Merge branch 'martin-datacite-import'

Pipfile.lock is broken.

* martin-datacite-import: (68 commits)
  datacite: pass in doi into factored out method
  datacite: reformat test cases and use jq . --sort-keys
  datacite: factor out contributor handling
  datacite: catch type mismatch in language detection
  datacite: adjust tests for release_month
  datacite: name extra.month, extra.release_month
  datacite: mark additional files as stub
  datacite: CCDC are entries, mostly
  datacite: use more specific release_type, if possible
  datacite: ignore certain names
  datacite: over 3% records have the same title: stub
  datacite: fill a few more release_type gaps
  datacite: adding datacite-specific extra metadata
  datacite: apply pylint suggestions
  datacite: fix typos
  datacite: set release_stage to published by default
  datacite: month field should be top-level
  datacite: include month in extra
  datacite: indicate mismatched file in test
  datacite: clean abstracts, use unknown value tokens
  ...

1 files changed, 166 insertions, 0 deletions

diff --git a/python/tests/files/datacite/datacite_doc_14.json b/python/tests/files/datacite/datacite_doc_14.json
new file mode 100644
index 00000000..c0911819
--- /dev/null
+++ b/python/tests/files/datacite/datacite_doc_14.json
@@ -0,0 +1,166 @@
+{
+  "attributes": {
+    "container": {},
+    "contentUrl": null,
+    "contributors": [],
+    "created": "2014-03-18T07:28:28.000Z",
+    "creators": [
+      {
+        "affiliation": [],
+        "familyName": "Stulz",
+        "givenName": "E.",
+        "name": "Stulz, E.",
+        "nameType": "Personal"
+      },
+      {
+        "affiliation": [],
+        "familyName": "Scott",
+        "givenName": "S.M.",
+        "name": "Scott, S.M.",
+        "nameType": "Personal"
+      },
+      {
+        "affiliation": [],
+        "familyName": "Ng",
+        "givenName": "Yiu-Fai",
+        "name": "Ng, Yiu-Fai",
+        "nameType": "Personal"
+      },
+      {
+        "affiliation": [],
+        "familyName": "Bond",
+        "givenName": "A.D.",
+        "name": "Bond, A.D.",
+        "nameType": "Personal"
+      },
+      {
+        "affiliation": [],
+        "familyName": "Teat",
+        "givenName": "S.J.",
+        "name": "Teat, S.J.",
+        "nameType": "Personal"
+      },
+      {
+        "affiliation": [],
+        "familyName": "Darling",
+        "givenName": "S.L.",
+        "name": "Darling, S.L.",
+        "nameType": "Personal"
+      },
+      {
+        "affiliation": [],
+        "familyName": "Feeder",
+        "givenName": "N.",
+        "name": "Feeder, N.",
+        "nameType": "Personal"
+      },
+      {
+        "affiliation": [],
+        "familyName": "Sanders",
+        "givenName": "J.K.M.",
+        "name": "Sanders, J.K.M.",
+        "nameType": "Personal"
+      }
+    ],
+    "dates": [
+      {
+        "date": "2004",
+        "dateType": "Issued"
+      }
+    ],
+    "descriptions": [
+      {
+        "description": "Related Article: E.Stulz, S.M.Scott, Yiu-Fai Ng, A.D.Bond, S.J.Teat, S.L.Darling, N.Feeder, J.K.M.Sanders|2003|Inorg.Chem.|42|6564|doi:10.1021/ic034699w",
+        "descriptionType": "Other"
+      },
+      {
+        "description": "An entry from the Cambridge Structural Database, the world’s repository for small molecule crystal structures. The entry contains experimental data from a crystal diffraction study. The deposited dataset for this entry is freely available from the CCDC and typically includes 3D coordinates, cell parameters, space group, experimental conditions and quality measures.",
+        "descriptionType": "Abstract"
+      }
+    ],
+    "doi": "10.5517/cc7gns3",
+    "formats": [
+      "CIF"
+    ],
+    "fundingReferences": [],
+    "geoLocations": [],
+    "identifiers": [
+      {
+        "identifier": "https://doi.org/10.5517/cc7gns3",
+        "identifierType": "DOI"
+      },
+      {
+        "identifier": "222635",
+        "identifierType": "CCDC"
+      }
+    ],
+    "isActive": true,
+    "language": "eng",
+    "metadataVersion": 2,
+    "publicationYear": 2004,
+    "published": "2004",
+    "publisher": "Cambridge Crystallographic Data Centre",
+    "reason": null,
+    "registered": "2014-03-18T07:28:29.000Z",
+    "relatedIdentifiers": [
+      {
+        "relatedIdentifier": "10.1021/ic034699w",
+        "relatedIdentifierType": "DOI",
+        "relationType": "IsSupplementTo"
+      }
+    ],
+    "rightsList": [],
+    "schemaVersion": "http://datacite.org/schema/kernel-3",
+    "sizes": [],
+    "source": null,
+    "state": "findable",
+    "subjects": [
+      {
+        "subject": "Crystal Structure"
+      },
+      {
+        "subject": "Experimental 3D Coordinates"
+      },
+      {
+        "subject": "Crystal System"
+      },
+      {
+        "subject": "Space Group"
+      },
+      {
+        "subject": "Cell Parameters"
+      },
+      {
+        "subject": "Crystallography"
+      },
+      {
+        "subject": "bis(mu~2~-5-(3,5-Di-t-butylphenyl)-15-(4-(2-(diphenylphosphino)ethynyl)phenyl)-2,8,12,18-tetrahexyl-3,7,13,17-tetramethylporphyrinato)-(5,15-bis(3,5-di-t-butylphenyl)-2,8,12,18-tetraethyl-3,7,13,17-tetramethylporphyrinato)-di-nickel-ruthenium chloroform solvate"
+      }
+    ],
+    "titles": [
+      {
+        "title": "CCDC 222635: Experimental Crystal Structure Determination"
+      }
+    ],
+    "types": {
+      "bibtex": "misc",
+      "citeproc": "dataset",
+      "resourceTypeGeneral": "Dataset",
+      "ris": "DATA",
+      "schemaOrg": "Dataset"
+    },
+    "updated": "2019-08-02T03:38:32.000Z",
+    "url": "http://www.ccdc.cam.ac.uk/services/structure_request?id=doi:10.5517/cc7gns3&sid=DataCite",
+    "version": null
+  },
+  "id": "10.5517/cc7gns3",
+  "relationships": {
+    "client": {
+      "data": {
+        "id": "ccdc.csd",
+        "type": "clients"
+      }
+    }
+  },
+  "type": "dois"
+}