{
  "_id": "6a2e64f83efcd9bda43105ca",
  "Package": "repboxDoc",
  "Type": "Package",
  "Title": "Heuristically prepare PDF or HTML articles or appendices for\nfurther repbox analysis",
  "Version": "0.1.0",
  "Author": "Sebastian Kranz",
  "Maintainer": "Sebastian Kranz <sebastian.kranz@uni-ulm.de>",
  "Description": "Heuristically prepare PDF or HTML articles or appendices\nfor further repbox analysis",
  "License": "GPL >= 2.0",
  "Encoding": "UTF-8",
  "Config/pak/sysreqs": "cmake libfontconfig1-dev libfreetype6-dev\nlibfribidi-dev git make libharfbuzz-dev libgit2-dev libicu-dev\nlibjpeg-dev libpng-dev libtiff-dev libuv1-dev libwebp-dev\nlibxml2-dev libssl-dev libx11-dev zlib1g-dev",
  "Repository": "https://skranz.r-universe.dev",
  "Date/Publication": "2026-04-15 09:20:28 UTC",
  "RemoteUrl": "https://github.com/repboxr/repboxDoc",
  "RemoteRef": "main",
  "RemoteSha": "e0f14b8502cc1b0d57d0ff83e33db74fe27b2bf5",
  "NeedsCompilation": "no",
  "Packaged": {
    "Date": "2026-06-14 08:20:14 UTC",
    "User": "root"
  },
  "MD5sum": "2eef7df14f3b69e8d4e93c3fc11bb188",
  "_user": "skranz",
  "_type": "src",
  "_file": "repboxDoc_0.1.0.tar.gz",
  "_fileid": "593625e34d588bb2daf8b703c7da84a621f690ca44b940b23319e3c9e78d7461",
  "_filesize": 147260,
  "_sha256": "593625e34d588bb2daf8b703c7da84a621f690ca44b940b23319e3c9e78d7461",
  "_created": "2026-06-14T08:20:14.000Z",
  "_published": "2026-06-14T08:23:20.028Z",
  "_distro": "noble",
  "_jobs": [
    {
      "job": 81261878330,
      "time": 146,
      "config": "linux-devel-x86_64",
      "r": "4.7.0",
      "check": "WARNING",
      "artifact": "7619097755"
    },
    {
      "job": 81261878321,
      "time": 146,
      "config": "linux-release-x86_64",
      "r": "4.6.0",
      "check": "WARNING",
      "artifact": "7619097072"
    },
    {
      "job": 81261878314,
      "time": 108,
      "config": "macos-oldrel-arm64",
      "r": "4.5.3",
      "check": "WARNING",
      "artifact": "7619092094"
    },
    {
      "job": 81261878318,
      "time": 88,
      "config": "macos-release-arm64",
      "r": "4.6.0",
      "check": "WARNING",
      "artifact": "7619089226"
    },
    {
      "job": 81261676884,
      "time": 187,
      "config": "source",
      "r": "4.6.0",
      "check": "OK",
      "artifact": "7619076898"
    },
    {
      "job": 81261878310,
      "time": 134,
      "config": "wasm-release",
      "r": "4.6.0",
      "check": "OK",
      "artifact": "7619096152"
    },
    {
      "job": 81261878352,
      "time": 84,
      "config": "windows-devel",
      "r": "4.7.0",
      "check": "WARNING",
      "artifact": "7619088866"
    },
    {
      "job": 81261878319,
      "time": 80,
      "config": "windows-oldrel",
      "r": "4.5.3",
      "check": "WARNING",
      "artifact": "7619088454"
    },
    {
      "job": 81261878320,
      "time": 79,
      "config": "windows-release",
      "r": "4.6.0",
      "check": "WARNING",
      "artifact": "7619088651"
    }
  ],
  "_buildurl": "https://github.com/r-universe/skranz/actions/runs/27492994348",
  "_status": "success",
  "_host": "GitHub-Actions",
  "_upstream": "https://github.com/repboxr/repboxDoc",
  "_commit": {
    "id": "e0f14b8502cc1b0d57d0ff83e33db74fe27b2bf5",
    "author": "skranz-auto <xsx50@uni-ulm.de>",
    "committer": "skranz-auto <xsx50@uni-ulm.de>",
    "message": "Update from server\n",
    "time": 1776244828
  },
  "_maintainer": {
    "name": "Sebastian Kranz",
    "email": "sebastian.kranz@uni-ulm.de",
    "login": "skranz",
    "bluesky": "@sebkranz.bsky.social",
    "description": "",
    "uuid": 1413022
  },
