Title: | Standardized Git Repository Data |
---|---|
Description: | Obtain standardized data from multiple 'Git' services, including 'GitHub' and 'GitLab'. Designed to be 'Git' service-agnostic, this package assists teams with activities spread across various 'Git' platforms by providing a unified way to access repository data. |
Authors: | Maciej Banas [aut, cre], Kamil Koziej [aut], Karolina Marcinkowska [aut], Matt Secrest [aut] |
Maintainer: | Maciej Banas <[email protected]> |
License: | MIT + file LICENSE |
Version: | 2.1.2 |
Built: | 2024-11-13 07:41:43 UTC |
Source: | CRAN |
GitStats
objectCreate a GitStats
object
create_gitstats()
create_gitstats()
A GitStats
object.
my_gitstats <- create_gitstats()
my_gitstats <- create_gitstats()
List all commits from all repositories for an organization or a vector of repositories.
get_commits( gitstats_object, since = NULL, until = Sys.Date() + lubridate::days(1), cache = TRUE, verbose = is_verbose(gitstats_object), progress = verbose )
get_commits( gitstats_object, since = NULL, until = Sys.Date() + lubridate::days(1), cache = TRUE, verbose = is_verbose(gitstats_object), progress = verbose )
gitstats_object |
A GitStats object. |
since |
A starting date. |
until |
An end date. |
cache |
A logical, if set to |
verbose |
A logical, |
progress |
A logical, by default set to |
A data.frame.
## Not run: 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") ## End(Not run)
## Not run: 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") ## End(Not run)
Prepare statistics from the pulled commits data.
get_commits_stats(gitstats_object, time_interval = c("month", "day", "week"))
get_commits_stats(gitstats_object, time_interval = c("month", "day", "week"))
gitstats_object |
A GitStats class object. |
time_interval |
A character, specifying time interval to show statistics. |
To make function work, you need first to get commits data with
GitStats
. See examples section.
A table of commits_stats
class.
## Not run: my_gitstats <- create_gitstats() %>% set_github_host( token = Sys.getenv("GITHUB_PAT"), repos = c("r-world-devs/GitStats", "openpharma/visR") ) get_commits(my_gitstats, since = "2022-01-01") get_commits_stats(my_gitstats, time_interval = "week") ## End(Not run)
## Not run: my_gitstats <- create_gitstats() %>% set_github_host( token = Sys.getenv("GITHUB_PAT"), repos = c("r-world-devs/GitStats", "openpharma/visR") ) get_commits(my_gitstats, since = "2022-01-01") get_commits_stats(my_gitstats, time_interval = "week") ## End(Not run)
Pull text files content for a given scope (orgs, repos or whole git hosts).
get_files_content( gitstats_object, file_path = NULL, use_files_structure = TRUE, only_text_files = TRUE, cache = TRUE, verbose = is_verbose(gitstats_object), progress = verbose )
get_files_content( gitstats_object, file_path = NULL, use_files_structure = TRUE, only_text_files = TRUE, cache = TRUE, verbose = is_verbose(gitstats_object), progress = verbose )
gitstats_object |
A GitStats object. |
file_path |
Optional. A standardized path to file(s) in repositories.
May be a character vector if multiple files are to be pulled. If set to
|
use_files_structure |
Logical. If |
only_text_files |
A logical, |
cache |
A logical, if set to |
verbose |
A logical, |
progress |
A logical, by default set to |
A data.frame.
## Not run: my_gitstats <- 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_content( gitstats_obj = my_gitstats, file_path = c("LICENSE", "DESCRIPTION") ) # example with files structure files_structure <- get_files_structure( gitstats_obj = my_gitstats, pattern = "\\.Rmd", depth = 2L ) # get_files_content() will make use of pulled earlier files structure files_content <- get_files_content( gitstats_obj = my_gitstats ) ## End(Not run)
## Not run: my_gitstats <- 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_content( gitstats_obj = my_gitstats, file_path = c("LICENSE", "DESCRIPTION") ) # example with files structure files_structure <- get_files_structure( gitstats_obj = my_gitstats, pattern = "\\.Rmd", depth = 2L ) # get_files_content() will make use of pulled earlier files structure files_content <- get_files_content( gitstats_obj = my_gitstats ) ## End(Not run)
Pulls file structure for a given repository.
get_files_structure( gitstats_object, pattern = NULL, depth = Inf, cache = TRUE, verbose = is_verbose(gitstats_object), progress = verbose )
get_files_structure( gitstats_object, pattern = NULL, depth = Inf, cache = TRUE, verbose = is_verbose(gitstats_object), progress = verbose )
gitstats_object |
A GitStats object. |
pattern |
An optional regular expression. If defined, it pulls file structure for a repository matching this pattern. |
depth |
An optional integer. Defines level of directories to retrieve
files from. E.g. if set to |
cache |
A logical, if set to |
verbose |
A logical, |
progress |
A logical, by default set to |
A list of vectors.
