summaryrefslogtreecommitdiffstats
path: root/python/tests
diff options
context:
space:
mode:
Diffstat (limited to 'python/tests')
-rw-r--r--python/tests/api_annotations.py39
-rw-r--r--python/tests/api_containers.py48
-rw-r--r--python/tests/api_creators.py44
-rw-r--r--python/tests/api_editgroups.py140
-rw-r--r--python/tests/api_files.py52
-rw-r--r--python/tests/api_filesets.py79
-rw-r--r--python/tests/api_misc.py8
-rw-r--r--python/tests/api_releases.py103
-rw-r--r--python/tests/api_webcaptures.py96
-rw-r--r--python/tests/citation_efficiency.py113
-rwxr-xr-xpython/tests/cli.sh2
-rw-r--r--python/tests/files/crossref-works.single.json2
-rw-r--r--python/tests/fixtures.py30
-rw-r--r--python/tests/import_crossref.py47
-rw-r--r--python/tests/import_grobid_metadata.py30
-rw-r--r--python/tests/import_issn.py26
-rw-r--r--python/tests/import_journal_metadata.py39
-rw-r--r--python/tests/import_matched.py28
-rw-r--r--python/tests/import_orcid.py33
-rw-r--r--python/tests/importer.py34
-rw-r--r--python/tests/transform_tests.py2
21 files changed, 870 insertions, 125 deletions
diff --git a/python/tests/api_annotations.py b/python/tests/api_annotations.py
new file mode 100644
index 00000000..0d3c5046
--- /dev/null
+++ b/python/tests/api_annotations.py
@@ -0,0 +1,39 @@
+
+import json
+import pytest
+from copy import copy
+
+from fatcat_client import *
+from fatcat_client.rest import ApiException
+from fixtures import *
+
+
+def test_annotations(api):
+
+ eg = quick_eg(api)
+
+ # ensure no annotations on this object
+ a = api.get_editgroup_annotations(eg.editgroup_id)
+ assert a == []
+
+ # create an annotation!
+ api.create_editgroup_annotation(
+ eg.editgroup_id,
+ EditgroupAnnotation(
+ comment_markdown="some *annotation*",
+ extra=dict(thing="thang")))
+
+ # check that we can fetch it all sorts of ways
+ a = api.get_editgroup_annotations(eg.editgroup_id)
+ assert len(a) == 1
+ assert a[0].extra['thing'] == "thang"
+
+ # the editor persists, so this is a hack to find a "recent" one
+ a2 = api.get_editor_annotations(eg.editor_id, limit=100)
+ found = None
+ for thing in a2:
+ if thing.annotation_id == a[0].annotation_id:
+ found = thing
+ break
+ assert thing
+ assert thing.extra['thing'] == "thang"
diff --git a/python/tests/api_containers.py b/python/tests/api_containers.py
new file mode 100644
index 00000000..674ae3b8
--- /dev/null
+++ b/python/tests/api_containers.py
@@ -0,0 +1,48 @@
+
+import json
+import pytest
+from copy import copy
+
+from fatcat_client import *
+from fatcat_client.rest import ApiException
+from fixtures import *
+
+
+def test_container(api):
+ eg = quick_eg(api)
+
+ # all the fields!
+ c1 = ContainerEntity(
+ name="some container name",
+ container_type="journal",
+ publisher="some container publisher",
+ issnl="1234-567X",
+ wikidata_qid="Q954248",
+ extra=dict(a=1, b=2),
+ )
+
+ c1edit = api.create_container(c1, editgroup_id=eg.editgroup_id)
+ api.accept_editgroup(eg.editgroup_id)
+ c2 = api.get_container(c1edit.ident)
+
+ # check that fields match
+ assert c1.name == c2.name
+ assert c1.container_type == c2.container_type
+ assert c1.publisher == c2.publisher
+ assert c1.issnl == c2.issnl
+ assert c1.wikidata_qid == c2.wikidata_qid
+ assert c1.extra == c2.extra
+
+ # expansion
+ # TODO: via release
+ # lookup
+ # TODO: via issnl; but need to generate random identifiers
+
+def test_container_examples(api):
+
+ api.lookup_container(issnl='1549-1277')
+
+ c1 = api.get_container('aaaaaaaaaaaaaeiraaaaaaaaam')
+ assert c1.name == "PLOS Medicine"
+ assert c1.issnl == "1549-1277"
+
diff --git a/python/tests/api_creators.py b/python/tests/api_creators.py
new file mode 100644
index 00000000..7443675b
--- /dev/null
+++ b/python/tests/api_creators.py
@@ -0,0 +1,44 @@
+
+import json
+import pytest
+from copy import copy
+
+from fatcat_client import *
+from fatcat_client.rest import ApiException
+from fixtures import *
+
+
+def test_creators(api):
+ eg = quick_eg(api)
+
+ # all the fields!
