{ "@context": [ "https://w3id.org/codemeta/3.0", "https://w3id.org/software-iodata", "https://w3id.org/nwo-research-fields", "https://raw.githubusercontent.com/jantman/repostatus.org/master/badges/latest/ontology.jsonld", "https://w3id.org/research-technology-readiness-levels", "https://schema.org", "https://w3id.org/software-types" ], "@id": "https://tools.clariah.nl/foliautils/0.23", "@type": "SoftwareSourceCode", "applicationSuite": "FoLiA", "author": [ { "@type": "Person", "affiliation": { "@id": "https://www.ru.nl/clst", "@type": "Organization", "name": "Centre for Language and Speech Technology", "parentOrganization": { "@id": "https://www.ru.nl/cls", "@type": "Organization", "name": "Centre for Language Studies", "parentOrganization": { "@id": "https://www.ru.nl", "@type": "Organization", "location": { "@type": "Place", "name": "Nijmegen" }, "name": "Radboud University", "url": "https://www.ru.nl" }, "url": "https://www.ru.nl/cls" }, "url": "https://www.ru.nl/clst" }, "email": "ko.vandersloot@let.ru.nl", "familyName": "van der Sloot", "givenName": "Ko" }, { "@id": "https://orcid.org/0000-0002-1046-0006", "@type": "Person", "affiliation": [ { "@id": "https://www.ru.nl/clst", "@type": "Organization", "name": "Centre for Language and Speech Technology", "parentOrganization": { "@id": "https://www.ru.nl/cls", "@type": "Organization", "name": "Centre for Language Studies", "parentOrganization": { "@id": "https://www.ru.nl", "@type": "Organization", "location": { "@type": "Place", "name": "Nijmegen" }, "name": "Radboud University", "url": "https://www.ru.nl" }, "url": "https://www.ru.nl/cls" }, "url": "https://www.ru.nl/clst" }, { "@id": "https://huc.knaw.nl", "@type": "Organization", "name": [ "Humanities Cluster", "KNAW Humanities Cluster" ], "parentOrganization": { "@id": "https://knaw.nl", "@type": "Organization", "location": { "@type": "Place", "name": "Amsterdam" }, "name": "KNAW", "url": "https://knaw.nl" }, "url": "https://huc.knaw.nl" }, { "@id": "https://www.ru.nl/cls", "@type": "Organization", "name": "Centre for Language Studies", "parentOrganization": { "@id": "https://www.ru.nl", "@type": "Organization", "location": { "@type": "Place", "name": "Nijmegen" }, "name": "Radboud University", "url": "https://www.ru.nl" }, "url": "https://www.ru.nl/cls" }, { "@id": "https://knaw.huc.nl" } ], "email": "proycon@anaproy.nl", "familyName": "van Gompel", "givenName": "Maarten", "position": 4, "url": "https://proycon.anaproy.nl" } ], "codeRepository": "https://github.com/languagemachines/foliautils", "continuousIntegration": { "@id": "https://travis-ci.org/LanguageMachines/foliautils" }, "contributor": [ { "@type": "Person", "affiliation": { "@id": "https://www.ru.nl/clst", "@type": "Organization", "name": "Centre for Language and Speech Technology", "parentOrganization": { "@id": "https://www.ru.nl/cls", "@type": "Organization", "name": "Centre for Language Studies", "parentOrganization": { "@id": "https://www.ru.nl", "@type": "Organization", "location": { "@type": "Place", "name": "Nijmegen" }, "name": "Radboud University", "url": "https://www.ru.nl" }, "url": "https://www.ru.nl/cls" }, "url": "https://www.ru.nl/clst" }, "email": "ko.vandersloot@let.ru.nl", "familyName": "van der Sloot", "givenName": "Ko" }, { "@id": "https://orcid.org/0000-0002-1046-0006", "@type": "Person", "affiliation": [ { "@id": "https://www.ru.nl/clst", "@type": "Organization", "name": "Centre for Language and Speech Technology", "parentOrganization": { "@id": "https://www.ru.nl/cls", "@type": "Organization", "name": "Centre for Language Studies", "parentOrganization": { "@id": "https://www.ru.nl", "@type": "Organization", "location": { "@type": "Place", "name": "Nijmegen" }, "name": "Radboud