aboutsummaryrefslogtreecommitdiffstats
path: root/fuzzycat/verify.py
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@archive.org>2021-07-01 16:26:13 -0700
committerBryan Newbold <bnewbold@archive.org>2021-07-01 16:26:13 -0700
commit839c4e7f3187b4eed4b5adbb9212a9a9456bf16f (patch)
tree0dd014ce688fd70a36be602582d4ac54e2b8b3af /fuzzycat/verify.py
parentb625155d565367141f7fbe0d5e507b9dc98ce4df (diff)
downloadfuzzycat-839c4e7f3187b4eed4b5adbb9212a9a9456bf16f.tar.gz
fuzzycat-839c4e7f3187b4eed4b5adbb9212a9a9456bf16f.zip
DOI clean/normalize helper; and use in verification etc
Diffstat (limited to 'fuzzycat/verify.py')
-rw-r--r--fuzzycat/verify.py6
1 files changed, 3 insertions, 3 deletions
diff --git a/fuzzycat/verify.py b/fuzzycat/verify.py
index f32121d..1eeea40 100644
--- a/fuzzycat/verify.py
+++ b/fuzzycat/verify.py
@@ -92,7 +92,7 @@ from fuzzycat.data import (CONTAINER_NAME_BLACKLIST, PUBLISHER_BLACKLIST, TITLE_
from fuzzycat.entities import entity_to_dict
from fuzzycat.utils import (author_similarity_score, contains_chemical_formula, dict_key_exists,
doi_prefix, has_doi_prefix, jaccard, num_project, parse_page_string,
- slugify_string)
+ slugify_string, clean_doi)
Verify = collections.namedtuple("Verify", "status reason")
@@ -167,8 +167,8 @@ def verify(a: Dict, b: Dict, min_title_length=5) -> Tuple[str, str]:
# A few items have the same DOI.
try:
- a_doi = glom(a, "ext_ids.doi")
- b_doi = glom(b, "ext_ids.doi")
+ a_doi = clean_doi(glom(a, "ext_ids.doi"))
+ b_doi = clean_doi(glom(b, "ext_ids.doi"))
if a_doi is not None and a_doi == b_doi:
return Verify(Status.EXACT, Reason.DOI)
except PathAccessError: