{
  "_id": "6ad33a3e6814ce853b65875e",
  "Package": "inpdfr",
  "Type": "Package",
  "Title": "Analyse Text Documents Using Ecological Tools",
  "Version": "0.1.12",
  "Author": "Rebaudo Francois (IRD, UMR EGCE, IRD, CNRS, Univ. ParisSaclay)",
  "Maintainer": "Rebaudo Francois <francois.rebaudo@ird.fr>",
  "Description": "A set of functions to analyse and compare texts, using\nclassical text mining functions, as well as those from\ntheoretical ecology.",
  "License": "GPL-2",
  "LazyData": "TRUE",
  "SystemRequirements": "XPDF (http://www.foolabs.com/xpdf/download.html)",
  "VignetteBuilder": "knitr",
  "RoxygenNote": "7.2.3",
  "URL": "https://github.com/frareb/inpdfr/",
  "BugReports": "https://github.com/frareb/inpdfr/issues",
  "Config/pak/sysreqs": "cmake make libicu-dev libxml2-dev",
  "Repository": "https://frareb.r-universe.dev",
  "Date/Publication": "2023-08-24 07:30:33 UTC",
  "RemoteUrl": "https://github.com/frareb/inpdfr",
  "RemoteRef": "HEAD",
  "RemoteSha": "845a901af9d67928993047774dda2a730027b3ca",
  "NeedsCompilation": "no",
  "Packaged": {
    "Date": "2026-10-17 08:59:46 UTC",
    "User": "root"
  },
  "_user": "frareb",
  "_type": "src",
  "_file": "inpdfr_0.1.12.tar.gz",
  "_fileid": "https://r2.ropensci.org/1e9da6d1e32422e2a1c4fb0b243a3962fb92bc90caec09812d5421fb4374dbcf",
  "_filesize": 201922,
  "_sha256": "1e9da6d1e32422e2a1c4fb0b243a3962fb92bc90caec09812d5421fb4374dbcf",
  "_expires": "2027-01-25T09:05:00.000Z",
  "_created": "2026-10-17T08:59:46.000Z",
  "_published": "2026-10-17T09:05:02.492Z",
  "_buildurl": "https://github.com/r-universe/frareb/actions/runs/39019233854",
  "_status": "success",
  "_host": "GitHub-Actions",
  "_jobs": [
    {
      "job": 117358153902,
      "time": 171,
      "config": "linux-devel-x86_64",
      "r": "4.7.0",
      "check": "OK",
      "artifact": "12096341459"
    },
    {
      "job": 117358153874,
      "time": 166,
      "config": "linux-release-x86_64",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "12095814290"
    },
    {
      "job": 117358153879,
      "time": 197,
      "config": "macos-oldrel-arm64",
      "r": "4.5.3",
      "check": "OK",
      "artifact": "12096182555"
    },
    {
      "job": 117358154026,
      "time": 193,
      "config": "macos-release-arm64",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "12095804541"
    },
    {
      "job": 117357579417,
      "time": 201,
      "config": "source",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "12096435808"
    },
    {
      "job": 117358153748,
      "time": 124,
      "config": "wasm-release",
      "r": "4.6.0",
      "check": "OK",
      "artifact": "12095744675"
    },
    {
      "job": 117358153806,
      "time": 125,
      "config": "windows-devel-x86_64",
      "r": "4.7.0",
      "check": "OK",
      "artifact": "12095634773"
    },
    {
      "job": 117358153792,
      "time": 110,
      "config": "windows-oldrel-x86_64",
      "r": "4.5.3",
      "check": "OK",
      "artifact": "12095634752"
    },
    {
      "job": 117358153839,
      "time": 149,
      "config": "windows-release-x86_64",
      "r": "4.6.1",
      "check": "OK",
      "artifact": "12096301634"
    }
  ],
  "_upstream": "https://github.com/frareb/inpdfr",
  "_commit": {
    "id": "845a901af9d67928993047774dda2a730027b3ca",
    "author": "frareb <francois.rebaudo@ird.fr>",
    "committer": "frareb <francois.rebaudo@ird.fr>",
    "message": "fix package documentation and PKGNAME-package \\alias\n",
    "time": 1692862233
  },
  "_maintainer": {
    "name": "Rebaudo Francois",
    "email": "francois.rebaudo@ird.fr",
    "login": "frareb",
    "description": "",
    "uuid": 16336998
  },
  "_distro": "resolute",
  "_registered": true,
  "_dependencies": [
    {
      "package": "R",
      "version": ">= 3.5.0",
      "role": "Depends"
    },
    {
      "package": "wordcloud",
      "version": ">= 2.5",
