gocr-ruby 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +22 -0
- data/Gemfile +4 -0
- data/LICENSE +21 -0
- data/LICENSE.txt +22 -0
- data/README.md +29 -0
- data/Rakefile +49 -0
- data/ext/gocr/Makefile +141 -0
- data/ext/gocr/Makefile.in +140 -0
- data/ext/gocr/amiga.h +31 -0
- data/ext/gocr/barcode.c +2108 -0
- data/ext/gocr/barcode.h +11 -0
- data/ext/gocr/box.c +496 -0
- data/ext/gocr/config.h +37 -0
- data/ext/gocr/config.h.in +36 -0
- data/ext/gocr/database.c +468 -0
- data/ext/gocr/detect.c +1003 -0
- data/ext/gocr/extconf.rb +6 -0
- data/ext/gocr/gocr.c +436 -0
- data/ext/gocr/gocr.h +290 -0
- data/ext/gocr/jconv.c +168 -0
- data/ext/gocr/job.c +92 -0
- data/ext/gocr/lines.c +364 -0
- data/ext/gocr/list.c +334 -0
- data/ext/gocr/list.h +91 -0
- data/ext/gocr/ocr0.c +7312 -0
- data/ext/gocr/ocr0.h +63 -0
- data/ext/gocr/ocr0n.c +1527 -0
- data/ext/gocr/ocr1.c +85 -0
- data/ext/gocr/ocr1.h +3 -0
- data/ext/gocr/otsu.c +310 -0
- data/ext/gocr/otsu.h +23 -0
- data/ext/gocr/output.c +291 -0
- data/ext/gocr/output.h +37 -0
- data/ext/gocr/pcx.c +153 -0
- data/ext/gocr/pcx.h +9 -0
- data/ext/gocr/pgm2asc.c +3259 -0
- data/ext/gocr/pgm2asc.h +105 -0
- data/ext/gocr/pixel.c +538 -0
- data/ext/gocr/pnm.c +538 -0
- data/ext/gocr/pnm.h +35 -0
- data/ext/gocr/progress.c +87 -0
- data/ext/gocr/progress.h +42 -0
- data/ext/gocr/remove.c +715 -0
- data/ext/gocr/tga.c +87 -0
- data/ext/gocr/tga.h +6 -0
- data/ext/gocr/unicode.c +1318 -0
- data/ext/gocr/unicode.h +62 -0
- data/ext/gocr/unicode_defs.h +1245 -0
- data/ext/gocr/version.h +2 -0
- data/gocr-ruby.gemspec +28 -0
- data/image.png +0 -0
- data/lib/gocr.rb +6 -0
- data/lib/gocr/image.rb +8 -0
- data/lib/gocr/version.rb +3 -0
- metadata +156 -0
data/ext/gocr/tga.c
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
1
|
+
/*
|
|
2
|
+
This is a Optical-Character-Recognition program
|
|
3
|
+
Copyright (C) 1999 Joerg Schulenburg
|
|
4
|
+
|
|
5
|
+
This program is free software; you can redistribute it and/or
|
|
6
|
+
modify it under the terms of the GNU General Public License
|
|
7
|
+
as published by the Free Software Foundation; either version 2
|
|
8
|
+
of the License, or (at your option) any later version.
|
|
9
|
+
|
|
10
|
+
This program is distributed in the hope that it will be useful,
|
|
11
|
+
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
12
|
+
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
13
|
+
GNU General Public License for more details.
|
|
14
|
+
|
|
15
|
+
You should have received a copy of the GNU General Public License
|
|
16
|
+
along with this program; if not, write to the Free Software
|
|
17
|
+
Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
|
|
18
|
+
|
|
19
|
+
see README for EMAIL-address
|
|
20
|
+
*/
|
|
21
|
+
|
|
22
|
+
#include <stdio.h>
|
|
23
|
+
#include <stdlib.h>
|
|
24
|
+
#include <assert.h>
|
|
25
|
+
|
|
26
|
+
#include "tga.h"
|
|
27
|
+
|
|
28
|
+
typedef unsigned char byte;
|
|
29
|
+
|
|
30
|
+
// --- needed for reading TGA-files
|
|
31
|
+
#if 0
|
|
32
|
+
char read_b(FILE *f1){ // filter #-comments
|
|
33
|
+
char c;
|
|
34
|
+
c=fgetc(f1); assert(!feof(f1)); assert(!ferror(f1));
|
|
35
|
+
return c;
|
|
36
|
+
}
|
|
37
|
+
#endif
|
|
38
|
+
|
|
39
|
+
//byte tga[18]={ 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,24,32};
|
|
40
|
+
/* header_hex= 00 00 02 00 00 00 00 00 00 00 00 00 xl xh yl yh
|
|
41
|
+
* 18 20 -- -- -- -- -- -- -- -- -- -- -- -- -- -- */
|
|
42
|
+
|
|
43
|
+
void readtga(char *name,pix *p,int mode){ // see pcx.format.txt
|
|
44
|
+
// mode: 0=gray,1=RGB
|
|
45
|
+
int nx,ny,i,x,y;
|
|
46
|
+
FILE *f1;
|
|
47
|
+
unsigned char *pic,h[18];
|
|
48
|
+
|
|
49
|
+
f1=fopen(name,"rb"); if(!f1) fprintf(stderr," error opening file\n");
|
|
50
|
+
assert(f1); // open-error
|
|
51
|
+
assert(fread(h,1,18,f1)==18); /* 18 Byte lesen -> h[] */
|
|
52
|
+
assert(h[ 0]== 0); // TGA0
|
|
53
|
+
assert(h[ 1]== 0); // TGA1
|
|
54
|
+
assert(h[ 2]== 2); // TGA2 no run length encoding
|
|
55
|
+
for(i=3;i<12;i++)
|
|
56
|
+
assert(h[ i]== 0); // ???
|
|
57
|
+
assert(h[16]==0x18); // TGA16
|
|
58
|
+
assert(h[17]==0x20); // TGA17
|
|
59
|
+
nx = h[12] + (h[13]<<8); /* x-dimension low high */
|
|
60
|
+
ny = h[14] + (h[15]<<8); /* y-dimension low high */
|
|
61
|
+
fprintf(stderr,"# TGA version=%d x=%d y=%d", h[2],nx,ny );
|
|
62
|
+
fflush(stdout);
|
|
63
|
+
pic=(unsigned char *)malloc( 3*nx*ny );
|
|
64
|
+
assert(pic!=NULL); // no memory
|
|
65
|
+
assert(ny==(int)fread(pic,3*nx,ny,f1)); // read all lines BGR
|
|
66
|
+
if(mode==0)
|
|
67
|
+
{
|
|
68
|
+
for(y=0;y<ny;y++) /* BGR => gray */
|
|
69
|
+
for(x=0;x<nx;x++)
|
|
70
|
+
{ i=x+y*nx; pic[i]=(pic[i*3+0]+pic[i*3+1]+pic[i*3+2])/3; }
|
|
71
|
+
}
|
|
72
|
+
else
|
|
73
|
+
if(mode==1)
|
|
74
|
+
{
|
|
75
|
+
byte b;
|
|
76
|
+
for(y=0;y<ny;y++) /* BGR => RGB */
|
|
77
|
+
for(x=0;x<nx;x++)
|
|
78
|
+
{ i=x+y*nx; b=pic[i*3+0]; pic[i*3+0]=pic[i*3+2]; pic[i*3+2]=b; }
|
|
79
|
+
}
|
|
80
|
+
else assert(0); // wrong mode
|
|
81
|
+
fclose(f1);
|
|
82
|
+
p->p=pic; p->x=nx; p->y=ny; p->bpp=1+2*mode;
|
|
83
|
+
fprintf(stderr," mode=%d\n",mode);
|
|
84
|
+
}
|
|
85
|
+
|
|
86
|
+
// ------------------------------------------------------------------------
|
|
87
|
+
|
data/ext/gocr/tga.h
ADDED
data/ext/gocr/unicode.c
ADDED
|
@@ -0,0 +1,1318 @@
|
|
|
1
|
+
/*
|
|
2
|
+
This is a Optical-Character-Recognition program
|
|
3
|
+
Copyright (C) 2000-2010 Joerg Schulenburg
|
|
4
|
+
|
|
5
|
+
This program is free software; you can redistribute it and/or
|
|
6
|
+
modify it under the terms of the GNU General Public License
|
|
7
|
+
as published by the Free Software Foundation; either version 2
|
|
8
|
+
of the License, or (at your option) any later version.
|
|
9
|
+
|
|
10
|
+
This program is distributed in the hope that it will be useful,
|
|
11
|
+
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
12
|
+
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
13
|
+
GNU General Public License for more details.
|
|
14
|
+
|
|
15
|
+
You should have received a copy of the GNU General Public License
|
|
16
|
+
along with this program; if not, write to the Free Software
|
|
17
|
+
Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
|
|
18
|
+
|
|
19
|
+
see README for EMAIL-address
|
|
20
|
+
*/
|
|
21
|
+
|
|
22
|
+
#include "unicode_defs.h" /* unicode table */
|
|
23
|
+
#include "unicode.h" /* convert functions and formats */
|
|
24
|
+
#include <stdio.h>
|
|
25
|
+
|
|
26
|
+
/* FIXME jb global */
|
|
27
|
+
int warn=0; /* if 1 a message is generated if composition is not defined */
|
|
28
|
+
|
|
29
|
+
/* Arguments: the character (main), and the modifier (accent, etc). See the
|
|
30
|
+
function if you want to know the modifiers.
|
|
31
|
+
Description: This function intends to be a small helper, to avoid having
|
|
32
|
+
to write switches in functions. It's therefore mainly to accents, and
|
|
33
|
+
specially for the most usual ones. It supports the basic greek
|
|
34
|
+
characters too, which is actually not very helpful.
|
|
35
|
+
Returns: the unicode character corresponding to the composed character.
|
|
36
|
+
|
|
37
|
+
ToDo:
|
|
38
|
+
- It seems to me, that tables should be more effectiv.
|
|
39
|
+
So we should use tables in future? (js)
|
|
40
|
+
*/
|
|
41
|
+
wchar_t compose(wchar_t main, wchar_t modifier) {
|
|
42
|
+
/* supported by now: part of ISO8859-1, basic greek characters */
|
|
43
|
+
if( main == UNKNOWN || main == PICTURE ) return main;
|
|
44
|
+
#ifdef DEBUG
|
|
45
|
+
if(modifier!=UNICODE_NULL && modifier!=SPACE)
|
|
46
|
+
printf(" compose(%c,%d)",(char)main,(int)modifier);
|
|
47
|
+
#endif
|
|
48
|
+
if(main>127 && modifier!=0 && modifier!=SPACE && warn)
|
|
49
|
+
fprintf(stderr,"# Warning compose %04x + %04x>127\n",
|
|
50
|
+
(int)modifier,(int)main);
|
|
51
|
+
switch (modifier) {
|
|
52
|
+
case UNICODE_NULL:
|
|
53
|
+
case SPACE:
|
|
54
|
+
return (wchar_t)main;
|
|
55
|
+
|
|
56
|
+
case APOSTROPHE: /* do NOT USE this. It's here for compatibility only.
