MetricsService: Send a hash of the UMA log in a header.

chrome/browser/metrics/metrics_log_serializer.cc

 // Copyright (c) 2012 The Chromium Authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
 
 #include "chrome/browser/metrics/metrics_log_serializer.h"
 
+#include <string>
+
 #include "base/base64.h"
 #include "base/md5.h"
 #include "base/metrics/histogram.h"
 #include "base/prefs/pref_service.h"
 #include "chrome/browser/browser_process.h"
 #include "chrome/browser/prefs/scoped_user_pref_update.h"
 #include "chrome/common/pref_names.h"
 
 namespace {
 
@@ skipping 28 matching lines @@
   return status;
 }
 
 }  // namespace
 
 
 MetricsLogSerializer::MetricsLogSerializer() {}
 
 MetricsLogSerializer::~MetricsLogSerializer() {}
 
-void MetricsLogSerializer::SerializeLogs(const std::vector<std::string>& logs,
-                                         MetricsLogManager::LogType log_type) {
+void MetricsLogSerializer::SerializeLogs(
+    const std::vector<MetricsLogManager::SerializedLog>& logs,
+    MetricsLogManager::LogType log_type) {
   PrefService* local_state = g_browser_process->local_state();
   DCHECK(local_state);
   const char* pref = NULL;
   size_t store_length_limit = 0;
   switch (log_type) {
     case MetricsLogManager::INITIAL_LOG:
       pref = prefs::kMetricsInitialLogs;
       store_length_limit = kInitialLogsPersistLimit;
       break;
     case MetricsLogManager::ONGOING_LOG:
       pref = prefs::kMetricsOngoingLogs;
       store_length_limit = kOngoingLogsPersistLimit;
       break;
     case MetricsLogManager::NO_LOG:
       NOTREACHED();
       return;
   };
 
   ListPrefUpdate update(local_state, pref);
   WriteLogsToPrefList(logs, store_length_limit, kStorageByteLimitPerLogType,
                       update.Get());
 }
 
-void MetricsLogSerializer::DeserializeLogs(MetricsLogManager::LogType log_type,
-                                           std::vector<std::string>* logs) {
+void MetricsLogSerializer::DeserializeLogs(
+    MetricsLogManager::LogType log_type,
+    std::vector<MetricsLogManager::SerializedLog>* logs) {
   DCHECK(logs);
   PrefService* local_state = g_browser_process->local_state();
   DCHECK(local_state);
 
   const char* pref;
   if (log_type == MetricsLogManager::INITIAL_LOG)
     pref = prefs::kMetricsInitialLogs;
   else
     pref = prefs::kMetricsOngoingLogs;
 
   const ListValue* unsent_logs = local_state->GetList(pref);
   ReadLogsFromPrefList(*unsent_logs, logs);
 }
 
 // static
 void MetricsLogSerializer::WriteLogsToPrefList(
-    const std::vector<std::string>& local_list,
+    const std::vector<MetricsLogManager::SerializedLog>& local_list,
     size_t list_length_limit,
     size_t byte_limit,
     base::ListValue* list) {
   // One of the limit arguments must be non-zero.
   DCHECK(list_length_limit > 0 || byte_limit > 0);
 
   list->Clear();
   if (local_list.size() == 0)
     return;
 
   size_t start = 0;
   // If there are too many logs, keep the most recent logs up to the length
   // limit, and at least to the minimum number of bytes.
   if (local_list.size() > list_length_limit) {
     start = local_list.size();
     size_t bytes_used = 0;
-    for (std::vector<std::string>::const_reverse_iterator
+    for (std::vector<MetricsLogManager::SerializedLog>::const_reverse_iterator
          it = local_list.rbegin(); it != local_list.rend(); ++it) {
-      size_t log_size = it->length();
+      size_t log_size = it->log_text.length();
       if (bytes_used >= byte_limit &&
           (local_list.size() - start) >= list_length_limit)
         break;
       bytes_used += log_size;
       --start;
     }
   }
   DCHECK_LT(start, local_list.size());
   if (start >= local_list.size())
     return;
 
