diff options
| author | Bryan Newbold <bnewbold@robocracy.org> | 2019-06-27 10:38:29 -0700 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@robocracy.org> | 2019-06-27 10:38:29 -0700 |
| commit | 847304be39c01ab7ca82dbc81ef92c1459e0ed23 (patch) | |
| tree | 916e90fc1afe261b82a867999e86e99a75151de4 | |
| parent | c2928f8f973be85fc74419e7d574905168937b0a (diff) | |
| download | fatcat-847304be39c01ab7ca82dbc81ef92c1459e0ed23.tar.gz fatcat-847304be39c01ab7ca82dbc81ef92c1459e0ed23.zip | |
finish fixup_longtail_issnl_unique; but not going to run it
| -rwxr-xr-x | extra/fixups/fixup_longtail_issnl_unique.py | 7 |
1 files changed, 3 insertions, 4 deletions
diff --git a/extra/fixups/fixup_longtail_issnl_unique.py b/extra/fixups/fixup_longtail_issnl_unique.py index 7c492fc3..2493a332 100755 --- a/extra/fixups/fixup_longtail_issnl_unique.py +++ b/extra/fixups/fixup_longtail_issnl_unique.py @@ -7,7 +7,7 @@ quickly. There are no tests. Example invocation: - zcat 2018-09-23-0405.30-dumpgrobidmetainsertable.longtail_join.filtered.tsv.gz | ./fixup_longtail_issnl_unique.py /srv/fatcat/datasets/single_domain_issnl.tsv - + zcat /srv/fatcat/datasets/2018-09-23-0405.30-dumpgrobidmetainsertable.longtail_join.filtered.tsv.gz | ./fixup_longtail_issnl_unique.py /srv/fatcat/datasets/single_domain_issnl.tsv - See also: - bnewbold/scratch:mellon/201904_longtail_issn.md @@ -108,7 +108,7 @@ class LongtailIssnlSingleDomainFixup(EntityImporter): return None # lookup file - print(sha1) + #print(sha1) try: file_entity = self.api.lookup_file(sha1=sha1) except fatcat_client.rest.ApiException as err: @@ -119,8 +119,7 @@ class LongtailIssnlSingleDomainFixup(EntityImporter): raise err # container ident - # TODO: memoize these issnl/container lookups - container_id = self.lookup_container(issnl) + container_id = self.lookup_issnl(issnl) if not container_id: self.counts['skip-container-not-found'] += 1 return None |