summaryrefslogtreecommitdiff
path: root/Build/source/texk/web2c/luatexdir/tex/textoken.w
blob: 2a57eff17c55933d18ae1d942ea5606abab4a2c3 (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
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
% textoken.w
% 
% Copyright 2006-2010 Taco Hoekwater <taco@@luatex.org>

% This file is part of LuaTeX.

% LuaTeX is free software; you can redistribute it and/or modify it under
% the terms of the GNU General Public License as published by the Free
% Software Foundation; either version 2 of the License, or (at your
% option) any later version.

% LuaTeX 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 Lesser General Public
% License for more details.

% You should have received a copy of the GNU General Public License along
% with LuaTeX; if not, see <http://www.gnu.org/licenses/>.

@ @c
static const char _svn_version[] =
    "$Id: textoken.w 4032 2010-12-11 09:38:19Z taco $"
    "$URL: http://foundry.supelec.fr/svn/luatex/tags/beta-0.66.0/source/texk/web2c/luatexdir/tex/textoken.w $";

#include "ptexlib.h"

@ @c
#define pausing int_par(pausing_code)
#define cat_code_table int_par(cat_code_table_code)
#define tracing_nesting int_par(tracing_nesting_code)
#define end_line_char int_par(end_line_char_code)
#define suppress_outer_error int_par(suppress_outer_error_code)

#define every_eof equiv(every_eof_loc)
#define box(A) equiv(box_base+(A))

#define detokenized_line() (line_catcode_table==NO_CAT_TABLE)

#define do_get_cat_code(a) do {                                         \
    if (line_catcode_table!=DEFAULT_CAT_TABLE)                          \
      a=get_cat_code(line_catcode_table,cur_chr);                       \
    else                                                                \
      a=get_cat_code(cat_code_table,cur_chr);                           \
  } while (0)

 
@ The \TeX\ system does nearly all of its own memory allocation, so that it
can readily be transported into environments that do not have automatic
facilities for strings, garbage collection, etc., and so that it can be in
control of what error messages the user receives. The dynamic storage
requirements of \TeX\ are handled by providing two large arrays called
|fixmem| and |varmem| in which consecutive blocks of words are used as
nodes by the \TeX\ routines.

Pointer variables are indices into this array, or into another array
called |eqtb| that will be explained later. A pointer variable might
also be a special flag that lies outside the bounds of |mem|, so we
allow pointers to assume any |halfword| value. The minimum halfword
value represents a null pointer. \TeX\ does not assume that |mem[null]| exists.



@ Locations in |fixmem| are used for storing one-word records; a conventional 
\.{AVAIL} stack is used for allocation in this array.

@c
smemory_word *fixmem;           /* the big dynamic storage area */
unsigned fix_mem_min;           /* the smallest location of one-word memory in use */
unsigned fix_mem_max;           /* the largest location of one-word memory in use */


@ In order to study the memory requirements of particular applications, it
is possible to prepare a version of \TeX\ that keeps track of current and
maximum memory usage. When code between the delimiters |@!stat| $\ldots$
|tats| is not ``commented out,'' \TeX\ will run a bit slower but it will
report these statistics when |tracing_stats| is sufficiently large.

@c
int var_used, dyn_used;         /* how much memory is in use */

halfword avail;                 /* head of the list of available one-word nodes */
unsigned fix_mem_end;           /* the last one-word node used in |mem| */

halfword garbage;               /* head of a junk list, write only */
halfword temp_token_head;       /* head of a temporary list of some kind */
halfword hold_token_head;       /* head of a temporary list of another kind */
halfword omit_template;         /* a constant token list */
halfword null_list;             /* permanently empty list */
halfword backup_head;           /* head of token list built by |scan_keyword| */

@ @c
void initialize_tokens(void)
{
    halfword p;
    avail = null;
    fix_mem_end = 0;
    p = get_avail();
    temp_token_head = p;
    set_token_info(temp_token_head, 0);
    p = get_avail();
    hold_token_head = p;
    set_token_info(hold_token_head, 0);
    p = get_avail();
    omit_template = p;
    set_token_info(omit_template, 0);
    p = get_avail();
    null_list = p;
    set_token_info(null_list, 0);
    p = get_avail();
    backup_head = p;
    set_token_info(backup_head, 0);
    p = get_avail();
    garbage = p;
    set_token_info(garbage, 0);
    dyn_used = 0;               /* initialize statistics */
}

@ The function |get_avail| returns a pointer to a new one-word node whose
|link| field is null. However, \TeX\ will halt if there is no more room left.
@^inner loop@>

If the available-space list is empty, i.e., if |avail=null|,
we try first to increase |fix_mem_end|. If that cannot be done, i.e., if
|fix_mem_end=fix_mem_max|, we try to reallocate array |fixmem|.
If, that doesn't work, we have to quit.

@c
halfword get_avail(void)
{                               /* single-word node allocation */
    unsigned p;                 /* the new node being got */
    unsigned t;
    p = (unsigned) avail;       /* get top location in the |avail| stack */
    if (p != null) {
        avail = token_link(avail);      /* and pop it off */
    } else if (fix_mem_end < fix_mem_max) {     /* or go into virgin territory */
        incr(fix_mem_end);
        p = fix_mem_end;
    } else {
        smemory_word *new_fixmem;       /* the big dynamic storage area */
        t = (fix_mem_max / 5);
        new_fixmem =
            fixmemcast(realloc
                       (fixmem, sizeof(smemory_word) * (fix_mem_max + t + 1)));
        if (new_fixmem == NULL) {
            runaway();          /* if memory is exhausted, display possible runaway text */
            overflow("token memory size", fix_mem_max);
        } else {
            fixmem = new_fixmem;
        }
        memset(voidcast(fixmem + fix_mem_max + 1), 0, t * sizeof(smemory_word));
        fix_mem_max += t;
        p = ++fix_mem_end;
    }
    token_link(p) = null;       /* provide an oft-desired initialization of the new node */
    incr(dyn_used);             /* maintain statistics */
    return (halfword) p;
}


@ The procedure |flush_list(p)| frees an entire linked list of
one-word nodes that starts at position |p|.
@^inner loop@>

@c
void flush_list(halfword p)
{                               /* makes list of single-word nodes available */
    halfword q, r;              /* list traversers */
    if (p != null) {
        r = p;
        do {
            q = r;
            r = token_link(r);
            decr(dyn_used);
        } while (r != null);    /* now |q| is the last node on the list */
        token_link(q) = avail;
        avail = p;
    }
}

@ A \TeX\ token is either a character or a control sequence, and it is
@^token@>
represented internally in one of two ways: (1)~A character whose ASCII
code number is |c| and whose command code is |m| is represented as the
number $2^{21}m+c$; the command code is in the range |1<=m<=14|. (2)~A control
sequence whose |eqtb| address is |p| is represented as the number
|cs_token_flag+p|. Here |cs_token_flag=@t$2^{25}-1$@>| is larger than
$2^{21}m+c$, yet it is small enough that |cs_token_flag+p< max_halfword|;
thus, a token fits comfortably in a halfword.

A token |t| represents a |left_brace| command if and only if
|t<left_brace_limit|; it represents a |right_brace| command if and only if
we have |left_brace_limit<=t<right_brace_limit|; and it represents a |match| or
|end_match| command if and only if |match_token<=t<=end_match_token|.
The following definitions take care of these token-oriented constants
and a few others.

@ A token list is a singly linked list of one-word nodes in |mem|, where
each word contains a token and a link. Macro definitions, output-routine
definitions, marks, \.{\\write} texts, and a few other things
are remembered by \TeX\ in the form
of token lists, usually preceded by a node with a reference count in its
|token_ref_count| field. The token stored in location |p| is called
|info(p)|.

Three special commands appear in the token lists of macro definitions.
When |m=match|, it means that \TeX\ should scan a parameter
for the current macro; when |m=end_match|, it means that parameter
matching should end and \TeX\ should start reading the macro text; and
when |m=out_param|, it means that \TeX\ should insert parameter
number |c| into the text at this point.

The enclosing \.{\char'173} and \.{\char'175} characters of a macro
definition are omitted, but the final right brace of an output routine
is included at the end of its token list.

Here is an example macro definition that illustrates these conventions.
After \TeX\ processes the text
$$\.{\\def\\mac a\#1\#2 \\b \{\#1\\-a \#\#1\#2 \#2\}}$$
the definition of \.{\\mac} is represented as a token list containing
$$\def\,{\hskip2pt}
\vbox{\halign{\hfil#\hfil\cr
(reference count), |letter|\,\.a, |match|\,\#, |match|\,\#, |spacer|\,\.\ ,
\.{\\b}, |end_match|,\cr
|out_param|\,1, \.{\\-}, |letter|\,\.a, |spacer|\,\.\ , |mac_param|\,\#,
|other_char|\,\.1,\cr
|out_param|\,2, |spacer|\,\.\ , |out_param|\,2.\cr}}$$
The procedure |scan_toks| builds such token lists, and |macro_call|
does the parameter matching.
@^reference counts@>

Examples such as
$$\.{\\def\\m\{\\def\\m\{a\}\ b\}}$$
explain why reference counts would be needed even if \TeX\ had no \.{\\let}
operation: When the token list for \.{\\m} is being read, the redefinition of
\.{\\m} changes the |eqtb| entry before the token list has been fully
consumed, so we dare not simply destroy a token list when its
control sequence is being redefined.

If the parameter-matching part of a definition ends with `\.{\#\{}',
the corresponding token list will have `\.\{' just before the `|end_match|'
and also at the very end. The first `\.\{' is used to delimit the parameter; the
second one keeps the first from disappearing.

