Skip to content

897 add relateditem field to UI #906

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
jsjiang merged 24 commits into from
Jul 28, 2025
Merged

897 add relateditem field to UI #906

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
24 commits
Select commit Hold shift + click to select a range
92d6b5e
Merge pull request #903 from CDLUC3/develop
jsjiang Jun 27, 2025
d57bb56
add form elements for related items
jsjiang Jun 28, 2025
4355ca5
Display related items
jsjiang Jul 1, 2025
b5f0c6b
add _datacite_relatedItem.html
jsjiang Jul 1, 2025
144e6e4
organize page payout for telated item
jsjiang Jul 1, 2025
74373c6
rename relatedItem fields follow formset name convenstion
jsjiang Jul 2, 2025
aeb0dc6
name attribute form field in element-attribute format
jsjiang Jul 4, 2025
aa91fd4
do not sort children elements for related item
jsjiang Jul 7, 2025
62e0d6d
handle elements order for relatedItem
jsjiang Jul 7, 2025
da1f81c
map datacite xml to form elements for related items
jsjiang Jul 7, 2025
65fa2d5
validate relatedItem data fields
jsjiang Jul 8, 2025
b5b57a4
clean up code
jsjiang Jul 8, 2025
96e2914
move datacite testing code to tests/test_datacite.py
jsjiang Jul 10, 2025
1d74839
test formElementsToDataciteXml
jsjiang Jul 10, 2025
a7dc575
add more datacite form elements to test record
jsjiang Jul 11, 2025
ed10937
add more datacite fields for testing
jsjiang Jul 11, 2025
a267f18
consolidate datacite test records and test cases
jsjiang Jul 11, 2025
28be3b6
adjust layout of related item
jsjiang Jul 12, 2025
8e22b9b
test relateditem form
jsjiang Jul 15, 2025
0e5d2cf
modify and implement the clearField function
jsjiang Jul 16, 2025
f67ebca
remove special handling for the select box
jsjiang Jul 17, 2025
4a4f462
use clearField function for duplicated clearing form fields logic
jsjiang Jul 18, 2025
987d473
remove comments
jsjiang Jul 18, 2025
51af508
add publisherIdentifierScheme to unit tests
jsjiang Jul 22, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
159 changes: 60 additions & 99 deletions impl/datacite_xml.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,7 @@
"descriptions",
"geoLocations",
"fundingReferences",
"relatedItems"
]

_numberedElementContainers = {
Expand Down Expand Up @@ -148,6 +149,11 @@ def processNode(path, node, index=None, separator="-"):
fc = _separateByFormType(d)
return fc

""" Representation of django forms and formsets used for DataCite XML """
FormColl = collections.namedtuple(
'FormColl',
'nonRepeating publisher resourceType creators titles descrs subjects contribs dates altids relids sizes formats rights geoLocations fundingReferences relatedItems',
)

def _separateByFormType(d):
"""Organize form elements into a manageable collection Turn empty dicts
Expand All @@ -168,12 +174,6 @@ def dict_generate(d, s):
dr = {k: v for (k, v) in list(d.items()) if k.startswith(s)}
return dr if dr else None

""" Representation of django forms and formsets used for DataCite XML """
FormColl = collections.namedtuple(
'FormColl',
'nonRepeating publisher resourceType creators titles descrs subjects contribs dates altids relids sizes formats rights geoLocations fundingReferences',
)

return FormColl(
nonRepeating=_nonRepeating if _nonRepeating else None,
publisher=dict_generate(d, 'publisher'),
Expand All @@ -191,18 +191,9 @@ def dict_generate(d, s):
rights=dict_generate(d, 'rightsList'),
geoLocations=dict_generate(d, 'geoLocations'),
fundingReferences=dict_generate(d, 'fundingReferences'),
relatedItems=dict_generate(d, 'relatedItems')
)

