{ "_id": "6a44cd6a6ff6f2357551b8c2", "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": "2026-07-01 08:14:05 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/0541b533c21277989eb4e334c9ac48255784742ba8e36b67a1e23ae1eac4ad89", "_filesize": 837220, "_sha256": "0541b533c21277989eb4e334c9ac48255784742ba8e36b67a1e23ae1eac4ad89", "_expires": "2026-10-09T08:18:50.000Z", "_created": "2026-07-01T08:14:05.000Z", "_published": "2026-07-01T08:18:50.569Z", "_jobs": [ { "job": 84486006595, "time": 182, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "8004046162" }, { "job": 84486006599, "time": 142, "config": "linux-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "8004032208" }, { "job": 84486006604, "time": 127, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "8004026647" }, { "job": 84486006648, "time": 88, "config": "macos-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "8004013000" }, { "job": 84485429528, "time": 183, "config": "pkgdown", "r": "4.6.0", "check": "OK", "artifact": "8003976041" }, { "job": 84485429514, "time": 193, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "8003979984" }, { "job": 84486006615, "time": 110, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "8004021163" }, { "job": 84486006636, "time": 74, "config": "windows-devel", "r": "4.7.0", "check": "OK", "artifact": "8004007855" }, { "job": 84486006602, "time": 76, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "8004009147" }, { "job": 84486006621, "time": 88, "config": "windows-release", "r": "4.6.1", "check": "OK", "artifact": "8004013037" } ], "_host": "GitHub-Actions", "_buildurl": "https://github.com/r-universe/ropensci/actions/runs/28503257121", "_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": 1106, "description": "Tools and R Packages for Open Science" }, "_downloads": { "count": 297, "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": "2026-07-01T08:17:09.000Z", "distro": "resolute", "commit": "350fcc3e90ab83dad8770021d6258147cf0c2ff0", "fileid": "https://r2.ropensci.org/d4d48b8670fd6c78a88034e99aaf78a73003fc8579ab970928a6ad4f4b70e409", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/ropensci/actions/runs/28503257121" }, { "r": "4.6.1", "os": "linux", "version": "3.2.3", "date": "2026-07-01T08:16:28.000Z", "distro": "resolute", "commit": "350fcc3e90ab83dad8770021d6258147cf0c2ff0", "fileid": "https://r2.ropensci.org/843dbbf0ee4500ee5538cdcf2e7f63a81f246b1505135bd16ffa582dba37a81d", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/ropensci/actions/runs/28503257121" }, { "r": "4.5.3", "os": "mac", "version": "3.2.3", "date": "2026-07-01T08:16:09.000Z", "commit": "350fcc3e90ab83dad8770021d6258147cf0c2ff0", "fileid": "https://r2.ropensci.org/ece5331a3b19e2a366c9fe858c889bbddba892639c28088cd9576caebd855bed", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/ropensci/actions/runs/28503257121" }, { "r": "4.6.1", "os": "mac", "version": "3.2.3", "date": "2026-07-01T08:15:37.000Z", "commit": "350fcc3e90ab83dad8770021d6258147cf0c2ff0", "fileid": "https://r2.ropensci.org/b9d626922e4aa33676a329e355dab25b7708a372e1fb1fa86c4a9cd5800c8265", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/ropensci/actions/runs/28503257121" }, { "r": "4.6.0", "os": "wasm", "version": "3.2.3", "date": "2026-07-01T08:16:10.000Z", "commit": "350fcc3e90ab83dad8770021d6258147cf0c2ff0", "fileid": "https://r2.ropensci.org/209c5248ee72e658f384a46be2bccd648663235fdde6e42471a6d282806e1229", "status": "success", "buildurl": "https://github.com/r-universe/ropensci/actions/runs/28503257121" }, { "r": "4.7.0", "os": "win", "version": "3.2.3", "date": "2026-07-01T08:15:15.000Z", "commit": "350fcc3e90ab83dad8770021d6258147cf0c2ff0", "fileid": "https://r2.ropensci.org/28a818793554282290cf76e8c8490d4c289b938ca908680358db8d4c107652f1", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/ropensci/actions/runs/28503257121" }, { "r": "4.5.3", "os": "win", "version": "3.2.3", "date": "2026-07-01T08:15:18.000Z", "commit": "350fcc3e90ab83dad8770021d6258147cf0c2ff0", "fileid": "https://r2.ropensci.org/b871ca1b16f950d00cc858aa4737675d40df0a63408df6574e41116fc543f0be", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/ropensci/actions/runs/28503257121" }, { "r": "4.6.1", "os": "win", "version": "3.2.3", "date": "2026-07-01T08:15:27.000Z", "commit": "350fcc3e90ab83dad8770021d6258147cf0c2ff0", "fileid": "https://r2.ropensci.org/ba76a6b0eb2cfcb17e03d68f961b027857870ea346057c9c7f47f79b123561f7", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/ropensci/actions/runs/28503257121" } ] }