File: acronym_matcher.cc

package info (click to toggle)
chromium 139.0.7258.127-1
  • links: PTS, VCS
  • area: main
  • in suites:
  • size: 6,122,068 kB
  • sloc: cpp: 35,100,771; ansic: 7,163,530; javascript: 4,103,002; python: 1,436,920; asm: 946,517; xml: 746,709; pascal: 187,653; perl: 88,691; sh: 88,436; objc: 79,953; sql: 51,488; cs: 44,583; fortran: 24,137; makefile: 22,147; tcl: 15,277; php: 13,980; yacc: 8,984; ruby: 7,485; awk: 3,720; lisp: 3,096; lex: 1,327; ada: 727; jsp: 228; sed: 36
file content (74 lines) | stat: -rw-r--r-- 2,199 bytes parent folder | download | duplicates (7)
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
// Copyright 2022 The Chromium Authors
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.

#include "chromeos/ash/components/string_matching/acronym_matcher.h"

#include <cstddef>
#include <string>

#include "base/i18n/case_conversion.h"
#include "chromeos/ash/components/string_matching/tokenized_string.h"

namespace ash::string_matching {

namespace {

using acronym_matcher_constants::kIsFrontOfTokenCharScore;
using acronym_matcher_constants::kIsPrefixCharScore;
using acronym_matcher_constants::kNoMatchScore;

}  // namespace

// AcronymMatcher:
//
// The factors below are applied when the current char of query matches
// the current char of the text to be matched. Different factors are chosen
// based on where the match happens:
//
// 1) `kIsPrefixCharScore` is used when we match the first char of the query to
// the first char of the text
//
// 2) `kIsFrontOfTokenCharScore` will be used if the first char of the token
// matches the current char of the query in all other cases.
//
// Examples:
//
//   For text: 'Google Chrome'.
//
//   Query 'gc' would use kIsPrefixCharScore for 'g' and
//       kIsFrontOfTokenCharScore for 'c'.

// kNoMatchScore is a relevance score that represents no match.

AcronymMatcher::AcronymMatcher(const TokenizedString& query,
                               const TokenizedString& text) {
  query_ = base::i18n::ToLower(query.text());
  for (auto token : text.tokens()) {
    text_acronym_.push_back(token[0]);
  }
  text_mapping_ = text.mappings();
}
AcronymMatcher::~AcronymMatcher() = default;

double AcronymMatcher::CalculateRelevance() {
  auto found_index = text_acronym_.find(query_);
  if (found_index == std::u16string::npos) {
    return kNoMatchScore;
  }

  double relevance = kIsFrontOfTokenCharScore * query_.size();
  if (found_index == 0) {
    relevance += kIsPrefixCharScore - kIsFrontOfTokenCharScore;
  }

  // update the |hits_| if there is a match.
  for (size_t i = 0; i < query_.size(); i++) {
    size_t start_pos = text_mapping_[found_index + i].start();
    hits_.emplace_back(start_pos, start_pos + 1);
  }

  return relevance;
}

}  // namespace ash::string_matching