+ c1 = CreatorEntity(
+ display_name="Emma Smith",
+ given_name="emma",
+ surname="smith",
+ orcid="0000-0002-1825-0097",
+ wikidata_qid="Q9542248",
+ extra=dict(a=1, b=5),
+ )
+
+ c1edit = api.create_creator(c1, editgroup_id=eg.editgroup_id)
+ api.accept_editgroup(eg.editgroup_id)
+ c2 = api.get_creator(c1edit.ident)
+
+ # check that fields match
+ assert c1.display_name == c2.display_name
+ assert c1.given_name == c2.given_name
+ assert c1.surname == c2.surname
+ assert c1.orcid == c2.orcid
+ assert c1.wikidata_qid == c2.wikidata_qid
+ assert c1.extra == c2.extra
+
+ # expansion
+ # TODO: via release
+ # lookup
+ # TODO: via issnl; but need to generate random identifiers
+
+def test_creators_examples(api):
+ # TODO: aaaaaaaaaaaaaircaaaaaaaaam
+
+ api.lookup_creator(orcid='0000-0003-3118-6859')
diff --git a/python/tests/api_editgroups.py b/python/tests/api_editgroups.py
new file mode 100644
index 00000000..722d8686
--- /dev/null
+++ b/python/tests/api_editgroups.py
@@ -0,0 +1,140 @@
+
+import json
+import pytest
+import datetime
+from copy import copy
+
+from fatcat_client import *
+from fatcat_client.rest import ApiException
+from fixtures import *
+
+
+def test_editgroup_submit(api):
+ # 1. check that edit group can be submitted/unsubmitted, and shows up in reviewable appropriately
+ # 2. accepted edits don't show up as reviewable and can't be submitted
+
+ c1 = CreatorEntity(display_name="test updates")
+ eg = quick_eg(api)
+ c1 = api.get_creator(api.create_creator(c1, editgroup_id=eg.editgroup_id).ident)
+
+ eg2 = api.get_editgroup(eg.editgroup_id)
+ assert not eg2.submitted
+ assert not eg2.changelog_index
+
+ reviewable = api.get_editgroups_reviewable(limit=100)
+ assert eg.editgroup_id not in [v.editgroup_id for v in reviewable]
+ wip = api.get_editor_editgroups(eg.editor_id, limit=100)
+ assert eg.editgroup_id in [v.editgroup_id for v in wip]
+
+ api.update_editgroup(eg.editgroup_id, eg2, submit=True)
+ eg3 = api.get_editgroup(eg.editgroup_id)
+ assert eg3.submitted
+ reviewable = api.get_editgroups_reviewable(limit=100)
+ assert eg.editgroup_id in [v.editgroup_id for v in reviewable]
+
+ api.update_editgroup(eg.editgroup_id, eg2, submit=False)
+ eg3 = api.get_editgroup(eg.editgroup_id)
+ assert not eg3.submitted
+ reviewable = api.get_editgroups_reviewable(limit=100)
+ assert eg.editgroup_id not in [v.editgroup_id for v in reviewable]
+
+ # put back in reviewable
+ api.update_editgroup(eg.editgroup_id, eg2, submit=True)
+ reviewable = api.get_editgroups_reviewable(limit=100)
+ assert eg.editgroup_id in [v.editgroup_id for v in reviewable]
+
+ # shouldn't be reviewable if accepted
+ api.accept_editgroup(eg.editgroup_id)
+ reviewable = api.get_editgroups_reviewable(limit=100)
+ assert eg.editgroup_id not in [v.editgroup_id for v in reviewable]
+ eg3 = api.get_editgroup(eg.editgroup_id)
+ #print(eg3)
+ assert eg3.submitted
+ assert eg3.changelog_index
+
+ with pytest.raises(fatcat_client.rest.ApiException):
+ api.update_editgroup(eg.editgroup_id, eg3, submit=True)
+ with pytest.raises(fatcat_client.rest.ApiException):
+ eg3.description = "something"
+ api.update_editgroup(eg.editgroup_id, eg3)
+
+
+def test_editgroup_ordering(api):
+
+ eg1 = quick_eg(api)
+ eg2 = quick_eg(api)
+ api.update_editgroup(
+ eg1.editgroup_id,
+ Editgroup(editgroup_id=eg1.editgroup_id, description="FAIL"),
+ submit=True)
+ api.update_editgroup(
+ eg2.editgroup_id,
+ Editgroup(editgroup_id=eg2.editgroup_id, description="FAIL"),
+ submit=True)
+
+ r1 = api.get_editgroups_reviewable()
+ #print(r1)
+ assert not r1[0].description
+ assert not r1[1].description
+ assert r1[0].submitted >= r1[1].submitted
+
+ # should be no editgroups "in the future" (since now + 1sec)
+ r1 = api.get_editgroups_reviewable(since=(datetime.datetime.utcnow() + datetime.timedelta(seconds=1)).isoformat()+"Z")
+ assert not r1
+
+ r1 = api.get_editgroups_reviewable(since=(datetime.datetime.utcnow() - datetime.timedelta(seconds=5)).isoformat()+"Z")
+ assert r1[0].submitted <= r1[1].submitted
+
+
+def test_editgroup_autoaccept(api):
+ # autoaccept changes: editgroups required when, in what combination
+
+ eg = quick_eg(api)
+ c1 = CreatorEntity(display_name="test autoaccept")
+ c2 = CreatorEntity(display_name="test another autoaccept")
+
+ with pytest.raises(fatcat_client.rest.ApiException):
+ edits = api.create_creator_batch([c1, c2])
+
+ with pytest.raises(fatcat_client.rest.ApiException):
+ edits = api.create_creator_batch([c1, c2], editgroup_id=eg.editgroup_id, autoaccept=True)
+
+ edits1 = api.create_creator_batch([c1, c2], editgroup_id=eg.editgroup_id)
+ edits2 = api.create_creator_batch([c1, c2], autoaccept=True)
+
+ assert edits1[0].editgroup_id == eg.editgroup_id
+ assert edits1[0].editgroup_id != edits2[1].editgroup_id
+ eg1 = api.get_editgroup(edits1[0].editgroup_id)
+ eg2 = api.get_editgroup(edits2[0].editgroup_id)
+
+ assert not eg1.changelog_index
+ assert eg2.changelog_index
+ #print(edits1)
+ #print(eg1.edits.creators)
+ assert eg1.edits.creators[0].ident in [t.ident for t in edits1]
+ assert eg2.edits.creators[0].ident in [t.ident for t in edits2]
+
+
+def test_batch_params(api):
+
+ eg = quick_eg(api)
+ c1 = CreatorEntity(display_name="test autoaccept")
+ c2 = CreatorEntity(display_name="test another autoaccept")
+
+ with pytest.raises(fatcat_client.rest.ApiException):
+ edits = api.create_creator_batch([c1, c2])
+
+ desc = "test description"
+ extra = dict(a=75, q="thing")
+ edits = api.create_creator_batch([c1, c2], autoaccept=True, description=desc, extra=json.dumps(extra))
+ eg = api.get_editgroup(edits[0].editgroup_id)
+
+ assert eg.description == desc
+ assert eg.extra == extra
+
+ # currently must manually json dumps() extra field
+ with pytest.raises(fatcat_client.rest.ApiException):
+ api.create_creator_batch([c1, c2], autoaccept=True, description=desc, extra=extra)
+
+ with pytest.raises(fatcat_client.rest.ApiException):
+ api.create_creator_batch([c1, c2], autoaccept=True, description=desc, extra="{")
diff --git a/python/tests/api_files.py b/python/tests/api_files.py
new file mode 100644
index 00000000..033538ef
--- /dev/null
+++ b/python/tests/api_files.py
@@ -0,0 +1,52 @@
+
+import json
+import pytest
+from copy import copy
+
+from fatcat_client import *
+from fatcat_client.rest import ApiException
+from fixtures import *
+
+
+def test_file(api):
+
+ eg = quick_eg(api)
+
+ # all the fields!
+ f1 = FileEntity(
+ size=89238,
+ md5="7ce6615b2a5904939576d9567bd5f68e",
+ sha1="027e7ed3ea1a40e92dd2657a1e3c992b5dc45dd2",
+ sha256="f1f4f18a904e76818863ccbc6141fce92b0dcb47b0d6041aec98bc6806e393c3",
+ mimetype="application/pdf",
+ extra=dict(a=2, b=5),
+ urls=[
+ FileEntityUrls(url="https://web.archive.org/web/12345542/something.com/blah.pdf", rel="webarchive"),
+ ],
+ release_ids=[],
+ )
+
+ f1edit = api.create_file(f1, editgroup_id=eg.editgroup_id)
+ api.accept_editgroup(eg.editgroup_id)
+ f2 = api.get_file(f1edit.ident)
+
+ # check that fields match
+ assert f1.size == f2.size
+ assert f1.md5 == f2.md5
+ assert f1.sha1 == f2.sha1
+ assert f1.sha256 == f2.sha256
+ assert f1.mimetype == f2.mimetype
+ assert f1.extra == f2.extra
+ assert f1.urls == f2.urls
+ assert f1.release_ids == f2.release_ids
+
+ # expansion
+ # TODO: via release
+ # lookup
+ # TODO: via hashes; but need to generate random?
