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
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
|
// $Id$
/***********************************************************************
Moses - factored phrase-based language decoder
Copyright (c) 2006 University of Edinburgh
All rights reserved.
Redistribution and use in source and binary forms, with or without modification,
are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright notice,
this list of conditions and the following disclaimer in the documentation
and/or other materials provided with the distribution.
* Neither the name of the University of Edinburgh nor the names of its contributors
may be used to endorse or promote products derived from this software
without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS
BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER
IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
***********************************************************************/
// example file on how to use moses library
#include <iostream>
#include <stack>
#include <boost/algorithm/string.hpp>
#include "moses/Syntax/KBestExtractor.h"
#include "moses/Syntax/PVertex.h"
#include "moses/Syntax/SHyperedge.h"
#include "moses/Syntax/S2T/DerivationWriter.h"
#include "moses/Syntax/SVertex.h"
#include "moses/TypeDef.h"
#include "moses/Util.h"
#include "moses/Hypothesis.h"
#include "moses/WordsRange.h"
#include "moses/TrellisPathList.h"
#include "moses/StaticData.h"
#include "moses/FeatureVector.h"
#include "moses/InputFileStream.h"
#include "moses/FF/StatefulFeatureFunction.h"
#include "moses/FF/StatelessFeatureFunction.h"
#include "moses/TreeInput.h"
#include "moses/ForestInput.h"
#include "moses/ConfusionNet.h"
#include "moses/WordLattice.h"
#include "moses/Incremental.h"
#include "moses/ChartManager.h"
#include "util/exception.hh"
#include "IOWrapper.h"
using namespace std;
namespace Moses
{
IOWrapper::IOWrapper()
:m_nBestStream(NULL)
,m_outputWordGraphStream(NULL)
,m_outputSearchGraphStream(NULL)
,m_detailedTranslationReportingStream(NULL)
,m_unknownsStream(NULL)
,m_alignmentInfoStream(NULL)
,m_latticeSamplesStream(NULL)
,m_surpressSingleBestOutput(false)
,spe_src(NULL)
,spe_trg(NULL)
,spe_aln(NULL)
{
const StaticData &staticData = StaticData::Instance();
m_inputFactorOrder = &staticData.GetInputFactorOrder();
size_t nBestSize = staticData.GetNBestSize();
string nBestFilePath = staticData.GetNBestFilePath();
staticData.GetParameter().SetParameter<string>(m_inputFilePath, "input-file", "");
if (m_inputFilePath.empty()) {
m_inputFile = NULL;
m_inputStream = &cin;
} else {
VERBOSE(2,"IO from File" << endl);
m_inputFile = new InputFileStream(m_inputFilePath);
m_inputStream = m_inputFile;
}
if (nBestSize > 0) {
if (nBestFilePath == "-" || nBestFilePath == "/dev/stdout") {
m_nBestStream = &std::cout;
m_nBestOutputCollector.reset(new Moses::OutputCollector(&std::cout));
m_surpressSingleBestOutput = true;
} else {
std::ofstream *file = new std::ofstream;
file->open(nBestFilePath.c_str());
m_nBestStream = file;
m_nBestOutputCollector.reset(new Moses::OutputCollector(file));
//m_nBestOutputCollector->HoldOutputStream();
}
}
// search graph output
if (staticData.GetOutputSearchGraph()) {
string fileName;
if (staticData.GetOutputSearchGraphExtended()) {
staticData.GetParameter().SetParameter<string>(fileName, "output-search-graph-extended", "");
} else {
staticData.GetParameter().SetParameter<string>(fileName, "output-search-graph", "");
}
std::ofstream *file = new std::ofstream;
m_outputSearchGraphStream = file;
file->open(fileName.c_str());
}
if (!staticData.GetOutputUnknownsFile().empty()) {
m_unknownsStream = new std::ofstream(staticData.GetOutputUnknownsFile().c_str());
m_unknownsCollector.reset(new Moses::OutputCollector(m_unknownsStream));
UTIL_THROW_IF2(!m_unknownsStream->good(),
"File for unknowns words could not be opened: " <<
staticData.GetOutputUnknownsFile());
}
if (!staticData.GetAlignmentOutputFile().empty()) {
m_alignmentInfoStream = new std::ofstream(staticData.GetAlignmentOutputFile().c_str());
