{ "_id": "6ad205291200a49930211f06", "Package": "daiR", "Title": "Interface with Google Cloud Document AI API", "Version": "1.2.1", "Authors@R": "person(\"Thomas\", \"Hegghammer\", , \"hegghammer@gmail.com\", role = c(\"aut\", \"cre\"),\ncomment = c(ORCID = \"0000-0001-6253-1518\"))", "Description": "R interface for the Google Cloud Services 'Document AI\nAPI' with additional\ntools for output file parsing and text reconstruction.\n'Document AI' is a powerful server-based OCR service that\nextracts text and tables from images and PDF files with high\naccuracy. 'daiR' gives R users programmatic access to this\nservice and additional tools to handle and visualize the\noutput. See the package website for more\ninformation and examples.", "License": "MIT + file LICENSE", "URL": "https://github.com/Hegghammer/daiR, https://dair.info", "BugReports": "https://github.com/Hegghammer/daiR/issues", "VignetteBuilder": "knitr", "Config/testthat/edition": "3", "Encoding": "UTF-8", "Roxygen": "list(markdown = TRUE)", "RoxygenNote": "7.3.2", "Config/pak/sysreqs": "cmake make libmagick++-dev gsfonts libicu-dev\nlibjpeg-dev libuv1-dev libxml2-dev libssl-dev\nlibpoppler-cpp-dev poppler-data zlib1g-dev", "Repository": "https://hegghammer.r-universe.dev", "Date/Publication": "2026-09-16 14:28:40 UTC", "RemoteUrl": "https://github.com/hegghammer/dair", "RemoteRef": "HEAD", "RemoteSha": "845385a3bb135c4f5908dd59a0ddbfe110925084", "NeedsCompilation": "no", "Packaged": { "Date": "2026-10-16 11:01:41 UTC", "User": "root" }, "Author": "Thomas Hegghammer [aut, cre] (ORCID:\n)", "Maintainer": "Thomas Hegghammer ", "_user": "hegghammer", "_type": "src", "_file": "daiR_1.2.1.tar.gz", "_fileid": "https://r2.ropensci.org/349ac5d848787f32dd35679bc1b9411b36ac5c48936dd4495d6174a05ea2d940", "_filesize": 4875344, "_sha256": "349ac5d848787f32dd35679bc1b9411b36ac5c48936dd4495d6174a05ea2d940", "_expires": "2027-01-24T11:06:14.000Z", "_created": "2026-10-16T11:01:41.000Z", "_published": "2026-10-16T11:06:17.061Z", "_buildurl": "https://github.com/r-universe/hegghammer/actions/runs/38890764268", "_status": "success", "_host": "GitHub-Actions", "_jobs": [ { "job": 116940534389, "time": 177, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "12042470844" }, { "job": 116940534342, "time": 191, "config": "linux-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "12041448649" }, { "job": 116940534319, "time": 198, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "12041209605" }, { "job": 116940534254, "time": 215, "config": "macos-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "12042266298" }, { "job": 116939548501, "time": 164, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "12041706590" }, { "job": 116940534264, "time": 115, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "12041368726" }, { "job": 116940534445, "time": 150, "config": "windows-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "12042176292" }, { "job": 116940534379, "time": 142, "config": "windows-oldrel-x86_64", "r": "4.5.3", "check": "OK", "artifact": "12041842461" }, { "job": 116940534406, "time": 147, "config": "windows-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "12041418621" } ], "_upstream": "https://github.com/hegghammer/dair", "_commit": { "id": "845385a3bb135c4f5908dd59a0ddbfe110925084", "author": "Hegghammer ", "committer": "Hegghammer ", "message": "add field_mask param to dai_async\n", "time": 1789568920 }, "_maintainer": { "name": "Thomas Hegghammer", "email": "hegghammer@gmail.com", "login": "hegghammer", "bluesky": "@hegghammer.net", "description": "Historian and political scientist studying