University", "url": "https://www.ru.nl" }, "url": "https://www.ru.nl/cls" }, "url": "https://www.ru.nl/clst" }, { "@id": "https://huc.knaw.nl", "@type": "Organization", "name": [ "Humanities Cluster", "KNAW Humanities Cluster" ], "parentOrganization": { "@id": "https://knaw.nl", "@type": "Organization", "location": { "@type": "Place", "name": "Amsterdam" }, "name": "KNAW", "url": "https://knaw.nl" }, "url": "https://huc.knaw.nl" }, { "@id": "https://www.ru.nl/cls", "@type": "Organization", "name": "Centre for Language Studies", "parentOrganization": { "@id": "https://www.ru.nl", "@type": "Organization", "location": { "@type": "Place", "name": "Nijmegen" }, "name": "Radboud University", "url": "https://www.ru.nl" }, "url": "https://www.ru.nl/cls" }, { "@id": "https://knaw.huc.nl" } ], "email": "proycon@anaproy.nl", "familyName": "van Gompel", "givenName": "Maarten", "position": 4, "url": "https://proycon.anaproy.nl" } ], "description": "Command-line utilities for working with the Format for Linguistic Annotation (FoLiA).", "developmentStatus": { "@id": "https://www.repostatus.org/#active", "@type": "skos:Concept", "og:image": "https://www.repostatus.org/badges/latest/active.svg", "skos:definition": "The project has reached a stable, usable state and is being actively developed.", "skos:inScheme": "https://www.repostatus.org", "skos:prefLabel": "Active" }, "https://github.com/proycon/codemetapy/errors": 0, "https://github.com/proycon/codemetapy/log": "(log file starts at Thu Jun 18 03:07:56 UTC 2026)\n\n[harvester info] --> Processing foliautils (https://github.com/languagemachines/foliautils) [Thu Jun 18 03:07:56 UTC 2026]\n\n[harvester info] Git updating cached clone of https://github.com/languagemachines/foliautils...\n\n[harvester info] Found release v0.23\n\n[harvester info] Using 'v0.23'\n\n[harvester info] Git reference: v0.23\n\n[harvester info] Scanning directory /tmp/codemeta-harvester.cache/foliautils for harvestable resources...\n\n[harvester info] found codemeta.json for foliautils (md5sum 74a53e2b5996399c452d74b8594d4daf); **NOTE: this is considered authoritative and most other detection methods will be skipped now!**\n\n[harvester info] Inferring repostatus information from git activity (used only as a fallback if not explicitly provided)...\n\n[harvester info] Inferred repostatus https://www.repostatus.org/#active\n\n[harvester info] Looking for repostatus information in README.md in master branch...\n\n[harvester info] Found repostatus (master branch) https://www.repostatus.org/#active\n\n[harvester info] Looking for repostatus information in README in master branch...\n\n[harvester info] Parsing MAINTAINERS from master branch...\n\n[harvester info] Setting group FoLiA\n\n[harvester info] Reconciliating: codemetapy --baseuri https://tools.clariah.nl --baseuri https://tools.clariah.nl --includecontext --addcontext https://w3id.org/nwo-research-fields --addcontext https://w3id.org/research-technology-readiness-levels --addcontextgraph https://vocabs.dariah.eu/rest/v1/tadirah/data?format=text/turtle --trl --identifier \"foliautils\" --codeRepository \"https://github.com/languagemachines/foliautils\" --validate /etc/software.ttl --released --enrich --textv \"Please consult the CLARIAH Software Metadata Requirements at https://github.com/CLARIAH/clariah-plus/blob/main/requirements/software-metadata-requirements.md for an in-depth explanation of any found problems\" -O /tmp/out/foliautils.codemeta.json /tmp/codemeta-harvester.cache//tmp/99-repostatus.foliautils.codemeta.json /tmp/codemeta-harvester.cache//tmp/10-jsonld.foliautils.codemeta.json /tmp/codemeta-harvester.cache//tmp/05-repostatus.foliautils.codemeta.json /tmp/codemeta-harvester.cache//tmp/05-maintainers.foliautils.codemeta.json /tmp/codemeta-harvester.cache//tmp/04-applicationSuite.foliautils.codemeta.json \n\n-- begin log --\n\nPassed 5 files/sources but specified 0 input types! Automatically guessing types...