diff options
Diffstat (limited to 'python/fatcat_tools')
| -rw-r--r-- | python/fatcat_tools/importers/doaj_article.py | 11 |
1 files changed, 9 insertions, 2 deletions
diff --git a/python/fatcat_tools/importers/doaj_article.py b/python/fatcat_tools/importers/doaj_article.py index 03752484..191a65d8 100644 --- a/python/fatcat_tools/importers/doaj_article.py +++ b/python/fatcat_tools/importers/doaj_article.py @@ -217,9 +217,16 @@ class DoajArticleImporter(EntityImporter): return False break - # TODO: in the future could do fuzzy match here, eg using elasticsearch + if not existing and self.do_fuzzy_match: + fuzzy_result = self.match_existing_release_fuzzy(re) + # TODO: in the future, could assign work_id for clustering, or for + # "EXACT" match, set existing and allow (optional) update code path + # to run + if fuzzy_result is not None: + self.counts["exists-fuzzy"] += 1 + return False - # create entity + # if no fuzzy existing match, create entity if not existing: return True |