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
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
|
// $Id$
// vim::tabstop=2
/***********************************************************************
Moses - factored phrase-based language decoder
Copyright (C) 2006 University of Edinburgh
This library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
This library 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
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with this library; if not, write to the Free Software
Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
***********************************************************************/
#include <sstream>
#include "memory.h"
#include "Word.h"
#include "TypeDef.h"
#include "StaticData.h" // needed to determine the FactorDelimiter
#include "util/exception.hh"
#include "util/tokenize_piece.hh"
using namespace std;
namespace Moses
{
// static
int Word::Compare(const Word &targetWord, const Word &sourceWord)
{
if (targetWord.IsNonTerminal() != sourceWord.IsNonTerminal()) {
return targetWord.IsNonTerminal() ? -1 : 1;
}
for (size_t factorType = 0 ; factorType < MAX_NUM_FACTORS ; factorType++) {
const Factor *targetFactor = targetWord[factorType]
,*sourceFactor = sourceWord[factorType];
if (targetFactor == NULL || sourceFactor == NULL)
continue;
if (targetFactor == sourceFactor)
continue;
return (targetFactor<sourceFactor) ? -1 : +1;
}
return 0;
}
void Word::Merge(const Word &sourceWord)
{
for (unsigned int currFactor = 0 ; currFactor < MAX_NUM_FACTORS ; currFactor++) {
const Factor *sourcefactor = sourceWord.m_factorArray[currFactor]
,*targetFactor = this ->m_factorArray[currFactor];
if (targetFactor == NULL && sourcefactor != NULL) {
m_factorArray[currFactor] = sourcefactor;
}
}
}
std::string Word::GetString(const vector<FactorType> factorType,bool endWithBlank) const
{
stringstream strme;
CHECK(factorType.size() <= MAX_NUM_FACTORS);
const std::string& factorDelimiter = StaticData::Instance().GetFactorDelimiter();
bool firstPass = true;
for (unsigned int i = 0 ; i < factorType.size() ; i++) {
const Factor *factor = m_factorArray[factorType[i]];
if (factor != NULL) {
if (firstPass) {
firstPass = false;
} else {
strme << factorDelimiter;
}
strme << factor->GetString();
}
}
if(endWithBlank) strme << " ";
return strme.str();
}
StringPiece Word::GetString(FactorType factorType) const
{
return m_factorArray[factorType]->GetString();
}
class StrayFactorException : public util::Exception {};
void Word::CreateFromString(FactorDirection direction
, const std::vector<FactorType> &factorOrder
, const StringPiece &str
, bool isNonTerminal)
{
FactorCollection &factorCollection = FactorCollection::Instance();
util::TokenIter<util::MultiCharacter> fit(str, StaticData::Instance().GetFactorDelimiter());
for (size_t ind = 0; ind < factorOrder.size() && fit; ++ind, ++fit) {
m_factorArray[factorOrder[ind]] = factorCollection.AddFactor(*fit);
}
UTIL_THROW_IF(fit, StrayFactorException, "You have configured " << factorOrder.size() << " factors but the word " << str << " contains factor delimiter " << StaticData::Instance().GetFactorDelimiter() << " too many times.");
// assume term/non-term same for all factors
m_isNonTerminal = isNonTerminal;
}
void Word::CreateUnknownWord(const Word &sourceWord)
{
FactorCollection &factorCollection = FactorCollection::Instance();
for (unsigned int currFactor = 0 ; currFactor < MAX_NUM_FACTORS ; currFactor++) {
FactorType factorType = static_cast<FactorType>(currFactor);
const Factor *sourceFactor = sourceWord[currFactor];
if (sourceFactor == NULL)
SetFactor(factorType, factorCollection.AddFactor(Output, factorType, UNKNOWN_FACTOR));
else
SetFactor(factorType, factorCollection.AddFactor(Output, factorType, sourceFactor->GetString()));
}
m_isNonTerminal = sourceWord.IsNonTerminal();
}
TO_STRING_BODY(Word);
// friend
ostream& operator<<(ostream& out, const Word& word)
{
stringstream strme;
const std::string& factorDelimiter = StaticData::Instance().GetFactorDelimiter();
bool firstPass = true;
for (unsigned int currFactor = 0 ; currFactor < MAX_NUM_FACTORS ; currFactor++) {
FactorType factorType = static_cast<FactorType>(currFactor);
const Factor *factor = word.GetFactor(factorType);
if (factor != NULL) {
if (firstPass) {
firstPass = false;
} else {
strme << factorDelimiter;
}
strme << *factor;
}
}
out << strme.str() << " ";
return out;
}
}
|