|
|
57
|
+
Use ACUTE_ACCENT instead. */
|
|
58
|
+
fprintf( stderr, "COMPOSE: got APOSTROPHE instead of ACUTE_ACCENT");
|
|
59
|
+
|
|
60
|
+
case ACUTE_ACCENT: /* acute/cedilla */
|
|
61
|
+
switch (main) {
|
|
62
|
+
case 'a': return LATIN_SMALL_LETTER_A_WITH_ACUTE;
|
|
63
|
+
case 'A': return LATIN_CAPITAL_LETTER_A_WITH_ACUTE;
|
|
64
|
+
case LATIN_SMALL_LETTER_AE: return LATIN_SMALL_LETTER_AE_WITH_ACUTE;
|
|
65
|
+
case LATIN_CAPITAL_LETTER_AE: return LATIN_CAPITAL_LETTER_AE_WITH_ACUTE;
|
|
66
|
+
case 'c': return LATIN_SMALL_LETTER_C_WITH_ACUTE;
|
|
67
|
+
case 'C': return LATIN_CAPITAL_LETTER_C_WITH_ACUTE;
|
|
68
|
+
case 'e': return LATIN_SMALL_LETTER_E_WITH_ACUTE;
|
|
69
|
+
case 'E': return LATIN_CAPITAL_LETTER_E_WITH_ACUTE;
|
|
70
|
+
case 'g': return LATIN_SMALL_LETTER_G_WITH_ACUTE;
|
|
71
|
+
case 'G': return LATIN_CAPITAL_LETTER_G_WITH_ACUTE;
|
|
72
|
+
case 'i': return LATIN_SMALL_LETTER_I_WITH_ACUTE;
|
|
73
|
+
case 'I': return LATIN_CAPITAL_LETTER_I_WITH_ACUTE;
|
|
74
|
+
case 'l': return LATIN_SMALL_LETTER_L_WITH_ACUTE;
|
|
75
|
+
case 'L': return LATIN_CAPITAL_LETTER_L_WITH_ACUTE;
|
|
76
|
+
case 'n': return LATIN_SMALL_LETTER_N_WITH_ACUTE;
|
|
77
|
+
case 'N': return LATIN_CAPITAL_LETTER_N_WITH_ACUTE;
|
|
78
|
+
case 'o': return LATIN_SMALL_LETTER_O_WITH_ACUTE;
|
|
79
|
+
case 'O': return LATIN_CAPITAL_LETTER_O_WITH_ACUTE;
|
|
80
|
+
case '0': return LATIN_CAPITAL_LETTER_O_WITH_ACUTE;
|
|
81
|
+
case 'r': return LATIN_SMALL_LETTER_R_WITH_ACUTE;
|
|
82
|
+
case 'R': return LATIN_CAPITAL_LETTER_R_WITH_ACUTE;
|
|
83
|
+
case 's': return LATIN_SMALL_LETTER_S_WITH_ACUTE;
|
|
84
|
+
case 'S': return LATIN_CAPITAL_LETTER_S_WITH_ACUTE;
|
|
85
|
+
case 'u': return LATIN_SMALL_LETTER_U_WITH_ACUTE;
|
|
86
|
+
case 'U': return LATIN_CAPITAL_LETTER_U_WITH_ACUTE;
|
|
87
|
+
case 'y': return LATIN_SMALL_LETTER_Y_WITH_ACUTE;
|
|
88
|
+
case 'Y': return LATIN_CAPITAL_LETTER_Y_WITH_ACUTE;
|
|
89
|
+
case 'z': return LATIN_SMALL_LETTER_Z_WITH_ACUTE;
|
|
90
|
+
case 'Z': return LATIN_CAPITAL_LETTER_Z_WITH_ACUTE;
|
|
91
|
+
default:
|
|
92
|
+
if(warn)fprintf( stderr, " COMPOSE: ACUTE_ACCENT+%04x not defined\n",(int)main);
|
|
93
|
+
}
|
|
94
|
+
break;
|
|
95
|
+
|
|
96
|
+
case BREVE: /* caron (latin2) "u"-above-... (small bow) */
|
|
97
|
+
switch (main) {
|
|
98
|
+
/* FIXME write separate heuristics for breve */
|
|
99
|
+
case 'a': return LATIN_SMALL_LETTER_A_WITH_BREVE;
|
|
100
|
+
case 'A': return LATIN_CAPITAL_LETTER_A_WITH_BREVE;
|
|
101
|
+
case 'e': return LATIN_SMALL_LETTER_E_WITH_BREVE;
|
|
102
|
+
case 'E': return LATIN_CAPITAL_LETTER_E_WITH_BREVE;
|
|
103
|
+
case 'g': return LATIN_SMALL_LETTER_G_WITH_BREVE;
|
|
104
|
+
case 'G': return LATIN_CAPITAL_LETTER_G_WITH_BREVE;
|
|
105
|
+
case 'i': return LATIN_SMALL_LETTER_I_WITH_BREVE;
|
|
106
|
+
case 'I': return LATIN_CAPITAL_LETTER_I_WITH_BREVE;
|
|
107
|
+
case 'o': return LATIN_SMALL_LETTER_O_WITH_BREVE;
|
|
108
|
+
case 'O': return LATIN_CAPITAL_LETTER_O_WITH_BREVE;
|
|
109
|
+
case 'u': return LATIN_SMALL_LETTER_U_WITH_BREVE;
|
|
110
|
+
case 'U': return LATIN_CAPITAL_LETTER_U_WITH_BREVE;
|
|
111
|
+
default:
|
|
112
|
+
if(warn)fprintf( stderr, " COMPOSE: BREVE+%04x not defined\n",(int)main);
|
|
113
|
+
}
|
|
114
|
+
break;
|
|
115
|
+
|
|
116
|
+
case CARON: /* caron (latin2) "v"-above-... */
|
|
117
|
+
switch (main) {
|
|
118
|
+
case 'a': return LATIN_SMALL_LETTER_A_WITH_CARON;
|
|
119
|
+
case 'A': return LATIN_CAPITAL_LETTER_A_WITH_CARON;
|
|
120
|
+
case 'c': return LATIN_SMALL_LETTER_C_WITH_CARON;
|
|
121
|
+
case 'C': return LATIN_CAPITAL_LETTER_C_WITH_CARON;
|
|
122
|
+
case 'e': return LATIN_SMALL_LETTER_E_WITH_CARON;
|
|
123
|
+
case 'E': return LATIN_CAPITAL_LETTER_E_WITH_CARON;
|
|
124
|
+
case 'i': return LATIN_SMALL_LETTER_I_WITH_CARON;
|
|
125
|
+
case 'I': return LATIN_CAPITAL_LETTER_I_WITH_CARON;
|
|
126
|
+
case 'o': return LATIN_SMALL_LETTER_O_WITH_CARON;
|
|
127
|
+
case 'O': return LATIN_CAPITAL_LETTER_O_WITH_CARON;
|
|
128
|
+
case '0': return LATIN_CAPITAL_LETTER_O_WITH_CARON;
|
|
129
|
+
case 's': return LATIN_SMALL_LETTER_S_WITH_CARON;
|
|
130
|
+
case 'S': return LATIN_CAPITAL_LETTER_S_WITH_CARON;
|
|
131
|
+
case 'u': return LATIN_SMALL_LETTER_U_WITH_CARON;
|
|
132
|
+
case 'U': return LATIN_CAPITAL_LETTER_U_WITH_CARON;
|
|
133
|
+
case 'z': return LATIN_SMALL_LETTER_Z_WITH_CARON;
|
|
134
|
+
case 'Z': return LATIN_CAPITAL_LETTER_Z_WITH_CARON;
|
|
135
|
+
default:
|
|
136
|
+
if(warn)fprintf( stderr, " COMPOSE: CARON+%04x not defined\n",(int)main);
|
|
137
|
+
}
|
|
138
|
+
break;
|
|
139
|
+
|
|
140
|
+
case CEDILLA:
|
|
141
|
+
switch (main) {
|
|
142
|
+
case 'c': return LATIN_SMALL_LETTER_C_WITH_CEDILLA;
|
|
143
|
+
case 'C': return LATIN_CAPITAL_LETTER_C_WITH_CEDILLA;
|
|
144
|
+
default:
|
|
145
|
+
if(warn)fprintf( stderr, " COMPOSE: CEDILLA+%04x not defined\n",(int)main);
|
|
146
|
+
}
|
|
147
|
+
break;
|
|
148
|
+
|
|
149
|
+
case TILDE:
|
|
150
|
+
switch (main) {
|
|
151
|
+
case 'a': return LATIN_SMALL_LETTER_A_WITH_TILDE;
|
|
152
|
+
case 'A': return LATIN_CAPITAL_LETTER_A_WITH_TILDE;
|
|
153
|
+
case 'i': return LATIN_SMALL_LETTER_I_WITH_TILDE;
|
|
154
|
+
case 'I': return LATIN_CAPITAL_LETTER_I_WITH_TILDE;
|
|
155
|
+
case 'n': return LATIN_SMALL_LETTER_N_WITH_TILDE;
|
|
156
|
+
case 'N': return LATIN_CAPITAL_LETTER_N_WITH_TILDE;
|
|
157
|
+
case 'o': return LATIN_SMALL_LETTER_O_WITH_TILDE;
|
|
158
|
+
case 'O': return LATIN_CAPITAL_LETTER_O_WITH_TILDE;
|
|
159
|
+
case '0': return LATIN_CAPITAL_LETTER_O_WITH_TILDE;
|
|
160
|
+
case 'u': return LATIN_SMALL_LETTER_U_WITH_TILDE;
|
|
161
|
+
case 'U': return LATIN_CAPITAL_LETTER_U_WITH_TILDE;
|
|
162
|
+
default:
|
|
163
|
+
if(warn)fprintf( stderr, " COMPOSE: TILDE+%04x not defined\n",(int)main);
|
|
164
|
+
}
|
|
165
|
+
break;
|
|
166
|
+
|
|
167
|
+
case GRAVE_ACCENT:
|
|
168
|
+
switch (main) {
|
|
169
|
+
case 'a': return LATIN_SMALL_LETTER_A_WITH_GRAVE;
|
|
170
|
+
case 'A': return LATIN_CAPITAL_LETTER_A_WITH_GRAVE;
|
|
171
|
+
case 'e': return LATIN_SMALL_LETTER_E_WITH_GRAVE;
|
|
172
|
+
case 'E': return LATIN_CAPITAL_LETTER_E_WITH_GRAVE;
|
|
173
|
+
case 'i': return LATIN_SMALL_LETTER_I_WITH_GRAVE;
|
|
174
|
+
case 'I': return LATIN_CAPITAL_LETTER_I_WITH_GRAVE;
|
|
175
|
+
case 'n': return LATIN_SMALL_LETTER_N_WITH_GRAVE;
|
|
176
|
+
case 'N': return LATIN_CAPITAL_LETTER_N_WITH_GRAVE;
|
|
177
|
+
case 'o': return LATIN_SMALL_LETTER_O_WITH_GRAVE;
|
|
178
|
+
case 'O': return LATIN_CAPITAL_LETTER_O_WITH_GRAVE;
|
|
179
|
+
case '0': return LATIN_CAPITAL_LETTER_O_WITH_GRAVE;
|
|
180
|
+
case 'u': return LATIN_SMALL_LETTER_U_WITH_GRAVE;
|
|
181
|
+
case 'U': return LATIN_CAPITAL_LETTER_U_WITH_GRAVE;
|
|
182
|
+
default:
|
|
183
|
+
if(warn)fprintf( stderr, " COMPOSE: GRAVE_ACCENT+%04x not defined\n",(int)main);
|
|
184
|
+
}
|
|
185
|
+
break;
|
|
186
|
+
|
|
187
|
+
case QUOTATION_MARK: /* do NOT USE this. It's here for compatibility only.