\n\nDetected input types: [('/tmp/codemeta-harvester.cache//tmp/99-repostatus.foliautils.codemeta.json', 'json'), ('/tmp/codemeta-harvester.cache//tmp/10-jsonld.foliautils.codemeta.json', 'json'), ('/tmp/codemeta-harvester.cache//tmp/05-repostatus.foliautils.codemeta.json', 'json'), ('/tmp/codemeta-harvester.cache//tmp/05-maintainers.foliautils.codemeta.json', 'json'), ('/tmp/codemeta-harvester.cache//tmp/04-applicationSuite.foliautils.codemeta.json', 'json')]\n\nAdding to contextgraph: /tmp/turtle\n\nInitial URI automatically generated, may be overriden later: https://tools.clariah.nl/foliautils\n\nProcessing source #1 of 5\n\nParsing json-ld file from /tmp/codemeta-harvester.cache//tmp/99-repostatus.foliautils.codemeta.json\n\n NOTE: Not a valid JSON-LD document, @context missing! Attempting to inject automatically...\n\n Injected (possibly temporary) URI https://tools.clariah.nl/foliautils\n\n[CODEMETA COMPOSITION (https://tools.clariah.nl/foliautils)] processed 1 new triples, total is now 2\n\nProcessing source #2 of 5\n\nParsing json-ld file from /tmp/codemeta-harvester.cache//tmp/10-jsonld.foliautils.codemeta.json\n\n Injected (possibly temporary) URI https://tools.clariah.nl/foliautils\n\n[CODEMETA 2 TO 3] Updating contIntegration -> continuousIntegration\n\n[CODEMETA 2 TO 3] Updating targetProduct -> isSourceCodeOf\n\n[CODEMETA 2 TO 3] Updating targetProduct -> isSourceCodeOf\n\n[CODEMETA 2 TO 3] Updating targetProduct -> isSourceCodeOf\n\n[CODEMETA 2 TO 3] Updating targetProduct -> isSourceCodeOf\n\n[CODEMETA 2 TO 3] Updating targetProduct -> isSourceCodeOf\n\n[CODEMETA 2 TO 3] Updating targetProduct -> isSourceCodeOf\n\n[CODEMETA 2 TO 3] Updating targetProduct -> isSourceCodeOf\n\n[CODEMETA 2 TO 3] Updating targetProduct -> isSourceCodeOf\n\n[CODEMETA 2 TO 3] Updating targetProduct -> isSourceCodeOf\n\n[CODEMETA 2 TO 3] Updating targetProduct -> isSourceCodeOf\n\n[CODEMETA 2 TO 3] Updating targetProduct -> isSourceCodeOf\n\n[CODEMETA 2 TO 3] Updating targetProduct -> isSourceCodeOf\n\n[CODEMETA 2 TO 3] Updating targetProduct -> isSourceCodeOf\n\n[CODEMETA CORRECTION (foliautils)] automatically converting spdx license URI from https:// to http:///\n\n[CODEMETA COMPOSITION (foliautils)] processed 198 new triples, total is now 198\n\nProcessing source #3 of 5\n\nParsing json-ld file from /tmp/codemeta-harvester.cache//tmp/05-repostatus.foliautils.codemeta.json\n\n NOTE: Not a valid JSON-LD document, @context missing! Attempting to inject automatically...\n\n Injected (possibly temporary) URI https://tools.clariah.nl/foliautils\n\n[CODEMETA COMPOSITION (foliautils)] processed 1 new triples, total is now 198\n\nProcessing source #4 of 5\n\nParsing json-ld file from /tmp/codemeta-harvester.cache//tmp/05-maintainers.foliautils.codemeta.json\n\n Found main resource with URI https://tools.clariah.nl/maintainers/snapshot\n\n Injected (possibly temporary) URI https://tools.clariah.nl/foliautils\n\n[CODEMETA COMPOSITION (foliautils)] processed 14 new triples, total is now 211\n\nProcessing source #5 of 5\n\nParsing json-ld file from /tmp/codemeta-harvester.cache//tmp/04-applicationSuite.foliautils.codemeta.json\n\n NOTE: Not a valid JSON-LD document, @context missing! Attempting to inject automatically...