      "role": "Imports"
    },
    {
      "package": "RColorBrewer",
      "version": ">= 1.1-2",
      "role": "Imports"
    },
    {
      "package": "tm",
      "version": ">= 0.6-2",
      "role": "Imports"
    },
    {
      "package": "SnowballC",
      "version": ">= 0.5.1",
      "role": "Imports"
    },
    {
      "package": "cluster",
      "version": ">= 2.0.1",
      "role": "Imports"
    },
    {
      "package": "entropart",
      "version": ">= 1.4.1",
      "role": "Imports"
    },
    {
      "package": "metacom",
      "version": ">= 1.4.4",
      "role": "Imports"
    },
    {
      "package": "parallel",
      "version": ">= 3.1.3",
      "role": "Imports"
    },
    {
      "package": "stringi",
      "version": ">= 1.0-1",
      "role": "Imports"
    },
    {
      "package": "R.devices",
      "version": ">= 2.14.0",
      "role": "Imports"
    },
    {
      "package": "knitr",
      "role": "Suggests"
    },
    {
      "package": "rmarkdown",
      "role": "Suggests"
    },
    {
      "package": "testthat",
      "role": "Suggests"
    }
  ],
  "_owner": "frareb",
  "_selfowned": true,
  "_usedby": 0,
  "_updates": [],
  "_tags": [],
  "_stars": 2,
  "_contributors": [
    {
      "user": "frareb",
      "count": 93,
      "uuid": 16336998
    }
  ],
  "_userbio": {
    "uuid": 16336998,
    "type": "user",
    "name": "frareb",
    "followers": 5
  },
  "_downloads": {
    "count": 284,
    "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/inpdfr"
  },
  "_devurl": "https://github.com/frareb/inpdfr",
  "_searchresults": 30,
  "_rbuild": "4.6.1",
  "_assets": [
    "extra/citation.cff",
    "extra/citation.html",
    "extra/citation.json",
    "extra/citation.txt",
    "extra/contents.json",
    "extra/inpdfr.html",
    "extra/manual.pdf",
    "extra/NEWS.html",
    "extra/NEWS.txt",
    "extra/readme.html",
    "extra/readme.md"
  ],
  "_homeurl": "https://github.com/frareb/inpdfr",
  "_realowner": "frareb",
  "_cranurl": true,
  "_releases": [
    {
      "version": "0.1.1",
      "date": "2016-02-24"
    },
    {
      "version": "0.1.2",
      "date": "2016-03-22"
    },
    {
      "version": "0.1.3",
      "date": "2016-04-18"
    },
    {
      "version": "0.1.5",
      "date": "2017-02-27"
    },
    {
      "version": "0.1.6",
      "date": "2017-12-20"
    },
    {
      "version": "0.1.8",
      "date": "2018-10-24"
    },
    {
      "version": "0.1.11",
      "date": "2020-01-16"
    },
    {
      "version": "0.1.12",
      "date": "2023-08-24"
    }
  ],
  "_exports": [
    "doCluster",
    "doKmeansClust",
    "doMetacomEntropart",
    "doMetacomMetacom",
    "excludeStopWords",
    "getAllAnalysis",
    "getListFiles",
    "getMostFreqWord",
    "getMostFreqWordCor",
    "getPDF",
    "getStopWords",
    "getSummaryStatsBARPLOT",
    "getSummaryStatsHISTO",
    "getSummaryStatsOCCUR",
    "getTXT",
    "getwordOccuDF",
    "getXFreqWord",
    "IdentifyStructure",
    "makeWordcloud",
    "mergeWordFreq",
    "postProcTxt",
    "preProcTxt",
    "quitSpaceFromChars",
    "truncNumWords"
  ],
  "_datasets": [
    {
      "name": "exclusionList_FR",
      "title": "Stop words in French.",
      "object": "exclusionList_FR",
      "class": [
        "character"
      ],
      "fields": [],
      "table": false,
      "tojson": true
    },
    {
      "name": "exclusionList_SP",
      "title": "Stop words in Spanish.",
      "object": "exclusionList_SP",
      "class": [
        "character"
      ],
      "fields": [],
      "table": false,
      "tojson": true
    },
    {
      "name": "exclusionList_UK",
      "title": "Stop words in English.",
      "object": "exclusionList_UK",
      "class": [
        "character"
      ],
      "fields": [],
      "table": false,
      "tojson": true
    },
    {
      "name": "loremIpsum",
      "title": "Lorem Ipsum text.",
      "object": "loremIpsum",
