summaryrefslogtreecommitdiff
path: root/Build/source/texk/web2c/uptexdir/upbibtex.ch
blob: 852ba3c589ca6fa9cf2433ccf1c9659a82e6b0d0 (plain)
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
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
@x
@d my_name=='pbibtex'
@d banner=='This is pBibTeX, Version 0.99d-j0.33'
@y
@d my_name=='upbibtex'
@d banner=='This is upBibTeX, Version 0.99d-j0.33-u1.24'
@z

@x
for i:=@'200 to @'237 do xchr[i]:=chr(i-@'200);
for i:=@'240 to 255 do xchr[i]:=chr(i);
@y
for i:=@'200 to 255 do xchr[i]:=chr(i);
@z

@x
for i:=@'200 to @'237 do xord[i]:= i-@'200;
for i:=@'240 to 255 do xord[i]:=i;
@y
for i:=@'200 to 255 do xord[i]:=i;
@z

@x
@d zen_pun_first = 161          {Zenkaku punctuation first byte; in EUC}
@d zen_space = 161              {Zenkaku space first, second byte; in EUC}
@d zen_kuten = 162              {Zenkaku kuten second byte; in EUC}
@d zen_ten = 163                {Zenkaku ten second byte; in EUC}
@d zen_comma = 164              {Zenkaku comman second byte; in EUC}
@d zen_period = 165             {Zenkaku period second byte; in EUC}
@d zen_question = 169           {Zenkaku question mark second byte; in EUC}
@d zen_exclamation = 170        {Zenkaku exclamation mark second byte; in EUC}
@y
@d e_ss3 = @"8F                 {single shift three in EUC}
@d e_pun_first = @"A1           {Zenkaku punctuation first byte; in EUC}
@d e_space = @"A1A1             {Zenkaku space; in EUC}
@d e_toten = @"A1A2             {Zenkaku kuten; in EUC}
@d e_kuten = @"A1A3             {Zenkaku toten; in EUC}
@d e_comma = @"A1A4             {Zenkaku comman; in EUC}
@d e_period = @"A1A5            {Zenkaku period; in EUC}
@d e_question = @"A1A9          {Zenkaku question mark; in EUC}
@d e_exclamation =@"A1AA        {Zenkaku exclamation mark; in EUC}
@d u_pun_first1 = @"E3          {Zenkaku punctuation first byte(1); in UTF-8}
@d u_pun_first2 = @"EF          {Zenkaku punctuation first byte(2); in UTF-8}
@d u_space = @"3000             {Zenkaku space; in UCS}
@d u_toten = @"3001             {Zenkaku toten; in UCS}
@d u_kuten = @"3002             {Zenkaku kuten; in UCS}
@d u_comma = @"FF0C             {Zenkaku comman; in UCS}
@d u_period = @"FF0E            {Zenkaku period; in UCS}
@d u_question = @"FF1F          {Zenkaku question mark; in UCS}
@d u_exclamation = @"FF01       {Zenkaku exclamation mark; in UCS}
@d u_double_question = @"2047   {Zenkaku double question mark; in UCS}
@d u_double_exclam   = @"203C   {Zenkaku double exclamation mark; in UCS}
@d u_question_exclam = @"2048   {Zenkaku question exclamation mark; in UCS}
@d u_exclam_question = @"2049   {Zenkaku exclamation question mark; in UCS}
@z

@x
for i:=@'200 to @'237 do lex_class[i] := illegal;
for i:=@'240 to 255 do lex_class[i] := alpha;
lex_class[@'33]:=alpha;
@y
@z

@x
for i:=@'200 to @'237 do id_class[i] := illegal_id_char;
@y
@z

@x
for i:=@'240 to 254 do char_width[i]:=514;
@y
@z

@x procedure get_the_top_level_aux_file_name
label aux_found,@!aux_not_found;
@y
label aux_found,@!aux_not_found;
var i:0..last_text_char;    {this is the first one declared}
@z
@x
  @<Process a possible command line@>
@y
  @<Process a possible command line@>
  @<Initialize variables depending on Kanji code@>
@z

@x
    zen_ten,
    zen_period,
    zen_question,
    zen_exclamation:
        if( str_pool[sp_ptr-1] = zen_pun_first ) then
            repush_string
        else
            @<Add the |period| (it's necessary) and push@>;
    othercases
        @<Add the |period| (it's necessary) and push@>
@y
    othercases
        begin
        if (is_internalEUC) then
            begin
            case (fromBUFF(str_pool, sp_ptr+1, sp_ptr-1)) of
                e_kuten,
                e_period,
                e_question,
                e_exclamation:
                    if (str_pool[sp_ptr-2]<>e_ss3) then
                       repush_string
                    else
                       @<Add the |period| (it's necessary) and push@>;
                othercases
                    @<Add the |period| (it's necessary) and push@>;
            endcases;
            end;
        if (is_internalUPTEX) then
            begin
            case (fromBUFF(str_pool, sp_ptr+1, sp_ptr-2)) of
                u_kuten,
                u_period,
                u_question,
                u_exclamation,
                u_double_question,
                u_double_exclam,
                u_question_exclam,
                u_exclam_question:
                    repush_string;
                othercases
                    @<Add the |period| (it's necessary) and push@>;
            endcases;
            end;
        end;
@z