  "_registered": true,
  "_dependencies": [
    {
      "package": "R",
      "version": ">= 3.5.0",
      "role": "Depends"
    },
    {
      "package": "repboxUtils",
      "role": "Depends"
    },
    {
      "package": "restorepoint",
      "role": "Depends"
    },
    {
      "package": "stringi",
      "role": "Depends"
    },
    {
      "package": "tidyr",
      "role": "Depends"
    },
    {
      "package": "dplyr",
      "role": "Depends"
    },
    {
      "package": "stringtools",
      "role": "Depends"
    },
    {
      "package": "ExtractSciTab",
      "role": "Depends"
    },
    {
      "package": "repboxTableTools",
      "role": "Depends"
    }
  ],
  "_owner": "repboxr",
  "_selfowned": true,
  "_usedby": 1,
  "_updates": [
    {
      "week": "2025-26",
      "n": 1
    },
    {
      "week": "2025-27",
      "n": 1
    },
    {
      "week": "2025-52",
      "n": 1
    },
    {
      "week": "2026-13",
      "n": 2
    },
    {
      "week": "2026-16",
      "n": 1
    }
  ],
  "_tags": [],
  "_stars": 0,
  "_contributors": [
    {
      "user": "skranz-auto",
      "count": 12,
      "uuid": 124874982
    },
    {
      "user": "skranz",
      "count": 1,
      "uuid": 1413022
    }
  ],
  "_userbio": {
    "uuid": 1413022,
    "type": "user",
    "name": "Sebastian Kranz",
    "followers": 216
  },
  "_downloads": {
    "count": 0,
    "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/repboxDoc"
  },
  "_devurl": "https://github.com/repboxr/repboxdoc",
  "_searchresults": 8,
  "_rbuild": "4.6.0",
  "_assets": [
    "extra/citation.cff",
    "extra/citation.html",
    "extra/citation.json",
    "extra/citation.txt",
    "extra/contents.json",
    "extra/readme.html",
    "extra/readme.md",
    "extra/repboxDoc.html",
    "manual.pdf"
  ],
  "_cranurl": false,
  "_exports": [
    "bind_rows_with_parent_fields",
    "cell_df_join",
    "cell_df_to_tabhtml",
    "change_file_ext",
    "check_and_repair_footnote_candidates",
    "combine_short_paragraphs",
    "combine_text_lines",
    "doc_dir_to_artid",
    "doc_dir_to_project_dir",
    "ecta_parse_html",
    "ecta_parse_html_table",
    "ends.with.text",
    "ensure_empty_types",
    "example",
    "example_mocr_make",
    "extract_all_to_index_df",
    "extract_num_from_sequence_text",
    "extract_order_num_from_sequence_text",
    "find_wrong_mocr",
    "first_repair_rdoc_pdf_text",
    "first.non.null",
    "from_to",
    "get_phrases_def",
    "guess_journ_from_artid",
    "html_tab_cell_row_panel_df",
    "html_table_cells_from_all_tr",
    "html_table_cells_from_tr",
    "html_text_part_df_standardize",
    "identify_figure_lines_on_page",
    "is_aer_pandp",
    "is_really_a_note_line",
    "is.true",
    "jpe_parse_html",
    "jpe_parse_html_table",
    "keep.overlapping.loc",
    "left_join_overlap",
    "line_df_find_figures",
    "line_df_find_footnotes",
    "line_df_find_junk_lines",
    "line_df_find_page_header_footer",
    "line_df_find_section_cands",
    "line_df_find_sections",
    "line_df_to_part_df",
    "lines_to_pages",
    "lines_to_plines",
    "load_phrases_def",
    "loc_sep_lines",
    "loc_to_df",
    "locate_all_as_df",
    "locate_col_refs_in_txt",
    "locate_sentences_in_txt",
    "locate_tab_fig_refs_in_txt",
    "make_phrases_def",
    "map_loc_to_parent_loc",
    "match_overlap",
    "mocr_copy_to_ejs",
    "mocr_html_extract_tables",
    "mocr_make_ocr",
    "mocr_md_to_html_by_page",
    "mocr_md_to_html_mono",
    "mocr_parse_html_parts",
    "most.common",
    "ms_parse_html",
    "ms_parse_html_table",
    "my_pandoc",