The |print_meaning| subroutine displays |cur_cmd| and |cur_chr| in
symbolic form, including the expansion of a macro or mark.

@c
void print_meaning(void)
{
    print_cmd_chr((quarterword) cur_cmd, cur_chr);
    if (cur_cmd >= call_cmd) {
        print_char(':');
        print_ln();
        token_show(cur_chr);
    } else {
        /* Show the meaning of a mark node */
        if ((cur_cmd == top_bot_mark_cmd) && (cur_chr < marks_code)) {
            print_char(':');
            print_ln();
            switch (cur_chr) {
            case first_mark_code:
                token_show(first_mark(0));
                break;
            case bot_mark_code:
                token_show(bot_mark(0));
                break;
            case split_first_mark_code:
                token_show(split_first_mark(0));
                break;
            case split_bot_mark_code:
                token_show(split_bot_mark(0));
                break;
            default:
                token_show(top_mark(0));
                break;
            }
        }
    }
}


@ The procedure |show_token_list|, which prints a symbolic form of
the token list that starts at a given node |p|, illustrates these
conventions. The token list being displayed should not begin with a reference
count. However, the procedure is intended to be robust, so that if the
memory links are awry or if |p| is not really a pointer to a token list,
nothing catastrophic will happen.

An additional parameter |q| is also given; this parameter is either null
or it points to a node in the token list where a certain magic computation
takes place that will be explained later. (Basically, |q| is non-null when
we are printing the two-line context information at the time of an error
message; |q| marks the place corresponding to where the second line
should begin.)

For example, if |p| points to the node containing the first \.a in the
token list above, then |show_token_list| will print the string
$$\hbox{`\.{a\#1\#2\ \\b\ ->\#1\\-a\ \#\#1\#2\ \#2}';}$$
and if |q| points to the node containing the second \.a,
the magic computation will be performed just before the second \.a is printed.

The generation will stop, and `\.{\\ETC.}' will be printed, if the length
of printing exceeds a given limit~|l|. Anomalous entries are printed in the
form of control sequences that are not followed by a blank space, e.g.,
`\.{\\BAD.}'; this cannot be confused with actual control sequences because
a real control sequence named \.{BAD} would come out `\.{\\BAD\ }'.

@c
void show_token_list(int p, int q, int l)
{
    int m, c;                   /* pieces of a token */
    ASCII_code match_chr;       /* character used in a `|match|' */
    ASCII_code n;               /* the highest parameter number, as an ASCII digit */
    match_chr = '#';
    n = '0';
    tally = 0;
    if (l < 0)
        l = 0x3FFFFFFF;
    while ((p != null) && (tally < l)) {
        if (p == q) {
            /* Do magic computation */
            set_trick_count();
        }
        /* Display token |p|, and |return| if there are problems */
        if ((p < (int) fix_mem_min) || (p > (int) fix_mem_end)) {
            tprint_esc("CLOBBERED.");
            return;
        }
        if (token_info(p) >= cs_token_flag) {
            if (!((inhibit_par_tokens) && (token_info(p) == par_token)))
                print_cs(token_info(p) - cs_token_flag);
        } else {
            m = token_cmd(token_info(p));
            c = token_chr(token_info(p));
            if (token_info(p) < 0) {
                tprint_esc("BAD.");
            } else {
                /* Display the token $(|m|,|c|)$ */
                /* The procedure usually ``learns'' the character code used for macro
                   parameters by seeing one in a |match| command before it runs into any
                   |out_param| commands. */
                switch (m) {
                case left_brace_cmd:
                case right_brace_cmd:
                case math_shift_cmd:
                case tab_mark_cmd:
                case sup_mark_cmd:
                case sub_mark_cmd:
                case spacer_cmd:
                case letter_cmd:
                case other_char_cmd:
                    print(c);
                    break;
                case mac_param_cmd:
                    if (!in_lua_escape)
                        print(c);
                    print(c);
                    break;
                case out_param_cmd:
                    print(match_chr);
                    if (c <= 9) {
                        print_char(c + '0');
                    } else {
                        print_char('!');
                        return;
                    }
                    break;
                case match_cmd:
                    match_chr = c;
                    print(c);
                    incr(n);
                    print_char(n);
                    if (n > '9')
                        return;
                    break;
                case end_match_cmd:
                    if (c == 0)
                        tprint("->");
                    break;
                default:
                    tprint_esc("BAD.");
                    break;
                }
            }
        }
        p = token_link(p);
    }
    if (p != null)
        tprint_esc("ETC.");
}

@ @c
#define do_buffer_to_unichar(a,b)  do {                         \
        a = (halfword)str2uni(buffer+b);                        \
        b += utf8_size(a);                                      \
    } while (0)


@ Here's the way we sometimes want to display a token list, given a pointer
to its reference count; the pointer may be null.

@c
void token_show(halfword p)
{
    if (p != null)
        show_token_list(token_link(p), null, 10000000);
}


 
@ |delete_token_ref|, is called when
a pointer to a token list's reference count is being removed. This means
that the token list should disappear if the reference count was |null|,
otherwise the count should be decreased by one.
@^reference counts@>

@c
void delete_token_ref(halfword p)
{                               /* |p| points to the reference count
                                   of a token list that is losing one reference */
    assert(token_ref_count(p) >= 0);
    if (token_ref_count(p) == 0)
        flush_list(p);
    else
        decr(token_ref_count(p));
}

@ @c
int get_char_cat_code(int cur_chr)
{
    int a;
    do_get_cat_code(a);
    return a;
}

@ @c
static void invalid_character_error(void)
{
    const char *hlp[] =
        { "A funny symbol that I can't read has just been input.",
        "Continue, and I'll forget that it ever happened.",
        NULL
    };
    deletions_allowed = false;
    tex_error("Text line contains an invalid character", hlp);
    deletions_allowed = true;
}

@ @c
static boolean process_sup_mark(void);  /* below */

static int scan_control_sequence(void); /* below */

typedef enum { next_line_ok, next_line_return,
    next_line_restart
} next_line_retval;

static next_line_retval next_line(void);        /* below */

 
@  In case you are getting bored, here is a slightly less trivial routine:
   Given a string of lowercase letters, like `\.{pt}' or `\.{plus}' or
   `\.{width}', the |scan_keyword| routine checks to see whether the next
   tokens of input match this string. The match must be exact, except that
   uppercase letters will match their lowercase counterparts; uppercase
   equivalents are determined by subtracting |"a"-"A"|, rather than using the
   |uc_code| table, since \TeX\ uses this routine only for its own limited
   set of keywords.

   If a match is found, the characters are effectively removed from the input
   and |true| is returned. Otherwise |false| is returned, and the input
   is left essentially unchanged (except for the fact that some macros
   may have been expanded, etc.).
   @^inner loop@>

@c
boolean scan_keyword(const char *s)
{                               /* look for a given string */
    halfword p;                 /* tail of the backup list */
    halfword q;                 /* new node being added to the token list via |store_new_token| */
    const char *k;              /* index into |str_pool| */
    halfword save_cur_cs = cur_cs;
    int saved_align_state = align_state;
    assert (strlen(s) > 1);
    p = backup_head;
    token_link(p) = null;
    k = s;
    while (*k) {
        get_x_token();      /* recursion is possible here */
        if ((cur_cs == 0) &&
            ((cur_chr == *k) || (cur_chr == *k - 'a' + 'A'))) {
            store_new_token(cur_tok);
            k++;
        } else if ((cur_cmd != spacer_cmd) || (p != backup_head)) {
            if (p != backup_head) {
                q = get_avail();
                token_info(q) = cur_tok;
                token_link(q) = null;
                token_link(p) = q;
                begin_token_list(token_link(backup_head), backed_up);
                if (cur_cmd != endv_cmd) 
   	           align_state = saved_align_state;
            } else {
                back_input();
            }
            cur_cs = save_cur_cs;
            return false;
        }
    }
    flush_list(token_link(backup_head));
    cur_cs = save_cur_cs;
    if (cur_cmd != endv_cmd)
        align_state = saved_align_state;
    return true;
}

@ We can not return |undefined_control_sequence| under some conditions
 (inside |shift_case|, for example). This needs thinking.
 
@c
halfword active_to_cs(int curchr, int force)
{
    halfword curcs;
    char *a, *b;
    char *utfbytes = xmalloc(10);
    int nncs = no_new_control_sequence;
    a = (char *) uni2str(0xFFFF);
    utfbytes = strcpy(utfbytes, a);
    if (force)
        no_new_control_sequence = false;
    if (curchr > 0) {
        b = (char *) uni2str((unsigned) curchr);
        utfbytes = strcat(utfbytes, b);
        free(b);
        curcs = string_lookup(utfbytes, strlen(utfbytes));
    } else {
        utfbytes[3] = '\0';
        curcs = string_lookup(utfbytes, 4);
    }
    no_new_control_sequence = nncs;
    free(a);
    free(utfbytes);
    return curcs;
}

@ TODO this function should listen to \.{\\escapechar} 

@c
static char *cs_to_string(halfword p)
{                               /* prints a control sequence */
    const char *s;
    char *sh;
    int k = 0;
    static char ret[256] = { 0 };
    if (p == 0 || p == null_cs) {
        ret[k++] = '\\';
        s = "csname";
        while (*s) {
            ret[k++] = *s++;
        }
        ret[k++] = '\\';
        s = "endcsname";
        while (*s) {
            ret[k++] = *s++;
        }
        ret[k] = 0;

    } else {
        str_number txt = cs_text(p);
        sh = makecstring(txt);
        s = sh;
        if (is_active_cs(txt)) {
            s = s + 3;
            while (*s) {
                ret[k++] = *s++;
            }
            ret[k] = 0;
        } else {
            ret[k++] = '\\';
            while (*s) {
                ret[k++] = *s++;
            }
            ret[k] = 0;
        }
        free(sh);
    }
    return (char *) ret;
}

@ TODO this is a quick hack, will be solved differently soon 

@c
static char *cmd_chr_to_string(int cmd, int chr)
{
    char *s;
    str_number str;
    int sel = selector;
    selector = new_string;
    print_cmd_chr((quarterword) cmd, chr);
    str = make_string();
    s = makecstring(str);
    selector = sel;
    flush_str(str);
    return s;
}

@ The heart of \TeX's input mechanism is the |get_next| procedure, which
we shall develop in the next few sections of the program. Perhaps we
shouldn't actually call it the ``heart,'' however, because it really acts
as \TeX's eyes and mouth, reading the source files and gobbling them up.
And it also helps \TeX\ to regurgitate stored token lists that are to be
processed again.
@^eyes and mouth@>

The main duty of |get_next| is to input one token and to set |cur_cmd|
and |cur_chr| to that token's command code and modifier. Furthermore, if
the input token is a control sequence, the |eqtb| location of that control
sequence is stored in |cur_cs|; otherwise |cur_cs| is set to zero.

