1 | /**************************************************************************** |
2 | ** |
3 | ** Copyright (C) 2016 The Qt Company Ltd. |
4 | ** Contact: https://www.qt.io/licensing/ |
5 | ** |
6 | ** This file is part of the Qt Linguist of the Qt Toolkit. |
7 | ** |
8 | ** $QT_BEGIN_LICENSE:GPL-EXCEPT$ |
9 | ** Commercial License Usage |
10 | ** Licensees holding valid commercial Qt licenses may use this file in |
11 | ** accordance with the commercial license agreement provided with the |
12 | ** Software or, alternatively, in accordance with the terms contained in |
13 | ** a written agreement between you and The Qt Company. For licensing terms |
14 | ** and conditions see https://www.qt.io/terms-conditions. For further |
15 | ** information use the contact form at https://www.qt.io/contact-us. |
16 | ** |
17 | ** GNU General Public License Usage |
18 | ** Alternatively, this file may be used under the terms of the GNU |
19 | ** General Public License version 3 as published by the Free Software |
20 | ** Foundation with exceptions as appearing in the file LICENSE.GPL3-EXCEPT |
21 | ** included in the packaging of this file. Please review the following |
22 | ** information to ensure the GNU General Public License requirements will |
23 | ** be met: https://www.gnu.org/licenses/gpl-3.0.html. |
24 | ** |
25 | ** $QT_END_LICENSE$ |
26 | ** |
27 | ****************************************************************************/ |
28 | |
29 | #ifndef SIMTEXTH_H |
30 | #define SIMTEXTH_H |
31 | |
32 | const int textSimilarityThreshold = 190; |
33 | |
34 | #include <QString> |
35 | #include <QList> |
36 | |
37 | QT_BEGIN_NAMESPACE |
38 | |
39 | class Translator; |
40 | |
41 | struct Candidate |
42 | { |
43 | Candidate() {} |
44 | Candidate(const QString &c, const QString &s, const QString &d, const QString &t) |
45 | : context(c), source(s), disambiguation(d), translation(t) |
46 | {} |
47 | |
48 | QString context; |
49 | QString source; |
50 | QString disambiguation; |
51 | QString translation; |
52 | }; |
53 | |
54 | inline bool operator==( const Candidate& c, const Candidate& d ) { |
55 | return c.translation == d.translation && c.source == d.source && c.context == d.context |
56 | && c.disambiguation == d.disambiguation; |
57 | } |
58 | inline bool operator!=( const Candidate& c, const Candidate& d ) { |
59 | return !operator==( c, d ); |
60 | } |
61 | |
62 | typedef QList<Candidate> CandidateList; |
63 | |
64 | struct CoMatrix |
65 | { |
66 | CoMatrix(const QString &str); |
67 | CoMatrix() {} |
68 | |
69 | /* |
70 | The matrix has 20 * 20 = 400 entries. This requires 50 bytes, or 13 |
71 | words. Some operations are performed on words for more efficiency. |
72 | */ |
73 | union { |
74 | quint8 b[52]; |
75 | quint32 w[13]; |
76 | }; |
77 | }; |
78 | |
79 | /** |
80 | * This class is more efficient for searching through a large array of candidate strings, since we only |
81 | * have to construct the CoMatrix for the \a stringToMatch once, |
82 | * after that we just call getSimilarityScore(strCandidate). |
83 | * \sa getSimilarityScore |
84 | */ |
85 | class StringSimilarityMatcher { |
86 | public: |
87 | StringSimilarityMatcher(const QString &stringToMatch); |
88 | int getSimilarityScore(const QString &strCandidate); |
89 | |
90 | private: |
91 | CoMatrix m_cm; |
92 | int m_length; |
93 | }; |
94 | |
95 | /** |
96 | * Checks how similar two strings are. |
97 | * The return value is the score, and a higher score is more similar |
98 | * than one with a low score. |
99 | * Linguist considers a score over 190 to be a good match. |
100 | * \sa StringSimilarityMatcher |
101 | */ |
102 | static inline int getSimilarityScore(const QString &str1, const QString &str2) |
103 | { |
104 | return StringSimilarityMatcher(str1).getSimilarityScore(strCandidate: str2); |
105 | } |
106 | |
107 | CandidateList similarTextHeuristicCandidates( const Translator *tor, |
108 | const QString &text, |
109 | int maxCandidates ); |
110 | |
111 | QT_END_NAMESPACE |
112 | |
113 | #endif |
114 | |