      "class": [
        "character"
      ],
      "fields": [],
      "table": false,
      "tojson": true
    },
    {
      "name": "wordOccuDF",
      "title": "Lorem Ipsum word occurrences.",
      "object": "wordOccuDF",
      "class": [
        "data.frame"
      ],
      "fields": [
        "word",
        "loremIpsum01",
        "loremIpsum02",
        "loremIpsum03",
        "loremIpsum04",
        "loremIpsum05"
      ],
      "rows": 161,
      "table": true,
      "tojson": true
    }
  ],
  "_help": [
    {
      "page": "doCluster",
      "title": "Performs a cluster analysis on the basis of the word-occurrence data.frame.",
      "topics": [
        "doCluster"
      ]
    },
    {
      "page": "doKmeansClust",
      "title": "Performs a k-means cluster analysis on the basis of the word-occurrence data.frame.",
      "topics": [
        "doKmeansClust"
      ]
    },
    {
      "page": "doMetacomEntropart",
      "title": "Performs an analysis of ecological diversity and structure.",
      "topics": [
        "doMetacomEntropart"
      ]
    },
    {
      "page": "doMetacomMetacom",
      "title": "Performs a metacomunity analysis.",
      "topics": [
        "doMetacomMetacom"
      ]
    },
    {
      "page": "excludeStopWords",
      "title": "Exclude StopWords form the word-occurrence data.frame.",
      "topics": [
        "excludeStopWords"
      ]
    },
    {
      "page": "exclusionList_FR",
      "title": "Stop words in French.",
      "topics": [
        "exclusionList_FR"
      ]
    },
    {
      "page": "exclusionList_SP",
      "title": "Stop words in Spanish.",
      "topics": [
        "exclusionList_SP"
      ]
    },
    {
      "page": "exclusionList_UK",
      "title": "Stop words in English.",
      "topics": [
        "exclusionList_UK"
      ]
    },
    {
      "page": "getAllAnalysis",
      "title": "A quick way to compute a set of analysis from the word-occurrence data.frame.",
      "topics": [
        "getAllAnalysis"
      ]
    },
    {
      "page": "getListFiles",
      "title": "List files in a specified directory sorted by extension.",
      "topics": [
        "getListFiles"
      ]
    },
    {
      "page": "getMostFreqWord",
      "title": "Returns most frequent words.",
      "topics": [
        "getMostFreqWord"
      ]
    },
    {
      "page": "getMostFreqWordCor",
      "title": "Test for correlation between the most frequent words.",
      "topics": [
        "getMostFreqWordCor"
      ]
    },
    {
      "page": "getPDF",
      "title": "Extract text from PDF files and return a word-occurrence data.frame.",
      "topics": [
        "getPDF"
      ]
    },
    {
      "page": "getStopWords",
      "title": "Load a list of stopwords.",
      "topics": [
        "getStopWords"
      ]
    },
    {
      "page": "getSummaryStatsBARPLOT",
      "title": "Perform a barplot with the number of unique words per document",
      "topics": [
        "getSummaryStatsBARPLOT"
      ]
    },
    {
      "page": "getSummaryStatsHISTO",
      "title": "Plot an histogram with the number of words excluding stop words",
      "topics": [
        "getSummaryStatsHISTO"
      ]
    },
    {
      "page": "getSummaryStatsOCCUR",
      "title": "Plot a scatter plot with the proportion of documents using similar words.",
      "topics": [
        "getSummaryStatsOCCUR"
      ]
    },
    {
      "page": "getTXT",
      "title": "Extract text from TXT files and return a word-occurrence data.frame.",
      "topics": [
        "getTXT"
      ]
    },
    {
      "page": "getwordOccuDF",
      "title": "A quick way to obtain the word-occurrence data.frame from a set of documents.",
      "topics": [
        "getwordOccuDF"
      ]
    },
    {
      "page": "getXFreqWord",
      "title": "Returns most frequent words",
      "topics": [
        "getXFreqWord"
      ]
    },
