forked from cltk/grc_software_tlgu
-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathtlgu.c
1529 lines (1441 loc) · 45.9 KB
/
tlgu.c
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
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/* tlgu: Translates TLG (D) / PHI text files to Unicode text
*
* Copyright (C) 2004, 2005, 2011, 2013, 2020 Dimitri Marinakis
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License Version 2
* as published by the Free Software Foundation.
*
* 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., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
*
* Usage:
* tlgu [options] [beta_code_file] [unicode_text_file]
*
* Options:
* -r -- primarily Roman text (e.g. Canon, PHI); default betastate = ROMAN, reset on every ID code
* -v -w -x -y -z -- work reference citations are printed in the form xxx.xxx...xxx
* -Z <custom_citation_format_prefix> -- use reference and description citation codes in string
* reference a-z, description A-Z also special codes \t(ab) \n(new line) \r(eturn)
* e.g. "%A/%Z/%v/%w/%y/%z\t"
* -e -- companion to -Z above; a string to put out when a defined citation slot
* is empty (e.g. "NONE", or "-")
*
* -b -- books are preceded by a page feed and description citations are printed
* -p -- pagination is observed, otherwise book lines are printed continuously
* -B -- output blank space (tab) after each new line (beginning of line)
*
* -X -- citations are printed as they change (v, w, x)
* -Y -- citations are printed as they change (w, x, y)
* -N -- no spaces - line ends, and hyphens before an ID code, are removed
*
* -C -- citation debug information is printed
* -S -- special code debug information is printed
* -T -- bracket debug information is printed
* -V -- processing debug information is printed
* -W -- multiple output files, one for each work
*
* Returns: exit code 1 if unsuccesful
*
* Make: gcc tlgu.c -o tlgu
*
* History: This is a re-write of a DOS program (tlgft.asm) written several
* years ago to translate Hellenic texts distributed on the TLG CD-ROM from
* "beta code" to something readable, editable and printable.
*
* Contributors: Troy Griffitts (tg), Nick White (nw)
*
* Pointers / References:
* TLG Project - www.tlg.uci.edu
* PHI CD ROM Format Description, Packard Humanities Institute, 19 April 1992
* Beta code reference - Text versions: tlgbeta.txt, tlgcode.txt, BCM2004.pdf (23-Jun-2004)
*
* ID locator reference - Text version tlgcodes.txt
*
* 14-Jun-2001 dm -- c port: ELOT-928 with custom dead-accent codes
* 14-Jun-2004 dm -- Unicode
* 26-Jun-2004 dm -- Command-line options
* 26-Feb-2005 dm -- Output file separation (-W option)
* 06-Mar-2005 dm -- Latin accent characters added (without parentheses)
* 02-Aug-2005 tg -- Free-form citations (options -Z, -e) and per-line processing
* 22-Apr-2006 dm -- Includes to make gcc (4.x) happy, final sigma fix for free text
* 02-Oct-2011 dm -- Output written to stdout if an output file name is not provided
* 16-Oct-2011 dm -- Code correction for lower case phi
* 20-Nov-2011 dm -- stop processing gracefully when writing to stdout
* 20-Nov-2011 dm -- e-book type citations (options -X -Y)
* 01-May-2012 nw -- reading from stdin
* 17-Mar-2013 dm -- minor error handling corrections
* 15-May-2020 dm -- vowels with acute accent may be output with U0370 codes (option -U), additional code points
* 18-May-2020 dm -- rudimentary quasi bracket handling
*
*/
#include "tlgu.h"
#include "tlgcodes.h"
/****************** PROTOTYPES FROM THE TOP DOWN *******************/
int tlgu (char * input_file, char * output_file);
void output_utf2(int ucode);
void output_utf(int ucode);
void output_string(char *outstr);