+
+def test_file_examples(api):
+
+ api.lookup_file(sha256='ffc1005680cb620eec4c913437dfabbf311b535cfe16cbaeb2faec1f92afc362')
+
+ f1 = api.get_file('aaaaaaaaaaaaamztaaaaaaaaam')
diff --git a/python/tests/api_filesets.py b/python/tests/api_filesets.py
new file mode 100644
index 00000000..966b85ca
--- /dev/null
+++ b/python/tests/api_filesets.py
@@ -0,0 +1,79 @@
+
+import json
+import pytest
+from copy import copy
+
+from fatcat_client import *
+from fatcat_client.rest import ApiException
+from fixtures import *
+
+
+def test_fileset(api):
+
+ eg = quick_eg(api)
+ r1 = ReleaseEntity(title="test fileset release")
+ r1edit = api.create_release(r1, editgroup_id=eg.editgroup_id)
+
+ fs1 = FilesetEntity(
+ manifest = [
+ FilesetEntityManifest(
+ path="data/thing.tar.gz",
+ size=54321,
+ md5="540da3ea6e448d8dfb057c05225f853a",
+ sha1="1dab6a0e110f9b5d70b18db0abf051f7f93faf06",
+ sha256="c7b49f3e84cd1b7cb0b0e3e9f632b7be7e21b4dc229df23331f880a8a7dfa75a",
+ extra={"a": 1, "b": 3},
+ ),
+ FilesetEntityManifest(
+ path="README.md",
+ size=54210,
+ md5="5f83592b5249671719bbed6ce91ecfa8",
+ sha1="455face3598611458efe1f072e58624790a67266",
+ sha256="429bcafa4d3d0072d5b2511e12c85c1aac1d304011d1c406da14707f7b9cd905",
+ extra={"x": 1, "y": "q"},
+ ),
+ ],
+ urls = [
+ FileEntityUrls(url="https://archive.org/download/fileset-123/", rel="repository"),
+ FileEntityUrls(url="https://humble-host.com/~user123/dataset/", rel="web"),
+ ],
+ release_ids = [r1edit.ident],
+ )
+
+ fs1edit = api.create_fileset(fs1, editgroup_id=eg.editgroup_id)
+ api.accept_editgroup(eg.editgroup_id)
+ fs2 = api.get_fileset(fs1edit.ident)
+
+ # check that fields match
+ assert fs1.urls == fs2.urls
+ assert fs1.manifest == fs2.manifest
+ assert fs1.release_ids == fs2.release_ids
+
+ # expansion
+ r1 = api.get_release(r1edit.ident, expand="filesets")
+ assert r1.filesets[0].manifest == fs1.manifest
+
+def test_fileset_examples(api):
+ fs3 = api.get_fileset('aaaaaaaaaaaaaztgaaaaaaaaam')
+
+ assert fs3.urls[0].url == 'http://other-personal-blog.name/dataset/'
+ assert fs3.urls[1].rel == 'archive'
+ assert fs3.manifest[1].md5 == 'f4de91152c7ab9fdc2a128f962faebff'
+ assert fs3.manifest[1].extra['mimetype'] == 'application/gzip'
+
+def test_bad_fileset(api):
+
+ eg = quick_eg(api)
+
+ bad_list = [
+ # good (for testing test itself)
+ #FilesetEntity(manifest=[FilesetEntityManifest(path="123.jpg", size=1234)]),
+ #FilesetEntity(urls=[FileEntityUrls(url="thing", rel="blah")]),
+ FilesetEntity(manifest=[FilesetEntityManifest(path="123.jpg", size="big")]),
+ FilesetEntity(release_ids=["asdf"]),
+ ]
+
+ for b in bad_list:
+ with pytest.raises(fatcat_client.rest.ApiException):
+ api.create_fileset(b, editgroup_id=eg.editgroup_id)
+
diff --git a/python/tests/api_misc.py b/python/tests/api_misc.py
index 3510ea82..0a0f16da 100644
--- a/python/tests/api_misc.py
+++ b/python/tests/api_misc.py
@@ -8,14 +8,6 @@ from fatcat_client.rest import ApiException
from fixtures import *
-def test_lookups(api):
-
- api.lookup_creator(orcid='0000-0003-3118-6859')
- api.lookup_container(issnl='1549-1277')
- api.lookup_file(sha256='ffc1005680cb620eec4c913437dfabbf311b535cfe16cbaeb2faec1f92afc362')
- api.lookup_release(pmid='54321')
- api.lookup_release(isbn13='978-3-16-148410-0')
-
def test_lookup_hide_extend(api):
r = api.lookup_release(doi='10.1371/journal.pmed.0020124')
diff --git a/python/tests/api_releases.py b/python/tests/api_releases.py
new file mode 100644
index 00000000..ed6f24a4
--- /dev/null
+++ b/python/tests/api_releases.py
@@ -0,0 +1,103 @@
+
+import json
+import pytest
+import datetime
+from copy import copy
+
+from fatcat_client import *
+from fatcat_client.rest import ApiException
+from fixtures import *
+
+
+def test_release(api):
+
+ eg = quick_eg(api)
+
+ # all the fields!
+ r1 = ReleaseEntity(
+ title="some title",
+ original_title="оригинальное название",
+ release_type="post-weblog",
+ release_status="pre-print",
+ release_date=datetime.datetime.utcnow().date(),
+ release_year=2015,
+ doi="10.5555/12345678",
+ pmid="12345",
+ pmcid="PMC4321",
+ wikidata_qid="Q1234",
+ isbn13="978-3-16-148410-0",
+ core_id="187348",
+ arxiv_id="aslkdjfh",
+ jstor_id="8328424",
+ volume="84",
+ issue="XII",
+ pages="4-99",
+ publisher="some publisher",
+ language="en",
+ license_slug="CC-0",
+ extra=dict(a=1, b=2),
+ contribs=[],
+ refs=[],
+ abstracts=[
+ ReleaseEntityAbstracts(
+ content="this is some abstract",
+ mimetype="text/plain",
+ lang="en"),
+ ReleaseEntityAbstracts(
+ content="this is some other abstract",
+ mimetype="text/plain",
+ lang="de"),
+ ],
+ )
+
+ r1edit = api.create_release(r1, editgroup_id=eg.editgroup_id)
+ api.accept_editgroup(eg.editgroup_id)
+ r2 = api.get_release(r1edit.ident)
+
+ # check that fields match
+ assert r1.title == r2.title
+ assert r1.original_title == r2.original_title
+ assert r1.release_type == r2.release_type
+ assert r1.release_date == r2.release_date
+ assert r1.release_year == r2.release_year
+ assert r1.doi == r2.doi
+ assert r1.pmid == r2.pmid
+ assert r1.pmcid == r2.pmcid
+ assert r1.wikidata_qid == r2.wikidata_qid
+ assert r1.isbn13 == r2.isbn13
+ assert r1.core_id == r2.core_id
+ assert r1.arxiv_id == r2.arxiv_id
+ assert r1.jstor_id == r2.jstor_id
+ assert r1.volume == r2.volume
+ assert r1.issue == r2.issue
+ assert r1.pages == r2.pages
+ assert r1.publisher == r2.publisher
+ assert r1.language == r2.language
+ assert r1.license_slug == r2.license_slug
+ assert r1.extra == r2.extra
+
+ for i in range(len(r1.abstracts)):
+ r1.abstracts[i].content == r2.abstracts[i].content
+ r1.abstracts[i].mimetype == r2.abstracts[i].mimetype
+ r1.abstracts[i].lang == r2.abstracts[i].lang
+ for i in range(len(r1.contribs)):
+ r1.contribs[i] == r2.contribs[i]
+ for i in range(len(r1.refs)):
+ r1.refs[i] == r2.refs[i]
+
+ # expansion
+ # TODO: via work
+ # lookup
+ # TODO: via all; but need to generate random identifiers
+
+def test_release_examples(api):
+
+ api.lookup_release(pmid='54321')
+ api.lookup_release(isbn13='978-3-16-148410-0')
+
+ r1 = api.get_release('aaaaaaaaaaaaarceaaaaaaaaai')
+ assert r1.title == "bigger example"
+ assert len(r1.refs) == 5
+ assert r1.contribs[0].role == "editor"
+ assert r1.abstracts[0].mimetype == "application/xml+jats"
+
diff --git a/python/tests/api_webcaptures.py b/python/tests/api_webcaptures.py
new file mode 100644
index 00000000..dc1754b3
--- /dev/null
+++ b/python/tests/api_webcaptures.py
@@ -0,0 +1,96 @@
+
+import json
+import pytest
+import datetime
+from copy import copy
+
+from fatcat_client import *
+from fatcat_client.rest import ApiException
+from fixtures import *
+
+
+def test_webcapture(api):
+
+ eg = quick_eg(api)
+ r1 = ReleaseEntity(title="test webcapture release")
+ r1edit = api.create_release(r1, editgroup_id=eg.editgroup_id)
+
+ wc1 = WebcaptureEntity(
+ original_url = "http://example.site",
+ #timestamp = "2012-01-02T03:04:05Z",
+ timestamp = datetime.datetime.now(datetime.timezone.utc),
+ cdx = [
+ WebcaptureEntityCdx(
+ surt="site,example,)/data/thing.tar.gz",
+ #timestamp="2012-01-02T03:04:05Z",
+ timestamp=datetime.datetime.now(datetime.timezone.utc),
+ url="http://example.site/data/thing.tar.gz",
+ mimetype="application/gzip",
+ status_code=200,
+ sha1="455face3598611458efe1f072e58624790a67266",
+ sha256="c7b49f3e84cd1b7cb0b0e3e9f632b7be7e21b4dc229df23331f880a8a7dfa75a",
+ ),
+ WebcaptureEntityCdx(
+ surt="site,example,)/README.md",
+ #timestamp="2012-01-02T03:04:05Z",
+ timestamp=datetime.datetime.now(datetime.timezone.utc),
+ url="http://example.site/README.md",
+ mimetype="text/markdown",
+ status_code=200,
+ sha1="455face3598611458efe1f072e58624790a67266",
+ sha256="429bcafa4d3d0072d5b2511e12c85c1aac1d304011d1c406da14707f7b9cd905",
+ ),
+ ],
+ archive_urls = [
+ FileEntityUrls(rel="wayback", url="https://web.archive.org/web/"),
+ ],
+ release_ids = [r1edit.ident],
+ )
+
+ wc1edit = api.create_webcapture(wc1, editgroup_id=eg.editgroup_id)
+ api.accept_editgroup(eg.editgroup_id)
+ wc2 = api.get_webcapture(wc1edit.ident)
+
+ # check that fields match
+ # I don't know why these aren't equal...
+ #print(wc1.archive_urls)
+ #print(wc2.archive_urls)
+ #assert wc1.archive_urls == wc2.archive_urls
+ assert wc1.archive_urls[0].rel == wc2.archive_urls[0].rel
+ assert wc1.archive_urls[0].url == wc2.archive_urls[0].url
+ assert wc1.cdx == wc2.cdx
+ assert wc1.release_ids == wc2.release_ids
+ assert wc1.timestamp == wc2.timestamp
+ assert wc1.original_url == wc2.original_url
+
+ # TODO: check release expansion
+ r1 = api.get_release(r1edit.ident, expand="webcaptures")
+ print(r1)
+ assert r1.webcaptures[0].cdx == wc1.cdx
+
+def test_webcapture_examples(api):
+ wc3 = api.get_webcapture('aaaaaaaaaaaaa53xaaaaaaaaam')
+
+ assert wc3.cdx[0].surt == 'org,asheesh)/'
+ assert wc3.cdx[1].sha1 == 'a637f1d27d9bcb237310ed29f19c07e1c8cf0aa5'
+ assert wc3.archive_urls[1].rel == 'warc'
+
+
+def test_bad_webcapture(api):
+
+ eg = quick_eg(api)
+
+ bad_list = [
+ # good (for testing test itself)
+ WebcaptureEntity(cdx=[
+ WebcaptureEntityCdx(
+ surt="site,example,)/123.jpg",
+ url="http://example.site/123.jpg",
+ sha1="455face3598611458efe1f072e58624790a67266",
+ timestamp=201506071122)]),
+ ]
+
+ for b in bad_list:
+ with pytest.raises(fatcat_client.rest.ApiException):
+ api.create_webcapture(b, editgroup_id=eg.editgroup_id)
+
diff --git a/python/tests/citation_efficiency.py b/python/tests/citation_efficiency.py
