blob: 8b20d0464aa63f539db24e68d85c6db45a21c959 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
|
// Copyright (C) 2022 Google LLC
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// 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.
#include "icing/index/string-section-indexing-handler.h"
#include <cstdint>
#include <memory>
#include <string>
#include <string_view>
#include "icing/text_classifier/lib3/utils/base/status.h"
#include "icing/text_classifier/lib3/utils/base/statusor.h"
#include "icing/index/index.h"
#include "icing/proto/logging.pb.h"
#include "icing/proto/schema.pb.h"
#include "icing/schema/section.h"
#include "icing/store/document-id.h"
#include "icing/transform/normalizer.h"
#include "icing/util/logging.h"
#include "icing/util/status-macros.h"
#include "icing/util/tokenized-document.h"
namespace icing {
namespace lib {
/* static */ libtextclassifier3::StatusOr<
std::unique_ptr<StringSectionIndexingHandler>>
StringSectionIndexingHandler::Create(const Normalizer* normalizer,
Index* index) {
ICING_RETURN_ERROR_IF_NULL(normalizer);
ICING_RETURN_ERROR_IF_NULL(index);
return std::unique_ptr<StringSectionIndexingHandler>(
new StringSectionIndexingHandler(normalizer, index));
}
libtextclassifier3::Status StringSectionIndexingHandler::Handle(
const TokenizedDocument& tokenized_document, DocumentId document_id,
PutDocumentStatsProto* put_document_stats) {
uint32_t num_tokens = 0;
libtextclassifier3::Status status;
for (const TokenizedSection& section :
tokenized_document.tokenized_string_sections()) {
if (section.metadata.tokenizer ==
StringIndexingConfig::TokenizerType::NONE) {
ICING_LOG(WARNING)
<< "Unexpected TokenizerType::NONE found when indexing document.";
}
// TODO(b/152934343): pass real namespace ids in
Index::Editor editor =
index_.Edit(document_id, section.metadata.id,
section.metadata.term_match_type, /*namespace_id=*/0);
for (std::string_view token : section.token_sequence) {
++num_tokens;
switch (section.metadata.tokenizer) {
case StringIndexingConfig::TokenizerType::VERBATIM:
// data() is safe to use here because a token created from the
// VERBATIM tokenizer is the entire string value. The character at
// data() + token.length() is guaranteed to be a null char.
status = editor.BufferTerm(token.data());
break;
case StringIndexingConfig::TokenizerType::NONE:
[[fallthrough]];
case StringIndexingConfig::TokenizerType::RFC822:
[[fallthrough]];
case StringIndexingConfig::TokenizerType::URL:
[[fallthrough]];
case StringIndexingConfig::TokenizerType::PLAIN:
std::string normalized_term = normalizer_.NormalizeTerm(token);
status = editor.BufferTerm(normalized_term.c_str());
}
if (!status.ok()) {
// We've encountered a failure. Bail out. We'll mark this doc as deleted
// and signal a failure to the client.
ICING_LOG(WARNING) << "Failed to buffer term in lite lexicon due to: "
<< status.error_message();
break;
}
}
if (!status.ok()) {
break;
}
// Add all the seen terms to the index with their term frequency.
status = editor.IndexAllBufferedTerms();
if (!status.ok()) {
ICING_LOG(WARNING) << "Failed to add hits in lite index due to: "
<< status.error_message();
break;
}
}
if (put_document_stats != nullptr) {
put_document_stats->mutable_tokenization_stats()->set_num_tokens_indexed(
num_tokens);
}
return status;
}
} // namespace lib
} // namespace icing
|