{
  "_id": "6ae2fa14327abcdf86865ec2",
  "Package": "rtika",
  "Type": "Package",
  "Title": "R Interface to 'Apache Tika'",
  "Version": "3.2.3",
  "Authors@R": "c(\nperson(given = \"Sasha\", family = \"Goodman\", email=\"goodmansasha@gmail.com\", role=c(\"aut\",\"cre\") ),\nperson(given = \"The Apache Software Foundation\", role=c(\"aut\",\"cph\") ),\nperson(given = \"Julia\", family = \"Silge\", role = c(\"rev\"), comment = \"Reviewed the package for rOpenSci, see https://github.com/ropensci/software-review/issues/191/\"),\nperson(given = \"David\",family = \"Gohel\", role = c(\"rev\"), comment = \"Reviewed the package for rOpenSci, see https://github.com/ropensci/software-review/issues/191/\")\n)",
  "Maintainer": "Sasha Goodman <goodmansasha@gmail.com>",
  "License": "Apache License 2.0 | file LICENSE",
  "SystemRequirements": "Java (>=11)",
  "Description": "Extract text or metadata from over a thousand file types,\nusing Apache Tika <https://tika.apache.org/>. Get either plain\ntext or structured XHTML content.",
  "Encoding": "UTF-8",
  "RoxygenNote": "7.3.3",
  "URL": "https://docs.ropensci.org/rtika/,\nhttps://github.com/ropensci/rtika/",
  "BugReports": "https://github.com/ropensci/rtika/issues/",
  "VignetteBuilder": "knitr",
  "Config/pak/sysreqs": "default-jdk libssl-dev",
  "Repository": "https://ropensci.r-universe.dev",
  "Date/Publication": "2025-10-12 13:59:05 UTC",
  "RemoteUrl": "https://github.com/ropensci/rtika",
  "RemoteRef": "HEAD",
  "RemoteSha": "350fcc3e90ab83dad8770021d6258147cf0c2ff0",
  "NeedsCompilation": "no",
  "Packaged": {
    "Date": "2026-10-29 07:43:36 UTC",
    "User": "root"
  },
  "Author": "Sasha Goodman [aut, cre],\nThe Apache Software Foundation [aut, cph],\nJulia Silge [rev] (Reviewed the package for rOpenSci, see\nhttps://github.com/ropensci/software-review/issues/191/),\nDavid Gohel [rev] (Reviewed the package for rOpenSci, see\nhttps://github.com/ropensci/software-review/issues/191/)",
  "_user": "ropensci",
  "_type": "src",
  "_file": "rtika_3.2.3.tar.gz",
  "_fileid": "https://r2.ropensci.org/850f128b7f43778df6ba24f8876b963d836d409b70d12276e64696287cb64133",
  "_filesize": 836006,
  "_sha256": "850f128b7f43778df6ba24f8876b963d836d409b70d12276e64696287cb64133",
  "_expires": "2027-02-06T07:47:30.000Z",
  "_created": "2026-10-29T07:43:36.000Z",
  "_published": "2026-10-29T07:47:32.446Z",
  "_upstream": "https://github.com/ropensci/rtika",
  "_status": "success",
  "_maintainer": {
    "name": "Sasha Goodman",
    "email": "goodmansasha@gmail.com",
    "login": "soshsquatch",
    "description": "Computational social science. ",
    "uuid": 4193801
  },
  "_jobs": [
    {
      "job": 123325002019,
      "time": 188,
      "config": "linux-devel-x86_64",
      "r": "4.7.0",
      "check": "OK",
      "artifact": "12881332584"
    },
    {
      "job": 123325001848,
      "time": 123,
      "config": "linux-release-x86_64",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "12880848676"
    },
    {
      "job": 123325001903,
      "time": 82,
      "config": "macos-oldrel-arm64",
      "r": "4.5.3",
      "check": "OK",
      "artifact": "12881686643"
    },
    {
      "job": 123325001749,
      "time": 92,
      "config": "macos-release-arm64",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "12881322334"
    },
    {
      "job": 123323675890,
      "time": 160,
      "config": "pkgdown",
      "r": "4.6.0",
      "check": "OK",
      "artifact": "12880957516"
    },
    {
      "job": 123323675742,
      "time": 228,
