summaryrefslogtreecommitdiff
path: root/strgen/strgen.c
blob: 1ebb114449743ba9201225ca598b147050f548d1 (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
/* $Id$ */

#define STRGEN

#include "../stdafx.h"
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <stdarg.h>

#if (!defined(WIN32) && !defined(WIN64)) || defined(__CYGWIN__)
#include <unistd.h>
#endif

#ifdef __MORPHOS__
#ifdef stderr
#undef stderr
#endif
#define stderr stdout
#endif // __MORPHOS__

/* Compiles a list of strings into a compiled string list */

typedef void (*ParseCmdProc)(char *buf, int value);

typedef struct {
	uint32 ident;
	uint32 version;			// 32-bits of auto generated version info which is basically a hash of strings.h
	char name[32];			// the international name of this language
	char own_name[32];	// the localized name of this language
	char isocode[16];	// the ISO code for the language (not country code)
	uint16 offsets[32];	// the offsets
	byte plural_form;		// plural form index
	byte pad[3];				// pad header to be a multiple of 4
} LanguagePackHeader;

typedef struct CmdStruct {
	const char *cmd;
	ParseCmdProc proc;
	long value;
	int8 consumes;
	byte flags;
} CmdStruct;

enum {
	C_DONTCOUNT = 1,
	C_CASE = 2,
};


typedef struct Case {
	int caseidx;
	char *string;
	struct Case *next;
} Case;

static bool _masterlang;
static bool _translated;
static const char* _file = "(unknown file)";
static int _cur_line;
static int _errors, _warnings;

typedef struct LangString {
	char *name;							// Name of the string
	char *english;					// English text
	char *translated;				// Translated text
	uint16 hash_next;				// next hash entry
	uint16 index;
	int line;               // line of string in source-file
	Case *english_case;			// cases for english
	Case *translated_case;	// cases for foreign
} LangString;

static LangString *_strings[65536];


#define HASH_SIZE 32767
static uint16 _hash_head[HASH_SIZE];

static byte _put_buf[4096];
static int _put_pos;
static int _next_string_id;

static uint32 _hash;
static char _lang_name[32], _lang_ownname[32], _lang_isocode[16];
static byte _lang_pluralform;
#define MAX_NUM_GENDER 8
static char _genders[MAX_NUM_GENDER][8];
static int _numgenders;

// contains the name of all cases.
#define MAX_NUM_CASES 50
static char _cases[MAX_NUM_CASES][16];
static int _numcases;

// for each plural value, this is the number of plural forms.
static const byte _plural_form_counts[] = { 2,1,2,3,3,3,3,3,4 };

static const char *_cur_ident;

typedef struct CmdPair {
	const CmdStruct *a;
	char *v;
} CmdPair;

typedef struct ParsedCommandStruct {
	int np;
	CmdPair pairs[32];
	const CmdStruct *cmd[32]; // ordered by param #
} ParsedCommandStruct;

// Used when generating some advanced commands.
static ParsedCommandStruct _cur_pcs;
static int _cur_argidx;

static uint HashStr(const char *s)
{
	uint hash = 0;
	for(; *s; s++)
		hash = ((hash << 3) | (hash >> 29)) ^ *s;
	return hash % HASH_SIZE;
}

static void HashAdd(const char *s, LangString *ls)
{
	uint hash = HashStr(s);
	ls->hash_next = _hash_head[hash];
	_hash_head[hash] = ls->index + 1;
}

static LangString *HashFind(const char *s)
{
	int idx = _hash_head[HashStr(s)];
	while (--idx >= 0) {
		LangString *ls = _strings[idx];
		if (!strcmp(ls->name, s)) return ls;
		idx = ls->hash_next;
	}
	return NULL;
}


static void CDECL Warning(const char *s, ...)
{
	char buf[1024];
	va_list va;
	va_start(va, s);
	vsprintf(buf, s, va);
	va_end(va);
	fprintf(stderr, "%s:%d: Warning: %s\n", _file, _cur_line, buf);
	_warnings++;
}


