Index: chrome/common/safe_browsing/client_model.proto |
diff --git a/chrome/common/safe_browsing/client_model.proto b/chrome/common/safe_browsing/client_model.proto |
index 622ba8f8fff67cebf48700d7860dc6687718d319..6a1a912d5f56a13f9f6cf1e1c26c2dd3f45bf76d 100644 |
--- a/chrome/common/safe_browsing/client_model.proto |
+++ b/chrome/common/safe_browsing/client_model.proto |
@@ -60,11 +60,12 @@ message ClientSideModel { |
// as lowercase UTF-8 strings. |
repeated int32 page_term = 3; |
- // List of indexes that point to the hashed page words. The page words |
- // correspond to all words that appear in page terms. If the term |
- // "one two" is in the list of page terms then "one" and "two" will be |
- // in the list of page words. |
- repeated int32 page_word = 4; |
+ // List of hashed page words. The page words correspond to all words that |
+ // appear in page terms. If the term "one two" is in the list of page terms |
+ // then "one" and "two" will be in the list of page words. For page words |
+ // we don't use SHA256 because it is too expensive. We use MurmurHash3 |
+ // instead. See: http://code.google.com/p/smhasher. |
+ repeated fixed32 page_word = 4; |
// Page terms in page_term contain at most this many page words. |
required int32 max_words_per_term = 5; |
@@ -84,4 +85,7 @@ message ClientSideModel { |
optional int32 size = 2 [default = 128]; |
}; |
repeated IPSubnet bad_subnet = 7; |
+ |
+ // Murmur hash seed that was used to hash the page words. |
+ optional fixed32 murmur_hash_seed = 8; |
} |