      "config": "source",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "12881187367"
    },
    {
      "job": 123325001716,
      "time": 96,
      "config": "wasm-release",
      "r": "4.6.0",
      "check": "OK",
      "artifact": "12881770004"
    },
    {
      "job": 123325001857,
      "time": 70,
      "config": "windows-devel-x86_64",
      "r": "4.7.0",
      "check": "OK",
      "artifact": "12880763990"
    },
    {
      "job": 123325001823,
      "time": 60,
      "config": "windows-oldrel-x86_64",
      "r": "4.5.3",
      "check": "OK",
      "artifact": "12880749199"
    },
    {
      "job": 123325001767,
      "time": 56,
      "config": "windows-release-x86_64",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "12881252200"
    }
  ],
  "_buildurl": "https://github.com/r-universe/ropensci/actions/runs/40836858311",
  "_commit": {
    "id": "350fcc3e90ab83dad8770021d6258147cf0c2ff0",
    "author": "Sasha Goodman Chase <4193801+soshsquatch@users.noreply.github.com>",
    "committer": "Sasha Goodman Chase <4193801+soshsquatch@users.noreply.github.com>",
    "message": "fixed tabulapdf link\n\nsmall fix, refreshed docs with pkgdown link to tabulapdf\n",
    "time": 1760277545
  },
  "_distro": "resolute",
  "_host": "GitHub-Actions",
  "_registered": true,
  "_dependencies": [
    {
      "package": "R",
      "version": ">= 3.5.0",
      "role": "Depends"
    },
    {
      "package": "curl",
      "role": "Imports"
    },
    {
      "package": "sys",
      "version": ">= 2.1",
      "role": "Imports"
    },
    {
      "package": "stats",
      "role": "Imports"
    },
    {
      "package": "utils",
      "role": "Imports"
    },
    {
      "package": "digest",
      "role": "Imports"
    },
    {
      "package": "backports",
      "role": "Imports"
    },
    {
      "package": "jsonlite",
      "role": "Suggests"
    },
    {
      "package": "xml2",
      "role": "Suggests"
    },
    {
      "package": "testthat",
      "role": "Suggests"
    },
    {
      "package": "knitr",
      "role": "Suggests"
    },
    {
      "package": "rmarkdown",
      "role": "Suggests"
    },
    {
      "package": "covr",
      "role": "Suggests"
    },
    {
      "package": "magrittr",
      "role": "Suggests"
    }
  ],
  "_owner": "ropensci",
  "_selfowned": true,
  "_usedby": 0,
  "_updates": [],
  "_tags": [],
  "_topics": [
    "extract-metadata",
    "extract-text",
    "java",
    "parse",
    "pdf-files",
    "peer-reviewed",
    "tesseract",
    "tika"
  ],
  "_stars": 55,
  "_contributors": [
    {
      "user": "soshsquatch",
      "count": 158,
      "uuid": 4193801
    },
    {
      "user": "jeroen",
      "count": 5,
      "uuid": 216319
    },
    {
      "user": "noamross",
      "count": 4,
      "uuid": 571752
    },
    {
      "user": "juliasilge",
      "count": 1,
      "uuid": 12505835
    }
  ],
  "_userbio": {
    "uuid": 1200269,
    "type": "organization",
    "name": "rOpenSci",
    "followers": 1166,
    "description": "Tools and R Packages for Open Science"
  },
  "_downloads": {
    "count": 135,
    "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/rtika"
  },
  "_devurl": "https://github.com/ropensci/rtika",
  "_pkgdown": "https://docs.ropensci.org/rtika/",
  "_searchresults": 3,
  "_metadata": {
    "review": {
      "id": 191,
      "status": "reviewed",
      "version": "0.1.2",
      "organization": "rOpenSci Software Review",
      "url": "https://github.com/ropensci/software-review/issues/191"
    },