new file mode 100644
index 00000000..fe5006cc
--- /dev/null
+++ b/python/tests/citation_efficiency.py
@@ -0,0 +1,113 @@
+
+import json
+import pytest
+from copy import copy
+
+from fatcat_client import *
+from fatcat_client.rest import ApiException
+from fixtures import *
+
+
+def test_citation_indexing(api):
+ # indexing is consistent and reacts to change
+
+ eg = quick_eg(api)
+ r1 = ReleaseEntity(title="the target")
+ r1.refs = [
+ ReleaseRef(key="first", title="the first title"),
+ ReleaseRef(key="second", title="the second title"),
+ ReleaseRef(key="third", title="a third title"),
+ ]
+ r1 = api.get_release(api.create_release(r1, editgroup_id=eg.editgroup_id).ident)
+ api.accept_editgroup(eg.editgroup_id)
+
+ assert r1.refs[0].index == 0
+ assert r1.refs[0].key == "first"
+ assert r1.refs[1].index == 1
+ assert r1.refs[1].key == "second"
+ assert r1.refs[2].index == 2
+ assert r1.refs[2].key == "third"
+
+ r1.refs.pop(1)
+ eg = quick_eg(api)
+ api.update_release(r1.ident, r1, editgroup_id=eg.editgroup_id)
+ api.accept_editgroup(eg.editgroup_id)
+ r1 = api.get_release(r1.ident)
+
+ assert r1.refs[0].index == 0
+ assert r1.refs[0].key == "first"
+ assert r1.refs[1].index == 1
+ assert r1.refs[1].key == "third"
+
+def test_citation_targets(api):
+ # invariant to linking citations
+ # also, updates work
+
+ eg = quick_eg(api)
+ r1 = ReleaseEntity(title="the target")
+ r1 = api.get_release(api.create_release(r1, editgroup_id=eg.editgroup_id).ident)
+ r2 = ReleaseEntity(title="the citer")
+ r2.refs = [
+ ReleaseRef(key="first", title="something else"),
+ ReleaseRef(key="second", title="the target title"),
+ ]
+ r2 = api.get_release(api.create_release(r2, editgroup_id=eg.editgroup_id).ident)
+ api.accept_editgroup(eg.editgroup_id)
+
+ eg = quick_eg(api)
+ r2.refs[1].target_release_id = r1.ident
+ api.update_release(r2.ident, r2, editgroup_id=eg.editgroup_id)
+ api.accept_editgroup(eg.editgroup_id)
+ r2 = api.get_release(r2.ident)
+ assert r2.refs[0].key == "first"
+ assert r2.refs[1].key == "second"
+ assert r2.refs[0].index == 0 # TODO: one-indexing?
+ assert r2.refs[1].index == 1
+ assert r2.refs[0].target_release_id == None
+ assert r2.refs[1].target_release_id == r1.ident
+ assert len(r2.refs) == 2
+
+def test_citation_empty_array(api):
+ # distinction between empty array (no citations) and no array (hidden)
+
+ r1 = ReleaseEntity(title="citation null")
+ r2 = ReleaseEntity(title="citation empty array")
+ r1.refs = None
+ r2.refs = []
+
+ eg = quick_eg(api)
+ r1 = api.get_release(api.create_release(r1, editgroup_id=eg.editgroup_id).ident)
+ r2 = api.get_release(api.create_release(r2, editgroup_id=eg.editgroup_id).ident)
+ api.accept_editgroup(eg.editgroup_id)
+
+ print(r1.refs)
+ print(r2.refs)
+ assert r1.refs == []
+ assert r1.refs == r2.refs
+
+ r1b = api.get_release(r1.ident, hide="refs")
+ assert r1b.refs == None
+
+def test_citation_encoding(api):
+ # escape-only changes (eg, \u1234 whatever for ASCII)
+
+ r1 = ReleaseEntity(title="citation encoding")
+ title = "title-unicode \\u0050 \\\" "
+ container = "container-unicode ☃︎ ä ö ü スティー"
+ extra = extra={'a': 1, 'b': 2, 'ö': 3}
+ locator = "p123"
+ r1.refs = [
+ ReleaseRef(key="1", year=1923, title=title, container_name=container,
+ extra=extra, locator=locator),
+ ReleaseRef(key="2"),
+ ]
+
+ eg = quick_eg(api)
+ r1 = api.get_release(api.create_release(r1, editgroup_id=eg.editgroup_id).ident)
+ api.accept_editgroup(eg.editgroup_id)
+
+ assert title == r1.refs[0].title
+ assert container == r1.refs[0].container_name
+ assert extra == r1.refs[0].extra
+ assert locator == r1.refs[0].locator
+
diff --git a/python/tests/cli.sh b/python/tests/cli.sh
index eba6d3a7..19d8a85b 100755
--- a/python/tests/cli.sh
+++ b/python/tests/cli.sh
@@ -14,7 +14,7 @@ set -x
./fatcat_import.py crossref tests/files/crossref-works.2018-01-21.badsample.json tests/files/ISSN-to-ISSN-L.snip.txt
./fatcat_import.py orcid tests/files/0000-0001-8254-7103.json
-./fatcat_import.py issn tests/files/journal_extra_metadata.snip.csv
+./fatcat_import.py journal-metadata tests/files/journal_extra_metadata.snip.csv
./fatcat_import.py matched tests/files/matched_sample.json
./fatcat_import.py matched tests/files/example_matched.json
./fatcat_import.py grobid-metadata tests/files/example_grobid_metadata_lines.tsv
diff --git a/python/tests/files/crossref-works.single.json b/python/tests/files/crossref-works.single.json
index 2af2b358..e3d2e05c 100644
--- a/python/tests/files/crossref-works.single.json
+++ b/python/tests/files/crossref-works.single.json
@@ -84,7 +84,7 @@
{
"given": "Carlos G.",
"family": "Diaz",
- "affiliation": ["Some University"]
+ "affiliation": [{"name": "Some University"}, {"name": "Some Department"}]
},
{
"given": "Francisco M.",
diff --git a/python/tests/fixtures.py b/python/tests/fixtures.py
index 6a880c48..3cc275b3 100644
--- a/python/tests/fixtures.py
+++ b/python/tests/fixtures.py
@@ -28,6 +28,7 @@ def api():
conf.api_key["Authorization"] = os.getenv("FATCAT_API_AUTH_TOKEN")
conf.api_key_prefix["Authorization"] = "Bearer"
api_client = fatcat_client.DefaultApi(fatcat_client.ApiClient(conf))
+ api_client.editor_id = "aaaaaaaaaaaabkvkaaaaaaaaae"
return api_client
def test_get_changelog_entry(api):
@@ -38,33 +39,6 @@ def test_get_changelog_entry(api):
## Helpers ##################################################################
def quick_eg(api_inst):
- eg = api_inst.create_editgroup(
- fatcat_client.Editgroup(editor_id='aaaaaaaaaaaabkvkaaaaaaaaae'))
+ eg = api_inst.create_editgroup(fatcat_client.Editgroup())
return eg
-# TODO: what are these even here for?