int process_beta (int input_count);
void beta_code(int input_count);
int id_code(int input_count);
void store_accents(unsigned char bufferchar);
const char *resolve_cite_format(const char *cformat);
/****************** PROGRAM VERSION INFORMATION *******************/
char *prog_version="1.8.2";
/****************** COMMAND LINE OPTIONS **************************/
int opt_roman = 0;
int opt_page = 0;
int opt_blank = 0;
int opt_acit = 0;
int opt_bcit = 0;
int opt_ccit = 0;
int opt_dcit = 0;
int opt_cit_id = 0; /* combines a, b, c */
int opt_vcit = 0;
int opt_wcit = 0;
int opt_xcit = 0;
int opt_ycit = 0;
int opt_cprefix = 0;
char cformat[253];
int opt_ecit_blank = 0;
char ecite[253];
int opt_zcit = 0;
int opt_verbose = 0;
int opt_debug_bracket = 0;
int opt_debug_cit = 0;
int opt_debug_special = 0;
int opt_multiple = 0;
int opt_ebook_cit_x = 0;
int opt_ebook_cit_y = 0;
int opt_nospace = 0;
int opt_U370 = 0;
/****************** GLOBAL VARIABLES *******************************/
int iptr = 0; /* input buffer pointer, reset before every read */
int optr = 0; /* output buffer pointer, reset after every write */
unsigned char input_buffer[INRECSIZE];
unsigned char output_buffer[OUTRECSIZE];
#define MAXFILELEN 256
int prev_cit_w = 0;
int prev_cit_x = 0;
int prev_cit_y = 0;
/************ GLOBAL BETA CODE PROCESSING VARIABLES **************/
unsigned int outcode;
int betastate; /* translation state machine */
int previous_state; /* needed for symbol translations */
int start_new_line = 0; /* needed for symbol translations */
int book_change = 0; /* needed for symbol translations */
int accents; /* holds accent combinations */
char *accented_chars = "AEHIOUWR";
char *accent_chars = ")(+/\\=|";
char *latin_accent_chars = "+/\\=|";
char *escape_codes = "$&%\"@#^[]<>{}";
char *punctuation_codes = " .,:;_\"%{}$&"; /* used by which_sigma */
char previous_bcit[52][32]; /* holds previous work (book) citation */
/****************** GLOBAL DESCRIPTOR VARIABLES *****************/
/*
Space is reserved for descriptive data as follows:
citations, binary component -- z, y, x, w, v, n (1 to 16383)
citations, ascii component -- a-z (1 to 15 characters + null, only a-d, n, v-z are actually used)
descriptors, binary component -- a-z (1 to 16383)
descriptors, ascii component -- a-z (1 to 31 characters + null)
Citations ---
a - author citation
b - work citation
c - preferred abbreviation for the work
d - preferred abbreviation for the author
n - if present signifies a document within a work
when it changes, v-z are nulled but are then independent
if n is not present, a change in an upper level nulls out the rest
v-z hierarchical citation levels, high to low
v
w
x - (chapter)
y - (verse) (book)
z - line
Descriptions ---
z - comment sequence number within a work
In the common data structures below, citations will hold the first 26 positions (0-25)
while descriptors will hold the next 26 positions.
*/
int icitation[52];
char citation[52][32];
int id_level; /* holds translated current id level as an index to ID arrays */
int id_char; /* holds the pointer for the ascii part of the ID arrays */
int id_command; /* holds the current instruction for ID handling */
int id_process; /* if non-zero, command must be processed */
/****************** HANDLE ARGUMENTS AND SYNTAX *******************/
void usage_info(void)
{
printf("\ntlgu: TLG/PHI beta code file to Unicode translator ver. %s\n", prog_version);
printf("\ntlgu: Copyright (C) 2004, 2005, 2011, 2013, 2020 Dimitri Marinakis");
printf("\ntlgu: This program is free software; you are encouraged to redistribute it under");
printf("\ntlgu: the terms of the GNU General Public License (version 2).\n");
