{
  "_id": "6ad6b25469e274306bae7175",
  "Package": "marcxmlr",
  "Title": "Efficient MARCXML Processing and Record Querying",
  "Version": "0.5.0",
  "Authors@R": "person(\"Lorenzo\", \"Isella\", email = \"lorenzo.isella@gmail.com\",\nrole = c(\"aut\", \"cre\"))",
  "Description": "Parses Machine-Readable Cataloging ('MARC 21') XML\n<https://www.loc.gov/standards/marcxml/> into a canonical tidy\nlong representation while preserving leaders, control fields,\ndata fields, indicators, repeated fields, repeated subfields,\nand source order. Provides in-memory reading, batched\nconversion to 'Parquet', and reconstruction of MARCXML from\ncanonical data. Supports MARC-aware selection of complete\nrecords before materialisation using native XML prefiltering,\nand after materialisation on canonical tables and 'Arrow'\ndatasets. Includes structural diagnostics for in-memory and\n'Arrow'-backed representations, optional recovery from\nmalformed MARC records, and local parallel processing.",
  "License": "MIT + file LICENSE",
  "URL": "https://github.com/larry77/marcxmlr",
  "BugReports": "https://github.com/larry77/marcxmlr/issues",
  "Encoding": "UTF-8",
  "Language": "en-US",
  "VignetteBuilder": "knitr",
  "Config/testthat/edition": "3",
  "SystemRequirements": "libxml2 (>= 2.9.0), Expat (optional, for record\nfiltering)",
  "NeedsCompilation": "yes",
  "Config/roxygen2/version": "8.1.0",
  "Packaged": {
    "Date": "2026-10-20 00:08:59 UTC",
    "User": "root"
  },
  "Author": "Lorenzo Isella [aut, cre]",
  "Maintainer": "Lorenzo Isella <lorenzo.isella@gmail.com>",
  "Config/pak/sysreqs": "libxml2-dev",
  "Repository": "https://cran.r-universe.dev",
  "Date/Publication": "2026-10-19 09:00:08 UTC",
  "RemoteUrl": "https://github.com/cran/marcxmlr",
  "RemoteRef": "HEAD",
  "RemoteSha": "43000f6d12a1c14655d9cb0d49b6387b99ebfd47",
  "_user": "cran",
  "_type": "src",
  "_file": "marcxmlr_0.5.0.tar.gz",
  "_fileid": "https://r2.ropensci.org/1c579bb90069e8c1e924d76183903805d625515bc175754ce730d9d0bc31469e",
  "_filesize": 733446,
  "_sha256": "1c579bb90069e8c1e924d76183903805d625515bc175754ce730d9d0bc31469e",
  "_expires": "2027-01-28T00:14:09.000Z",
  "_created": "2026-10-20T00:08:59.000Z",
  "_published": "2026-10-20T00:14:12.087Z",
  "_upstream": "https://github.com/cran/marcxmlr",
  "_status": "success",
  "_maintainer": {
    "name": "Lorenzo Isella",
    "email": "lorenzo.isella@gmail.com",
    "login": "larry77",
    "description": "",
    "uuid": 502614
  },
  "_jobs": [
    {
      "job": 118378454594,
      "time": 121,
      "config": "linux-devel-arm64",
      "r": "4.7.0",
      "check": "NOTE",
      "artifact": "12230188364"
    },
    {
      "job": 118378454560,
      "time": 132,
      "config": "linux-devel-x86_64",
      "r": "4.7.0",
      "check": "NOTE",
      "artifact": "12230833616"
    },
    {
      "job": 118378454620,
      "time": 121,
      "config": "linux-release-arm64",
      "r": "4.6.1",
      "check": "NOTE",
      "artifact": "12230753741"
    },
    {
      "job": 118378454533,
      "time": 152,
      "config": "linux-release-x86_64",
      "r": "4.6.1",
      "check": "NOTE",
      "artifact": "12230619018"
    },
    {
      "job": 118377314661,
      "time": 200,
      "config": "source",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "12231067046"
    },
    {
      "job": 118378454312,
      "time": 124,
      "config": "wasm-release",
      "r": "4.6.0",
      "check": "OK",
      "artifact": "12230923583"
    },
    {
      "job": 118378454771,
      "time": 261,
      "config": "windows-devel-arm64",
      "r": "4.7.0",
      "check": "NOTE",
      "artifact": "12230898979"
    },
    {
      "job": 118378454410,
      "time": 181,
      "config": "windows-devel-x86_64",
      "r": "4.7.0",
      "check": "NOTE",
      "artifact": "12231317124"
    },
    {
      "job": 118378454443,