\n\n Injected (possibly temporary) URI https://tools.clariah.nl/foliautils\n\n[CODEMETA COMPOSITION (foliautils)] processed 1 new triples, total is now 212\n\nRemapping URI to (possibly) new identifier and version component: https://tools.clariah.nl/foliautils -> https://tools.clariah.nl/foliautils/0.23\n\n[CODEMETA VALIDATION (foliautils)] done\n\n[CODEMETA ENRICHMENT (foliautils)] adding author https://tools.clariah.nl/stub/H-6ab7142cf0e9b4ea as contributor\n\n[CODEMETA ENRICHMENT (foliautils)] adding author https://orcid.org/0000-0002-1046-0006 as contributor\n\n[CODEMETA ENRICHMENT (foliautils)] adding affiliation(s) of first author as producer\n\nVALIDATION https://tools.clariah.nl/foliautils/0.23 #1: Warning: Documentation *SHOULD* be expressed (This is missing in the metadata)\n\nVALIDATION https://tools.clariah.nl/foliautils/0.23 #2: Info: The funder *SHOULD* be acknowledged (This is missing in the metadata)\n\nVALIDATION https://tools.clariah.nl/foliautils/0.23 #3: Info: The technology readiness level *SHOULD* be expressed (This is missing in the metadata)\n\nVALIDATION https://tools.clariah.nl/foliautils/0.23 #4: Info: A research domain *SHOULD* be expressed as a category using the NWO Research Fields vocabulary, if applicable (This is missing in the metadata)\n\nVALIDATION https://tools.clariah.nl/foliautils/0.23 #5: Info: A research activity *SHOULD* be expressed as a category using the TaDiRaH vocabulary (This is missing in the metadata)\n\n-- end log --\n\n[harvester info] Output written to /tmp/out/foliautils.codemeta.json\n\n[harvester info] <-- Finished processing foliautils (https://github.com/languagemachines/foliautils) [Thu Jun 18 03:08:01 UTC 2026]\n", "identifier": "foliautils", "isSourceCodeOf": [ { "@type": "CommandLineApplication", "consumesData": { "@type": "TextDigitalDocument", "encodingFormat": "application/folia+xml" }, "description": "Convert FoLiA documents into plain text", "executableName": "FoLiA-2text", "name": "FoLiA-2text", "producesData": { "@type": "TextDigitalDocument", "encodingFormat": "text/plain" } }, { "@type": "CommandLineApplication", "description": "Convert ALTO DIDL files into a series of FoLiA documents", "executableName": "FoLiA-alto", "name": "FoLiA-alto" }, { "@type": "CommandLineApplication", "consumesData": { "@type": "TextDigitalDocument", "encodingFormat": "application/folia+xml" }, "description": "FoLiA-clean will produce a cleaned up version of a FoLiA file, or a whole directory of FoLiA files, removing specified annotation types and specified text classes", "executableName": "FoLiA-clean", "name": "FoLiA-clean", "producesData": { "@type": "TextDigitalDocument", "encodingFormat": "application/folia+xml" } }, { "@type": "CommandLineApplication", "consumesData": { "@type": "Dataset", "encodingFormat": "text/tab-seperated-values" }, "description": "Collect n-gram statistics from tsv files produced by FoLiA-stats, aggregating results.", "executableName": "FoLiA-collect", "name": "FoLiA-collect", "producesData": { "@type": "Dataset", "encodingFormat": "text/tab-separated-values" } }, { "@type": "CommandLineApplication", "consumesData": { "@type": "TextDigitalDocument", "encodingFormat": "application/folia+xml" }, "description": "Correct FoLiA documents using correction candidates generated by TICCL-rank (from ticcltools)", "executableName": "FoLiA-correct", "name": "FoLiA-correct", "producesData": { "@type": "TextDigitalDocument", "encodingFormat": "application/folia+xml" } }, { "@type": "CommandLineApplication", "consumesData": { "@type": "TextDigitalDocument", "encodingFormat": "text/html" }, "description": "Convert hOCR (as outputted by Tesseract) to FoLiA", "executableName": "FoLiA-hocr", "name": "FoLiA-hocr", "producesData": { "@type": "TextDigitalDocument", "encodingFormat": "application/folia+xml" } }, { "@type": "CommandLineApplication", "consumesData": { "@type": "TextDigitalDocument", "encodingFormat": "application/folia+xml" }, "description": "Count