    "ropensci_category": "literature"
  },
  "_rbuild": "4.6.1",
  "_assets": [
    "extra/citation.cff",
    "extra/citation.html",
    "extra/citation.json",
    "extra/citation.txt",
    "extra/contents.json",
    "extra/manual.pdf",
    "extra/NEWS.html",
    "extra/NEWS.txt",
    "extra/readme.html",
    "extra/readme.md",
    "extra/rtika.html",
    "LICENSE"
  ],
  "_realowner": "ropensci",
  "_cranurl": false,
  "_releases": [
    {
      "version": "0.1.8",
      "date": "2018-05-02"
    },
    {
      "version": "1.1.19",
      "date": "2018-10-05"
    },
    {
      "version": "1.19.1",
      "date": "2018-11-15"
    },
    {
      "version": "1.20",
      "date": "2019-03-04"
    },
    {
      "version": "1.21",
      "date": "2019-06-22"
    },
    {
      "version": "1.22",
      "date": "2019-08-02"
    },
    {
      "version": "1.23",
      "date": "2019-12-13"
    },
    {
      "version": "1.24.1",
      "date": "2020-04-25"
    },
    {
      "version": "2.0.0",
      "date": "2021-08-06"
    },
    {
      "version": "2.4.1",
      "date": "2022-09-26"
    },
    {
      "version": "2.7.0",
      "date": "2023-05-05"
    },
    {
      "version": "3.2.3",
      "date": "2025-10-12"
    }
  ],
  "_exports": [
    "install_tika",
    "java",
    "tika",
    "tika_check",
    "tika_fetch",
    "tika_html",
    "tika_jar",
    "tika_json",
    "tika_json_text",
    "tika_text",
    "tika_xml"
  ],
  "_help": [
    {
      "page": "install_tika",
      "title": "Install or Update the Apache Tika 'jar'",
      "topics": [
        "install_tika"
      ]
    },
    {
      "page": "java",
      "title": "System Command to Run Java",
      "topics": [
        "java"
      ]
    },
    {
      "page": "tika",
      "title": "Main R Interface to 'Apache Tika'",
      "topics": [
        "tika"
      ]
    },
    {
      "page": "tika_check",
      "title": "Check Tika against a checksum",
      "topics": [
        "tika_check"
      ]
    },
    {
      "page": "tika_fetch",
      "title": "Fetch Files with the Content-Type Preserved in the File Extension",
      "topics": [
        "tika_fetch"
      ]
    },
    {
      "page": "tika_html",
      "title": "Get Structured XHTML",
      "topics": [
        "tika_html"
      ]
    },
    {
      "page": "tika_jar",
      "title": "Path to Apache Tika",
      "topics": [
        "tika_jar"
      ]
    },
    {
      "page": "tika_json",
      "title": "Get json Metadata and XHTML Content",
      "topics": [
        "tika_json"
      ]
    },
    {
      "page": "tika_json_text",
      "title": "Get json Metadata and Plain Text Content",
      "topics": [
        "tika_json_text"
      ]
    },
    {
      "page": "tika_text",
      "title": "Get Plain Text",
      "topics": [
        "tika_text"
      ]
    },
    {
      "page": "tika_xml",
      "title": "Get a Structured XHTML Rendition",
      "topics": [
        "tika_xml"
      ]
    }
  ],
  "_readme": "https://github.com/ropensci/rtika/raw/HEAD/README.md",
  "_rundeps": [
    "backports",
    "curl",
    "digest",
    "sys"
  ],
  "_vignettes": [
    {
      "source": "rtika_introduction.Rmd",
      "filename": "rtika_introduction.html",
      "title": "Introduction to rtika",
      "author": "Sasha Goodman",
      "engine": "knitr::rmarkdown",
      "headings": [
        "A Digital Babel Fish",
        "Extract Plain Text",
        "Preserve Content-Type when Downloading",
        "Settings for Big Datasets",
        "Get a Structured XHTML Rendition",