|
|
188
|
+
Use DIAERESIS instead. */
|
|
189
|
+
fprintf( stderr, "COMPOSE: got APOSTROPHE instead of ACUTE_ACCENT");
|
|
190
|
+
|
|
191
|
+
case DIAERESIS:
|
|
192
|
+
switch (main) {
|
|
193
|
+
case 'a': return LATIN_SMALL_LETTER_A_WITH_DIAERESIS;
|
|
194
|
+
case 'A': return LATIN_CAPITAL_LETTER_A_WITH_DIAERESIS;
|
|
195
|
+
case 'e': return LATIN_SMALL_LETTER_E_WITH_DIAERESIS;
|
|
196
|
+
case 'E': return LATIN_CAPITAL_LETTER_E_WITH_DIAERESIS;
|
|
197
|
+
case 'i': return LATIN_SMALL_LETTER_I_WITH_DIAERESIS;
|
|
198
|
+
case 'I': return LATIN_CAPITAL_LETTER_I_WITH_DIAERESIS;
|
|
199
|
+
case 'o': return LATIN_SMALL_LETTER_O_WITH_DIAERESIS;
|
|
200
|
+
case 'O': return LATIN_CAPITAL_LETTER_O_WITH_DIAERESIS;
|
|
201
|
+
case '0': return LATIN_CAPITAL_LETTER_O_WITH_DIAERESIS;
|
|
202
|
+
case 'u': return LATIN_SMALL_LETTER_U_WITH_DIAERESIS;
|
|
203
|
+
case 'U': return LATIN_CAPITAL_LETTER_U_WITH_DIAERESIS;
|
|
204
|
+
case 'y': return LATIN_SMALL_LETTER_Y_WITH_DIAERESIS;
|
|
205
|
+
case 'Y': return LATIN_CAPITAL_LETTER_Y_WITH_DIAERESIS;
|
|
206
|
+
default:
|
|
207
|
+
if(warn)fprintf( stderr, " COMPOSE: DIAERESIS+%04x (%c) not defined\n",(int)main,(char)main);
|
|
208
|
+
}
|
|
209
|
+
break;
|
|
210
|
+
|
|
211
|
+
case CIRCUMFLEX_ACCENT: /* ^ */
|
|
212
|
+
switch (main) {
|
|
213
|
+
case 'a': return LATIN_SMALL_LETTER_A_WITH_CIRCUMFLEX;
|
|
214
|
+
case 'A': return LATIN_CAPITAL_LETTER_A_WITH_CIRCUMFLEX;
|
|
215
|
+
case 'c': return LATIN_SMALL_LETTER_C_WITH_CIRCUMFLEX;
|
|
216
|
+
case 'C': return LATIN_CAPITAL_LETTER_C_WITH_CIRCUMFLEX;
|
|
217
|
+
case 'e': return LATIN_SMALL_LETTER_E_WITH_CIRCUMFLEX;
|
|
218
|
+
case 'E': return LATIN_CAPITAL_LETTER_E_WITH_CIRCUMFLEX;
|
|
219
|
+
case 'g': return LATIN_SMALL_LETTER_G_WITH_CIRCUMFLEX;
|
|
220
|
+
case 'G': return LATIN_CAPITAL_LETTER_G_WITH_CIRCUMFLEX;
|
|
221
|
+
case 'h': return LATIN_SMALL_LETTER_H_WITH_CIRCUMFLEX;
|
|
222
|
+
case 'H': return LATIN_CAPITAL_LETTER_H_WITH_CIRCUMFLEX;
|
|
223
|
+
case 'i': return LATIN_SMALL_LETTER_I_WITH_CIRCUMFLEX;
|
|
224
|
+
case 'I': return LATIN_CAPITAL_LETTER_I_WITH_CIRCUMFLEX;
|
|
225
|
+
case 'j': return LATIN_SMALL_LETTER_J_WITH_CIRCUMFLEX;
|
|
226
|
+
case 'J': return LATIN_CAPITAL_LETTER_J_WITH_CIRCUMFLEX;
|
|
227
|
+
case 'o': return LATIN_SMALL_LETTER_O_WITH_CIRCUMFLEX;
|
|
228
|
+
case 'O': return LATIN_CAPITAL_LETTER_O_WITH_CIRCUMFLEX;
|
|
229
|
+
case '0': return LATIN_CAPITAL_LETTER_O_WITH_CIRCUMFLEX;
|
|
230
|
+
case 's': return LATIN_SMALL_LETTER_S_WITH_CIRCUMFLEX;
|
|
231
|
+
case 'S': return LATIN_CAPITAL_LETTER_S_WITH_CIRCUMFLEX;
|
|
232
|
+
case 'u': return LATIN_SMALL_LETTER_U_WITH_CIRCUMFLEX;
|
|
233
|
+
case 'U': return LATIN_CAPITAL_LETTER_U_WITH_CIRCUMFLEX;
|
|
234
|
+
case 'w': return LATIN_SMALL_LETTER_W_WITH_CIRCUMFLEX;
|
|
235
|
+
case 'W': return LATIN_CAPITAL_LETTER_W_WITH_CIRCUMFLEX;
|
|
236
|
+
case 'y': return LATIN_SMALL_LETTER_Y_WITH_CIRCUMFLEX;
|
|
237
|
+
case 'Y': return LATIN_CAPITAL_LETTER_Y_WITH_CIRCUMFLEX;
|
|
238
|
+
default:
|
|
239
|
+
if(warn)fprintf( stderr, " COMPOSE: CIRCUMFLEX_ACCENT+%04x not defined\n",(int)main);
|
|
240
|
+
}
|
|
241
|
+
break;
|
|
242
|
+
|
|
243
|
+
case MACRON: /* a minus sign above the char (latin2) */
|
|
244
|
+
switch (main) {
|
|
245
|
+
case 'a': return LATIN_SMALL_LETTER_A_WITH_MACRON;
|
|
246
|
+
case 'A': return LATIN_CAPITAL_LETTER_A_WITH_MACRON;
|
|
247
|
+
case 'e': return LATIN_SMALL_LETTER_E_WITH_MACRON;
|
|
248
|
+
case 'E': return LATIN_CAPITAL_LETTER_E_WITH_MACRON;
|
|
249
|
+
case 'i': return LATIN_SMALL_LETTER_I_WITH_MACRON;
|
|
250
|
+
case 'I': return LATIN_CAPITAL_LETTER_I_WITH_MACRON;
|
|
251
|
+
case 'o': return LATIN_SMALL_LETTER_O_WITH_MACRON;
|
|
252
|
+
case 'O': return LATIN_CAPITAL_LETTER_O_WITH_MACRON;
|
|
253
|
+
case 'u': return LATIN_SMALL_LETTER_U_WITH_MACRON;
|
|
254
|
+
case 'U': return LATIN_CAPITAL_LETTER_U_WITH_MACRON;
|
|
255
|
+
case 'y': return LATIN_SMALL_LETTER_Y_WITH_MACRON;
|
|
256
|
+
case 'Y': return LATIN_CAPITAL_LETTER_Y_WITH_MACRON;
|
|
257
|
+
case LATIN_SMALL_LETTER_AE: return LATIN_SMALL_LETTER_AE_WITH_MACRON;
|
|
258
|
+
case LATIN_CAPITAL_LETTER_AE: return LATIN_CAPITAL_LETTER_AE_WITH_MACRON;
|
|
259
|
+
case '=': return IDENTICAL_TO;
|
|
260
|
+
case '-': return '=';
|
|
261
|
+
case ' ': return MODIFIER_LETTER_MACRON;
|
|
262
|
+
default:
|
|
263
|
+
if(warn)fprintf( stderr, " COMPOSE: MACRON+%04x not defined\n",(int)main);
|
|
264
|
+
}
|
|
265
|
+
break;
|
|
266
|
+
|
|
267
|
+
case DOT_ABOVE: /* latin2 */
|
|
268
|
+
switch (main) {
|
|
269
|
+
case 'a': return LATIN_SMALL_LETTER_A_WITH_DOT_ABOVE;
|
|
270
|
+
case 'A': return LATIN_CAPITAL_LETTER_A_WITH_DOT_ABOVE;
|
|
271
|
+
case 'c': return LATIN_SMALL_LETTER_C_WITH_DOT_ABOVE;
|
|
272
|
+
case 'C': return LATIN_CAPITAL_LETTER_C_WITH_DOT_ABOVE;
|
|
273
|
+
case 'e': return LATIN_SMALL_LETTER_E_WITH_DOT_ABOVE;
|
|
274
|
+
case 'E': return LATIN_CAPITAL_LETTER_E_WITH_DOT_ABOVE;
|
|
275
|
+
case 'g': return LATIN_SMALL_LETTER_G_WITH_DOT_ABOVE;
|
|
276
|
+
case 'G': return LATIN_CAPITAL_LETTER_G_WITH_DOT_ABOVE;
|
|
277
|
+
case 'l': return 'i'; /* correct wrong recognition */
|
|
278
|
+
case 'i': return 'i';
|
|
279
|
+
case LATIN_SMALL_LETTER_DOTLESS_I: return 'i';
|
|
280
|
+
case 'I': return LATIN_CAPITAL_LETTER_I_WITH_DOT_ABOVE;
|
|
281
|
+
case 'j': return 'j';
|
|
282
|
+
case 'o': return LATIN_SMALL_LETTER_O_WITH_DOT_ABOVE;
|
|
283
|
+
case 'O': return LATIN_CAPITAL_LETTER_O_WITH_DOT_ABOVE;
|
|
284
|
+
case 'z': return LATIN_SMALL_LETTER_Z_WITH_DOT_ABOVE;
|
|
285
|
+
case 'Z': return LATIN_CAPITAL_LETTER_Z_WITH_DOT_ABOVE;
|
|
286
|
+
case ',': return ';';
|
|
287
|
+
case '.': return ':';
|
|
288
|
+
default:
|
|
289
|
+
if(warn)fprintf( stderr, " COMPOSE: DOT_ABOVE+%04x not defined\n",(int)main);
|
|
290
|
+
}
|
|
291
|
+
break;
|
|
292
|
+
|
|
293
|
+
case RING_ABOVE:
|
|
294
|
+
switch (main) {
|
|
295
|
+
case 'a': return LATIN_SMALL_LETTER_A_WITH_RING_ABOVE;
|
|
296
|
+
case 'A': return LATIN_CAPITAL_LETTER_A_WITH_RING_ABOVE;
|
|
297
|
+
case 'u': return LATIN_SMALL_LETTER_U_WITH_RING_ABOVE;
|
|
298
|
+
case 'U': return LATIN_CAPITAL_LETTER_U_WITH_RING_ABOVE;
|
|
299
|
+
default:
|
|
300
|
+
if(warn)fprintf( stderr, " COMPOSE: RING_ABOVE+%04x not defined\n",(int)main);
|
|
301
|
+
}
|
|
302
|
+
break;
|
|
303
|
+
|
|
304
|
+
case 'e': /* e ligatures: ae, oe. */
|
|
305
|
+
case 'E':
|
|
306
|
+
switch (main) {
|
|
307
|
+
case 'a': return LATIN_SMALL_LETTER_AE;
|
|
308
|
+
case 'A': return LATIN_CAPITAL_LETTER_AE;
|
|
309
|
+
case 'o': return LATIN_SMALL_LIGATURE_OE;
|
|
310
|
+
case 'O': return LATIN_CAPITAL_LIGATURE_OE;
|
|
311
|
+
case '0': return LATIN_CAPITAL_LIGATURE_OE;
|
|
312
|
+
default:
|
|
313
|
+
if(warn)fprintf( stderr, " COMPOSE: %04x+e/E not defined\n",(int)main);
|
|
314
|
+
}
|
|
315
|
+
break;
|
|
316
|
+
|
|
317
|
+
case 'g': /* greek */
|
|
318
|
+
switch (main) {
|
|
319
|
+
/* missing 0x37A-0x390 */
|
|
320
|
+
/* weird cases: Q -> theta (it resembles a little, doesn't it?)
|
|
321
|
+
V -> psi (what can I do?) */
|
|
322
|
+
case 'A': return GREEK_CAPITAL_LETTER_ALPHA;
|
|
323
|
+
case 'B': return GREEK_CAPITAL_LETTER_BETA;
|
|
324
|
+
case 'G': return GREEK_CAPITAL_LETTER_GAMMA;
|
|
325
|
+
case 'D': return GREEK_CAPITAL_LETTER_DELTA;
|
|
326
|
+
case 'E': return GREEK_CAPITAL_LETTER_EPSILON;
|
|
327
|
+
case 'Z': return GREEK_CAPITAL_LETTER_ZETA;
|
|
328
|
+
case 'H': return GREEK_CAPITAL_LETTER_ETA;
|
|
329
|
+
case 'Q': return GREEK_CAPITAL_LETTER_THETA;
|
|
330
|
+
case 'I': return GREEK_CAPITAL_LETTER_IOTA;
|
|
331
|
+
case 'K': return GREEK_CAPITAL_LETTER_KAPPA;
|
|
332
|
+
case 'L': return GREEK_CAPITAL_LETTER_LAMDA;
|
|
333
|
+
case 'M': return GREEK_CAPITAL_LETTER_MU;
|
|
334
|
+
case 'N': return GREEK_CAPITAL_LETTER_NU;
|
|
335
|
+
case 'X': return GREEK_CAPITAL_LETTER_XI;
|
|
336
|
+
case 'O': return GREEK_CAPITAL_LETTER_OMICRON;
|
|
337
|
+
case 'P': return GREEK_CAPITAL_LETTER_PI;
|
|
338
|
+
case 'R': return GREEK_CAPITAL_LETTER_RHO;
|
|
339
|
+
case 'S': return GREEK_CAPITAL_LETTER_SIGMA;
|
|
340
|
+
case 'T': return GREEK_CAPITAL_LETTER_TAU;
|
|
341
|
+
case 'Y': return GREEK_CAPITAL_LETTER_UPSILON;
|
|
342
|
+
case 'F': return GREEK_CAPITAL_LETTER_PHI;
|
|
343
|
+
case 'C': return GREEK_CAPITAL_LETTER_CHI;
|
|
344
|
+
case 'V': return GREEK_CAPITAL_LETTER_PSI;
|
|
345
|
+
case 'W': return GREEK_CAPITAL_LETTER_OMEGA;
|
|
346
|
+
/*
|
|
347
|
+
case '': return GREEK_CAPITAL_LETTER_IOTA_WITH_DIALYTIKA;
|
|
348
|
+
case '': return GREEK_CAPITAL_LETTER_UPSILON_WITH_DIALYTIKA;
|
|
349
|
+
case '': return GREEK_SMALL_LETTER_ALPHA_WITH_TONOS;
|
|
350
|
+
case '': return GREEK_SMALL_LETTER_EPSILON_WITH_TONOS;
|
|
351
|
+
case '': return GREEK_SMALL_LETTER_ETA_WITH_TONOS;
|
|
352
|
+
case '': return GREEK_SMALL_LETTER_IOTA_WITH_TONOS;
|
|
353
|
+
case '': return GREEK_SMALL_LETTER_UPSILON_WITH_DIALYTIKA_AND_TONOS;
|
|
354
|
+
*/
|
|
355
|
+
case 'a': return GREEK_SMALL_LETTER_ALPHA;
|
|
356
|
+
case 'b': return GREEK_SMALL_LETTER_BETA;
|
|
357
|
+
case 'g': return GREEK_SMALL_LETTER_GAMMA;
|
|
358
|
+
case 'd': return GREEK_SMALL_LETTER_DELTA;
|
|
359
|
+
case 'e': return GREEK_SMALL_LETTER_EPSILON;
|
|
360
|
+
case 'z': return GREEK_SMALL_LETTER_ZETA;
|
|
361
|
+
case 'h': return GREEK_SMALL_LETTER_ETA;
|
|
362
|
+
case 'q': return GREEK_SMALL_LETTER_THETA;
|
|
363
|
+
case 'i': return GREEK_SMALL_LETTER_IOTA;
|
|
364
|
+
case 'k': return GREEK_SMALL_LETTER_KAPPA;
|
|
365
|
+
case 'l': return GREEK_SMALL_LETTER_LAMDA;
|
|
366
|
+
case 'm': return GREEK_SMALL_LETTER_MU;
|
|
367
|
+
case 'n': return GREEK_SMALL_LETTER_NU;
|
|
368
|
+
case 'x': return GREEK_SMALL_LETTER_XI;
|
|
369
|
+
case 'o': return GREEK_SMALL_LETTER_OMICRON;
|
|
370
|
+
case 'p': return GREEK_SMALL_LETTER_PI;
|
|
371
|
+
case 'r': return GREEK_SMALL_LETTER_RHO;
|
|
372
|
+
case '&': return GREEK_SMALL_LETTER_FINAL_SIGMA;
|
|
373
|
+
case 's': return GREEK_SMALL_LETTER_SIGMA;
|
|
374
|
+
case 't': return GREEK_SMALL_LETTER_TAU;
|
|
375
|
+
case 'y': return GREEK_SMALL_LETTER_UPSILON;
|
|
376
|
+
case 'f': return GREEK_SMALL_LETTER_PHI;
|
|
377
|
+
case 'c': return GREEK_SMALL_LETTER_CHI;
|
|
378
|
+
case 'v': return GREEK_SMALL_LETTER_PSI;
|
|
379
|
+
case 'w': return GREEK_SMALL_LETTER_OMEGA;
|
|
380
|
+
/*
|
|
381
|
+
case '': return GREEK_SMALL_LETTER_IOTA_WITH_DIALYTIKA;
|
|
382
|
+
case '': return GREEK_SMALL_LETTER_UPSILON_WITH_DIALYTIKA;
|
|
383
|
+
case '': return GREEK_SMALL_LETTER_OMICRON_WITH_TONOS;
|
|
384
|
+
case '': return GREEK_SMALL_LETTER_UPSILON_WITH_TONOS;
|
|
385
|
+
case '': return GREEK_SMALL_LETTER_OMEGA_WITH_TONOS;
|
|
386
|
+
case '': return GREEK_BETA_SYMBOL;
|
|
387
|
+
case '': return GREEK_THETA_SYMBOL;
|
|
388
|
+
case '': return GREEK_UPSILON_WITH_HOOK_SYMBOL;
|
|
389
|
+
case '': return GREEK_UPSILON_WITH_ACUTE_AND_HOOK_SYMBOL;
|
|
390
|
+
case '': return GREEK_UPSILON_WITH_DIAERESIS_AND_HOOK_SYMBOL;
|
|
391
|
+
case '': return GREEK_PHI_SYMBOL;
|
|
392
|
+
case '': return GREEK_PI_SYMBOL;
|
|
393
|
+
*/
|
|
394
|
+
default:
|
|
395
|
+
if(warn)fprintf( stderr, " COMPOSE: GREEK %04x not defined\n",(int)main);
|
|
396
|
+
}
|
|
397
|
+
break;
|
|
398
|
+
|
|
399
|
+
default:
|
|
400
|
+
fprintf( stderr, " COMPOSE: modifier %04x not defined\n",(int)modifier);
|
|
401
|
+
}
|
|
402
|
+
return (wchar_t)main;
|
|
403
|
+
}
|
|
404
|
+
|
|
405
|
+
#define UNDEFINED "~"
|
|
406
|
+
|
|
407
|
+
/* Arguments: character in Unicode format, type of format to convert to.
