{ "_id": "6a6c2dc63388593b7e8cbc5d", "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 ", "License": "Apache License 2.0 | file LICENSE", "SystemRequirements": "Java (>=11)", "Description": "Extract text or metadata from over a thousand file types,\nusing Apache Tika . 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": "master", "RemoteSha": "350fcc3e90ab83dad8770021d6258147cf0c2ff0", "NeedsCompilation": "no", "Packaged": { "Date": "2026-07-31 05:04:44 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/abd9639351041b17e36e5cc7ae1d3b7b353744d2a0ee26e8f535bb052bd93d18", "_filesize": 838160, "_sha256": "abd9639351041b17e36e5cc7ae1d3b7b353744d2a0ee26e8f535bb052bd93d18", "_expires": "2026-11-08T05:08:20.000Z", "_created": "2026-07-31T05:04:44.000Z", "_published": "2026-07-31T05:08:22.556Z", "_jobs": [ { "job": 91077697992, "time": 166, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "8783573349" }, { "job": 91077698050, "time": 147, "config": "linux-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "8783567620" }, { "job": 91077697983, "time": 69, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "8783549293" }, { "job": 91077698002, "time": 110, "config": "macos-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "8783558796" }, { "job": 91077253887, "time": 184, "config": "pkgdown", "r": "4.6.0", "check": "OK", "artifact": "8783527504" }, { "job": 91077253913, "time": 210, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "8783532188" }, { "job": 91077698016, "time": 137, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "8783565169" }, { "job": 91077698069, "time": 69, "config": "windows-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "8783549541" }, { "job": 91077698028, "time": 77, "config": "windows-oldrel-x86_64", "r": "4.5.3", "check": "OK", "artifact": "8783551783" }, { "job": 91077698003, "time": 64, "config": "windows-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "8783548118" } ], "_host": "GitHub-Actions", "_buildurl": "https://github.com/r-universe/ropensci/actions/runs/30605632907", "_status": "success", "_upstream": "https://github.com/ropensci/rtika", "_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 }, "_maintainer": { "name": "Sasha Goodman", "email": "goodmansasha@gmail.com", "login": "soshsquatch", "description": "Computational social science. ", "uuid": 4193801 }, "_distro": "resolute", "_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": [ { "week": "2025-41", "n": 5 } ], "_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": 1133, "description": "Tools and R Packages for Open Science" }, "_downloads": { "count": 249, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/rtika" }, "_devurl": "https://github.com/ropensci/rtika", "_pkgdown": "https://docs.ropensci.org/rtika/", "_searchresults": 13, "_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/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "extra/rtika.html", "LICENSE", "manual.pdf" ], "_homeurl": "https://github.com/ropensci/rtika", "_realowner": "ropensci", "_cranurl": true, "_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/master/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": 6.030397300856762, "_indexed": true, "_nocasepkg": "rtika", "_universes": [ "ropensci", "soshsquatch" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "3.2.3", "date": "2026-07-31T05:07:36.000Z", "distro": "resolute", "commit": "350fcc3e90ab83dad8770021d6258147cf0c2ff0", "fileid": "https://r2.ropensci.org/109b908521d9799856883ddb0e27cc3d19e09a27ebe1654336185525ede93a70", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/ropensci/actions/runs/30605632907" }, { "r": "4.6.1", "os": "linux", "version": "3.2.3", "date": "2026-07-31T05:07:17.000Z", "distro": "resolute", "commit": "350fcc3e90ab83dad8770021d6258147cf0c2ff0", "fileid": "https://r2.ropensci.org/7de0a13a20b808271e16ed1e3e13af60bd4e9fdc5985e9315ad4d385a6764dec", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/ropensci/actions/runs/30605632907" }, { "r": "4.5.3", "os": "mac", "version": "3.2.3", "date": "2026-07-31T05:06:02.000Z", "commit": "350fcc3e90ab83dad8770021d6258147cf0c2ff0", "fileid": "https://r2.ropensci.org/b9e34c2f4369ac96ed044c2e7c5c69073c87b50730c6a7557ee3a95ddff146d6", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/ropensci/actions/runs/30605632907" }, { "r": "4.6.1", "os": "mac", "version": "3.2.3", "date": "2026-07-31T05:06:36.000Z", "commit": "350fcc3e90ab83dad8770021d6258147cf0c2ff0", "fileid": "https://r2.ropensci.org/f09d905240be55ea620293bda14873df7a1385ab044650735a63ae2f0d91ab19", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/ropensci/actions/runs/30605632907" }, { "r": "4.6.0", "os": "wasm", "version": "3.2.3", "date": "2026-07-31T05:07:17.000Z", "commit": "350fcc3e90ab83dad8770021d6258147cf0c2ff0", "fileid": "https://r2.ropensci.org/0e31e8b36fa51eb5a719dd0b0266890013c591a4bd8973e01903222e733c4571", "status": "success", "buildurl": "https://github.com/r-universe/ropensci/actions/runs/30605632907" }, { "r": "4.7.0", "os": "win", "version": "3.2.3", "date": "2026-07-31T05:05:51.000Z", "commit": "350fcc3e90ab83dad8770021d6258147cf0c2ff0", "fileid": "https://r2.ropensci.org/21f1fbe18be61fb2b35d9c8af64092440afe6119dd44459f05343af8af427132", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/ropensci/actions/runs/30605632907" }, { "r": "4.5.3", "os": "win", "version": "3.2.3", "date": "2026-07-31T05:06:00.000Z", "commit": "350fcc3e90ab83dad8770021d6258147cf0c2ff0", "fileid": "https://r2.ropensci.org/0c97f99a44f0deba1300552303c703d65a98614a3e84f658958bde547d403c39", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/ropensci/actions/runs/30605632907" }, { "r": "4.6.1", "os": "win", "version": "3.2.3", "date": "2026-07-31T05:05:46.000Z", "commit": "350fcc3e90ab83dad8770021d6258147cf0c2ff0", "fileid": "https://r2.ropensci.org/90f98c60eba6f9a6d07159e52fc5b41af9288a9c5cf5b963229588c4b5a6ec3a", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/ropensci/actions/runs/30605632907" } ] }