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
|
%module constraint_grammar
%include <std_map.i>
%include <std_string.i>
%include <std_vector.i>
%inline%{
namespace CG3 {}
using namespace CG3;
%}
%include <Grammar.hpp>
%typemap(in) (int argc, char **argv) {
if (PyTuple_Check($input)) {
int i = 0;
$1 = PyTuple_Size($input);
$2 = (char **) malloc(($1 + 1)*sizeof(char *));
for (i = 0; i < $1; i++) {
PyObject *py_obj = PyTuple_GetItem($input, i);
if (PyUnicode_Check(py_obj)) {
$2[i] = strdup(PyUnicode_AsUTF8(py_obj));
}
else {
PyErr_SetString(PyExc_TypeError, "tuple must contain strings");
free($2);
return NULL;
}
}
$2[i] = 0;
} else {
PyErr_SetString(PyExc_TypeError, "not a tuple");
return NULL;
}
}
%typemap(freearg) (int argc, char **argv) {
free((char *) $2);
}
%inline%{
#define SWIG_FILE_WITH_INIT
#include "stdafx.hpp"
#include "Grammar.hpp"
#include "TextualParser.hpp"
#include "BinaryGrammar.hpp"
#include "ApertiumApplicator.hpp"
#include "MatxinApplicator.hpp"
#include "GrammarApplicator.hpp"
#include <getopt.h>
class CGProc: public CG3::Grammar
{
private:
CG3::Grammar grammar;
public:
CGProc(char *dictionary_path);
void cg_proc(int argc, char **argv, char *input_path, char *output_path);
};
CGProc::CGProc(char *dictionary_path)
{
std::unique_ptr<CG3::IGrammarParser> parser;
FILE* dictionary = fopen(dictionary_path, "rb");
fread(&CG3::cbuffers[0][0], 1, 4, dictionary);
fclose(dictionary);
if (CG3::cbuffers[0][0] == 'C' && CG3::cbuffers[0][1] == 'G' && CG3::cbuffers[0][2] == '3' && CG3::cbuffers[0][3] == 'B') {
parser.reset(new CG3::BinaryGrammar(grammar, std::cerr));
}
else {
parser.reset(new CG3::TextualParser(grammar, std::cerr));
}
parser->parse_grammar(dictionary_path);
}
void CGProc::cg_proc(int argc, char **argv, char *input_path, char *output_path)
{
bool trace = false;
bool wordform_case = false;
bool print_word_forms = true;
bool only_first = false;
int sections = 0;
std::string single_rule;
std::ifstream input;
input.open(input_path, std::ios::binary);
std::istream& ux_stdin = input;
std::ofstream output;
output.open(output_path, std::ios::binary);
std::ostream& ux_stdout = output;
int c = 0;
optind = 1;
while (true) {
c = getopt(argc, argv, "s:f:tn1wz");
if (c == -1) {
break;
}
switch (c) {
case 'f':
break;
case 't':
trace = true;
break;
case 's':
sections = atoi(optarg);
break;
case 'n':
print_word_forms = false;
break;
case '1':
only_first = true;
break;
case 'w':
wordform_case = true;
break;
case 'z':
break;
}
}
grammar.reindex();
std::unique_ptr<CG3::GrammarApplicator> applicator;
CG3::ApertiumApplicator* apertiumApplicator = new CG3::ApertiumApplicator(std::cerr);
apertiumApplicator->wordform_case = wordform_case;
apertiumApplicator->print_word_forms = print_word_forms;
apertiumApplicator->print_only_first = only_first;
applicator.reset(apertiumApplicator);
applicator->setGrammar(&grammar);
for (int32_t i = 1; i <= sections; i++) {
applicator->sections.push_back(i);
}
applicator->trace = trace;
applicator->unicode_tags = true;
applicator->unique_tags = false;
applicator->runGrammarOnText(ux_stdin, ux_stdout);
u_cleanup();
}
%}
|