static void CDECL Error(const char *s, ...)
{
	char buf[1024];
	va_list va;
	va_start(va, s);
	vsprintf(buf, s, va);
	va_end(va);
	fprintf(stderr, "%s:%d: Error: %s\n", _file, _cur_line, buf);
	_errors++;
}


static void NORETURN CDECL Fatal(const char *s, ...)
{
	char buf[1024];
	va_list va;
	va_start(va, s);
	vsprintf(buf, s, va);
	va_end(va);
	fprintf(stderr, "%s:%d: FATAL: %s\n", _file, _cur_line, buf);
	exit(1);
}


static void ttd_strlcpy(char *dst, const char *src, size_t len)
{
	assert(len > 0);
	while (--len && *src)
		*dst++=*src++;
	*dst = 0;
}


static void PutByte(byte c)
{
	if (_put_pos == lengthof(_put_buf))
		Fatal("Put buffer too small");
	_put_buf[_put_pos++] = c;
}


static void EmitSingleByte(char *buf, int value)
{
	if (*buf != '\0')
		Warning("Ignoring trailing letters in command");
	PutByte((byte)value);
}


static void EmitEscapedByte(char *buf, int value)
{
	if (*buf != '\0')
		Warning("Ignoring trailing letters in command");
	PutByte((byte)0x85);
	PutByte((byte)value);
}

static void EmitSetX(char *buf, int value)
{
	char *err;
	int x = strtol(buf, &err, 0);
	if (*err != 0)
		Fatal("SetX param invalid");
	PutByte(1);
	PutByte((byte)x);
}


static void EmitSetXY(char *buf, int value)
{
	char *err;
	int x,y;

	x = strtol(buf, &err, 0);
	if (*err != ' ') Fatal("SetXY param invalid");
	y = strtol(err+1, &err, 0);
	if (*err != 0) Fatal("SetXY param invalid");

	PutByte(2);
	PutByte((byte)x);
	PutByte((byte)y);
}

// The plural specifier looks like
// {NUM} {PLURAL -1 passenger passengers} then it picks either passenger/passengers depending on the count in NUM

// This is encoded like
//  CommandByte <ARG#> <NUM> {Length of each string} {each string}

bool ParseRelNum(char **buf, int *value)
{
	char *s = *buf, *end;
	bool rel = false;
	int v;

	while (*s == ' ' || *s == '\t') s++;
	if (*s == '+') { rel = true; s++; }
	v = strtol(s, &end, 0);
	if (end == s) return false;
	if (rel || (v < 0))
		*value += v;
	else
		*value = v;
	*buf = end;
	return true;
}

// Parse out the next word, or NULL
char *ParseWord(char **buf)
{
	char *s = *buf, *r;
	while (*s == ' ' || *s == '\t') s++;
	if (*s == 0)
		return NULL;

	if (*s == '"') {
		r = ++s;
		// parse until next " or NUL
		for(;;) {
			if (*s == 0)
				break;
			if (*s == '"') {
				*s++ = 0;
				break;
			}
			s++;
		}
	} else {
		// proceed until whitespace or NUL
		r = s;
		for(;;) {
			if (*s == 0)
				break;
			if (*s == ' ' || *s == '\t') {
				*s++ = 0;
				break;
			}
			s++;
		}
	}
	*buf = s;
	return r;
}

// Forward declaration
static int TranslateArgumentIdx(int arg);

static void EmitWordList(char **words, int nw)
{
	int i,j;

	PutByte(nw);
	for(i=0; i<nw; i++)
		PutByte(strlen(words[i]));
	for(i=0; i<nw; i++) {
		for(j=0; words[i][j]; j++)
			PutByte(words[i][j]);
	}
}

static void EmitPlural(char *buf, int value)
{
	int argidx = _cur_argidx;
	char *words[5];
	int nw = 0;

	// Parse out the number, if one exists. Otherwise default to prev arg.
	if (!ParseRelNum(&buf, &argidx))
		argidx--;

