{ "_id": "6a1535f5acfb0bcc41d4f68e", "Package": "tesseract", "Type": "Package", "Title": "Open Source OCR Engine", "Version": "5.2.5", "Authors@R": "person(\"Jeroen\", \"Ooms\", role = c(\"aut\", \"cre\"), email = \"jeroenooms@gmail.com\",\ncomment = c(ORCID = \"0000-0002-4035-0289\"))", "Description": "Bindings to 'Tesseract': a powerful optical character\nrecognition (OCR) engine that supports over 100 languages. The\nengine is highly configurable in order to tune the detection\nalgorithms and obtain the best possible results.", "License": "Apache License 2.0", "URL": "https://docs.ropensci.org/tesseract/\nhttps://ropensci.r-universe.dev/tesseract", "BugReports": "https://github.com/ropensci/tesseract/issues", "SystemRequirements": "Tesseract >= 3.03 (libtesseract-dev /\ntesseract-devel) and Leptonica (libleptonica-dev /\nleptonica-devel). On Debian you need to install the English\ntraining data separately (tesseract-ocr-eng)", "RoxygenNote": "7.3.3", "Encoding": "UTF-8", "VignetteBuilder": "knitr", "Language": "en-US", "NeedsCompilation": "yes", "Packaged": { "Date": "2026-05-26 05:53:07 UTC", "User": "root" }, "Author": "Jeroen Ooms [aut, cre] (ORCID:\n)", "Maintainer": "Jeroen Ooms ", "Config/pak/sysreqs": "libleptonica-dev libtesseract-dev tesseract-ocr-eng", "Repository": "https://cran.r-universe.dev", "Date/Publication": "2026-01-26 14:30:02 UTC", "RemoteUrl": "https://github.com/cran/tesseract", "RemoteRef": "HEAD", "RemoteSha": "57d6b6e806b89ad1263c33775c57ab9bd6c81957", "MD5sum": "5d16413ac5ec357e166b3395b6b05659", "_user": "cran", "_type": "src", "_file": "tesseract_5.2.5.tar.gz", "_fileid": "561ad0077e37df72cbaa03cb1ea4b178634bf70f2c22639b1c5287e0d5e95141", "_filesize": 270867, "_sha256": "561ad0077e37df72cbaa03cb1ea4b178634bf70f2c22639b1c5287e0d5e95141", "_created": "2026-05-26T05:53:07.000Z", "_published": "2026-05-26T05:56:05.266Z", "_distro": "noble", "_jobs": [ { "job": 77815592254, "time": 133, "config": "linux-devel-arm64", "r": "4.7.0", "check": "NOTE", "artifact": "7209867765" }, { "job": 77815592219, "time": 133, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "NOTE", "artifact": "7209868055" }, { "job": 77815592251, "time": 130, "config": "linux-release-arm64", "r": "4.6.0", "check": "NOTE", "artifact": "7209867336" }, { "job": 77815592226, "time": 132, "config": "linux-release-x86_64", "r": "4.6.0", "check": "NOTE", "artifact": "7209867930" }, { "job": 77815231262, "time": 212, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7209841447" }, { "job": 77815592199, "time": 116, "config": "wasm-release", "r": "4.6.0", "check": "FAIL", "artifact": "" } ], "_buildurl": "https://github.com/r-universe/cran/actions/runs/26434834314", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/cran/tesseract", "_commit": { "id": "57d6b6e806b89ad1263c33775c57ab9bd6c81957", "author": "Jeroen Ooms ", "committer": "cran-robot ", "message": "version 5.2.5\n", "time": 1769437802 }, "_maintainer": { "name": "Jeroen Ooms", "email": "jeroenooms@gmail.com", "login": "jeroen", "mastodon": "@jeroenooms@fosstodon.org", "bluesky": "@jeroenooms.bsky.social", "description": "Staff research engineer at @ropensci, tidyverse team member, and project lead for R-universe", "uuid": 216319, "orcid": "0000-0002-4035-0289" }, "_registered": true, "_dependencies": [ { "package": "Rcpp", "role": "LinkingTo" }, { "package": "Rcpp", "version": ">= 0.12.12", "role": "Imports" }, { "package": "pdftools", "version": ">= 1.5", "role": "Imports" }, { "package": "curl", "role": "Imports" }, { "package": "rappdirs", "role": "Imports" }, { "package": "digest", "role": "Imports" }, { "package": "magick", "version": ">= 1.7", "role": "Suggests" }, { "package": "spelling", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "tibble", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" } ], "_owner": "cran", "_selfowned": false, "_usedby": 0, "_updates": [ { "week": "2026-01", "n": 1 }, { "week": "2026-05", "n": 1 } ], "_tags": [ { "name": "5.2.4", "date": "2025-12-29" }, { "name": "5.2.5", "date": "2026-01-26" } ], "_stars": 0, "_contributors": [ { "user": "jeroen", "count": 25, "uuid": 216319 } ], "_userbio": { "uuid": 6899542, "type": "organization", "name": "cran", "description": "Unofficial read-only mirror of all CRAN R packages" }, "_downloads": { "count": 99840, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/tesseract" }, "_mentions": 2, "_devurl": "https://github.com/ropensci/tesseract", "_pkgdown": "https://docs.ropensci.org/tesseract/", "_searchresults": 