    {
      "page": "IdentifyStructure",
      "title": "Copy of the identifyStructure function from Tad Dallas metacom package.",
      "topics": [
        "IdentifyStructure"
      ]
    },
    {
      "page": "inpdfr",
      "title": "inpdfr: A package to analyse PDF Files Using Ecological Tools.",
      "topics": [
        "inpdfr-package",
        "inpdfr"
      ]
    },
    {
      "page": "loremIpsum",
      "title": "Lorem Ipsum text.",
      "topics": [
        "loremIpsum"
      ]
    },
    {
      "page": "makeWordcloud",
      "title": "Word cloud based on the word-occurrence data.frame.",
      "topics": [
        "makeWordcloud"
      ]
    },
    {
      "page": "mergeWordFreq",
      "title": "Merge word-occurrence data.frames into a single data.frame.",
      "topics": [
        "mergeWordFreq"
      ]
    },
    {
      "page": "postProcTxt",
      "title": "Prossess vectors containing words into a data.frame of word occurrences.",
      "topics": [
        "postProcTxt"
      ]
    },
    {
      "page": "preProcTxt",
      "title": "Extract text from txt files and pre-process content.",
      "topics": [
        "preProcTxt"
      ]
    },
    {
      "page": "quitSpaceFromChars",
      "title": "Delete spaces in file names.",
      "topics": [
        "quitSpaceFromChars"
      ]
    },
    {
      "page": "truncNumWords",
      "title": "Truncate the word-occurrence data.frame.",
      "topics": [
        "truncNumWords"
      ]
    },
    {
      "page": "wordOccuDF",
      "title": "Lorem Ipsum word occurrences.",
      "topics": [
        "wordOccuDF"
      ]
    }
  ],
  "_readme": "https://github.com/frareb/inpdfr/raw/HEAD/README.md",
  "_rundeps": [
    "abind",
    "ape",
    "backports",
    "base64enc",
    "BH",
    "boot",
    "broom",
    "car",
    "carData",
    "cli",
    "cluster",
    "colorspace",
    "corrplot",
    "cowplot",
    "cpp11",
    "Deriv",
    "digest",
    "doBy",
    "dplyr",
    "entropart",
    "EntropyEstimation",
    "farver",
    "forecast",
    "Formula",
    "fracdiff",
    "generics",
    "ggplot2",
    "ggpubr",
    "ggrepel",
    "ggsci",
    "ggsignif",
    "glue",
    "gridExtra",
    "gtable",
    "isoband",
    "labeling",
    "lattice",
    "lifecycle",
    "lme4",
    "lmtest",
    "magrittr",
    "MASS",
    "Matrix",
    "MatrixModels",
    "metacom",
    "mgcv",
    "minqa",
    "modelr",
    "nlme",
    "nloptr",
    "NLP",
    "nnet",
    "numDeriv",
    "pbkrtest",
    "permute",
    "pillar",
    "pkgconfig",
    "plyr",
    "polynom",
    "purrr",
    "quantreg",
    "R.devices",
    "R.methodsS3",
    "R.oo",
    "R.utils",
    "R6",
    "rbibutils",
    "RColorBrewer",
    "Rcpp",
    "RcppArmadillo",
    "RcppEigen",
    "Rdpack",
    "reformulas",
    "reshape2",
    "rlang",
    "rstatix",
    "S7",
    "scales",
    "slam",
    "SnowballC",
    "SparseM",
    "stringi",
    "stringr",
    "survival",
    "tibble",
    "tidyr",
    "tidyselect",
    "timeDate",
    "tm",
    "urca",
    "utf8",
    "vctrs",
    "vegan",
    "viridisLite",
    "withr",
    "wordcloud",
    "xml2",
    "zoo"
  ],
  "_vignettes": [
    {
      "source": "inpdfr-vignette.Rmd",
      "filename": "inpdfr-vignette.html",
      "title": "Introduction to inpdfr package",
      "author": "François Rebaudo, Institut de Recherche pour le Développement, UMR EGCE, Univ.Paris Sud-CNRS-IRD-Univ.Paris Saclay, France",
      "engine": "knitr::rmarkdown",
      "headings": [
        "1. Using inpdfr from command line",
        "1.1 Obtaining the word-occurrence data.frame from a set of documents",
        "1.1.1. Extracting text from PDF",
        "1.1.2. Excluding stop words",
        "1.1.3. Truncation of the number of words",
        "1.1.4. Merging data.frames",
        "1.1.5. Quick function",
        "1.2. Computing a set of analysis from the word-occurrence data.frame",
