{ "_id": "6a226af1cd65a98ecbd46691", "Package": "textreuse", "Type": "Package", "Title": "Detect Text Reuse and Document Similarity", "Version": "1.0.1", "Date": "2026-05-06", "Authors@R": "c(\nperson(\"Lincoln\", \"Mullen\", role = \"aut\",\ncomment = c(ORCID = \"0000-0001-5103-6917\")\n),\nperson(\"Yaoxiang\", \"Li\", role = c(\"aut\", \"cre\"),\nemail = \"liyaoxiang@outlook.com\",\ncomment = c(ORCID = \"0000-0001-9200-1016\")))", "Description": "Tools for measuring similarity among documents and\ndetecting passages which have been reused. Implements shingled\nn-gram, skip n-gram, and other tokenizers;\nsimilarity/dissimilarity functions; pairwise comparisons;\nminhash and locality sensitive hashing algorithms; and a\nversion of the Smith-Waterman local alignment algorithm\nsuitable for natural language.", "License": "MIT + file LICENSE", "URL": "https://docs.ropensci.org/textreuse/,\nhttps://github.com/ropensci/textreuse", "BugReports": "https://github.com/ropensci/textreuse/issues", "VignetteBuilder": "knitr", "RoxygenNote": "7.3.2", "Encoding": "UTF-8", "Config/pak/sysreqs": "libicu-dev", "Repository": "https://ropensci.r-universe.dev", "Date/Publication": "2026-05-06 16:00:52 UTC", "RemoteUrl": "https://github.com/ropensci/textreuse", "RemoteRef": "master", "RemoteSha": "6f8cbe38029502e7cc6baeb169f587a6da0da655", "NeedsCompilation": "yes", "Packaged": { "Date": "2026-06-05 06:15:07 UTC", "User": "root" }, "Author": "Lincoln Mullen [aut] (ORCID: ),\nYaoxiang Li [aut, cre] (ORCID: )", "Maintainer": "Yaoxiang Li ", "MD5sum": "2461e614b45671c78449d274d0996aed", "_user": "ropensci", "_type": "src", "_file": "textreuse_1.0.1.tar.gz", "_fileid": "176f63b055b07f2f3da97916218daa592f09cbba1f00c4e2d102aa8b8e073725", "_filesize": 1417407, "_sha256": "176f63b055b07f2f3da97916218daa592f09cbba1f00c4e2d102aa8b8e073725", "_created": "2026-06-05T06:15:07.000Z", "_published": "2026-06-05T06:21:37.039Z", "_distro": "noble", "_jobs": [ { "job": 79674525643, "time": 162, "config": "linux-devel-arm64", "r": "4.7.0", "check": "OK", "artifact": "7430093106" }, { "job": 79674525607, "time": 180, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "7430096302" }, { "job": 79674525619, "time": 181, "config": "linux-release-arm64", "r": "4.6.0", "check": "OK", "artifact": "7430097163" }, { "job": 79674525592, "time": 154, "config": "linux-release-x86_64", "r": "4.6.0", "check": "OK", "artifact": "7430090654" }, { "job": 79674525582, "time": 106, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "7430089760" }, { "job": 79674525746, "time": 246, "config": "macos-oldrel-x86_64", "r": "4.5.3", "check": "OK", "artifact": "7430134060" }, { "job": 79674525635, "time": 94, "config": "macos-release-arm64", "r": "4.6.0", "check": "OK", "artifact": "7430090386" }, { "job": 79674525561, "time": 239, "config": "macos-release-x86_64", "r": "4.6.0", "check": "OK", "artifact": "7430120237" }, { "job": 79674148105, "time": 170, "config": "pkgdown", "r": "4.6.0", "check": "OK", "artifact": "7430047959" }, { "job": 79674148100, "time": 200, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7430054948" }, { "job": 79674525631, "time": 133, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7430085973" }, { "job": 79674525655, "time": 146, "config": "windows-devel", "r": "4.7.0", "check": "OK", "artifact": "7430088880" }, { "job": 79674525638, "time": 120, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "7430082646" }, { "job": 