|
|
408
|
+
Returns: a string containing the Unicode character converted to the chosen
|
|
409
|
+
format. This string is statically allocated and should not be freed.
|
|
410
|
+
ToDo: better using tables?
|
|
411
|
+
*/
|
|
412
|
+
const char *decode(wchar_t c, FORMAT type) {
|
|
413
|
+
/* static char d; --- js: big bug (missing \0) if &d returned */
|
|
414
|
+
/*FIXME jb static*/ static char bbuf[8*32]; /* space for 8 buffers, rotating */
|
|
415
|
+
/*FIXME jb static*/ static char *buf=bbuf; /* used for UTF8 sequences and undefined codes */
|
|
416
|
+
buf+=32; if(buf>=bbuf+8*32) buf=bbuf;
|
|
417
|
+
buf[0]=buf[1]=buf[2]=0;
|
|
418
|
+
switch (type) {
|
|
419
|
+
case ISO8859_1:
|
|
420
|
+
if ( c <= 0xFF ) { /* UNICODE == ISO8859-1 */
|
|
421
|
+
buf[0] = (char)c;
|
|
422
|
+
return buf;
|
|
423
|
+
}
|
|
424
|
+
switch (c) { /* not found in list, but perhaps we can describe it */
|
|
425
|
+
/* todo: add greek. GREEK_SMALL_LETTER_ALPHA = alpha */
|
|
426
|
+
|
|
427
|
+
/* general puctuation */
|
|
428
|
+
case HYPHEN:
|
|
429
|
+
return (const char *)"-";
|
|
430
|
+
case FIGURE_DASH:
|
|
431
|
+
case EN_DASH:
|
|
432
|
+
return (const char *)"--";
|
|
433
|
+
case EM_DASH:
|
|
434
|
+
return (const char *)"---";
|
|
435
|
+
case LEFT_SINGLE_QUOTATION_MARK:
|
|
436
|
+
return (const char *)"`";
|
|
437
|
+
case RIGHT_SINGLE_QUOTATION_MARK:
|
|
438
|
+
return (const char *)"'";
|
|
439
|
+
case SINGLE_LOW_9_QUOTATION_MARK:
|
|
440
|
+
return (const char *)",";
|
|
441
|
+
case SINGLE_HIGH_REVERSED_9_QUOTATION_MARK:
|
|
442
|
+
return (const char *)UNDEFINED;
|
|
443
|
+
case LEFT_DOUBLE_QUOTATION_MARK:
|
|
444
|
+
return (const char *)"``";
|
|
445
|
+
case RIGHT_DOUBLE_QUOTATION_MARK:
|
|
446
|
+
return (const char *)"''";
|
|
447
|
+
case DOUBLE_LOW_9_QUOTATION_MARK:
|
|
448
|
+
return (const char *)",,";
|
|
449
|
+
case DOUBLE_HIGH_REVERSED_9_QUOTATION_MARK:
|
|
450
|
+
return (const char *)UNDEFINED;
|
|
451
|
+
case DAGGER:
|
|
452
|
+
return (const char *)"+";
|
|
453
|
+
case DOUBLE_DAGGER:
|
|
454
|
+
return (const char *)"*";
|
|
455
|
+
case BULLET:
|
|
456
|
+
return (const char *)"*";
|
|
457
|
+
case TRIANGULAR_BULLET:
|
|
458
|
+
return (const char *)"*";
|
|
459
|
+
case HYPHENATION_POINT:
|
|
460
|
+
return (const char *)"-";
|
|
461
|
+
case HORIZONTAL_ELLIPSIS:
|
|
462
|
+
return (const char *)"...";
|
|
463
|
+
case PER_MILLE_SIGN:
|
|
464
|
+
return (const char *)"%%"; /* awk! */
|
|
465
|
+
case SINGLE_LEFT_POINTING_ANGLE_QUOTATION_MARK:
|
|
466
|
+
return (const char *)"<";
|
|
467
|
+
case SINGLE_RIGHT_POINTING_ANGLE_QUOTATION_MARK:
|
|
468
|
+
return (const char *)">";
|
|
469
|
+
case EURO_CURRENCY_SIGN:
|
|
470
|
+
return (const char *)"EUR"; /* change it! */
|
|
471
|
+
|
|
472
|
+
/* ligatures */
|
|
473
|
+
case LATIN_SMALL_LIGATURE_FF:
|
|
474
|
+
return (const char *)"ff";
|
|
475
|
+
case LATIN_SMALL_LIGATURE_FI:
|
|
476
|
+
return (const char *)"fi";
|
|
477
|
+
case LATIN_SMALL_LIGATURE_FL:
|
|
478
|
+
return (const char *)"fl";
|
|
479
|
+
case LATIN_SMALL_LIGATURE_FFI:
|
|
480
|
+
return (const char *)"ffi";
|
|
481
|
+
case LATIN_SMALL_LIGATURE_FFL:
|
|
482
|
+
return (const char *)"ffl";
|
|
483
|
+
case LATIN_SMALL_LIGATURE_LONG_S_T:
|
|
484
|
+
case LATIN_SMALL_LIGATURE_ST:
|
|
485
|
+
return (const char *)"st";
|
|
486
|
+
|
|
487
|
+
/* extra */
|
|
488
|
+
case UNKNOWN:
|
|
489
|
+
return (const char *)"_";
|
|
490
|
+
case PICTURE:
|
|
491
|
+
return (const char *)"_"; /* Due to Mobile OCR */
|
|
492
|
+
|
|
493
|
+
default:
|
|
494
|
+
/* snprintf seems to be no standard, so I use insecure sprintf */
|
|
495
|
+
sprintf(buf,"\\code(%04x)",(unsigned)c);
|
|
496
|
+
return buf; /* UNDEFINED; */
|
|
497
|
+
}
|
|
498
|
+
break;
|
|
499
|
+
case TeX:
|
|
500
|
+
if ( c >= SPACE && c <= TILDE ) { /* ASCII */
|
|
501
|
+
switch (c) {
|
|
502
|
+
case '$':
|
|
503
|
+
return (const char *)"\\$";
|
|
504
|
+
case '&':
|
|
505
|
+
return (const char *)"\\&";
|
|
506
|
+
case '%':
|
|
507
|
+
return (const char *)"\\%";
|
|
508
|
+
case '#':
|
|
509
|
+
return (const char *)"\\#";
|
|
510
|
+
case '_':
|
|
511
|
+
return (const char *)"\\_";
|
|
512
|
+
case '{':
|
|
513
|
+
return (const char *)"\\{";
|
|
514
|
+
case '}':
|
|
515
|
+
return (const char *)"\\}";
|
|
516
|
+
case '\\':
|
|
517
|
+
return (const char *)"\\textbackslash";
|
|
518
|
+
case '~':
|
|
519
|
+
return (const char *)"\\~{}";
|
|
520
|
+
case '^':
|
|
521
|
+
return (const char *)"\\^{}";
|
|
522
|
+
default:
|
|
523
|
+
buf[0] = (char)c;
|
|
524
|
+
return (const char *)buf;
|
|
525
|
+
}
|
|
526
|
+
}
|
|
527
|
+
switch (c) {
|
|
528
|
+
/* ISO8859_1 */
|
|
529
|
+
case NO_BREAK_SPACE:
|
|
530
|
+
return (const char *)"~";
|
|
531
|
+
case INVERTED_EXCLAMATION_MARK:
|
|
532
|
+
return (const char *)"!'";
|
|
533
|
+
case CENT_SIGN:
|
|
534
|
+
return (const char *)"\\textcent"; /* \usepackage{textcomp} */
|
|
535
|
+
case POUND_SIGN:
|
|
536
|
+
return (const char *)"\\pounds";
|
|
537
|
+
case EURO_CURRENCY_SIGN:
|
|
538
|
+
return (const char *)"\\euro"; /* \usepackage{eurosans} */
|
|
539
|
+
case CURRENCY_SIGN:
|
|
540
|
+
return (const char *)"\\textcurrency"; /* \usepackage{textcomp} */
|
|
541
|
+
case YEN_SIGN:
|
|
542
|
+
return (const char *)"\\textyen"; /* \usepackage{textcomp} */
|
|
543
|
+
case BROKEN_BAR:
|
|
544
|
+
return (const char *)"\\textbrokenbar"; /* \usepackage{textcomp} */
|
|
545
|
+
case SECTION_SIGN:
|
|
546
|
+
return (const char *)"\\S";
|
|
547
|
+
case DIAERESIS:
|
|
548
|
+
return (const char *)"\"";
|
|
549
|
+
case COPYRIGHT_SIGN:
|
|
550
|
+
return (const char *)"\\copyright";
|
|
551
|
+
case FEMININE_ORDINAL_INDICATOR:
|
|
552
|
+
return (const char *)"$^{\\underbar{a}}$";
|
|
553
|
+
case LEFT_POINTING_DOUBLE_ANGLE_QUOTATION_MARK:
|
|
554
|
+
return (const char *)"\\flqq{}";
|
|
555
|
+
case NOT_SIGN:
|
|
556
|
+
return (const char *)"$\\lnot$";
|
|
557
|
+
case SOFT_HYPHEN:
|
|
558
|
+
return (const char *)"\\-";
|
|
559
|
+
case REGISTERED_SIGN:
|
|
560
|
+
return (const char *)"\\textregistered";/* \usepackage{textcomp} */
|
|
561
|
+
case MACRON:
|
|
562
|
+
return (const char *)"\\textasciimacron";/* \usepackage{textcomp} */
|
|
563
|
+
case DEGREE_SIGN:
|
|
564
|
+
return (const char *)"$^{o}$";
|
|
565
|
+
case PLUS_MINUS_SIGN:
|
|
566
|
+
return (const char *)"$\\pm$";
|
|
567
|
+
case SUPERSCRIPT_TWO:
|
|
568
|
+
return (const char *)"$^{2}$";
|
|
569
|
+
case SUPERSCRIPT_THREE:
|
|
570
|
+
return (const char *)"$^{3}$";
|
|
571
|
+
case ACUTE_ACCENT:
|
|
572
|
+
return (const char *)"\\( \\prime \\)";
|
|
573
|
+
case MICRO_SIGN:
|
|
574
|
+
return (const char *)"$\\mu$";
|
|
575
|
+
case PILCROW_SIGN:
|
|
576
|
+
return (const char *)"\\P";
|
|
577
|
+
case MIDDLE_DOT:
|
|
578
|
+
return (const char *)"$\\cdot$";
|
|
579
|
+
case CEDILLA:
|
|
580
|
+
return (const char *)"\\,";
|
|
581
|
+
case SUPERSCRIPT_ONE:
|
|
582
|
+
return (const char *)"$^{1}$";
|
|
583
|
+
case MASCULINE_ORDINAL_INDICATOR:
|
|
584
|
+
return (const char *)"$^{\\underbar{o}}$";
|
|
585
|
+
case RIGHT_POINTING_DOUBLE_ANGLE_QUOTATION_MARK:
|
|
586
|
+
return (const char *)"\\frqq{}";
|
|
587
|
+
case VULGAR_FRACTION_ONE_QUARTER: /* these fractions are not good*/
|
|
588
|
+
return (const char *)"\\( 1\\over 4 \\)";
|
|
589
|
+
case VULGAR_FRACTION_ONE_HALF:
|
|
590
|
+
return (const char *)"\\( 1\\over 2 \\)";
|
|
591
|
+
case VULGAR_FRACTION_THREE_QUARTERS:
|
|
592
|
+
return (const char *)"\\( 3\\over 4 \\)";
|
|
593
|
+
case INVERTED_QUESTION_MARK:
|
|
594
|
+
return (const char *)"?'";
|
|
595
|
+
case LATIN_CAPITAL_LETTER_A_WITH_GRAVE:
|
|
596
|
+
return (const char *)"\\`A";
|
|
597
|
+
case LATIN_CAPITAL_LETTER_A_WITH_ACUTE:
|
|
598
|
+
return (const char *)"\\'A";
|
|
599
|
+
case LATIN_CAPITAL_LETTER_A_WITH_CIRCUMFLEX:
|
|