      "time": 210,
      "config": "windows-release-arm64",
      "r": "4.6.1",
      "check": "NOTE",
      "artifact": "12230299612"
    },
    {
      "job": 118378454651,
      "time": 129,
      "config": "windows-release-x86_64",
      "r": "4.6.1",
      "check": "NOTE",
      "artifact": "12230324457"
    }
  ],
  "_buildurl": "https://github.com/r-universe/cran/actions/runs/39345568056",
  "_commit": {
    "id": "43000f6d12a1c14655d9cb0d49b6387b99ebfd47",
    "author": "Lorenzo Isella <lorenzo.isella@gmail.com>",
    "committer": "cran-robot <csardi.gabor+cran@gmail.com>",
    "message": "version 0.5.0\n",
    "time": 1792400408
  },
  "_distro": "resolute",
  "_host": "GitHub-Actions",
  "_registered": true,
  "_dependencies": [
    {
      "package": "R",
      "version": ">= 4.1.0",
      "role": "Depends"
    },
    {
      "package": "future",
      "version": ">= 1.69.0",
      "role": "Imports"
    },
    {
      "package": "futurize",
      "role": "Imports"
    },
    {
      "package": "purrr",
      "version": ">= 1.0.0",
      "role": "Imports"
    },
    {
      "package": "rlang",
      "role": "Imports"
    },
    {
      "package": "stats",
      "role": "Imports"
    },
    {
      "package": "tibble",
      "version": ">= 3.0.0",
      "role": "Imports"
    },
    {
      "package": "xml2",
      "version": ">= 1.3.0",
      "role": "Imports"
    },
    {
      "package": "arrow",
      "role": "Suggests"
    },
    {
      "package": "dplyr",
      "role": "Suggests"
    },
    {
      "package": "future.mirai",
      "role": "Suggests"
    },
    {
      "package": "furrr",
      "role": "Suggests"
    },
    {
      "package": "knitr",
      "role": "Suggests"
    },
    {
      "package": "mori",
      "role": "Suggests"
    },
    {
      "package": "rmarkdown",
      "role": "Suggests"
    },
    {
      "package": "testthat",
      "version": ">= 3.0.0",
      "role": "Suggests"
    },
    {
      "package": "XML",
      "role": "Suggests"
    }
  ],
  "_owner": "cran",
  "_selfowned": false,
  "_usedby": 0,
  "_updates": [
    {
      "week": "2026-37",
      "n": 1
    },
    {
      "week": "2026-38",
      "n": 1
    },
    {
      "week": "2026-40",
      "n": 1
    },
    {
      "week": "2026-42",
      "n": 1
    },
    {
      "week": "2026-43",
      "n": 1
    }
  ],
  "_tags": [
    {
      "name": "0.1.0",
      "date": "2026-09-12"
    },
    {
      "name": "0.2.1",
      "date": "2026-09-20"
    },
    {
      "name": "0.3.1",
      "date": "2026-09-28"
    },
    {
      "name": "0.4.0",
      "date": "2026-10-12"
    },
    {
      "name": "0.5.0",
      "date": "2026-10-19"
    }
  ],
  "_stars": 0,
  "_contributors": [
    {
      "user": "larry77",
      "count": 5,
      "uuid": 502614
    }
  ],
  "_userbio": {
    "uuid": 6899542,
    "type": "organization",
    "name": "cran",
    "followers": 634,
    "description": "Unofficial read-only mirror of all CRAN R packages"
  },
  "_downloads": {
    "count": 663,
    "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/marcxmlr"
  },
  "_devurl": "https://github.com/larry77/marcxmlr",
  "_searchresults": 5,
  "_topics": [
    "libxml2",
    "expat"
  ],
  "_rbuild": "4.6.1",
  "_assets": [
    "extra/citation.cff",
    "extra/citation.html",
    "extra/citation.json",
    "extra/citation.txt",
    "extra/contents.json",
    "extra/manual.pdf",
    "extra/marcxmlr.html",
    "extra/NEWS.html",
    "extra/NEWS.txt",
    "extra/readme.html",
    "extra/readme.md",
    "LICENSE"
  ],
  "_homeurl": "https://github.com/larry77/marcxmlr",
  "_realowner": "larry77",
  "_cranurl": false,
  "_releases": [
    {
      "version": "0.1.0",
      "date": "2026-09-12"
    },
    {
      "version": "0.2.1",
      "date": "2026-09-20"
    },
    {
      "version": "0.3.1",
      "date": "2026-09-28"
    },
    {
      "version": "0.4.0",