printf("\ntlgu: This program comes with ABSOLUTELY NO WARRANTY. See the GNU General Public");
printf("\ntlgu: License in the file named `COPYING' for more details.\n");
printf("\ntlgu: Syntax: tlgu [options] [beta_code_file] [unicode_text_file]\n");
printf("\ntlgu: -r -- primarily Roman text (e.g. Canon, PHI); default betastate = ROMAN, reset on every ID code");
printf("\ntlgu: -v -w -x -y -z -- work reference citations are printed in the form xxx.xxx...xxx");
printf("\ntlgu: -Z <custom_citation_format_prefix> -- use reference and description citation codes in string");
printf("\ntlgu: reference a-z, description A-Z also special codes \\t(ab) \\n(new line) \\r(eturn)");
printf("\ntlgu: e.g. \"%%A/%%Z/%%v/%%w/%%y/%%z\\t\" \n");
printf("\ntlgu: -e <custom_blank_citation_string> -- e.g. \"[NONE]\" instead of default \"\"");
printf("\ntlgu: -X -- citations are printed as they change (v, w, x)");
printf("\ntlgu: -Y -- citations are printed as they change (w, x, y)");
printf("\ntlgu: -N -- no spaces - line ends, and hyphens before an ID code, are removed");
printf("\n");
printf("\ntlgu: -b -- books are preceded by a page feed and description citations are printed");
printf("\ntlgu: -p -- pagination is observed, otherwise book lines are printed continuously");
printf("\ntlgu: -B -- output blank space (tab) at the beginning of each line");
printf("\n");
printf("\ntlgu: -C -- citation debug information is printed");
printf("\ntlgu: -S -- special code debug information is printed");
printf("\ntlgu: -V -- processing debug information is printed");
printf("\ntlgu: -U -- output acute accents as tonoi in the Greek and Coptic Unicode block (U+0370 ff.)");
printf("\ntlgu: -W -- multiple output files, one for each work (book); output filename must be specified");
printf("\n");
}
int main(int argc, char * argv[])
{
unsigned char ucc; /* test variable */
int idx;
if (sizeof(ucc) != 1) {
printf("\ntlgu: I need 8-bit characters to work\n");
exit(1);
}
while(argc > 1 && argv[1][0] == '-') {
switch(argv[1][1]) {
case 'U':
opt_U370 = 1;
break;
case 'N':
opt_nospace = 1;
break;
case 'W':
opt_multiple = 1;
break ;
case 'V':
opt_verbose = 1;
break ;
case 'S':
opt_debug_special = 1;
break ;
case 'T':
opt_debug_bracket = 1;
break ;
case 'C':
opt_debug_cit = 1;
break ;
case 'X':
opt_ebook_cit_x = 1;
opt_ebook_cit_y = 0;
break;
case 'Y':
opt_ebook_cit_y = 1;
opt_ebook_cit_x = 0;
break;
case 'B':
opt_blank = 1;
break ;
case 'p':
opt_page = 1;
break ;
case 'r':
opt_roman = 1;
break ;
case 'a':
opt_acit = 1;
opt_cit_id = 1;
break ;
case 'b':
opt_bcit = 1;
opt_cit_id = 1;
break ;
case 'c':
opt_ccit = 1;
opt_cit_id = 1;
break ;
case 'd':
opt_dcit = 1;
opt_cit_id = 1;
break ;
case 'v':
opt_vcit = 1;
break ;
case 'w':
opt_wcit = 1;
break ;
case 'x':
opt_xcit = 1;
break;
case 'y':
opt_ycit = 1;
break ;
case 'z':
opt_zcit = 1;
break;
case 'e':
opt_ecit_blank = 1;
strcpy(ecite, argv[1]);
argc-- ;
argv++ ;
break;
case 'Z':
opt_cprefix = 1;
strcpy(cformat, argv[1]);
argc-- ;
argv++ ;
break;
default:
usage_info() ;
exit(0) ;
}
argc-- ;
argv++ ;
}
switch(argc) {
case 1:
return tlgu("", "");
break;
case 2:
return tlgu(argv[1], "");
break;
default:
return tlgu(argv[1], argv[2]);
}
}
/****************** FILE READ-WRITE LOOP **************************/
int tlgu(char *input_file, char *output_file)
{
int i; /* counter */
int j; /* counter */
int infile; /* input file descriptor */
int outfile;/* output file descriptor */
int icnt; /* input file bytes read in input buffer */
int ocnt; /* output file bytes written */
int bytes_to_process; /* bytes read minus bytes already processed */
int wehaveinput; /* flag for while */