	// Parse each string
	for (nw = 0; nw < 5; nw++) {
		words[nw] = ParseWord(&buf);
		if (!words[nw])
			break;
	}

	if (nw == 0)
		Fatal("%s: No plural words", _cur_ident);

	if (_plural_form_counts[_lang_pluralform] != nw) {
		if (_translated) {
			Fatal("%s: Invalid number of plural forms. Expecting %d, found %d.", _cur_ident,
				_plural_form_counts[_lang_pluralform], nw);
		} else {
			Warning("'%s' is untranslated. Tweaking english string to allow compilation for plural forms", _cur_ident);
			if (nw > _plural_form_counts[_lang_pluralform]) {
				nw = _plural_form_counts[_lang_pluralform];
			} else {
				for(; nw < _plural_form_counts[_lang_pluralform]; nw++) {
					words[nw] = words[nw - 1];
				}
			}
		}
	}

	PutByte(0x8D);
	PutByte(TranslateArgumentIdx(argidx));
	EmitWordList(words, nw);
}


static void EmitGender(char *buf, int value)
{
	int argidx = _cur_argidx;
	char *words[8];
	int nw;

	if (buf[0] == '=') {
		buf++;

		// This is a {G=DER} command
		for(nw=0; ;nw++) {
			if (nw >= 8)
				Fatal("G argument '%s' invalid", buf);
			if (!strcmp(buf, _genders[nw]))
				break;
		}
		// now nw contains the gender index
		PutByte(0x87);
		PutByte(nw);

	} else {
		// This is a {G 0 foo bar two} command.
		// If no relative number exists, default to +0
		if (!ParseRelNum(&buf, &argidx)) {}

		for(nw=0; nw<8; nw++) {
			words[nw] = ParseWord(&buf);
			if (!words[nw])
				break;
		}
		if (nw != _numgenders) Fatal("Bad # of arguments for gender command");
		PutByte(0x85);
		PutByte(13);
		PutByte(TranslateArgumentIdx(argidx));
		EmitWordList(words, nw);
	}
}


static const CmdStruct _cmd_structs[] = {
	// Update position
	{"SETX",  EmitSetX,  1, 0, 0},
	{"SETXY", EmitSetXY, 2, 0, 0},

	// Font size
	{"TINYFONT", EmitSingleByte, 8, 0, 0},
	{"BIGFONT",  EmitSingleByte, 9, 0, 0},

	// New line
	{"", EmitSingleByte, 10, 0, C_DONTCOUNT},

	{"{", EmitSingleByte, '{', 0, C_DONTCOUNT},

	// Colors
	{"BLUE",    EmitSingleByte, 15, 0, 0},
	{"SILVER",  EmitSingleByte, 16, 0, 0},
	{"GOLD",    EmitSingleByte, 17, 0, 0},
	{"RED",     EmitSingleByte, 18, 0, 0},
	{"PURPLE",  EmitSingleByte, 19, 0, 0},
	{"LTBROWN", EmitSingleByte, 20, 0, 0},
	{"ORANGE",  EmitSingleByte, 21, 0, 0},
	{"GREEN",   EmitSingleByte, 22, 0, 0},
	{"YELLOW",  EmitSingleByte, 23, 0, 0},
	{"DKGREEN", EmitSingleByte, 24, 0, 0},
	{"CREAM",   EmitSingleByte, 25, 0, 0},
	{"BROWN",   EmitSingleByte, 26, 0, 0},
	{"WHITE",   EmitSingleByte, 27, 0, 0},
	{"LTBLUE",  EmitSingleByte, 28, 0, 0},
	{"GRAY",    EmitSingleByte, 29, 0, 0},
	{"DKBLUE",  EmitSingleByte, 30, 0, 0},
	{"BLACK",   EmitSingleByte, 31, 0, 0},

	// 0x85
	{"CURRCOMPACT",   EmitEscapedByte, 0, 1, 0}, // compact currency (32 bits)
	{"REV",           EmitEscapedByte, 2, 0, 0}, // openttd revision string
	{"SHORTCARGO",    EmitEscapedByte, 3, 2, 0}, // short cargo description, only ### tons, or ### litres
	{"CURRCOMPACT64", EmitEscapedByte, 4, 2, 0}, // compact currency 64 bits

	{"COMPANY", EmitEscapedByte, 5, 1, 0},				// company string. This is actually a {STRING1}
																						// The first string includes the second string.

