{ "_id": "6ab7cfd799f7aa8c6aa34340", "Package": "DCC", "Type": "Package", "Title": "Data Cleaning Center for Survey and Assessment Data", "Version": "1.2.1", "Authors@R": "c(\nperson(\"Kunxiang\", \"Ma\", role = c(\"aut\", \"cre\"),\nemail = \"makunxiang@weiandata.com\"),\nperson(\"WEIAN DATA TECH (Beijing) Co., Ltd.\",\nrole = c(\"cph\", \"fnd\"), email = \"contact@weiandata.com\"))", "Description": "Rule-driven, auditable cleaning of survey and assessment\nresponse data, implementing the WeianData Detect-Execute-Report\nworkflow. Provides a multi-format, multi-encoding input layer\n(CSV, 'Excel', 'SPSS', 'Stata', 'SAS', Parquet, JSON), the\ndcc_data container with a provenance chain, level-0 structural\ndiagnostics, five built-in response-quality detectors (missing\nitems, straight-lining, response time, trap items, score\nanomalies), a declarative YAML rule engine, an execution engine\nwith a cell-level audit log, answer-key scoring, multi-form to\nmaster item bank mapping, a normalized report model rendered as\nbilingual staff workbooks and HTML, complete statistical\nbundles, and versioned machine JSON/JSONL with\nfindings-to-changes reconciliation, cell-level lineage tracing,\nand manifest-based one-command reproduction. Includes a\nprotected bilingual strict project workbook and matching JSON\ncontract with cell-addressed validation, non-mutating\npreflight, preview-first execution, and localized staff\nguidance. All formally supported input backends install with\nthe package; PDF is optional rather than a fixed report output.", "License": "GPL (>= 2)", "Copyright": "See file inst/COPYRIGHTS.", "Encoding": "UTF-8", "Language": "en", "Config/testthat/edition": "3", "VignetteBuilder": "knitr", "URL": "https://github.com/weiandata/DCC", "BugReports": "https://github.com/weiandata/DCC/issues", "Roxygen": "list(markdown = TRUE)", "RoxygenNote": "7.3.2", "Config/DCC/Installation": "complete format backends in Imports; PDF\noptional", "Config/pak/sysreqs": "cmake make libicu-dev libssl-dev libx11-dev\nzlib1g-dev", "Repository": "https://weiandata.r-universe.dev", "Date/Publication": "2026-09-02 12:20:25 UTC", "RemoteUrl": "https://github.com/weiandata/dcc", "RemoteRef": "HEAD", "RemoteSha": "26c7b668670610cc4b95606cc015b0445c14993a", "NeedsCompilation": "no", "Packaged": { "Date": "2026-09-26 13:54:34 UTC", "User": "root" }, "Author": "Kunxiang Ma [aut, cre],\nWEIAN DATA TECH (Beijing) Co., Ltd. [cph, fnd]", "Maintainer": "Kunxiang Ma ", "_user": "weiandata", "_type": "src", "_file": "DCC_1.2.1.tar.gz", "_fileid": "https://r2.ropensci.org/b35dd57fd17b1d5fd30a78dacf4c70eae8d8dbee8bcd99a0555bab51ba3b7f76", "_filesize": 516032, "_sha256": "b35dd57fd17b1d5fd30a78dacf4c70eae8d8dbee8bcd99a0555bab51ba3b7f76", "_expires": "2027-01-04T13:59:50.000Z", "_created": "2026-09-26T13:54:34.000Z", "_published": "2026-09-26T13:59:51.935Z", "_jobs": [ { "job": 108417204687, "time": 263, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "10907732550" }, { "job": 108417204629, "time": 273, "config": "linux-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "10907538461" }, { "job": 108417204689, "time": 161, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "10907786401" }, { "job": 108417204622, "time": 143, "config": "macos-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "10907946106" }, { "job": 108416594061, "time": 252, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "10907228945" }, { "job": 108417204630, "time": 145, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "10907358990" }, { "job": 108417204651, "time": 195, "config": "windows-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "10908185434" }, { "job": 