{
  "_id": "6a1f0f02b401979e7341d471",
  "Package": "orderanalyzer",
  "Type": "Package",
  "Title": "Extracting Order Position Tables from PDF-Based Order Documents",
  "Version": "1.0.1",
  "Date": "2026-01-15",
  "Authors@R": "c(person(\"Michael\", \"Scholz\", email = \"michael.scholz@th-deg.de\", role = c(\"cre\", \"aut\")),\nperson(\"Joerg\", \"Bauer\", email = \"joerg.bauer@th-deg.de\", role = c(\"aut\")))",
  "Maintainer": "Michael Scholz <michael.scholz@th-deg.de>",
  "Description": "Functions for extracting text and tables from PDF-based\norder documents. It provides an n-gram-based approach for\nidentifying the language of an order document. It furthermore\nuses R-package 'pdftools' to extract the text from an order\ndocument. In the case that the PDF document is only including\nan image (because it is scanned document), R package\n'tesseract' is used for OCR. Furthermore, the package provides\nfunctionality for identifying and extracting order position\ntables in order documents based on a clustering approach.",
  "License": "GPL-3",
  "SystemRequirements": "Tesseract >= 5.0.0, libtesseract-dev (deb),\ntesseract-devel (rpm), libleptonica-dev (deb), leptonica-devel\n(rpm), tesseract-ocr-eng (deb), libpoppler-cpp-dev (deb),\npoppler-cpp-devel (rpm), poppler-data (rpm/deb), libxml2-dev\n(deb), libxml2-devel (rpm)",
  "Encoding": "UTF-8",
  "RoxygenNote": "7.3.3",
  "NeedsCompilation": "no",
  "Packaged": {
    "Date": "2026-05-17 08:43:57 UTC",
    "User": "root"
  },
  "Author": "Michael Scholz [cre, aut], Joerg Bauer [aut]",
  "Config/pak/sysreqs": "libleptonica-dev libicu-dev libxml2-dev\npoppler-data libtesseract-dev tesseract-ocr-eng",
  "Repository": "https://michael-scholz-dev.r-universe.dev",
  "Date/Publication": "2026-01-15 08:48:56 UTC",
  "RemoteUrl": "https://github.com/cran/orderanalyzer",
  "RemoteRef": "HEAD",
  "RemoteSha": "1080393bb8afdc39aa38db6aa14c89a95694d284",
  "MD5sum": "6b626eaf8e23db51815dec59486a3eb2",
  "_user": "michael-scholz-dev",
  "_type": "src",
  "_file": "orderanalyzer_1.0.1.tar.gz",
  "_fileid": "661905426dd354486e4669146e5cc3debbf97a84618179ad9f564066cdba7b6e",
  "_filesize": 306835,
  "_sha256": "661905426dd354486e4669146e5cc3debbf97a84618179ad9f564066cdba7b6e",
  "_created": "2026-05-17T08:43:57.000Z",
  "_published": "2026-06-02T17:12:34.338Z",
  "_distro": "noble",
  "_jobs": [
    {
      "job": 79128989559,
      "time": 135,
      "config": "linux-devel-x86_64",
      "r": "4.7.0",
      "check": "OK",
      "artifact": "7040933520"
    },
    {
      "job": 79128989515,
      "time": 154,
      "config": "linux-release-x86_64",
      "r": "4.6.0",
      "check": "OK",
      "artifact": "7040935959"
    },
    {
      "job": 79128989564,
      "time": 165,
      "config": "macos-oldrel-arm64",
      "r": "4.5.3",
      "check": "OK",
      "artifact": "7040932903"
    },
    {
      "job": 79128988925,
      "time": 146,
      "config": "macos-release-arm64",
      "r": "4.6.0",
      "check": "OK",
      "artifact": "7040932378"
    },
    {
      "job": 79128988791,
      "time": 160,
      "config": "source",
      "r": "4.6.0",
      "check": "OK",
      "artifact": "7040917480"
    },
    {
      "job": 79128988350,
      "time": 110,
      "config": "wasm-release",
      "r": "4.6.0",
      "check": "OK",
      "artifact": "7364754002"
    },
    {
      "job": 79128989027,
      "time": 123,
      "config": "windows-devel",
      "r": "4.7.0",
      "check": "OK",
      "artifact": "7040932126"
    },
    {
      "job": 79128989676,
      "time": 108,
      "config": "windows-oldrel",
      "r": "4.5.3",
      "check": "OK",
      "artifact": "7040930372"
    },
    {
      "job": 79128989264,