Underlying this simple description is a certain amount of complexity
because of all the cases that need to be handled.
However, the inner loop of |get_next| is reasonably short and fast.

When |get_next| is asked to get the next token of a \.{\\read} line,
it sets |cur_cmd=cur_chr=cur_cs=0| in the case that no more tokens
appear on that line. (There might not be any tokens at all, if the
|end_line_char| has |ignore| as its catcode.)


@ The value of |par_loc| is the |eqtb| address of `\.{\\par}'. This quantity
is needed because a blank line of input is supposed to be exactly equivalent
to the appearance of \.{\\par}; we must set |cur_cs:=par_loc|
when detecting a blank line.

@c
halfword par_loc;               /* location of `\.{\\par}' in |eqtb| */
halfword par_token;             /* token representing `\.{\\par}' */


@ Parts |get_next| are executed more often than any other instructions of \TeX.
@^mastication@>@^inner loop@>



@ The global variable |force_eof| is normally |false|; it is set |true|
by an \.{\\endinput} command. |luacstrings| is the number of lua print
statements waiting to be input, it is changed by |luatokencall|.

@c
boolean force_eof;              /* should the next \.{\\input} be aborted early? */
int luacstrings;                /* how many lua strings are waiting to be input? */


@ If the user has set the |pausing| parameter to some positive value,
and if nonstop mode has not been selected, each line of input is displayed
on the terminal and the transcript file, followed by `\.{=>}'.
\TeX\ waits for a response. If the response is simply |carriage_return|, the
line is accepted as it stands, otherwise the line typed is
used instead of the line in the file.

@c
void firm_up_the_line(void)
{
    int k;                      /* an index into |buffer| */
    ilimit = last;
    if (pausing > 0) {
        if (interaction > nonstop_mode) {
            wake_up_terminal();
            print_ln();
            if (istart < ilimit) {
                for (k = istart; k <= ilimit - 1; k++)
                    print_char(buffer[k]);
            }
            first = ilimit;
            prompt_input("=>"); /* wait for user response */
            if (last > first) {
                for (k = first; k < +last - 1; k++)     /* move line down in buffer */
                    buffer[k + istart - first] = buffer[k];
                ilimit = istart + last - first;
            }
        }
    }
}



@ Before getting into |get_next|, let's consider the subroutine that
   is called when an `\.{\\outer}' control sequence has been scanned or
   when the end of a file has been reached. These two cases are distinguished
   by |cur_cs|, which is zero at the end of a file.

@c
void check_outer_validity(void)
{
    halfword p;                 /* points to inserted token list */
    halfword q;                 /* auxiliary pointer */
    if (suppress_outer_error)
        return;
    if (scanner_status != normal) {
        deletions_allowed = false;
        /* Back up an outer control sequence so that it can be reread; */
        /* An outer control sequence that occurs in a \.{\\read} will not be reread,
           since the error recovery for \.{\\read} is not very powerful. */
        if (cur_cs != 0) {
            if ((istate == token_list) || (iname < 1) || (iname > 17)) {
                p = get_avail();
                token_info(p) = cs_token_flag + cur_cs;
                begin_token_list(p, backed_up); /* prepare to read the control sequence again */
            }
            cur_cmd = spacer_cmd;
            cur_chr = ' ';      /* replace it by a space */
        }
        if (scanner_status > skipping) {
            const char *errhlp[] =
                { "I suspect you have forgotten a `}', causing me",
                "to read past where you wanted me to stop.",
                "I'll try to recover; but if the error is serious,",
                "you'd better type `E' or `X' now and fix your file.",
                NULL
            };
            char errmsg[256];
            const char *startmsg;
            const char *scannermsg;
            /* Tell the user what has run away and try to recover */
            runaway();          /* print a definition, argument, or preamble */
            if (cur_cs == 0) {
                startmsg = "File ended";
            } else {
                cur_cs = 0;
                startmsg = "Forbidden control sequence found";
            }
            /* Print either `\.{definition}' or `\.{use}' or `\.{preamble}' or `\.{text}',
               and insert tokens that should lead to recovery; */
            /* The recovery procedure can't be fully understood without knowing more
               about the \TeX\ routines that should be aborted, but we can sketch the
               ideas here:  For a runaway definition we will insert a right brace; for a
               runaway preamble, we will insert a special \.{\\cr} token and a right
               brace; and for a runaway argument, we will set |long_state| to
               |outer_call| and insert \.{\\par}. */
            p = get_avail();
            switch (scanner_status) {
            case defining:
                scannermsg = "definition";
                token_info(p) = right_brace_token + '}';
                break;
            case matching:
                scannermsg = "use";
                token_info(p) = par_token;
                long_state = outer_call_cmd;
                break;
            case aligning:
                scannermsg = "preamble";
                token_info(p) = right_brace_token + '}';
                q = p;
                p = get_avail();
                token_link(p) = q;
                token_info(p) = cs_token_flag + frozen_cr;
                align_state = -1000000;
                break;
            case absorbing:
                scannermsg = "text";
                token_info(p) = right_brace_token + '}';
                break;
            default:           /* can't happen */
                scannermsg = "unknown";
                break;
            }                   /*there are no other cases */
            begin_token_list(p, inserted);
            snprintf(errmsg, 255, "%s while scanning %s of %s",
                     startmsg, scannermsg, cs_to_string(warning_index));
            tex_error(errmsg, errhlp);
        } else {
            char errmsg[256];
            const char *errhlp_no[] =
                { "The file ended while I was skipping conditional text.",
                "This kind of error happens when you say `\\if...' and forget",
                "the matching `\\fi'. I've inserted a `\\fi'; this might work.",
                NULL
            };
            const char *errhlp_cs[] =
                { "A forbidden control sequence occurred in skipped text.",
                "This kind of error happens when you say `\\if...' and forget",
                "the matching `\\fi'. I've inserted a `\\fi'; this might work.",
                NULL
            };
            const char **errhlp = (const char **) errhlp_no;
            char *ss;
            if (cur_cs != 0) {
                errhlp = errhlp_cs;
                cur_cs = 0;
            }
            ss = cmd_chr_to_string(if_test_cmd, cur_if);
            snprintf(errmsg, 255,
                     "Incomplete %s; all text was ignored after line %d",
                     ss, (int) skip_line);
            free(ss);
            /* Incomplete \\if... */
            cur_tok = cs_token_flag + frozen_fi;
            /* back up one inserted token and call |error| */
            {
                OK_to_interrupt = false;
                back_input();
                token_type = inserted;
                OK_to_interrupt = true;
                tex_error(errmsg, errhlp);
            }
        }
        deletions_allowed = true;
    }
}

@ @c
static boolean get_next_file(void)
{
  SWITCH:
    if (iloc <= ilimit) {       /* current line not yet finished */
        do_buffer_to_unichar(cur_chr, iloc);