606, "_topics": [ "tesseract", "cpp" ], "_rbuild": "4.6.0", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/NEWS.html", "extra/NEWS.txt", "extra/tesseract.html", "manual.pdf" ], "_homeurl": "https://github.com/ropensci/tesseract", "_realowner": "ropensci", "_cranurl": false, "_releases": [ { "version": "1.0", "date": "2016-11-03" }, { "version": "1.1", "date": "2016-11-10" }, { "version": "1.2", "date": "2016-11-13" }, { "version": "1.3", "date": "2016-12-07" }, { "version": "1.4", "date": "2017-03-21" }, { "version": "1.6", "date": "2017-08-14" }, { "version": "1.8", "date": "2018-01-26" }, { "version": "1.9", "date": "2018-02-16" }, { "version": "2.0", "date": "2018-03-02" }, { "version": "2.1", "date": "2018-05-03" }, { "version": "2.2", "date": "2018-07-10" }, { "version": "2.3", "date": "2018-08-10" }, { "version": "4.0", "date": "2018-11-02" }, { "version": "4.1", "date": "2019-07-25" }, { "version": "4.1.1", "date": "2021-05-10" }, { "version": "4.1.2", "date": "2021-09-18" }, { "version": "4.2.0", "date": "2021-12-03" }, { "version": "5.0.0", "date": "2022-01-10" }, { "version": "5.1.0", "date": "2022-05-29" }, { "version": "5.2.0", "date": "2023-09-26" }, { "version": "5.2.1", "date": "2023-11-20" }, { "version": "5.2.2", "date": "2024-10-04" }, { "version": "5.2.3", "date": "2025-03-23" }, { "version": "5.2.4", "date": "2025-12-29" }, { "version": "5.2.5", "date": "2026-01-26" } ], "_exports": [ "ocr", "ocr_data", "tesseract", "tesseract_download", "tesseract_info", "tesseract_params" ], "_help": [ { "page": "ocr", "title": "Tesseract OCR", "concept": [ "tesseract" ], "topics": [ "ocr", "ocr_data" ] }, { "page": "tesseract", "title": "Tesseract Engine", "concept": [ "tesseract" ], "topics": [ "tesseract", "tesseract_info", "tesseract_params" ] }, { "page": "tessdata", "title": "Tesseract Training Data", "concept": [ "tesseract" ], "topics": [ "tessdata", "tesseract_download" ] } ], "_rundeps": [ "askpass", "curl", "digest", "pdftools", "qpdf", "rappdirs", "Rcpp", "sys" ], "_sysdeps": [ { "shlib": "libtesseract", "package": "libtesseract5", "headers": "libtesseract-dev", "source": "tesseract", "version": "5.3.4-1build5", "name": "tesseract", "homepage": "https://github.com/tesseract-ocr/", "description": "Tesseract OCR library" }, { "shlib": "libstdc++", "package": "libstdc++6", "source": "gcc", "version": "14.2.0-4ubuntu2~24.04.1", "name": "c++", "homepage": "http://gcc.gnu.org/", "description": "GNU Standard C++ Library v3" } ], "_vignettes": [ { "source": "intro.Rmd", "filename": "intro.html", "title": "Using the Tesseract OCR engine in R", "engine": "knitr::rmarkdown", "headings": [ "Extract Text from Images", "Language Data", "Preprocessing with Magick", "Read from PDF files", "Tesseract Control Parameters", "Whitelist / Blacklist characters" ], "created": "2018-03-02 16:35:34", "modified": "2023-11-21 02:42:40", "commits": 9 } ], "_score": 6.383837187832597, "_indexed": false, "_nocasepkg": "tesseract", "_universes": [ "cran" ], "_indexurl": "https://ropensci.r-universe.dev/tesseract", "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "5.2.5", "date": "2026-05-26T05:55:29.000Z", "distro": "noble", "arch": "aarch64", "commit": "57d6b6e806b89ad1263c33775c57ab9bd6c81957", "fileid": "53a6f2cf2c806f3ce40b24df3e1088133d51a64d9bee2346140841d74e8b73ca", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/cran/actions/runs/26434834314" }, { "r": "4.7.0", "os": "linux", "version": "5.2.5", "date": "2026-05-26T05:55:26.000Z", "distro": "noble", "arch": "x86_64", "commit": "57d6b6e806b89ad1263c33775c57ab9bd6c81957", "fileid": "feae2b47b2e507f4fbab0f96e91a908bac820048c1069e21608351bd91733e6e", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/cran/actions/runs/26434834314" }, { "r": "4.6.0", "os": "linux", "version": "5.2.5", "date": "2026-05-26T05:55:24.000Z", "distro": "noble", "arch": "aarch64", "commit": "57d6b6e806b89ad1263c33775c57ab9bd6c81957", "fileid": "97816af7d11c12828f3325ee46843cfc0bc3404273f3df8fb914e733976aa524", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/cran/actions/runs/26434834314" }, { "r": "4.6.0", "os": "linux", "version": "5.2.5", "date": "2026-05-26T05:55:24.000Z", "distro": "noble", "arch": "x86_64", "commit": "57d6b6e806b89ad1263c33775c57ab9bd6c81957", "fileid": "da8051e1242b597572a8abcca9a0152e4e73092b08077e7310d70a5f6cb141d4", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/cran/actions/runs/26434834314" } ] }