summaryrefslogtreecommitdiffstats
path: root/python/fatcat_tools/importers/matched.py
diff options
context:
space:
mode:
Diffstat (limited to 'python/fatcat_tools/importers/matched.py')
-rw-r--r--python/fatcat_tools/importers/matched.py10
1 files changed, 8 insertions, 2 deletions
diff --git a/python/fatcat_tools/importers/matched.py b/python/fatcat_tools/importers/matched.py
index 774019c7..732fccbe 100644
--- a/python/fatcat_tools/importers/matched.py
+++ b/python/fatcat_tools/importers/matched.py
@@ -4,7 +4,7 @@ import json
import sqlite3
import itertools
import fatcat_client
-from fatcat_tools.importers.common import FatcatImporter
+from .common import FatcatImporter
#row = row.split('\t')
#assert len(row) == 2
@@ -13,8 +13,14 @@ from fatcat_tools.importers.common import FatcatImporter
#print(sha1)
#dois = [d.lower() for d in json.loads(row[1])]
-class FatcatMatchedImporter(FatcatImporter):
+class MatchedImporter(FatcatImporter):
"""
+ Importer for "file to crossref DOI" matches.
+
+ These matches are currently generated by Internet Archive hadoop jobs
+ written in scala (part of the 'sandcrawler' repo/project), but could be
+ generated by other parties as well.
+
Input format is JSON with keys:
- dois (list)
- sha1 (hex)