1
0
mirror of https://github.com/ilri/csv-metadata-quality.git synced 2024-12-26 14:04:29 +01:00

data/test.csv: Add test case for uncommon filename extension

This commit is contained in:
Alan Orth 2019-08-10 23:46:56 +03:00
parent e801042340
commit a99fbd8a51
Signed by: alanorth
GPG Key ID: 0FB860CC9C45B1B9

View File

@ -1,23 +1,24 @@
dc.contributor.author,birthdate,dc.identifier.issn,dc.identifier.isbn,dc.language.iso,dc.subject,cg.coverage.country
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 639-2 language,2019-07-29,,,jp,,
Invalid ISO 639-3 language,2019-07-29,,,chi,,
Invalid language,2019-07-29,,,Span,,
Invalid AGROVOC subject,2019-07-29,,,,FOREST,
dc.contributor.author,birthdate,dc.identifier.issn,dc.identifier.isbn,dc.language.iso,dc.subject,cg.coverage.country,filename
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 639-2 language,2019-07-29,,,jp,,,
Invalid ISO 639-3 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
NIA",,
Missing date,,,,,,,
Invalid country,2019-08-01,,,,,KENYAA,
Uncommon filename extension,2019-08-10,,,,,,file.pdf.lck

1 dc.contributor.author birthdate dc.identifier.issn dc.identifier.isbn dc.language.iso dc.subject cg.coverage.country filename
2 Leading space 2019-07-29
3 Trailing space 2019-07-29
4 Excessive space 2019-07-29
5 Miscellaenous ||whitespace | issues 2019-07-29
6 Duplicate||Duplicate 2019-07-29
7 Invalid ISSN 2019-07-29 2321-2302
8 Invalid ISBN 2019-07-29 978-0-306-40615-6
9 Multiple valid ISSNs 2019-07-29 0378-5955||0024-9319
10 Multiple valid ISBNs 2019-07-29 99921-58-10-7||978-0-306-40615-7
11 Invalid date 2019-07-260
12 Multiple dates 2019-07-26||2019-01-10
13 Invalid multi-value separator 2019-07-29 0378-5955|0024-9319
14 Unnecessary Unicode​ 2019-07-29
15 Suspicious character||foreˆt 2019-07-29
16 Invalid ISO 639-2 language 2019-07-29 jp
17 Invalid ISO 639-3 language 2019-07-29 chi
18 Invalid language 2019-07-29 Span
19 Invalid AGROVOC subject 2019-07-29 FOREST
20 Newline (LF) 2019-07-30 TANZA NIA
21 Missing date
22 Invalid country 2019-08-01 KENYAA
23 Uncommon filename extension 2019-08-10 file.pdf.lck
24