	{"PLAYERNAME", EmitEscapedByte, 5, 1, 0},		// playername string. This is actually a {STRING1}
																						// The first string includes the second string.

	{"VEHICLE", EmitEscapedByte, 5, 1, 0},		// playername string. This is actually a {STRING1}
																						// The first string includes the second string.


	{"STRING1", EmitEscapedByte, 5, 1, C_CASE},				// included string that consumes ONE argument
	{"STRING2", EmitEscapedByte, 6, 2, C_CASE},				// included string that consumes TWO arguments
	{"STRING3", EmitEscapedByte, 7, 3, C_CASE},				// included string that consumes THREE arguments
	{"STRING4", EmitEscapedByte, 8, 4, C_CASE},				// included string that consumes FOUR arguments
	{"STRING5", EmitEscapedByte, 9, 5, C_CASE},				// included string that consumes FIVE arguments

	{"STATIONFEATURES", EmitEscapedByte, 10, 1, 0}, // station features string, icons of the features
	{"INDUSTRY",        EmitEscapedByte, 11, 1, 0}, // industry, takes an industry #
	{"VOLUME",          EmitEscapedByte, 12, 1, 0},
	{"DATE_TINY",       EmitEscapedByte, 14, 1, 0},
	{"CARGO",           EmitEscapedByte, 15, 2, 0},

	{"P", EmitPlural, 0, 0, C_DONTCOUNT},					// plural specifier
	{"G", EmitGender, 0, 0, C_DONTCOUNT},					// gender specifier

	{"DATE_LONG",  EmitSingleByte, 0x82, 1, 0},
	{"DATE_SHORT", EmitSingleByte, 0x83, 1, 0},

	{"VELOCITY", EmitSingleByte, 0x84, 1, 0},

	{"SKIP", EmitSingleByte, 0x86, 1, 0},

	{"STRING", EmitSingleByte, 0x88, 1, C_CASE},

	// Numbers
	{"COMMA", EmitSingleByte, 0x8B, 1, 0}, // Number with comma
	{"NUM",   EmitSingleByte, 0x8E, 1, 0}, // Signed number

	{"CURRENCY", EmitSingleByte, 0x8F, 1, 0},

	{"WAYPOINT",   EmitSingleByte, 0x99, 1, 0}, // waypoint name
	{"STATION",    EmitSingleByte, 0x9A, 1, 0},
	{"TOWN",       EmitSingleByte, 0x9B, 1, 0},
	{"CURRENCY64", EmitSingleByte, 0x9C, 2, 0},
	// 0x9D is used for the pseudo command SETCASE
	// 0x9E is used for case switching

	// 0x9E=158 is the LAST special character we may use.

	{"UPARROW", EmitSingleByte, 0x80, 0, 0},

	{"NBSP",       EmitSingleByte, 0xA0, 0, C_DONTCOUNT},
	{"POUNDSIGN",  EmitSingleByte, 0xA3, 0, 0},
	{"YENSIGN",    EmitSingleByte, 0xA5, 0, 0},
	{"COPYRIGHT",  EmitSingleByte, 0xA9, 0, 0},
	{"DOWNARROW",  EmitSingleByte, 0xAA, 0, 0},
	{"CHECKMARK",  EmitSingleByte, 0xAC, 0, 0},
	{"CROSS",      EmitSingleByte, 0xAD, 0, 0},
	{"RIGHTARROW", EmitSingleByte, 0xAF, 0, 0},

	{"TRAIN", EmitSingleByte, 0x94, 0, 0},
	{"LORRY", EmitSingleByte, 0x95, 0, 0},
	{"BUS",   EmitSingleByte, 0x96, 0, 0},
	{"PLANE", EmitSingleByte, 0x97, 0, 0},
	{"SHIP",  EmitSingleByte, 0x98, 0, 0},

