|
1
2
3
4
|
#include <iostream>
#include <cstdlib>
#include "cli.hpp"
|
|
5
|
#include "../const.hpp"
|
|
6
7
8
9
|
using namespace std;
using namespace ez;
|
|
10
11
|
namespace morfeusz {
|
|
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
|
static inline void printCLIUsage(ezOptionParser& opt, ostream& out) {
string usage;
opt.getUsage(usage);
out << usage;
}
ezOptionParser* getOptions(int argc, const char** argv, MorfeuszProcessorType processorType) {
ezOptionParser& opt = *(new ezOptionParser());
opt.overview = processorType == ANALYZER
? "Morfeusz analyzer"
: "Morfeusz generator";
opt.syntax = string(argv[0]) + " [OPTIONS]";
opt.example = string(argv[0]) + " --aggl strict --praet split --input /path/to/file.fsa";
// opt.footer = "Morfeusz Copyright (C) 2014\n";
|
|
28
|
|
|
29
|
opt.add(
|
|
30
31
32
33
34
35
36
37
38
39
|
"", // Default.
0, // Required?
0, // Number of args expected.
0, // Delimiter if expecting multiple args.
"Display usage instructions.", // Help description.
"-h", // Flag token.
"-help", // Flag token.
"--help", // Flag token.
"--usage" // Flag token.
);
|
|
40
|
|
|
41
42
43
44
45
46
47
48
49
50
|
opt.add(
"", // Default.
0, // Required?
1, // Number of args expected.
0, // Delimiter if expecting multiple args.
"file with analyzer finite state automaton and data, created with buildfsa.py script.", // Help description.
"-i", // Flag token.
"-input", // Flag token.
"--input" // Flag token.
);
|
|
51
|
|
|
52
53
54
55
56
57
58
59
60
61
|
opt.add(
"", // Default.
0, // Required?
1, // Number of args expected.
0, // Delimiter if expecting multiple args.
"aggl option.", // Help description.
"-a", // Flag token.
"-aggl", // Flag token.
"--aggl" // Flag token.
);
|
|
62
|
|
|
63
64
65
66
67
68
69
70
71
72
|
opt.add(
"", // Default.
0, // Required?
1, // Number of args expected.
0, // Delimiter if expecting multiple args.
"praet option.", // Help description.
"-p", // Flag token.
"-praet", // Flag token.
"--praet" // Flag token.
);
|
|
73
|
|
|
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
|
opt.add(
"", // Default.
0, // Required?
1, // Number of args expected.
0, // Delimiter if expecting multiple args.
"input/output charset", // Help description.
"-c", // Flag token.
"-charset", // Flag token.
"--charset" // Flag token.
);
if (processorType == ANALYZER) {
opt.add(
"", // Default.
0, // Required?
1, // Number of args expected.
0, // Delimiter if expecting multiple args.
|
|
91
92
93
94
95
96
|
"case handling strategy.\n \
WEAK - Case-sensitive but allows interpretations that do not match case but there is no alternative\n \
STRICT - strictly case-sensitive\n \
IGNORE - ignores case\n", // Help description.
"-case-handling", // Flag token.
"--case-handling" // Flag token.
|
|
97
98
99
100
101
102
|
);
opt.add(
"", // Default.
0, // Required?
1, // Number of args expected.
0, // Delimiter if expecting multiple args.
|
|
103
104
105
|
"token numbering strategy \
SEPARATE - Start from 0 and reset counter for every line\n \
CONTINUOUS - start from 0 and never reset counter", // Help description.
|
|
106
107
108
|
"-token-numbering", // Flag token.
"--token-numbering" // Flag token.
);
|
|
109
110
111
112
113
114
115
116
117
118
119
120
|
opt.add(
"", // Default.
0, // Required?
1, // Number of args expected.
0, // Delimiter if expecting multiple args.
"whitespace handling strategy. \n \
SKIP - ignore whitespaces \n \
APPEND - append whitespaces to preceding segment\n \
KEEP - whitespaces are separate segments", // Help description.
"-whitespace-handling", // Flag token.
"--whitespace-handling" // Flag token.
);
|
|
121
|
}
|
|
122
|
|
|
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
|
opt.add(
"", // Default.
0, // Required?
0, // Number of args expected.
0, // Delimiter if expecting multiple args.
"show some debug information.", // Help description.
"-d", // Flag token.
"-debug", // Flag token.
"--debug" // Flag token.