      "date": "2026-10-12"
    },
    {
      "version": "0.5.0",
      "date": "2026-10-19"
    }
  ],
  "_exports": [
    "diagnose_canonical",
    "marc_filter_records",
    "marc_has",
    "marcxml_to_parquet",
    "read_marcxml",
    "write_marcxml"
  ],
  "_help": [
    {
      "page": "marcxmlr-package",
      "title": "marcxmlr: Faithful and Scalable MARCXML Parsing",
      "topics": [
        "marcxmlr-package",
        "marcxmlr"
      ]
    },
    {
      "page": "diagnose_canonical",
      "title": "Diagnose a canonical MARC representation",
      "topics": [
        "diagnose_canonical"
      ]
    },
    {
      "page": "marc_filter_records",
      "title": "Filter complete canonical MARC records",
      "topics": [
        "marc_filter_records"
      ]
    },
    {
      "page": "marc_has",
      "title": "Test whether a MARC record contains a matching field or subfield",
      "topics": [
        "marc_has",
        "Ops.marc_query"
      ]
    },
    {
      "page": "marcxml_to_parquet",
      "title": "Convert a MARCXML collection to a Parquet dataset",
      "topics": [
        "marcxml_to_parquet"
      ]
    },
    {
      "page": "read_marcxml",
      "title": "Read MARCXML into a canonical long tibble",
      "topics": [
        "read_marcxml"
      ]
    },
    {
      "page": "write_marcxml",
      "title": "Write a canonical MARC representation as MARCXML",
      "topics": [
        "write_marcxml"
      ]
    }
  ],
  "_readme": "https://github.com/cran/marcxmlr/raw/HEAD/README.md",
  "_rundeps": [
    "cli",
    "codetools",
    "digest",
    "future",
    "futurize",
    "globals",
    "glue",
    "lifecycle",
    "listenv",
    "magrittr",
    "parallelly",
    "pillar",
    "pkgconfig",
    "purrr",
    "rlang",
    "tibble",
    "utf8",
    "vctrs",
    "xml2"
  ],
  "_sysdeps": [
    {
      "shlib": "libxml2",
      "package": "libxml2-16",
      "headers": "libxml2-dev",
      "source": "libxml2",
      "version": "2.15.2+dfsg-0.1ubuntu0.3",
      "name": "libxml2",
      "homepage": "http://xmlsoft.org",
      "description": "GNOME XML library"
    },
    {
      "shlib": "libexpat",
      "package": "libexpat1",
      "headers": "libexpat1-dev",
      "source": "expat",
      "version": "2.7.4-1ubuntu0.2",
      "name": "expat",
      "homepage": "https://libexpat.github.io/",
      "description": "XML parsing C library - runtime library"
    }
  ],
  "_vignettes": [
    {
      "source": "marcxmlr-workflow.Rmd",
      "filename": "marcxmlr-workflow.html",
      "title": "Statistical profiling of bibliographic metadata with marcxmlr",
      "author": "Lorenzo Isella",
      "engine": "knitr::rmarkdown",
      "headings": [
        "A catalogue as a statistical population",
        "Dataset and limits of inference",
        "1. Coverage: how often does a record have topical subject access?",
        "2. Indexing intensity: how many topical subject fields per record?",
        "3. Authority identifiers: use field instances, not subfield rows",
        "4. A more revealing association: subject subdivisions and $0",
        "Check an important confounding factor: subject vocabulary",
        "5. Return from a statistical pattern to original MARC fields",
        "6. Reuse a MARC-aware query to select complete records",
        "7. From a sample to a catalogue-scale study",
        "Conclusions"
      ],
      "created": "2026-10-12 19:40:02",
      "modified": "2026-10-19 09:00:08",
      "commits": 2
    }
  ],
  "_score": 3.3979400086720375,
  "_indexed": false,
  "_nocasepkg": "marcxmlr",
  "_universes": [
    "cran"
  ],
  "_indexurl": "https://larry77.r-universe.dev/marcxmlr",
  "_previous": "0.4.0",
  "_binaries": [
    {
      "r": "4.7.0",
      "os": "linux",
      "version": "0.5.0",
      "date": "2026-10-20T00:10:55.000Z",
      "distro": "resolute",
      "arch": "aarch64",
