aboutsummaryrefslogtreecommitdiffstats
path: root/searchlib/src/vespa/searchlib/attribute/dfa_fuzzy_matcher.cpp
blob: 18f480eebcd37e0ddb2281456162b0670f49ada7 (plain) (blame)
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
// Copyright Yahoo. Licensed under the terms of the Apache 2.0 license. See LICENSE in the project root.

#include "dfa_fuzzy_matcher.h"
#include <vespa/vespalib/text/utf8.h>
#include <vespa/vespalib/text/lowercase.h>

using vespalib::fuzzy::LevenshteinDfa;
using vespalib::LowerCase;
using vespalib::Utf8Reader;
using vespalib::Utf8ReaderForZTS;

namespace search::attribute {

namespace {

std::vector<uint32_t>
extract_prefix(std::string_view target, uint32_t prefix_size, bool cased)
{
    std::vector<uint32_t> result;
    result.reserve(prefix_size);
    Utf8Reader reader(vespalib::stringref(target.data(), target.size()));
    for (size_t pos = 0; pos < prefix_size && reader.hasMore(); ++pos) {
        uint32_t code_point = reader.getChar();
        if (!cased) {
            code_point = LowerCase::convert(code_point);
        }
        result.emplace_back(code_point);
    }
    return result;
}

std::string_view
extract_suffix(std::string_view target, uint32_t prefix_size)
{
    Utf8Reader reader(vespalib::stringref(target.data(), target.size()));
    for (size_t pos = 0; pos < prefix_size && reader.hasMore(); ++pos) {
        (void) reader.getChar();
    }
    std::string_view result = target;
    result.remove_prefix(reader.getPos());
    return result;
}

}

DfaFuzzyMatcher::DfaFuzzyMatcher(std::string_view target, uint8_t max_edits, uint32_t prefix_size, bool cased, LevenshteinDfa::DfaType dfa_type)
    : _dfa(vespalib::fuzzy::LevenshteinDfa::build(extract_suffix(target, prefix_size), max_edits, (cased ? LevenshteinDfa::Casing::Cased : LevenshteinDfa::Casing::Uncased), dfa_type)),
      _successor(),
      _prefix(extract_prefix(target, prefix_size, cased)),
      _prefix_size(prefix_size),
      _cased(cased)
{
    _successor = _prefix;
}

DfaFuzzyMatcher::~DfaFuzzyMatcher() = default;

const char*
DfaFuzzyMatcher::skip_prefix(const char* word) const
{
    Utf8ReaderForZTS reader(word);
    size_t pos = 0;
    for (; pos < _prefix.size() && reader.hasMore(); ++pos) {
        (void) reader.getChar();
    }
    assert(pos == _prefix.size());
    return reader.get_current_ptr();
}

bool
DfaFuzzyMatcher::is_match(const char* word) const
{
    if (_prefix_size > 0) {
        Utf8ReaderForZTS reader(word);
        size_t pos = 0;
        for (; pos < _prefix.size() && reader.hasMore(); ++pos) {
            uint32_t code_point = reader.getChar();
            if (!_cased) {
                code_point = LowerCase::convert(code_point);
            }
            if (code_point != _prefix[pos]) {
                break;
            }
        }
        if (!reader.hasMore() && pos == _prefix.size() && pos < _prefix_size) {
            return true;
        }
        if (pos != _prefix_size) {
            return false;
        }
        word = reader.get_current_ptr();
    }
    auto match = _dfa.match(word);
    return match.matches();
}

}