CXX-1506 Don't checksum GridFS files

The GridFS spec has deprecated the checksum feature, and FIPS compliance
prohibits MD5.

Author: ajdavis

THIRD-PARTY-NOTICES

@@ -36,27 +36,3 @@ distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
 WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
 License for the specific language governing permissions and limitations
 under the License.
-
-3) License notice for Aladdin MD5
----------------------------------
-
-Copyright (C) 1999, 2002 Aladdin Enterprises.  All rights reserved.
-
-This software is provided 'as-is', without any express or implied
-warranty.  In no event will the authors be held liable for any damages
-arising from the use of this software.
-
-Permission is granted to anyone to use this software for any purpose,
-including commercial applications, and to alter it and redistribute it
-freely, subject to the following restrictions:
-
-1. The origin of this software must not be misrepresented; you must not
-   claim that you wrote the original software. If you use this software
-   in a product, an acknowledgment in the product documentation would be
-   appreciated but is not required.
-2. Altered source versions must be plainly marked as such, and must not be
-   misrepresented as being the original software.
-3. This notice may not be removed or altered from any source distribution.
-
-L. Peter Deutsch
-ghost@aladdin.com

src/mongocxx/CMakeLists.txt

@@ -107,7 +107,6 @@ set(mongocxx_sources
     result/insert_one.cpp
     result/replace_one.cpp
     result/update.cpp
-    third_party/md5.cpp
     uri.cpp
     validation_criteria.cpp
     write_concern.cpp

src/mongocxx/gridfs/private/uploader.hh

@@ -17,7 +17,6 @@
 #include <string>
 #include <vector>
 
-#include <mongocxx/third_party/md5.h>
 #include <bsoncxx/stdx/make_unique.hpp>
 #include <bsoncxx/string/to_string.hpp>
 #include <mongocxx/gridfs/uploader.hpp>
@@ -45,9 +44,7 @@ class uploader::impl {
           filename{bsoncxx::string::to_string(filename)},
           files{std::move(files)},
           metadata{std::move(metadata)},
-          result{std::move(result)} {
-        md5_init(&md5);
-    }
+          result{std::move(result)} {}
 
     // Bytes that have been written for the current chunk.
     std::unique_ptr<std::uint8_t[]> buffer;
@@ -76,9 +73,6 @@ class uploader::impl {
     // The collection to which the files document will be written.
     collection files;
 
-    // Keeps track of the md5 hash of the file.
-    md5_state_t md5;
-
     // User-specified metadata for the file.
     stdx::optional<bsoncxx::document::value> metadata;
 

src/mongocxx/gridfs/uploader.cpp

@@ -111,18 +111,6 @@ result::gridfs::upload uploader::close() {
     file.append(kvp("length", bytes_uploaded + leftover));
     file.append(kvp("chunkSize", _get_impl().chunk_size));
     file.append(kvp("uploadDate", bsoncxx::types::b_date{std::chrono::system_clock::now()}));
-
-    md5_byte_t md5_hash_array[16];
-    md5_finish(&_get_impl().md5, md5_hash_array);
-
-    std::stringstream md5_hash;
-
-    for (auto i = 0; i < 16; ++i) {
-        md5_hash << std::setfill('0') << std::setw(2) << std::hex
-                 << static_cast<int>(md5_hash_array[i]);
-    }
-
-    file.append(kvp("md5", md5_hash.str()));
     file.append(kvp("filename", _get_impl().filename));
 
     if (_get_impl().metadata) {
@@ -175,9 +163,6 @@ void uploader::finish_chunk() {
                                   static_cast<std::uint32_t>(bytes_in_chunk),
                                   _get_impl().buffer.get()};
 
-    md5_append(
-        &_get_impl().md5, _get_impl().buffer.get(), static_cast<std::int32_t>(bytes_in_chunk));
-
     chunk.append(kvp("data", data));
     _get_impl().chunks_collection_documents.push_back(chunk.extract());
 

src/mongocxx/private/md5.hh

@@ -65,6 +65,10 @@ void validate_gridfs_file(database db,
     REQUIRE(files_doc->view()["filename"].get_utf8().value ==
             stdx::string_view(expected_file_name));
 
+    // md5 is deprecated in GridFS, we don't include it:
+    // https://github.com/mongodb/specifications/blob/master/source/gridfs/gridfs-spec.rst
+    REQUIRE(!files_doc->view()["md5"]);
+
     std::int32_t index = 0;
 
     for (auto&& chunks_doc :

src/mongocxx/test/gridfs/bucket.cpp

@@ -160,10 +160,6 @@ void compare_collections(database db) {
         REQUIRE(actual["chunkSize"]);
         REQUIRE(expected["chunkSize"].get_int32().value == actual["chunkSize"].get_int32().value);
 
-        REQUIRE(expected["md5"]);
-        REQUIRE(actual["md5"]);
-        REQUIRE(expected["md5"].get_utf8().value == actual["md5"].get_utf8().value);
-
         REQUIRE(expected["filename"]);
         REQUIRE(actual["filename"]);
         REQUIRE(expected["filename"].get_utf8().value == actual["filename"].get_utf8().value);