## Not run: my_gitstats <- 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_structure( gitstats_obj = my_gitstats, pattern = "\\.md" ) ## End(Not run)
## Not run: my_gitstats <- 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_structure( gitstats_obj = my_gitstats, pattern = "\\.md" ) ## End(Not run)
Wrapper over searching repositories by code blobs related to
loading package (library(package)
and require(package)
in all files) or
using it as a dependency (package
in DESCRIPTION
and NAMESPACE
files).
get_R_package_usage( gitstats_object, packages, only_loading = FALSE, split_output = FALSE, cache = TRUE, verbose = is_verbose(gitstats_object) )
get_R_package_usage( gitstats_object, packages, only_loading = FALSE, split_output = FALSE, cache = TRUE, verbose = is_verbose(gitstats_object) )
gitstats_object |
A GitStats object. |
packages |
A character vector, names of R packages to look for. |
only_loading |
A boolean, if |
split_output |
Optional, a boolean. If |
cache |
A logical, if set to |
verbose |
A logical, |
A tibble
or list
of tibbles
depending on split_output
parameter.
## Not run: my_gitstats <- create_gitstats() %>% set_github_host( token = Sys.getenv("GITHUB_PAT"), orgs = c("r-world-devs", "openpharma") ) get_R_package_usage( gitstats_object = my_gitstats, packages = c("purrr", "shiny"), split_output = TRUE ) ## End(Not run)
## Not run: my_gitstats <- create_gitstats() %>% set_github_host( token = Sys.getenv("GITHUB_PAT"), orgs = c("r-world-devs", "openpharma") ) get_R_package_usage( gitstats_object = my_gitstats, packages = c("purrr", "shiny"), split_output = TRUE ) ## End(Not run)
Pull release logs from repositories.
get_release_logs( gitstats_object, since = NULL, until = Sys.Date() + lubridate::days(1), cache = TRUE, verbose = is_verbose(gitstats_object), progress = verbose )
get_release_logs( gitstats_object, since = NULL, until = Sys.Date() + lubridate::days(1), cache = TRUE, verbose = is_verbose(gitstats_object), progress = verbose )
gitstats_object |
A GitStats object. |
since |
A starting date. |
until |
An end date. |
cache |
A logical, if set to |
verbose |
A logical, |
progress |
A logical, by default set to |
A data.frame.
## Not run: my_gitstats <- create_gitstats() %>% set_github_host( token = Sys.getenv("GITHUB_PAT"), orgs = c("r-world-devs", "openpharma") ) get_release_logs(my_gistats, since = "2024-01-01") ## End(Not run)
## Not run: my_gitstats <- create_gitstats() %>% set_github_host( token = Sys.getenv("GITHUB_PAT"), orgs = c("r-world-devs", "openpharma") ) get_release_logs(my_gistats, since = "2024-01-01") ## End(Not run)
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.
get_repos( gitstats_object, add_contributors = TRUE, with_code = NULL, in_files = NULL, with_files = NULL, cache = TRUE, verbose = is_verbose(gitstats_object), progress = verbose )
get_repos( gitstats_object, add_contributors = TRUE, with_code = NULL, in_files = NULL, with_files = NULL, cache = TRUE, verbose = is_verbose(gitstats_object), progress = verbose )
gitstats_object |
A GitStats object. |
add_contributors |
A logical parameter to decide whether to add
information about repositories' contributors to the repositories output
(table). If set to |
with_code |
A character vector, if defined, GitStats will pull repositories with specified code phrases in code blobs. |
in_files |
A character vector of file names. Works when |
with_files |
A character vector, if defined, GitStats will pull repositories with specified files. |
cache |
A logical, if set to |
verbose |
A logical, |
progress |
A logical, by default set to |
A data.frame.
## Not run: 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") ## End(Not run)
## Not run: 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") ## End(Not run)
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).
get_repos_urls( gitstats_object, type = "web", with_code = NULL, in_files = NULL, with_files = NULL, cache = TRUE, verbose = is_verbose(gitstats_object), progress = verbose )
get_repos_urls( gitstats_object, type = "web", with_code = NULL, in_files = NULL, with_files = NULL, cache = TRUE, verbose = is_verbose(gitstats_object), progress = verbose )
gitstats_object |
A GitStats object. |
type |
A character, choose if |
with_code |
A character vector, if defined, GitStats will pull repositories with specified code phrases in code blobs. |
in_files |
A character vector of file names. Works when |
with_files |
A character vector, if defined, GitStats will pull repositories with specified files. |
cache |
A logical, if set to |
verbose |
A logical, |
progress |
A logical, by default set to |
A character vector.
## Not run: 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")) ## End(Not run)
## Not run: 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")) ## End(Not run)
GitStats
storageRetrieves whole or particular data (see storage
parameter)
pulled earlier with GitStats
.
get_storage(gitstats_object, storage = NULL)
get_storage(gitstats_object, storage = NULL)
gitstats_object |
A GitStats object. |
storage |
A character, type of the data you want to get from storage:
|
A list of tibbles (if storage
set to NULL
) or a tibble (if
storage
defined).
