1/*
2 * Copyright (C) 2017 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 "common/embedding-feature-extractor.h"
18
19#include <stddef.h>
20
21#include <vector>
22
23#include "common/feature-extractor.h"
24#include "common/feature-types.h"
25#include "common/task-context.h"
26#include "util/base/integral_types.h"
27#include "util/base/logging.h"
28#include "util/strings/numbers.h"
29#include "util/strings/split.h"
30
31namespace libtextclassifier {
32namespace nlp_core {
33
34bool GenericEmbeddingFeatureExtractor::Init(TaskContext *context) {
35  // Don't use version to determine how to get feature FML.
36  const std::string features = context->Get(GetParamName("features"), "");
37  TC_LOG(INFO) << "Features: " << features;
38
39  const std::string embedding_names =
40      context->Get(GetParamName("embedding_names"), "");
41  TC_LOG(INFO) << "Embedding names: " << embedding_names;
42
43  const std::string embedding_dims =
44      context->Get(GetParamName("embedding_dims"), "");
45  TC_LOG(INFO) << "Embedding dims: " << embedding_dims;
46
47  embedding_fml_ = strings::Split(features, ';');
48  embedding_names_ = strings::Split(embedding_names, ';');
49  for (const std::string &dim : strings::Split(embedding_dims, ';')) {
50    int32 parsed_dim = 0;
51    if (!ParseInt32(dim.c_str(), &parsed_dim)) {
52      TC_LOG(ERROR) << "Unable to parse dim " << dim;
53      return false;
54    }
55    embedding_dims_.push_back(parsed_dim);
56  }
57  if ((embedding_fml_.size() != embedding_names_.size()) ||
58      (embedding_fml_.size() != embedding_dims_.size())) {
59    TC_LOG(ERROR) << "Mismatch: #fml specs = " << embedding_fml_.size()
60                  << "; #names = " << embedding_names_.size()
61                  << "; #dims = " << embedding_dims_.size();
62    return false;
63  }
64  return true;
65}
66
67}  // namespace nlp_core
68}  // namespace libtextclassifier
69