Add error handling for gzipped file decompression and external command failures in fread() (#7097)

* improve error handling in fread() for cmd exe and decompression

* trailing ws

* added tests

* Update test no.

* more crptd file in 2nd test

* improved error mssg in 2nd test

* enhance test 2

* explained meaning of these numbers

* wrng instead of error in test 2

* also catch warning; clean-up

* windows-only warning

---------

Co-authored-by: Michael Chirico <[email protected]>

Author: Mukulyadav2004

R/fread.R

@@ -70,9 +70,13 @@ yaml=FALSE, tmpdir=tempdir(), tz="UTC")
     }
   }
   if (!is.null(cmd)) {
-    (if (.Platform$OS.type == "unix") system else shell)(paste0('(', cmd, ') > ', tmpFile<-tempfile(tmpdir=tmpdir)))
-    file = tmpFile
+    tmpFile = tempfile(tmpdir=tmpdir)
     on.exit(unlink(tmpFile), add=TRUE)
+    status = (if (.Platform$OS.type == "unix") system else shell)(paste0('(', cmd, ') > ', tmpFile))
+    if (status != 0) {
+      stopf("External command failed with exit code %d. This can happen when the disk is full in the temporary directory ('%s'). See ?fread for the tmpdir argument.", status, tmpdir)
+    }
+    file = tmpFile
   }
   if (!is.null(file)) {
     if (!is.character(file) || length(file)!=1L)
@@ -116,9 +120,14 @@ yaml=FALSE, tmpdir=tempdir(), tz="UTC")
       if (!requireNamespace("R.utils", quietly = TRUE))
         stopf("To read %s files directly, fread() requires 'R.utils' package which cannot be found. Please install 'R.utils' using 'install.packages('R.utils')'.", if (w<=2L || gzsig) "gz" else "bz2") # nocov
       FUN = if (w<=2L || gzsig) gzfile else bzfile
-      R.utils::decompressFile(file, decompFile<-tempfile(tmpdir=tmpdir), ext=NULL, FUN=FUN, remove=FALSE)   # ext is not used by decompressFile when destname is supplied, but isn't optional
-      file = decompFile   # don't use 'tmpFile' symbol again, as tmpFile might be the http://domain.org/file.csv.gz download
+      decompFile = tempfile(tmpdir=tmpdir)
       on.exit(unlink(decompFile), add=TRUE)
+      tryCatch({
+        R.utils::decompressFile(file, decompFile, ext=NULL, FUN=FUN, remove=FALSE)   # ext is not used by decompressFile when destname is supplied, but isn't optional
+      }, error = function(e) {
+        stopf("R.utils::decompressFile failed to decompress file '%s':\n  %s\n. This can happen when the disk is full in the temporary directory ('%s'). See ?fread for the tmpdir argument.", file, conditionMessage(e), tmpdir)
+      })
+      file = decompFile   # don't use 'tmpFile' symbol again, as tmpFile might be the http://domain.org/file.csv.gz download
     }
     file = enc2native(file) # CfreadR cannot handle UTF-8 if that is not the native encoding, see #3078.
 

inst/tests/tests.Rraw

@@ -21215,3 +21215,16 @@ test(2319.1, !is.null(attr(dt_get, ".internal.selfref")))
 dt_get0 = data.frame(a = 1:3, b = letters[1:3])
 setDT(get0("dt_get0"))
 test(2319.2, !is.null(attr(dt_get0, ".internal.selfref")))
+
+# Improved fread error handling for cmd exe and decompression #5415
+test(2320.1, fread(cmd="false"), error="External command failed with exit code", warning = if (.Platform$OS.type=="windows") "execution failed")
+
+if (test_R.utils) local({
+  tmp <- tempfile(fileext=".gz")
+  file.create(tmp); on.exit(unlink(tmp))
+  local({
+    conn <- file(tmp, 'wb'); on.exit(close(conn))
+    writeBin(as.raw(c(31L, 139L)), conn) # Gzip header magic numbers to trigger that read path
+  })
+  test(2320.2, fread(tmp), error="R.utils::decompressFile failed to decompress", warning="invalid")
+})