Fixes to release

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: GitStats
 Title: Standardized Git Repository Data
-Version: 2.2.0
+Version: 2.1.0.9010
 Authors@R: c(
     person(given = "Maciej", family = "Banas", email = "banasmaciek@gmail.com", role = c("aut", "cre")),
     person(given = "Kamil", family = "Koziej", email = "koziej.k@gmail.com", role = "aut"),

R/EngineGraphQL.R

@@ -71,7 +71,7 @@ EngineGraphQL <- R6::R6Class(
     },
 
     filter_files_by_pattern = function(files_structure, pattern) {
-      files_structure[grepl(pattern, files_structure)]
+      files_structure[grepl(paste0(pattern, collapse = "|"), files_structure)]
     },
 
     get_path_from_files_structure = function(host_files_structure,

R/GitHost.R

@@ -1226,7 +1226,9 @@
         files_structure_list <- purrr::map(private$orgs, function(org) {
           if (verbose) {
             user_info <- if (!is.null(pattern)) {
-              glue::glue("Pulling files structure...[files matching pattern: '{pattern}']")
+              glue::glue(
+                "Pulling files structure...[files matching pattern: '{paste0(pattern, collapse = '|')}']"
+              )
             } else {
               glue::glue("Pulling files structure...")
             }
@@ -1273,7 +1275,9 @@
         files_structure_list <- purrr::map(orgs, function(org) {
           if (verbose) {
             user_info <- if (!is.null(pattern)) {
-              glue::glue("Pulling files structure...[files matching pattern: '{pattern}']")
+              glue::glue(
+                "Pulling files structure...[files matching pattern: '{paste0(pattern, collapse = '|')}']"
+              )
             } else {
               glue::glue("Pulling files structure...")
             }

R/GitStats.R

@@ -211,7 +211,7 @@ GitStats <- R6::R6Class(
                          progress = verbose) {
       private$check_for_host()
       args_list <- list(
-        "file_pattern" = paste0(file_path, pattern),
+        "file_pattern" = paste(file_path, pattern),
         "depth" = depth
       )
       trigger <- private$trigger_pulling(
@@ -1007,7 +1007,7 @@ GitStats <- R6::R6Class(
           }
           attr_data <- attr_data %>% paste0(collapse = separator)
         }
-        return(cli::col_grey(glue::glue("[{attr_name}: {attr_data}]")))
+        return(cli::col_grey(glue::glue("[{attr_name}: {trimws(attr_data)}]")))
       } else {
         return("")
       }

R/get_commits_stats.R → R/get_commits.R

@@ -1,3 +1,49 @@
+#' @title Get data on commits
+#' @name get_commits
+#' @description List all commits from all repositories for an organization or a
+#'   vector of repositories.
+#' @param gitstats A GitStats object.
+#' @param since A starting date.
+#' @param until An end date.
+#' @param cache A logical, if set to `TRUE` GitStats will retrieve the last
+#'   result from its storage.
+#' @param verbose A logical, `TRUE` by default. If `FALSE` messages and printing
+#'   output is switched off.
+#' @param progress A logical, by default set to `verbose` value. If `FALSE` no
+#'   `cli` progress bar will be displayed.
+#' @return A data.frame.
+#' @examples
+#' \dontrun{
+#' my_gitstats <- create_gitstats() %>%
+#'   set_github_host(
+#'     token = Sys.getenv("GITHUB_PAT"),
+#'     repos = c("openpharma/DataFakeR", "openpharma/visR")
+#'   ) %>%
+#'   set_gitlab_host(
+#'     token = Sys.getenv("GITLAB_PAT_PUBLIC"),
+#'     orgs = "mbtests"
+#'   )
+#'  get_commits(my_gitstats, since = "2018-01-01")
+#' }
+#' @export
+get_commits <- function(gitstats,
+                        since    = NULL,
+                        until    = Sys.Date() + lubridate::days(1),
+                        cache    = TRUE,
+                        verbose  = is_verbose(gitstats),
+                        progress = verbose) {
+  if (is.null(since)) {
+    cli::cli_abort(cli::col_red("You need to pass date to `since` parameter."), call = NULL)
+  }
+  gitstats$get_commits(
+    since    = since,
+    until    = until,
+    cache    = cache,
+    verbose  = verbose,
+    progress = progress
+  )
+}
+
 #' @title Get commits statistics
 #' @name get_commits_stats
 #' @description Prepare statistics from the pulled commits data.