600
|
+
return (const char *)"\\^A";
|
|
601
|
+
case LATIN_CAPITAL_LETTER_A_WITH_TILDE:
|
|
602
|
+
return (const char *)"\\~A";
|
|
603
|
+
case LATIN_CAPITAL_LETTER_A_WITH_DIAERESIS:
|
|
604
|
+
return (const char *)"\\\"A";
|
|
605
|
+
case LATIN_CAPITAL_LETTER_A_WITH_RING_ABOVE:
|
|
606
|
+
return (const char *)"\\AA";
|
|
607
|
+
case LATIN_CAPITAL_LETTER_AE:
|
|
608
|
+
return (const char *)"\\AE";
|
|
609
|
+
case LATIN_CAPITAL_LETTER_C_WITH_CARON:
|
|
610
|
+
return (const char *)"\\v{C}";
|
|
611
|
+
case LATIN_CAPITAL_LETTER_C_WITH_CEDILLA:
|
|
612
|
+
return (const char *)"\\C";
|
|
613
|
+
case LATIN_CAPITAL_LETTER_E_WITH_GRAVE:
|
|
614
|
+
return (const char *)"\\`E";
|
|
615
|
+
case LATIN_CAPITAL_LETTER_E_WITH_ACUTE:
|
|
616
|
+
return (const char *)"\\'E";
|
|
617
|
+
case LATIN_CAPITAL_LETTER_E_WITH_CARON:
|
|
618
|
+
return (const char *)"\\v{E}";
|
|
619
|
+
case LATIN_CAPITAL_LETTER_E_WITH_CIRCUMFLEX:
|
|
620
|
+
return (const char *)"\\^E";
|
|
621
|
+
case LATIN_CAPITAL_LETTER_E_WITH_DIAERESIS:
|
|
622
|
+
return (const char *)"\\\"E";
|
|
623
|
+
case LATIN_CAPITAL_LETTER_I_WITH_GRAVE:
|
|
624
|
+
return (const char *)"\\`I";
|
|
625
|
+
case LATIN_CAPITAL_LETTER_I_WITH_ACUTE:
|
|
626
|
+
return (const char *)"\\'I";
|
|
627
|
+
case LATIN_CAPITAL_LETTER_I_WITH_CIRCUMFLEX:
|
|
628
|
+
return (const char *)"\\^I";
|
|
629
|
+
case LATIN_CAPITAL_LETTER_I_WITH_DIAERESIS:
|
|
630
|
+
return (const char *)"\\\"I";
|
|
631
|
+
case LATIN_CAPITAL_LETTER_ETH:
|
|
632
|
+
return (const char *)UNDEFINED;
|
|
633
|
+
case LATIN_CAPITAL_LETTER_N_WITH_TILDE:
|
|
634
|
+
return (const char *)"\\~N";
|
|
635
|
+
case LATIN_CAPITAL_LETTER_O_WITH_GRAVE:
|
|
636
|
+
return (const char *)"\\`O";
|
|
637
|
+
case LATIN_CAPITAL_LETTER_O_WITH_ACUTE:
|
|
638
|
+
return (const char *)"\\'O";
|
|
639
|
+
case LATIN_CAPITAL_LETTER_O_WITH_CIRCUMFLEX:
|
|
640
|
+
return (const char *)"\\^O";
|
|
641
|
+
case LATIN_CAPITAL_LETTER_O_WITH_TILDE:
|
|
642
|
+
return (const char *)"\\~O";
|
|
643
|
+
case LATIN_CAPITAL_LETTER_O_WITH_DIAERESIS:
|
|
644
|
+
return (const char *)"\\\"O";
|
|
645
|
+
case MULTIPLICATION_SIGN:
|
|
646
|
+
return (const char *)"$\\times$";
|
|
647
|
+
case LATIN_CAPITAL_LETTER_O_WITH_STROKE:
|
|
648
|
+
return (const char *)"\\O";
|
|
649
|
+
case LATIN_CAPITAL_LETTER_S_WITH_CARON:
|
|
650
|
+
return (const char *)"\\v{S}";
|
|
651
|
+
case LATIN_CAPITAL_LETTER_U_WITH_GRAVE:
|
|
652
|
+
return (const char *)"\\`U";
|
|
653
|
+
case LATIN_CAPITAL_LETTER_U_WITH_ACUTE:
|
|
654
|
+
return (const char *)"\\'U";
|
|
655
|
+
case LATIN_CAPITAL_LETTER_U_WITH_CIRCUMFLEX:
|
|
656
|
+
return (const char *)"\\^U";
|
|
657
|
+
case LATIN_CAPITAL_LETTER_U_WITH_DIAERESIS:
|
|
658
|
+
return (const char *)"\\\"U";
|
|
659
|
+
case LATIN_CAPITAL_LETTER_Y_WITH_ACUTE:
|
|
660
|
+
return (const char *)"\\'Y";
|
|
661
|
+
case LATIN_CAPITAL_LETTER_Z_WITH_CARON:
|
|
662
|
+
return (const char *)"\\v{Z}";
|
|
663
|
+
case LATIN_CAPITAL_LETTER_THORN:
|
|
664
|
+
return (const char *)UNDEFINED;
|
|
665
|
+
case LATIN_SMALL_LETTER_SHARP_S:
|
|
666
|
+
return (const char *)"\\ss";
|
|
667
|
+
case LATIN_SMALL_LETTER_A_WITH_GRAVE:
|
|
668
|
+
return (const char *)"\\`a";
|
|
669
|
+
case LATIN_SMALL_LETTER_A_WITH_ACUTE:
|
|
670
|
+
return (const char *)"\\'a";
|
|
671
|
+
case LATIN_SMALL_LETTER_A_WITH_CIRCUMFLEX:
|
|
672
|
+
return (const char *)"\\^a";
|
|
673
|
+
case LATIN_SMALL_LETTER_A_WITH_TILDE:
|
|
674
|
+
return (const char *)"\\~a";
|
|
675
|
+
case LATIN_SMALL_LETTER_A_WITH_DIAERESIS:
|
|
676
|
+
return (const char *)"\\\"a";
|
|
677
|
+
case LATIN_SMALL_LETTER_A_WITH_RING_ABOVE:
|
|
678
|
+
return (const char *)"\\aa";
|
|
679
|
+
case LATIN_SMALL_LETTER_AE:
|
|
680
|
+
return (const char *)"\\ae";
|
|
681
|
+
case LATIN_SMALL_LETTER_C_WITH_CARON:
|
|
682
|
+
return (const char *)"\\v{c}";
|
|
683
|
+
case LATIN_SMALL_LETTER_C_WITH_CEDILLA:
|
|
684
|
+
return (const char *)"\\c";
|
|
685
|
+
case LATIN_SMALL_LETTER_E_WITH_GRAVE:
|
|
686
|
+
return (const char *)"\\`e";
|
|
687
|
+
case LATIN_SMALL_LETTER_E_WITH_ACUTE:
|
|
688
|
+
return (const char *)"\\'e";
|
|
689
|
+
case LATIN_SMALL_LETTER_E_WITH_CARON:
|
|
690
|
+
return (const char *)"\\v{e}";
|
|
691
|
+
case LATIN_SMALL_LETTER_E_WITH_CIRCUMFLEX:
|
|
692
|
+
return (const char *)"\\^e";
|
|
693
|
+
case LATIN_SMALL_LETTER_E_WITH_DIAERESIS:
|
|
694
|
+
return (const char *)"\\\"e";
|
|
695
|
+
case LATIN_SMALL_LETTER_I_WITH_GRAVE:
|
|
696
|
+
return (const char *)"\\`i";
|
|
697
|
+
case LATIN_SMALL_LETTER_I_WITH_ACUTE:
|
|
698
|
+
return (const char *)"\\'i";
|
|
699
|
+
case LATIN_SMALL_LETTER_I_WITH_CIRCUMFLEX:
|
|
700
|
+
return (const char *)"\\^i";
|
|
701
|
+
case LATIN_SMALL_LETTER_I_WITH_DIAERESIS:
|
|
702
|
+
return (const char *)"\\\"i";
|
|
703
|
+
case LATIN_SMALL_LETTER_ETH:
|
|
704
|
+
return (const char *)UNDEFINED;
|
|
705
|
+
case LATIN_SMALL_LETTER_N_WITH_TILDE:
|
|
706
|
+
return (const char *)"\\~n";
|
|
707
|
+
case LATIN_SMALL_LETTER_O_WITH_GRAVE:
|
|
708
|
+
return (const char *)"\\`o";
|
|
709
|
+
case LATIN_SMALL_LETTER_O_WITH_ACUTE:
|
|
710
|
+
return (const char *)"\\'o";
|
|
711
|
+
case LATIN_SMALL_LETTER_O_WITH_CIRCUMFLEX:
|
|
712
|
+
return (const char *)"\\^o";
|
|
713
|
+
case LATIN_SMALL_LETTER_O_WITH_TILDE:
|
|
714
|
+
return (const char *)"\\~o";
|
|
715
|
+
case LATIN_SMALL_LETTER_O_WITH_DIAERESIS:
|
|
716
|
+
return (const char *)"\\\"o";
|
|
717
|
+
case DIVISION_SIGN:
|
|
718
|
+
return (const char *)"$\\div$";
|
|
719
|
+
case LATIN_SMALL_LETTER_O_WITH_STROKE:
|
|
720
|
+
return (const char *)"\\o";
|
|
721
|
+
case LATIN_SMALL_LETTER_S_WITH_CARON:
|
|
722
|
+
return (const char *)"\\v{s}";
|
|
723
|
+
case LATIN_SMALL_LETTER_U_WITH_GRAVE:
|
|
724
|
+
return (const char *)"\\`u";
|
|
725
|
+
case LATIN_SMALL_LETTER_U_WITH_ACUTE:
|
|
726
|
+
return (const char *)"\\'u";
|
|
727
|
+
case LATIN_SMALL_LETTER_U_WITH_CIRCUMFLEX:
|
|
728
|
+
return (const char *)"\\^u";
|
|
729
|
+
case LATIN_SMALL_LETTER_U_WITH_DIAERESIS:
|
|
730
|
+
return (const char *)"\\\"u";
|
|
731
|
+
case LATIN_SMALL_LETTER_Y_WITH_ACUTE:
|
|
732
|
+
return (const char *)"\\'y";
|
|
733
|
+
case LATIN_SMALL_LETTER_THORN:
|
|
734
|
+
return (const char *)UNDEFINED;
|
|
735
|
+
case LATIN_SMALL_LETTER_Y_WITH_DIAERESIS:
|
|
736
|
+
return (const char *)"\\\"y";
|
|
737
|
+
case LATIN_SMALL_LETTER_Z_WITH_CARON:
|
|
738
|
+
return (const char *)"\\v{z}";
|
|
739
|
+
|
|
740
|
+
/* greek */
|
|
741
|
+
/* some (punctuation, accents, accented capital) greek letters missing*/
|
|
742
|
+
case GREEK_CAPITAL_LETTER_ALPHA:
|
|
743
|
+
return (const char *)"A";
|
|
744
|
+
case GREEK_CAPITAL_LETTER_BETA:
|
|
745
|
+
return (const char *)"B";
|
|
746
|
+
case GREEK_CAPITAL_LETTER_GAMMA:
|
|
747
|
+
return (const char *)"\\( \\Gamma \\)";
|
|
748
|
+
case GREEK_CAPITAL_LETTER_DELTA:
|
|
749
|
+
return (const char *)"\\( \\Delta \\)";
|
|
750
|
+
case GREEK_CAPITAL_LETTER_EPSILON:
|
|
751
|
+
return (const char *)"E";
|
|
752
|
+
case GREEK_CAPITAL_LETTER_ZETA:
|
|
753
|
+
return (const char *)"Z";
|
|
754
|
+
case GREEK_CAPITAL_LETTER_ETA:
|
|
755
|
+
return (const char *)"H";
|
|
756
|
+
case GREEK_CAPITAL_LETTER_THETA:
|
|
757
|
+
return (const char *)"\\( \\Theta \\)";
|
|
758
|
+
case GREEK_CAPITAL_LETTER_IOTA:
|
|
759
|
+
return (const char *)"I";
|
|
760
|
+
case GREEK_CAPITAL_LETTER_KAPPA:
|
|
761
|
+
return (const char *)"K";
|
|
762
|
+
case GREEK_CAPITAL_LETTER_LAMDA:
|
|
763
|
+
return (const char *)"\\( \\Lambda \\)";
|
|
764
|
+
case GREEK_CAPITAL_LETTER_MU:
|
|
765
|
+
return (const char *)"M";
|
|
766
|
+
case GREEK_CAPITAL_LETTER_NU:
|
|
767
|
+
return (const char *)"N";
|
|
768
|
+
case GREEK_CAPITAL_LETTER_XI:
|
|
769
|
+
return (const char *)"\\( \\Xi \\)";
|
|
770
|
+
case GREEK_CAPITAL_LETTER_OMICRON:
|
|
771
|
+
return (const char *)"O";
|
|
772
|
+
case GREEK_CAPITAL_LETTER_PI:
|
|
773
|
+
return (const char *)"\\( \\Pi \\)";
|
|
774
|
+
case GREEK_CAPITAL_LETTER_RHO:
|
|
775
|
+
return (const char *)"P";
|
|
776
|
+
case GREEK_CAPITAL_LETTER_SIGMA:
|
|
777
|
+
return (const char *)"\\( \\Sigma \\)";
|
|
778
|
+
case GREEK_CAPITAL_LETTER_TAU:
|
|
779
|
+
return (const char *)"T";
|
|
780
|
+
case GREEK_CAPITAL_LETTER_UPSILON:
|
|
781
|
+
return (const char *)"\\( \\Upsilon \\)";
|
|
782
|
+
case GREEK_CAPITAL_LETTER_PHI:
|
|
783
|
+
return (const char *)"\\( \\Phi \\)";
|
|
784
|
+
case GREEK_CAPITAL_LETTER_CHI:
|
|
785
|
+
return (const char *)"\\( \\Chi \\)";
|
|
786
|
+
case GREEK_CAPITAL_LETTER_PSI:
|
|
787
|
+
return (const char *)"\\( \\Psi \\)";
|
|
788
|
+
case GREEK_CAPITAL_LETTER_OMEGA:
|
|
789
|
+
return (const char *)"\\( \\Omega \\)";
|
|
790
|
+
case GREEK_CAPITAL_LETTER_IOTA_WITH_DIALYTIKA:
|
|
791
|
+
return (const char *)UNDEFINED;
|
|
792
|
+
case GREEK_CAPITAL_LETTER_UPSILON_WITH_DIALYTIKA:
|
|
793
|
+
return (const char *)UNDEFINED;
|
|
794
|
+
case GREEK_SMALL_LETTER_ALPHA_WITH_TONOS:
|
|
795
|
+
return (const char *)UNDEFINED;
|
|
796
|
+
case GREEK_SMALL_LETTER_EPSILON_WITH_TONOS:
|
|
797
|
+
return (const char *)UNDEFINED;
|
|
798
|
+
case GREEK_SMALL_LETTER_ETA_WITH_TONOS:
|
|
799
|
+
return (const char *)UNDEFINED;
|
|
800
|
+
case GREEK_SMALL_LETTER_IOTA_WITH_TONOS:
|
|
801
|
+
return (const char *)UNDEFINED;
|
|
802
|
+
case GREEK_SMALL_LETTER_UPSILON_WITH_DIALYTIKA_AND_TONOS:
|
|
803
|
+
return (const char *)UNDEFINED;
|
|
804
|
+
case GREEK_SMALL_LETTER_ALPHA:
|
|
805
|
+
return (const char *)"\\( \\alpha \\)";
|
|
806
|
+
case GREEK_SMALL_LETTER_BETA:
|
|
807
|
+
return (const char *)"\\( \\beta \\)";
|
|
808
|
+
case GREEK_SMALL_LETTER_GAMMA:
|
|
809
|
+
return (const char *)"\\( \\gamma \\)";
|
|
810
|
+
case GREEK_SMALL_LETTER_DELTA:
|
|
811
|
+
return (const char *)"\\( \\delta \\)";
|
|
812
|
+
case GREEK_SMALL_LETTER_EPSILON:
|
|
813
|
+
return (const char *)"\\( \\epsilon \\)";
|
|
814
|
+
case GREEK_SMALL_LETTER_ZETA:
|
|
815
|
+
return (const char *)"\\( \\zeta \\)";
|
|
816
|
+
case GREEK_SMALL_LETTER_ETA:
|
|
817
|
+
return (const char *)"\\( \\eta \\)";
|
|
818
|
+
case GREEK_SMALL_LETTER_THETA:
|
|
819
|
+
return (const char *)"\\( \\theta \\)";
|
|
820
|
+
case GREEK_SMALL_LETTER_IOTA:
|
|
821
|
+
return (const char *)"\\( \\iota \\)";
|
|
822
|
+
case GREEK_SMALL_LETTER_KAPPA:
|
|
823
|
+
return (const char *)"\\( \\kappa \\)";
|
|
824
|
+
case GREEK_SMALL_LETTER_LAMDA:
|
|
825
|
+
return (const char *)"\\( \\lambda \\)";
|
|
826
|
+
case GREEK_SMALL_LETTER_MU:
|
|
827
|
+
return (const char *)"\\( \\mu \\)";
|
|
828
|
+
case GREEK_SMALL_LETTER_NU:
|
|
829
|
+
return (const char *)"\\( \\nu \\)";
|
|
830
|
+
case GREEK_SMALL_LETTER_XI:
|
|
831
|
+
return (const char *)"\\( \\xi \\)";
|
|
832
|
+
case GREEK_SMALL_LETTER_OMICRON:
|
|
833
|
+
return (const char *)"\\( \\omicron \\)";
|
|
834
|
+
case GREEK_SMALL_LETTER_PI:
|
|
835
|
+
return (const char *)"\\( \\pi \\)";
|
|
836
|
+
case GREEK_SMALL_LETTER_RHO:
|
|
837
|
+
return (const char *)"\\( \\rho \\)";
|
|
838
|
+
case GREEK_SMALL_LETTER_FINAL_SIGMA:
|
|
839
|
+
return (const char *)"\\( \\varsigma \\)";
|
|
840
|
+
case GREEK_SMALL_LETTER_SIGMA:
|
|
841
|
+
return (const char *)"\\( \\sigma \\)";
|
|
842
|
+
case GREEK_SMALL_LETTER_TAU:
|
|
843
|
+
return (const char *)"\\( \\tau \\)";
|
|
844
|
+
case GREEK_SMALL_LETTER_UPSILON:
|
|
845
|
+
return (const char *)"\\( \\upsilon \\)";
|
|
846
|
+
case GREEK_SMALL_LETTER_PHI:
|
|
847
|
+
return (const char *)"\\( \\varphi \\)";
|
|
848
|
+
case GREEK_SMALL_LETTER_CHI:
|
|
849
|
+
return (const char *)"\\( \\chi \\)";
|
|
850
|
+
case GREEK_SMALL_LETTER_PSI:
|
|
851
|
+
return (const char *)"\\( \\psi \\)";
|
|
852
|
+
case GREEK_SMALL_LETTER_OMEGA:
|
|
853
|
+
return (const char *)"\\( \\omega \\)";
|
|
854
|
+
case GREEK_SMALL_LETTER_IOTA_WITH_DIALYTIKA:
|
|
855
|
+
return (const char *)UNDEFINED;
|
|
856
|
+
case GREEK_SMALL_LETTER_UPSILON_WITH_DIALYTIKA:
|
|
857
|
+
return (const char *)UNDEFINED;
|
|
858
|
+
case GREEK_SMALL_LETTER_OMICRON_WITH_TONOS:
|
|
859
|
+
return (const char *)UNDEFINED;
|
|
860
|
+
case GREEK_SMALL_LETTER_UPSILON_WITH_TONOS:
|
|
861
|
+
return (const char *)UNDEFINED;
|
|
862
|
+
case GREEK_SMALL_LETTER_OMEGA_WITH_TONOS:
|
|
863
|
+
return (const char *)UNDEFINED;
|
|
864
|
+
case GREEK_BETA_SYMBOL:
|
|
865
|
+
return (const char *)UNDEFINED;
|
|
866
|
+
case GREEK_THETA_SYMBOL:
|
|
867
|
+
return (const char *)"\\( \\vartheta \\)";
|
|
868
|
+
case GREEK_UPSILON_WITH_HOOK_SYMBOL:
|
|
869
|
+
return (const char *)UNDEFINED;
|
|
870
|
+
case GREEK_UPSILON_WITH_ACUTE_AND_HOOK_SYMBOL:
|
|
871
|
+
return (const char *)UNDEFINED;
|
|
872
|
+
case GREEK_UPSILON_WITH_DIAERESIS_AND_HOOK_SYMBOL:
|
|
873
|
+
return (const char *)UNDEFINED;
|
|
874
|
+
case GREEK_PHI_SYMBOL:
|
|
875
|
+
return (const char *)"\\( \\phi \\)";
|
|
876
|
+
case GREEK_PI_SYMBOL:
|
|
877
|
+
return (const char *)"\\( \\varpi \\)";
|
|
878
|
+
/* and some greek letters missing*/
|
|
879
|
+
|
|
880
|
+
/* punctuation (partial) */
|
|
881
|
+
case HYPHEN:
|
|
882
|
+
return (const char *)"-";
|
|
883
|
+
case NON_BREAKING_HYPHEN:
|
|
884
|
+
return (const char *)UNDEFINED;
|
|
885
|
+
case FIGURE_DASH:
|
|
886
|
+
case EN_DASH:
|
|
887
|
+
return (const char *)"--";
|
|
888
|
+
case EM_DASH:
|
|
889
|
+
return (const char *)"---";
|
|
890
|
+
case HORIZONTAL_BAR:
|
|
891
|
+
return (const char *)UNDEFINED;
|
|
892
|
+
case LEFT_SINGLE_QUOTATION_MARK:
|
|
893
|
+
return (const char *)"`";
|
|
894
|
+
case RIGHT_SINGLE_QUOTATION_MARK:
|
|
895
|
+
return (const char *)"'";
|
|
896
|
+
case SINGLE_LOW_9_QUOTATION_MARK:
|
|
897
|
+
return (const char *)"\\glq{}";
|
|
898
|
+
case SINGLE_HIGH_REVERSED_9_QUOTATION_MARK:
|
|
899
|
+
return (const char *)UNDEFINED;
|
|
900
|
+
case LEFT_DOUBLE_QUOTATION_MARK:
|
|
901
|
+
return (const char *)"``";
|
|
902
|
+
case RIGHT_DOUBLE_QUOTATION_MARK:
|
|
903
|
+
return (const char *)"''";
|
|
904
|
+
case DOUBLE_LOW_9_QUOTATION_MARK:
|
|
905
|
+
return (const char *)"\\glqq{}";
|
|
906
|
+
case DOUBLE_HIGH_REVERSED_9_QUOTATION_MARK:
|
|
907
|
+
return (const char *)UNDEFINED;
|
|
908
|
+
case DAGGER:
|
|
909
|
+
return (const char *)"\\dag";
|
|
910
|
+
case DOUBLE_DAGGER:
|
|
911
|
+
return (const char *)"\\ddag";
|
|
912
|
+
case BULLET:
|
|
913
|
+
return (const char *)"$\\bullet$";
|
|
914
|
+
case TRIANGULAR_BULLET:
|
|
915
|
+
return (const char *)"$\\blacktriangleright";
|
|
916
|
+
case HYPHENATION_POINT:
|
|
917
|
+
return (const char *)"\\-";
|
|
918
|
+
case HORIZONTAL_ELLIPSIS:
|
|
919
|
+
return (const char *)"\\ldots";
|
|
920
|
+
case PER_MILLE_SIGN:
|
|
921
|
+
return (const char *)UNDEFINED;
|
|
922
|
+
case SINGLE_LEFT_POINTING_ANGLE_QUOTATION_MARK:
|
|
923
|
+
return (const char *)"\\flq{}";
|
|
924
|
+
case SINGLE_RIGHT_POINTING_ANGLE_QUOTATION_MARK:
|
|
925
|
+
return (const char *)"\\frq{}";
|
|
926
|
+
/* ligatures */
|
|
927
|
+
case LATIN_SMALL_LIGATURE_FF:
|
|
928
|
+
return (const char *)"ff";
|
|
929
|
+
case LATIN_SMALL_LIGATURE_FI:
|
|
930
|
+
return (const char *)"fi";
|
|
931
|
+
case LATIN_SMALL_LIGATURE_FL:
|
|
932
|
+
return (const char *)"fl";
|
|
933
|
+
case LATIN_SMALL_LIGATURE_FFI:
|
|
934
|
+
return (const char *)"ffi";
|
|
935
|
+
case LATIN_SMALL_LIGATURE_FFL:
|
|
936
|
+
return (const char *)"ffl";
|
|
937
|
+
case LATIN_SMALL_LIGATURE_LONG_S_T:
|
|
938
|
+
case LATIN_SMALL_LIGATURE_ST:
|
|
939
|
+
return (const char *)"st";
|
|
940
|
+
/* math */
|
|
941
|
+
case UNICODE_INFINITY:
|
|
942
|
+
return (const char *)"\\infty";
|
|
943
|
+
/* reserved */
|
|
944
|
+
case 0:
|
|
945
|
+
return (const char *)"";
|
|
946
|
+
case UNKNOWN:
|
|
947
|
+
