From c9bfb0be4c7e38b6668f49588f2ffecee7b17912 Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Tue, 17 Nov 2020 18:38:06 -0800 Subject: handle more non-ASCII DOI cases --- python/fatcat_tools/normal.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'python/fatcat_tools') diff --git a/python/fatcat_tools/normal.py b/python/fatcat_tools/normal.py index 39927651..ed439225 100644 --- a/python/fatcat_tools/normal.py +++ b/python/fatcat_tools/normal.py @@ -62,7 +62,7 @@ def clean_doi(raw): # will likely want to expand DOI_REGEX to exclude non-ASCII characters, but # for now block specific characters so we can get PubMed importer running # again. - if 'ä' in raw or '\u200e' in raw: + if 'ä' in raw or 'á' in raw or '\u200e' in raw or '\u2043' in raw: return None return raw @@ -79,6 +79,8 @@ def test_clean_doi(): assert clean_doi("10.4149/gpb¬_2017042") == None # "logical negation" character assert clean_doi("10.6002/ect.2020.häyry") == None # this example via pubmed (pmid:32519616) assert clean_doi("10.30466/vrf.2019.98547.2350\u200e") == None + assert clean_doi("10.12016/j.issn.2096⁃1456.2017.06.014") == None + assert clean_doi("10.4025/diálogos.v17i2.36030") == None ARXIV_ID_REGEX = re.compile(r"^(\d{4}.\d{4,5}|[a-z\-]+(\.[A-Z]{2})?/\d{7})(v\d+)?$") -- cgit v1.2.3