R/get_files.R

@@ -2,38 +2,74 @@
 #' @name get_files
 #' @description Pulls text files and their content.
 #' @param gitstats A `GitStats` object.
-#' @param pattern A regular expression. If defined, it pulls file structure for
-#'   a repository matching this pattern. Can be defined if `file_path` stays
+#' @param pattern A regular expression. If defined, it pulls content of all
+#'   files in a repository matching this pattern reaching to the level of
+#'   directories defined by `depth` parameter. Works only if `file_path` stays
 #'   `NULL`.
-#' @param depth An optional integer. Defines level of directories to retrieve
-#'   files from. E.g. if set to `0`, it will pull files only from root, if `1L`,
-#'   will take data from `root` directory and directories visible in `root`
-#'   directory. If left with no argument, will pull files from all directories.
-#' @param file_path Optional. A standardized path to file(s) in repositories.
-#'   May be a character vector if multiple files are to be pulled. Can be
-#'   defined if `pattern` stays `NULL`.
-#' @param cache A logical, if set to `TRUE` GitStats will retrieve the last
+#' @param depth Defines level of directories to retrieve files from. E.g. if set
+#'   to `0`, it will pull files only from `root`, if `1L`, will take data from
+#'   `root` directory and directories visible in `root` directory. If left with
+#'   no argument, will pull files from all directories.
+#' @param file_path A specific path to file(s) in repositories. May be a
+#'   character vector if multiple files are to be pulled. If defined, the
+#'   function pulls content of this specific `file_path`. Can be defined only if
+#'   `pattern` stays `NULL`.
+#' @param cache A logical, if set to `TRUE` `GitStats` will retrieve the last
 #'   result from its storage.
 #' @param verbose A logical, `TRUE` by default. If `FALSE` messages and printing
 #'   output is switched off.
 #' @param progress A logical, by default set to `verbose` value. If `FALSE` no
 #'   `cli` progress bar will be displayed.
+#' @details `get_files()` may be used in two ways: either with `pattern` (with
+#'   optional `depth`) or `file_path` argument defined.
+#'
+#'   In the first scenario, `GitStats` will pull first a files structure
+#'   responding to the passed `pattern` and `depth` arguments and afterwards
+#'   files content for all of these files. In the second scenario, `GitStats`
+#'   will pull only the content of files for the specific `file_path` of the
+#'   repository.
+#'
+#'   If user wants to pull a particular file or files, a `file_path` approach
+#'   seems more reasonable, as it is a faster way since it omits pulling the
+#'   whole file structure from the repo.
+#'
+#'   For example, if user wants to pull content of `README.md` and/or `NEWS.md`
+#'   files placed in the `root` directories of the repositories, he should take
+#'   the `file_path` approach as he already knows precisely paths of the files.
+#'
+#'   On the other hand, if user wants to pull specific type of files (e.g. all
+#'   `.md` or `.Rmd` files in the repository), without knowing their path, it is
+#'   recommended to use a `pattern` approach, which will trigger `GitStats` to
+#'   find all the files in the repository on the given level of directories
+#'   (`pattern` argument) and afterwards pull their content.
+#'
+#'   The latter approach is slower than the former but may be more useful
+#'   depending on users' goals. Both approaches return data in the same format:
+#'   `tibble` with data on `files`, namely their `path` and their `content`.
+#'
 #' @examples
 #' \dontrun{
-#'  rmd_files <- create_gitstats() |>
+#'  git_stats <- create_gitstats() |>
 #'   set_github_host(
 #'     token = Sys.getenv("GITHUB_PAT"),
 #'     orgs = c("r-world-devs")
-#'   ) %>%
+#'   ) |>
 #'   set_gitlab_host(
 #'     token = Sys.getenv("GITLAB_PAT_PUBLIC"),
 #'     orgs = "mbtests"
-#'   ) |>
-#'  get_files(
+#'   )
+#'
+#'  rmd_files <- get_files(
+#'    gitstats = git_stats,
 #'    pattern = "\\.Rmd",
 #'    depth = 2L
 #'  )
 #'
+#'  app_files <- get_files(
+#'    gitstats = git_stats,
+#'    file_path = c("R/app.R", "R/ui.R", "R/server.R")
+#'  )
+#'
 #' }
 #' @return A data.frame.
 #' @export

