add support for remote repos

Author: e-kotov

CITATION.cff

@@ -9,7 +9,7 @@ type: software
 license: MIT
 title: 'rdocdump: Dump ''R'' Package Source, Documentation, and Vignettes into One
   File'
-version: 0.1.1
+version: 0.2.0.9000
 doi: 10.32614/CRAN.package.rdocdump
 identifiers:
 - type: doi
@@ -62,7 +62,7 @@ references:
     given-names: Jeroen
     email: jeroenooms@gmail.com
     orcid: https://orcid.org/0000-0002-4035-0289
-  year: '2025'
+  year: '2026'
   doi: 10.32614/CRAN.package.curl
 - type: software
   title: quarto
@@ -79,8 +79,31 @@ references:
     given-names: Christophe
     email: cderv@posit.co
     orcid: https://orcid.org/0000-0003-4474-2498
-  year: '2025'
+  year: '2026'
   doi: 10.32614/CRAN.package.quarto
+- type: software
+  title: remotes
+  abstract: 'remotes: R Package Installation from Remote Repositories, Including ''GitHub'''
+  notes: Suggests
+  url: https://remotes.r-lib.org
+  repository: https://CRAN.R-project.org/package=remotes
+  authors:
+  - family-names: Csárdi
+    given-names: Gábor
+    email: csardi.gabor@gmail.com
+  - family-names: Hester
+    given-names: Jim
+  - family-names: Wickham
+    given-names: Hadley
+  - family-names: Chang
+    given-names: Winston
+  - family-names: Morgan
+    given-names: Martin
+  - family-names: Tenenbaum
+    given-names: Dan
+  year: '2026'
+  doi: 10.32614/CRAN.package.remotes
+  version: '>= 2.2.0'
 - type: software
   title: testthat
   abstract: 'testthat: Unit Testing for R'
@@ -91,7 +114,7 @@ references:
   - family-names: Wickham
     given-names: Hadley
     email: hadley@posit.co
-  year: '2025'
+  year: '2026'
   doi: 10.32614/CRAN.package.testthat
   version: '>= 3.0.0'
 - type: software
@@ -117,6 +140,6 @@ references:
     email: hadley@posit.co
   - family-names: Chang
     given-names: Winston
-  year: '2025'
+  year: '2026'
   doi: 10.32614/CRAN.package.withr
 

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: rdocdump
 Title: Dump 'R' Package Source, Documentation, and Vignettes into One File
-Version: 0.1.1.9000
+Version: 0.2.0.9000
 Authors@R: 
     person("Egor", "Kotov", , "kotov.egor@gmail.com", role = c("aut", "cre", "cph"),
            comment = c(ORCID = "0000-0001-6690-5345"))
@@ -19,6 +19,7 @@ BugReports: https://github.com/e-kotov/rdocdump/issues
 Suggests:
     curl,
     quarto,
+    remotes (>= 2.2.0),
     testthat (>= 3.0.0),
     withr
 VignetteBuilder: 
@@ -27,4 +28,4 @@ Config/testthat/edition: 3
 Encoding: UTF-8
 Language: en
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.3.2
+RoxygenNote: 7.3.3

NEWS.md

@@ -1,5 +1,7 @@
 # rdocdump (development version)
 
+* Added support for remote repository references (GitHub, GitLab, Bitbucket) in `rdd_to_txt()` and `rdd_extract_code()`. This includes support for specific branches/tags/commits and packages in subdirectories, as well as direct URLs (to branches and/or folders within repositories). Therefore the `remotes` package to `Suggests` to handle remote downloads.
+
 # rdocdump 0.1.1 (2025-08-21)
 
 * Added `version` argument to `rdd_to_txt()` and `rdd_extract_code()` functions to specify the version of the package to download from CRAN for processing.

