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
|
/* Copyright (C) 2005-2022 J.F.Dockes
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the
* Free Software Foundation, Inc.,
* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
*/
/**
* Management of the auxiliary databases listing stems and their expansion terms
*/
#include "autoconfig.h"
#include "safeunistd.h"
#include <algorithm>
#include <map>
#include <iostream>
#include <string>
using namespace std;
#include <xapian.h>
#include "stemdb.h"
#include "log.h"
#include "smallut.h"
#include "synfamily.h"
#include "unacpp.h"
#include "rclconfig.h"
namespace Rcl {
/**
* Expand for one or several languages
*/
bool StemDb::stemExpand(const std::string& langs, const std::string& _term, vector<string>& result)
{
vector<string> llangs;
stringToStrings(langs, llangs);
// The stemdb keys may have kept their diacritics or not but they are always lower-case. It
// would be more logical for the term transformers to perform before doing the stemming, but
// this would be inefficient when there are several stemming languages
string term;
unacmaybefold(_term, term, UNACOP_FOLD);
for (const auto& lang : llangs) {
SynTermTransStem stemmer(lang);
XapComputableSynFamMember expander(getdb(), synFamStem, lang, &stemmer);
(void)expander.synExpand(term, result);
}
if (!o_index_stripchars) {
string unac;
unacmaybefold(term, unac, UNACOP_UNAC);
// Expand the unaccented stem, using the unaccented stem db. Because it's a different db, We
// need to do it even if the input has no accent (unac == term)
for (const auto& lang : llangs) {
SynTermTransStem stemmer(lang);
XapComputableSynFamMember expander(getdb(), synFamStemUnac, lang, &stemmer);
(void)expander.synExpand(unac, result);
}
}
if (result.empty())
result.push_back(term);
sort(result.begin(), result.end());
auto uit = unique(result.begin(), result.end());
result.resize(uit - result.begin());
LOGDEB1("stemExpand:" << langs << ": " << term << " -> " << stringsToString(result) << "\n");
return true;
}
}
|
