blob: dacc42836421b8bef96679a2aa371731af310428 (
plain)
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
|
#include "data_array.h"
#include <fstream>
#include <iostream>
#include <sstream>
#include <string>
using namespace std;
namespace extractor {
int DataArray::NULL_WORD = 0;
int DataArray::END_OF_LINE = 1;
string DataArray::NULL_WORD_STR = "__NULL__";
string DataArray::END_OF_LINE_STR = "__END_OF_LINE__";
DataArray::DataArray() {
InitializeDataArray();
}
DataArray::DataArray(const string& filename) {
InitializeDataArray();
ifstream infile(filename.c_str());
vector<string> lines;
string line;
while (getline(infile, line)) {
lines.push_back(line);
}
CreateDataArray(lines);
}
DataArray::DataArray(const string& filename, const Side& side) {
InitializeDataArray();
ifstream infile(filename.c_str());
vector<string> lines;
string line, delimiter = "|||";
while (getline(infile, line)) {
int position = line.find(delimiter);
if (side == SOURCE) {
lines.push_back(line.substr(0, position));
} else {
lines.push_back(line.substr(position + delimiter.size()));
}
}
CreateDataArray(lines);
}
void DataArray::InitializeDataArray() {
word2id[NULL_WORD_STR] = NULL_WORD;
id2word.push_back(NULL_WORD_STR);
word2id[END_OF_LINE_STR] = END_OF_LINE;
id2word.push_back(END_OF_LINE_STR);
}
void DataArray::CreateDataArray(const vector<string>& lines) {
for (size_t i = 0; i < lines.size(); ++i) {
sentence_start.push_back(data.size());
istringstream iss(lines[i]);
string word;
while (iss >> word) {
if (word2id.count(word) == 0) {
word2id[word] = id2word.size();
id2word.push_back(word);
}
data.push_back(word2id[word]);
sentence_id.push_back(i);
}
data.push_back(END_OF_LINE);
sentence_id.push_back(i);
}
sentence_start.push_back(data.size());
data.shrink_to_fit();
sentence_id.shrink_to_fit();
sentence_start.shrink_to_fit();
}
DataArray::~DataArray() {}
vector<int> DataArray::GetData() const {
return data;
}
int DataArray::AtIndex(int index) const {
return data[index];
}
string DataArray::GetWordAtIndex(int index) const {
return id2word[data[index]];
}
vector<int> DataArray::GetWordIds(int index, int size) const {
return vector<int>(data.begin() + index, data.begin() + index + size);
}
vector<string> DataArray::GetWords(int start_index, int size) const {
vector<string> words;
for (int word_id: GetWordIds(start_index, size)) {
words.push_back(id2word[word_id]);
}
return words;
}
int DataArray::GetSize() const {
return data.size();
}
int DataArray::GetVocabularySize() const {
return id2word.size();
}
int DataArray::GetNumSentences() const {
return sentence_start.size() - 1;
}
int DataArray::GetSentenceStart(int position) const {
return sentence_start[position];
}
int DataArray::GetSentenceLength(int sentence_id) const {
// Ignore end of line markers.
return sentence_start[sentence_id + 1] - sentence_start[sentence_id] - 1;
}
int DataArray::GetSentenceId(int position) const {
return sentence_id[position];
}
bool DataArray::HasWord(const string& word) const {
return word2id.count(word);
}
int DataArray::GetWordId(const string& word) const {
auto result = word2id.find(word);
return result == word2id.end() ? -1 : result->second;
}
string DataArray::GetWord(int word_id) const {
return id2word[word_id];
}
bool DataArray::operator==(const DataArray& other) const {
return word2id == other.word2id && id2word == other.id2word &&
data == other.data && sentence_start == other.sentence_start &&
sentence_id == other.sentence_id;
}
} // namespace extractor
|