return (const char *)"\\_";
|
|
948
|
+
case PICTURE:
|
|
949
|
+
return (const char *)"(PICTURE)";
|
|
950
|
+
default:
|
|
951
|
+
/* snprintf seems to be no standard, so I use insecure sprintf */
|
|
952
|
+
sprintf(buf,"\\symbol{%u}",(unsigned)c);
|
|
953
|
+
return buf; /* UNDEFINED; */
|
|
954
|
+
}
|
|
955
|
+
case HTML:
|
|
956
|
+
if ( c >= SPACE && c <= TILDE ) { /* ASCII */
|
|
957
|
+
switch (c) {
|
|
958
|
+
case '&':
|
|
959
|
+
return (const char *)"&";
|
|
960
|
+
/* semicolon must not be coded */
|
|
961
|
+
case '\'':
|
|
962
|
+
return (const char *)"'";
|
|
963
|
+
case '"':
|
|
964
|
+
return (const char *)""";
|
|
965
|
+
case '<':
|
|
966
|
+
return (const char *)"<";
|
|
967
|
+
case '>':
|
|
968
|
+
return (const char *)">";
|
|
969
|
+
}
|
|
970
|
+
buf[0] = (char)c;
|
|
971
|
+
return buf;
|
|
972
|
+
}
|
|
973
|
+
switch (c) {
|
|
974
|
+
case PICTURE:
|
|
975
|
+
return (const char *)"<!--PICTURE-->";
|
|
976
|
+
case UNKNOWN:
|
|
977
|
+
return (const char *)"_"; /* better use colored symbol? */
|
|
978
|
+
case LINE_FEED:
|
|
979
|
+
return (const char *)"<br />"; /* \n handled somwhere else? */
|
|
980
|
+
case FORM_FEED:
|
|
981
|
+
case CARRIAGE_RETURN:
|
|
982
|
+
return (const char *)"<br />";
|
|
983
|
+
case NO_BREAK_SPACE:
|
|
984
|
+
return (const char *)"<nobr />";
|
|
985
|
+
case INVERTED_EXCLAMATION_MARK:
|
|
986
|
+
return (const char *)"¡";
|
|
987
|
+
case CENT_SIGN:
|
|
988
|
+
return (const char *)"¢";
|
|
989
|
+
case POUND_SIGN:
|
|
990
|
+
return (const char *)"£";
|
|
991
|
+
case CURRENCY_SIGN:
|
|
992
|
+
return (const char *)"¤";
|
|
993
|
+
case YEN_SIGN:
|
|
994
|
+
return (const char *)"¥";
|
|
995
|
+
case BROKEN_BAR:
|
|
996
|
+
return (const char *)"¦";
|
|
997
|
+
case SECTION_SIGN:
|
|
998
|
+
return (const char *)"§";
|
|
999
|
+
case DIAERESIS:
|
|
1000
|
+
return (const char *)"¨";
|
|
1001
|
+
case COPYRIGHT_SIGN:
|
|
1002
|
+
return (const char *)"©";
|
|
1003
|
+
case FEMININE_ORDINAL_INDICATOR:
|
|
1004
|
+
return (const char *)"ªem;";
|
|
1005
|
+
case LEFT_POINTING_DOUBLE_ANGLE_QUOTATION_MARK:
|
|
1006
|
+
return (const char *)"«";
|
|
1007
|
+
case NOT_SIGN:
|
|
1008
|
+
return (const char *)"¬";
|
|
1009
|
+
case SOFT_HYPHEN:
|
|
1010
|
+
return (const char *)"­";
|
|
1011
|
+
case REGISTERED_SIGN:
|
|
1012
|
+
return (const char *)"®";
|
|
1013
|
+
case MACRON:
|
|
1014
|
+
return (const char *)"¯";
|
|
1015
|
+
case DEGREE_SIGN:
|
|
1016
|
+
return (const char *)"°";
|
|
1017
|
+
case PLUS_MINUS_SIGN:
|
|
1018
|
+
return (const char *)"±";
|
|
1019
|
+
case SUPERSCRIPT_TWO:
|
|
1020
|
+
return (const char *)"²";
|
|
1021
|
+
case SUPERSCRIPT_THREE:
|
|
1022
|
+
return (const char *)"³";
|
|
1023
|
+
case ACUTE_ACCENT:
|
|
1024
|
+
return (const char *)"´";
|
|
1025
|
+
case MICRO_SIGN:
|
|
1026
|
+
return (const char *)"µ";
|
|
1027
|
+
case PILCROW_SIGN:
|
|
1028
|
+
return (const char *)"¶";
|
|
1029
|
+
case MIDDLE_DOT:
|
|
1030
|
+
return (const char *)"·";
|
|
1031
|
+
case CEDILLA:
|
|
1032
|
+
return (const char *)"¸";
|
|
1033
|
+
case SUPERSCRIPT_ONE:
|
|
1034
|
+
return (const char *)"¹";
|
|
1035
|
+
case MASCULINE_ORDINAL_INDICATOR:
|
|
1036
|
+
return (const char *)"º";
|
|
1037
|
+
case RIGHT_POINTING_DOUBLE_ANGLE_QUOTATION_MARK:
|
|
1038
|
+
return (const char *)"»";
|
|
1039
|
+
case VULGAR_FRACTION_ONE_QUARTER:
|
|
1040
|
+
return (const char *)"¼";
|
|
1041
|
+
case VULGAR_FRACTION_ONE_HALF:
|
|
1042
|
+
return (const char *)"½";
|
|
1043
|
+
case VULGAR_FRACTION_THREE_QUARTERS:
|
|
1044
|
+
return (const char *)"¾";
|
|
1045
|
+
case INVERTED_QUESTION_MARK:
|
|
1046
|
+
return (const char *)"¿";
|
|
1047
|
+
case LATIN_CAPITAL_LETTER_A_WITH_GRAVE:
|
|
1048
|
+
return (const char *)"À";
|
|
1049
|
+
case LATIN_CAPITAL_LETTER_A_WITH_ACUTE:
|
|
1050
|
+
return (const char *)"Á";
|
|
1051
|
+
case LATIN_CAPITAL_LETTER_A_WITH_BREVE:
|
|
1052
|
+
return (const char *)"Ă";
|
|
1053
|
+
case LATIN_CAPITAL_LETTER_A_WITH_CIRCUMFLEX:
|
|
1054
|
+
return (const char *)"Â";
|
|
1055
|
+
case LATIN_CAPITAL_LETTER_A_WITH_TILDE:
|
|
1056
|
+
return (const char *)"Ã";
|
|
1057
|
+
case LATIN_CAPITAL_LETTER_A_WITH_DIAERESIS:
|
|
1058
|
+
return (const char *)"Ä";
|
|
1059
|
+
case LATIN_CAPITAL_LETTER_A_WITH_RING_ABOVE:
|
|
1060
|
+
return (const char *)"Å";
|
|
1061
|
+
case LATIN_CAPITAL_LETTER_AE:
|
|
1062
|
+
return (const char *)"Æ";
|
|
1063
|
+
case LATIN_CAPITAL_LETTER_C_WITH_CARON:
|
|
1064
|
+
return (const char *)"Č";
|
|
1065
|
+
case LATIN_CAPITAL_LETTER_C_WITH_CEDILLA:
|
|
1066
|
+
return (const char *)"Ç";
|
|
1067
|
+
case LATIN_CAPITAL_LETTER_E_WITH_GRAVE:
|
|
1068
|
+
return (const char *)"È";
|
|
1069
|
+
case LATIN_CAPITAL_LETTER_E_WITH_ACUTE:
|
|
1070
|
+
return (const char *)"É";
|
|
1071
|
+
case LATIN_CAPITAL_LETTER_E_WITH_CARON:
|
|
1072
|
+
return (const char *)"Ě";
|
|
1073
|
+
case LATIN_CAPITAL_LETTER_E_WITH_CIRCUMFLEX:
|
|
1074
|
+
return (const char *)"Ê";
|
|
1075
|
+
case LATIN_CAPITAL_LETTER_E_WITH_DIAERESIS:
|
|
1076
|
+
return (const char *)"Ë";
|
|
1077
|
+
case LATIN_CAPITAL_LETTER_I_WITH_GRAVE:
|
|
1078
|
+
return (const char *)"Ì";
|
|
1079
|
+
case LATIN_CAPITAL_LETTER_I_WITH_ACUTE:
|
|
1080
|
+
return (const char *)"Í";
|
|
1081
|
+
case LATIN_CAPITAL_LETTER_I_WITH_CIRCUMFLEX:
|
|
1082
|
+
return (const char *)"Î";
|
|
1083
|
+
case LATIN_CAPITAL_LETTER_I_WITH_DIAERESIS:
|
|
1084
|
+
return (const char *)"Ï";
|
|
1085
|
+
case LATIN_CAPITAL_LETTER_ETH:
|
|
1086
|
+
return (const char *)"Ð";
|
|
1087
|
+
case LATIN_CAPITAL_LETTER_N_WITH_TILDE:
|
|
1088
|
+
return (const char *)"Ñ";
|
|
1089
|
+
case LATIN_CAPITAL_LETTER_O_WITH_GRAVE:
|
|
1090
|
+
return (const char *)"Ò";
|
|
1091
|
+
case LATIN_CAPITAL_LETTER_O_WITH_ACUTE:
|
|
1092
|
+
return (const char *)"Ó";
|
|
1093
|
+
case LATIN_CAPITAL_LETTER_O_WITH_CIRCUMFLEX:
|
|
1094
|
+
return (const char *)"Ô";
|
|
1095
|
+
case LATIN_CAPITAL_LETTER_O_WITH_TILDE:
|
|
1096
|
+
return (const char *)"Õ";
|
|
1097
|
+
case LATIN_CAPITAL_LETTER_O_WITH_DIAERESIS:
|
|
1098
|
+
return (const char *)"Ö";
|
|
1099
|
+
case MULTIPLICATION_SIGN:
|
|
1100
|
+
return (const char *)"×";
|
|
1101
|
+
case LATIN_CAPITAL_LETTER_O_WITH_STROKE:
|
|
1102
|
+
return (const char *)"Ø";
|
|
1103
|
+
case LATIN_CAPITAL_LETTER_S_WITH_CARON:
|
|
1104
|
+
return (const char *)"Š";
|
|
1105
|
+
case LATIN_CAPITAL_LETTER_U_WITH_GRAVE:
|
|
1106
|
+
return (const char *)"Ù";
|
|
1107
|
+
case LATIN_CAPITAL_LETTER_U_WITH_ACUTE:
|
|
1108
|
+
return (const char *)"Ú";
|
|
1109
|
+
case LATIN_CAPITAL_LETTER_U_WITH_CIRCUMFLEX:
|
|
1110
|
+
return (const char *)"Û";
|
|
1111
|
+
case LATIN_CAPITAL_LETTER_U_WITH_DIAERESIS:
|
|
1112
|
+
return (const char *)"Ü";
|
|
1113
|
+
case LATIN_CAPITAL_LETTER_Y_WITH_ACUTE:
|
|
1114
|
+
return (const char *)"Ý";
|
|
1115
|
+
case LATIN_CAPITAL_LETTER_Z_WITH_CARON:
|
|
1116
|
+
return (const char *)"Ž";
|
|
1117
|
+
case LATIN_CAPITAL_LETTER_THORN:
|
|
1118
|
+
return (const char *)"Þ";
|
|
1119
|
+
case LATIN_SMALL_LETTER_SHARP_S:
|
|
1120
|
+
return (const char *)"ß";
|
|
1121
|
+
case LATIN_SMALL_LETTER_A_WITH_GRAVE:
|
|
1122
|
+
return (const char *)"à";
|
|
1123
|
+
case LATIN_SMALL_LETTER_A_WITH_ACUTE:
|
|
1124
|
+
return (const char *)"á";
|
|
1125
|
+
case LATIN_SMALL_LETTER_A_WITH_BREVE:
|
|
1126
|
+
return (const char *)"ă";
|
|
1127
|
+
case LATIN_SMALL_LETTER_A_WITH_CARON:
|
|
1128
|
+
return (const char *)"&acaron;";
|
|
1129
|
+
case LATIN_SMALL_LETTER_A_WITH_CIRCUMFLEX:
|
|
1130
|
+
return (const char *)"â";
|
|
1131
|
+
case LATIN_SMALL_LETTER_A_WITH_TILDE:
|
|
1132
|
+
return (const char *)"ã";
|
|
1133
|
+
case LATIN_SMALL_LETTER_A_WITH_DIAERESIS:
|
|
1134
|
+
return (const char *)"ä";
|
|
1135
|
+
case LATIN_SMALL_LETTER_A_WITH_RING_ABOVE:
|
|
1136
|
+
return (const char *)"å";
|
|
1137
|
+