      RESWITCH:
        if (detokenized_line()) {
            cur_cmd = (cur_chr == ' ' ? 10 : 12);
        } else {
            do_get_cat_code(cur_cmd);
        }
        /* 
           Change state if necessary, and |goto switch| if the current
           character should be ignored, or |goto reswitch| if the current
           character changes to another;
         */
        /* The following 48-way switch accomplishes the scanning quickly, assuming
           that a decent C compiler has translated the code. Note that the numeric
           values for |mid_line|, |skip_blanks|, and |new_line| are spaced
           apart from each other by |max_char_code+1|, so we can add a character's
           command code to the state to get a single number that characterizes both.
         */
        switch (istate + cur_cmd) {
        case mid_line + ignore_cmd:
        case skip_blanks + ignore_cmd:
        case new_line + ignore_cmd:
        case skip_blanks + spacer_cmd:
        case new_line + spacer_cmd:    /* Cases where character is ignored */
            goto SWITCH;
            break;
        case mid_line + escape_cmd:
        case new_line + escape_cmd:
        case skip_blanks + escape_cmd: /* Scan a control sequence ...; */
            istate = (unsigned char) scan_control_sequence();
            if (cur_cmd >= outer_call_cmd)
                check_outer_validity();
            break;
        case mid_line + active_char_cmd:
        case new_line + active_char_cmd:
        case skip_blanks + active_char_cmd:    /* Process an active-character  */
            cur_cs = active_to_cs(cur_chr, false);
            cur_cmd = eq_type(cur_cs);
            cur_chr = equiv(cur_cs);
            istate = mid_line;
            if (cur_cmd >= outer_call_cmd)
                check_outer_validity();
            break;
        case mid_line + sup_mark_cmd:
        case new_line + sup_mark_cmd:
        case skip_blanks + sup_mark_cmd:       /* If this |sup_mark| starts */
            if (process_sup_mark())
                goto RESWITCH;
            else
                istate = mid_line;
            break;
        case mid_line + invalid_char_cmd:
        case new_line + invalid_char_cmd:
        case skip_blanks + invalid_char_cmd:   /* Decry the invalid character and |goto restart|; */
            invalid_character_error();
            return false;       /* because state may be |token_list| now */
            break;
        case mid_line + spacer_cmd:    /* Enter |skip_blanks| state, emit a space; */
            istate = skip_blanks;
            cur_chr = ' ';
            break;
        case mid_line + car_ret_cmd:   /* Finish line, emit a space; */
            /* When a character of type |spacer| gets through, its character code is
               changed to $\.{"\ "}=040$. This means that the ASCII codes for tab and space,
               and for the space inserted at the end of a line, will
               be treated alike when macro parameters are being matched. We do this
               since such characters are indistinguishable on most computer terminal displays.
             */
            iloc = ilimit + 1;
            cur_cmd = spacer_cmd;
            cur_chr = ' ';
            break;
        case skip_blanks + car_ret_cmd:
        case mid_line + comment_cmd:
        case new_line + comment_cmd:
        case skip_blanks + comment_cmd:        /* Finish line, |goto switch|; */
            iloc = ilimit + 1;
            goto SWITCH;
            break;
        case new_line + car_ret_cmd:   /* Finish line, emit a \.{\\par}; */
            iloc = ilimit + 1;
            cur_cs = par_loc;
            cur_cmd = eq_type(cur_cs);
            cur_chr = equiv(cur_cs);
            if (cur_cmd >= outer_call_cmd)
                check_outer_validity();
            break;
        case skip_blanks + left_brace_cmd:
        case new_line + left_brace_cmd:
            istate = mid_line;  /* fall through */
        case mid_line + left_brace_cmd:
            align_state++;
            break;
        case skip_blanks + right_brace_cmd:
        case new_line + right_brace_cmd:
            istate = mid_line;  /* fall through */
        case mid_line + right_brace_cmd:
            align_state--;
            break;
        case mid_line + math_shift_cmd:
        case mid_line + tab_mark_cmd:
        case mid_line + mac_param_cmd:
        case mid_line + sub_mark_cmd:
        case mid_line + letter_cmd:
        case mid_line + other_char_cmd:
            break;
#if 0
               case skip_blanks + math_shift:
               case skip_blanks + tab_mark:
               case skip_blanks + mac_param:
               case skip_blanks + sub_mark:
               case skip_blanks + letter:
               case skip_blanks + other_char:     
               case new_line    + math_shift:
               case new_line    + tab_mark:
               case new_line    + mac_param:
               case new_line    + sub_mark:
               case new_line    + letter:
               case new_line    + other_char: 
#else
        default:
#endif
            istate = mid_line;
            break;
        }
    } else {
        if (iname != 21)
            istate = new_line;

        /*
           Move to next line of file,
           or |goto restart| if there is no next line,
           or |return| if a \.{\\read} line has finished;
         */
        do {
            next_line_retval r = next_line();
            if (r == next_line_return) {
                return true;
            } else if (r == next_line_restart) {
                return false;
            }
        } while (0);
        check_interrupt();
        goto SWITCH;
    }
    return true;
}

@ @c
#define is_hex(a) ((a>='0'&&a<='9')||(a>='a'&&a<='f'))

#define add_nybble(a)   do {                                            \
    if (a<='9') cur_chr=(cur_chr<<4)+a-'0';                             \
    else        cur_chr=(cur_chr<<4)+a-'a'+10;                          \
  } while (0)

#define hex_to_cur_chr do {                                             \
    if (c<='9')  cur_chr=c-'0';                                         \
    else         cur_chr=c-'a'+10;                                      \
    add_nybble(cc);                                                     \
  } while (0)

#define four_hex_to_cur_chr do {                                        \
    hex_to_cur_chr;                                                     \
    add_nybble(ccc); add_nybble(cccc);                                  \
  } while (0)

#define five_hex_to_cur_chr  do {                                       \
    four_hex_to_cur_chr;                                                \
    add_nybble(ccccc);                                                  \
  } while (0)

#define six_hex_to_cur_chr do {                                         \
    five_hex_to_cur_chr;                                                \
    add_nybble(cccccc);                                                 \
  } while (0)


@ Notice that a code like \.{\^\^8} becomes \.x if not followed by a hex digit.

@c
static boolean process_sup_mark(void)
{
    if (cur_chr == buffer[iloc]) {
        int c, cc;
        if (iloc < ilimit) {
            if ((cur_chr == buffer[iloc + 1]) && (cur_chr == buffer[iloc + 2])
                && (cur_chr == buffer[iloc + 3])
                && (cur_chr == buffer[iloc + 4])
                && ((iloc + 10) <= ilimit)) {
                int ccc, cccc, ccccc, cccccc;   /* constituents of a possible expanded code */
                c = buffer[iloc + 5];
                cc = buffer[iloc + 6];
                ccc = buffer[iloc + 7];
                cccc = buffer[iloc + 8];
                ccccc = buffer[iloc + 9];
                cccccc = buffer[iloc + 10];
                if ((is_hex(c)) && (is_hex(cc)) && (is_hex(ccc))
                    && (is_hex(cccc))
                    && (is_hex(ccccc)) && (is_hex(cccccc))) {
                    iloc = iloc + 11;
                    six_hex_to_cur_chr;
                    return true;
                }
            }
            if ((cur_chr == buffer[iloc + 1]) && (cur_chr == buffer[iloc + 2])
                && (cur_chr == buffer[iloc + 3]) && ((iloc + 8) <= ilimit)) {
                int ccc, cccc, ccccc;   /* constituents of a possible expanded code */
                c = buffer[iloc + 4];
                cc = buffer[iloc + 5];
                ccc = buffer[iloc + 6];
                cccc = buffer[iloc + 7];
                ccccc = buffer[iloc + 8];
                if ((is_hex(c)) && (is_hex(cc)) && (is_hex(ccc))
                    && (is_hex(cccc)) && (is_hex(ccccc))) {
                    iloc = iloc + 9;
                    five_hex_to_cur_chr;
                    return true;
                }
            }
            if ((cur_chr == buffer[iloc + 1]) && (cur_chr == buffer[iloc + 2])
                && ((iloc + 6) <= ilimit)) {
                int ccc, cccc;  /* constituents of a possible expanded code */
                c = buffer[iloc + 3];
                cc = buffer[iloc + 4];
                ccc = buffer[iloc + 5];
                cccc = buffer[iloc + 6];
                if ((is_hex(c)) && (is_hex(cc)) && (is_hex(ccc))
                    && (is_hex(cccc))) {
                    iloc = iloc + 7;
                    four_hex_to_cur_chr;
                    return true;
                }
            }
            c = buffer[iloc + 1];
            if (c < 0200) {     /* yes we have an expanded char */
                iloc = iloc + 2;
                if (is_hex(c) && iloc <= ilimit) {
                    cc = buffer[iloc];
                    if (is_hex(cc)) {
                        incr(iloc);
                        hex_to_cur_chr;
                        return true;
                    }
                }
                cur_chr = (c < 0100 ? c + 0100 : c - 0100);
                return true;
            }
        }
    }
    return false;
}

@ Control sequence names are scanned only when they appear in some line of
   a file; once they have been scanned the first time, their |eqtb| location
   serves as a unique identification, so \TeX\ doesn't need to refer to the
   original name any more except when it prints the equivalent in symbolic form.
   
   The program that scans a control sequence has been written carefully
   in order to avoid the blowups that might otherwise occur if a malicious
   user tried something like `\.{\\catcode\'15=0}'. The algorithm might
   look at |buffer[ilimit+1]|, but it never looks at |buffer[ilimit+2]|.

   If expanded characters like `\.{\^\^A}' or `\.{\^\^df}'
   appear in or just following
   a control sequence name, they are converted to single characters in the
   buffer and the process is repeated, slowly but surely.

@c
static boolean check_expanded_code(int *kk);    /* below */

static int scan_control_sequence(void)
{
    int retval = mid_line;
    if (iloc > ilimit) {
        cur_cs = null_cs;       /* |state| is irrelevant in this case */
    } else {
        register int cat;       /* |cat_code(cur_chr)|, usually */
        while (1) {
            int k = iloc;
            do_buffer_to_unichar(cur_chr, k);
            do_get_cat_code(cat);
            if (cat != letter_cmd || k > ilimit) {
                retval = (cat == spacer_cmd ? skip_blanks : mid_line);
                if (cat == sup_mark_cmd && check_expanded_code(&k))     /* If an expanded...; */
                    continue;
            } else {
                retval = skip_blanks;
                do {
                    do_buffer_to_unichar(cur_chr, k);
                    do_get_cat_code(cat);
                } while (cat == letter_cmd && k <= ilimit);

                if (cat == sup_mark_cmd && check_expanded_code(&k))     /* If an expanded...; */
                    continue;
                if (cat != letter_cmd) {
                    decr(k);
                    if (cur_chr > 0xFFFF)
                        decr(k);
                    if (cur_chr > 0x7FF)
                        decr(k);
                    if (cur_chr > 0x7F)
                        decr(k);
                }               /* now |k| points to first nonletter */
            }
            cur_cs = id_lookup(iloc, k - iloc);
            iloc = k;
            break;
        }
    }
    cur_cmd = eq_type(cur_cs);
    cur_chr = equiv(cur_cs);
    return retval;
}

@ Whenever we reach the following piece of code, we will have
   |cur_chr=buffer[k-1]| and |k<=ilimit+1| and |cat=get_cat_code(cat_code_table,cur_chr)|. If an
   expanded code like \.{\^\^A} or \.{\^\^df} appears in |buffer[(k-1)..(k+1)]|
   or |buffer[(k-1)..(k+2)]|, we
   will store the corresponding code in |buffer[k-1]| and shift the rest of
   the buffer left two or three places.