-def check_entity_fields(e):
- for key in ('rev', 'is_live', 'redirect_id'):
- assert key in e
- for key in ('id',):
- assert e[key] is not None
-
-def check_release(e):
- for key in ('work', 'release_type'):
- assert key in e
- for key in ('title', ):
- assert e[key] is not None
- for key in ('refs', 'creators'):
- assert type(e[key]) == list
-
-def check_creator(e):
- for key in ('name',):
- assert e[key] is not None
-
-def check_container(e):
- for key in ('name',):
- assert e[key] is not None
-
-def check_file(e):
- for key in ('size', 'sha1'):
- assert e[key] is not None
diff --git a/python/tests/import_crossref.py b/python/tests/import_crossref.py
index e2ca6122..193f78f6 100644
--- a/python/tests/import_crossref.py
+++ b/python/tests/import_crossref.py
@@ -1,35 +1,51 @@
import json
import pytest
-from fatcat_tools.importers import CrossrefImporter
+from fatcat_tools.importers import CrossrefImporter, JsonLinePusher
from fixtures import api
@pytest.fixture(scope="function")
def crossref_importer(api):
with open('tests/files/ISSN-to-ISSN-L.snip.txt', 'r') as issn_file:
- yield CrossrefImporter(api, issn_file, extid_map_file='tests/files/example_map.sqlite3', check_existing=False)
+ yield CrossrefImporter(api, issn_file, extid_map_file='tests/files/example_map.sqlite3', bezerk_mode=True)
@pytest.fixture(scope="function")
def crossref_importer_existing(api):
with open('tests/files/ISSN-to-ISSN-L.snip.txt', 'r') as issn_file:
- yield CrossrefImporter(api, issn_file, extid_map_file='tests/files/example_map.sqlite3', check_existing=True)
+ yield CrossrefImporter(api, issn_file, extid_map_file='tests/files/example_map.sqlite3', bezerk_mode=False)
def test_crossref_importer_batch(crossref_importer):
with open('tests/files/crossref-works.2018-01-21.badsample.json', 'r') as f:
- crossref_importer.process_batch(f)
+ JsonLinePusher(crossref_importer, f).run()
def test_crossref_importer(crossref_importer):
+ last_index = crossref_importer.api.get_changelog(limit=1)[0].index
with open('tests/files/crossref-works.2018-01-21.badsample.json', 'r') as f:
- crossref_importer.process_source(f)
+ crossref_importer.bezerk_mode = True
+ counts = JsonLinePusher(crossref_importer, f).run()
+ assert counts['insert'] == 14
+ assert counts['exists'] == 0
+ assert counts['skip'] == 0
+
# fetch most recent editgroup
- changes = crossref_importer.api.get_changelog(limit=1)
- eg = changes[0].editgroup
+ change = crossref_importer.api.get_changelog_entry(index=last_index+1)
+ eg = change.editgroup
assert eg.description
assert "crossref" in eg.description.lower()
assert eg.extra['git_rev']
assert "fatcat_tools.CrossrefImporter" in eg.extra['agent']
+ last_index = crossref_importer.api.get_changelog(limit=1)[0].index
+ with open('tests/files/crossref-works.2018-01-21.badsample.json', 'r') as f:
+ crossref_importer.bezerk_mode = False
+ crossref_importer.reset()
+ counts = JsonLinePusher(crossref_importer, f).run()
+ assert counts['insert'] == 0
+ assert counts['exists'] == 14
+ assert counts['skip'] == 0
+ assert last_index == crossref_importer.api.get_changelog(limit=1)[0].index
+
def test_crossref_mappings(crossref_importer):
assert crossref_importer.map_release_type('journal-article') == "article-journal"
assert crossref_importer.map_release_type('asdf') is None
@@ -39,13 +55,13 @@ def test_crossref_mappings(crossref_importer):
def test_crossref_importer_create(crossref_importer):
crossref_importer.create_containers = True
with open('tests/files/crossref-works.2018-01-21.badsample.json', 'r') as f:
- crossref_importer.process_source(f)
+ JsonLinePusher(crossref_importer, f).run()
def test_crossref_dict_parse(crossref_importer):
with open('tests/files/crossref-works.single.json', 'r') as f:
# not a single line
raw = json.loads(f.read())
- (r, c) = crossref_importer.parse_crossref_dict(raw)
+ r = crossref_importer.parse_record(raw)
extra = r.extra['crossref']
assert r.title == "Renormalized perturbation theory by the moment method for degenerate states: Anharmonic oscillators"
assert r.doi == "10.1002/(sici)1097-461x(1998)66:4<261::aid-qua1>3.0.co;2-t"
@@ -61,7 +77,8 @@ def test_crossref_dict_parse(crossref_importer):
assert len(r.contribs) == 5
assert r.contribs[0].raw_name == "Marcelo D. Radicioni"
assert r.contribs[0].index == 0
- assert r.contribs[1].extra['affiliations'] == ["Some University"]
+ assert r.contribs[1].raw_affiliation == "Some University"
+ assert r.contribs[1].extra['more_affiliations'] == ["Some Department"]
assert r.contribs[1].role == "author"
assert r.contribs[3].role == "editor"
assert r.contribs[3].index is None
@@ -78,8 +95,10 @@ def test_crossref_dict_parse(crossref_importer):
def test_stateful_checking(crossref_importer_existing):
with open('tests/files/crossref-works.single.json', 'r') as f:
# not a single line, a whole document
- raw = json.loads(f.read())
+ raw = f.read()
# might not exist yet...
- crossref_importer_existing.process_source([json.dumps(raw)])
- # ok, make sure we get 'None' back
- assert crossref_importer_existing.parse_crossref_dict(raw) is None
+ crossref_importer_existing.push_record(json.loads(raw))
+ crossref_importer_existing.finish()
+ # make sure we wouldn't insert again
+ entity = crossref_importer_existing.parse_record(json.loads(raw))
+ assert crossref_importer_existing.try_update(entity) is False
diff --git a/python/tests/import_grobid_metadata.py b/python/tests/import_grobid_metadata.py
index 97ebcaef..4fed4aaa 100644
--- a/python/tests/import_grobid_metadata.py
+++ b/python/tests/import_grobid_metadata.py
@@ -3,7 +3,7 @@ import os
import json
import base64
import pytest
-from fatcat_tools.importers import GrobidMetadataImporter
+from fatcat_tools.importers import GrobidMetadataImporter, LinePusher
from fixtures import api
"""
@@ -15,10 +15,6 @@ side-effects. Should probably be disabled or re-written.
def grobid_metadata_importer(api):
yield GrobidMetadataImporter(api)
-# TODO: use API to check that entities actually created...