words in a series of FoLiA documents and compute IDF statistics, which are outputted to a tsv file", "executableName": "FoLiA-idf", "name": "FoLiA-idf", "producesData": { "@type": "Dataset", "encodingFormat": "text/tab-separated-values" } }, { "@type": "CommandLineApplication", "consumesData": { "@type": "TextDigitalDocument", "encodingFormat": "application/folia+xml" }, "description": "Language Identification using textcat.", "executableName": "FoLiA-langcat", "name": "FoLiA-langcat", "producesData": { "@type": "TextDigitalDocument", "encodingFormat": "application/folia+xml" } }, { "@type": "CommandLineApplication", "consumesData": { "@type": "TextDigitalDocument", "encodingFormat": "application/page+xml" }, "description": "Convert PAGE XML to FoLiA", "executableName": "FoLiA-page", "name": "FoLiA-page", "producesData": { "@type": "TextDigitalDocument", "encodingFormat": "application/folia+xml" } }, { "@type": "CommandLineApplication", "description": "Convert Political Maskup XML to FoLiA", "executableName": "/FoLiA-pm", "name": "FoLiA-pm", "producesData": { "@type": "TextDigitalDocument", "encodingFormat": "application/folia+xml" } }, { "@type": "CommandLineApplication", "consumesData": { "@type": "TextDigitalDocument", "encodingFormat": "application/folia+xml" }, "description": "Gather n-gram statistics over a series of FoLiA documents", "executableName": "FoLiA-stats", "name": "FoLiA-stats", "producesData": { "@type": "Dataset", "encodingFormat": "text/tab-separated-values" } }, { "@type": "CommandLineApplication", "consumesData": { "@type": "TextDigitalDocument", "encodingFormat": "text/plain" }, "description": "Convert plain text to FoLiA, the output will contain only

and nodes. See ucto or rst2folia (FoLiA-tools) for alternatives.", "executableName": "FoLiA-txt", "name": "FoLiA-txt", "producesData": { "@type": "TextDigitalDocument", "encodingFormat": "application/folia+xml" } }, { "@type": "CommandLineApplication", "consumesData": { "@type": "TextDigitalDocument", "encodingFormat": "application/folia+xml" }, "description": "Simple word-by-word translator on the basis of a dictonary and/or rewrite rules", "executableName": "FoLiA-wordtranslate", "name": "FoLiA-wordtranslate", "producesData": { "@type": "TextDigitalDocument", "encodingFormat": "application/folia+xml" } } ], "issueTracker": "https://github.com/LanguageMachines/foliautils/issues", "keywords": [ "folia", "linguistic annotation", "natural language processing", "nlp", "xml" ], "license": { "@id": "http://spdx.org/licenses/GPL-3.0-only", "name": "GNU General Public License v3" }, "maintainer": [ { "@id": "https://tools.clariah.nl/person/maarten-van-gompel", "@type": "Person", "affiliation": [ { "@id": "https://tools.clariah.nl/org/knaw-humanities-cluster", "@type": "Organization", "name": "KNAW Humanities Cluster", "url": "https://huc.knaw.nl/" }, { "@id": "https://tools.clariah.nl/org/knaw-humanities-cluster-clst-radboud-university", "@type": "Organization", "name": "KNAW Humanities Cluster & CLST, Radboud University" } ], "email": "proycon@anaproy.nl", "familyName": [ "van Gompel", "van gompel" ], "givenName": "Maarten", "url": "https://proycon.anaproy.nl" }, { "@id": "https://tools.clariah.nl/person/ko-van-der-sloot", "@type": "Person", "email": [ "K.vanderSloot@let.ru.nl", "Ko.vanderSloot@ziggo.nl" ], "familyName": "van der Sloot", "givenName": "Ko" } ], "name": "foliautils", "operatingSystem": "POSIX", "owl:sameAs": { "@id": "https://tools.clariah.nl/maintainers/snapshot" }, "producer": { "@id": "https://www.ru.nl/clst", "@type": "Organization", "name": "Centre