@c
static boolean check_expanded_code(int *kk)
{
    int l;
    int k = *kk;
    int d = 1;                  /* number of excess characters in an expanded code */
    int c, cc, ccc, cccc, ccccc, cccccc;        /* constituents of a possible expanded code */
    if (buffer[k] == cur_chr && k < ilimit) {
        if ((cur_chr == buffer[k + 1]) && (cur_chr == buffer[k + 2])
            && ((k + 6) <= ilimit)) {
            d = 4;
            if ((cur_chr == buffer[k + 3]) && ((k + 8) <= ilimit))
                d = 5;
            if ((cur_chr == buffer[k + 4]) && ((k + 10) <= ilimit))
                d = 6;
            c = buffer[k + d - 1];
            cc = buffer[k + d];
            ccc = buffer[k + d + 1];
            cccc = buffer[k + d + 2];
            if (d == 6) {
                ccccc = buffer[k + d + 3];
                cccccc = buffer[k + d + 4];
                if (is_hex(c) && is_hex(cc) && is_hex(ccc) && is_hex(cccc)
                    && is_hex(ccccc) && is_hex(cccccc))
                    six_hex_to_cur_chr;
            } else if (d == 5) {
                ccccc = buffer[k + d + 3];
                if (is_hex(c) && is_hex(cc) && is_hex(ccc) && is_hex(cccc)
                    && is_hex(ccccc))
                    five_hex_to_cur_chr;
            } else {
                if (is_hex(c) && is_hex(cc) && is_hex(ccc) && is_hex(cccc))
                    four_hex_to_cur_chr;
            }
        } else {
            c = buffer[k + 1];
            if (c < 0200) {
                d = 1;
                if (is_hex(c) && (k + 2) <= ilimit) {
                    cc = buffer[k + 2];
                    if (is_hex(c) && is_hex(cc)) {
                        d = 2;
                        hex_to_cur_chr;
                    }
                } else if (c < 0100) {
                    cur_chr = c + 0100;
                } else {
                    cur_chr = c - 0100;
                }
            }
        }
        if (d > 2)
            d = 2 * d - 1;
        else
            d++;
        if (cur_chr <= 0x7F) {
            buffer[k - 1] = (packed_ASCII_code) cur_chr;
        } else if (cur_chr <= 0x7FF) {
            buffer[k - 1] = (packed_ASCII_code) (0xC0 + cur_chr / 0x40);
            k++;
            d--;
            buffer[k - 1] = (packed_ASCII_code) (0x80 + cur_chr % 0x40);
        } else if (cur_chr <= 0xFFFF) {
            buffer[k - 1] = (packed_ASCII_code) (0xE0 + cur_chr / 0x1000);
            k++;
            d--;
            buffer[k - 1] =
                (packed_ASCII_code) (0x80 + (cur_chr % 0x1000) / 0x40);
            k++;
            d--;
            buffer[k - 1] =
                (packed_ASCII_code) (0x80 + (cur_chr % 0x1000) % 0x40);
        } else {
            buffer[k - 1] = (packed_ASCII_code) (0xF0 + cur_chr / 0x40000);
            k++;
            d--;
            buffer[k - 1] =
                (packed_ASCII_code) (0x80 + (cur_chr % 0x40000) / 0x1000);
            k++;
            d--;
            buffer[k - 1] =
                (packed_ASCII_code) (0x80 +
                                     ((cur_chr % 0x40000) % 0x1000) / 0x40);
            k++;
            d--;
            buffer[k - 1] =
                (packed_ASCII_code) (0x80 +
                                     ((cur_chr % 0x40000) % 0x1000) % 0x40);
        }
        l = k;
        ilimit = ilimit - d;
        while (l <= ilimit) {
            buffer[l] = buffer[l + d];
            l++;
        }
        *kk = k;
        return true;
    }
    return false;
}

@ todo: this is a function because it is still used from the converted pascal.
   once that is gone, it can be a \#define again

@c
boolean end_line_char_inactive(void)
{
    return ((end_line_char < 0) || (end_line_char > 127));
}

@ All of the easy branches of |get_next| have now been taken care of.
  There is one more branch.

@c
static next_line_retval next_line(void)
{
    boolean inhibit_eol = false;        /* a way to end a pseudo file without trailing space */
    if (iname > 17) {
        /* Read next line of file into |buffer|, or |goto restart| if the file has ended */
        incr(line);
        first = istart;
        if (!force_eof) {
            if (iname <= 20) {
                if (pseudo_input()) {   /* not end of file */
                    firm_up_the_line(); /* this sets |ilimit| */
                    line_catcode_table = DEFAULT_CAT_TABLE;
                    if ((iname == 19) && (pseudo_lines(pseudo_files) == null))
                        inhibit_eol = true;
                } else if ((every_eof != null) && !eof_seen[iindex]) {
                    ilimit = first - 1;
                    eof_seen[iindex] = true;    /* fake one empty line */
                    if (iname != 19)
                        begin_token_list(every_eof, every_eof_text);
                    return next_line_restart;
                } else {
                    force_eof = true;
                }
            } else {
                if (iname == 21) {
                    if (luacstring_input()) {   /* not end of strings  */
                        firm_up_the_line();
                        line_catcode_table = (short) luacstring_cattable();
                        line_partial = (signed char) luacstring_partial();
                        if (luacstring_final_line() || line_partial
                            || line_catcode_table == NO_CAT_TABLE)
                            inhibit_eol = true;
                        if (!line_partial)
                            istate = new_line;
                    } else {
                        force_eof = true;
                    }
                } else {
                    if (lua_input_ln(cur_file, 0, true)) {      /* not end of file */
                        firm_up_the_line();     /* this sets |ilimit| */
                        line_catcode_table = DEFAULT_CAT_TABLE;
                    } else if ((every_eof != null) && (!eof_seen[iindex])) {
                        ilimit = first - 1;
                        eof_seen[iindex] = true;        /* fake one empty line */
                        begin_token_list(every_eof, every_eof_text);
                        return next_line_restart;
                    } else {
                        force_eof = true;
                    }
                }
            }
        }
        if (force_eof) {
            if (tracing_nesting > 0)
                if ((grp_stack[in_open] != cur_boundary)
                    || (if_stack[in_open] != cond_ptr))
                    if (!((iname == 19) || (iname == 21)))
                        file_warning(); /* give warning for some unfinished groups and/or conditionals */
            if ((iname > 21) || (iname == 20)) {
                if (tracefilenames)
                    print_char(')');
                open_parens--;
#if 0
                update_terminal(); /* show user that file has been read */
#endif
            }
            force_eof = false;
            if (iname == 21 ||  /* lua input */
                iname == 19) {  /* \.{\\scantextokens} */
                end_file_reading();
            } else {
                end_file_reading();
                check_outer_validity();
            }
            return next_line_restart;
        }
        if (inhibit_eol || end_line_char_inactive())
            ilimit--;
        else
            buffer[ilimit] = (packed_ASCII_code) end_line_char;
        first = ilimit + 1;
        iloc = istart;          /* ready to read */
    } else {
        if (!terminal_input) {  /* \.{\\read} line has ended */
            cur_cmd = 0;
            cur_chr = 0;
            return next_line_return;    /* OUTER */
        }
        if (input_ptr > 0) {    /* text was inserted during error recovery */
            end_file_reading();
            return next_line_restart;   /* resume previous level */
        }
        if (selector < log_only)
            open_log_file();
        if (interaction > nonstop_mode) {
            if (end_line_char_inactive())
                ilimit++;
            if (ilimit == istart) {     /* previous line was empty */
                tprint_nl("(Please type a command or say `\\end')");
            }
            print_ln();
            first = istart;
            prompt_input("*");  /* input on-line into |buffer| */
            ilimit = last;
            if (end_line_char_inactive())
                ilimit--;
            else
                buffer[ilimit] = (packed_ASCII_code) end_line_char;
            first = ilimit + 1;
            iloc = istart;
        } else {
            fatal_error("*** (job aborted, no legal \\end found)");
            /* nonstop mode, which is intended for overnight batch processing,
               never waits for on-line input */
        }
    }
    return next_line_ok;
}

@ Let's consider now what happens when |get_next| is looking at a token list. 