	{"SMALLUPARROW",   EmitSingleByte, 0x90, 0, 0},
	{"SMALLDOWNARROW", EmitSingleByte, 0x91, 0, 0}
};


static const CmdStruct *FindCmd(const char *s, int len)
{
	int i;
	const CmdStruct *cs = _cmd_structs;
	for(i=0; i != lengthof(_cmd_structs); i++, cs++) {
		if (!strncmp(cs->cmd, s, len) && cs->cmd[len] == '\0')
			return cs;
	}
	return NULL;
}

static int ResolveCaseName(const char *str, int len)
{
	int i;
	for(i=0; i<MAX_NUM_CASES; i++)
		if (!memcmp(_cases[i], str, len) && _cases[i][len] == 0)
			return i + 1;
	Fatal("Invalid case-name '%s'", str);
}


// returns NULL on eof
// else returns command struct
static const CmdStruct *ParseCommandString(const char **str, char *param, int *argno, int *casei)
{
	const char *s = *str, *start;
	const CmdStruct *cmd;
	byte c;

	*argno = -1;
	*casei = -1;

	// Scan to the next command, exit if there's no next command.
	for(; *s != '{'; s++) {
		if (*s == '\0')
			return NULL;
	}
	s++; // Skip past the {

	if (*s >= '0' && *s <= '9') {
		char *end;
		*argno = strtoul(s, &end, 0);
		if (*end != ':') {
				Fatal("missing arg #");
			}
		s = end + 1;
	}

	// parse command name
	start = s;
	do {
		c = *s++;
	} while (c != '}' && c != ' ' && c != '=' && c != '.' && c != 0);

	cmd = FindCmd(start, s - start - 1);
	if (cmd == NULL) {
		Error("Undefined command '%.*s'", s - start - 1, start);
		return NULL;
	}

	if (c == '.') {
		const char *casep = s;

		if (!(cmd->flags & C_CASE))
			Fatal("Command '%s' can't have a case", cmd->cmd);

		do c = *s++; while (c != '}' && c != ' ' && c != '\0');
		*casei = ResolveCaseName(casep, s-casep-1);
	}

	if (c == '\0') {
		Error("Missing } from command '%s'", start);
		return NULL;
	}


	if (c != '}') {
		if (c == '=') s--;
		// copy params
		start = s;
		for(;;) {
			c = *s++;
			if (c == '}') break;
			if (c == '\0') {
				Error("Missing } from command '%s'", start);
				return NULL;
			}
			if ( s - start == 250)
				Fatal("param command too long");
			*param++ = c;
		}
	}
	*param = 0;

	*str = s;

	return cmd;
}


static void HandlePragma(char *str)
{
	if (!memcmp(str, "id ", 3)) {
		_next_string_id = strtoul(str + 3, NULL, 0);
	} else if (!memcmp(str, "name ", 5)) {
		ttd_strlcpy(_lang_name, str + 5, sizeof(_lang_name));
	} else if (!memcmp(str, "ownname ", 8)) {
		ttd_strlcpy(_lang_ownname, str + 8, sizeof(_lang_ownname));
	} else if (!memcmp(str, "isocode ", 8)) {
		ttd_strlcpy(_lang_isocode, str + 8, sizeof(_lang_isocode));
	} else if (!memcmp(str, "plural ", 7)) {
		_lang_pluralform = atoi(str + 7);
		if (_lang_pluralform >= lengthof(_plural_form_counts))
			Fatal("Invalid pluralform %d", _lang_pluralform);
	} else if (!memcmp(str, "gender ", 7)) {
		char *buf = str + 7, *s;
		for(;;) {
			s = ParseWord(&buf);
			if (!s) break;
			if (_numgenders >= MAX_NUM_GENDER) Fatal("Too many genders, max %d", MAX_NUM_GENDER);
			ttd_strlcpy(_genders[_numgenders], s, sizeof(_genders[_numgenders]));
			_numgenders++;
		}
	} else if (!memcmp(str, "case ", 5)) {
		char *buf = str + 5, *s;
		for(;;) {
			s = ParseWord(&buf);
			if (!s) break;
			if (_numcases >= MAX_NUM_CASES) Fatal("Too many cases, max %d", MAX_NUM_CASES);
			ttd_strlcpy(_cases[_numcases], s, sizeof(_cases[_numcases]));
			_numcases++;
		}
	} else {
		Fatal("unknown pragma '%s'", str);
	}
}

