Removes all valid metadata (.yml files) from the path when they don't
have accompanying data (.tsv file). Invalid metadata triggers a warning
without removing the metadata file.
Use this function with caution since it will remove all valid metadata files
without asking for confirmation. We strongly recommend to use this
function on files under version control. See
vignette("workflow", package = "git2rdata") for some examples on how to use
this.
Usage
prune_meta(root = ".", path = NULL, recursive = TRUE, ...)
# S3 method for class 'git_repository'
prune_meta(root, path = NULL, recursive = TRUE, ..., stage = FALSE)Arguments
- root
The root of a project. Can be a file path or a
git-repository. Defaults to the current working directory (".").- path
the directory in which to clean all the data files. The directory is relative to
root.- recursive
remove files in subdirectories too.
- ...
parameters used in some methods
- stage
stage the changes after removing the files. Defaults to
FALSE.
See also
Other storage:
display_metadata(),
list_data(),
read_vc(),
relabel(),
rename_variable(),
rm_data(),
update_metadata(),
verify_vc(),
write_vc()
Examples
## on file system
# create a directory
root <- tempfile("git2rdata-")
dir.create(root)
# store a dataframe as git2rdata object. Capture the result to minimise
# screen output
junk <- write_vc(iris[1:6, ], "iris", root, sorting = "Sepal.Length")
# write a standard tab separate file (non git2rdata object)
write.table(iris, file = file.path(root, "standard.tsv"), sep = "\t")
# write a YAML file
yml <- list(
authors = list(
"Research Institute for Nature and Forest" = list(
href = "https://www.inbo.be/en")))
yaml::write_yaml(yml, file = file.path(root, "_pkgdown.yml"))
# list the git2rdata objects
list_data(root)
#> [1] "iris.tsv"
# list the files
list.files(root, recursive = TRUE)
#> [1] "_pkgdown.yml" "iris.tsv" "iris.yml" "standard.tsv"
# remove all .tsv files from valid git2rdata objects
rm_data(root, path = ".")
# check the removal of the .tsv file
list.files(root, recursive = TRUE)
#> [1] "_pkgdown.yml" "iris.yml" "standard.tsv"
list_data(root)
#> character(0)
# remove dangling git2rdata metadata files
prune_meta(root, path = ".")
#> Warning: Invalid metadata files found. See ?is_git2rmeta():
#> _pkgdown.yml
# check the removal of the metadata
list.files(root, recursive = TRUE)
#> [1] "_pkgdown.yml" "standard.tsv"
list_data(root)
#> character(0)
## on git repo
# initialise a git repo using git2r
repo_path <- tempfile("git2rdata-repo-")
dir.create(repo_path)
repo <- git2r::init(repo_path)
git2r::config(repo, user.name = "Alice", user.email = "alice@example.org")
# store a dataframe
write_vc(iris[1:6, ], "iris", repo, sorting = "Sepal.Length", stage = TRUE)
#> 09d5bfd6a65e682a4ca030c766348180861568c8
#> "iris.tsv"
#> 0d434e56d22a710c99c5b912e8624d52abd41aaf
#> "iris.yml"
# check that the dataframe is stored
status(repo)
#> Staged changes:
#> New: iris.tsv
#> New: iris.yml
#>
list_data(repo)
#> [1] "iris.tsv"
# commit the current version and check the git repo
commit(repo, "add iris data", session = TRUE)
#> [4a80e15] 2024-11-05: add iris data
status(repo)
#> working directory clean
# remove the data files from the repo
rm_data(repo, path = ".")
# check the removal
list_data(repo)
#> character(0)
status(repo)
#> Unstaged changes:
#> Deleted: iris.tsv
#>
# remove dangling metadata
prune_meta(repo, path = ".")
# check the removal
list_data(repo)
#> character(0)
status(repo)
#> Unstaged changes:
#> Deleted: iris.tsv
#> Deleted: iris.yml
#>