# commnented out for now, as it was created for testing in the edit function in ui_manage.py.
# consider moving it to tests/test_xxx.py if needed in the future. JJiang 2025-06-10
# def temp_mockxml():
# # An item whose Creator has two nameIDs and two affiliations
# # return unicode('<resource xmlns="http://datacite.org/schema/kernel-3" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://datacite.org/schema/kernel-3 http://schema.datacite.org/meta/kernel-3/metadata.xsd"><identifier identifierType="ARK"/><creators><creator><creatorName>test</creatorName><givenName>Elizabeth</givenName><familyName>Miller</familyName><nameIdentifier schemeURI="http://orcid.org/" nameIdentifierScheme="ORCID">0000-0001-5000-0001</nameIdentifier><nameIdentifier schemeURI="http://orcid.org/2" nameIdentifierScheme="ORCID2">0000-0001-5000-0002</nameIdentifier><affiliation>DataCite1</affiliation><affiliation>DataCite2</affiliation></creator></creators><titles><title xml:lang="en-us">test</title></titles><publisher>test</publisher><publicationYear>1990</publicationYear><subjects><subject xml:lang="ar-afb" schemeURI="testURI" subjectScheme="testScheme">TESTTESTTESTTEST</subject><subject xml:lang="en" subjectScheme="testScheme2" schemeURI="testURI2">test2</subject></subjects><contributors><contributor contributorType="ProjectLeader"><contributorName>Starr, Joan</contributorName><nameIdentifier schemeURI="http://orcid.org/" nameIdentifierScheme="ORCID">0000-0002-7285-027X</nameIdentifier><nameIdentifier schemeURI="http://orcid.org/" nameIdentifierScheme="ORCID">0000-0002-7285-1000</nameIdentifier><nameIdentifier schemeURI="http://orcid.org/" nameIdentifierScheme="ORCID">0000-0002-7285-2222</nameIdentifier><nameIdentifier schemeURI="http://orcid.org/" nameIdentifierScheme="ORCID">0000-0002-7285-3333</nameIdentifier><nameIdentifier schemeURI="http://orcid.org/" nameIdentifierScheme="ORCID">0000-0002-7285-4444</nameIdentifier><nameIdentifier schemeURI="http://orcid.org/" nameIdentifierScheme="ORCID">0000-0002-7285-5555</nameIdentifier><affiliation>California Digital Library</affiliation><affiliation>National SPAM Committee</affiliation><affiliation>NASCAR</affiliation></contributor><contributor contributorType="ProjectLeader"><contributorName>Rawls, Lou</contributorName><nameIdentifier schemeURI="http://orcid.org/" nameIdentifierScheme="ORCID">0000-0002-7285-027X</nameIdentifier><affiliation>Chicago</affiliation></contributor></contributors><resourceType resourceTypeGeneral="Dataset">Dataset</resourceType><descriptions><description xml:lang="es-419" descriptionType="Abstract">testDescr</description><description xml:lang="zh-Hans" descriptionType="Other">testDescr2</description><description xml:lang="ast" descriptionType="SeriesInformation">testDescr3</description></descriptions></resource>')
# # An item with 2 Creators, both with three nameIDs
# return str(
# '<resource xmlns="http://datacite.org/schema/kernel-3" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://datacite.org/schema/kernel-3 http://schema.datacite.org/meta/kernel-3/metadata.xsd"><identifier identifierType="ARK"/><creators><creator><creatorName>test</creatorName><givenName>Elizabeth</givenName><familyName>Miller</familyName><nameIdentifier schemeURI="http://orcid.org/" nameIdentifierScheme="ORCID">0000-0001-5000-0001</nameIdentifier><nameIdentifier schemeURI="http://orcid.org/2" nameIdentifierScheme="ORCID2">0000-0001-5000-0002</nameIdentifier><nameIdentifier schemeURI="http://orcid.org/3" nameIdentifierScheme="ORCID3">0000-0001-5000-0003</nameIdentifier><affiliation>DataCite1</affiliation><affiliation>DataCite2</affiliation></creator><creator><creatorName>test</creatorName><givenName>Elizabeth</givenName><familyName>Miller</familyName><nameIdentifier schemeURI="http://orcid.org/" nameIdentifierScheme="ORCID">0000-0001-5000-0001</nameIdentifier><nameIdentifier schemeURI="http://orcid.org/2" nameIdentifierScheme="ORCID2">0000-0001-5000-0002</nameIdentifier><nameIdentifier schemeURI="http://orcid.org/3" nameIdentifierScheme="ORCID3">0000-0001-5000-0003</nameIdentifier><nameIdentifier schemeURI="http://orcid.org/" nameIdentifierScheme="ORCID">0000-0001-5000-0001</nameIdentifier><nameIdentifier schemeURI="http://orcid.org/2" nameIdentifierScheme="ORCID2">0000-0001-5000-0002</nameIdentifier><nameIdentifier schemeURI="http://orcid.org/3" nameIdentifierScheme="ORCID3">0000-0001-5000-0003</nameIdentifier><affiliation>DataCite1</affiliation><affiliation>DataCite2</affiliation></creator></creators><titles><title xml:lang="en-us">test</title></titles><publisher>test</publisher><publicationYear>1990</publicationYear><subjects><subject xml:lang="ar-afb" schemeURI="testURI" subjectScheme="testScheme">TESTTESTTESTTEST</subject><subject xml:lang="en" subjectScheme="testScheme2" schemeURI="testURI2">test2</subject></subjects><resourceType resourceTypeGeneral="Dataset">Dataset</resourceType><descriptions><description xml:lang="es-419" descriptionType="Abstract">testDescr</description><description xml:lang="zh-Hans" descriptionType="Other">testDescr2</description><description xml:lang="ast" descriptionType="SeriesInformation">testDescr3</description></descriptions></resource>'
# )