case LATIN_SMALL_LETTER_AE:
|
|
1138
|
+
return (const char *)"æ";
|
|
1139
|
+
case LATIN_SMALL_LETTER_C_WITH_CARON:
|
|
1140
|
+
return (const char *)"č";
|
|
1141
|
+
case LATIN_SMALL_LETTER_C_WITH_CEDILLA:
|
|
1142
|
+
return (const char *)"ç";
|
|
1143
|
+
case LATIN_SMALL_LETTER_E_WITH_GRAVE:
|
|
1144
|
+
return (const char *)"è";
|
|
1145
|
+
case LATIN_SMALL_LETTER_E_WITH_ACUTE:
|
|
1146
|
+
return (const char *)"é";
|
|
1147
|
+
case LATIN_SMALL_LETTER_E_WITH_CARON:
|
|
1148
|
+
return (const char *)"ě";
|
|
1149
|
+
case LATIN_SMALL_LETTER_E_WITH_CIRCUMFLEX:
|
|
1150
|
+
return (const char *)"ê";
|
|
1151
|
+
case LATIN_SMALL_LETTER_E_WITH_DIAERESIS:
|
|
1152
|
+
return (const char *)"ë";
|
|
1153
|
+
case LATIN_SMALL_LETTER_I_WITH_GRAVE:
|
|
1154
|
+
return (const char *)"ì";
|
|
1155
|
+
case LATIN_SMALL_LETTER_I_WITH_ACUTE:
|
|
1156
|
+
return (const char *)"í";
|
|
1157
|
+
case LATIN_SMALL_LETTER_I_WITH_CIRCUMFLEX:
|
|
1158
|
+
return (const char *)"î";
|
|
1159
|
+
case LATIN_SMALL_LETTER_I_WITH_DIAERESIS:
|
|
1160
|
+
return (const char *)"ï";
|
|
1161
|
+
case LATIN_SMALL_LETTER_ETH:
|
|
1162
|
+
return (const char *)"ð";
|
|
1163
|
+
case LATIN_SMALL_LETTER_N_WITH_TILDE:
|
|
1164
|
+
return (const char *)"ñ";
|
|
1165
|
+
case LATIN_SMALL_LETTER_O_WITH_GRAVE:
|
|
1166
|
+
return (const char *)"ò";
|
|
1167
|
+
case LATIN_SMALL_LETTER_O_WITH_ACUTE:
|
|
1168
|
+
return (const char *)"ó";
|
|
1169
|
+
case LATIN_SMALL_LETTER_O_WITH_CIRCUMFLEX:
|
|
1170
|
+
return (const char *)"ô";
|
|
1171
|
+
case LATIN_SMALL_LETTER_O_WITH_TILDE:
|
|
1172
|
+
return (const char *)"õ";
|
|
1173
|
+
case LATIN_SMALL_LETTER_O_WITH_DIAERESIS:
|
|
1174
|
+
return (const char *)"ö";
|
|
1175
|
+
case DIVISION_SIGN:
|
|
1176
|
+
return (const char *)"÷";
|
|
1177
|
+
case LATIN_SMALL_LETTER_O_WITH_STROKE:
|
|
1178
|
+
return (const char *)"ø";
|
|
1179
|
+
case LATIN_SMALL_LETTER_S_WITH_CARON:
|
|
1180
|
+
return (const char *)"š";
|
|
1181
|
+
case LATIN_SMALL_LETTER_U_WITH_GRAVE:
|
|
1182
|
+
return (const char *)"ù";
|
|
1183
|
+
case LATIN_SMALL_LETTER_U_WITH_ACUTE:
|
|
1184
|
+
return (const char *)"ú";
|
|
1185
|
+
case LATIN_SMALL_LETTER_U_WITH_CIRCUMFLEX:
|
|
1186
|
+
return (const char *)"û";
|
|
1187
|
+
case LATIN_SMALL_LETTER_U_WITH_DIAERESIS:
|
|
1188
|
+
return (const char *)"ü";
|
|
1189
|
+
case LATIN_SMALL_LETTER_Y_WITH_ACUTE:
|
|
1190
|
+
return (const char *)"ý";
|
|
1191
|
+
case LATIN_SMALL_LETTER_THORN:
|
|
1192
|
+
return (const char *)"þ";
|
|
1193
|
+
case LATIN_SMALL_LETTER_Y_WITH_DIAERESIS:
|
|
1194
|
+
return (const char *)"ÿ";
|
|
1195
|
+
case LATIN_SMALL_LETTER_Z_WITH_CARON:
|
|
1196
|
+
return (const char *)"ž";
|
|
1197
|
+
case EURO_CURRENCY_SIGN:
|
|
1198
|
+
return (const char *)"€";
|
|
1199
|
+
case 0:
|
|
1200
|
+
return (const char *)"";
|
|
1201
|
+
default:
|
|
1202
|
+
sprintf(buf,"&#%u;",(unsigned)c);
|
|
1203
|
+
return buf; /* undefined */
|
|
1204
|
+
}
|
|
1205
|
+
/* break; unreachable code */
|
|
1206
|
+
case XML: /* only 5 &xxx;-ENTITIES ar defined by default */
|
|
1207
|
+
if ( c >= SPACE && c <= TILDE ) { /* ASCII */
|
|
1208
|
+
switch (c) {
|
|
1209
|
+
case '&':
|
|
1210
|
+
return (const char *)"&";
|
|
1211
|
+
case '\'':
|
|
1212
|
+
return (const char *)"'";
|
|
1213
|
+
case '"':
|
|
1214
|
+
return (const char *)""";
|
|
1215
|
+
case '<':
|
|
1216
|
+
return (const char *)"<";
|
|
1217
|
+
case '>':
|
|
1218
|
+
return (const char *)">";
|
|
1219
|
+
}
|
|
1220
|
+
buf[0] = (char)c;
|
|
1221
|
+
return buf;
|
|
1222
|
+
}
|
|
1223
|
+
switch (c) { /* subject of change! */
|
|
1224
|
+
case PICTURE:
|
|
1225
|
+
return (const char *)"(PICTURE)";
|
|
1226
|
+
case UNKNOWN:
|
|
1227
|
+
return (const char *)"_"; /* better use colored symbol? */
|
|
1228
|
+
case LINE_FEED: /* \n handled somwhere else? */
|
|
1229
|
+
case FORM_FEED:
|
|
1230
|
+
case CARRIAGE_RETURN:
|
|
1231
|
+
return (const char *)"<br />";
|
|
1232
|
+
case NO_BREAK_SPACE:
|
|
1233
|
+
return (const char *)"<nobr />";
|
|
1234
|
+
case 0:
|
|
1235
|
+
return (const char *)"";
|
|
1236
|
+
default:
|
|
1237
|
+
sprintf(buf,"&#x%03x;",(unsigned)c);
|
|
1238
|
+
return buf; /* undefined */
|
|
1239
|
+
}
|
|
1240
|
+
/* break; unreachable code */
|
|
1241
|
+
case SGML:
|
|
1242
|
+
switch (c) {
|
|
1243
|
+
default:
|
|
1244
|
+
sprintf(buf,"&#%u;",(unsigned)c);
|
|
1245
|
+
return buf; /* UNDEFINED */
|
|
1246
|
+
}
|
|
1247
|
+
/* break; unreachable code */
|
|
1248
|
+
case ASCII: /* mainly used for debugging */
|
|
1249
|
+
if ( c=='\n' || (c>= 0x20 && c <= 0x7F) ) {
|
|
1250
|
+
buf[0] = (char)c;
|
|
1251
|
+
return buf;
|
|
1252
|
+
}
|
|
1253
|
+
switch (c) {
|
|
1254
|
+
/* extra */
|
|
1255
|
+
case UNKNOWN:
|
|
1256
|
+
return (const char *)"(?)";
|
|
1257
|
+
case PICTURE:
|
|
1258
|
+
return (const char *)"(?)";
|
|
1259
|
+
|
|
1260
|
+
default:
|
|
1261
|
+
/* snprintf seems to be no standard, so I use insecure sprintf */
|
|
1262
|
+
if ((unsigned)c>255) sprintf(buf,"(0x%04x)",(unsigned)c);
|
|
1263
|
+
else sprintf(buf,"(0x%02x)",(unsigned)c);
|
|
1264
|
+
return buf; /* UNDEFINED; */
|
|
1265
|
+
}
|
|
1266
|
+
/* break; unreachable code */
|
|
1267
|
+
default: /* use UTF8 as default, test with xterm -u8 */
|
|
1268
|
+
/* extra */
|
|
1269
|
+
if ( c == UNKNOWN ) return (const char *)"_";
|
|
1270
|
+
if ( c == PICTURE ) return (const char *)"_"; /* Due to Mobile OCR */
|
|
1271
|
+
if ( c <= (wchar_t)0x0000007F ) { /* UTF8 == 7bit ASCII */
|
|
1272
|
+
buf[0] = (char)c;
|
|
1273
|
+
return buf;
|
|
1274
|
+
}
|
|
1275
|
+
if ( c <= (wchar_t)0x000007FF ) { /* UTF8 == 11bit */
|
|
1276
|
+
buf[0] = (char)(0xc0|((c>> 6) & 0x1f)); /* 110xxxxx */
|
|
1277
|
+
buf[1] = (char)(0x80|( c & 0x3f)); /* 10xxxxxx */
|
|
1278
|
+
buf[2] = (char)0; /* terminate string */
|
|
1279
|
+
return buf;
|
|
1280
|
+
}
|
|
1281
|
+
/* wchar_t is 16bit for Borland-C !? Jan07 */
|
|
1282
|
+
if ( c <= (wchar_t)0x0000FFFF ) { /* UTF8 == 16bit */
|
|
1283
|
+
buf[0] = (char)(0xe0|((c>>12) & 0x0f)); /* 1110xxxx */
|
|
1284
|
+
buf[1] = (char)(0x80|((c>> 6) & 0x3f)); /* 10xxxxxx */
|
|
1285
|
+
buf[2] = (char)(0x80|( c & 0x3f)); /* 10xxxxxx */
|
|
1286
|
+
buf[3] = (char)0; /* terminate string */
|
|
1287
|
+
return buf;
|
|
1288
|
+
}
|
|
1289
|
+
if ( c <= (wchar_t)0x001FFFFF ) { /* UTF8 == 21bit */
|
|
1290
|
+
buf[0] = (char)(0xf0|((c>>18) & 0x07)); /* 11110xxx */
|
|
1291
|
+
buf[1] = (char)(0x80|((c>>12) & 0x3f)); /* 10xxxxxx */
|
|
1292
|
+
buf[2] = (char)(0x80|((c>> 6) & 0x3f)); /* 10xxxxxx */
|
|
1293
|
+
buf[3] = (char)(0x80|( c & 0x3f)); /* 10xxxxxx */
|
|
1294
|
+
buf[4] = (char)0; /* terminate string */
|
|
1295
|
+
return buf;
|
|
1296
|
+
}
|
|
1297
|
+
if ( c <= (wchar_t)0x03FFFFFF ) { /* UTF8 == 26bit */
|
|
1298
|
+
buf[0] = (char)(0xf8|((c>>24) & 0x03)); /* 111110xx */
|
|
1299
|
+
buf[1] = (char)(0x80|((c>>18) & 0x3f)); /* 10xxxxxx */
|
|
1300
|
+
buf[2] = (char)(0x80|((c>>12) & 0x3f)); /* 10xxxxxx */
|
|
1301
|
+
buf[3] = (char)(0x80|((c>> 6) & 0x3f)); /* 10xxxxxx */
|
|
1302
|
+
buf[4] = (char)(0x80|( c & 0x3f)); /* 10xxxxxx */
|
|
1303
|
+
buf[5] = (char)0; /* terminate string */
|
|
1304
|
+
return buf;
|
|
1305
|
+
}
|
|
1306
|
+
if ( c <= (wchar_t)0x7FFFFFFF ) { /* UTF8 == 31bit */
|
|
1307
|
+
buf[0] = (char)(0xfc|((c>>30) & 0x01)); /* 1111110x */
|
|
1308
|
+
buf[1] = (char)(0x80|((c>>24) & 0x3f)); /* 10xxxxxx */
|
|
1309
|
+
buf[2] = (char)(0x80|((c>>18) & 0x3f)); /* 10xxxxxx */
|
|
1310
|
+
buf[3] = (char)(0x80|((c>>12) & 0x3f)); /* 10xxxxxx */
|
|
1311
|
+
buf[4] = (char)(0x80|((c>> 6) & 0x3f)); /* 10xxxxxx */
|
|
1312
|
+
buf[5] = (char)(0x80|( c & 0x3f)); /* 10xxxxxx */
|
|
1313
|
+
buf[6] = (char)0; /* terminate string */
|
|
1314
|
+
return buf;
|
|
1315
|
+
}
|
|
1316
|
+
return (const char *)UNDEFINED;
|
|
1317
|
+
}
|
|
1318
|
+
}
|