Skip to content

Commit

Permalink
KP-8714 Make publisher parsing work for persons
Browse files Browse the repository at this point in the history 
CMDI has separate distributionRigtsHolderPerson and
distributionRightsHolderOrganization elements, which is a bit tricky for
the current parsing. At the moment, sole organizations are not added as
actors at all though:
```
$ git show b815790
commit b815790
Author: Anni Järvenpää <[email protected]>
Date:   Tue Feb 27 11:37:54 2024 +0000

    KP-7427 Skip empty actors

    Because the organizations have not been implemented yet, some of the
    actors had just a role and an empty person dict. Metax does not like
    this, so those are skipped altogether now.
```

Thus it's less bad to read the person element than to read the
organization element. This needs to be made to work with both
organizations and persons though if (when?) we remove the person data
requirement is lifted.
  • Loading branch information
@aajarven
aajarven committed Oct 16, 2024
1 parent 9710598 commit 5e23213
Show file tree
Hide file tree
Showing 3 changed files with 211 additions and 1 deletion.
2 changes: 1 addition & 1 deletion harvester/metadata_parser.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -288,7 +288,7 @@ def _get_actors(self):

actor_role_element_xpaths = {
"creator": "//cmd:metadataInfo/cmd:metadataCreator",
"publisher": "//cmd:distributionInfo/cmd:licenceInfo/cmd:distributionRightsHolderOrganization",
"publisher": "//cmd:distributionInfo/cmd:licenceInfo/cmd:distributionRightsHolderPerson",
"curator": "//cmd:resourceInfo/cmd:contactPerson",
"rights_holder": "//cmd:distributionInfo/cmd:iprHolderPerson",
}
Expand Down
192 changes: 192 additions & 0 deletions tests/test_data/kielipankki_record_sample_with_publisher_person.xml
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,192 @@
<record xmlns="http://www.openarchives.org/OAI/2.0/">
<header>
<identifier>oai:clarino.uib.no:lb-20140730134</identifier>
<datestamp>2024-06-19T07:39:34Z</datestamp>
<setSpec>FIN-CLARIN</setSpec>
</header>
<metadata>
<CMD xmlns="http://www.clarin.eu/cmd/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" CMDVersion="1.1" xsi:schemaLocation="http://www.clarin.eu/cmd/ http://catalog.clarin.eu/ds/ComponentRegistry/rest/registry/profiles/clarin.eu:cr1:p_1361876010571/xsd">
<Header>
<MdCreator>metashareToCmdi.xsl remove_metashare_namespace.xsl</MdCreator>
<MdCreationDate>2023-03-22</MdCreationDate>
<MdSelfLink>urn:nbn:fi:lb-20140730134</MdSelfLink>
<MdProfile>clarin.eu:cr1:p_1361876010571</MdProfile>
</Header>
<Resources>
<ResourceProxyList/>
<JournalFileProxyList/>
<ResourceRelationList/>
<IsPartOfList/>
</Resources>
<Components>
<resourceInfo>
<identificationInfo ComponentId="clarin.eu:cr1:c_1349361150743">
<resourceName xml:lang="en">
The Finnish Broadcasting Company Corpus of Subtitles
</resourceName>
<description xml:lang="fi">
Kuvaus tekstityskorpukselle vuosilta 1992-2004.
</description>
<description xml:lang="en">
Description for subtitle corpus from 1992-2004.
</description>
<resourceShortName xml:lang="fi">YLE-korpus</resourceShortName>
<metaShareId>NOT_DEFINED_FOR_V2</metaShareId>
<identifier>http://urn.fi/urn:nbn:fi:lb-20140730134</identifier>
</identificationInfo>
<distributionInfo ComponentId="clarin.eu:cr1:c_1352813745459">
<availability>underNegotiation</availability>
<licenceInfo ComponentId="clarin.eu:cr1:c_1352813745464">
