{
"_id": "69e0772ac5259ad4cd8fe91b",
"Package": "tabulapdf",
"Type": "Package",
"Title": "Extract Tables from PDF Documents",
"Description": "Bindings for the 'Tabula' \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": "main",
"RemoteSha": "03cabea1c4cd5fec818a9539115d773c5cb4ff0b",
"NeedsCompilation": "no",
"Packaged": {
"Date": "2026-04-15 08:03:38 UTC",
"User": "root"
},
"Author": "Thomas J. Leeper [aut] (ORCID: ),\nMauricio Vargas Sepulveda [aut, cre] (ORCID:\n),\nTom Paskhalis [aut] (ORCID: ),\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 ",
"MD5sum": "2a841cdad937bfab479067c6a2738a2b",
"_user": "ropensci",
"_type": "src",
"_file": "tabulapdf_1.0.5-5.tar.gz",
"_fileid": "18cba5c6e6b8b01917b8043922f81970d2de3b08aa2a17a3bbe0016eaac5376d",
"_filesize": 13038053,
"_sha256": "18cba5c6e6b8b01917b8043922f81970d2de3b08aa2a17a3bbe0016eaac5376d",
"_created": "2026-04-15T08:03:38.000Z",
"_published": "2026-04-16T05:44:10.327Z",
"_distro": "noble",
"_jobs": [
{
"job": 71579504219,
"time": 161,
"config": "linux-devel-x86_64",
"r": "4.6.0",
"check": "OK",
"artifact": "6445774967"
},
{
"job": 71579504352,
"time": 160,
"config": "linux-release-x86_64",
"r": "4.5.3",
"check": "OK",
"artifact": "6445774665"
},
{
"job": 71579504085,
"time": 113,
"config": "macos-oldrel-arm64",
"r": "4.5.3",
"check": "OK",
"artifact": "6466735957"
},
{
"job": 71579504164,
"time": 118,
"config": "macos-release-arm64",
"r": "4.6.0",
"check": "OK",
"artifact": "6445764227"
},
{
"job": 71579504054,
"time": 163,
"config": "pkgdown",
"r": "4.5.2",
"check": "OK",
"artifact": "6445725983"
},
{
"job": 71579504070,
"time": 182,
"config": "source",
"r": "4.5.3",
"check": "OK",
"artifact": "6445731222"
},
{
"job": 71579504250,
"time": 142,
"config": "wasm-release",
"r": "4.5.1",
"check": "OK",
"artifact": "6445769951"
},
{
"job": 71579504329,
"time": 113,
"config": "windows-devel",
"r": "4.7.0",
"check": "OK",
"artifact": "6445762416"
},
{
"job": 71579504265,
"time": 107,
"config": "windows-oldrel",
"r": "4.5.3",
"check": "OK",
"artifact": "6445760804"
},
{
"job": 71579504295,
"time": 113,
"config": "windows-release",
"r": "4.6.0",
"check": "OK",
"artifact": "6445762622"
}
],
"_buildurl": "https://github.com/r-universe/ropensci/actions/runs/24443254205",
"_status": "success",
"_host": "GitHub-Actions",
"_upstream": "https://github.com/ropensci/tabulapdf",
"_commit": {
"id": "03cabea1c4cd5fec818a9539115d773c5cb4ff0b",
"author": "Mauricio 'Pacha' Vargas Sepulveda ",
"committer": "Mauricio 'Pacha' Vargas Sepulveda ",
"message": "add CRAN changes to repo\n",
"time": 1735893068
},
"_maintainer": {
"name": "Mauricio Vargas Sepulveda",
"email": "m.sepulveda@mail.utoronto.ca",
"login": "pachadotdev",
"orcid": "0000-0003-1017-7574",
"uuid": 10091065
},
"_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": 566,
"_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",
"description": "Tools and R Packages for Open Science"
},
"_downloads": {
"count": 1788,
"source": "https://cranlogs.r-pkg.org/downloads/total/last-month/tabulapdf"
},
"_devurl": "https://github.com/ropensci/tabulapdf",