@c
static boolean get_next_tokenlist(void)
{
    register halfword t;        /* a token */
    t = token_info(iloc);
    iloc = token_link(iloc);    /* move to next */
    if (t >= cs_token_flag) {   /* a control sequence token */
        cur_cs = t - cs_token_flag;
        cur_cmd = eq_type(cur_cs);
        if (cur_cmd >= outer_call_cmd) {
            if (cur_cmd == dont_expand_cmd) {   /* Get the next token, suppressing expansion */
                /* The present point in the program is reached only when the |expand|
                   routine has inserted a special marker into the input. In this special
                   case, |token_info(iloc)| is known to be a control sequence token, and |token_link(iloc)=null|.
                 */
                cur_cs = token_info(iloc) - cs_token_flag;
                iloc = null;
                cur_cmd = eq_type(cur_cs);
                if (cur_cmd > max_command_cmd) {
                    cur_cmd = relax_cmd;
                    cur_chr = no_expand_flag;
                    return true;
                }
            } else {
                check_outer_validity();
            }
        }
        cur_chr = equiv(cur_cs);
    } else {
        cur_cmd = token_cmd(t);
        cur_chr = token_chr(t);
        switch (cur_cmd) {
        case left_brace_cmd:
            align_state++;
            break;
        case right_brace_cmd:
            align_state--;
            break;
        case out_param_cmd:    /* Insert macro parameter and |goto restart|; */
            begin_token_list(param_stack[param_start + cur_chr - 1], parameter);
            return false;
            break;
        }
    }
    return true;
}

@ Now we're ready to take the plunge into |get_next| itself. Parts of
   this routine are executed more often than any other instructions of \TeX.
   @^mastication@>@^inner loop@>

@ sets |cur_cmd|, |cur_chr|, |cur_cs| to next token 

@c
void get_next(void)
{
  RESTART:
    cur_cs = 0;
    if (istate != token_list) {
        /* Input from external file, |goto restart| if no input found */
        if (!get_next_file())
            goto RESTART;
    } else {
        if (iloc == null) {
            end_token_list();
            goto RESTART;       /* list exhausted, resume previous level */
        } else if (!get_next_tokenlist()) {
            goto RESTART;       /* parameter needs to be expanded */
        }
    }
    /* If an alignment entry has just ended, take appropriate action */
    if ((cur_cmd == tab_mark_cmd || cur_cmd == car_ret_cmd) && align_state == 0) {
        insert_vj_template();
        goto RESTART;
    }
}


@ Since |get_next| is used so frequently in \TeX, it is convenient
to define three related procedures that do a little more:

\yskip\hang|get_token| not only sets |cur_cmd| and |cur_chr|, it
also sets |cur_tok|, a packed halfword version of the current token.

\yskip\hang|get_x_token|, meaning ``get an expanded token,'' is like
|get_token|, but if the current token turns out to be a user-defined
control sequence (i.e., a macro call), or a conditional,
or something like \.{\\topmark} or \.{\\expandafter} or \.{\\csname},
it is eliminated from the input by beginning the expansion of the macro
or the evaluation of the conditional.

\yskip\hang|x_token| is like |get_x_token| except that it assumes that
|get_next| has already been called.

\yskip\noindent
In fact, these three procedures account for almost every use of |get_next|.

No new control sequences will be defined except during a call of
|get_token|, or when \.{\\csname} compresses a token list, because
|no_new_control_sequence| is always |true| at other times.

@c
void get_token(void)
{                               /* sets |cur_cmd|, |cur_chr|, |cur_tok| */
    no_new_control_sequence = false;
    get_token_lua();
    no_new_control_sequence = true;
    if (cur_cs == 0)
        cur_tok = token_val(cur_cmd, cur_chr);
    else
        cur_tok = cs_token_flag + cur_cs;
}

@ @c
void get_token_lua(void)
{
    register int callback_id;
    callback_id = callback_defined(token_filter_callback);
    if (callback_id > 0) {
        while (istate == token_list && iloc == null && iindex != v_template)
            end_token_list();
        /* there is some stuff we don't want to see inside the callback */
        if (!(istate == token_list &&
              ((nofilter == true) || (iindex == backed_up && iloc != null)))) {
            do_get_token_lua(callback_id);
            return;
        }
    }
    get_next();
}


@ changes the string |s| to a token list 
@c
halfword string_to_toks(char *ss)
{
    halfword p;                 /* tail of the token list */
    halfword q;                 /* new node being added to the token list via |store_new_token| */
    halfword t;                 /* token being appended */
    char *s = ss, *se = ss + strlen(s);
    p = temp_token_head;
    set_token_link(p, null);
    while (s < se) {
        t = (halfword) str2uni((unsigned char *) s);
        s += utf8_size(t);
        if (t == ' ')
            t = space_token;
        else
            t = other_token + t;
        fast_store_new_token(t);
    }
    return token_link(temp_token_head);
}

@ The token lists for macros and for other things like \.{\\mark} and \.{\\output}
and \.{\\write} are produced by a procedure called |scan_toks|.

Before we get into the details of |scan_toks|, let's consider a much
simpler task, that of converting the current string into a token list.
The |str_toks| function does this; it classifies spaces as type |spacer|
and everything else as type |other_char|.

The token list created by |str_toks| begins at |link(temp_token_head)| and ends
at the value |p| that is returned. (If |p=temp_token_head|, the list is empty.)

|lua_str_toks| is almost identical, but it also escapes the three
symbols that |lua| considers special while scanning a literal string

@c
static halfword lua_str_toks(lstring b)
{                               /* changes the string |str_pool[b..pool_ptr]| to a token list */
    halfword p;                 /* tail of the token list */
    halfword q;                 /* new node being added to the token list via |store_new_token| */
    halfword t;                 /* token being appended */
    unsigned char *k;           /* index into string */
    p = temp_token_head;
    set_token_link(p, null);
    k = (unsigned char *) b.s;
    while (k < (unsigned char *) b.s + b.l) {
        t = pool_to_unichar(k);
        k += utf8_size(t);
        if (t == ' ') {
            t = space_token;
        } else {
            if ((t == '\\') || (t == '"') || (t == '\'') || (t == 10)
                || (t == 13))
                fast_store_new_token(other_token + '\\');
            if (t == 10)
                t = 'n';
            if (t == 13)
                t = 'r';
            t = other_token + t;
        }
        fast_store_new_token(t);
    }
    return p;
}


@ Incidentally, the main reason for wanting |str_toks| is the function |the_toks|, 
which has similar input/output characteristics.

@c
halfword str_toks(lstring s)
{                               /* changes the string |str_pool[b..pool_ptr]| to a token list */
    halfword p;                 /* tail of the token list */
    halfword q;                 /* new node being added to the token list via |store_new_token| */
    halfword t;                 /* token being appended */
    unsigned char *k, *l;       /* index into string */
    p = temp_token_head;
    set_token_link(p, null);
    k = s.s;
    l = k + s.l;
    while (k < l) {
        t = pool_to_unichar(k);
        k += utf8_size(t);
        if (t == ' ')
            t = space_token;
        else
            t = other_token + t;
        fast_store_new_token(t);
    }
    return p;
}

@ Here's part of the |expand| subroutine that we are now ready to complete:
@c
void ins_the_toks(void)
{
    (void) the_toks();
    ins_list(token_link(temp_token_head));
}


@ Here is a routine that print the result of a convert command, using
   the argument |i|. It returns |false | if it does not know to print
   the code |c|. The function exists because lua code and tex code can
   both call it to convert something. 

@c
static boolean print_convert_string(halfword c, int i)
{
    int ff;                     /* for use with |set_ff| */
    boolean ret = true;
    switch (c) {
    case number_code:
        print_int(i);
        break;
    case roman_numeral_code:
        print_roman_int(i);
        break;
    case etex_code:
        tprint(eTeX_version_string);
        break;
    case omega_code:
        tprint(Omega_version_string);
        break;
    case aleph_code:
        tprint(Aleph_version_string);
        break;
    case pdftex_revision_code:
        tprint(pdftex_revision);
        break;
    case luatex_revision_code:
        print(get_luatexrevision());
        break;
    case luatex_date_code:
        print_int(get_luatex_date_info());
        break;
    case pdftex_banner_code:
        tprint(pdftex_banner);
        break;
    case uniform_deviate_code:
        print_int(unif_rand(i));
        break;
    case normal_deviate_code:
        print_int(norm_rand());
        break;
    case format_name_code:
        print(format_name);
        break;
    case job_name_code:
        print(job_name);
        break;
    case font_name_code:
        append_string((unsigned char *) font_name(i),
                      (unsigned) strlen(font_name(i)));
        if (font_size(i) != font_dsize(i)) {
            tprint(" at ");
            print_scaled(font_size(i));
            tprint("pt");
        }
        break;
    case math_style_code:
        print_math_style();
        break;
    case pdf_font_name_code:
    case pdf_font_objnum_code:
        set_ff(i);
        if (c == pdf_font_name_code)
            print_int(obj_info(static_pdf, pdf_font_num(ff)));
        else
            print_int(pdf_font_num(ff));
        break;
    case pdf_font_size_code:
        print_scaled(font_size(i));
        tprint("pt");
        break;
    case pdf_page_ref_code:
        print_int(get_obj(static_pdf, obj_type_page, i, false));
        break;
    case pdf_xform_name_code:
        print_int(obj_info(static_pdf, i));
        break;
    case Aleph_revision_code:
        tprint(Aleph_revision);
        break;
    case Omega_revision_code:
        tprint(Omega_revision);
        break;
    case eTeX_revision_code:
        tprint(eTeX_revision);
        break;
    default:
        ret = false;
        break;
    }
    return ret;
}

@ @c
int scan_lua_state(void)
{
    int sn = 0;
    if (scan_keyword("name")) {
        scan_pdf_ext_toks();
        sn = def_ref;
    }
    /* Parse optional lua state integer, or an instance name to be stored in |sn| */
    /* Get the next non-blank non-relax non-call token */
    do {
        get_x_token();
    } while ((cur_cmd == spacer_cmd) || (cur_cmd == relax_cmd));

    back_input();               /* have to push it back, whatever it is  */
    if (cur_cmd != left_brace_cmd) {
        scan_register_num();
        if (get_lua_name(cur_val))
            sn = (cur_val - 65536);
    }
    return sn;
}


@ The procedure |conv_toks| uses |str_toks| to insert the token list
for |convert| functions into the scanner; `\.{\\outer}' control sequences
are allowed to follow `\.{\\string}' and `\.{\\meaning}'.

The extra temp string |u| is needed because |pdf_scan_ext_toks| incorporates
any pending string in its output. In order to save such a pending string,
we have to create a temporary string that is destroyed immediately after.