for Language and Speech Technology", "parentOrganization": { "@id": "https://www.ru.nl/cls", "@type": "Organization", "name": "Centre for Language Studies", "parentOrganization": { "@id": "https://www.ru.nl", "@type": "Organization", "location": { "@type": "Place", "name": "Nijmegen" }, "name": "Radboud University", "url": "https://www.ru.nl" }, "url": "https://www.ru.nl/cls" }, "url": "https://www.ru.nl/clst" }, "programmingLanguage": { "@type": "ComputerLanguage", "identifier": "c++", "name": "C++" }, "readme": "https://github.com/LanguageMachines/foliautils/blob/master/README.md", "referencePublication": [ { "@type": "ScholarlyArticle", "author": [ "Maarten van Gompel", "Martin Reynaert" ], "isPartOf": { "@type": "PublicationIssue", "datePublised": "2014", "issue": "3", "name": "Computational Linguistics in the Netherlands Journal" }, "name": "FoLiA: A practical XML format for linguistic annotation - a descriptive and comparative study", "pageEnd": 81, "pageStart": 63, "url": "http://www.clinjournal.org/sites/clinjournal.org/files/05-vanGompel-Reynaert-CLIN2013.pdf" }, { "@type": "TechArticle", "author": [ "Maarten van Gompel" ], "isPartOf": { "@type": "PublicationIssue", "datePublised": "2014", "issue": "14-01", "location": "Nijmegen, the Netherlands", "name": "Language and Speech Technology Technical Report Series" }, "name": "FoLiA: Format for Linguistic Annotation, Documentation", "url": "https://github.com/proycon/folia/raw/master/docs/folia.pdf" } ], "releaseNotes": "https://github.com/LanguageMachines/foliautils/releases", "review": { "@id": "https://tools.clariah.nl/validation/N1aa00d06ed6042cd5077125811400e3c", "@type": "Review", "author": [ "codemetapy validator using software.ttl" ], "datePublished": "2026-06-18 03:08:00", "name": "Automatic software metadata validation report for foliautils 0.23", "reviewBody": "Please consult the CLARIAH Software Metadata Requirements at https://github.com/CLARIAH/clariah-plus/blob/main/requirements/software-metadata-requirements.md for an in-depth explanation of any found problems\n\nValidation of foliautils 0.23 was successful (score=3/5), but there are some warnings which should be addressed:\n\n1. Warning: Documentation *SHOULD* be expressed (This is missing in the metadata)\n2. Info: The funder *SHOULD* be acknowledged (This is missing in the metadata)\n3. Info: The technology readiness level *SHOULD* be expressed (This is missing in the metadata)\n4. Info: A research domain *SHOULD* be expressed as a category using the NWO Research Fields vocabulary, if applicable (This is missing in the metadata)\n5. Info: A research activity *SHOULD* be expressed as a category using the TaDiRaH vocabulary (This is missing in the metadata)", "reviewRating": 3 }, "softwareRequirements": [ { "@type": "SoftwareApplication", "identifier": "icu", "name": "icu" }, { "@type": "SoftwareApplication", "identifier": "libfolia", "name": "libfolia" }, { "@type": "SoftwareApplication", "identifier": "libxml2", "name": "libxml2" }, { "@type": "SoftwareApplication", "identifier": "ticcutils", "name": "ticcutils" } ], "sourceOrganization": { "@id": "https://www.ru.nl/clst", "@type": "Organization", "name": "Centre for Language and Speech Technology", "parentOrganization": { "@id": "https://www.ru.nl/cls", "@type": "Organization", "name": "Centre for Language Studies", "parentOrganization": { "@id": "https://www.ru.nl", "@type": "Organization", "location": { "@type": "Place", "name": "Nijmegen" }, "name": "Radboud University", "url": "https://www.ru.nl" }, "url": "https://www.ru.nl/cls" }, "url": "https://www.ru.nl/clst" }, "url": "https://github.com/LanguageMachines/foliautils", "version": "0.23" }