int beta_return; /* process beta return code */
char new_file[MAXFILELEN];
struct stat filestat;
/* Open input and output files
*/
// infile = open(input_file, O_RDONLY);
if (strlen(input_file) == 0) {
infile = STDIN_FILENO;
} else {
infile = open(input_file, O_RDONLY);
}
if (infile < 0) {
perror("\ntlgu: input file open");
return(1);
} else {
if (strlen(output_file) == 0) {
outfile = STDOUT_FILENO;
} else {
if (strlen(output_file) < MAXFILELEN-5) {
strcpy(new_file, output_file);
} else {
printf("\ntlgu: output filename too long - exiting\n");
return(1);
}
outfile = open(new_file, O_WRONLY | O_CREAT | O_TRUNC);
}
if (outfile < 0) {
perror("\ntlgu: output file create");
close(infile);
return(1);
}
}
/* Initialize citation
* and descriptor indicators
*/
for (i = 0; i < 52; i++) {
icitation[i] = 0;
for (j = 0; j < 32; j++) {
citation[i][j]=0;
}
}
/* Initialize beta processing defaults
* e.g. The TLG Canon needs ROMAN as default
* Hellenic should be reset at each ID CODE
*/
if (opt_roman) betastate = ROMAN;
else betastate = HELLENIC;
/* Read, process and write file blocks,
* Optionally create one file per book (-W), unless no output file name is specified
* Change file mode (equivalent to chmod 644 output_file),
* and return.
* Note: Local deblocking usually yields higher speeds
*/
wehaveinput = 1;
while (wehaveinput) {
/* Read and process beta code in input_buffer */
icnt = read(infile, input_buffer, sizeof(input_buffer));
if (icnt == 0) wehaveinput = 0;
iptr = 0;
while ((icnt > 0) && (iptr < icnt)) {
bytes_to_process = icnt - iptr;
beta_return = process_beta(bytes_to_process);
/* Write processed data and reset output buffer pointer */
if (optr > 0) {
ocnt = write(outfile, output_buffer, optr);
optr = 0;
if (ocnt < 0) {
perror("\ntlgu output file write");
wehaveinput = 0;
}
} else if (beta_return != -2) { /* no more bytes to write, no book change request */
if (opt_verbose) printf("\ntlgu: no more bytes to write");
wehaveinput = 0; /* signal no more input */
}
if ((beta_return == -2) && (outfile != STDOUT_FILENO)) {
/* book change request, close current file and open a new one */
if (opt_verbose) printf("\ntlgu: book change request: %s", previous_bcit[1]);
if (close(outfile)) return(1);
if (chmod(new_file, S_IRUSR | S_IWUSR | S_IRGRP | S_IROTH)) return(1);
/* request file information and delete zero-length files
*/
stat(new_file, &filestat);
if (filestat.st_size == 0) unlink(new_file);
sprintf(new_file, "%s-%s.txt", output_file, previous_bcit[1]);
outfile = open(new_file, O_WRONLY | O_CREAT | O_TRUNC);
if (outfile < 0) {
perror("\ntlgu: new_file create");
close(infile);
return(1);
}
}
}
}
/* Close input and output files,
* make output file readable
*/
close(infile);
if (opt_verbose) printf("\ntlgu: processing complete\n");
if (outfile == STDOUT_FILENO) printf("\n");
if (close(outfile)) {
perror("\ntlgu output file close");
return(1);
}
if (outfile != STDOUT_FILENO) {
if (chmod(new_file, S_IRUSR | S_IWUSR | S_IRGRP | S_IROTH)) {
perror("\ntlgu output file chmod");
return(1);
}
}
return(0);
}
/****************** PROCESSING *************************************/
/* process_beta:
* Processes <input_count> bytes in <input_buffer>
* Returns: -1 for EOF, -2 for book change
* Changes: iptr
*/
int process_beta (int input_count)
{
unsigned char inchar;
unsigned int outcode;
int processing;
int iptr_max; /* holds the calculated maximum input pointer value */
int return_code; /* id_code and beta_code bytes written; error if negative */
char outstring[511];
char nstring[253];
return_code = 0;
/* A beta code stream includes two kinds of data:
* ID data - always has the high bit set.
* Text data - always has the high bit reset.