static void ExtractCommandString(ParsedCommandStruct *p, char *s, bool warnings)
{
	const CmdStruct *ar;
	char param[100];
	int argno;
	int argidx = 0;
	int casei;

	memset(p, 0, sizeof(*p));

	for(;;) {
		// read until next command from a.
		ar = ParseCommandString((const char **)&s, param, &argno, &casei);
		if (ar == NULL)
			break;

		// Sanity checking
		if (argno != -1 && !ar->consumes) Fatal("Non consumer param can't have a paramindex");

		if (ar->consumes) {
			if (argno != -1)
				argidx = argno;
			if (argidx < 0 || argidx >= lengthof(p->cmd)) Fatal("invalid param idx %d", argidx);
			if (p->cmd[argidx] != NULL && p->cmd[argidx] != ar) Fatal("duplicate param idx %d", argidx);

			p->cmd[argidx++] = ar;
		} else if (!(ar->flags & C_DONTCOUNT)) { // Ignore some of them
			if (p->np >= lengthof(p->pairs)) Fatal("too many commands in string, max %d", lengthof(p->pairs));
			p->pairs[p->np].a = ar;
			p->pairs[p->np].v = param[0]?strdup(param):"";
			p->np++;
		}
	}
}


static const CmdStruct *TranslateCmdForCompare(const CmdStruct *a)
{
	if (!a) return NULL;

	if (!strcmp(a->cmd, "STRING1") ||
			!strcmp(a->cmd, "STRING2") ||
			!strcmp(a->cmd, "STRING3") ||
			!strcmp(a->cmd, "STRING4") ||
			!strcmp(a->cmd, "STRING5"))
		return FindCmd("STRING", 6);

	if (!strcmp(a->cmd, "SKIP"))
		return NULL;

	return a;
}


static bool CheckCommandsMatch(char *a, char *b, const char *name)
{
	ParsedCommandStruct templ;
	ParsedCommandStruct lang;
	int i,j;
	bool result = true;

	ExtractCommandString(&templ, b, true);
	ExtractCommandString(&lang, a, true);

	// For each string in templ, see if we find it in lang
	if (templ.np != lang.np) {
		Warning("%s: template string and language string have a different # of commands", name);
		result = false;
	}

	for(i = 0; i < templ.np; i++) {
		// see if we find it in lang, and zero it out
		bool found = false;
		for(j = 0; j < lang.np; j++) {
			if (templ.pairs[i].a == lang.pairs[j].a &&
					!strcmp(templ.pairs[i].v, lang.pairs[j].v)) {
				// it was found in both. zero it out from lang so we don't find it again
				lang.pairs[j].a = NULL;
				found = true;
				break;
			}
		}

		if (!found) {
			Warning("%s: command '%s' exists in template file but not in language file", name, templ.pairs[i].a->cmd);
			result = false;
		}
	}

	// if we reach here, all non consumer commands match up.
	// Check if the non consumer commands match up also.
	for(i = 0; i < lengthof(templ.cmd); i++) {
		if (TranslateCmdForCompare(templ.cmd[i]) != TranslateCmdForCompare(lang.cmd[i])) {
			Warning("%s: Param idx #%d '%s' doesn't match with template command '%s'", name, i,
				!lang.cmd[i] ? "<empty>" : lang.cmd[i]->cmd,
				!templ.cmd[i] ? "<empty>" : templ.cmd[i]->cmd);
			result = false;
		}
	}

	return result;
}

static void HandleString(char *str, bool master)
{
	char *s,*t;
	LangString *ent;
	char *casep;

	if (*str == '#') {
		if (str[1] == '#' && str[2] != '#')
			HandlePragma(str + 2);
		return;
	}