    "my_rank",
    "na.false",
    "na.remove",
    "na.val",
    "pdf_to_txt_pages",
    "plines_to_lines",
    "rdoc_document_url",
    "rdoc_find_in_text_fixed",
    "rdoc_form",
    "rdoc_guess_journ",
    "rdoc_has_art_mocr",
    "rdoc_has_html",
    "rdoc_has_pdf",
    "rdoc_has_two_col",
    "rdoc_html_file",
    "rdoc_html_process",
    "rdoc_html_tab_standardize",
    "rdoc_html_to_parts",
    "rdoc_is_processed",
    "rdoc_load_art_meta_data",
    "rdoc_load_page_df",
    "rdoc_load_part_df",
    "rdoc_load_ref_li",
    "rdoc_load_sent_df",
    "rdoc_load_tab_df",
    "rdoc_load_with_cache",
    "rdoc_mocr_process",
    "rdoc_options",
    "rdoc_opts",
    "rdoc_pdf_extract_raw_tabs",
    "rdoc_pdf_extract_tabs",
    "rdoc_pdf_file",
    "rdoc_pdf_pages_to_parts",
    "rdoc_pdf_process",
    "rdoc_pdf_to_txt_pages",
    "rdoc_phrase_analysis",
    "rdoc_process",
    "rdoc_refs_analysis",
    "rdoc_repair_two_col",
    "rdoc_repair_two_col_aer_pandp",
    "rdoc_sent_df",
    "rdoc_steps_from",
    "rdoc_tab_fig_refs",
    "rdoc_tab_phrase_analysis",
    "rdoc_tab_ref_text",
    "rdoc_tabs_file",
    "rdoc_text_parts_phrase_analysis",
    "rdoc_type",
    "rdoc_update_project",
    "readRDS.or.null",
    "refine_cell_df_and_add_panel_info",
    "remove_nested_html_elements",
    "remove.cols",
    "remove.overlapping.loc",
    "repair_ejd_files_art_mocr",
    "repbox_all_pdf_file",
    "repbox_doc_dirs",
    "repbox_doc_file_select",
    "repbox_doc_files_info",
    "repbox_doc_types",
    "repbox_journ_list",
    "repbox_pdf_file",
    "repbox_process_all_docs",
    "repbox_rdoc_opts",
    "restat_parse_html",
    "restud_parse_html",
    "restud_parse_html_table",
    "rle_block",
    "rle_cummax_block",
    "rle_table",
    "save_rds_create_dir",
    "sentences_merge_with_next",
    "seq_rows",
    "show_cell_df_html",
    "substitute_wrong_pdf_txt_chars",
    "text_df_add_section_cols",
    "text_parts_tab_fig_references",
    "text_parts_to_loc",
    "txt_locate_keywords",
    "txt_locate_rx_keywords",
    "txt_locate_typed_keywords",
    "txt_phrase_analysis"
  ],
  "_help": [],
  "_readme": "https://github.com/repboxr/repboxDoc/raw/main/README.md",
  "_rundeps": [
    "askpass",
    "base64enc",
    "brew",
    "brio",
    "bslib",
    "cachem",
    "callr",
    "cli",
    "clipr",
    "commonmark",
    "cpp11",
    "crayon",
    "credentials",
    "curl",
    "data.table",
    "desc",
    "devtools",
    "diffobj",
    "digest",
    "downlit",
    "dplyr",
    "ellipsis",
    "evaluate",
    "ExtractSciTab",
    "fansi",
    "fastmap",
    "fontawesome",
    "fs",
    "generics",
    "gert",
    "gitcreds",
    "glue",
    "highr",
    "htmltools",
    "htmlwidgets",
    "httpuv",
    "httr",
    "httr2",
    "ini",
    "jquerylib",
    "jsonlite",
    "knitr",
    "later",
    "lifecycle",
    "magrittr",
    "memoise",
    "mime",
    "miniUI",
    "openssl",
    "otel",
    "pak",
    "pillar",
    "pkgbuild",
    "pkgconfig",
    "pkgdown",
    "pkgload",
    "praise",
    "prettyunits",
    "processx",
    "profvis",
    "promises",
    "ps",
    "purrr",
    "R6",
    "ragg",
    "rappdirs",
    "rcmdcheck",
    "Rcpp",
    "repboxDB",
    "repboxTableTools",
    "repboxUtils",
    "restorepoint",
    "rlang",
    "rmarkdown",
    "roxygen2",
    "rprojroot",
    "rstudioapi",
    "rversions",
    "rvest",
    "sass",
    "selectr",
    "sessioninfo",
    "shiny",
    "sourcetools",
    "stringi",
    "stringr",
    "stringtools",
    "sys",
    "systemfonts",
    "testthat",
    "textshaping",
    "tibble",
    "tidyr",
    "tidyselect",
