{
  "_id": "6ae2fba995ca2370cc8cd214",
  "Package": "tabulapdf",
  "Type": "Package",
  "Title": "Extract Tables from PDF Documents",
  "Description": "Bindings for the 'Tabula' <https://tabula.technology/>\n'Java' library, which can extract tables from PDF files. This\ntool can reduce time and effort in data extraction processes in\nfields like investigative journalism. It allows for automatic\nand manual table extraction, the latter facilitated through a\n'Shiny' interface, enabling manual areas selection\\ with a\ncomputer mouse for data retrieval.",
  "Version": "1.0.5-5",
  "Authors@R": "c(\nperson(\"Thomas J.\", \"Leeper\",\nrole = \"aut\",\nemail = \"thosjleeper@gmail.com\",\ncomment = c(ORCID = \"0000-0003-4097-6326\")),\nperson(\"Mauricio\", \"Vargas Sepulveda\",\nrole = c(\"aut\",\"cre\"),\nemail = \"m.sepulveda@mail.utoronto.ca\",\ncomment = c(ORCID = \"0000-0003-1017-7574\")),\nperson(\"Tom\", \"Paskhalis\",\nrole = \"aut\",\nemail = \"tpaskhalis@gmail.com\",\ncomment = c(ORCID = \"0000-0001-9298-8850\")),\nperson(\"Manuel\", \"Aristaran\",\nrole = \"ctb\"),\nperson(\"David\", \"Gohel\",\nrole = \"ctb\",\ncomment = \"rOpenSci reviewer\"),\nperson(\"Lincoln\", \"Mullen\",\nrole = \"ctb\",\ncomment = \"rOpenSci reviewer\"),\nperson(\"Munk School of Global Affairs and Public Policy\",\nrole = \"fnd\")\n)",
  "License": "Apache License (>= 2)",
  "URL": "https://docs.ropensci.org/tabulapdf/ (website)\nhttps://github.com/ropensci/tabulapdf/",
  "BugReports": "https://github.com/ropensci/tabulapdf/issues/",
  "SystemRequirements": "Java (>= 7.0): openjdk-11-jdk (deb),\njava-11-openjdk.x86_64 (rpm), openjdk@11 (brew)",
  "VignetteBuilder": "knitr",
  "Encoding": "UTF-8",
  "RoxygenNote": "7.3.2",
  "Config/pak/sysreqs": "make default-jdk libpng-dev libx11-dev",
  "Repository": "https://ropensci.r-universe.dev",
  "Date/Publication": "2025-01-03 08:31:08 UTC",
  "RemoteUrl": "https://github.com/ropensci/tabulapdf",
  "RemoteRef": "HEAD",
  "RemoteSha": "03cabea1c4cd5fec818a9539115d773c5cb4ff0b",
  "NeedsCompilation": "no",
  "Packaged": {
    "Date": "2026-10-29 07:50:24 UTC",
    "User": "root"
  },
  "Author": "Thomas J. Leeper [aut] (ORCID: <https://orcid.org/0000-0003-4097-6326>),\nMauricio Vargas Sepulveda [aut, cre] (ORCID:\n<https://orcid.org/0000-0003-1017-7574>),\nTom Paskhalis [aut] (ORCID: <https://orcid.org/0000-0001-9298-8850>),\nManuel Aristaran [ctb],\nDavid Gohel [ctb] (rOpenSci reviewer),\nLincoln Mullen [ctb] (rOpenSci reviewer),\nMunk School of Global Affairs and Public Policy [fnd]",
  "Maintainer": "Mauricio Vargas Sepulveda <m.sepulveda@mail.utoronto.ca>",
  "_user": "ropensci",
  "_type": "src",
  "_file": "tabulapdf_1.0.5-5.tar.gz",
  "_fileid": "https://r2.ropensci.org/629e5761292719516e11055b1f34a4a139348c6a7dbbd76c3e554f436ecac03a",
  "_filesize": 13035175,
  "_sha256": "629e5761292719516e11055b1f34a4a139348c6a7dbbd76c3e554f436ecac03a",
  "_expires": "2027-02-06T07:54:15.000Z",
  "_created": "2026-10-29T07:50:24.000Z",
  "_published": "2026-10-29T07:54:17.480Z",
  "_upstream": "https://github.com/ropensci/tabulapdf",
  "_status": "success",
  "_maintainer": {
    "name": "Mauricio Vargas Sepulveda",
    "email": "m.sepulveda@mail.utoronto.ca",
    "login": "pachadotdev",
    "orcid": "0000-0003-1017-7574",
    "description": "Statistician interested in applying statistical methods to address specific policy-relevant questions, particularly in international trade.",
    "uuid": 10091065
  },
  "_jobs": [
    {
      "job": 123327446674,
      "time": 166,
      "config": "linux-devel-x86_64",
      "r": "4.7.0",
      "check": "NOTE",
      "artifact": "12881860889"
    },
    {
      "job": 123327446792,
      "time": 136,