-#def test_grobid_metadata_importer_batch(grobid_metadata_importer):
-# with open('tests/files/example_grobid_metadata_lines.tsv', 'r') as f:
-# grobid_metadata_importer.process_batch(f)
def test_grobid_metadata_parse(grobid_metadata_importer):
with open('tests/files/example_grobid_metadata_lines.tsv', 'r') as f:
@@ -30,7 +26,8 @@ def test_grobid_metadata_parse(grobid_metadata_importer):
print(re.contribs)
assert re.contribs[0].raw_name == "Wahyu Ary"
assert re.publisher == None
- assert re.extra.get('container_name') == None
+ if re.extra:
+ assert re.extra.get('container_name') == None
assert len(re.refs) == 27
def test_file_metadata_parse(grobid_metadata_importer):
@@ -53,13 +50,28 @@ def test_file_metadata_parse(grobid_metadata_importer):
assert len(fe.release_ids) == 0
def test_grobid_metadata_importer(grobid_metadata_importer):
+ last_index = grobid_metadata_importer.api.get_changelog(limit=1)[0].index
with open('tests/files/example_grobid_metadata_lines.tsv', 'r') as f:
- grobid_metadata_importer.process_source(f)
+ grobid_metadata_importer.bezerk_mode = True
+ counts = LinePusher(grobid_metadata_importer, f).run()
+ assert counts['insert'] == 10
+ assert counts['inserted.release'] == 10
+ assert counts['exists'] == 0
+ assert counts['skip'] == 0
# fetch most recent editgroup
- changes = grobid_metadata_importer.api.get_changelog(limit=1)
- eg = changes[0].editgroup
+ change = grobid_metadata_importer.api.get_changelog_entry(index=last_index+1)
+ eg = change.editgroup
assert eg.description
assert "grobid" in eg.description.lower()
assert eg.extra['git_rev']
assert "fatcat_tools.GrobidMetadataImporter" in eg.extra['agent']
+
+ with open('tests/files/example_grobid_metadata_lines.tsv', 'r') as f:
+ grobid_metadata_importer.reset()
+ grobid_metadata_importer.bezerk_mode = False
+ counts = LinePusher(grobid_metadata_importer, f).run()
+ assert counts['insert'] == 0
+ assert counts['inserted.release'] == 0
+ assert counts['exists'] == 10
+ assert counts['skip'] == 0
diff --git a/python/tests/import_issn.py b/python/tests/import_issn.py
deleted file mode 100644
index 6b5978d9..00000000
--- a/python/tests/import_issn.py
+++ /dev/null
@@ -1,26 +0,0 @@
-
-import pytest
-from fatcat_tools.importers import IssnImporter
-from fixtures import api
-
-
-@pytest.fixture(scope="function")
-def issn_importer(api):
- yield IssnImporter(api)
-
-# TODO: use API to check that entities actually created...
-def test_issn_importer_batch(issn_importer):
- with open('tests/files/journal_extra_metadata.snip.csv', 'r') as f:
- issn_importer.process_csv_batch(f)
-
-def test_issn_importer(issn_importer):
- with open('tests/files/journal_extra_metadata.snip.csv', 'r') as f:
- issn_importer.process_csv_source(f)
-
- # fetch most recent editgroup
- changes = issn_importer.api.get_changelog(limit=1)
- eg = changes[0].editgroup
- assert eg.description
- assert "container" in eg.description.lower()
- assert eg.extra['git_rev']
- assert "fatcat_tools.IssnImporter" in eg.extra['agent']
diff --git a/python/tests/import_journal_metadata.py b/python/tests/import_journal_metadata.py
new file mode 100644
index 00000000..a2b10a65
--- /dev/null
+++ b/python/tests/import_journal_metadata.py
@@ -0,0 +1,39 @@
+
+import pytest
+from fatcat_tools.importers import JournalMetadataImporter, CsvPusher
+from fixtures import api
+
+
+@pytest.fixture(scope="function")
+def journal_metadata_importer(api):
+ yield JournalMetadataImporter(api)
+
+# TODO: use API to check that entities actually created...
+def test_journal_metadata_importer_batch(journal_metadata_importer):
+ with open('tests/files/journal_extra_metadata.snip.csv', 'r') as f:
+ CsvPusher(journal_metadata_importer, f).run()
+
+def test_journal_metadata_importer(journal_metadata_importer):
+ last_index = journal_metadata_importer.api.get_changelog(limit=1)[0].index
+ with open('tests/files/journal_extra_metadata.snip.csv', 'r') as f:
+ journal_metadata_importer.bezerk_mode = True
+ counts = CsvPusher(journal_metadata_importer, f).run()
+ assert counts['insert'] == 9
+ assert counts['exists'] == 0
+ assert counts['skip'] == 0
+
+ # fetch most recent editgroup
+ change = journal_metadata_importer.api.get_changelog_entry(index=last_index+1)
+ eg = change.editgroup
+ assert eg.description
+ assert "container" in eg.description.lower()
+ assert eg.extra['git_rev']
+ assert "fatcat_tools.JournalMetadataImporter" in eg.extra['agent']
+
+ with open('tests/files/journal_extra_metadata.snip.csv', 'r') as f:
+ journal_metadata_importer.reset()
+ journal_metadata_importer.bezerk_mode = False
+ counts = CsvPusher(journal_metadata_importer, f).run()
+ assert counts['insert'] == 0
+ assert counts['exists'] == 9
+ assert counts['skip'] == 0
diff --git a/python/tests/import_matched.py b/python/tests/import_matched.py
index 080674ac..8f694456 100644
--- a/python/tests/import_matched.py
+++ b/python/tests/import_matched.py
@@ -1,7 +1,7 @@
import json
import pytest
-from fatcat_tools.importers import MatchedImporter
+from fatcat_tools.importers import MatchedImporter, JsonLinePusher
from fixtures import api
@@ -10,26 +10,40 @@ def matched_importer(api):
yield MatchedImporter(api)