@x
    if(str_pool[str_start[pop_lit1]]>127) then { a KANJI char is 2byte long }
@y
    if(str_pool[str_start[pop_lit1]]>127) then { a KANJI char is |2..4|byte long }
@z

@x
    if( (ex_buf[ex_buf_ptr-1]=zen_comma) or (ex_buf[ex_buf_ptr-1]=zen_kuten) )
    then ex_buf_ptr := ex_buf_ptr - 2
    else ex_buf_ptr := ex_buf_ptr - 4;
@y
    if (is_internalEUC) then
      if((fromBUFF(ex_buf, ex_buf_length, ex_buf_ptr-2) = e_comma) or
         (fromBUFF(ex_buf, ex_buf_length, ex_buf_ptr-2) = e_toten))
      then ex_buf_ptr := ex_buf_ptr - 2
      else ex_buf_ptr := ex_buf_ptr - 4;
    if (is_internalUPTEX) then
      if((fromBUFF(ex_buf, ex_buf_length, ex_buf_ptr-3) = u_comma) or
         (fromBUFF(ex_buf, ex_buf_length, ex_buf_ptr-3) = u_toten))
      then ex_buf_ptr := ex_buf_ptr - 3
      else ex_buf_ptr := ex_buf_ptr - 4;
@z

@x
     zen_pun_first:
        begin
          if((ex_buf[ex_buf_ptr+1]=zen_comma) or
             (ex_buf[ex_buf_ptr+1]=zen_kuten) ) then
@y
     e_pun_first:
        if (is_internalEUC) then
        begin
          if ((fromBUFF(ex_buf, ex_buf_length, ex_buf_ptr) = e_comma) or 
              (fromBUFF(ex_buf, ex_buf_length, ex_buf_ptr) = e_toten)) then
@z
@x
          else if(ex_buf[ex_buf_ptr+1]=zen_space) then
@y
          else if (fromBUFF(ex_buf,ex_buf_length,ex_buf_ptr) = e_space) then
@z
@x
        end;
@y
        end else begin
            ex_buf_ptr := ex_buf_ptr + multibytelen(ex_buf[ex_buf_ptr]);
            preceding_white := false;
        end;
     u_pun_first1,
     u_pun_first2:
        if (is_internalUPTEX) then
        begin
          if ((fromBUFF(ex_buf, ex_buf_length, ex_buf_ptr) = u_comma) or 
              (fromBUFF(ex_buf, ex_buf_length, ex_buf_ptr) = u_toten)) then
                begin
                  preceding_white := false;
                  and_found  := true
                end
          else if (fromBUFF(ex_buf,ex_buf_length,ex_buf_ptr) = u_space) then
               begin
                  ex_buf[ex_buf_ptr]   := space;
                  ex_buf[ex_buf_ptr+1] := space;
                  ex_buf[ex_buf_ptr+2] := space;
                  preceding_white := true;
               end;
          ex_buf_ptr := ex_buf_ptr + 3;
        end else begin
            ex_buf_ptr := ex_buf_ptr + multibytelen(ex_buf[ex_buf_ptr]);
            preceding_white := false;
        end;
@z

@x
                if( ex_buf[ex_buf_ptr] > 127 ) then
                        ex_buf_ptr := ex_buf_ptr +2
                else
                        incr(ex_buf_ptr);
@y
            ex_buf_ptr := ex_buf_ptr + multibytelen(ex_buf[ex_buf_ptr]);
@z

@x
            if name_buf[name_bf_ptr]>127 then begin
                append_ex_buf_char_and_check (name_buf[name_bf_ptr]);
                incr(name_bf_ptr);
                append_ex_buf_char_and_check (name_buf[name_bf_ptr]);
            end
            else
                append_ex_buf_char_and_check (name_buf[name_bf_ptr]);
@y
        append_ex_buf_char_and_check (name_buf[name_bf_ptr]);
        if multibytelen(name_buf[name_bf_ptr]) > 1 then
            append_ex_buf_char_and_check (name_buf[name_bf_ptr+1]);
        if multibytelen(name_buf[name_bf_ptr]) > 2 then
            append_ex_buf_char_and_check (name_buf[name_bf_ptr+2]);
        if multibytelen(name_buf[name_bf_ptr]) > 3 then
            append_ex_buf_char_and_check (name_buf[name_bf_ptr+3]);
        name_bf_ptr := name_bf_ptr + multibytelen(name_buf[name_bf_ptr])-1;
@z