      "time": 150,
      "config": "windows-release",
      "r": "4.6.0",
      "check": "OK",
      "artifact": "7040935457"
    }
  ],
  "_buildurl": "https://github.com/r-universe/michael-scholz-dev/actions/runs/25986137741",
  "_status": "success",
  "_host": "GitHub-Actions",
  "_upstream": "https://github.com/cran/orderanalyzer",
  "_commit": {
    "id": "1080393bb8afdc39aa38db6aa14c89a95694d284",
    "author": "Michael Scholz <michael.scholz@th-deg.de>",
    "committer": "cran-robot <csardi.gabor+cran@gmail.com>",
    "message": "version 1.0.1\n",
    "time": 1768466936
  },
  "_maintainer": {
    "name": "Michael Scholz",
    "email": "michael.scholz@th-deg.de",
    "login": "michael-scholz-dev",
    "description": "",
    "uuid": 191120234
  },
  "_registered": true,
  "_dependencies": [
    {
      "package": "R",
      "version": ">= 4.3.0",
      "role": "Depends"
    },
    {
      "package": "tidyselect",
      "role": "Depends"
    },
    {
      "package": "data.table",
      "role": "Imports"
    },
    {
      "package": "dplyr",
      "role": "Imports"
    },
    {
      "package": "matrixcalc",
      "role": "Imports"
    },
    {
      "package": "quanteda",
      "role": "Imports"
    },
    {
      "package": "rlist",
      "role": "Imports"
    },
    {
      "package": "stringr",
      "role": "Imports"
    },
    {
      "package": "tibble",
      "role": "Imports"
    },
    {
      "package": "tidyr",
      "role": "Imports"
    },
    {
      "package": "utils",
      "role": "Imports"
    },
    {
      "package": "purrr",
      "role": "Imports"
    },
    {
      "package": "digest",
      "role": "Imports"
    },
    {
      "package": "lubridate",
      "role": "Imports"
    },
    {
      "package": "pdftools",
      "role": "Suggests"
    },
    {
      "package": "tesseract",
      "role": "Suggests"
    },
    {
      "package": "xml2",
      "role": "Suggests"
    }
  ],
  "_owner": "cran",
  "_selfowned": true,
  "_usedby": 0,
  "_updates": [
    {
      "week": "2026-03",
      "n": 1
    }
  ],
  "_tags": [
    {
      "name": "1.0.1",
      "date": "2026-01-15"
    }
  ],
  "_stars": 0,
  "_contributors": [
    {
      "user": "michael-scholz-dev",
      "count": 2,
      "uuid": 191120234
    }
  ],
  "_userbio": {
    "uuid": 191120234,
    "type": "user",
    "name": "Michael-Scholz-Dev"
  },
  "_downloads": {
    "count": 486,
    "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/orderanalyzer"
  },
  "_searchresults": 0,
  "_rbuild": "4.6.0",
  "_assets": [
    "extra/citation.cff",
    "extra/citation.html",
    "extra/citation.json",
    "extra/citation.txt",
    "extra/contents.json",
    "extra/orderanalyzer.html",
    "manual.pdf"
  ],
  "_realowner": "michael-scholz-dev",
  "_cranurl": false,
  "_releases": [
    {
      "version": "1.0.0",
      "date": "2024-12-12"
    },
    {
      "version": "1.0.1",
      "date": "2026-01-15"
    }
  ],
  "_exports": [
    "extractTables",
    "extractText",
    "identifyLanguage"
  ],
  "_help": [
    {
      "page": "orderanalyzer-package",
      "title": "Extracting order position tables from PDF-based order documents",
      "topics": [
        "orderanalyzer-package",
        "orderanalyzer"
      ]
    },
    {
      "page": "extractTables",
      "title": "Extract tables from a given words-dataframe",
      "topics": [
        "extractTables"
      ]
    },
    {
      "page": "extractText",
      "title": "Extracts the text from a PDF file",
      "topics": [
        "extractText"
      ]
    },
    {
      "page": "identifyLanguage",
      "title": "Identifies the language of a given text based on frequent trigrams",
      "topics": [