      "config": "linux-release-x86_64",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "12881761215"
    },
    {
      "job": 123327446899,
      "time": 169,
      "config": "macos-oldrel-arm64",
      "r": "4.5.3",
      "check": "OK",
      "artifact": "12882145132"
    },
    {
      "job": 123327446700,
      "time": 124,
      "config": "macos-release-arm64",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "12881931055"
    },
    {
      "job": 123326065523,
      "time": 139,
      "config": "pkgdown",
      "r": "4.6.0",
      "check": "OK",
      "artifact": "12880913813"
    },
    {
      "job": 123326065436,
      "time": 235,
      "config": "source",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "12880968850"
    },
    {
      "job": 123327446628,
      "time": 132,
      "config": "wasm-release",
      "r": "4.6.0",
      "check": "OK",
      "artifact": "12882030310"
    },
    {
      "job": 123327446913,
      "time": 133,
      "config": "windows-devel-x86_64",
      "r": "4.7.0",
      "check": "NOTE",
      "artifact": "12881013255"
    },
    {
      "job": 123327446813,
      "time": 131,
      "config": "windows-oldrel-x86_64",
      "r": "4.5.3",
      "check": "OK",
      "artifact": "12881791479"
    },
    {
      "job": 123327446729,
      "time": 107,
      "config": "windows-release-x86_64",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "12881825897"
    }
  ],
  "_buildurl": "https://github.com/r-universe/ropensci/actions/runs/40837591349",
  "_commit": {
    "id": "03cabea1c4cd5fec818a9539115d773c5cb4ff0b",
    "author": "Mauricio 'Pacha' Vargas Sepulveda <m.sepulveda@mail.utoronto.ca>",
    "committer": "Mauricio 'Pacha' Vargas Sepulveda <m.sepulveda@mail.utoronto.ca>",
    "message": "add CRAN changes to repo\n",
    "time": 1735893068
  },
  "_distro": "resolute",
  "_host": "GitHub-Actions",
  "_registered": true,
  "_dependencies": [
    {
      "package": "png",
      "role": "Imports"
    },
    {
      "package": "readr",
      "role": "Imports"
    },
    {
      "package": "rJava",
      "role": "Imports"
    },
    {
      "package": "tools",
      "role": "Imports"
    },
    {
      "package": "utils",
      "role": "Imports"
    },
    {
      "package": "graphics",
      "role": "Suggests"
    },
    {
      "package": "grDevices",
      "role": "Suggests"
    },
    {
      "package": "knitr",
      "role": "Suggests"
    },
    {
      "package": "miniUI",
      "role": "Suggests"
    },
    {
      "package": "shiny",
      "role": "Suggests"
    },
    {
      "package": "testthat",
      "role": "Suggests"
    },
    {
      "package": "rmarkdown",
      "role": "Suggests"
    },
    {
      "package": "covr",
      "role": "Suggests"
    }
  ],
  "_owner": "ropensci",
  "_selfowned": true,
  "_usedby": 2,
  "_updates": [],
  "_tags": [],
  "_topics": [
    "java",
    "pdf",
    "pdf-document",
    "peer-reviewed",
    "ropensci",
    "tabula",
    "tabular-data",
    "openjdk"
  ],
  "_stars": 567,
  "_contributors": [
    {
      "user": "leeper",
      "count": 76,
      "uuid": 3505428
    },
    {
      "user": "tpaskhalis",
      "count": 59,
      "uuid": 2973437
    },
    {
      "user": "pachadotdev",
      "count": 36,
      "uuid": 10091065
    },
    {
      "user": "jeroen",
      "count": 4,
      "uuid": 216319
    },
    {
      "user": "aqlt",
      "count": 2,
      "uuid": 24825189
    },
    {
      "user": "albansagouis",
      "count": 1,
      "uuid": 25483578
    },
    {
      "user": "b-rodrigues",
      "count": 1,
      "uuid": 2998834
    },
    {
      "user": "karthik",
      "count": 1,
      "uuid": 138494
    },
    {
