just-mr fetch: Fix exception on fetched data hash mismatch

After successfully fetching data over the network for an archive,
if the optional checksums are not provided, the code will throw if
there is a mismatch between the hash of the fetched data stream
and the provided content hash.

This commit fixes the issue by adding an additional check which
properly handles the possible mismatch.

(cherry-picked from 9acaa7f60c88c97f58b757ffb6ce206f3f2953a2)

1 files changed, 11 insertions, 3 deletions

diff --git a/src/other_tools/ops_maps/content_cas_map.cpp b/src/other_tools/ops_maps/content_cas_map.cpp
index 4a25b15c..2d1b0de7 100644
--- a/src/other_tools/ops_maps/content_cas_map.cpp
+++ b/src/other_tools/ops_maps/content_cas_map.cpp
@@ -120,14 +120,22 @@ auto CreateContentCASMap(JustMR::PathsPtr const& just_mr_paths,
         }
         // add the fetched data to CAS
         auto path = JustMR::Utils::AddToCAS(*data);
-        // check one last time if content is in CAS now
+        // check that storing the fetched data succeeded
         if (not path) {
-            (*logger)(fmt::format("Failed to fetch a file with id {} from {}",
-                                  key.content,
+            (*logger)(fmt::format("Failed to store fetched content from {}",
                                   key.fetch_url),
                       /*fatal=*/true);
             return;
         }
+        // check that the data we stored actually produces the requested digest
+        if (not cas.BlobPath(digest, /*is_executable=*/false)) {
+            (*logger)(fmt::format(
+                          "Content {} was not found at given fetch location {}",
+                          key.content,
+                          key.fetch_url),
+                      /*fatal=*/true);
+            return;
+        }
         JustMRProgress::Instance().TaskTracker().Stop(key.origin);
         (*setter)(true);
     };