<licence>underNegotiation</licence>
<distributionAccessMedium>CD-ROM</distributionAccessMedium>
<userNature>academic</userNature>
<licensorPerson ComponentId="clarin.eu:cr1:c_1352813745465">
<role>licensor</role>
<personInfo ComponentId="clarin.eu:cr1:c_1349361150746">
<surname xml:lang="en">Lisensoija</surname>
<givenName xml:lang="en">Late</givenName>
<sex>male</sex>
<communicationInfo ComponentId="clarin.eu:cr1:c_1352813745460">
<email>[email protected]</email>
</communicationInfo>
<affiliation ComponentId="clarin.eu:cr1:c_1352813745462">
<role>affiliation</role>
<organizationInfo ComponentId="clarin.eu:cr1:c_1352813745461">
<organizationName xml:lang="fi">Itä-Suomen yliopisto</organizationName>
<organizationName xml:lang="en">University of Eastern Finland</organizationName>
<organizationShortName xml:lang="en">UEF</organizationShortName>
<communicationInfo ComponentId="clarin.eu:cr1:c_1352813745460">
<email>[email protected]</email>
<url>http://www.uef.fi/uef/english</url>
<url>https://ror.org/00cyydd11</url>
<country>Finland</country>
</communicationInfo>
</organizationInfo>
</affiliation>
</personInfo>
</licensorPerson>
<distributionRightsHolderPerson ComponentId="clarin.eu:cr1:c_1352813745466">
<role>distributionRightsHolder</role>
<personInfo ComponentId="clarin.eu:cr1:c_1349361150746">
<surname xml:lang="en">Lisensoija</surname>
<givenName xml:lang="en">Late</givenName>
<sex>male</sex>
<communicationInfo ComponentId="clarin.eu:cr1:c_1352813745460">
<email>[email protected]</email>
</communicationInfo>
<affiliation ComponentId="clarin.eu:cr1:c_1352813745462">
<role>affiliation</role>
<organizationInfo ComponentId="clarin.eu:cr1:c_1352813745461">
<organizationName xml:lang="fi">Itä-Suomen yliopisto</organizationName>
<organizationName xml:lang="en">University of Eastern Finland</organizationName>
<organizationShortName xml:lang="en">UEF</organizationShortName>
<communicationInfo ComponentId="clarin.eu:cr1:c_1352813745460">
<email>[email protected]</email>
<url>http://www.uef.fi/uef/english</url>
<url>https://ror.org/00cyydd11</url>
<country>Finland</country>
</communicationInfo>
</organizationInfo>
</affiliation>
</personInfo>
</distributionRightsHolderPerson>
</licenceInfo>
<iprHolderPerson ComponentId="clarin.eu:cr1:c_1352813745463">
<role>iprHolder</role>
<personInfo ComponentId="clarin.eu:cr1:c_1349361150746">
<surname xml:lang="en">Lisensoija</surname>
<givenName xml:lang="en">Late</givenName>
<sex>male</sex>
<communicationInfo ComponentId="clarin.eu:cr1:c_1352813745460">
<email>[email protected]</email>
</communicationInfo>
<affiliation ComponentId="clarin.eu:cr1:c_1352813745462">
<role>affiliation</role>
<organizationInfo ComponentId="clarin.eu:cr1:c_1352813745461">
<organizationName xml:lang="fi">Itä-Suomen yliopisto</organizationName>
<organizationName xml:lang="en">University of Eastern Finland</organizationName>
<organizationShortName xml:lang="en">UEF</organizationShortName>
<communicationInfo ComponentId="clarin.eu:cr1:c_1352813745460">
<email>[email protected]</email>
<url>http://www.uef.fi/uef/english</url>
<url>https://ror.org/00cyydd11</url>
<country>Finland</country>
</communicationInfo>
</organizationInfo>
</affiliation>
</personInfo>
</iprHolderPerson>
</distributionInfo>
<contactPerson ComponentId="clarin.eu:cr1:c_1352813745468">
<role>contactPerson</role>
<personInfo ComponentId="clarin.eu:cr1:c_1349361150746">
<surname xml:lang="en">Lisensoija</surname>
