untar: Make behavior similar to GNU or BSD tar

RTEMS untar implementation had problems with overwriting or integrating
archives into existing directory structures. This patch adapts the
behavior to mimic that of a GNU tar or BSD tar and extends the tar01
test to check for the behavior. That is:

* If a directory structure exists, the files from the archive will be
  integrated. Existing files are overwritten.

* If a file exists and the archive contains a directory with the same
  name, the file is removed and a directory is created. In the above
  example: if l1/l2 is a file it will be overwritten with a new
  directory.

* If a directory exists and the archive contains a file with the same
  name, the directory will be replaced if it is empty. If it contains
  files, the result is an error.

* An archive also can contain only a file without the parent
  directories. If in that case one of the parent directories exists as a
  file extracting the archive results in an error. In the example: if
  l1/l2 is a file and the archive doesn't contain the directories but
  only the file l1/l2/x.txt that would be an error.

* In case of an error, it is possible that the archive has been
  partially extracted.

Closes #4568

1 files changed, 37 insertions, 20 deletions

diff --git a/cpukit/libmisc/untar/untar.c b/cpukit/libmisc/untar/untar.c
index a2f09fb99f..8888ab2c57 100644
--- a/cpukit/libmisc/untar/untar.c
+++ b/cpukit/libmisc/untar/untar.c
@@ -126,30 +126,25 @@ Make_Path(const rtems_printer *printer, char *path)
 
     *p = '\0';
     if (p[1] == '\0') {
-      /* Speculatively unlink the last component so that it can be re-created */
-      unlink(path);
       return 0;
     }
 
     if (mkdir(path, S_IRWXU | S_IRWXG | S_IRWXO) != 0) {
-      if (errno == EEXIST || errno == EISDIR) {
+      if (errno == EEXIST) {
+        /* If it exists already: Check whether it is a directory */
         struct stat sb;
-
-        if (stat(path, &sb) != 0) {
+        if (lstat(path, &sb) != 0) {
+          Print_Error(printer, "lstat", path);
+          return -1;
+        } else if (!S_ISDIR(sb.st_mode)) {
+          rtems_printf(printer,
+                       "untar: mkdir: %s: exists but is not a directory\n",
+                       path);
           return -1;
         }
-
-        if (!S_ISDIR(sb.st_mode)) {
-          if (unlink(path) != 0) {
-            Print_Error(printer, "unlink", path);
-            return -1;
-          }
-
-          if (mkdir(path, S_IRWXU | S_IRWXG | S_IRWXO) != 0) {
-            Print_Error(printer, "mkdir (unlink)", path);
-            return -1;
-          }
-        }
+      } else {
+        Print_Error(printer, "mkdir", path);
+        return -1;
       }
     }
 
@@ -206,6 +201,12 @@ Untar_ProcessHeader(
 
   if (Make_Path(ctx->printer, ctx->file_path) != 0) {
     retval = UNTAR_FAIL;
+  } else {
+    /*
+     * Speculatively unlink. This should unlink everything but non-empty
+     * directories or write protected stuff.
+     */
+    unlink(ctx->file_path);
   }
 
   if (ctx->linkflag == SYMTYPE) {
@@ -225,8 +226,22 @@ Untar_ProcessHeader(
     rtems_printf(ctx->printer, "untar: dir: %s\n", ctx->file_path);
     r = mkdir(ctx->file_path, ctx->mode);
     if (r != 0) {
-      Print_Error(ctx->printer, "mkdir", ctx->file_path);
-      retval = UNTAR_FAIL;
+      if (errno == EEXIST) {
+        /* If it exists already: Check whether it is a directory */
+        struct stat sb;
+        if (lstat(ctx->file_path, &sb) != 0) {
+          Print_Error(ctx->printer, "lstat", ctx->file_path);
+          retval = UNTAR_FAIL;
+        } else if (!S_ISDIR(sb.st_mode)) {
+          rtems_printf(ctx->printer,
+                       "untar: mkdir: %s: exists but is not a directory\n",
+                       ctx->file_path);
+          retval = UNTAR_FAIL;
+        }
+      } else {
+        Print_Error(ctx->printer, "mkdir", ctx->file_path);
+        retval = UNTAR_FAIL;
+      }
     }
   }
 
@@ -426,7 +441,9 @@ Untar_FromFile_Print(
        */
 
       if ((out_fd = creat(ctx.file_path, ctx.mode)) == -1) {
-        (void) lseek(fd, SEEK_CUR, 512UL * ctx.nblocks);
+        /* Couldn't create that file. Abort. */
+        retval = UNTAR_FAIL;
+        break;
       } else {
         for (i = 0; i < ctx.nblocks; i++) {
           n = read(fd, bufr, 512);