def _id_type(str):
m = re.compile("^[a-z]+")
Expand All @@ -215,7 +206,11 @@ def _id_type(str):
# The following exhaustive list of DataCite XML elements must form a
# partial topological order, that is, if two elements have the same
# parent, they must appear in the list in the same order that they
# must appear in an XML document.
# must appear in an XML document defined in datacite/metadata.xsd.
# Embedded elements such as the titles, creators and contributors in
# the relatedItems may have a different topological order than what
# they appear at the element level. Define the order in a sub-elements
# list when needed.

_elementList = [
"identifier",
Expand Down Expand Up @@ -259,22 +254,56 @@ def _id_type(str):
"geoLocationBox",
"geoLocationPolygon",
"polygonPoint",
"fundingReferences",
"fundingReference",
"funderName",
"funderIdentifier",
"awardNumber",
"awardTitle",
"pointLongitude",
"pointLatitude",
"westBoundLongitude",
"eastBoundLongitude",
"southBoundLatitude",
"northBoundLatitude",
"fundingReferences",
"fundingReference",
"funderName",
"funderIdentifier",
"awardNumber",
"awardTitle",
"relatedItems",
"relatedItem",
"relatedItemIdentifier",
"volume",
"issue",
"number",
"firstPage",
"lastPage",
"edition",
]

_elementList_relatedItem = [
"relatedItemIdentifier",
"creators",
"creator",
"creatorName",
"titles",
"title",
"publicationYear",
"volume",
"issue",
"number",
"firstPage",
"lastPage",
"publisher",
"edition",
"contributors",
"contributor",
"givenName",
"familyName",
]

# elements with topological order in sequence number, such as:
# {'identifier': 0, 'creators': 1, 'creator': 2, 'creatorName': 3, etc.
_elements = dict((e, i) for i, e in enumerate(_elementList))

_elements_relatedItem = dict((e, i) for i, e in enumerate(_elementList_relatedItem))


def formElementsToDataciteXml(d, shoulder=None, identifier=None):
"""The inverse of dataciteXmlToFormElements
Expand Down Expand Up @@ -339,21 +368,25 @@ def tagName(tag):
node.attrib[k] = value
key = remainder

def sortValue(node):
def sortValue(node, ordered_elements):
v = tagName(node.tag)
m = re.match(".*_(\\d+)$", v)
if m:
return _elements[v.split("_", 1)[0]], int(m.group(1))
return ordered_elements[v.split("_", 1)[0]], int(m.group(1))
else:
return _elements[v], 0
return ordered_elements[v], 0

def sortChildren(node):
if (
tagName(node.tag) not in _repeatableElementContainers
and tagName(node.tag) != "geoLocationPolygon"
):
if tagName(node.tag) == "relatedItem":
ordered_elements = _elements_relatedItem
else:
ordered_elements = _elements
children = node.getchildren()
children.sort(key=lambda c: sortValue(c))
children.sort(key=lambda c: sortValue(c, ordered_elements))
for i, c in enumerate(children):
node.insert(i, c)
for c in node.iterchildren():
Expand Down Expand Up @@ -381,75 +414,3 @@ def _addIdentifierInfo(d, shoulder=None, identifier=None):
d['identifier'] = identifier # Only for already created IDs
return d


