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, 114 insertions, 0 deletions

diff --git a/python/tests/files/datacite/datacite_result_14.json b/python/tests/files/datacite/datacite_result_14.json
new file mode 100644
index 00000000..2ce68d29
--- /dev/null
+++ b/python/tests/files/datacite/datacite_result_14.json
@@ -0,0 +1,114 @@
+{
+  "abstracts": [
+    {
+      "content": "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.",
+      "lang": "en",
+      "mimetype": "text/plain"
+    }
+  ],
+  "contribs": [
+    {
+      "given_name": "E.",
+      "index": 0,
+      "raw_name": "E. Stulz",
+      "role": "author",
+      "surname": "Stulz"
+    },
+    {
+      "given_name": "S.M.",
+      "index": 1,
+      "raw_name": "S.M. Scott",
+      "role": "author",
+      "surname": "Scott"
+    },
+    {
+      "given_name": "Yiu-Fai",
+      "index": 2,
+      "raw_name": "Yiu-Fai Ng",
+      "role": "author",
+      "surname": "Ng"
+    },
+    {
+      "given_name": "A.D.",
+      "index": 3,
+      "raw_name": "A.D. Bond",
+      "role": "author",
+      "surname": "Bond"
+    },
+    {
+      "given_name": "S.J.",
+      "index": 4,
+      "raw_name": "S.J. Teat",
+      "role": "author",
+      "surname": "Teat"
+    },
+    {
+      "given_name": "S.L.",
+      "index": 5,
+      "raw_name": "S.L. Darling",
+      "role": "author",
+      "surname": "Darling"
+    },
+    {
+      "given_name": "N.",
+      "index": 6,
+      "raw_name": "N. Feeder",
+      "role": "author",
+      "surname": "Feeder"
+    },
+    {
+      "given_name": "J.K.M.",
+      "index": 7,
+      "raw_name": "J.K.M. Sanders",
+      "role": "author",
+      "surname": "Sanders"
+    }
+  ],
+  "ext_ids": {
+    "doi": "10.5517/cc7gns3"
+  },
+  "extra": {
+    "datacite": {
+      "metadataVersion": 2,
+      "relations": [
+        {
+          "relatedIdentifier": "10.1021/ic034699w",
+          "relatedIdentifierType": "DOI",
+          "relationType": "IsSupplementTo"
+        }
+      ],
+      "resourceTypeGeneral": "Dataset",
+      "schemaVersion": "http://datacite.org/schema/kernel-3",
+      "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"
+        }
+      ]
+    }
+  },
+  "language": "en",
+  "publisher": "Cambridge Crystallographic Data Centre",
+  "refs": [],
+  "release_stage": "published",
+  "release_type": "entry",
+  "release_year": 2004,
+  "title": "CCDC 222635: Experimental Crystal Structure Determination"
+}