<givenName xml:lang="en">Late</givenName>
<sex>male</sex>
<communicationInfo ComponentId="clarin.eu:cr1:c_1352813745460">
<email>[email protected]</email>
</communicationInfo>
<affiliation ComponentId="clarin.eu:cr1:c_1352813745462">
<role>affiliation</role>
<organizationInfo ComponentId="clarin.eu:cr1:c_1352813745461">
<organizationName xml:lang="fi">Itä-Suomen yliopisto</organizationName>
<organizationName xml:lang="en">University of Eastern Finland</organizationName>
<organizationShortName xml:lang="en">UEF</organizationShortName>
<communicationInfo ComponentId="clarin.eu:cr1:c_1352813745460">
<email>[email protected]</email>
<url>http://www.uef.fi/uef/english</url>
<url>https://ror.org/00cyydd11</url>
<country>Finland</country>
</communicationInfo>
</organizationInfo>
</affiliation>
</personInfo>
</contactPerson>
<metadataInfo ComponentId="clarin.eu:cr1:c_1349361150745">
<metadataCreationDate>2012-08-02</metadataCreationDate>
<metadataLanguageName>Finnish</metadataLanguageName>
<metadataLanguageName>English</metadataLanguageName>
<metadataLanguageId>Fi</metadataLanguageId>
<metadataLanguageId>en</metadataLanguageId>
<metadataLastDateUpdated>2014-04-24</metadataLastDateUpdated>
</metadataInfo>
<corpusInfo ComponentId="clarin.eu:cr1:c_1355150532309">
<resourceType>corpus</resourceType>
<corpusMediaType ComponentId="clarin.eu:cr1:c_1355150532310">
<corpusTextInfo ComponentId="clarin.eu:cr1:c_1355150532311">
<mediaType>text</mediaType>
<lingualityInfo ComponentId="clarin.eu:cr1:c_1355150532313">
<lingualityType>multilingual</lingualityType>
<multilingualityType>multilingualSingleText</multilingualityType>
</lingualityInfo>
<languageInfo ComponentId="clarin.eu:cr1:c_1355150532314">
<languageId>Fi</languageId>
<languageName>Finnish</languageName>
</languageInfo>
<languageInfo ComponentId="clarin.eu:cr1:c_1355150532314">
<languageId>En</languageId>
<languageName>English</languageName>
</languageInfo>
<languageInfo ComponentId="clarin.eu:cr1:c_1355150532314">
<languageId>Sv</languageId>
<languageName>Swedish</languageName>
</languageInfo>
<languageInfo ComponentId="clarin.eu:cr1:c_1355150532314">
<languageId>smi</languageId>
<languageName>Sami languages</languageName>
</languageInfo>
<modalityInfo ComponentId="clarin.eu:cr1:c_1355150532318">
<modalityType>spokenLanguage</modalityType>
</modalityInfo>
<sizeInfo ComponentId="clarin.eu:cr1:c_1353678848785">
<size>100000000</size>
<sizeUnit>words</sizeUnit>
</sizeInfo>
</corpusTextInfo>
</corpusMediaType>
</corpusInfo>
</resourceInfo>
</Components>
</CMD>
</metadata>
</record>
18 changes: 18 additions & 0 deletions tests/test_metadata_parser.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -379,3 +379,21 @@ def test_multiple_names_for_actor():
actors = record._get_actors()
assert len(actors) == 1
assert actors[0]["person"]["name"] == "Carl Gustaf Bernadotte"


def test_publisher_person():
"""
Check that personal information for a publisher is correctly extracted.
This is not properly covered with the other test data, as it is more common that the
publisher is an organization.
"""
record = MSRecordParser(
_get_file_as_lxml(
"tests/test_data/kielipankki_record_sample_with_publisher_person.xml"
)
)
actors = record.to_dict(data_catalog="catalog_id")["actors"]
assert len(actors) == 1
assert "publisher" in actors[0]["roles"]
assert actors[0]["person"]["name"] == "Late Lisensoija"

0 comments on commit 5e23213

Please sign in to comment.