        "1.2.1. Simple manipulations of the word occurrence data.frame",
        "1.2.2. Word cloud",
        "1.2.3. Summary statistics",
        "1.2.4. Word frequency",
        "1.2.5. Correspondance analysis",
        "1.2.6. Cluster analysis",
        "1.2.7. K-means cluster analysis",
        "1.2.8. Metacommunity analysis with entropart",
        "1.2.9. Metacommunity analysis with metacom",
        "1.2.10. Quick function",
        "2. Using inpdfr from the Graphical User Interface (GUI)",
        "3. Going further"
      ],
      "created": "2016-03-11 19:04:38",
      "modified": "2023-08-24 07:30:33",
      "commits": 3
    }
  ],
  "_score": 4.477121254719663,
  "_indexed": true,
  "_nocasepkg": "inpdfr",
  "_universes": [
    "frareb"
  ],
  "_binaries": [
    {
      "r": "4.7.0",
      "os": "linux",
      "version": "0.1.12",
      "date": "2026-10-17T09:02:22.000Z",
      "distro": "resolute",
      "commit": "845a901af9d67928993047774dda2a730027b3ca",
      "fileid": "https://r2.ropensci.org/b4ef83bb37575badccb261adde00832370a0141dee80da520bc8a7cffa08705a",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/frareb/actions/runs/39019233854"
    },
    {
      "r": "4.6.1",
      "os": "linux",
      "version": "0.1.12",
      "date": "2026-10-17T09:02:23.000Z",
      "distro": "resolute",
      "commit": "845a901af9d67928993047774dda2a730027b3ca",
      "fileid": "https://r2.ropensci.org/1fcab01a29d8394f6837424d722213ddd8907aa09bb61178a452ade63b9fb41e",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/frareb/actions/runs/39019233854"
    },
    {
      "r": "4.5.3",
      "os": "mac",
      "version": "0.1.12",
      "date": "2026-10-17T09:03:26.000Z",
      "commit": "845a901af9d67928993047774dda2a730027b3ca",
      "fileid": "https://r2.ropensci.org/1dff2cf944ad7883909480174d6b5f190e32ce0bed875432e65bed64a3fefc17",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/frareb/actions/runs/39019233854"
    },
    {
      "r": "4.6.1",
      "os": "mac",
      "version": "0.1.12",
      "date": "2026-10-17T09:03:40.000Z",
      "commit": "845a901af9d67928993047774dda2a730027b3ca",
      "fileid": "https://r2.ropensci.org/9381109b168b8033179ce8e3b4b524f0bfecc59eb3653c204ef85cd5871e1d6c",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/frareb/actions/runs/39019233854"
    },
    {
      "r": "4.6.0",
      "os": "wasm",
      "version": "0.1.12",
      "date": "2026-10-17T09:02:03.000Z",
      "commit": "845a901af9d67928993047774dda2a730027b3ca",
      "fileid": "https://r2.ropensci.org/8010ca86aa39f64b8893905121f8acbb3db935de714b048636eeff6d79664ec2",
      "status": "success",
      "buildurl": "https://github.com/r-universe/frareb/actions/runs/39019233854"
    },
    {
      "r": "4.7.0",
      "os": "win",
      "version": "0.1.12",
      "date": "2026-10-17T09:01:26.000Z",
      "commit": "845a901af9d67928993047774dda2a730027b3ca",
      "fileid": "https://r2.ropensci.org/1782a5ca7f23dde8bbe1fc606f854a25344005802c35a4c551a57cc077fa5910",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/frareb/actions/runs/39019233854"
    },
    {
      "r": "4.5.3",
      "os": "win",
      "version": "0.1.12",
      "date": "2026-10-17T09:01:19.000Z",
      "commit": "845a901af9d67928993047774dda2a730027b3ca",
      "fileid": "https://r2.ropensci.org/17a9c999b4bb44fe07cff7072136da8f112e555571386d74bd58591768645d94",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/frareb/actions/runs/39019233854"
    },
    {
      "r": "4.6.1",
      "os": "win",
      "version": "0.1.12",
      "date": "2026-10-17T09:01:54.000Z",
      "commit": "845a901af9d67928993047774dda2a730027b3ca",
      "fileid": "https://r2.ropensci.org/142543bf1679c86ad351b45b1b2eb7c77b491ee77bebc69653e8173347b27880",
      "status": "success",
      "check": "OK",
      "buildurl": "https://github.com/r-universe/frareb/actions/runs/39019233854"
    }
  ]
}