# baseURI: https://www.archives.gov/files/lod/dpframework/id/NF00833

@prefix : <https://www.archives.gov/files/lod/dpframework/schema> .
@prefix dcterms: <http://purl.org/dc/terms/> .
@prefix nara: <https://www.archives.gov/data/lod/dpframework/def/> .
@prefix naraid: <https://www.archives.gov/data/lod/dpframework/id/> .
@prefix owl: <http://www.w3.org/2002/07/owl#> .
@prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .
@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#> .
@prefix wikidata: <http://www.wikidata.org/entity/> .
@prefix xsd: <http://www.w3.org/2001/XMLSchema#> .

naraid:NF00833
  a nara:FileFormat ;
  dcterms:description "A CDX file is a plain text file that accompanies ARC and WARC files. It consists of individual lines of text, each of which summarizes a single web document. CDX files are created as websites are crawled and are used by tools like pywb and OpenWayback to look up captures in WARC files. CDX has an open specification; the 2015 specification has been proposed as an International Internet Preservation Consortium (IIPC) standard but not officially adopted. It notes that default usage has changed for the Internet Archive and that some fields from the 2006 specification appear to be obsolete. It is recommended to retain CDX files as-is or transform them into OpenWayback CDXJ." ;
  dcterms:identifier "NF00833" ;
  rdfs:label "NF00833" ;
  wikidata:p1163 "text/plain" ;
  wikidata:p1195 "cdx" ;
  wikidata:p2748 "https://www.nationalarchives.gov.uk/PRONOM/fmt/869" ;
  wikidata:p3266 "https://www.loc.gov/preservation/digital/formats/fdd/fdd000590.shtml" ;
  wikidata:p973 "https://iipc.github.io/warc-specifications/specifications/cdx-format/cdx-2006/" ;
  wikidata:p973 "https://www.wikidata.org/wiki/Q47538013" ;
  nara:category naraid:Web ;
  nara:formatName "CDX Internet Archive Index" ;
  nara:preservationAction naraid:Retain ;
  nara:preservationPlan "Retain or transform to CDXJ" ;
  nara:riskLevel naraid:Low ;
  nara:tools """pywb or OpenWayback for the processing of the WARC contents
""" ;
  <https://www.archives.gov/files/lod/dpframework/schemaArchiveTeamURL> "http://fileformats.archiveteam.org/wiki/CDX" ;
.
<https://www.archives.gov/files/lod/dpframework/id/NF00833>
  a owl:Ontology ;
.