# TODO: use API to check that entities actually created...
-def test_matched_importer_batch(matched_importer):
+def test_matched_importer(matched_importer):
with open('tests/files/example_matched.json', 'r') as f:
- matched_importer.process_batch(f)
+ JsonLinePusher(matched_importer, f).run()
def test_matched_importer(matched_importer):
+ last_index = matched_importer.api.get_changelog(limit=1)[0].index
with open('tests/files/example_matched.json', 'r') as f:
- matched_importer.process_source(f)
+ matched_importer.bezerk_mode = True
+ counts = JsonLinePusher(matched_importer, f).run()
+ assert counts['insert'] == 2
+ assert counts['exists'] == 0
+ assert counts['skip'] == 11
# fetch most recent editgroup
- changes = matched_importer.api.get_changelog(limit=1)
- eg = changes[0].editgroup
+ change = matched_importer.api.get_changelog_entry(index=last_index+1)
+ eg = change.editgroup
assert eg.description
assert "file-to-release" in eg.description.lower()
assert eg.extra['git_rev']
assert "fatcat_tools.MatchedImporter" in eg.extra['agent']
+ # re-insert; should skip
+ with open('tests/files/example_matched.json', 'r') as f:
+ matched_importer.reset()
+ matched_importer.bezerk_mode = False
+ counts = JsonLinePusher(matched_importer, f).run()
+ assert counts['insert'] == 0
+ assert counts['exists'] == 2
+ assert counts['skip'] == 11
+
def test_matched_dict_parse(matched_importer):
with open('tests/files/example_matched.json', 'r') as f:
raw = json.loads(f.readline())
- f = matched_importer.parse_matched_dict(raw)
+ f = matched_importer.parse_record(raw)
assert f.sha1 == "00242a192acc258bdfdb151943419437f440c313"
assert f.md5 == "f4de91152c7ab9fdc2a128f962faebff"
assert f.mimetype == "application/pdf"
diff --git a/python/tests/import_orcid.py b/python/tests/import_orcid.py
index 717a1328..57886b52 100644
--- a/python/tests/import_orcid.py
+++ b/python/tests/import_orcid.py
@@ -1,7 +1,7 @@
import json
import pytest
-from fatcat_tools.importers import OrcidImporter
+from fatcat_tools.importers import OrcidImporter, JsonLinePusher
from fixtures import api
@@ -9,37 +9,46 @@ from fixtures import api
def orcid_importer(api):
yield OrcidImporter(api)
-# TODO: use API to check that entities actually created...
-def test_orcid_importer_batch(orcid_importer):
- with open('tests/files/0000-0001-8254-7103.json', 'r') as f:
- orcid_importer.process_batch(f)
-
def test_orcid_importer_badid(orcid_importer):
with open('tests/files/0000-0001-8254-710X.json', 'r') as f:
- orcid_importer.process_batch(f)
+ JsonLinePusher(orcid_importer, f).run()
+# TODO: use API to check that entities actually created...
def test_orcid_importer(orcid_importer):
+ last_index = orcid_importer.api.get_changelog(limit=1)[0].index
with open('tests/files/0000-0001-8254-7103.json', 'r') as f:
- orcid_importer.process_source(f)
+ orcid_importer.bezerk_mode = True
+ counts = JsonLinePusher(orcid_importer, f).run()
+ assert counts['insert'] == 1
+ assert counts['exists'] == 0
+ assert counts['skip'] == 0
# fetch most recent editgroup
- changes = orcid_importer.api.get_changelog(limit=1)
- eg = changes[0].editgroup
+ change = orcid_importer.api.get_changelog_entry(index=last_index+1)
+ eg = change.editgroup
assert eg.description
assert "orcid" in eg.description.lower()
assert eg.extra['git_rev']
assert "fatcat_tools.OrcidImporter" in eg.extra['agent']
+ with open('tests/files/0000-0001-8254-7103.json', 'r') as f:
+ orcid_importer.reset()
+ orcid_importer.bezerk_mode = False
+ counts = JsonLinePusher(orcid_importer, f).run()
+ assert counts['insert'] == 0
+ assert counts['exists'] == 1
+ assert counts['skip'] == 0
+
def test_orcid_importer_x(orcid_importer):
with open('tests/files/0000-0003-3953-765X.json', 'r') as f:
- orcid_importer.process_source(f)
+ JsonLinePusher(orcid_importer, f).run()
c = orcid_importer.api.lookup_creator(orcid="0000-0003-3953-765X")
assert c is not None
def test_orcid_dict_parse(orcid_importer):
with open('tests/files/0000-0001-8254-7103.json', 'r') as f:
raw = json.loads(f.readline())
- c = orcid_importer.parse_orcid_dict(raw)
+ c = orcid_importer.parse_record(raw)
assert c.given_name == "Man-Hui"
assert c.surname == "Li"
assert c.display_name == "Man-Hui Li"
diff --git a/python/tests/importer.py b/python/tests/importer.py
index 34efa5d8..9308ba84 100644
--- a/python/tests/importer.py
+++ b/python/tests/importer.py
@@ -1,13 +1,13 @@
import pytest
-from fatcat_tools.importers import FatcatImporter
+from fatcat_tools.importers import CrossrefImporter, OrcidImporter
from fixtures import api
def test_issnl_mapping_lookup(api):
with open('tests/files/ISSN-to-ISSN-L.snip.txt', 'r') as issn_file:
- fi = FatcatImporter(api, issn_map_file=issn_file)
+ fi = CrossrefImporter(api, issn_map_file=issn_file)
assert fi.issn2issnl('0000-0027') == '0002-0027'
assert fi.issn2issnl('0002-0027') == '0002-0027'
@@ -18,20 +18,18 @@ def test_issnl_mapping_lookup(api):
def test_identifiers(api):
with open('tests/files/ISSN-to-ISSN-L.snip.txt', 'r') as issn_file:
- fi = FatcatImporter(api, issn_map_file=issn_file)
-
- assert fi.is_issnl("1234-5678") == True
- assert fi.is_issnl("1234-5678.") == False
- assert fi.is_issnl("12345678") == False
- assert fi.is_issnl("1-2345678") == False
-
- assert fi.is_doi("10.1234/56789") == True
- assert fi.is_doi("101234/56789") == False
- assert fi.is_doi("10.1234_56789") == False
-
- assert fi.is_orcid("0000-0003-3118-6591") == True
- assert fi.is_orcid("0000-0003-3953-765X") == True
- assert fi.is_orcid("0000-00x3-3118-659") == False
- assert fi.is_orcid("0000-00033118-659") == False
- assert fi.is_orcid("0000-0003-3118-659.") == False
+ ci = CrossrefImporter(api, issn_map_file=issn_file)
+
+ assert ci.is_issnl("1234-5678") == True
+ assert ci.is_issnl("1234-5678.") == False
+ assert ci.is_issnl("12345678") == False
+ assert ci.is_issnl("1-2345678") == False
+
+ oi = OrcidImporter(api)
+
+ assert oi.is_orcid("0000-0003-3118-6591") == True
+ assert oi.is_orcid("0000-0003-3953-765X") == True
+ assert oi.is_orcid("0000-00x3-3118-659") == False
+ assert oi.is_orcid("0000-00033118-659") == False
+ assert oi.is_orcid("0000-0003-3118-659.") == False
diff --git a/python/tests/transform_tests.py b/python/tests/transform_tests.py
index e9d23250..6d6c6c82 100644
--- a/python/tests/transform_tests.py
+++ b/python/tests/transform_tests.py
@@ -11,7 +11,7 @@ def test_elasticsearch_convert(crossref_importer):
with open('tests/files/crossref-works.single.json', 'r') as f:
# not a single line
raw = json.loads(f.read())
- (r, c) = crossref_importer.parse_crossref_dict(raw)
+ r = crossref_importer.parse_record(raw)
r.state = 'active'
release_to_elasticsearch(r)
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-27 21:43:41 +0000