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
|
/**
* Yudit Unicode Editor Source File
*
* GNU Copyright (C) 1997-2023 Gaspar Sinai <gaspar@yudit.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, version 2,
* dated June 1991. See file COPYYING for details.
*
* This program 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 General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#include "stoolkit/sencoder/SB_UInput.h"
#include "stoolkit/SString.h"
#include "stoolkit/SStringVector.h"
#include "stoolkit/STypes.h"
#include <stdlib.h>
/**
* This is a sample (base) implementation of the core encoding class
* @author: Gaspar Sinai <gaspar@yudit.org>
* @version: 2000-05-12
* E2 80 A8 E2 80 A9 are paragraph and line seps in utf-8 (U+20A8, U+20A9)
*/
SB_UInput::SB_UInput() : SBEncoder ("\n,\r\n,\r,\342\200\250,\342\200\251")
{
}
SB_UInput::~SB_UInput ()
{
}
/**
* This is encoding a unicode string into a bytestring
* @param input is a unicode string.
* endecode is not quite reversible
* it is producing \UXXXXXXXX and \uxxxx
*/
const SString&
SB_UInput::encode (const SV_UCS4& iucs)
{
sstring.clear();
for (unsigned int i=0; i<iucs.size(); i++)
{
quoteString (iucs[i]);
}
return sstring;
}
/**
* Decode an input string into a unicode string.
* This is good for an input method.
* @param input is a string.
* he output can be null, in this case a line is not
* read fully. If input size is zero output will be flushed.
* uXXXX or UXXXXXXXX
*/
const SV_UCS4&
SB_UInput::decode (const SString& _input)
{
ucs4string.clear();
if (_input.size()==0)
{
for (unsigned int k=0; k<input.size(); k++)
{
ucs4string.append ((SS_UCS4) ((unsigned char)input[k]));
}
input.clear();
return ucs4string;
}
input.append (_input);
SString cin = input;
cin.append ((char)0);
const unsigned char* in = (const unsigned char*) cin.array();
char* next;
unsigned int rd = 0;
/* see what we have */
SS_UCS4 decoded;
for (unsigned int i=0; i<input.size(); i++)
{
if (input.size() > i+4 && in[i] == 'u')
{
decoded = (SS_UCS4) strtoul ((char*) &in[i+1], &next, 16);
// success we append even zeros
if (in + i + 5 == (unsigned char*) next)
{
ucs4string.append (decoded);
rd += 5;
i += 4;
continue;
}
}
else if (input.size() > i+8 && in[i] == 'U')
{
decoded = (SS_UCS4) strtoul ((char*) &in[i+1], &next, 16);
// success we append even zeros
if (in + i + 9 == (unsigned char*) next)
{
ucs4string.append (decoded);
rd += 9;
i += 8;
continue;
}
}
unsigned int expected = 0;
if (input.size() ==1 && (in[i] == 'u' || in[i] == 'U')) break;
if (input.size() > 1 && in[i] == 'u')
{
expected = 5;
}
if (input.size() > 1 && in[i] == 'U')
{
expected = 9;
}
/* see if all can be good */
if (input.size() < i+expected && _input.size())
{
unsigned int j;
for (j=i+1; j<input.size(); j++)
{
if ((in[j] >= '0' && in[j] <='9')
|| (in[j] >= 'a' && in[j] <='f')
|| (in[j] >= 'A' && in[j] <='F'))
{
continue;
}
break;
}
if (j==input.size()) break;
}
decoded = (SS_UCS4) in[i];
ucs4string.append (decoded);
rd += 1;
}
while (rd--) input.remove(0);
return ucs4string;
}
/**
* clear input and output buffers.
*/
void
SB_UInput::clear ()
{
//input.clear();
}
SString
SB_UInput::preEditBuffer() const
{
return SString(input);
}
/**
* These methods guess the line delimiters for the input
* The one without arguments is giving the 'first approximation'
* It returns an inclusive list of all possibilities.
*/
const SStringVector&
SB_UInput::delimiters ()
{
return realDelimiters;
}
/**
* These methods guess the line delimiters for the input
* The one without arguments is giving the 'first approximation'
* It returns an exact list
*/
const SStringVector&
SB_UInput::delimiters (const SString& sample)
{
return sampleDelimiters;
}
/**
* return key value map to see what decodes to what
* @param key will contain the keys
* @param value will contain the values
* @param _size is the maximum size of returned arrays
* @return the real size of the arrays.
*/
unsigned int
SB_UInput::getDecoderMap (SStringVector* key, SStringVector* value,
unsigned int _size)
{
key->clear();
value->clear();
char sk[64];
char sv[64];
for (unsigned int i=0; i<_size && i<128 - 32; i++)
{
snprintf (sk, 64, "u%04d", i+32);
key->append (sk);
sv[0] = (char)(i+32);
sv[1] = 0;
value->append (sv);
}
return 0x7fffffff;
}
|
