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
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
246
247
248
249
250
251
252
253
|
{
This file is part of the Free Pascal run time library.
Copyright (c) 2000 by Florian Klaempfl
member of the Free Pascal development team.
This unit implements several classes for charset conversions
See the file COPYING.FPC, included in this distribution,
for details about the copyright.
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.
**********************************************************************
}
unit charset;
{$i fpcdefs.inc}
interface
type
tunicodechar = word;
tunicodestring = ^tunicodechar;
tcsconvert = class
// !!!!!!1constructor create;
end;
tunicodecharmappingflag = (umf_noinfo,umf_leadbyte,umf_undefined,
umf_unused);
punicodecharmapping = ^tunicodecharmapping;
tunicodecharmapping = record
unicode : tunicodechar;
flag : tunicodecharmappingflag;
reserved : byte;
end;
punicodemap = ^tunicodemap;
tunicodemap = record
cpname : string[20];
map : punicodecharmapping;
lastchar : longint;
next : punicodemap;
internalmap : boolean;
end;
tcp2unicode = class(tcsconvert)
end;
function loadunicodemapping(const cpname,f : string) : punicodemap;
procedure registermapping(p : punicodemap);
function getmap(const s : string) : punicodemap;
function mappingavailable(const s : string) : boolean;
function getunicode(c : char;p : punicodemap) : tunicodechar;
function getascii(c : tunicodechar;p : punicodemap) : string;
implementation
var
mappings : punicodemap;
function loadunicodemapping(const cpname,f : string) : punicodemap;
var
data : punicodecharmapping;
datasize : longint;
t : text;
s,hs : string;
scanpos,charpos,unicodevalue : longint;
code : integer;
flag : tunicodecharmappingflag;
p : punicodemap;
lastchar : longint;
begin
lastchar:=-1;
loadunicodemapping:=nil;
datasize:=256;
getmem(data,sizeof(tunicodecharmapping)*datasize);
assign(t,f);
{$I-}
reset(t);
{$I+}
if ioresult<>0 then
begin
freemem(data,sizeof(tunicodecharmapping)*datasize);
exit;
end;
while not(eof(t)) do
begin
readln(t,s);
if (s[1]='0') and (s[2]='x') then
begin
flag:=umf_unused;
scanpos:=3;
hs:='$';
while s[scanpos] in ['0'..'9','A'..'F','a'..'f'] do
begin
hs:=hs+s[scanpos];
inc(scanpos);
end;
val(hs,charpos,code);
if code<>0 then
begin
freemem(data,sizeof(tunicodecharmapping)*datasize);
close(t);
exit;
end;
while not(s[scanpos] in ['0','#']) do
inc(scanpos);
if s[scanpos]='#' then
begin
{ special char }
unicodevalue:=$ffff;
hs:=copy(s,scanpos,length(s)-scanpos+1);
if hs='#DBCS LEAD BYTE' then
flag:=umf_leadbyte;
end
else
begin
{ C hex prefix }
inc(scanpos,2);
hs:='$';
while s[scanpos] in ['0'..'9','A'..'F','a'..'f'] do
begin
hs:=hs+s[scanpos];
inc(scanpos);
end;
val(hs,unicodevalue,code);
if code<>0 then
begin
freemem(data,sizeof(tunicodecharmapping)*datasize);
close(t);
exit;
end;
if charpos>datasize then
begin
{ allocate 1024 bytes more because }
{ if we need more than 256 entries it's }
{ probably a mbcs with a lot of }
{ entries }
datasize:=charpos+1024;
reallocmem(data,sizeof(tunicodecharmapping)*datasize);
end;
flag:=umf_noinfo;
end;
data[charpos].flag:=flag;
data[charpos].unicode:=unicodevalue;
if charpos>lastchar then
lastchar:=charpos;
end;
end;
close(t);
new(p);
p^.lastchar:=lastchar;
p^.cpname:=cpname;
p^.internalmap:=false;
p^.next:=nil;
p^.map:=data;
loadunicodemapping:=p;
end;
procedure registermapping(p : punicodemap);
begin
p^.next:=mappings;
mappings:=p;
end;
function getmap(const s : string) : punicodemap;
var
hp : punicodemap;
const
mapcache : string = '';
mapcachep : punicodemap = nil;
begin
if (mapcache=s) and (mapcachep^.cpname=s) then
begin
getmap:=mapcachep;
exit;
end;
hp:=mappings;
while assigned(hp) do
begin
if hp^.cpname=s then
begin
getmap:=hp;
mapcache:=s;
mapcachep:=hp;
exit;
end;
hp:=hp^.next;
end;
getmap:=nil;
end;
function mappingavailable(const s : string) : boolean;
begin
mappingavailable:=getmap(s)<>nil;
end;
function getunicode(c : char;p : punicodemap) : tunicodechar;
begin
if ord(c)<=p^.lastchar then
getunicode:=p^.map[ord(c)].unicode
else
getunicode:=0;
end;
function getascii(c : tunicodechar;p : punicodemap) : string;
var
i : longint;
begin
{ at least map to space }
getascii:=#32;
for i:=0 to p^.lastchar do
if p^.map[i].unicode=c then
begin
if i<256 then
getascii:=chr(i)
else
getascii:=chr(i div 256)+chr(i mod 256);
exit;
end;
end;
var
hp : punicodemap;
initialization
mappings:=nil;
finalization
while assigned(mappings) do
begin
hp:=mappings^.next;
if not(mappings^.internalmap) then
begin
freemem(mappings^.map);
dispose(mappings);
end;
mappings:=hp;
end;
end.
|