Dependency filters for production

DESCRIPTION

@@ -29,6 +29,7 @@ Depends:
   R (>= 3.5.0)
 Imports:
   gh,
+  igraph,
   jsonlite,
   nanonext,
   pkgsearch,

NAMESPACE

@@ -6,6 +6,7 @@ export(assert_package)
 export(assert_release_exists)
 export(get_current_versions)
 export(issues_checks)
+export(issues_dependencies)
 export(issues_descriptions)
 export(issues_versions)
 export(meta_checks)
@@ -16,6 +17,10 @@ export(review_pull_request)
 export(review_pull_requests)
 export(try_message)
 importFrom(gh,gh)
+importFrom(igraph,V)
+importFrom(igraph,graph)
+importFrom(igraph,neighbors)
+importFrom(igraph,subcomponent)
 importFrom(jsonlite,parse_json)
 importFrom(jsonlite,read_json)
 importFrom(jsonlite,stream_in)

R/issues_dependencies.R

@@ -0,0 +1,72 @@
+#' @title Report package dependency issues
+#' @export
+#' @family issues
+#' @description Flag packages which have issues in their strong dependencies
+#'   (`Imports:`, `Depends:`, and `LinkingTo:` in the `DESCRIPTION`.)
+#'   These include indirect/upstream dependencies, as well, not just
+#'   the explicit mentions in the `DESCRIPTION` file.
+#' @inheritSection record_issues Package issues
+#' @return A nested list of problems triggered by dependencies.
+#'   The names of top-level elements are packages affected downstream.
+#'   The value of each top-level element is a list whose names are
+#    packages at the source of a problem upstream.
+#'   Each element of this inner list is a character
+#'   vector of relevant dependencies of the downstream package.
+#'
+#'   For example, consider a linear dependency graph where `crew.cluster`
+#'   depends on `crew`, `crew` depends on `mirai`, and
+#'   `mirai` depends on `nanonext`. We represent the graph like this:
+#'      `nanonext -> mirai -> crew -> crew.cluster`.
+#'   If `nanonext` has an issue, then [issues_dependencies()] returns
+#'   `list(crew.cluster = list(nanonext = "crew"), ...)`, where `...`
+#'   stands for additional named list entries. From this list, we deduce
+#'   that `nanonext` is causing an issue affecting `crew.cluster` through
+#'   the direct dependency on `crew`.
+#'
+#'   The choice in output format from [issues_dependencies()] allows package
+#'   maintainers to more easily figure out which direct dependencies
+#'   are contributing issues and drop those direct dependencies if necessary.
+#' @param packages Character vector of names of packages with other issues.
+#' @param meta A data frame with R-universe package check results
+#'   returned by [meta_checks()].
+#' @examples
+#'   meta <- meta_packages(repo = "https://wlandau.r-universe.dev")
+#'   issues_dependencies(packages = character(0L), meta = meta)
+#'   issues_dependencies(packages = "crew.aws.batch", meta = meta)
+#'   issues_dependencies(packages = "nanonext", meta = meta)
+#'   issues_dependencies(packages = "crew", meta = meta)
+#'   issues_dependencies(packages = c("crew", "mirai"), meta = meta)
+issues_dependencies <- function(packages, meta) {
+  graph <- issues_dependencies_graph(meta)
+  vertices <- names(igraph::V(graph))
+  issues <- list()
+  for (package in intersect(packages, vertices)) {
+    revdeps <- names(igraph::subcomponent(graph, v = package, mode = "out"))
+    revdeps <- setdiff(revdeps, package)
+    for (revdep in revdeps) {
+      neighbors <- names(igraph::neighbors(graph, v = revdep, mode = "in"))
+      issues[[revdep]][[package]] <- intersect(neighbors, revdeps)
+    }
+  }
+  issues
+}
+
+issues_dependencies_graph <- function(meta) {
+  repo_packages <- meta$package
+  repo_dependencies <- meta[["_dependencies"]]
+  edge_list <- list()
+  for (index in seq_len(nrow(meta))) {
+    package <- .subset2(repo_packages, index)
+    all <- .subset2(repo_dependencies, index)
+    packages <- .subset2(all, "package")
+    role <- .subset2(all, "role")
+    strong <- packages[role %in% c("Depends", "Imports", "LinkingTo")]
+    strong <- intersect(setdiff(unique(strong), "R"), repo_packages)
+    edges <- rep(strong, each = 2L)
+    if (length(edges) >= 2L) {
+      edges[seq(from = 2L, to = length(edges), by = 2L)] <- package
+      edge_list[[index]] <- edges
+    }
+  }
+  igraph::graph(edges = unlist(edge_list))
+}

R/package.R

@@ -1,4 +1,5 @@
 #' @importFrom gh gh
+#' @importFrom igraph graph neighbors subcomponent V
 #' @importFrom jsonlite parse_json read_json stream_in write_json
 #' @importFrom nanonext ncurl parse_url status_code
 #' @importFrom pkgsearch cran_package

R/record_issues.R

@@ -66,8 +66,15 @@ record_issues <- function(
   issues <- list() |>
     add_issues(issues_checks(meta = checks), "checks") |>
     add_issues(issues_descriptions(meta = packages), "descriptions") |>
-    add_issues(issues_versions(versions = versions), "versions") |>
-    overwrite_issues(output = output, today = today)
+    add_issues(issues_versions(versions = versions), "versions")
+  issues <- issues |>
+    add_issues(issues_dependencies(names(issues), packages), "dependencies")
+  overwrite_issues(
+    issues = issues,
+    output = output,
+    today = today,
+    packages = packages
+  )
   invisible()
 }
 
@@ -78,15 +85,15 @@ add_issues <- function(total, subset, category) {
   total
 }
 
-overwrite_issues <- function(issues, output, today) {
-  packages <- list.files(output)
+overwrite_issues <- function(issues, output, today, packages) {
+  with_issues <- list.files(output)
   dates <- lapply(
-    X = packages,
+    X = with_issues,
     FUN = function(path) {
       jsonlite::read_json(file.path(output, path), simplifyVector = TRUE)$date
     }
   )
-  names(dates) <- packages
+  names(dates) <- with_issues
   unlink(output, recursive = TRUE)
   dir.create(output)
   lapply(
@@ -95,7 +102,8 @@ overwrite_issues <- function(issues, output, today) {
     issues = issues,
     output = output,
     today = today,
-    dates = dates
+    dates = dates,
+    packages = packages
   )
 }
 
@@ -104,10 +112,14 @@ overwrite_package_issues <- function(
   issues,
   output,
   today,
-  dates
+  dates,
+  packages
 ) {
   path <- file.path(output, package)
   issues[[package]]$date <- dates[[package]] %||% today
+  index <- packages$package == package
+  issues[[package]]$version <- packages[["version"]][index]
+  issues[[package]]$remote_hash <- packages[["remotesha"]][index]
   jsonlite::write_json(
     x = issues[[package]],
     path = file.path(output, package),

_pkgdown.yml

@@ -16,6 +16,7 @@ reference:
 - title: Check issues
   contents:
   - issues_checks
+  - issues_dependencies
   - issues_descriptions
   - issues_versions
 - title: Record issues