*/
processing = 1;
iptr_max = iptr + input_count;
if (opt_verbose) printf("\n\ntlgu: process_beta - %d bytes, iptr = %4.4x, iptr_max = %4.4x", input_count, iptr, iptr_max);
while (processing) {
if ((iptr < INRECSIZE) && (iptr < iptr_max)) {
inchar = input_buffer[iptr++];
if (optr < OUTRECSIZE) {
if (inchar == 0) {
/* do nothing for null characters */
} else if (inchar > 0x7F) {
/* ID data - decrement input pointer before processing */
--iptr;
/* Reset beta decoding state if roman option specified */
if (opt_roman) betastate = ROMAN;
/* Process ID code */
return_code = id_code(input_count);
if (return_code == -1) {
if (opt_verbose) printf("\ntlgu: EOF while processing id code");
processing = 0;
} else if (return_code == -2) {
if (opt_verbose) printf("\ntlgu: book change request");
processing = 0;
}
start_new_line = 1;
} else {
/* text data < 0x80 - decrement input pointer before processing */
--iptr;
if (start_new_line) {
/* Write info on (book) citation change */
if (book_change) {
if (opt_cit_id) {
sprintf(outstring, "\n\f[%s] ", citation[0]);
output_string(outstring);
sprintf(outstring, "[%s] ", citation[1]);
output_string(outstring);
sprintf(outstring, "[%s] ", citation[2]);
output_string(outstring);
sprintf(outstring, "[%s]\n", citation[3]);
output_string(outstring);
}
book_change = 0;
}
if (opt_nospace) {
outstring[0] = 0x0;
}
else {
sprintf(outstring, "\n");
}
if (opt_blank)
strcat(outstring, "\t");
else if (opt_cprefix) {
strcat(outstring, resolve_cite_format(cformat));
}
else if (opt_ebook_cit_x) {
if (prev_cit_x != icitation[23]) {
prev_cit_x = icitation[23];
if (prev_cit_w != icitation[22]) {
prev_cit_w = icitation[22];
sprintf(nstring, "\n[%d.%d] ", icitation[22], icitation[23]);
}
else {
sprintf(nstring, "\n[%d] ", icitation[23]);
}
strcat(outstring, nstring);
}
}
else if (opt_ebook_cit_y) {
if (prev_cit_y != icitation[24]) {
prev_cit_y = icitation[24];
if (prev_cit_x != icitation[23]) {
prev_cit_x = icitation[23];
sprintf(nstring, "\n[%d.%d] ", icitation[23], icitation[24]);
}
else {
sprintf(nstring, "\n[%d] ", icitation[24]);
}
strcat(outstring, nstring);
}
}
else if (opt_vcit || opt_wcit || opt_xcit || opt_ycit || opt_zcit) {
if (opt_vcit) {
if (icitation[21] == 0) sprintf(nstring, "%s.", citation[21]);
else sprintf(nstring, "%d%s.", icitation[21], citation[21]);
if ((opt_ecit_blank) && (!*nstring)) strcpy(nstring, ecite);
strcat(outstring, nstring);
}
if (opt_wcit) {
if (icitation[22] == 0) sprintf(nstring, "%s.", citation[22]);
else sprintf(nstring, "%d%s.", icitation[22], citation[22]);
if ((opt_ecit_blank) && (!*nstring)) strcpy(nstring, ecite);
strcat(outstring, nstring);
}
if (opt_xcit) {
if (icitation[23] == 0) sprintf(nstring, "%s.", citation[23]);
else sprintf(nstring, "%d%s.", icitation[23], citation[23]);
if ((opt_ecit_blank) && (!*nstring)) strcpy(nstring, ecite);
strcat(outstring, nstring);
}
if (opt_ycit) {
if (icitation[24] == 0) sprintf(nstring, "%s.", citation[24]);
else sprintf(nstring, "%d%s.", icitation[24], citation[24]);
if ((opt_ecit_blank) && (!*nstring)) strcpy(nstring, ecite);
strcat(outstring, nstring);
}
if (opt_zcit) {
if (icitation[25] == 0) sprintf(nstring, "%s.", citation[25]);
else sprintf(nstring, "%d%s", icitation[25], citation[25]);
if ((opt_ecit_blank) && (!*nstring)) strcpy(nstring, ecite);
strcat(outstring, nstring);
}
/* Separate text from citation using a tab character */
