.gz fatcat-1aa68e94508559d88891d44182e61aba07f828f5.zip | |
fix GROBID null/short abstract additions
| -rw-r--r-- | python/fatcat_tools/importers/grobid_metadata.py | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/python/fatcat_tools/importers/grobid_metadata.py b/python/fatcat_tools/importers/grobid_metadata.py index 84771083..28358959 100644 --- a/python/fatcat_tools/importers/grobid_metadata.py +++ b/python/fatcat_tools/importers/grobid_metadata.py @@ -79,7 +79,8 @@ class GrobidMetadataImporter(EntityImporter): extra_grobid = dict() - if obj.get('abstract') and len(obj.get('abstract')) < MAX_ABSTRACT_BYTES: + abstract = obj.get('abstract') + if abstract and len(abstract) < MAX_ABSTRACT_BYTES and len(abstract) > 10: abobj = dict( mimetype="text/plain", language=None, |