def temp_mockFormElements():
return {
'alternateIdentifiers-alternateIdentifier-0-alternateIdentifier': '',
'alternateIdentifiers-alternateIdentifier-0-alternateIdentifierType': '',
'contributors-contributor-0-affiliation': '',
'contributors-contributor-0-affiliationIdentifier': '',
'contributors-contributor-0-affiliationIdentifierScheme': '',
'contributors-contributor-0-schemeURI': '',
'contributors-contributor-0-contributorName': '',
'contributors-contributor-0-contributorType': '',
'contributors-contributor-0-familyName': '',
'contributors-contributor-0-givenName': '',
'contributors-contributor-0-nameIdentifier_0-nameIdentifier': '',
'contributors-contributor-0-nameIdentifier_0-nameIdentifierScheme': '',
'contributors-contributor-0-nameIdentifier_0-schemeURI': '',
'contributors-contributor-0-nameIdentifier_1-nameIdentifier': '',
'contributors-contributor-0-nameIdentifier_1-nameIdentifierScheme': '',
'contributors-contributor-0-nameIdentifier_1-schemeURI': '',
'creators-creator-0-affiliation': '',
'creators-creator-0-affiliationIdentifier': '',
'creators-creator-0-affiliationIdentifierScheme': '',
'creators-creator-0-schemeURI': '',
'creators-creator-0-creatorName': 'test',
'creators-creator-0-familyName': '',
'creators-creator-0-givenName': '',
'creators-creator-0-nameIdentifier_0-nameIdentifier': '',
'creators-creator-0-nameIdentifier_0-nameIdentifierScheme': '',
'creators-creator-0-nameIdentifier_0-schemeURI': '',
'creators-creator-0-nameIdentifier_1-nameIdentifier': '',
'creators-creator-0-nameIdentifier_1-nameIdentifierScheme': '',
'creators-creator-0-nameIdentifier_1-schemeURI': '',
'dates-date-0-date': '',
'dates-date-0-dateType': '',
'dates-date-0-dateInformation': '',
'descriptions-description-0-description': '',
'descriptions-description-0-descriptionType': '',
'descriptions-description-0-{http://www.w3.org/XML/1998/namespace}lang': '',
'formats-format-0-format': '',
'fundingReferences-fundingReference-0-awardNumber': '',
'fundingReferences-fundingReference-0-awardTitle': '',
'fundingReferences-fundingReference-0-awardNumber-awardURI': '',
'fundingReferences-fundingReference-0-funderIdentifier': 'test',
'fundingReferences-fundingReference-0-funderIdentifier-funderIdentifierType': 'ISNI',
'fundingReferences-fundingReference-0-funderName': 'test',
'geoLocations-geoLocation-0-geoLocationBox': '',
'geoLocations-geoLocation-0-geoLocationPlace': '',
'geoLocations-geoLocation-0-geoLocationPoint': '',
'language': '',
'publicationYear': '1999',
'publisher': 'test',
'relatedIdentifiers-relatedIdentifier-0-relatedIdentifier': '',
'relatedIdentifiers-relatedIdentifier-0-relatedIdentifierType': '',
'relatedIdentifiers-relatedIdentifier-0-relatedMetadataScheme': '',
'relatedIdentifiers-relatedIdentifier-0-relationType': '',
'relatedIdentifiers-relatedIdentifier-0-schemeType': '',
'relatedIdentifiers-relatedIdentifier-0-schemeURI': '',
'resourceType': 'Dataset',
'resourceType-resourceTypeGeneral': 'Dataset',
'rightsList-rights-0-rights': '',
'rightsList-rights-0-rightsURI': '',
'sizes-size-0-size': '',
'subjects-subject-0-schemeURI': '',
'subjects-subject-0-subject': '',
'subjects-subject-0-subjectScheme': '',
'subjects-subject-0-valueURI': '',
'subjects-subject-0-{http://www.w3.org/XML/1998/namespace}lang': '',
'titles-title-0-title': 'test',
'titles-title-0-titleType': '',
'titles-title-0-{http://www.w3.org/XML/1998/namespace}lang': '',
'version': '',
}
Loading