@x
{ 2 bytes Kanji code break check }
tps:=str_start[pop_lit3];
while (tps < sp_ptr) do begin
    if str_pool[tps] > 127
    then tps := tps + 2
    else incr(tps);
end;
tpe:=tps;
while (tpe < sp_end) do begin
    if str_pool[tpe] > 127
    then tpe := tpe+2
    else incr(tpe);
end;
if tps<>sp_ptr then begin
    if tps>str_start[pop_lit3]
    then decr(sp_ptr)
    else incr(sp_ptr);
end;
if tpe<>sp_end then begin
    if tpe<str_start[pop_lit3+1]
    then incr(sp_end)
    else decr(sp_end);
end;
@y
{ |2..4| bytes Kanji code break check }
tps:=str_start[pop_lit3];
tpe:=tps;
while tpe < str_start[pop_lit3+1] do begin
    if multibytelen(str_pool[tpe])<0
        or (str_start[pop_lit3+1] < tpe+multibytelen(str_pool[tpe])) then
        break;
    tpe := tpe + multibytelen(str_pool[tpe]);
    if tpe<=sp_ptr then
        tps := tpe;
    if sp_end<=tpe then break;
end;
sp_ptr := tps;
sp_end := tpe;
@z

@x
    if str_pool[sp_ptr] >127 then begin
         append_char (str_pool[sp_ptr]); incr(sp_ptr);
         append_char (str_pool[sp_ptr]); incr(sp_ptr);
         end
    else begin
         append_char (str_pool[sp_ptr]); incr(sp_ptr);
         end;
@y
    append_char (str_pool[sp_ptr]);
    incr(sp_ptr);
@z

@x
            incr(sp_xptr1); num_text_chars:=num_text_chars+2;
@y
            num_text_chars := num_text_chars + multibytelen(str_pool[sp_xptr1-1]);
            sp_xptr1 := sp_xptr1-1 + multibytelen(str_pool[sp_xptr1-1]);
@z

@x
const n_options = 6; {Pascal won't count array lengths for us.}
@y
const n_options = 7; {Pascal won't count array lengths for us.}
@z

@x
      usage_help (PBIBTEX_HELP, 'issue@@texjp.org');
@y
      usage_help (UPBIBTEX_HELP, 'issue@@texjp.org');
@z

@x
    end; {Else it was a flag; |getopt| has already done the assignment.}
@y
    end else if argument_is ('kanji-internal') then begin
      if (not (set_enc_string(nil,optarg) and
               (is_internalEUC or is_internalUPTEX))) then
        write_ln('Bad internal kanji encoding "', stringcast(optarg), '".');

    end; {Else it was a flag; |getopt| has already done the assignment.}
@z

@x
@ An element with all zeros always ends the list.
@y
@ Kanji-internal option.
@.-kanji-internal@>

@<Define the option...@> =
long_options[current_option].name := 'kanji-internal';
long_options[current_option].has_arg := 1;
long_options[current_option].flag := 0;
long_options[current_option].val := 0;
incr(current_option);

@ An element with all zeros always ends the list.
@z

@x
exit:end;
@y
exit:end;

@ @<Initialize variables depending on Kanji code@>=
if (is_internalUPTEX) then
  begin
    for i:=@"80 to @"BF do lex_class[i] := alpha; { trail bytes }
    for i:=@"C0 to @"C1 do lex_class[i] := illegal;
    for i:=@"C2 to @"F4 do lex_class[i] := alpha; { lead bytes }
    for i:=@"F5 to @"FF do lex_class[i] := illegal;
    for i:=@"C0 to @"C1 do id_class[i] := illegal_id_char;
    for i:=@"F5 to @"FF do id_class[i] := illegal_id_char;
    for i:=@"80 to @"BF do char_width[i]:=257; { trail bytes }
    for i:=@"C2 to @"DF do char_width[i]:=771; { lead bytes (2bytes) }
    for i:=@"E0 to @"EF do char_width[i]:=514; { lead bytes (3bytes) }
    for i:=@"F0 to @"F4 do char_width[i]:=257; { lead bytes (4bytes) }
  end
else
  begin { is_internalEUC }
    for i:=@'200 to @'240 do lex_class[i] := illegal;
    for i:=@'241 to 254 do lex_class[i] := alpha;
    lex_class[255]:=illegal;
    for i:=@'200 to @'240 do id_class[i] := illegal_id_char;
    id_class[255]:=illegal_id_char;
    lex_class[@'33]:=alpha;
    lex_class[e_ss3]:=alpha;
    for i:=@'241 to 254 do char_width[i]:=514;
    char_width[e_ss3]:=0;
  end;
@z