108417204671, "time": 184, "config": "windows-oldrel-x86_64", "r": "4.5.3", "check": "OK", "artifact": "10907632934" }, { "job": 108417204645, "time": 185, "config": "windows-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "10907652871" } ], "_host": "GitHub-Actions", "_buildurl": "https://github.com/r-universe/weiandata/actions/runs/36246492383", "_status": "success", "_upstream": "https://github.com/weiandata/dcc", "_commit": { "id": "26c7b668670610cc4b95606cc015b0445c14993a", "author": "makunxiang-weiandata ", "committer": "GitHub ", "message": "Merge pull request #26 from weiandata/fix/renv-lock-drift\n\nfix: re-freeze renv.lock after CRAN drift breaks macOS CI", "time": 1788351625 }, "_maintainer": { "name": "Kunxiang Ma", "email": "makunxiang@weiandata.com", "login": "makunxiang-weiandata", "description": "", "uuid": 301971568 }, "_distro": "resolute", "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 4.1", "role": "Depends" }, { "package": "arrow", "role": "Imports" }, { "package": "data.table", "version": ">= 1.14.0", "role": "Imports" }, { "package": "haven", "version": ">= 2.5.5", "role": "Imports" }, { "package": "jsonlite", "role": "Imports" }, { "package": "openxlsx2", "version": ">= 1.28", "role": "Imports" }, { "package": "readODS", "version": ">= 2.3.5", "role": "Imports" }, { "package": "readxl", "version": ">= 1.5.0", "role": "Imports" }, { "package": "stringi", "version": ">= 1.7.0", "role": "Imports" }, { "package": "methods", "role": "Imports" }, { "package": "stats", "role": "Imports" }, { "package": "tools", "role": "Imports" }, { "package": "utils", "role": "Imports" }, { "package": "writexl", "role": "Imports" }, { "package": "yaml", "role": "Imports" }, { "package": "knitr", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" }, { "package": "testthat", "version": ">= 3.0.0", "role": "Suggests" }, { "package": "withr", "role": "Suggests" } ], "_owner": "weiandata", "_selfowned": true, "_usedby": 0, "_updates": [ { "week": "2026-28", "n": 13 }, { "week": "2026-29", "n": 69 }, { "week": "2026-30", "n": 1 }, { "week": "2026-31", "n": 1 }, { "week": "2026-36", "n": 2 } ], "_tags": [], "_stars": 0, "_contributors": [ { "user": "makunxiang-weiandata", "count": 114, "uuid": 301971568 } ], "_userbio": { "uuid": 301974597, "type": "organization", "name": "WeianData", "followers": 0, "description": "Trustworthy measurement, statistical software, and AI-assisted research delivery." }, "_downloads": { "count": 0, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/DCC" }, "_devurl": "https://github.com/weiandata/dcc", "_rbuild": "4.6.1", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/DCC.html", "extra/manual.pdf", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md" ], "_homeurl": "https://github.com/weiandata/dcc", "_realowner": "weiandata", "_cranurl": true, "_releases": [ { "version": "1.2.1", "date": "2026-09-26" } ], "_exports": [ "dcc_apply_codebook", "dcc_audit_log", "dcc_capabilities", "dcc_check", "dcc_cleaned", "dcc_codebook_changes", "dcc_config", "dcc_data", "dcc_detect", "dcc_detect_chunked", "dcc_detect_encoding", "dcc_dictionary", "dcc_dispositions", "dcc_doctor", "dcc_execute", "dcc_export_log", "dcc_findings", "dcc_help", "dcc_import", "dcc_item_map", "dcc_l0_diagnose", "dcc_manifest", "dcc_map_forms", "dcc_mapping_findings", "dcc_missing_states", "dcc_provenance", "dcc_read", "dcc_read_config", "dcc_read_plan", "dcc_read_report", "dcc_reconcile", "dcc_report", "dcc_report_machine", "dcc_report_model", "dcc_report_staff", "dcc_report_statistical", "dcc_rerun", "dcc_result_summary", "dcc_rules", "dcc_run", "dcc_run_files", "dcc_schema", "dcc_score", "dcc_template", "dcc_trace", "dcc_unhandled", "dcc_validate_config", "dcc_validate_data", "dcc_validate_json", "dcc_validate_jsonl", "dcc_validate_plan", "dcc_validate_report_model", "dcc_validate_rules", "dcc_validation_errors", "dcc_write_config_template", "detect_missing_items", "detect_response_time", "detect_score_anomaly", "detect_straightlining", "detect_trap_items" ], "_help": [ { "page": "dcc_apply_codebook", "title": "Apply a declarative codebook to a dataset", "topics": [ "dcc_apply_codebook" ] }, { "page": "dcc_audit_log", "title": "Accessors for dcc_result objects", "topics": [ "dcc_audit_log", "dcc_cleaned" ] }, { "page": "dcc_capabilities", "title": "Machine-readable DCC capability document", "topics": [ "dcc_capabilities" ] }, { "page": "dcc_check", "title": "Check a strict DCC project without changing data", "topics": [ "dcc_check" ] }, { "page": "dcc_codebook_changes", "title": "The planned changes of a codebook preview", "topics": [ "dcc_codebook_changes" ] }, { "page": "dcc_config", "title": "A cleaning configuration", "topics": [ "dcc_config" ] }, { "page": "dcc_data", "title": "The dcc_data container", "topics": [ "dcc_data" ] }, { "page": "dcc_detect", "title": "Run a rule set against data (Detect stage)", "topics": [ "dcc_detect" ] }, { "page": "dcc_detect_chunked", "title": "Run record-local checks over a file in chunks", "topics": [ "dcc_detect_chunked" ] }, { "page": "dcc_detect_encoding", "title": "Detect the character encoding of a text file", "topics": [ "dcc_detect_encoding" ] }, { "page": "dcc_dictionary", "title": "Canonical variable dictionary", "topics": [ "dcc_dictionary" ] }, { "page": "dcc_dispositions", "title": "Terminal dispositions of a cleaning result", "topics": [ "dcc_dispositions" ] }, { "page": "dcc_doctor", "title": "Run every validator over a dataset and rule set", "topics": [ "dcc_doctor" ] }, { "page": "dcc_execute", "title": "Execute actions on detected findings (Execute stage)", "topics": [ "dcc_execute" ] }, { "page": "dcc_export_log", "title": "Export an audit log for external auditors", "topics": [ "dcc_export_log" ] }, { "page": "dcc_findings", "title": "The dcc_findings table", "topics": [ "dcc_findings" ] }, { "page": "dcc_help", "title": "Explain a DCC workflow code in Chinese or English", "topics": [ "dcc_help" ] }, { "page": "dcc_import", "title": "Strict canonical import", "topics": [ "dcc_import" ] }, { "page": "dcc_item_map", "title": "Master item map of a form-mapped dataset", "topics": [ "dcc_item_map" ] }, { "page": "dcc_l0_diagnose", "title": "Level-0 structural diagnostics", "topics": [ "dcc_l0_diagnose" ] }, { "page": "dcc_manifest", "title": "Build a reproducibility manifest for a cleaning run", "topics": [ "dcc_manifest" ] }, { "page": "dcc_map_forms", "title": "Map multi-form responses onto the master item bank", "topics": [ "dcc_map_forms" ] }, { "page": "dcc_mapping_findings", "title": "Mapping problems found while aligning forms", "topics": [ "dcc_mapping_findings" ] }, { "page": "dcc_missing_states", "title": "Canonical cell-level missing states", "topics": [ "dcc_missing_states" ] }, { "page": "dcc_provenance", "title": "Provenance chain of a dcc_data object", "topics": [ "dcc_provenance" ] }, { "page": "dcc_read", "title": "Read a data file into a dcc_data object", "topics": [ "dcc_read" ] }, { "page": "dcc_read_config", "title": "Read an Excel cleaning-plan configuration", "topics": [ "dcc_read_config" ] }, { "page": "dcc_read_plan", "title": "Read a strict DCC Excel or JSON plan", "topics": [ "dcc_read_plan" ] }, { "page": "dcc_read_report", "title": "Read report of a dcc_data object", "topics": [ "dcc_read_report" ] }, { "page": "dcc_reconcile", "title": "Reconcile