      "user": "uribo",
      "count": 1,
      "uuid": 228649
    }
  ],
  "_userbio": {
    "uuid": 1200269,
    "type": "organization",
    "name": "rOpenSci",
    "followers": 1166,
    "description": "Tools and R Packages for Open Science"
  },
  "_downloads": {
    "count": 1191,
    "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/tabulapdf"
  },
  "_devurl": "https://github.com/ropensci/tabulapdf",
  "_pkgdown": "https://docs.ropensci.org/tabulapdf/",
  "_searchresults": 284,
  "_metadata": {
    "review": {
      "id": 42,
      "status": "reviewed",
      "version": "0.1.11",
      "organization": "rOpenSci Software Review",
      "url": "https://github.com/ropensci/software-review/issues/42"
    },
    "ropensci_category": "data-extraction"
  },
  "_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/tabulapdf.html"
  ],
  "_homeurl": "https://github.com/ropensci/tabulapdf",
  "_realowner": "ropensci",
  "_cranurl": true,
  "_releases": [
    {
      "version": "1.0.5-3",
      "date": "2024-05-21"
    },
    {
      "version": "1.0.5-5",
      "date": "2024-11-15"
    }
  ],
  "_exports": [
    "extract_areas",
    "extract_metadata",
    "extract_tables",
    "extract_text",
    "get_n_pages",
    "get_page_dims",
    "locate_areas",
    "make_thumbnails",
    "merge_pdfs",
    "split_pdf",
    "stop_logging"
  ],
  "_help": [
    {
      "page": "tabulapdf-package",
      "title": "tabulapdf",
      "topics": [
        "tabulapdf-package",
        "tabulapdf"
      ]
    },
    {
      "page": "extract_metadata",
      "title": "extract_metadata",
      "topics": [
        "extract_metadata"
      ]
    },
    {
      "page": "extract_tables",
      "title": "extract_tables",
      "topics": [
        "extract_tables"
      ]
    },
    {
      "page": "extract_text",
      "title": "extract_text",
      "topics": [
        "extract_text"
      ]
    },
    {
      "page": "get_page_dims",
      "title": "Page length and dimensions",
      "topics": [
        "get_n_pages",
        "get_page_dims"
      ]
    },
    {
      "page": "extract_areas",
      "title": "extract_areas",
      "topics": [
        "extract_areas",
        "locate_areas"
      ]
    },
    {
      "page": "make_thumbnails",
      "title": "make_thumbnails",
      "topics": [
        "make_thumbnails"
      ]
    },
    {
      "page": "split_merge",
      "title": "Split and merge PDFs",
      "topics": [
        "merge_pdfs",
        "split_pdf"
      ]
    },
    {
      "page": "stop_logging",
      "title": "rJava logging",
      "topics": [
        "stop_logging"
      ]
    }
  ],
  "_pkglogo": "https://github.com/ropensci/tabulapdf/raw/HEAD/man/figures/logo.svg",
  "_readme": "https://github.com/ropensci/tabulapdf/raw/HEAD/README.md",
  "_rundeps": [
    "bit",
    "bit64",
    "cli",
    "clipr",
    "cpp11",
    "crayon",
    "glue",
    "hms",
    "lifecycle",
    "magrittr",
    "pillar",
    "pkgconfig",
    "png",
    "prettyunits",
    "progress",
    "R6",
    "readr",
    "rJava",
    "rlang",
    "tibble",
    "tidyselect",
    "tzdb",
    "utf8",
    "vctrs",
    "vroom",
    "withr"
  ],
  "_sysdeps": [
    {
      "shlib": "libjvm",
      "package": "openjdk-25-jre-headless",
      "headers": "openjdk-25-jre-headless",
      "source": "openjdk",
      "version": "25.0.4.1+1-1~26.04.4",
      "name": "openjdk",
      "homepage": "https://openjdk.java.net/",
      "description": "OpenJDK Java runtime, using Hotspot JIT (headless)"
    }
  ],
  "_vignettes": [
    {
      "source": "tabulapdf.Rmd",
      "filename": "tabulapdf.html",
      "title": "Introduction to tabulapdf",
      "engine": "knitr::rmarkdown",
      "headings": [