79674525639, "time": 134, "config": "windows-release", "r": "4.6.0", "check": "OK", "artifact": "7430086156" } ], "_buildurl": "https://github.com/r-universe/ropensci/actions/runs/26998742684", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/ropensci/textreuse", "_commit": { "id": "6f8cbe38029502e7cc6baeb169f587a6da0da655", "author": "Yaoxiang Li ", "committer": "Yaoxiang Li ", "message": "Prepare CRAN resubmission\n", "time": 1778083252 }, "_maintainer": { "name": "Yaoxiang Li", "email": "liyaoxiang@outlook.com", "login": "yaoxiangli", "description": "The most beautiful thing we can experience is the mysterious. It is the source of all true art and science.", "uuid": 18198096, "orcid": "0000-0001-9200-1016" }, "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 3.1.1", "role": "Depends" }, { "package": "BH", "role": "LinkingTo" }, { "package": "Rcpp", "role": "LinkingTo" }, { "package": "RcppProgress", "role": "LinkingTo" }, { "package": "assertthat", "version": ">= 0.1", "role": "Imports" }, { "package": "digest", "version": ">= 0.6.8", "role": "Imports" }, { "package": "dplyr", "version": ">= 0.8.0", "role": "Imports" }, { "package": "NLP", "version": ">= 0.1.8", "role": "Imports" }, { "package": "Matrix", "role": "Imports" }, { "package": "Rcpp", "version": ">= 0.12.0", "role": "Imports" }, { "package": "RcppProgress", "version": ">= 0.1", "role": "Imports" }, { "package": "stringr", "version": ">= 1.0.0", "role": "Imports" }, { "package": "tibble", "version": ">= 3.0.1", "role": "Imports" }, { "package": "tidyr", "version": ">= 1.0.0", "role": "Imports" }, { "package": "testthat", "version": ">= 0.11.0", "role": "Suggests" }, { "package": "knitr", "version": ">= 1.11", "role": "Suggests" }, { "package": "rmarkdown", "version": ">= 0.8", "role": "Suggests" }, { "package": "covr", "role": "Suggests" } ], "_owner": "ropensci", "_selfowned": true, "_usedby": 0, "_updates": [ { "week": "2026-19", "n": 29 } ], "_tags": [ { "name": "v1.0.0", "date": "2026-05-06" }, { "name": "v1.0.1", "date": "2026-05-06" } ], "_topics": [ "peer-reviewed", "cpp" ], "_stars": 200, "_contributors": [ { "user": "lmullen", "count": 282, "uuid": 183672 }, { "user": "yaoxiangli", "count": 49, "uuid": 18198096 }, { "user": "jeroen", "count": 2, "uuid": 216319 }, { "user": "noamross", "count": 2, "uuid": 571752 }, { "user": "romainfrancois", "count": 2, "uuid": 2625526 }, { "user": "ashander", "count": 1, "uuid": 510776 }, { "user": "karthik", "count": 1, "uuid": 138494 }, { "user": "mayeulk", "count": 1, "uuid": 768570 } ], "_userbio": { "uuid": 1200269, "type": "organization", "name": "rOpenSci", "description": "Tools and R Packages for Open Science" }, "_downloads": { "count": 695, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/textreuse" }, "_mentions": 1, "_devurl": "https://github.com/ropensci/textreuse", "_pkgdown": "https://docs.ropensci.org/textreuse/", "_searchresults": 235, "_metadata": { "review": { "id": 20, "status": "reviewed", "version": "0.0.1.9001", "organization": "rOpenSci Software Review", "url": "https://github.com/ropensci/software-review/issues/20" }, "ropensci_category": "literature" }, "_rbuild": "4.6.0", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "extra/textreuse.html", "manual.pdf" ], "_homeurl": "https://github.com/ropensci/textreuse", "_realowner": "ropensci", "_cranurl": true, "_releases": [ { "version": "0.1.0", "date": "2015-10-30" }, { "version": "0.1.1", "date": "2015-11-04" }, { "version": "0.1.2", "date": "2015-11-05" }, { "version": "0.1.3", "date": "2016-03-28" }, { "version": "0.1.4", "date": "2016-11-28" }, { "version": "0.1.5", "date": "2020-05-15" }, { "version": "1.0.1", "date": "2026-05-07" } ], "_exports": [ "align_local", "as_sparse_matrix", "content", "content<-", "count_matches", "filenames", "has_content", "has_hashes", "has_minhashes", "has_tokens", "hash_string", "hashes", "hashes<-", "is.TextReuseCorpus", "is.TextReuseTextDocument", "jaccard_bag_similarity", "jaccard_dissimilarity", "jaccard_similarity", "lsh", "lsh_add", "lsh_candidates", "lsh_compare", "lsh_probability", "lsh_query", "lsh_subset", "lsh_threshold", "matching_tokens", "meta", "meta<-", "minhash_generator", "minhashes", "minhashes<-", "pairwise_candidates", "pairwise_compare", "ratio_of_matches", "rehash", "skipped", "TextReuseCorpus", "TextReuseTextDocument", "token_index", "token_index_candidates", "tokenize", "tokenize_ngrams", "tokenize_sentences", "tokenize_skip_ngrams", "tokenize_words", "tokens", "tokens<-", "wordcount" ], "_help": [ { "page": "textreuse-package", "title": "textreuse: Detect Text Reuse and Document Similarity", "topics": [ "textreuse-package", "textreuse" ] }, { "page": "align_local", "title": "Local alignment of natural language texts", "topics": [ "align_local" ] }, { "page": "as.matrix.textreuse_candidates", "title": "Convert candidates data frames to other formats", "topics": [ "as.matrix.textreuse_candidates", "as_sparse_matrix" ] }, { "page": "filenames", "title": "Filenames from paths", "topics": [ "filenames" ] }, { "page": "hash_string", "title": "Hash a string to an integer", "topics": [ "hash_string" ] }, { "page": "lsh", "title": "Locality sensitive hashing for minhash", "topics": [ "lsh" ] }, { "page": "lsh_add", "title": "Add documents to a LSH cache", "topics": [ "lsh_add" ] }, { "page": "lsh_candidates", "title": "Candidate pairs from LSH comparisons", "topics": [ "lsh_candidates" ] }, { "page": "lsh_compare", "title": "Compare candidates identified by LSH", "topics": [ "lsh_compare" ] }, { "page": "lsh_probability", "title": "Probability that a candidate pair will be detected with LSH", "topics": [ "lsh_probability", "lsh_threshold" ] }, { "page": "lsh_query", "title": "Query a LSH cache for matches to a single document", "topics": [ "lsh_query" ] }, { "page": "lsh_subset", "title": "List of all candidates in a corpus", "topics": [ "lsh_subset" ] }, { "page": "minhash_generator", "title": "Generate a minhash function", "topics": [ "minhash_generator" ] }, { "page": "pairwise_candidates", "title": "Candidate pairs from pairwise comparisons", "topics": [ "pairwise_candidates" ] }, { "page": "pairwise_compare", "title": "Pairwise comparisons among documents in a corpus", "topics": [ "pairwise_compare" ] }, { "page": "rehash", "title": "Recompute the hashes for a document or corpus", "topics": [ "rehash" ] }, { "page": "similarity-functions", "title": "Measure similarity/dissimilarity in documents", "topics": [ "count_matches", "jaccard_bag_similarity", "jaccard_dissimilarity", "jaccard_similarity", "matching_tokens", "ratio_of_matches", "similarity-functions" ] }, { "page": "TextReuseCorpus", "title": "TextReuseCorpus", "topics": [ "is.TextReuseCorpus", "skipped", "TextReuseCorpus" ] }, { "page": "TextReuseTextDocument", "title": "TextReuseTextDocument", "topics": [ "has_content", "has_hashes", "has_minhashes", "has_tokens", "is.TextReuseTextDocument", "TextReuseTextDocument" ] }, { "page": "TextReuseTextDocument-accessors", "title": "Accessors for TextReuse objects", "topics": [ "hashes", "hashes<-", "minhashes", "minhashes<-", "TextReuseTextDocument-accessors", "tokens", "tokens<-" ] }, { "page": "token_index", "title": "Build an index of tokens and documents", "topics": [ "token_index" ] }, { "page": "token_index_candidates", "title": "Extract candidate document pairs from a token index", "topics": [ "token_index_candidates" ] }, { "page": "tokenize", "title": "Recompute the tokens for a document or corpus", "topics": [ "tokenize" ] }, { "page": "tokenizers", "title": "Split texts into tokens", "topics": [ "tokenizers", "tokenize_ngrams", "tokenize_sentences", "tokenize_skip_ngrams", "tokenize_words" ] }, { "page": "wordcount", "title": "Count words", "topics": [ "wordcount" ] } ], "_readme": "https://github.com/ropensci/textreuse/raw/master/README.md", "_rundeps": [ "assertthat", "BH", "cli", "cpp11", "digest", "dplyr", "generics", "glue", "lattice", "lifecycle", "magrittr", "Matrix", "NLP", "pillar", "pkgconfig", "purrr", "R6", "Rcpp", "RcppProgress", "rlang", "stringi", "stringr", "tibble", "tidyr", "tidyselect", "utf8", "vctrs", "withr" ], "_sysdeps": [ { "shlib": "libstdc++", "package": "libstdc++6", "source": "gcc", "version": "14.2.0-4ubuntu2~24.04.1", "name": "c++", "homepage": "http://gcc.gnu.org/", "description": "GNU Standard C++ Library v3" } ], "_vignettes": [ { "source": "textreuse-introduction.Rmd", "filename": "textreuse-introduction.html", "title": "Introduction to the textreuse package", "author": "Lincoln Mullen, Yaoxiang Li", "engine": "knitr::rmarkdown", "headings": [ "TextReuse classes", "TextReuseTextDocument", "TextReuseCorpus", "Tokenizers", "Hash functions", "Comparison functions", "Parallelization" ], "created": "2015-10-22 01:12:28", "modified": "2026-05-05 07:25:00", "commits": 10 }, { "source": "textreuse-minhash.Rmd", "filename": "textreuse-minhash.html", "title": "Minhash and locality-sensitive hashing", "author": "Lincoln Mullen, Yaoxiang Li", "engine": "knitr::rmarkdown", "headings": [], "created": "2015-10-22 01:12:28", "modified": "2026-05-05 07:25:00", "commits": 8 }, { "source": "textreuse-pairwise.Rmd", "filename": "textreuse-pairwise.html", "title": "Pairwise comparisons for document similarity", "author": "Lincoln Mullen, Yaoxiang Li", "engine": "knitr::rmarkdown", "headings": [], "created": "2015-10-22 01:12:28", "modified": "2026-05-05 07:25:00", "commits": 4 }, { "source": "textreuse-alignment.Rmd", "filename": "textreuse-alignment.html", "title": "Text Alignment", "author": "Lincoln Mullen, Yaoxiang Li", "engine": "knitr::rmarkdown", "headings": [], "created": "2015-10-22 01:12:28", "modified": "2026-05-05 07:25:00", "commits": 5 } ], "_score": 8.818225893613956, "_indexed": true, "_nocasepkg": "textreuse", "_universes": [ "ropensci", "yaoxiangli" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "1.0.1", "date": "2026-06-05T06:17:53.000Z", "distro": "noble", "arch": "aarch64", "commit": "6f8cbe38029502e7cc6baeb169f587a6da0da655", "fileid": "8840249b6576325eecf3591a6f2d5605cb44eb43ad31f5bea683799a6c1b5df8", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/ropensci/actions/runs/26998742684" }, { "r": "4.7.0", "os": "linux", "version": "1.0.1", "date": "2026-06-05T06:17:56.000Z", "distro": "noble", "arch": "x86_64", "commit": "6f8cbe38029502e7cc6baeb169f587a6da0da655", "fileid": "954bd1ed135dcb26ebfadab487292fdd119272dc129d03c256da6d7eaa11bdaf", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/ropensci/actions/runs/26998742684" }, { "r": "4.6.0", "os": "linux", "version": "1.0.1", "date": "2026-06-05T06:18:09.000Z", "distro": "noble", "arch": "aarch64", "commit": "6f8cbe38029502e7cc6baeb169f587a6da0da655", "fileid": "1324932efb54f3717ecd913392459c3d6bfc7fd4054a0730a11207c4c2793a8e", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/ropensci/actions/runs/26998742684" }, { "r": "4.6.0", "os": "linux", "version": "1.0.1", "date": "2026-06-05T06:17:38.000Z", "distro": "noble", "arch": "x86_64", "commit": "6f8cbe38029502e7cc6baeb169f587a6da0da655", "fileid": "9b2596a742863fcc960eabe0ef89e208368435c2acc62999e2e02f403616324e", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/ropensci/actions/runs/26998742684" }, { "r": "4.5.3", "os": "mac", "version": "1.0.1", "date": "2026-06-05T06:17:35.000Z", "arch": "aarch64", "commit": "6f8cbe38029502e7cc6baeb169f587a6da0da655", "fileid": "23c6242a5fa8597dadb61e213422637f5ff2dbe7965748d8b1c6cd28fcabe795", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/ropensci/actions/runs/26998742684" }, { "r": "4.5.3", "os": "mac", "version": "1.0.1", "date": "2026-06-05T06:20:19.000Z", "arch": "x86_64", "commit": "6f8cbe38029502e7cc6baeb169f587a6da0da655", "fileid": "4b998de77eac4db6928abef954a7c5fb350af6a5175d299baf48a397ac75e940", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/ropensci/actions/runs/26998742684" }, { "r": "4.6.0", "os": "mac", "version": "1.0.1", "date": "2026-06-05T06:17:43.000Z", "arch": "aarch64", "commit": "6f8cbe38029502e7cc6baeb169f587a6da0da655", "fileid": "9c7b1c7061766fac3259b5db550bcbc460a2f6d5ddbff5e7e0f37b959f098c1c", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/ropensci/actions/runs/26998742684" }, { "r": "4.6.0", "os": "mac", "version": "1.0.1", "date": "2026-06-05T06:19:11.000Z", "arch": "x86_64", "commit": "6f8cbe38029502e7cc6baeb169f587a6da0da655", "fileid": "28b8b9c72a3c6625a9fc2a70705bcc0b064b376a7d0bcb789bf2c80204377068", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/ropensci/actions/runs/26998742684" }, { "r": "4.6.0", "os": "wasm", "version": "1.0.1", "date": "2026-06-05T06:17:36.000Z", "arch": "emscripten", "commit": "6f8cbe38029502e7cc6baeb169f587a6da0da655", "fileid": "a19acf56632b5ade0b116184d76e36df6dafd7b3510535a8787475cd1d0aeaad", "status": "success", "buildurl": "https://github.com/r-universe/ropensci/actions/runs/26998742684" }, { "r": "4.7.0", "os": "win", "version": "1.0.1", "date": "2026-06-05T06:16:58.000Z", "arch": "x86_64", "commit": "6f8cbe38029502e7cc6baeb169f587a6da0da655", "fileid": "5f508963bd6eb588c16b2f91425ccabb7c5c8b4da4c132c31a026f0a2ce2609f", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/ropensci/actions/runs/26998742684" }, { "r": "4.5.3", "os": "win", "version": "1.0.1", "date": "2026-06-05T06:16:40.000Z", "arch": "x86_64", "commit": "6f8cbe38029502e7cc6baeb169f587a6da0da655", "fileid": "5ce2c0b829845452f6d230e988b0bb2a1c15a277ce497e2584f8fc224e96e253", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/ropensci/actions/runs/26998742684" }, { "r": "4.6.0", "os": "win", "version": "1.0.1", "date": "2026-06-05T06:16:49.000Z", "arch": "x86_64", "commit": "6f8cbe38029502e7cc6baeb169f587a6da0da655", "fileid": "2b9df16103c02ba9fa67607f3f60c83755e33059319ec71766cdd000e6c1e2de", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/ropensci/actions/runs/26998742684" } ] }