Hello, sorry for not being clear enough.
My problem is represented with the following code, running on OSX: mkdir ~/test ln -s ~/test ~/testlink touch ~/test/foo Rscript -e 'Sys.readlink(c("~/test/foo", "~/testlink/foo")); normalizePath(c("~/test/foo","~/testlink/foo"))' I expected `Sys.readlink` to show the same output as `normalizePath`. Also, I think the readlink.h imported to R to be the same as from the system's `readlink` command, thus mimicking the command line difference. Am I wrong with the latter? Anyway, the behaviour is irritating, thus the request to at least mention `normalizePath` in the Rd of `Sys.readlink`. Best, Sven > On 29 Feb 2016, at 11:44, Mikko Korpela <mikko.korp...@aalto.fi> wrote: > > On 29.02.2016 10:34, Sven E. Templer wrote: >> Hello together, >> >> the function `Sys.readlink` uses the system's readlink command to resolve >> symlink paths. On OSX/BSD the command has a different meaning than on Linux >> [1]. >> >> There exists the tool 'realpath', which seems suitable for the task, at >> least applied at the command line level [2]. It is used in `normalizePath`. >> >> I suggest (at least the latter) to >> * use realpath instead readlink within Sys.readlink (do_readlink -> >> do_normalizepath) >> * link to `normalizePath` in the Rd document, eventually mentioning the >> difference >> >> Many thanks, >> Sven >> >> [1] see >> https://www.freebsd.org/cgi/man.cgi?query=readlink >> vs >> http://linux.die.net/man/1/readlink >> >> [2] >> https://www.freebsd.org/cgi/man.cgi?query=realpath >> http://linux.die.net/man/1/realpath > > What do you mean by "different meaning"? How are the command line tools > [1] relevant when R is using the C function 'readlink'? > > http://pubs.opengroup.org/onlinepubs/9699919799/functions/readlink.html > https://www.freebsd.org/cgi/man.cgi?query=readlink&sektion=2 > http://man7.org/linux/man-pages/man2/readlink.2.html > > -- > Mikko Korpela > Aalto University School of Science > Department of Computer Science ______________________________________________ R-devel@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-devel