strcat(outstring, "\t");
}
if (input_buffer[iptr] < 0x80) {
/* Print only if not followed by another ID byte */
output_string(outstring);
}
start_new_line = 0;
if (opt_roman) betastate = ROMAN;
else betastate = HELLENIC;
}
beta_code(input_count);
}
} else {
/* Output size is greater than input -- intermediate write */
printf("\ntlgu: FIXME -- DATA LOSS: ERROR output size iptr - %x optr - %x", iptr, optr);
processing = 0;
}
} else {
/* Finished processing all input */
processing = 0;
}
} /* end while processing*/
if (opt_verbose) printf("\ntlgu: iptr - %4.4x, optr - %4.4x ", iptr, optr);
return return_code;
}
/****************** LIBRARY FUNCTIONS ******************************/
/* get_accents:
* gets accents in <accents>
* Returns: number of accents found or zero
* Changes: accents, iptr
*/
int get_accents(void)
{
unsigned char bufferchar;
int processing = 1;
int number_of_accents = 0;
accents = 0;
while (processing) {
if (iptr < INRECSIZE) {
bufferchar = input_buffer[iptr++];
if (betastate == ROMAN) {
if (strchr(latin_accent_chars, bufferchar)) {
store_accents(bufferchar);
number_of_accents++;
} else {
--iptr;
processing = 0;
}
} else if (strchr(accent_chars, bufferchar)) {
store_accents(bufferchar);
number_of_accents++;
} else {
--iptr;
processing = 0;
}
} else {
processing = 0;
}
}
return number_of_accents;
}
/* store_accents:
* Stores accent character passed as a parameter to <accents>
* 0 00 00 --- 0 00 00 no accent
* | | |
* | | ---- 01 psili, 10 dasia, 11 dialytika
* | ------- 01 varia, 10 oxia, 11 perispomeni
* ----------- 1 ypogegrammeni
* Changes: accents
* Caveat: currently only ORs new accent... expects an all-zero accent variable
*
* 15-May-2020 dm -- single acute accent option (Unicode U0370 code block)
*/
void store_accents(unsigned char bufferchar)
{
switch (bufferchar)
{
case ')':
accents = accents | 1;
break;
case '(':
accents = accents | 2;
break;
case '+':
accents = accents | 3;
break;
case '\\':
accents = accents | 4;
break;
case '/':
accents = accents | 8;
break;
case '=':
accents = accents | 0xc;
break;
case '|':
accents = accents | 0x10;
break;
default:
break;
}
accents &= 0x1f;
}
/* mod_accents:
*
* Part of the U0370 character output option:
*
* If accents are acute, diaeresis (dialytica) or a combination of the two
* <accents> which is used as an index to the accented character tables is
* modified for pointing to the alternate character
*
* Changes: accents
*
* 15-May 2020 dm
*/
void mod_accents(void)
{
if (accents == 8) accents = 0x20;
else if (accents == 3) accents = 0x21;
else if (accents == 11) accents = 0x22;
}
/* output_accents:
* Input: <accents>
* 0 00 00 --- 0 00 00 no accent
* | | |
* | | ---- 01 psili, 10 dasia, 11 dialytika
* | ------- 01 varia, 10 oxia, 11 perispomeni
* ----------- 1 ypogegrammeni
* Changes: optr (output_utf)
*/
void output_accents(void)
{
int paccents;
paccents = accents & 3;
if (paccents == 1)
output_utf(PSILI);
else if (paccents == 2)
output_utf(DASIA);
else if (paccents == 3)
output_utf(DIALYTIKA);
paccents = (accents & 0xc) >> 2;
if (paccents == 1)
output_utf(VARIA);
else if (paccents == 2)
output_utf(OXIA);
else if (paccents == 3) {
if (betastate == ROMAN)
output_utf(CARET);
else
output_utf(PERISPOMENI);
}
paccents = accents & 0x10;
if (paccents)
output_utf(YPOGEGRAMMENI);
}
/* getnum:
* Collects a non-zero number from the current <input_buffer> position.
