1 /*
2 * Copyright (C) 2018 The Android Open Source Project
3 *
4 * Licensed under the Apache License, Version 2.0 (the "License");
5 * you may not use this file except in compliance with the License.
6 * You may obtain a copy of the License at
7 *
8 * http://www.apache.org/licenses/LICENSE-2.0
9 *
10 * Unless required by applicable law or agreed to in writing, software
11 * distributed under the License is distributed on an "AS IS" BASIS,
12 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13 * See the License for the specific language governing permissions and
14 * limitations under the License.
15 */
16
17 #include "utils/sentencepiece/test_utils.h"
18
19 #include <memory>
20
21 #include "utils/base/integral_types.h"
22 #include "utils/sentencepiece/double_array_trie.h"
23 #include "utils/strings/stringpiece.h"
24
25 namespace libtextclassifier3 {
26
NormalizerFromSpec(StringPiece spec,bool add_dummy_prefix,bool remove_extra_whitespaces,bool escape_whitespaces)27 SentencePieceNormalizer NormalizerFromSpec(StringPiece spec,
28 bool add_dummy_prefix,
29 bool remove_extra_whitespaces,
30 bool escape_whitespaces) {
31 const uint32 trie_blob_size = reinterpret_cast<const uint32*>(spec.data())[0];
32 spec.RemovePrefix(sizeof(trie_blob_size));
33 const TrieNode* trie_blob = reinterpret_cast<const TrieNode*>(spec.data());
34 spec.RemovePrefix(trie_blob_size);
35 const int num_nodes = trie_blob_size / sizeof(TrieNode);
36 return SentencePieceNormalizer(
37 DoubleArrayTrie(trie_blob, num_nodes),
38 /*charsmap_normalized=*/StringPiece(spec.data(), spec.size()),
39 add_dummy_prefix, remove_extra_whitespaces, escape_whitespaces);
40 }
41
42 } // namespace libtextclassifier3
43