Update a specific R package and its dependencies

Question

I have around 4000 R packages installed in my system (a server) and most of them are outdated because they were built before R-3.0.0. Now I know

update.pack         


        

Answer 1

My answer builds on Gavin's answer... Note that the original poster, user3175783, asked for a more intelligent version of update.packages(). That function skips installing packages that are already up-to-date. But Gavin's solution installs a package and all its dependencies, whether they are up-to-date or not. I used Gavin's tip of skipping base packages (which are not actually installable), and coded up a solution which also skips up-to-date packages.

The main function is installPackages(). This function and its helpers perform a topological-sort of the dependency tree rooted at a given set of packages. The packages in the resulting list are checked for staleness and installed one by one. Here's some example output:

> remove.packages("tibble")
Removing package from ‘/home/frederik/.local/lib/x86_64/R/packages’
(as ‘lib’ is unspecified)
> installPackages(c("ggplot2","stringr","Rcpp"), dry_run=T)
##  Package  digest  is out of date ( 0.6.9 < 0.6.10 )
Would have installed package  digest 
##  Package  gtable  is up to date ( 0.2.0 )
##  Package  MASS  is up to date ( 7.3.45 )
##  Package  Rcpp  is out of date ( 0.12.5 < 0.12.8 )
Would have installed package  Rcpp 
##  Package  plyr  is out of date ( 1.8.3 < 1.8.4 )
Would have installed package  plyr 
##  Package  stringi  is out of date ( 1.0.1 < 1.1.2 )
Would have installed package  stringi 
##  Package  magrittr  is up to date ( 1.5 )
##  Package  stringr  is out of date ( 1.0.0 < 1.1.0 )
Would have installed package  stringr 
...
##  Package  lazyeval  is out of date ( 0.1.10 < 0.2.0 )
Would have installed package  lazyeval 
##  Package  tibble  is not currently installed, installing
Would have installed package  tibble 
##  Package  ggplot2  is out of date ( 2.1.0 < 2.2.0 )
Would have installed package  ggplot2 

Here's the code, sorry about the length:

library(tools)

# Helper: a "functional" interface depth-first-search
fdfs = function(get.children) {
  rec = function(root) {
    cs = get.children(root);
    out = c();
    for(c in cs) {
      l = rec(c);
      out = c(out, setdiff(l, out));
    }
    c(out, root);
  }
  rec
}

# Entries in the package "Priority" field which indicate the
# package can't be upgraded. Not sure why we would exclude
# recommended packages, since they can be upgraded...
#excl_prio = c("base","recommended")
excl_prio = c("base")

# Find the non-"base" dependencies of a package.
nonBaseDeps = function(packages,
  ap=available.packages(),
  ip=installed.packages(), recursive=T) {

  stopifnot(is.character(packages));
  all_deps = c();
  for(p in packages) {
    # Get package dependencies. Note we are ignoring version
    # information
    deps = package_dependencies(p, db = ap, recursive = recursive)[[1]];
    ipdeps = match(deps,ip[,"Package"])
    # We want dependencies which are either not installed, or not part
    # of Base (e.g. not installed with R)
    deps = deps[is.na(ipdeps) | !(ip[ipdeps,"Priority"] %in% excl_prio)];
    # Now check that these are in the "available.packages()" database
    apdeps = match(deps,ap[,"Package"])
    notfound = is.na(apdeps)
    if(any(notfound)) {
      notfound=deps[notfound]
      stop("Package ",p," has dependencies not in database: ",paste(notfound,collapse=" "));
    }
    all_deps = union(deps,all_deps);
  }
  all_deps
}

# Return a topologically-sorted list of dependencies for a given list
# of packages. The output vector contains the "packages" argument, and
# recursive dependencies, with each dependency occurring before any
# package depending on it.
packageOrderedDeps = function(packages, ap=available.packages()) {

  # get ordered dependencies
  odeps = sapply(packages,
    fdfs(function(p){nonBaseDeps(p,ap=ap,recursive=F)}))
  # "unique" preserves the order of its input
  odeps = unique(unlist(odeps));

  # sanity checks
  stopifnot(length(setdiff(packages,odeps))==0);
  seen = list();
  for(d in odeps) {
    ddeps = nonBaseDeps(d,ap=ap,recursive=F)
    stopifnot(all(ddeps %in% seen));
    seen = c(seen,d);
  }

  as.vector(odeps)
}

# Checks if a package is up-to-date. 
isPackageCurrent = function(p,
  ap=available.packages(),
  ip=installed.packages(),
  verbose=T) {

    if(verbose) msg = function(...) cat("## ",...)
    else msg = function(...) NULL;

    aprow = match(p, ap[,"Package"]);
    iprow = match(p, ip[,"Package"]);
    if(!is.na(iprow) && (ip[iprow,"Priority"] %in% excl_prio)) {
      msg("Package ",p," is a ",ip[iprow,"Priority"]," package\n");
      return(T);
    }
    if(is.na(aprow)) {
      stop("Couldn't find package ",p," among available packages");
    }
    if(is.na(iprow)) {
      msg("Package ",p," is not currently installed, installing\n");
      F;
    } else {
      iv = package_version(ip[iprow,"Version"]);
      av = package_version(ap[aprow,"Version"]);
      if(iv < av) {
        msg("Package ",p," is out of date (",
            as.character(iv),"<",as.character(av),")\n");
        F;
      } else {
        msg("Package ",p," is up to date (",
            as.character(iv),")\n");
        T;
      }
    }
}

# Like install.packages, but skips packages which are already
# up-to-date. Specify dry_run=T to just see what would be done.
installPackages =
    function(packages,
             ap=available.packages(), dry_run=F,
             want_deps=T) {

  stopifnot(is.character(packages));

  ap=tools:::.remove_stale_dups(ap)
  ip=installed.packages();
  ip=tools:::.remove_stale_dups(ip)

  if(want_deps) {
    packages = packageOrderedDeps(packages, ap);
  }

  for(p in packages) {
    curr = isPackageCurrent(p,ap,ip);
    if(!curr) {
      if(dry_run) {
        cat("Would have installed package ",p,"\n");
      } else {
        install.packages(p,dependencies=F);
      }
    }
  }
}

# Convenience function to make sure all the libraries we have loaded
# in the current R session are up-to-date (and to update them if they
# are not)
updateAttachedLibraries = function(dry_run=F) {
  s=search();
  s=s[grep("^package:",s)];
  s=gsub("^package:","",s)
  installPackages(s,dry_run=dry_run);
}