militant Islamism. Senior Research Fellow at All Souls College, Oxford University. ", "uuid": 64712218, "orcid": "0000-0001-6253-1518" }, "_distro": "resolute", "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 4.2.0", "role": "Depends" }, { "package": "base64enc", "role": "Imports" }, { "package": "beepr", "role": "Imports" }, { "package": "cli", "role": "Imports" }, { "package": "data.table", "role": "Imports" }, { "package": "fs", "role": "Imports" }, { "package": "gargle", "role": "Imports" }, { "package": "glue", "role": "Imports" }, { "package": "googleCloudStorageR", "role": "Imports" }, { "package": "graphics", "role": "Imports" }, { "package": "grDevices", "role": "Imports" }, { "package": "httr", "role": "Imports" }, { "package": "jsonlite", "role": "Imports" }, { "package": "lifecycle", "role": "Imports" }, { "package": "magick", "role": "Imports" }, { "package": "pdftools", "role": "Imports" }, { "package": "purrr", "role": "Imports" }, { "package": "readtext", "role": "Imports" }, { "package": "stats", "role": "Imports" }, { "package": "stringr", "role": "Imports" }, { "package": "utils", "role": "Imports" }, { "package": "xml2", "role": "Imports" }, { "package": "knitr", "role": "Suggests" }, { "package": "ngram", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" }, { "package": "testthat", "version": ">= 3.1.10", "role": "Suggests" } ], "_owner": "hegghammer", "_selfowned": true, "_usedby": 0, "_updates": [ { "week": "2025-47", "n": 5 }, { "week": "2026-04", "n": 1 }, { "week": "2026-27", "n": 1 }, { "week": "2026-38", "n": 1 } ], "_tags": [], "_topics": [ "google-cloud", "ocr" ], "_stars": 44, "_contributors": [ { "user": "hegghammer", "count": 216, "uuid": 64712218 } ], "_userbio": { "uuid": 64712218, "type": "user", "name": "Thomas Hegghammer", "followers": 47, "description": "Historian and political scientist studying militant Islamism. Senior Research Fellow at All Souls College, Oxford University. " }, "_downloads": { "count": 358, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/daiR" }, "_devurl": "https://github.com/hegghammer/dair", "_pkgdown": "https://dair.info", "_searchresults": 52, "_rbuild": "4.6.1", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/daiR.html", "extra/manual.pdf", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "LICENSE" ], "_homeurl": "https://github.com/hegghammer/dair", "_realowner": "hegghammer", "_cranurl": true, "_releases": [ { "version": "0.9.0", "date": "2021-06-11" }, { "version": "0.9.9", "date": "2023-09-07" }, { "version": "1.0.0", "date": "2024-02-12" }, { "version": "1.0.1", "date": "2024-11-14" }, { "version": "1.2.0", "date": "2025-11-18" } ], "_exports": [ "build_block_df", "build_token_df", "create_processor", "dai_async", "dai_async_tab", "dai_auth", "dai_notify", "dai_status", "dai_sync", "dai_sync_tab", "dai_token", "dai_user", "delete_processor", "disable_processor", "draw_blocks", "draw_entities", "draw_lines", "draw_paragraphs", "draw_tokens", "enable_processor", "from_labelme", "get_entities", "get_ids_by_type", "get_processor_info", "get_processor_versions", "get_processors", "get_project_id", "get_tables", "get_text", "get_versions_by_type", "image_to_pdf", "img_to_binbase", "is_colour", "is_json", "is_pdf", "list_processor_types", "make_hocr", "merge_shards", "pdf_to_binbase", "reassign_tokens", "reassign_tokens2", "redraw_blocks", "split_block", "tables_from_dai_file", "tables_from_dai_response", "text_from_dai_file", "text_from_dai_response" ], "_help": [ { "page": "dot-onAttach", "title": "Run when daiR is attached", "topics": [ ".onAttach" ] }, { "page": "build_block_df", "title": "Build block dataframe", "topics": [ "build_block_df" ] }, { "page": "build_token_df", "title": "Build token dataframe", "topics": [ "build_token_df" ] }, { "page": "create_processor", "title": "Create processor", "topics": [ "create_processor" ] }, { "page": "dai_async", "title": "OCR documents asynchronously", "topics": [ "dai_async" ] }, { "page": "dai_auth", "title": "Check authentication", "topics": [ "dai_auth" ] }, { "page": "dai_notify", "title": "Notify on job completion", "topics": [ "dai_notify" ] }, { "page": "dai_status", "title": "Check job status", "topics": [ "dai_status" ] }, { "page": "dai_sync", "title": "OCR document synchronously", "topics": [ "dai_sync" ] }, { "page": "dai_token", "title": "Produce access token", "topics": [ "dai_token" ] }, { "page": "dai_user", "title": "Get user information", "topics": [ "dai_user" ] }, { "page": "delete_processor", "title": "Delete processor", "topics": [ "delete_processor" ] }, { "page": "disable_processor", "title": "Disable processor", "topics": [ "disable_processor" ] }, { "page": "draw_blocks", "title": "Draw block bounding boxes", "topics": [ "draw_blocks" ] }, { "page": "draw_entities", "title": "Draw entity bounding boxes", "topics": [ "draw_entities" ] }, { "page": "draw_lines", "title": "Draw line bounding boxes", "topics": [ "draw_lines" ] }, { "page": "draw_paragraphs", "title": "Draw paragraph bounding boxes", "topics": [ "draw_paragraphs" ] }, { "page": "draw_tokens", "title": "Draw token bounding boxes", "topics": [ "draw_tokens" ] }, { "page": "enable_processor", "title": "Enable processor", "topics": [ "enable_processor" ] }, { "page": "from_labelme", "title": "Extract block coordinates from labelme files", "topics": [ "from_labelme" ] }, { "page": "get_entities", "title": "Get entities", "topics": [ "get_entities" ] }, { "page": "get_ids_by_type", "title": "List ids of available processors of a given type", "topics": [ "get_ids_by_type" ] }, { "page": "get_processor_info", "title": "Get information about processor", "topics": [ "get_processor_info" ] }, { "page": "get_processor_versions", "title": "List available versions of processor", "topics": [ "get_processor_versions" ] }, { "page": "get_processors", "title": "List created processors", "topics": [ "get_processors" ] }, { "page": "get_project_id", "title": "Get project id", "topics": [ "get_project_id" ] }, { "page": "get_tables", "title": "Get tables", "topics": [ "get_tables" ] }, { "page": "get_text", "title": "Get text", "topics": [ "get_text" ] }, { "page": "get_versions_by_type", "title": "List versions of available processors of a given type", "topics": [ "get_versions_by_type" ] }, { "page": "image_to_pdf", "title": "Convert images to PDF", "topics": [ "image_to_pdf" ] }, { "page": "img_to_binbase", "title": "Image to base64 tiff", "topics": [ "img_to_binbase" ] }, { "page": "is_colour", "title": "Check that a string is a valid colour representation", "topics": [ "is_colour" ] }, { "page": "is_json", "title": "Check that a file is JSON", "topics": [ "is_json" ] }, { "page": "is_pdf", "title": "Check that a file is PDF", "topics": [ "is_pdf" ] }, { "page": "list_processor_types", "title": "List available processor types", "topics": [ "list_processor_types" ] }, { "page": "make_hocr", "title": "Make hOCR file", "topics": [ "make_hocr" ] }, { "page": "merge_shards", "title": "Merge shards", "topics": [ "merge_shards" ] }, { "page": "pdf_to_binbase", "title": "PDF to base64 tiff", "topics": [ "pdf_to_binbase" ] }, { "page": "reassign_tokens", "title": "Assign tokens to new blocks", "topics": [ "reassign_tokens" ] }, { "page": "reassign_tokens2", "title": "Assign tokens to a single new block", "topics": [ "reassign_tokens2" ] }, { "page": "redraw_blocks", "title": "Inspect revised block bounding boxes", "topics": [ "redraw_blocks" ] }, { "page": "split_block", "title": "Split a block bounding box", "topics": [ "split_block" ] }, { "page": "tables_from_dai_file", "title": "Get tables from output file", "topics": [ "tables_from_dai_file" ] }, { "page": "tables_from_dai_response", "title": "Get tables from response object", "topics": [ "tables_from_dai_response" ] } ], "_pkglogo": "https://github.com/hegghammer/dair/raw/HEAD/man/figures/logo.png", "_readme": "https://github.com/hegghammer/dair/raw/HEAD/README.md", "_rundeps": [ "antiword", "askpass", "assertthat", "audio", "base64enc", "beepr", "bitops", "cachem", "cellranger", "cli", "cpp11", "crayon", "curl", "data.table", "digest", "fastmap", "fs", "gargle", "glue", "googleAuthR", "googleCloudStorageR", "hms", "httr", "jsonlite", "lifecycle", "magick", "magrittr", "memoise", "mime", "minty", "ndjson", "openssl", "pdftools", "pillar", "pkgconfig", "prettyunits", "progress", "purrr", "qpdf", "R6", "rappdirs", "Rcpp", "RCurl", "readODS", "readtext", "readxl", "rematch", "rjson", "rlang", "streamR", "stringi", "stringr", "striprtf", "sys", "tibble", "tzdb", "utf8", "vctrs", "withr", "xml2", "yaml", "zip" ], "_vignettes": [ { "source": "usage.Rmd", "filename": "usage.html", "title": "Basic usage", "author": "Thomas Hegghammer", "engine": "knitr::rmarkdown", "headings": [ "Synchronous processing", "Asynchronous processing", "Large batches", "Merging shards" ], "created": "2024-02-11 23:36:04", "modified": "2025-11-17 19:30:12", "commits": 2 }, { "source": "complex_file_and_folder_management.Rmd", "filename": "complex_file_and_folder_management.html", "title": "Complex file and folder management", "engine": "knitr::rmarkdown", "headings": [ "Image files", "Processing a folder tree" ], "created": "2023-08-28 20:58:42", "modified": "2023-08-28 20:58:42", "commits": 1 }, { "source": "configuration.Rmd", "filename": "configuration.html", "title": "Configuration", "author": "Thomas Hegghammer", "engine": "knitr::rmarkdown", "headings": [ "Authentication", "Step 1: Get a Gmail account", "Step 2: Activate the Google Cloud Console", "Step 3: Link your project to your billing account", "Step 4: Set up a service account", "Step 5: Download a json file with the service account key", "Step 6: Store the path to the credentials file as an environment variable", "Step 7: Activate Document AI", "Step 8: Create a processor", "Step 9: Store the processor id as an environment variable", "Cheatsheet" ], "created": "2024-02-11 23:36:04", "modified": "2024-02-28 21:18:31", "commits": 2 }, { "source": "reconstructing_text.Rmd", "filename": "reconstructing_text.html", "title": "Correcting text output", "author": "Thomas Hegghammer", "engine": "knitr::rmarkdown", "headings": [ "The problem", "Reordering blocks", "Splitting blocks", "Mathematical splitting", "Manual splitting" ], "created": "2021-03-04 16:25:24", "modified": "2024-11-12 20:40:55", "commits": 12 }, { "source": "tables.Rmd", "filename": "tables.html", "title": "Extracting tables", "author": "Thomas Hegghammer", "engine": "knitr::rmarkdown", "headings": [ "Activating a form parser processor", "Synchronous processing with form parsers", "Asynchronous processing with form parsers", "How good is it?" ], "created": "2024-02-11 23:36:04", "modified": "2024-11-13 21:18:22", "commits": 3 }, { "source": "quickstart.Rmd", "filename": "quickstart.html", "title": "Quickstart", "engine": "knitr::rmarkdown", "headings": [ "Set up a Google Cloud Services account", "Process synchronously", "Process asynchronously", "1. Upload files to your Google Cloud Storage bucket", "2. Tell Document AI to process them:", "3. Download the JSON output and extract the text:" ], "created": "2024-02-11 23:36:04", "modified": "2024-02-28 21:18:31", "commits": 2 }, { "source": "gcs_storage.Rmd", "filename": "gcs_storage.html", "title": "Working with Google Cloud Storage", "author": "Thomas Hegghammer", "engine": "knitr::rmarkdown", "headings": [ "Setup", "Creating and inspecting buckets", "Uploading files", "Downloading files", "Deleting", "Convenience functions", "Cheatsheet" ], "created": "2024-02-11 23:36:04", "modified": "2024-02-28 21:18:31", "commits": 2 } ], "_score": 7.505584055799225, "_indexed": true, "_nocasepkg": "dair", "_universes": [ "hegghammer" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "1.2.1", "date": "2026-10-16T11:04:00.000Z", "distro": "resolute", "commit": "845385a3bb135c4f5908dd59a0ddbfe110925084", "fileid": "https://r2.ropensci.org/c674c311f952575d73f05aacd5e82699eab529399a1aa8c8c578834be3b29312", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/hegghammer/actions/runs/38890764268" }, { "r": "4.6.1", "os": "linux", "version": "1.2.1", "date": "2026-10-16T11:04:00.000Z", "distro": "resolute", "commit": "845385a3bb135c4f5908dd59a0ddbfe110925084", "fileid": "https://r2.ropensci.org/73a866260c78fbd93b28f108ff31505dacc032de4a05cdb452094bca96833080", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/hegghammer/actions/runs/38890764268" }, { "r": "4.5.3", "os": "mac", "version": "1.2.1", "date": "2026-10-16T11:04:11.000Z", "commit": "845385a3bb135c4f5908dd59a0ddbfe110925084", "fileid": "https://r2.ropensci.org/e8d79ef76ec50a1bade8e6ceb330a0594dc77569a977f6059709debfbe0e1526", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/hegghammer/actions/runs/38890764268" }, { "r": "4.6.1", "os": "mac", "version": "1.2.1", "date": "2026-10-16T11:04:02.000Z", "commit": "845385a3bb135c4f5908dd59a0ddbfe110925084", "fileid": "https://r2.ropensci.org/5ec17a18a743a9e083eb8f1a15dce9c0416c63a31667802b35beb3e610c6d8f7", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/hegghammer/actions/runs/38890764268" }, { "r": "4.6.0", "os": "wasm", "version": "1.2.1", "date": "2026-10-16T11:03:53.000Z", "commit": "845385a3bb135c4f5908dd59a0ddbfe110925084", "fileid": "https://r2.ropensci.org/7e5f1dca839ba85affaaa222a214ae5ed6d43011ca67a1449e9044249246e784", "status": "success", "buildurl": "https://github.com/r-universe/hegghammer/actions/runs/38890764268" }, { "r": "4.7.0", "os": "win", "version": "1.2.1", "date": "2026-10-16T11:02:58.000Z", "commit": "845385a3bb135c4f5908dd59a0ddbfe110925084", "fileid": "https://r2.ropensci.org/9d9d06632299a1627fae43b673c3e108e0f36259f7c7b27cc851bec96236839d", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/hegghammer/actions/runs/38890764268" }, { "r": "4.5.3", "os": "win", "version": "1.2.1", "date": "2026-10-16T11:03:03.000Z", "commit": "845385a3bb135c4f5908dd59a0ddbfe110925084", "fileid": "https://r2.ropensci.org/aa8d14418d519f0eb5da8cb99f146bcf7a68e2233d3206f1f09c39808c7bd8a3", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/hegghammer/actions/runs/38890764268" }, { "r": "4.6.1", "os": "win", "version": "1.2.1", "date": "2026-10-16T11:03:01.000Z", "commit": "845385a3bb135c4f5908dd59a0ddbfe110925084", "fileid": "https://r2.ropensci.org/a505b059e59a3010c8a328cde59e62a1043f620f02b929d282bf146f7cd22734", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/hegghammer/actions/runs/38890764268" } ] }