   // Store size at the beginning of the list.
   list->Append(Value::CreateIntegerValue(local_list.size() - start));
 
   base::MD5Context ctx;
   base::MD5Init(&ctx);
   std::string encoded_log;
-  for (std::vector<std::string>::const_iterator it = local_list.begin() + start;
-       it != local_list.end(); ++it) {
+  std::vector<MetricsLogManager::SerializedLog>::const_iterator it;

[Ilya Sherman, 2013/10/16 18:26:14]

nit: Please keep this scoped within the for loop.  I know the code looks uglier
that way, but IMO it's more important not to accidentally leak the scope,
especially since "it" is such a commonly reused variable name.

[Alexei Svitkine (slow), 2013/10/16 19:31:46]

Done.

+  for (it = local_list.begin() + start; it != local_list.end(); ++it) {
     // We encode the compressed log as Value::CreateStringValue() expects to
     // take a valid UTF8 string.
-    if (!base::Base64Encode(*it, &encoded_log)) {
+    if (!base::Base64Encode(it->log_text, &encoded_log)) {
       list->Clear();
       return;
     }
     base::MD5Update(&ctx, encoded_log);
     list->Append(Value::CreateStringValue(encoded_log));
   }
 
   // Append hash to the end of the list.
   base::MD5Digest digest;
   base::MD5Final(&digest, &ctx);
   list->Append(Value::CreateStringValue(base::MD5DigestToBase16(digest)));
   DCHECK(list->GetSize() >= 3);  // Minimum of 3 elements (size, data, hash).
 }
 
 // static
 MetricsLogSerializer::LogReadStatus MetricsLogSerializer::ReadLogsFromPrefList(
     const ListValue& list,
-    std::vector<std::string>* local_list) {
+    std::vector<MetricsLogManager::SerializedLog>* local_list) {
   if (list.GetSize() == 0)
     return MakeRecallStatusHistogram(LIST_EMPTY);
   if (list.GetSize() < 3)
     return MakeRecallStatusHistogram(LIST_SIZE_TOO_SMALL);
 
   // The size is stored at the beginning of the list.
   int size;
   bool valid = (*list.begin())->GetAsInteger(&size);
   if (!valid)
     return MakeRecallStatusHistogram(LIST_SIZE_MISSING);
@@ skipping 19 matching lines @@
        ++it, ++local_index) {
     bool valid = (*it)->GetAsString(&encoded_log);
     if (!valid) {
       local_list->clear();
       return MakeRecallStatusHistogram(LOG_STRING_CORRUPTION);
     }
 
     base::MD5Update(&ctx, encoded_log);
 
     DCHECK_LT(local_index, local_list->size());
-    std::string& decoded_log = (*local_list)[local_index];
-    if (!base::Base64Decode(encoded_log, &decoded_log)) {
+    MetricsLogManager::SerializedLog* decoded_log = &(*local_list)[local_index];
+    if (!base::Base64Decode(encoded_log, &decoded_log->log_text)) {
       local_list->clear();
       return MakeRecallStatusHistogram(DECODE_FAIL);
     }
+    decoded_log->UpdateHash();
   }
 
   // Verify checksum.
   base::MD5Digest digest;
   base::MD5Final(&digest, &ctx);
   std::string recovered_md5;
   // We store the hash at the end of the list.
   valid = (*(list.end() - 1))->GetAsString(&recovered_md5);
   if (!valid) {
     local_list->clear();
     return MakeRecallStatusHistogram(CHECKSUM_STRING_CORRUPTION);
   }
   if (recovered_md5 != base::MD5DigestToBase16(digest)) {
     local_list->clear();
     return MakeRecallStatusHistogram(CHECKSUM_CORRUPTION);
   }
   return MakeRecallStatusHistogram(RECALL_SUCCESS);
 }