        "Introduction",
        "Basic usage",
        "Specifying the extraction method",
        "Extracting areas",
        "Interactive table extraction",
        "Use case: COVID-19 treatments in Italy",
        "Miscellaneous functionality"
      ],
      "created": "2024-04-11 02:55:08",
      "modified": "2024-09-19 19:14:11",
      "commits": 7
    }
  ],
  "_score": 9.663024402134328,
  "_indexed": true,
  "_nocasepkg": "tabulapdf",
  "_universes": [
    "ropensci",
    "pachadotdev"
  ],
  "_binaries": [
    {
      "r": "4.7.0",
      "os": "linux",
      "version": "1.0.5-5",
      "date": "2026-10-29T07:52:53.000Z",
      "distro": "resolute",
      "commit": "03cabea1c4cd5fec818a9539115d773c5cb4ff0b",
      "fileid": "https://r2.ropensci.org/c07a6d6993c74b8fe2833f48ea9e098439edf978b5433ec4e0222d5072c8ed18",
      "status": "success",
      "check": "NOTE",
      "buildurl": "https://github.com/r-universe/ropensci/actions/runs/40837591349"
    },
    {
      "r": "4.6.1",
      "os": "linux",
      "version": "1.0.5-5",
      "date": "2026-10-29T07:52:38.000Z",
      "distro": "resolute",
      "commit": "03cabea1c4cd5fec818a9539115d773c5cb4ff0b",
      "fileid": "https://r2.ropensci.org/4366654c82f8590ed1aee466b695c30f2265e7dc7c557627bbf310e9efa37eb4",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/ropensci/actions/runs/40837591349"
    },
    {
      "r": "4.5.3",
      "os": "mac",
      "version": "1.0.5-5",
      "date": "2026-10-29T07:52:53.000Z",
      "commit": "03cabea1c4cd5fec818a9539115d773c5cb4ff0b",
      "fileid": "https://r2.ropensci.org/48b3476456e7a84b2398e79c2c998d2c25a90e6f4f5161f867ee03a78b3d7724",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/ropensci/actions/runs/40837591349"
    },
    {
      "r": "4.6.1",
      "os": "mac",
      "version": "1.0.5-5",
      "date": "2026-10-29T07:52:20.000Z",
      "commit": "03cabea1c4cd5fec818a9539115d773c5cb4ff0b",
      "fileid": "https://r2.ropensci.org/bed13fbd21871d5dab4c536e7853bb8894958b81e3457fad226b57c23d82bfcd",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/ropensci/actions/runs/40837591349"
    },
    {
      "r": "4.6.0",
      "os": "wasm",
      "version": "1.0.5-5",
      "date": "2026-10-29T07:52:58.000Z",
      "commit": "03cabea1c4cd5fec818a9539115d773c5cb4ff0b",
      "fileid": "https://r2.ropensci.org/8823cddee732259e4ce2e398643308571b6207137768800511198bf0ea5c6a06",
      "status": "success",
      "buildurl": "https://github.com/r-universe/ropensci/actions/runs/40837591349"
    },
    {
      "r": "4.7.0",
      "os": "win",
      "version": "1.0.5-5",
      "date": "2026-10-29T07:51:58.000Z",
      "commit": "03cabea1c4cd5fec818a9539115d773c5cb4ff0b",
      "fileid": "https://r2.ropensci.org/2ee787a66e106a5be92d4353a06eb273bb5510d6fb8f43081bba3e5e083250e1",
      "status": "success",
      "check": "NOTE",
      "buildurl": "https://github.com/r-universe/ropensci/actions/runs/40837591349"
    },
    {
      "r": "4.5.3",
      "os": "win",
      "version": "1.0.5-5",
      "date": "2026-10-29T07:51:58.000Z",
      "commit": "03cabea1c4cd5fec818a9539115d773c5cb4ff0b",
      "fileid": "https://r2.ropensci.org/8a4104578fd46fc4d3ebb359e930f7b3faee4d9e27ea59787082ba93d29b70e2",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/ropensci/actions/runs/40837591349"
    },
    {
      "r": "4.6.1",
      "os": "win",
      "version": "1.0.5-5",
      "date": "2026-10-29T07:51:46.000Z",
      "commit": "03cabea1c4cd5fec818a9539115d773c5cb4ff0b",
      "fileid": "https://r2.ropensci.org/13c1fed07d74ea5953d3746c1e42b7c530609340ea4c3b72aee7a295a71c170f",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/ropensci/actions/runs/40837591349"
    }
  ]
}