findings against logged changes (closed loop)", "topics": [ "dcc_reconcile" ] }, { "page": "dcc_report", "title": "Generate a cleaning report (Report stage)", "topics": [ "dcc_report" ] }, { "page": "dcc_report_machine", "title": "Render the machine report bundle", "topics": [ "dcc_report_machine" ] }, { "page": "dcc_report_model", "title": "Build and validate the normalized report model", "topics": [ "dcc_report_model", "dcc_validate_report_model" ] }, { "page": "dcc_report_staff", "title": "Render the bilingual staff report", "topics": [ "dcc_report_staff" ] }, { "page": "dcc_report_statistical", "title": "Render the statistical report bundle", "topics": [ "dcc_report_statistical" ] }, { "page": "dcc_rerun", "title": "Re-run a cleaning pipeline from its manifest and verify the output", "topics": [ "dcc_rerun" ] }, { "page": "dcc_result_summary", "title": "Create a structured AI summary of a DCC result", "topics": [ "dcc_result_summary" ] }, { "page": "dcc_rules", "title": "Load a declarative rule set from a YAML file", "topics": [ "dcc_rules" ] }, { "page": "dcc_run", "title": "Run a cleaning workflow with one command", "topics": [ "dcc_run" ] }, { "page": "dcc_run_files", "title": "Output files written by a run", "topics": [ "dcc_run_files" ] }, { "page": "dcc_schema", "title": "Published JSON Schema for a DCC object", "topics": [ "dcc_schema" ] }, { "page": "dcc_score", "title": "Score responses against an answer key", "topics": [ "dcc_score" ] }, { "page": "dcc_template", "title": "Create the strict bilingual DCC Excel template", "topics": [ "dcc_template" ] }, { "page": "dcc_trace", "title": "Trace the cleaning history of a record or cell", "topics": [ "dcc_trace" ] }, { "page": "dcc_unhandled", "title": "Findings left unhandled by execution", "topics": [ "dcc_unhandled" ] }, { "page": "dcc_validate_config", "title": "Validate a cleaning configuration", "topics": [ "dcc_validate_config" ] }, { "page": "dcc_validate_data", "title": "Validate data against a rule set before detection", "topics": [ "dcc_validate_data" ] }, { "page": "dcc_validate_json", "title": "Validate DCC JSON and JSON Lines artifacts", "topics": [ "dcc_validate_json", "dcc_validate_jsonl" ] }, { "page": "dcc_validate_plan", "title": "Validate a strict DCC project plan", "topics": [ "dcc_validate_plan" ] }, { "page": "dcc_validate_rules", "title": "Validate a rule set before it is used", "topics": [ "dcc_validate_rules" ] }, { "page": "dcc_validation_errors", "title": "The failing issues of a validation report", "topics": [ "dcc_validation_errors" ] }, { "page": "dcc_write_config_template", "title": "Write a starter Excel cleaning-plan template", "topics": [ "dcc_write_config_template" ] }, { "page": "detect_missing_items", "title": "Detect excessive item nonresponse per respondent", "topics": [ "detect_missing_items" ] }, { "page": "detect_response_time", "title": "Detect implausibly fast or anomalous response times", "topics": [ "detect_response_time" ] }, { "page": "detect_score_anomaly", "title": "Detect group-wise score anomalies", "topics": [ "detect_score_anomaly" ] }, { "page": "detect_straightlining", "title": "Detect straight-lining (longstring)", "topics": [ "detect_straightlining" ] }, { "page": "detect_trap_items", "title": "Detect failed trap (attention-check) items", "topics": [ "detect_trap_items" ] } ], "_readme": "https://github.com/weiandata/dcc/raw/HEAD/README.md", "_rundeps": [ "arrow", "assertthat", "bit", "bit64", "cellranger", "cli", "clipr", "cpp11", "crayon", "data.table", "forcats", "glue", "haven", "hms", "jsonlite", "lifecycle", "magrittr", "minty", "openxlsx2", "pillar", "pkgconfig", "prettyunits", "progress", "purrr", "R6", "Rcpp", "readODS", "readr", "readxl", "rematch", "rlang", "stringi", "tibble", "tidyselect", "tzdb", "utf8", "vctrs", "vroom", "withr", "writexl", "yaml", "zip" ], "_vignettes": [ { "source": "statistical-report.Rmd", "filename": "statistical-report.html", "title": "Reproducible statistical reports with DCC", "engine": "knitr::rmarkdown", "headings": [], "created": "2026-07-15 15:33:35", "modified": "2026-07-29 00:16:51", "commits": 2 }, { "source": "dcc-pipeline.Rmd", "filename": "dcc-pipeline.html", "title": "The DCC cleaning pipeline: Detect, Execute, Report", "engine": "knitr::rmarkdown", "headings": [ "A small dataset and a rule set", "Detect", "Execute", "Report", "Trace and reproduce", "Larger-than-memory input" ], "created": "2026-07-12 07:15:29", "modified": "2026-07-12 14:56:19", "commits": 2 } ], "_score": 4.698970004336019, "_indexed": true, "_nocasepkg": "dcc", "_universes": [ "weiandata", "makunxiang-weiandata" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "1.2.1", "date": "2026-09-26T13:57:38.000Z", "distro": "resolute", "commit": "26c7b668670610cc4b95606cc015b0445c14993a", "fileid": "https://r2.ropensci.org/9c4756822173e013f22f03f21f04f28a76c30d6ae128bba51ba8699f29472b32", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/weiandata/actions/runs/36246492383" }, { "r": "4.6.1", "os": "linux", "version": "1.2.1", "date": "2026-09-26T13:57:49.000Z", "distro": "resolute", "commit": "26c7b668670610cc4b95606cc015b0445c14993a", "fileid": "https://r2.ropensci.org/c96fd3cbd957b180cc65ab519a639de2ebfbbf640b7bab4d93f8c832946175e8", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/weiandata/actions/runs/36246492383" }, { "r": "4.5.3", "os": "mac", "version": "1.2.1", "date": "2026-09-26T13:56:21.000Z", "commit": "26c7b668670610cc4b95606cc015b0445c14993a", "fileid": "https://r2.ropensci.org/29736a7ddd8b1b15d068c65ec0d6d7715c28893fea0128aa23cc5307a036c4b9", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/weiandata/actions/runs/36246492383" }, { "r": "4.6.1", "os": "mac", "version": "1.2.1", "date": "2026-09-26T13:56:07.000Z", "commit": "26c7b668670610cc4b95606cc015b0445c14993a", "fileid": "https://r2.ropensci.org/55901aaf61d78c16ac699d83e32ecca445f1de2f0af9c09123e96929a0b884af", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/weiandata/actions/runs/36246492383" }, { "r": "4.6.0", "os": "wasm", "version": "1.2.1", "date": "2026-09-26T13:57:18.000Z", "commit": "26c7b668670610cc4b95606cc015b0445c14993a", "fileid": "https://r2.ropensci.org/d2c017650cfbfe1b3e610c6e49d04714630582641e52539bfef351959a9a3773", "status": "success", "buildurl": "https://github.com/r-universe/weiandata/actions/runs/36246492383" }, { "r": "4.7.0", "os": "win", "version": "1.2.1", "date": "2026-09-26T13:55:48.000Z", "commit": "26c7b668670610cc4b95606cc015b0445c14993a", "fileid": "https://r2.ropensci.org/2a55394b0a97ba32a8931419c0f9864bc189acb3b0978f21cd35b8434d1e4344", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/weiandata/actions/runs/36246492383" }, { "r": "4.5.3", "os": "win", "version": "1.2.1", "date": "2026-09-26T13:55:41.000Z", "commit": "26c7b668670610cc4b95606cc015b0445c14993a", "fileid": "https://r2.ropensci.org/46c40dfc68bb58ee5615f33842c61ccfc94dcc8af217021cd4de8884346569e7", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/weiandata/actions/runs/36246492383" }, { "r": "4.6.1", "os": "win", "version": "1.2.1", "date": "2026-09-26T13:55:55.000Z", "commit": "26c7b668670610cc4b95606cc015b0445c14993a", "fileid": "https://r2.ropensci.org/a79c91c1c9ca9f6580fb5eb064699e6765443777367e04a75f5056f2a9a7624e", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/weiandata/actions/runs/36246492383" } ] }