* Returns: an integer or zero if no number found, -1 on end of buffer
* Changes: iptr
* 22-Apr-2006 dm - dropped unsigned attribute from bufferchar and modnumber
*/
int getnum(void)
{
#define MAXNUMBERS 32
char bufferchar;
char modnumber[MAXNUMBERS]; /* symbol or font modifier number string */
int imodnumber = 0; /* index to modnumber */
int convnumber = 0; /* converted modnumber string */
int processing = 1;
modnumber[0] = 0;
while (processing) {
if ( (iptr < INRECSIZE) && (imodnumber < MAXNUMBERS) ) {
bufferchar = input_buffer[iptr++];
if (isdigit(bufferchar)) {
modnumber[imodnumber++] = bufferchar;
} else {
--iptr;
modnumber[imodnumber] = 0;
sscanf(modnumber, "%d", &convnumber);
processing = 0;
}
} else {
convnumber = -1;
processing = 0;
}
}
if (convnumber < 0) perror("\ndid not complete number\n");
return convnumber;
}
/* output_utf2:
* Converts the input code into a UTF-8 byte sequence in output_buffer
* Changes: optr, output_buffer
* NOTE: this is a duplicate of output_utf (in order to avoid recursion)
*/
void output_utf2(int ucode)
{
if ((optr+3) > OUTRECSIZE) {
perror("\noptr out of range");
} else if (ucode == 0){
/* do nothing */
} else if (ucode < 0x80) {
output_buffer[optr++] = ucode;
} else if (ucode < 0x800) {
output_buffer[optr++] = (ucode >> 6) | 0xc0;
output_buffer[optr++] = (ucode & 0x3f) | 0x80;
} else if (ucode <= 0xffff) {
output_buffer[optr++] = ((ucode & 0xf000) >> 12) | 0xe0;
output_buffer[optr++] = ((ucode & 0x0fc0) >> 6) | 0x80;
output_buffer[optr++] = (ucode & 0x3f) | 0x80;
} else if (ucode <= 0x10ffff) {
output_buffer[optr++] = ((ucode & 0x1C0000) >> 18) | 0xF0;
output_buffer[optr++] = ((ucode & 0x03f000) >> 12) | 0x80;
output_buffer[optr++] = ((ucode & 0x000fc0) >> 6) | 0x80;
output_buffer[optr++] = (ucode & 0x3f) | 0x80;
} else {
/* higher codes are not defined for UTF-8*/
}
}
/* output_utf:
* Converts the input code into a UTF-8 byte sequence in output_buffer
* Changes: optr, output_buffer
*/
void output_utf(int ucode)
{
if ((optr+3) > OUTRECSIZE) {
perror("\noptr out of range");
} else if (ucode == 0){
/* do nothing */
} else if (ucode < 0x80) {
output_buffer[optr++] = ucode;
} else if (ucode < 0x800) {
output_buffer[optr++] = (ucode >> 6) | 0xc0;
output_buffer[optr++] = (ucode & 0x3f) | 0x80;
} else if (ucode <= 0xffff) {
output_buffer[optr++] = ((ucode & 0xf000) >> 12) | 0xe0;
output_buffer[optr++] = ((ucode & 0x0fc0) >> 6) | 0x80;
output_buffer[optr++] = (ucode & 0x3f) | 0x80;
} else if (ucode <= 0x10ffff) {
output_buffer[optr++] = ((ucode & 0x1C0000) >> 18) | 0xF0;
output_buffer[optr++] = ((ucode & 0x03f000) >> 12) | 0x80;
output_buffer[optr++] = ((ucode & 0x000fc0) >> 6) | 0x80;
output_buffer[optr++] = (ucode & 0x3f) | 0x80;
} else {
/* higher codes are not defined for UTF-8*/
}
/* Output combining codes for brackets */
if (quasi_bracket_code) output_utf2(quasi_bracket_code);
}
/* output_string:
* Calls output_utf to write a string in <output_buffer>
* Returns: the number of bytes written
* Changes: optr, output_buffer
*/
void output_string(char *outstr)
{
int nextchar;
int cnt;
for (cnt = 0; cnt < strlen(outstr); cnt++) {
output_utf(outstr[cnt]);
}
}
/* handle_escape_codes:
* Formatting and character output based on escape codes: $&%"@#^[]<>{}
