From a4eb79f6258100c2b02abf94b5cd67f4883b3268 Mon Sep 17 00:00:00 2001 From: Alan Orth Date: Wed, 8 Dec 2021 15:17:55 +0200 Subject: [PATCH] data/test.csv: add data for countries without regions check --- data/test.csv | 73 ++++++++++++++++++++++++++------------------------- 1 file changed, 37 insertions(+), 36 deletions(-) diff --git a/data/test.csv b/data/test.csv index 2fe7a38..7bed091 100644 --- a/data/test.csv +++ b/data/test.csv @@ -1,37 +1,38 @@ -dc.title,dcterms.issued,dc.identifier.issn,dc.identifier.isbn,dcterms.language,dcterms.subject,cg.coverage.country,filename,dcterms.license,dcterms.type,dcterms.bibliographicCitation,cg.identifier.doi - Leading space,2019-07-29,,,,,,,,,, -Trailing space ,2019-07-29,,,,,,,,,, -Excessive space,2019-07-29,,,,,,,,,, -Miscellaenous ||whitespace | issues ,2019-07-29,,,,,,,,,, -Duplicate||Duplicate,2019-07-29,,,,,,,,,, -Invalid ISSN,2019-07-29,2321-2302,,,,,,,,, -Invalid ISBN,2019-07-29,,978-0-306-40615-6,,,,,,,, -Multiple valid ISSNs,2019-07-29,0378-5955||0024-9319,,,,,,,,, -Multiple valid ISBNs,2019-07-29,,99921-58-10-7||978-0-306-40615-7,,,,,,,, -Invalid date,2019-07-260,,,,,,,,,, -Multiple dates,2019-07-26||2019-01-10,,,,,,,,,, -Invalid multi-value separator,2019-07-29,0378-5955|0024-9319,,,,,,,,, -Unnecessary Unicode​,2019-07-29,,,,,,,,,, -Suspicious character||foreˆt,2019-07-29,,,,,,,,,, -Invalid ISO 639-1 (alpha 2) language,2019-07-29,,,jp,,,,,,, -Invalid ISO 639-3 (alpha 3) language,2019-07-29,,,chi,,,,,,, -Invalid language,2019-07-29,,,Span,,,,,,, -Invalid AGROVOC subject,2019-07-29,,,,FOREST,,,,,, +dc.title,dcterms.issued,dc.identifier.issn,dc.identifier.isbn,dcterms.language,dcterms.subject,cg.coverage.country,filename,dcterms.license,dcterms.type,dcterms.bibliographicCitation,cg.identifier.doi,cg.coverage.region + Leading space,2019-07-29,,,,,,,,,,, +Trailing space ,2019-07-29,,,,,,,,,,, +Excessive space,2019-07-29,,,,,,,,,,, +Miscellaenous ||whitespace | issues ,2019-07-29,,,,,,,,,,, +Duplicate||Duplicate,2019-07-29,,,,,,,,,,, +Invalid ISSN,2019-07-29,2321-2302,,,,,,,,,, +Invalid ISBN,2019-07-29,,978-0-306-40615-6,,,,,,,,, +Multiple valid ISSNs,2019-07-29,0378-5955||0024-9319,,,,,,,,,, +Multiple valid ISBNs,2019-07-29,,99921-58-10-7||978-0-306-40615-7,,,,,,,,, +Invalid date,2019-07-260,,,,,,,,,,, +Multiple dates,2019-07-26||2019-01-10,,,,,,,,,,, +Invalid multi-value separator,2019-07-29,0378-5955|0024-9319,,,,,,,,,, +Unnecessary Unicode​,2019-07-29,,,,,,,,,,, +Suspicious character||foreˆt,2019-07-29,,,,,,,,,,, +Invalid ISO 639-1 (alpha 2) language,2019-07-29,,,jp,,,,,,,, +Invalid ISO 639-3 (alpha 3) language,2019-07-29,,,chi,,,,,,,, +Invalid language,2019-07-29,,,Span,,,,,,,, +Invalid AGROVOC subject,2019-07-29,,,,FOREST,,,,,,, Newline (LF),2019-07-30,,,,"TANZA -NIA",,,,,, -Missing date,,,,,,,,,,, -Invalid country,2019-08-01,,,,,KENYAA,,,,, -Uncommon filename extension,2019-08-10,,,,,,file.pdf.lck,,,, -Unneccesary unicode (U+002D + U+00AD),2019-08-10,,978-­92-­9043-­823-­6,,,,,,,, -"Missing space,after comma",2019-08-27,,,,,,,,,, -Incorrect ISO 639-1 language,2019-09-26,,,es,,,,,,, -Incorrect ISO 639-3 language,2019-09-26,,,spa,,,,,,, -Composéd Unicode,2020-01-14,,,,,,,,,, -Decomposéd Unicode,2020-01-14,,,,,,,,,, -Unnecessary multi-value separator,2021-01-03,0378-5955||,,,,,,,,, -Invalid SPDX license identifier,2021-03-11,,,,,,,CC-BY,,, -Duplicate Title,2021-03-17,,,,,,,,Report,, -Duplicate Title,2021-03-17,,,,,,,,Report,, -Mojibake,2021-03-18,,,,Publicaçao CIAT,,,,Report,, -"DOI in citation, but missing cg.identifier.doi",2021-10-06,,,,,,,,,"Orth, A. 2021. DOI in citation, but missing cg.identifier.doi. doi: 10.1186/1743-422X-9-218", -Title missing from citation,2021-12-05,,,,,,,,,"Orth, A. 2021. Title missing f rom citation.", +NIA",,,,,,, +Missing date,,,,,,,,,,,, +Invalid country,2019-08-01,,,,,KENYAA,,,,,, +Uncommon filename extension,2019-08-10,,,,,,file.pdf.lck,,,,, +Unneccesary unicode (U+002D + U+00AD),2019-08-10,,978-­92-­9043-­823-­6,,,,,,,,, +"Missing space,after comma",2019-08-27,,,,,,,,,,, +Incorrect ISO 639-1 language,2019-09-26,,,es,,,,,,,, +Incorrect ISO 639-3 language,2019-09-26,,,spa,,,,,,,, +Composéd Unicode,2020-01-14,,,,,,,,,,, +Decomposéd Unicode,2020-01-14,,,,,,,,,,, +Unnecessary multi-value separator,2021-01-03,0378-5955||,,,,,,,,,, +Invalid SPDX license identifier,2021-03-11,,,,,,,CC-BY,,,, +Duplicate Title,2021-03-17,,,,,,,,Report,,, +Duplicate Title,2021-03-17,,,,,,,,Report,,, +Mojibake,2021-03-18,,,,Publicaçao CIAT,,,,Report,,, +"DOI in citation, but missing cg.identifier.doi",2021-10-06,,,,,,,,,"Orth, A. 2021. DOI in citation, but missing cg.identifier.doi. doi: 10.1186/1743-422X-9-218",, +Title missing from citation,2021-12-05,,,,,,,,,"Orth, A. 2021. Title missing f rom citation.",, +Country missing region,2021-12-08,,,,,Kenya,,,,,,