R/get_repos.R

@@ -0,0 +1,121 @@
+#' @title Get data on repositories
+#' @name get_repos
+#' @description  Pulls data on all repositories for an organization, individual
+#'   user or those with a given text in code blobs (`with_code` parameter) or a
+#'   file (`with_files` parameter) and parse it into table format.
+#' @param gitstats A GitStats object.
+#' @param add_contributors A logical parameter to decide whether to add
+#'   information about repositories' contributors to the repositories output
+#'   (table). If set to `FALSE` it makes function run faster as, in the case of
+#'   `org` search mode, it reaches only `GraphQL` endpoint with a query on
+#'   repositories, and in the case of `code` search mode it reaches only
+#'   `repositories REST API` endpoint. However, the pitfall is that the result
+#'   does not convey information on contributors. \cr\cr When set to `TRUE` (by
+#'   default), `GitStats` iterates additionally over pulled repositories and
+#'   reaches to the `contributors APIs`, which makes it slower, but gives
+#'   additional information.
+#' @param with_code A character vector, if defined, GitStats will pull
+#'   repositories with specified code phrases in code blobs.
+#' @param in_files A character vector of file names. Works when `with_code` is
+#'   set - then it searches code blobs only in files passed to `in_files`
+#'   parameter.
+#' @param with_files A character vector, if defined, GitStats will pull
+#'   repositories with specified files.
+#' @param cache A logical, if set to `TRUE` GitStats will retrieve the last
+#'   result from its storage.
+#' @param verbose A logical, `TRUE` by default. If `FALSE` messages and printing
+#'   output is switched off.
+#' @param progress A logical, by default set to `verbose` value. If `FALSE` no
+#'   `cli` progress bar will be displayed.
+#' @return A data.frame.
+#' @examples
+#' \dontrun{
+#' my_gitstats <- create_gitstats() %>%
+#'   set_github_host(
+#'     token = Sys.getenv("GITHUB_PAT"),
+#'     orgs = c("r-world-devs", "openpharma")
+#'   ) %>%
+#'   set_gitlab_host(
+#'     token = Sys.getenv("GITLAB_PAT_PUBLIC"),
+#'     orgs = "mbtests"
+#'   )
+#' get_repos(my_gitstats)
+#' get_repos(my_gitstats, add_contributors = FALSE)
+#' get_repos(my_gitstats, with_code = "Shiny", in_files = "renv.lock")
+#' get_repos(my_gitstats, with_files = "DESCRIPTION")
+#' }
+#' @export
+get_repos <- function(gitstats,
+                      add_contributors = TRUE,
+                      with_code        = NULL,
+                      in_files         = NULL,
+                      with_files       = NULL,
+                      cache            = TRUE,
+                      verbose          = is_verbose(gitstats),
+                      progress         = verbose) {
+  gitstats$get_repos(
+    add_contributors = add_contributors,
+    with_code        = with_code,
+    in_files         = in_files,
+    with_files       = with_files,
+    cache            = cache,
+    verbose          = verbose,
+    progress         = progress
+  )
+}
+
+#' @title Get repository URLS
+#' @name get_repos_urls
+#' @description Pulls a vector of repositories URLs (web or API): either all for
+#'   an organization or those with a given text in code blobs (`with_code`
+#'   parameter) or a file (`with_files` parameter).
+#' @param gitstats A GitStats object.
+#' @param type A character, choose if `api` or `web` (`html`) URLs should be
+#'   returned.
+#' @param with_code A character vector, if defined, GitStats will pull
+#'   repositories with specified code phrases in code blobs.
+#' @param in_files A character vector of file names. Works when `with_code` is
+#'   set - then it searches code blobs only in files passed to `in_files`
+#'   parameter.
+#' @param with_files A character vector, if defined, GitStats will pull
+#'   repositories with specified files.
+#' @param cache A logical, if set to `TRUE` GitStats will retrieve the last
+#'   result from its storage.
+#' @param verbose A logical, `TRUE` by default. If `FALSE` messages and printing
+#'   output is switched off.
+#' @param progress A logical, by default set to `verbose` value. If `FALSE` no
+#'   `cli` progress bar will be displayed.
+#' @return A character vector.
+#' @examples
+#' \dontrun{
+#' my_gitstats <- create_gitstats() %>%
+#'   set_github_host(
+#'     token = Sys.getenv("GITHUB_PAT"),
+#'     orgs = c("r-world-devs", "openpharma")
+#'   ) %>%
+#'   set_gitlab_host(
+#'     token = Sys.getenv("GITLAB_PAT_PUBLIC"),
+#'     orgs = "mbtests"
+#'   )
+#' get_repos_urls(my_gitstats, type = "api")
+#' get_repos_urls(my_gitstats, with_files = c("DESCRIPTION", "LICENSE"))
+#' }
+#' @export
+get_repos_urls <- function(gitstats,
+                           type       = "web",
+                           with_code  = NULL,
+                           in_files   = NULL,
+                           with_files = NULL,
+                           cache      = TRUE,
+                           verbose    = is_verbose(gitstats),
+                           progress   = verbose) {
+  gitstats$get_repos_urls(
+    type       = type,
+    with_code  = with_code,
+    in_files   = in_files,
+    with_files = with_files,
+    cache      = cache,
+    verbose    = verbose,
+    progress   = progress
+  )
+}