* Input: escape code, optional number
* Changes: optr, output_buffer
*/
void handle_escape_codes(unsigned char beta, int number)
{
int temp = 0;
switch (beta)
{
case '$':
betastate = HELLENIC;
accents = 0;
break;
case '&':
betastate = ROMAN;
accents = 0;
break;
case '%':
if (opt_debug_special) printf("%%%d -- %s %d.%d.%d\n", number, citation[1], icitation[23], icitation[24], icitation[25]);
if (number < MAX_PUNCTUATION)
output_utf(punctuation[number]);
break;
case '\"':
if (opt_debug_special) printf("\"%d -- %s %d.%d.%d\n", number, citation[1], icitation[23], icitation[24], icitation[25]);
if (number < MAX_QUOTATION) {
if (quotation_open[number]) {
output_utf(quotation_close_symbol[number]);
quotation_open[number] = 0;
} else {
output_utf(quotation_open_symbol[number]);
quotation_open[number] = 1;
}
}
break;
case '@':
/* FIXME: If citations are active, paging should be disabled */
if (opt_debug_special) printf("@%d -- %s %d.%d.%d\n", number, citation[1], icitation[23], icitation[24], icitation[25]);
/* Page formats -- FIXME: incomplete */
if (number == 0) {
output_utf(0x20);
output_utf(0x20);
} else if (number == 1) {
if (opt_page) output_utf(0xc);
//FIXME: reinstate else output_utf(0xa);
} //fixme: reinstate else output_utf(0xa);
break;
case '#':
if (opt_debug_special) printf("#%d -- %s %d.%d.%d\n", number, citation[1], icitation[23], icitation[24], icitation[25]);
if (number < MAX_TEXT_SYMBOLS) {
output_utf(text_symbols[number]);
}
break;
case '^':
/* quarter-spaces: will output at least one space */
if (number > 0) temp = number / 4;
while (temp >= 0) {
output_utf(0x20);
temp--;
}
break;
case '[':
if (opt_debug_bracket) printf("[%d -- %s %d.%d.%d\n", number, citation[1], icitation[23], icitation[24], icitation[25]);
if (number < MAX_BRACKET) {
output_utf(bracket_open_symbol[number]);
}
break;
case ']':
if (opt_debug_bracket) printf("]%d -- %s %d.%d.%d\n", number, citation[1], icitation[23], icitation[24], icitation[25]);
if (number < MAX_BRACKET) {
output_utf(bracket_close_symbol[number]);
}
break;
case '<':
if (opt_debug_bracket) printf("<%d -- %s %d.%d.%d\n", number, citation[1], icitation[23], icitation[24], icitation[25]);
if (number < MAX_QUASI_BRACKET) {
if (number == 0 || number == 1 || number == 3 || number == 4 || number == 5 \
|| number == 8 || number == 17 || number == 18) {
quasi_bracket_code = quasi_bracket_open_symbol[number];
} else {
output_utf(quasi_bracket_open_symbol[number]);
}
}
break;
case '>':
if (opt_debug_bracket) printf(">%d -- %s %d.%d.%d\n", number, citation[1], icitation[23], icitation[24], icitation[25]);
if (number < MAX_QUASI_BRACKET) {
if (quasi_bracket_code) {
quasi_bracket_code = 0; /* stop outputting combining codes */
} else {
output_utf(quasi_bracket_close_symbol[number]);
}
}
break;
case '{':
if (opt_debug_bracket) printf("{%d -- %s %d.%d.%d\n", number, citation[1], icitation[23], icitation[24], icitation[25]);
if (number < MAX_NON_TEXT) {
output_utf(non_text_open_symbol[number]);
}
break;
case '}':
if (opt_debug_bracket) printf("{%d -- %s %d.%d.%d\n", number, citation[1], icitation[23], icitation[24], icitation[25]);
if (number < MAX_NON_TEXT) {
output_utf(non_text_close_symbol[number]);