        "Access Metadata in the XHTML",
        "Get Metadata in JSON Format",
        "Get Metadata from \"Container\" Documents",
        "Extending rtika",
        "References"
      ],
      "created": "2018-03-02 03:09:08",
      "modified": "2019-08-02 05:39:32",
      "commits": 19
    }
  ],
  "_score": 4.9164539485499255,
  "_indexed": true,
  "_nocasepkg": "rtika",
  "_universes": [
    "ropensci",
    "soshsquatch"
  ],
  "_binaries": [
    {
      "r": "4.7.0",
      "os": "linux",
      "version": "3.2.3",
      "date": "2026-10-29T07:46:45.000Z",
      "distro": "resolute",
      "commit": "350fcc3e90ab83dad8770021d6258147cf0c2ff0",
      "fileid": "https://r2.ropensci.org/9d08ca5be53e46716e6013f6cac22e118c4ccffda1bbeeefcf12601809155fc4",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/ropensci/actions/runs/40836858311"
    },
    {
      "r": "4.6.1",
      "os": "linux",
      "version": "3.2.3",
      "date": "2026-10-29T07:45:39.000Z",
      "distro": "resolute",
      "commit": "350fcc3e90ab83dad8770021d6258147cf0c2ff0",
      "fileid": "https://r2.ropensci.org/7357427c536886fe6ffefb45d6006bb219e22848d34316d1514e084be5bcbad9",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/ropensci/actions/runs/40836858311"
    },
    {
      "r": "4.5.3",
      "os": "mac",
      "version": "3.2.3",
      "date": "2026-10-29T07:45:24.000Z",
      "commit": "350fcc3e90ab83dad8770021d6258147cf0c2ff0",
      "fileid": "https://r2.ropensci.org/8be01eb55201f56cf063ca018e3ec61530ddb8283f4978eed68f272514ddab2f",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/ropensci/actions/runs/40836858311"
    },
    {
      "r": "4.6.1",
      "os": "mac",
      "version": "3.2.3",
      "date": "2026-10-29T07:45:15.000Z",
      "commit": "350fcc3e90ab83dad8770021d6258147cf0c2ff0",
      "fileid": "https://r2.ropensci.org/e1475bf16e385c5e032cceed59f88f464e1fd0ba0da938bd5d3da7528b3b0993",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/ropensci/actions/runs/40836858311"
    },
    {
      "r": "4.6.0",
      "os": "wasm",
      "version": "3.2.3",
      "date": "2026-10-29T07:45:25.000Z",
      "commit": "350fcc3e90ab83dad8770021d6258147cf0c2ff0",
      "fileid": "https://r2.ropensci.org/3a8bdc5401eb486c3a20cd7ee11caa04984da3080543f6b8e1a5a6e0123c86be",
      "status": "success",
      "buildurl": "https://github.com/r-universe/ropensci/actions/runs/40836858311"
    },
    {
      "r": "4.7.0",
      "os": "win",
      "version": "3.2.3",
      "date": "2026-10-29T07:44:38.000Z",
      "commit": "350fcc3e90ab83dad8770021d6258147cf0c2ff0",
      "fileid": "https://r2.ropensci.org/1424c86969932dfbe283ccc070f3ed379c7c606d68ea8c70f902dc1fcd2370e3",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/ropensci/actions/runs/40836858311"
    },
    {
      "r": "4.5.3",
      "os": "win",
      "version": "3.2.3",
      "date": "2026-10-29T07:44:35.000Z",
      "commit": "350fcc3e90ab83dad8770021d6258147cf0c2ff0",
      "fileid": "https://r2.ropensci.org/d17386f9e4d3669eca8622a254ef2397a3833a449e9da23d94e474894cabaa92",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/ropensci/actions/runs/40836858311"
    },
    {
      "r": "4.6.1",
      "os": "win",
      "version": "3.2.3",
      "date": "2026-10-29T07:44:30.000Z",
      "commit": "350fcc3e90ab83dad8770021d6258147cf0c2ff0",
      "fileid": "https://r2.ropensci.org/8f36a8b9b2ca56677216f7dcff1634be390225560e7d289f2981570870f2ca5c",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/ropensci/actions/runs/40836858311"
    }
  ]
}