@c
void conv_toks(void)
{
    int old_setting;            /* holds |selector| setting */
    halfword p, q;
    int save_scanner_status;    /* |scanner_status| upon entry */
    halfword save_def_ref;      /* |def_ref| upon entry, important if inside `\.{\\message}' */
    halfword save_warning_index;
    boolean bool;               /* temp boolean */
    str_number s;               /* first temp string */
    int sn;                     /* lua chunk name */
    str_number u = 0;           /* third temp string, will become non-nil if a string is already being built */
    int i = 0;                  /* first temp integer */
    int j = 0;                  /* second temp integer */
    int c = cur_chr;            /* desired type of conversion */
    str_number str;
    /* Scan the argument for command |c| */
    switch (c) {
    case number_code:
    case roman_numeral_code:
        scan_int();
        break;
    case string_code:
    case meaning_code:
        save_scanner_status = scanner_status;
        scanner_status = normal;
        get_token();
        scanner_status = save_scanner_status;
        break;
    case etex_code:
    case omega_code:
    case aleph_code:
        break;
    case font_name_code:
        scan_font_ident();
        break;
    case pdftex_revision_code:
    case luatex_revision_code:
    case luatex_date_code:
    case pdftex_banner_code:
        break;
    case pdf_font_name_code:
    case pdf_font_objnum_code:
    case pdf_font_size_code:
        scan_font_ident();
        if (cur_val == null_font)
            pdf_error("font", "invalid font identifier");
        if (c != pdf_font_size_code) {
            pdf_check_vf(cur_val);
            if (!font_used(cur_val))
                pdf_init_font(static_pdf, cur_val);
        }
        break;
    case pdf_page_ref_code:
        scan_int();
        if (cur_val <= 0)
            pdf_error("pageref", "invalid page number");
        break;
    case left_margin_kern_code:
    case right_margin_kern_code:
        scan_int();
        if ((box(cur_val) == null) || (type(box(cur_val)) != hlist_node))
            pdf_error("marginkern", "a non-empty hbox expected");
        break;
    case pdf_xform_name_code:
        scan_int();
        check_obj_type(static_pdf, obj_type_xform, cur_val);
        break;
    case pdf_creation_date_code:
        ins_list(string_to_toks(getcreationdate(static_pdf)));
        return;
        break;
    case format_name_code:
    case job_name_code:
        if (job_name == 0)
            open_log_file();
        break;
    case pdf_colorstack_init_code:
        bool = scan_keyword("page");
        if (scan_keyword("direct"))
            cur_val = direct_always;
        else if (scan_keyword("page"))
            cur_val = direct_page;
        else
            cur_val = set_origin;
        save_scanner_status = scanner_status;
        save_warning_index = warning_index;
        save_def_ref = def_ref;
        u = save_cur_string();
        scan_pdf_ext_toks();
        s = tokens_to_string(def_ref);
        delete_token_ref(def_ref);
        def_ref = save_def_ref;
        warning_index = save_warning_index;
        scanner_status = save_scanner_status;
        cur_val = newcolorstack(s, cur_val, bool);
        flush_str(s);
        cur_val_level = int_val_level;
        if (cur_val < 0) {
            print_err("Too many color stacks");
            help2("The number of color stacks is limited to 32768.",
                  "I'll use the default color stack 0 here.");
            error();
            cur_val = 0;
            restore_cur_string(u);
        }
        break;
    case uniform_deviate_code:
        scan_int();
        break;
    case normal_deviate_code:
        break;
    case lua_escape_string_code:
        {
            lstring str;
            int l = 0;
            save_scanner_status = scanner_status;
            save_def_ref = def_ref;
            save_warning_index = warning_index;
            scan_pdf_ext_toks();
            bool = in_lua_escape;
            in_lua_escape = true;
            str.s = (unsigned char *) tokenlist_to_cstring(def_ref, false, &l);
            str.l = (unsigned) l;
            in_lua_escape = bool;
            delete_token_ref(def_ref);
            def_ref = save_def_ref;
            warning_index = save_warning_index;
            scanner_status = save_scanner_status;
            (void) lua_str_toks(str);
            ins_list(token_link(temp_token_head));
            free(str.s);
            return;
        }
        break;
    case math_style_code:
        break;
    case expanded_code:
        save_scanner_status = scanner_status;
        save_warning_index = warning_index;
        save_def_ref = def_ref;
        u = save_cur_string();
        scan_pdf_ext_toks();
        warning_index = save_warning_index;
        scanner_status = save_scanner_status;
        ins_list(token_link(def_ref));
        def_ref = save_def_ref;
        restore_cur_string(u);
        return;
        break;
    case lua_code:
        u = save_cur_string();
        save_scanner_status = scanner_status;
        save_def_ref = def_ref;
        save_warning_index = warning_index;
        sn = scan_lua_state();
        scan_pdf_ext_toks();
        s = def_ref;
        warning_index = save_warning_index;
        def_ref = save_def_ref;
        scanner_status = save_scanner_status;
        luacstrings = 0;
        luatokencall(s, sn);
        delete_token_ref(s);
        restore_cur_string(u);  /* TODO: check this, was different */
        if (luacstrings > 0)
            lua_string_start();
        return;
        break;
    case pdf_insert_ht_code:
        scan_register_num();
        break;
    case pdf_ximage_bbox_code:
        scan_int();
        check_obj_type(static_pdf, obj_type_ximage, cur_val);
        i = obj_data_ptr(static_pdf, cur_val);
        scan_int();
        j = cur_val;
        if ((j < 1) || (j > 4))
            pdf_error("pdfximagebbox", "invalid parameter");
        break;
        /* Cases of 'Scan the argument for command |c|' */
    case Aleph_revision_code:
    case Omega_revision_code:
    case eTeX_revision_code:
        break;
    default:
        confusion("convert");
        break;
    }

    old_setting = selector;
    selector = new_string;

    /* Print the result of command |c| */
    if (!print_convert_string(c, cur_val)) {
        switch (c) {
        case string_code:
            if (cur_cs != 0)
                sprint_cs(cur_cs);
            else
                print(cur_chr);
            break;
        case meaning_code:
            print_meaning();
            break;
        case left_margin_kern_code:
            p = list_ptr(box(cur_val));
            if ((p != null) && (!is_char_node(p)) &&
                (type(p) == glue_node) && (subtype(p) == left_skip_code + 1))
                p = vlink(p);
            if ((p != null) && (!is_char_node(p)) &&
                (type(p) == margin_kern_node) && (subtype(p) == left_side))
                print_scaled(width(p));
            else
                print_char('0');
            tprint("pt");
            break;
        case right_margin_kern_code:
            q = list_ptr(box(cur_val));
            p = null;
            if (q != null) {
                p = prev_rightmost(q, null);
                if ((p != null) && (!is_char_node(p)) && (type(p) == glue_node)
                    && (subtype(p) == right_skip_code + 1))
                    p = prev_rightmost(q, p);
            }
            if ((p != null) && (!is_char_node(p)) &&
                (type(p) == margin_kern_node) && (subtype(p) == right_side))
                print_scaled(width(p));
            else
                print_char('0');
            tprint("pt");
            break;
        case pdf_colorstack_init_code:
            print_int(cur_val);
            break;
        case pdf_insert_ht_code:
            i = cur_val;
            p = page_ins_head;
            while (i >= subtype(vlink(p)))
                p = vlink(p);
            if (subtype(p) == i)
                print_scaled(height(p));
            else
                print_char('0');
            tprint("pt");
            break;
        case pdf_ximage_bbox_code:
            if (is_pdf_image(i)) {
                switch (j) {
                case 1:
                    print_scaled(epdf_orig_x(i));
                    break;
                case 2:
                    print_scaled(epdf_orig_y(i));
                    break;
                case 3:
                    print_scaled(epdf_orig_x(i) + epdf_xsize(i));
                    break;
                case 4:
                    print_scaled(epdf_orig_y(i) + epdf_ysize(i));
                    break;
                }
            } else {
                print_scaled(0);
            }
            tprint("pt");
            break;
        case pdf_creation_date_code:
        case lua_escape_string_code:
        case lua_code:
        case expanded_code:
            break;
        default:
            confusion("convert");
            break;
        }
    }

    selector = old_setting;
    str = make_string();
    (void) str_toks(str_lstring(str));
    flush_str(str);
    ins_list(token_link(temp_token_head));
}

@ This boolean is keeping track of the lua string escape state
@c
boolean in_lua_escape;

@ probably not needed anymore 
@c
boolean is_convert(halfword c)
{
    return (c == convert_cmd);
}

str_number the_convert_string(halfword c, int i)
{
    int old_setting;            /* saved |selector| setting */
    str_number ret = 0;
    old_setting = selector;
    selector = new_string;
    if (print_convert_string(c, i)) {
        ret = make_string();
    } else if (c == font_identifier_code) {
        print_font_identifier(i);
        ret = make_string();
    }
    selector = old_setting;
    return ret;
}

@ Another way to create a token list is via the \.{\\read} command. The
sixteen files potentially usable for reading appear in the following
global variables. The value of |read_open[n]| will be |closed| if
stream number |n| has not been opened or if it has been fully read;
|just_open| if an \.{\\openin} but not a \.{\\read} has been done;
and |normal| if it is open and ready to read the next line.

@c
FILE *read_file[16];            /* used for \.{\\read} */
int read_open[17];              /* state of |read_file[n]| */

void initialize_read(void)
{
    int k;
    for (k = 0; k <= 16; k++)
        read_open[k] = closed;
}

@ The |read_toks| procedure constructs a token list like that for any
macro definition, and makes |cur_val| point to it. Parameter |r| points
to the control sequence that will receive this token list.