"_pkgdown": "https://docs.ropensci.org/tabulapdf/",
"_searchresults": 217,
"_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": "4.5.3",
"_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/tabulapdf.html",
"manual.pdf"
],
"_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/main/man/figures/logo.svg",
"_readme": "https://github.com/ropensci/tabulapdf/raw/main/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-21-jre-headless",
"headers": "openjdk-21-jre-headless",
"source": "openjdk",
"version": "21.0.10+7-1~24.04",
"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": 9.721854921208305,
"_indexed": true,
"_nocasepkg": "tabulapdf",
"_universes": [
"ropensci",
"pachadotdev"
],
"_binaries": [
{
"r": "4.6.0",
"os": "linux",
"version": "1.0.5-5",
"date": "2026-04-15T08:06:09.000Z",
"distro": "noble",
"commit": "03cabea1c4cd5fec818a9539115d773c5cb4ff0b",
"fileid": "873694b82b2093cbad4000d23fbd2c5a8ab1f79003d178067f1a43680d6c505e",
"status": "success",
"check": "OK",
"buildurl": "https://github.com/r-universe/ropensci/actions/runs/24443254205"
},
{
"r": "4.5.3",
"os": "mac",
"version": "1.0.5-5",
"date": "2026-04-16T05:43:18.000Z",
"commit": "03cabea1c4cd5fec818a9539115d773c5cb4ff0b",
"fileid": "3499ab97139cf16840574171b7e50c35e683f10934dd63ee6dcef2578284e145",
"status": "success",
"check": "OK",
"buildurl": "https://github.com/r-universe/ropensci/actions/runs/24443254205"
},
{
"r": "4.6.0",
"os": "mac",
"version": "1.0.5-5",
"date": "2026-04-15T08:05:28.000Z",
"commit": "03cabea1c4cd5fec818a9539115d773c5cb4ff0b",
"fileid": "bea4e9c6e0be090e1770d8d6167036f2aadaee34f54b814eebdb229a02f14eae",
"status": "success",
"check": "OK",
"buildurl": "https://github.com/r-universe/ropensci/actions/runs/24443254205"
},
{
"r": "4.5.1",
"os": "wasm",
"version": "1.0.5-5",
"date": "2026-04-15T08:06:18.000Z",
"commit": "03cabea1c4cd5fec818a9539115d773c5cb4ff0b",
"fileid": "2d712ac85b6d87480da20f79951c8a65c5b311b83ce98cf8f4695f32e9458a31",
"status": "success",
"buildurl": "https://github.com/r-universe/ropensci/actions/runs/24443254205"
},
{
"r": "4.7.0",
"os": "win",
"version": "1.0.5-5",
"date": "2026-04-15T08:04:56.000Z",
"commit": "03cabea1c4cd5fec818a9539115d773c5cb4ff0b",
"fileid": "14fd9bc77b30da5d63360bcd680e7274d4acc1a915e66bc1b87d34999a488b84",
"status": "success",
"check": "OK",
"buildurl": "https://github.com/r-universe/ropensci/actions/runs/24443254205"
},
{
"r": "4.5.3",
"os": "win",
"version": "1.0.5-5",
"date": "2026-04-15T08:04:51.000Z",
"commit": "03cabea1c4cd5fec818a9539115d773c5cb4ff0b",
"fileid": "754624ceb1bfe225b76d37ad3b3de080979a64fa838e115bb99f9b31566cc203",
"status": "success",
"check": "OK",
"buildurl": "https://github.com/r-universe/ropensci/actions/runs/24443254205"
},
{
"r": "4.6.0",
"os": "win",
"version": "1.0.5-5",
"date": "2026-04-15T08:04:55.000Z",
"commit": "03cabea1c4cd5fec818a9539115d773c5cb4ff0b",
"fileid": "5bf700973929dce9ce1f2ba06a6fd639ec3f5a7c89d1fe7afc1fe8b7ce51c2c1",
"status": "success",
"check": "OK",
"buildurl": "https://github.com/r-universe/ropensci/actions/runs/24443254205"
}
]
}