    "tinytex",
    "urlchecker",
    "usethis",
    "utf8",
    "vctrs",
    "waldo",
    "whisker",
    "withr",
    "xfun",
    "xml2",
    "xopen",
    "xtable",
    "yaml",
    "zip"
  ],
  "_score": 2.8750612633917,
  "_indexed": false,
  "_nocasepkg": "repboxdoc",
  "_universes": [
    "skranz"
  ],
  "_indexurl": "https://repboxr.r-universe.dev/repboxDoc",
  "_binaries": [
    {
      "r": "4.7.0",
      "os": "linux",
      "version": "0.1.0",
      "date": "2026-06-14T08:22:47.000Z",
      "distro": "noble",
      "commit": "e0f14b8502cc1b0d57d0ff83e33db74fe27b2bf5",
      "fileid": "b51a91eafdc4850c0ab2b2523c8cbe5b68cae99450075eeaae351feb28009b3d",
      "status": "success",
      "check": "WARNING",
      "buildurl": "https://github.com/r-universe/skranz/actions/runs/27492994348"
    },
    {
      "r": "4.6.0",
      "os": "linux",
      "version": "0.1.0",
      "date": "2026-06-14T08:22:42.000Z",
      "distro": "noble",
      "commit": "e0f14b8502cc1b0d57d0ff83e33db74fe27b2bf5",
      "fileid": "43c3a0a411d30d6675056f804fecee6deb4d3737e499f8574b384e7c95095db9",
      "status": "success",
      "check": "WARNING",
      "buildurl": "https://github.com/r-universe/skranz/actions/runs/27492994348"
    },
    {
      "r": "4.5.3",
      "os": "mac",
      "version": "0.1.0",
      "date": "2026-06-14T08:22:05.000Z",
      "commit": "e0f14b8502cc1b0d57d0ff83e33db74fe27b2bf5",
      "fileid": "4322bc6c260386ff4f80bd51b7145767d97fb7dc21e8ed49d0aabe9eb397ae6e",
      "status": "success",
      "check": "WARNING",
      "buildurl": "https://github.com/r-universe/skranz/actions/runs/27492994348"
    },
    {
      "r": "4.6.0",
      "os": "mac",
      "version": "0.1.0",
      "date": "2026-06-14T08:21:46.000Z",
      "commit": "e0f14b8502cc1b0d57d0ff83e33db74fe27b2bf5",
      "fileid": "5f99081976711751120ab2ee660c3787d67d1ee9a5dd188e7ac5fd031b49cd70",
      "status": "success",
      "check": "WARNING",
      "buildurl": "https://github.com/r-universe/skranz/actions/runs/27492994348"
    },
    {
      "r": "4.6.0",
      "os": "wasm",
      "version": "0.1.0",
      "date": "2026-06-14T08:22:51.000Z",
      "commit": "e0f14b8502cc1b0d57d0ff83e33db74fe27b2bf5",
      "fileid": "811cd28a32af25219622cdb7af2081ca4c26d4269e43696f7545847aea5c5314",
      "status": "success",
      "buildurl": "https://github.com/r-universe/skranz/actions/runs/27492994348"
    },
    {
      "r": "4.7.0",
      "os": "win",
      "version": "0.1.0",
      "date": "2026-06-14T08:21:34.000Z",
      "commit": "e0f14b8502cc1b0d57d0ff83e33db74fe27b2bf5",
      "fileid": "640cd479685a784bee40a36b4b9ea7049fe38074294f1045e4b872bbadbdd27b",
      "status": "success",
      "check": "WARNING",
      "buildurl": "https://github.com/r-universe/skranz/actions/runs/27492994348"
    },
    {
      "r": "4.5.3",
      "os": "win",
      "version": "0.1.0",
      "date": "2026-06-14T08:21:30.000Z",
      "commit": "e0f14b8502cc1b0d57d0ff83e33db74fe27b2bf5",
      "fileid": "0e899fdf860d38f4c30db7ea13a3df6a0a66b4946d04b63f87b4dd87375184e4",
      "status": "success",
      "check": "WARNING",
      "buildurl": "https://github.com/r-universe/skranz/actions/runs/27492994348"
    },
    {
      "r": "4.6.0",
      "os": "win",
      "version": "0.1.0",
      "date": "2026-06-14T08:21:37.000Z",
      "commit": "e0f14b8502cc1b0d57d0ff83e33db74fe27b2bf5",
      "fileid": "4b18ed96f3e362f154c70a8667d1fefce002e6154a32b9ccd200599fb1a16950",
      "status": "success",
      "check": "WARNING",
      "buildurl": "https://github.com/r-universe/skranz/actions/runs/27492994348"
    }
  ]
}