R/extract_code.R

@@ -5,10 +5,20 @@
 #'
 #' @param pkg A `character` string specifying the package. This can be:
 #' \itemize{
-#' \item an installed package name,
+#' \item an installed package name (e.g., `"ggplot2"`),
 #' \item a full path to a package source directory,
-#' \item a full path to a package archive file (tar.gz), or
-#' \item a package name not installed (which will then be downloaded from CRAN).
+#' \item a full path to a package archive file (tar.gz),
+#' \item a package name not installed (which will then be downloaded from CRAN),
+#' \item a GitHub repository reference (e.g., `"tidyverse/ggplot2"` or
+#'       `"github::tidyverse/ggplot2"`),
+#' \item a GitLab repository reference (e.g., `"gitlab::user/repo"`),
+#' \item a repository reference with specific branch/tag/commit
+#'       (e.g., `"user/repo@v1.0.0"` or `"user/repo@main"`),
+#' \item a repository reference with subdirectory
+#'       (e.g., `"user/repo/subdir"` for packages not at repo root),
+#' \item a full GitHub or GitLab web URL
+#'       (e.g., `"https://github.com/apache/sedona-db/tree/main/r/sedonadb"` or
+#'       `"https://github.com/ipeaGIT/r5r/tree/master/r-package"`).
 #' }
 #' @param file Optional. Save path for the output text file. If set, the function will return the path to the file instead of the combined text. Defaults to `NULL`.
 #' @param include_tests `logical`. If `TRUE`, for non-installed packages, the function will also include R source code from the `tests` directory. Defaults to `FALSE`.

R/to_txt.R

@@ -5,10 +5,20 @@
 #'
 #' @param pkg A `character` string specifying the package. This can be:
 #' \itemize{
-#'   \item an installed package name,
+#'   \item an installed package name (e.g., `"ggplot2"`),
 #'   \item a full path to a package source directory,
-#'   \item a full path to a package archive file (tar.gz), or
-#'   \item a package name not installed (which will then be downloaded from CRAN).
+#'   \item a full path to a package archive file (tar.gz),
+#'   \item a package name not installed (which will then be downloaded from CRAN),
+#'   \item a GitHub repository reference (e.g., `"tidyverse/ggplot2"` or
+#'         `"github::tidyverse/ggplot2"`),
+#'   \item a GitLab repository reference (e.g., `"gitlab::user/repo"`),
+#'   \item a repository reference with specific branch/tag/commit
+#'         (e.g., `"user/repo@v1.0.0"` or `"user/repo@main"`),
+#'   \item a repository reference with subdirectory
+#'         (e.g., `"user/repo/subdir"` for packages not at repo root),
+#'   \item a full GitHub or GitLab web URL
+#'         (e.g., `"https://github.com/apache/sedona-db/tree/main/r/sedonadb"` or
+#'         `"https://github.com/ipeaGIT/r5r/tree/master/r-package"`).
 #' }
 #' @param file Optional. Save path for the output text file. If set, the function will return the path to the file instead of the combined text. Defaults to `NULL`.
 #' @param force_fetch `logical`. If `TRUE`, the package source will be fetched from CRAN as a tar.gz archive even if the package is already installed locally. Default is `FALSE`, but when `version` is specified, it will be set to `TRUE`.
@@ -45,6 +55,17 @@
 #' docs <- rdd_to_txt("splines")
 #' cat(substr(docs, 1, 500))
 #'
+#' \dontrun{
+#' # Extract from GitHub repository
+#' docs <- rdd_to_txt("r-lib/rlang")
+#'
+#' # Extract specific version from GitHub
+#' docs <- rdd_to_txt("r-lib/rlang@v1.1.0")
+#'
+#' # Extract from GitLab
+#' docs <- rdd_to_txt("gitlab::user/repo")
+#' }
+#'
 #' \donttest{
 #' # set cache directory for `rdocdump`
 #' rdd_set_cache_path(paste0(tempdir(), "/rdocdump_cache"))

R/util_resolve_pkg_path.R

@@ -21,6 +21,12 @@ resolve_pkg_path <- function(
     stop("Argument 'pkg' must be a single character string.")
   }
 
+  # Check if it's a remote reference (GitHub, GitLab, etc.)
+  if (is_remote_reference(pkg)) {
+    message("Fetching package source from remote repository...")
+    return(resolve_remote_pkg(pkg, cache_path))
+  }
+
   # Helper function to parse tarball filename into package name and version.
   parse_tarball_name <- function(tar_path) {
     base_name <- basename(tar_path) # e.g., "rJavaEnv_0.2.2.tar.gz"