Licenses

All that legal stuff…
Author

Valerie Han

Published

March 9, 2023

Frontmatter check Render rmarkdown

Prompt:

The DESCRIPTION file of a package contains the package’s meta information. Most of the fields in this file are quite straight forward: author, version number, and a short package description. When you call library(help="<package name>") for package <package name> you can see the contents of the DESCRIPTION file for that package (and some parts of the NAMESPACE file).

Read through Colin Fay’s (short) book on Licensing R

Write a blog post addressing the following questions:

Under what license does R operate? What is the license for ggplot2?

R uses a GNU General Public License (either Version 2 or Version 3). ggplot2 uses an MIT license.

What are the dependencies of the package you made?

Read through chapter 5.2 of Licensing R. Combine and adjust the code pieces to create the dependencies for a package that is on github rather than CRAN. (Don’t forget about the package desc.) What dependencies does the package have that you created for Lab-3? Which licenses are involved? Are all of these dependencies required? Elaborate.

The dependecies are dplyr, lubridate, purrr, R (>= 2.10), readr, tabulizer, and tibble.

They use MIT licenses for the most part with one GPL (\(\geq 2\)) license. All these dependencies are required for the package as it’s currently written because we use functions from these packages in our package’s functions.

# code adapted from section 5.2 of https://thinkr-open.github.io/licensing-r/practical.html

library(tidyr)
library(dplyr)

pkgdb <- tools::CRAN_package_db()

extract_from_cran_db <- function(deps, pkgdb){
  pkgdb %>%
    as_tibble(.name_repair = "universal") %>%
    filter(Package %in% deps) 
}

# copied from DESCRIPTION file
deps <- c("dplyr",
          "lubridate",
          "purrr",
          "readr",
          "tabulizer", # has MIT license (checked its github repo)
          "tibble",
          "utils")

deps <- extract_from_cran_db(deps, pkgdb)

deps %>%
  count(
    License
  )

Under which license should this blog post be published? Make sure that you are using an appropriate license. (You can change the current licenses with the help of commands from the use_license_XXX family in the usethis package)

This blog post should be published under the same license as the book (CC BY-NC-SA 4.0 license) since we use modified code from the book. (Note that the libraries we use for the code are all MIT-licensed.)

deps <- c("dplyr",
          "tidyr",
          "tools")

deps <- extract_from_cran_db(deps, pkgdb)

deps %>%
  count(
    License
  )

Can I publish an R package on CRAN under an MIT license when I have a dependency on a package that is licensed under GPL-3?

When confronted with the above question, ChatGPT gave two – quite different – responses, as shown below. The main point in both responses is ‘your package may be considered derivative work’. At the specific problem of the package developed for Lab 3, what is your opinion about potential copyright infringements when releasing the package with an MIT license? Make sure to take the relevant passage in Colin Fay’s book under consideration.

The legal implications of publishing an R package on CRAN under an MIT license while having a dependency on a package that is licensed under GPL-3 are complex and can vary depending on the specific circumstances. It is always advisable to seek legal advice from a licensed attorney if you have any doubts or concerns about licensing issues.

However, in general, it is possible to publish an R package on CRAN under an MIT license when you have a dependency on a package that is licensed under GPL-3. This is because the MIT license is a permissive open-source license that allows for more flexibility in how the software can be used and distributed, and it is generally considered compatible with the GPL-3 license.

That being said, if your package depends on a GPL-3-licensed package, your package may be considered a derivative work and therefore subject to the terms of the GPL-3 license. This means that if you distribute your package, you may need to also distribute the source code for your package under the GPL-3 license or a compatible license, and you may need to ensure that the requirements of the GPL-3 license are met for the entire distribution, including any dependencies.

It is also worth noting that the R community has its own guidelines and recommendations for package licensing, and it is important to comply with these guidelines if you want to publish your package on CRAN. The CRAN Repository Policy states that packages should have a "permissive" or "GPL-compatible" license, but does not explicitly require that packages use the GPL license or any other specific license.

In summary, while it is possible to publish an R package on CRAN under an MIT license while having a dependency on a package that is licensed under GPL-3, it is important to understand the implications of the different licenses and to ensure that you comply with any applicable guidelines and recommendations from the R community.

After harping a bit on copyright infringement in general, ChatGPT changed its response to

Technically, you can publish an R package on CRAN under an MIT license when you have a dependency on a package that is licensed under GPL-3, but doing so would not be compliant with the terms of the GPL-3 license.

The GPL-3 license is a strong copyleft license that requires derivative works to be released under the same license. If your package depends on a GPL-3-licensed package, your package may be considered a derivative work and therefore must be licensed under the GPL-3 license or a compatible license.

The MIT license, on the other hand, is a permissive license that allows for more flexibility in how the software is used and distributed. However, it is not compatible with the GPL-3 license, and therefore cannot be used for derivative works of GPL-3-licensed software.

Publishing an R package on CRAN under an MIT license when you have a dependency on a package that is licensed under GPL-3 would be a licensing violation, and could potentially result in legal action or other consequences. It is important to comply with the licensing requirements of all dependencies in your package to avoid any legal issues.

The ‘harping’ questions:

  • Is it legal to publish an R package on CRAN under an MIT license when I have a dependency on a package that is licensed under GPL-3?

  • Is it illegal to publish an R package on CRAN under an MIT license when I have a dependency on a package that is licensed under GPL-3?

  • Is it a copyright infringement to publish an R package on CRAN under an MIT license when I have a dependency on a package that is licensed under GPL-3?

  • Can I publish an R package on CRAN under an MIT license when I have a dependency on a package that is licensed under GPL-3 without infringing copyright?

I believe the best route to take would be to publish under the more restrictive license to be safe because it seems that such a dependency is in the “borderline case” of being considered a “combined work.” The argument in the book is that we have to install the dependent packages to run our package’s functions and therefore we would be violating the GPL license. However, it seems that by using an MIT license, we would be saying our code is fine for people to use, so publishing our package under an MIT license would still allow people to use our functions that don’t depend on those GPL-licensed packages or modify code from our package to write their own functions. Essentially, I think the applying the MIT license to our package could still increase the utility for others compared to publishing with the GPL license.

Submission

Write answers to the questions directly into the file README.Rmd. Push the blog post to your blog-7 repo. Make sure that all of the checks are passing.