be/src/storage/index/analyzer_key_matcher.h
Line | Count | Source |
1 | | // Licensed to the Apache Software Foundation (ASF) under one |
2 | | // or more contributor license agreements. See the NOTICE file |
3 | | // distributed with this work for additional information |
4 | | // regarding copyright ownership. The ASF licenses this file |
5 | | // to you under the Apache License, Version 2.0 (the |
6 | | // "License"); you may not use this file except in compliance |
7 | | // with the License. You may obtain a copy of the License at |
8 | | // |
9 | | // http://www.apache.org/licenses/LICENSE-2.0 |
10 | | // |
11 | | // Unless required by applicable law or agreed to in writing, |
12 | | // software distributed under the License is distributed on an |
13 | | // "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY |
14 | | // KIND, either express or implied. See the License for the |
15 | | // specific language governing permissions and limitations |
16 | | // under the License. |
17 | | |
18 | | #pragma once |
19 | | |
20 | | #include <string> |
21 | | #include <string_view> |
22 | | #include <unordered_map> |
23 | | #include <vector> |
24 | | |
25 | | #include "storage/index/inverted/inverted_index_parser.h" |
26 | | #include "storage/index/inverted/inverted_index_reader.h" |
27 | | |
28 | | namespace doris::segment_v2 { |
29 | | |
30 | | struct ReaderEntry { |
31 | | InvertedIndexReaderType type; |
32 | | std::string analyzer_key; |
33 | | InvertedIndexReaderPtr reader; |
34 | | }; |
35 | | |
36 | | // Result of analyzer key matching operation. |
37 | | // Contains candidate readers that match the requested analyzer key. |
38 | | struct AnalyzerMatchResult { |
39 | | // Pointers to matching reader entries. Valid only within the scope of |
40 | | // the InvertedIndexIterator that owns the entries. |
41 | | std::vector<const ReaderEntry*> candidates; |
42 | | |
43 | | // True if fallback strategy was used (no exact match found) |
44 | | bool used_fallback = false; |
45 | | |
46 | | // Convenience methods |
47 | 10 | bool empty() const { return candidates.empty(); } |
48 | 7 | size_t size() const { return candidates.size(); } |
49 | | }; |
50 | | |
51 | | // Utility class for matching analyzer keys against reader entries. |
52 | | // Stateless - all methods are static. |
53 | | // |
54 | | // Matching strategy: |
55 | | // 1. If key is empty (user did not specify), return all readers for query-type-based selection |
56 | | // 2. If key is non-empty (user specified), try exact match |
57 | | // 3. If explicit key with no match, return empty (caller decides whether to bypass) |
58 | | class AnalyzerKeyMatcher { |
59 | | public: |
60 | | // Match analyzer key against reader entries. |
61 | | // @param analyzer_key: Normalized analyzer key (lowercase, or empty for auto-select) |
62 | | // @param entries: Available reader entries |
63 | | // @param key_index: Index mapping analyzer_key -> entry indices |
64 | | // @return MatchResult with candidates and fallback flag |
65 | | static AnalyzerMatchResult match( |
66 | | std::string_view analyzer_key, const std::vector<ReaderEntry>& entries, |
67 | | const std::unordered_map<std::string, std::vector<size_t>>& key_index); |
68 | | |
69 | | // Check if analyzer key is explicitly specified by user. |
70 | | // Empty string means "user did not specify" (auto-select mode). |
71 | | // Non-empty means "user wrote USING ANALYZER xxx". |
72 | 6 | static bool is_explicit(std::string_view key) { return !key.empty(); } |
73 | | |
74 | | // Check if fallback (returning all readers) is allowed for this key. |
75 | | // Only empty key (user did not specify) allows fallback. |
76 | 15 | static bool allows_fallback(std::string_view key) { return key.empty(); } |
77 | | }; |
78 | | |
79 | | } // namespace doris::segment_v2 |