        "identifyLanguage"
      ]
    }
  ],
  "_rundeps": [
    "cli",
    "cpp11",
    "data.table",
    "digest",
    "dplyr",
    "fastmatch",
    "generics",
    "glue",
    "ISOcodes",
    "jsonlite",
    "lattice",
    "lifecycle",
    "lubridate",
    "magrittr",
    "Matrix",
    "matrixcalc",
    "pillar",
    "pkgconfig",
    "purrr",
    "quanteda",
    "R6",
    "Rcpp",
    "rlang",
    "rlist",
    "SnowballC",
    "stopwords",
    "stringi",
    "stringr",
    "tibble",
    "tidyr",
    "tidyselect",
    "timechange",
    "utf8",
    "vctrs",
    "withr",
    "XML",
    "xml2",
    "yaml"
  ],
  "_score": 1,
  "_indexed": true,
  "_nocasepkg": "orderanalyzer",
  "_universes": [
    "michael-scholz-dev"
  ],
  "_binaries": [
    {
      "r": "4.7.0",
      "os": "linux",
      "version": "1.0.1",
      "date": "2026-05-17T08:45:53.000Z",
      "distro": "noble",
      "commit": "1080393bb8afdc39aa38db6aa14c89a95694d284",
      "fileid": "6803879975532086bcafeccef6bf9370d6aa16083936b245568d3a30228b8e29",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/michael-scholz-dev/actions/runs/25986137741"
    },
    {
      "r": "4.6.0",
      "os": "linux",
      "version": "1.0.1",
      "date": "2026-05-17T08:46:09.000Z",
      "distro": "noble",
      "commit": "1080393bb8afdc39aa38db6aa14c89a95694d284",
      "fileid": "c5958f4dd2d6596976fe27418aac4599f3122ab5372bb21b70ee210a946c501c",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/michael-scholz-dev/actions/runs/25986137741"
    },
    {
      "r": "4.5.3",
      "os": "mac",
      "version": "1.0.1",
      "date": "2026-05-17T08:46:02.000Z",
      "commit": "1080393bb8afdc39aa38db6aa14c89a95694d284",
      "fileid": "414ddd39039c1e209c5f5c9f70b4121f6951995a7e05fe985561437e3867dea5",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/michael-scholz-dev/actions/runs/25986137741"
    },
    {
      "r": "4.6.0",
      "os": "mac",
      "version": "1.0.1",
      "date": "2026-05-17T08:45:56.000Z",
      "commit": "1080393bb8afdc39aa38db6aa14c89a95694d284",
      "fileid": "2fbdf4cca74cd9c6b9b2a193ea2a124e63db0c3f5fda9ae5dcdf38479edd868c",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/michael-scholz-dev/actions/runs/25986137741"
    },
    {
      "r": "4.7.0",
      "os": "win",
      "version": "1.0.1",
      "date": "2026-05-17T08:45:34.000Z",
      "commit": "1080393bb8afdc39aa38db6aa14c89a95694d284",
      "fileid": "f685b447d6466b35af5e7dca933e089bdbe10a94a466dddfecde5e3ae6aaee19",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/michael-scholz-dev/actions/runs/25986137741"
    },
    {
      "r": "4.5.3",
      "os": "win",
      "version": "1.0.1",
      "date": "2026-05-17T08:45:13.000Z",
      "commit": "1080393bb8afdc39aa38db6aa14c89a95694d284",
      "fileid": "e0c2567389d078621f07d837f3b941e43d46ccfbaa7c3cfeba1e68e69b2b6ada",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/michael-scholz-dev/actions/runs/25986137741"
    },
    {
      "r": "4.6.0",
      "os": "win",
      "version": "1.0.1",
      "date": "2026-05-17T08:45:59.000Z",
      "commit": "1080393bb8afdc39aa38db6aa14c89a95694d284",
      "fileid": "724519ae7bc3f85cb8812c8ddbdf6e9247f63f51b3f3d118252e749c7ac68aea",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/michael-scholz-dev/actions/runs/25986137741"
    },
    {
      "r": "4.6.0",
      "os": "wasm",
      "version": "1.0.1",
      "date": "2026-06-02T17:12:15.000Z",
      "commit": "1080393bb8afdc39aa38db6aa14c89a95694d284",
      "fileid": "68323225c4034aa5c0099fc328fb11335ae7add5430c2c5ab9df5f8b653c485a",
      "status": "success",
      "buildurl": "https://github.com/r-universe/michael-scholz-dev/actions/runs/25986137741"
    }
  ]
}