@c
void read_toks(int n, halfword r, halfword j)
{
    halfword p;                 /* tail of the token list */
    halfword q;                 /* new node being added to the token list via |store_new_token| */
    int s;                      /* saved value of |align_state| */
    int m;                      /* stream number */
    scanner_status = defining;
    warning_index = r;
    p = get_avail();
    def_ref = p;
    set_token_ref_count(def_ref, 0);
    p = def_ref;                /* the reference count */
    store_new_token(end_match_token);
    if ((n < 0) || (n > 15))
        m = 16;
    else
        m = n;
    s = align_state;
    align_state = 1000000;      /* disable tab marks, etc. */
    do {
        /* Input and store tokens from the next line of the file */
        begin_file_reading();
        iname = m + 1;
        if (read_open[m] == closed) {
            /* Input for \.{\\read} from the terminal */
            /* Here we input on-line into the |buffer| array, prompting the user explicitly
               if |n>=0|.  The value of |n| is set negative so that additional prompts
               will not be given in the case of multi-line input. */
            if (interaction > nonstop_mode) {
                if (n < 0) {
                    prompt_input("");
                } else {
                    wake_up_terminal();
                    print_ln();
                    sprint_cs(r);
                    prompt_input(" =");
                    n = -1;
                }
            } else {
                fatal_error
                    ("*** (cannot \\read from terminal in nonstop modes)");
            }

        } else if (read_open[m] == just_open) {
            /* Input the first line of |read_file[m]| */
            /* The first line of a file must be treated specially, since |lua_input_ln|
               must be told not to start with |get|. */
            if (lua_input_ln(read_file[m], (m + 1), false)) {
                read_open[m] = normal;
            } else {
                lua_a_close_in(read_file[m], (m + 1));
                read_open[m] = closed;
            }

        } else {
            /* Input the next line of |read_file[m]| */
            /*  An empty line is appended at the end of a |read_file|. */
            if (!lua_input_ln(read_file[m], (m + 1), true)) {
                lua_a_close_in(read_file[m], (m + 1));
                read_open[m] = closed;
                if (align_state != 1000000) {
                    runaway();
                    print_err("File ended within \\read");
                    help1("This \\read has unbalanced braces.");
                    align_state = 1000000;
                    error();
                }
            }

        }
        ilimit = last;
        if (end_line_char_inactive())
            decr(ilimit);
        else
            buffer[ilimit] = (packed_ASCII_code) int_par(end_line_char_code);
        first = ilimit + 1;
        iloc = istart;
        istate = new_line;
        /* Handle \.{\\readline} and |goto done|; */
        if (j == 1) {
            while (iloc <= ilimit) {    /* current line not yet finished */
                cur_chr = buffer[iloc];
                incr(iloc);
                if (cur_chr == ' ')
                    cur_tok = space_token;
                else
                    cur_tok = cur_chr + other_token;
                store_new_token(cur_tok);
            }
        } else {
            while (1) {
                get_token();
                if (cur_tok == 0)
                    break;      /* |cur_cmd=cur_chr=0| will occur at the end of the line */
                if (align_state < 1000000) {    /* unmatched `\.\}' aborts the line */
                    do {
                        get_token();
                    } while (cur_tok != 0);
                    align_state = 1000000;
                    break;
                }
                store_new_token(cur_tok);
            }
        }
        end_file_reading();

    } while (align_state != 1000000);
    cur_val = def_ref;
    scanner_status = normal;
    align_state = s;
}

@ @c
str_number tokens_to_string(halfword p)
{                               /* return a string from tokens list */
    int old_setting;
    if (selector == new_string)
        pdf_error("tokens",
                  "tokens_to_string() called while selector = new_string");
    old_setting = selector;
    selector = new_string;
    show_token_list(token_link(p), null, -1);
    selector = old_setting;
    return make_string();
}

@ @c
#define make_room(a)                                    \
    if ((unsigned)i+a+1>alloci) {                      \
        ret = xrealloc(ret,(alloci+64));                \
        alloci = alloci + 64;                           \
    }


#define append_i_byte(a) ret[i++] = (char)(a)

#define Print_char(a) make_room(1); append_i_byte(a)

#define Print_uchar(s) {                                           \
    make_room(4);                                                  \
    if (s<=0x7F) {                                                 \
      append_i_byte(s);                                            \
    } else if (s<=0x7FF) {                                         \
      append_i_byte(0xC0 + (s / 0x40));                            \
      append_i_byte(0x80 + (s % 0x40));                            \
    } else if (s<=0xFFFF) {                                        \
      append_i_byte(0xE0 + (s / 0x1000));                          \
      append_i_byte(0x80 + ((s % 0x1000) / 0x40));                 \
      append_i_byte(0x80 + ((s % 0x1000) % 0x40));                 \
    } else if (s>=0x110000) {                                      \
      append_i_byte(s-0x11000);                                    \
    } else {                                                       \
      append_i_byte(0xF0 + (s / 0x40000));                         \
      append_i_byte(0x80 + ((s % 0x40000) / 0x1000));              \
      append_i_byte(0x80 + (((s % 0x40000) % 0x1000) / 0x40));     \
      append_i_byte(0x80 + (((s % 0x40000) % 0x1000) % 0x40));     \
    } }


#define Print_esc(b) {                                          \
    const char *v = b;                                          \
    if (e>0 && e<STRING_OFFSET) {                               \
        Print_uchar (e);                                        \
    }                                                           \
    make_room(strlen(v));                                       \
    while (*v) { append_i_byte(*v); v++; }                      \
  }

#define is_cat_letter(a)                                                \
    (get_char_cat_code(pool_to_unichar(str_string((a)))) == 11)

@ the actual token conversion in this function is now functionally 
   equivalent to |show_token_list|, except that it always prints the
   whole token list.
   TODO: check whether this causes problems in the lua library.

@c
char *tokenlist_to_cstring(int pp, int inhibit_par, int *siz)
{
    register int p, c, m;
    int q;
    int infop;
    char *s, *sh;
    int e = 0;
    char *ret;
    int match_chr = '#';
    int n = '0';
    unsigned alloci = 1024;
    int i = 0;
    p = pp;
    if (p == null) {
        if (siz != NULL)
            *siz = 0;
        return NULL;
    }
    ret = xmalloc(alloci);
    p = token_link(p);          /* skip refcount */
    if (p != null) {
        e = int_par(escape_char_code);
    }
    while (p != null) {
        if (p < (int) fix_mem_min || p > (int) fix_mem_end) {
            Print_esc("CLOBBERED.");
            break;
        }
        infop = token_info(p);
        if (infop >= cs_token_flag) {
            if (!(inhibit_par && infop == par_token)) {
                q = infop - cs_token_flag;
                if (q < hash_base) {
                    if (q == null_cs) {
                        Print_esc("csname");
                        Print_esc("endcsname");
                    } else {
                        Print_esc("IMPOSSIBLE.");
                    }
                } else if ((q >= undefined_control_sequence)
                           && ((q <= eqtb_size)
                               || (q > eqtb_size + hash_extra))) {
                    Print_esc("IMPOSSIBLE.");
                } else if ((cs_text(q) < 0) || (cs_text(q) >= str_ptr)) {
                    Print_esc("NONEXISTENT.");
                } else {
                    str_number txt = cs_text(q);
                    sh = makecstring(txt);
                    s = sh;
                    if (is_active_cs(txt)) {
                        s = s + 3;
                        while (*s) {
                            Print_char(*s);
                            s++;
                        }
                    } else {
                        Print_uchar(e);
                        while (*s) {
                            Print_char(*s);
                            s++;
                        }
                        if ((!single_letter(txt)) || is_cat_letter(txt)) {
                            Print_char(' ');
                        }
                    }
                    free(sh);
                }
            }
        } else {
            if (infop < 0) {
                Print_esc("BAD.");
            } else {
                m = token_cmd(infop);
                c = token_chr(infop);
                switch (m) {
                case left_brace_cmd:
                case right_brace_cmd:
                case math_shift_cmd:
                case tab_mark_cmd:
                case sup_mark_cmd:
                case sub_mark_cmd:
                case spacer_cmd:
                case letter_cmd:
                case other_char_cmd:
                    Print_uchar(c);
                    break;
                case mac_param_cmd:
                    if (!in_lua_escape)
                        Print_uchar(c);
                    Print_uchar(c);
                    break;
                case out_param_cmd:
                    Print_uchar(match_chr);
                    if (c <= 9) {
                        Print_char(c + '0');
                    } else {
                        Print_char('!');
                        goto EXIT;
                    }
                    break;
                case match_cmd:
                    match_chr = c;
                    Print_uchar(c);
                    n++;
                    Print_char(n);
                    if (n > '9')
                        goto EXIT;
                    break;
                case end_match_cmd:
                    if (c == 0) {
                        Print_char('-');
                        Print_char('>');
                    }
                    break;
                default:
                    Print_esc("BAD.");
                    break;
                }
            }
        }
        p = token_link(p);
    }
  EXIT:
    ret[i] = '\0';
    if (siz != NULL)
        *siz = i;
    return ret;
}

@ @c
lstring *tokenlist_to_lstring(int pp, int inhibit_par)
{
    int siz;
    lstring *ret = xmalloc(sizeof(lstring));
    ret->s = (unsigned char *) tokenlist_to_cstring(pp, inhibit_par, &siz);
    ret->l = (size_t) siz;
    return ret;
}

@ @c
void free_lstring(lstring * ls)
{
    if (ls == NULL)
        return;
    if (ls->s != NULL)
        free(ls->s);
    free(ls);
}