m_alignmentInfoCollector.reset(new Moses::OutputCollector(m_alignmentInfoStream));
UTIL_THROW_IF2(!m_alignmentInfoStream->good(),
"File for alignment output could not be opened: " << staticData.GetAlignmentOutputFile());
}
if (staticData.GetOutputSearchGraph()) {
string fileName;
staticData.GetParameter().SetParameter<string>(fileName, "output-search-graph", "");
std::ofstream *file = new std::ofstream;
m_outputSearchGraphStream = file;
file->open(fileName.c_str());
m_searchGraphOutputCollector.reset(new Moses::OutputCollector(m_outputSearchGraphStream));
}
// detailed translation reporting
if (staticData.IsDetailedTranslationReportingEnabled()) {
const std::string &path = staticData.GetDetailedTranslationReportingFilePath();
m_detailedTranslationReportingStream = new std::ofstream(path.c_str());
m_detailedTranslationCollector.reset(new Moses::OutputCollector(m_detailedTranslationReportingStream));
}
if (staticData.IsDetailedTreeFragmentsTranslationReportingEnabled()) {
const std::string &path = staticData.GetDetailedTreeFragmentsTranslationReportingFilePath();
m_detailedTreeFragmentsTranslationReportingStream = new std::ofstream(path.c_str());
m_detailTreeFragmentsOutputCollector.reset(new Moses::OutputCollector(m_detailedTreeFragmentsTranslationReportingStream));
}
// wordgraph output
if (staticData.GetOutputWordGraph()) {
string fileName;
staticData.GetParameter().SetParameter<string>(fileName, "output-word-graph", "");
std::ofstream *file = new std::ofstream;
m_outputWordGraphStream = file;
file->open(fileName.c_str());
m_wordGraphCollector.reset(new OutputCollector(m_outputWordGraphStream));
}
size_t latticeSamplesSize = staticData.GetLatticeSamplesSize();
string latticeSamplesFile = staticData.GetLatticeSamplesFilePath();
if (latticeSamplesSize) {
if (latticeSamplesFile == "-" || latticeSamplesFile == "/dev/stdout") {
m_latticeSamplesCollector.reset(new OutputCollector());
m_surpressSingleBestOutput = true;
} else {
m_latticeSamplesStream = new ofstream(latticeSamplesFile.c_str());
if (!m_latticeSamplesStream->good()) {
TRACE_ERR("ERROR: Failed to open " << latticeSamplesFile << " for lattice samples" << endl);
exit(1);
}
m_latticeSamplesCollector.reset(new OutputCollector(m_latticeSamplesStream));
}
}
if (!m_surpressSingleBestOutput) {
m_singleBestOutputCollector.reset(new Moses::OutputCollector(&std::cout));
}
if (staticData.GetParameter().GetParam("spe-src")) {
spe_src = new ifstream(staticData.GetParameter().GetParam("spe-src")->at(0).c_str());
spe_trg = new ifstream(staticData.GetParameter().GetParam("spe-trg")->at(0).c_str());
spe_aln = new ifstream(staticData.GetParameter().GetParam("spe-aln")->at(0).c_str());
}
}
IOWrapper::~IOWrapper()
{
if (m_inputFile != NULL)
delete m_inputFile;
if (m_nBestStream != NULL && !m_surpressSingleBestOutput) {
// outputting n-best to file, rather than stdout. need to close file and delete obj
delete m_nBestStream;
}
delete m_detailedTranslationReportingStream;
delete m_alignmentInfoStream;
delete m_unknownsStream;
delete m_outputSearchGraphStream;
delete m_outputWordGraphStream;
delete m_latticeSamplesStream;
}
InputType*
IOWrapper::
GetInput(InputType* inputType)
{
if(inputType->Read(*m_inputStream, *m_inputFactorOrder)) {
return inputType;
} else {
delete inputType;
return NULL;
}
}
bool
IOWrapper
::ReadInput(InputTypeEnum inputType,
InputType*& source,
TranslationTask const* ttask)
{
delete source;
switch(inputType) {
case SentenceInput:
source = GetInput(new Sentence(ttask));
break;
case ConfusionNetworkInput:
source = GetInput(new ConfusionNet(ttask));
break;
case WordLatticeInput:
source = GetInput(new WordLattice(ttask));
break;
case TreeInputType:
source = GetInput(new TreeInput(ttask));
break;
case TabbedSentenceInput:
source = GetInput(new TabbedSentence(ttask));
break;
case ForestInputType:
source = GetInput(new ForestInput(ttask));
break;
default:
TRACE_ERR("Unknown input type: " << inputType << "\n");
}
return (source ? true : false);
}
} // namespace
|