## Not run: my_gitstats <- create_gitstats() %>% set_github_host( token = Sys.getenv("GITHUB_PAT"), orgs = c("r-world-devs", "openpharma") ) get_release_logs(my_gistats, since = "2024-01-01") get_repos(my_gitstats) release_logs <- get_storage( gitstats_object = my_gitstats, storage = "release_logs" ) ## End(Not run)
## Not run: my_gitstats <- create_gitstats() %>% set_github_host( token = Sys.getenv("GITHUB_PAT"), orgs = c("r-world-devs", "openpharma") ) get_release_logs(my_gistats, since = "2024-01-01") get_repos(my_gitstats) release_logs <- get_storage( gitstats_object = my_gitstats, storage = "release_logs" ) ## End(Not run)
Get users data
get_users( gitstats_object, logins, cache = TRUE, verbose = is_verbose(gitstats_object) )
get_users( gitstats_object, logins, cache = TRUE, verbose = is_verbose(gitstats_object) )
gitstats_object |
A GitStats object. |
logins |
A character vector of logins. |
cache |
A logical, if set to |
verbose |
A logical, |
A data.frame.
## Not run: my_gitstats <- 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_users(my_gitstats, c("maciekabanas", "marcinkowskak")) ## End(Not run)
## Not run: my_gitstats <- 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_users(my_gitstats, c("maciekabanas", "marcinkowskak")) ## End(Not run)
Is verbose mode switched on
is_verbose(gitstats_object)
is_verbose(gitstats_object)
gitstats_object |
A GitStats object. |
Set GitHub host
set_github_host( gitstats_object, host = NULL, token = NULL, orgs = NULL, repos = NULL, verbose = is_verbose(gitstats_object) )
set_github_host( gitstats_object, host = NULL, token = NULL, orgs = NULL, repos = NULL, verbose = is_verbose(gitstats_object) )
gitstats_object |
A GitStats object. |
host |
A character, optional, URL name of the host. If not passed, a public host will be used. |
token |
A token. |
orgs |
An optional character vector of organisations. If you pass it,
|
repos |
An optional character vector of repositories full names
(organization and repository name, e.g. "r-world-devs/GitStats"). If you
pass it, |
verbose |
A logical, |
If you do not define orgs
and repos
, GitStats
will be set to
scan whole Git platform (such as enterprise version of GitHub or GitLab),
unless it is a public platform. In case of a public one (like GitHub) you
need to define orgs
or repos
as scanning through all organizations may
take large amount of time.
A GitStats
object with added information on host.
## Not run: my_gitstats <- create_gitstats() %>% set_github_host( orgs = c("r-world-devs", "openpharma", "pharmaverse") ) ## End(Not run)
## Not run: my_gitstats <- create_gitstats() %>% set_github_host( orgs = c("r-world-devs", "openpharma", "pharmaverse") ) ## End(Not run)
Set GitLab host
set_gitlab_host( gitstats_object, host = NULL, token = NULL, orgs = NULL, repos = NULL, verbose = is_verbose(gitstats_object) )
set_gitlab_host( gitstats_object, host = NULL, token = NULL, orgs = NULL, repos = NULL, verbose = is_verbose(gitstats_object) )
gitstats_object |
A GitStats object. |
host |
A character, optional, URL name of the host. If not passed, a public host will be used. |
token |
A token. |
orgs |
An optional character vector of organisations. If you pass it,
|
repos |
An optional character vector of repositories full names
(organization and repository name, e.g. "r-world-devs/GitStats"). If you
pass it, |
verbose |
A logical, |
If you do not define orgs
and repos
, GitStats
will be set to
scan whole Git platform (such as enterprise version of GitHub or GitLab),
unless it is a public platform. In case of a public one (like GitHub) you
need to define orgs
or repos
as scanning through all organizations may
take large amount of time.
A GitStats
object with added information on host.
## Not run: my_gitstats <- create_gitstats() %>% set_gitlab_host( token = Sys.getenv("GITLAB_PAT_PUBLIC"), orgs = "mbtests" ) ## End(Not run)
## Not run: my_gitstats <- create_gitstats() %>% set_gitlab_host( token = Sys.getenv("GITLAB_PAT_PUBLIC"), orgs = "mbtests" ) ## End(Not run)
GitStats
Retrieves organizations set or pulled by GitStats
. Especially
helpful when user is scanning whole git platform and wants to have a
glimpse at organizations.
show_orgs(gitstats_object)
show_orgs(gitstats_object)
gitstats_object |
A GitStats object. |
A vector of organizations.
Stop printing messages and output.
verbose_off(gitstats_object)
verbose_off(gitstats_object)
gitstats_object |
A GitStats object. |
A GitStats object.
Print all messages and output.
verbose_on(gitstats_object)
verbose_on(gitstats_object)
gitstats_object |
A GitStats object. |
A GitStats object.