      "commit": "43000f6d12a1c14655d9cb0d49b6387b99ebfd47",
      "fileid": "https://r2.ropensci.org/1d02e80ce136e4c6540e33050ad293225726f516e0660e16bba02530b5d4ddec",
      "status": "success",
      "check": "NOTE",
      "buildurl": "https://github.com/r-universe/cran/actions/runs/39345568056"
    },
    {
      "r": "4.7.0",
      "os": "linux",
      "version": "0.5.0",
      "date": "2026-10-20T00:11:09.000Z",
      "distro": "resolute",
      "arch": "x86_64",
      "commit": "43000f6d12a1c14655d9cb0d49b6387b99ebfd47",
      "fileid": "https://r2.ropensci.org/01418aa19da59797c8acc748fe7cd24dafab7c7cf783701dc78a772879a84ef2",
      "status": "success",
      "check": "NOTE",
      "buildurl": "https://github.com/r-universe/cran/actions/runs/39345568056"
    },
    {
      "r": "4.6.1",
      "os": "linux",
      "version": "0.5.0",
      "date": "2026-10-20T00:10:55.000Z",
      "distro": "resolute",
      "arch": "aarch64",
      "commit": "43000f6d12a1c14655d9cb0d49b6387b99ebfd47",
      "fileid": "https://r2.ropensci.org/6bfa578d57059ec92187121bd8ce33a50a1a1a53cfb8f143f0519eb9bdd865db",
      "status": "success",
      "check": "NOTE",
      "buildurl": "https://github.com/r-universe/cran/actions/runs/39345568056"
    },
    {
      "r": "4.6.1",
      "os": "linux",
      "version": "0.5.0",
      "date": "2026-10-20T00:11:14.000Z",
      "distro": "resolute",
      "arch": "x86_64",
      "commit": "43000f6d12a1c14655d9cb0d49b6387b99ebfd47",
      "fileid": "https://r2.ropensci.org/80ead00b97e98d36ce0ef92ab289aef079a970b6afc191a7273855894187a9a4",
      "status": "success",
      "check": "NOTE",
      "buildurl": "https://github.com/r-universe/cran/actions/runs/39345568056"
    },
    {
      "r": "4.6.0",
      "os": "wasm",
      "version": "0.5.0",
      "date": "2026-10-20T00:11:24.000Z",
      "arch": "emscripten",
      "commit": "43000f6d12a1c14655d9cb0d49b6387b99ebfd47",
      "fileid": "https://r2.ropensci.org/a82525b0c8891c80fcd558279ef334e64c73eb58fcc10a1913132d5bdb59f036",
      "status": "success",
      "buildurl": "https://github.com/r-universe/cran/actions/runs/39345568056"
    },
    {
      "r": "4.7.0",
      "os": "win",
      "version": "0.5.0",
      "date": "2026-10-20T00:12:45.000Z",
      "arch": "aarch64",
      "commit": "43000f6d12a1c14655d9cb0d49b6387b99ebfd47",
      "fileid": "https://r2.ropensci.org/39e75cf2a79e9c0081d62d41caaf91c156008d975fc625928db05907936f900b",
      "status": "success",
      "check": "NOTE",
      "buildurl": "https://github.com/r-universe/cran/actions/runs/39345568056"
    },
    {
      "r": "4.7.0",
      "os": "win",
      "version": "0.5.0",
      "date": "2026-10-20T00:10:28.000Z",
      "arch": "x86_64",
      "commit": "43000f6d12a1c14655d9cb0d49b6387b99ebfd47",
      "fileid": "https://r2.ropensci.org/22d1ed29e80d3df9c33985cee64cad30fbf1095b94ed96945378ee04de8a4bcb",
      "status": "success",
      "check": "NOTE",
      "buildurl": "https://github.com/r-universe/cran/actions/runs/39345568056"
    },
    {
      "r": "4.6.1",
      "os": "win",
      "version": "0.5.0",
      "date": "2026-10-20T00:12:00.000Z",
      "arch": "aarch64",
      "commit": "43000f6d12a1c14655d9cb0d49b6387b99ebfd47",
      "fileid": "https://r2.ropensci.org/f76fae146f77440565a306c13610d8c732b68c095e267b2301d039c4742599ae",
      "status": "success",
      "check": "NOTE",
      "buildurl": "https://github.com/r-universe/cran/actions/runs/39345568056"
    },
    {
      "r": "4.6.1",
      "os": "win",
      "version": "0.5.0",
      "date": "2026-10-20T00:10:22.000Z",
      "arch": "x86_64",
      "commit": "43000f6d12a1c14655d9cb0d49b6387b99ebfd47",
      "fileid": "https://r2.ropensci.org/6fa867682f64431f31f6cf6a986d7005e75691867a062390eed8dd65cc8e8e3a",
      "status": "success",
      "check": "NOTE",
      "buildurl": "https://github.com/r-universe/cran/actions/runs/39345568056"
    }
  ]
}