File size: 3,716 Bytes
edace67 |
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 |
/***********************************************************************
Moses - factored phrase-based language decoder
Copyright (C) 2009 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 <string.h>
#include <fstream>
#include <vector>
#include <string>
#include <iostream>
#include <cstdlib>
#include "InputFileStream.h"
#include "OutputFileStream.h"
#include "util/tokenize.hh"
using namespace std;
vector< string > splitLine(const char *line)
{
vector< string > item;
int start=0;
int i=0;
for(; line[i] != '\0'; i++) {
if (line[i] == ' ' &&
line[i+1] == '|' &&
line[i+2] == '|' &&
line[i+3] == '|' &&
line[i+4] == ' ') {
if (start > i) start = i; // empty item
item.push_back( string( line+start, i-start ) );
start = i+5;
i += 3;
}
}
item.push_back( string( line+start, i-start ) );
return item;
}
bool getLine( istream &fileP, vector< string > &item )
{
if (fileP.eof())
return false;
string line;
if (getline(fileP, line)) {
item = splitLine(line.c_str());
return true;
} else {
return false;
}
}
int main(int argc, char* argv[])
{
cerr << "Starting..." << endl;
char* &fileNameDirect = argv[1];
Moses::InputFileStream fileDirect(fileNameDirect);
//fileDirect.open(fileNameDirect);
if (fileDirect.fail()) {
cerr << "ERROR: could not open extract file " << fileNameDirect << endl;
exit(1);
}
istream &fileDirectP = fileDirect;
char* &fileNameConsolidated = argv[2];
ostream *fileConsolidated;
if (strcmp(fileNameConsolidated, "-") == 0) {
fileConsolidated = &cout;
} else {
Moses::OutputFileStream *outputFile = new Moses::OutputFileStream();
bool success = outputFile->Open(fileNameConsolidated);
if (!success) {
cerr << "ERROR: could not open file phrase table file "
<< fileNameConsolidated << endl;
exit(1);
}
fileConsolidated = outputFile;
}
int i=0;
while(true) {
i++;
if (i%1000 == 0) cerr << "." << flush;
if (i%10000 == 0) cerr << ":" << flush;
if (i%100000 == 0) cerr << "!" << flush;
vector< string > itemDirect;
if (! getLine(fileDirectP, itemDirect ))
break;
const vector< string > count = util::tokenize( itemDirect[4] );
float countEF = atof(count[0].c_str());
float countF = atof(count[1].c_str());
float prob = countF/countEF;
(*fileConsolidated) << itemDirect[0] << " ||| " // source
<< itemDirect[1] << " ||| " // target
<< prob << " ||| " // prob
<< itemDirect[2] << "||| " // alignment
<< itemDirect[4] << " " << countEF // counts
<< " ||| " << endl;
}
fileConsolidated->flush();
if (fileConsolidated != &cout) {
delete fileConsolidated;
}
cerr << "Finished" << endl;
}
|