);
opt.parse(argc, argv);
if (opt.firstArgs.size() > 1) {
cerr << "Invalid argument (not bound to any flag): " << *opt.firstArgs[1] << endl;
exit(1);
|
|
139
|
}
|
|
140
141
142
143
144
145
146
147
148
149
150
151
|
if (!opt.lastArgs.empty()) {
cerr << "Invalid argument (not bound to any flag): " << *opt.lastArgs[0] << endl;
exit(1);
}
if (opt.isSet("-h")) {
printCLIUsage(opt, cout);
exit(0);
}
return &opt;
|
|
152
|
}
|
|
153
154
155
156
157
158
159
160
161
162
163
164
165
166
|
static Charset getCharset(const string& encodingStr) {
if (encodingStr == "UTF8")
return UTF8;
else if (encodingStr == "ISO8859_2")
return ISO8859_2;
else if (encodingStr == "CP1250")
return CP1250;
else if (encodingStr == "CP852")
return CP852;
else {
cerr << "Invalid encoding: '" << encodingStr << "'. Must be one of: UTF8, ISO8859_2, WINDOWS1250" << endl;
throw "Invalid encoding";
}
|
|
167
|
}
|
|
168
169
170
171
172
173
174
175
176
177
|
static TokenNumbering getTokenNumbering(const string& optionStr) {
if (optionStr == "SEPARATE")
return SEPARATE;
else if (optionStr == "CONTINUOUS")
return CONTINUOUS;
else {
cerr << "Invalid token numbering: '" << optionStr << "'. Must be one of: SEPARATE, CONTINUOUS" << endl;
throw "Invalid token numbering";
}
|
|
178
|
}
|
|
179
180
181
182
183
184
185
186
187
188
189
190
191
|
static CaseHandling getCaseHandling(const string& optionStr) {
if (optionStr == "WEAK")
return WEAK;
else if (optionStr == "STRICT")
return STRICT;
else if (optionStr == "IGNORE")
return IGNORE;
else {
cerr << "Invalid case handling: '" << optionStr << "'. Must be one of: WEAK, STRICT, IGNORE" << endl;
throw "Invalid token numbering";
}
}
|
|
192
193
194
195
196
197
198
199
200
201
202
203
204
|
static WhitespaceHandling getWhitespaceHandling(const string& optionStr) {
if (optionStr == "SKIP")
return SKIP;
else if (optionStr == "APPEND")
return APPEND;
else if (optionStr == "KEEP")
return KEEP;
else {
cerr << "Invalid whitespace handling: '" << optionStr << "'. Must be one of: SKIP, APPEND, KEEP" << endl;
throw "Invalid whitespace handling";
}
}
|
|
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
|
void initializeMorfeusz(ezOptionParser& opt, Morfeusz& morfeusz, MorfeuszProcessorType processorType) {
if (opt.isSet("-i")) {
string dictFile;
opt.get("-i")->getString(dictFile);
switch (processorType) {
case ANALYZER:
morfeusz.setAnalyzerDictionary(dictFile);
break;
case GENERATOR:
morfeusz.setGeneratorDictionary(dictFile);
break;
default:
break;
}
printf("Using dictionary from %s\n", dictFile.c_str());
}
if (opt.isSet("-a")) {
string aggl;
opt.get("-a")->getString(aggl);
cerr << "setting aggl option to " << aggl << endl;
morfeusz.setAggl(aggl);
}
if (opt.isSet("-p")) {
string praet;
opt.get("-p")->getString(praet);
cerr << "setting praet option to " << praet << endl;
morfeusz.setPraet(praet);
}
if (opt.isSet("-d")) {
cerr << "setting debug to TRUE" << endl;
morfeusz.setDebug(true);
}
if (opt.isSet("-c")) {
string charset;
opt.get("-c")->getString(charset);
cerr << "setting charset to " << charset << endl;
morfeusz.setCharset(getCharset(charset));
}
if (processorType == ANALYZER) {
|
|
246
247
248
249
250
|
if (opt.isSet("-case-handling")) {
string caseHandling;
opt.get("-case-handling")->getString(caseHandling);
cerr << "setting case handling to " << caseHandling << endl;
morfeusz.setCaseHandling(getCaseHandling(caseHandling));
|
|
251
252
253
254
255
256
257
258
|
}
if (opt.isSet("-token-numbering")) {
string tokenNumbering;
opt.get("-token-numbering")->getString(tokenNumbering);
cerr << "setting token numbering to " << tokenNumbering << endl;
morfeusz.setTokenNumbering(getTokenNumbering(tokenNumbering));
}
|
|
259
260
261
262
263
264
265
|
if (opt.isSet("-whitespace-handling")) {
string whitespaceHandling;
opt.get("-whitespace-handling")->getString(whitespaceHandling);
cerr << "setting whitespace handling to " << whitespaceHandling << endl;
morfeusz.setWhitespaceHandling(getWhitespaceHandling(whitespaceHandling));
}
|
|
266
267
|
}
|
|
268
|
#if defined(_WIN64) || defined(_WIN32)
|
|
269
|
morfeusz.setCharset(CP852);
|
|
270
|
#endif
|
|
271
|
}
|
|
272
273
|
}
|