	// Ignore comments & blank lines
	if (*str == ';' || *str == ' ' || *str == '\0')
		return;

	s = strchr(str, ':');
	if (s == NULL) {
		Error("Line has no ':' delimiter");
		return;
	}

	// Trim spaces.
	// After this str points to the command name, and s points to the command contents
	for(t = s; t > str && (t[-1]==' ' || t[-1]=='\t'); t--);
	*t = 0;
	s++;

	// Check if the string has a case..
	// The syntax for cases is IDENTNAME.case
	casep = strchr(str, '.');
	if (casep) *casep++ = 0;

	// Check if this string already exists..
	ent = HashFind(str);

	if (master) {
		if (ent != NULL && !casep) {
			Error("String name '%s' is used multiple times", str);
			return;
		}

		if (ent == NULL && casep) {
			Error("Base string name '%s' doesn't exist yet. Define it before defining a case.", str);
			return;
		}

		if (ent == NULL) {
			if (_strings[_next_string_id]) {
				Error("String ID 0x%X for '%s' already in use by '%s'", ent, str, _strings[_next_string_id]->name);
				return;
			}

			// Allocate a new LangString
			ent = calloc(sizeof(LangString), 1);
			_strings[_next_string_id] = ent;
			ent->index = _next_string_id++;
			ent->name = strdup(str);
			ent->line = _cur_line;

			HashAdd(str, ent);
		}

		if (casep) {
			Case *c = malloc(sizeof(Case));
			c->caseidx = ResolveCaseName(casep, strlen(casep));
			c->string = strdup(s);
			c->next = ent->english_case;
			ent->english_case = c;
		} else {
			ent->english = strdup(s);
		}

	} else {
		if (ent == NULL) {
			Warning("String name '%s' does not exist in master file", str);
			return;
		}

		if (ent->translated && !casep) {
			Error("String name '%s' is used multiple times", str);
			return;
		}

		if (s[0] == ':' && s[1] == '\0' && casep == NULL) {
			// Special syntax :: means we should just inherit the master string
			ent->translated = strdup(ent->english);
		} else {
			// make sure that the commands match
			if (!CheckCommandsMatch(s, ent->english, str))
				return;

			if (casep) {
				Case *c = malloc(sizeof(Case));
				c->caseidx = ResolveCaseName(casep, strlen(casep));
				c->string = strdup(s);
				c->next = ent->translated_case;
				ent->translated_case = c;
			} else {
				ent->translated = strdup(s);
			}
		}
	}
}


static void rstrip(char *buf)
{
	int i = strlen(buf);
	while (i>0 && (buf[i-1]=='\r' || buf[i-1]=='\n' || buf[i-1] == ' ')) i--;
	buf[i] = 0;
}


static void ParseFile(const char *file, bool english)
{
	FILE *in;
	char buf[2048];

	_file = file;

	// For each new file we parse, reset the genders.
	_numgenders = 0;
	// TODO:!! We can't reset the cases. In case the translated strings
	// derive some strings from english....


	in = fopen(file, "r");
	if (in == NULL) Fatal("Cannot open file");
	_cur_line = 1;
	while (fgets(buf, sizeof(buf),in) != NULL) {
		rstrip(buf);
		HandleString(buf, english);
		_cur_line++;
	}
	fclose(in);
}


static uint32 MyHashStr(uint32 hash, const char *s)
{
	for(; *s; s++) {
		hash = ((hash << 3) | (hash >> 29)) ^ *s;
		if (hash & 1) hash = (hash>>1) ^ 0xDEADBEEF; else hash >>= 1;
	}
	return hash;
}


// make a hash of the file to get a unique "version number"
static void MakeHashOfStrings(void)
{
	uint32 hash = 0;
	LangString *ls;
	char *s;
	const CmdStruct *cs;
	char buf[256];
	int i;
	int argno;
	int casei;

	for(i = 0; i != 65536; i++) {
		if ((ls=_strings[i]) != NULL) {
			s = ls->name;
			hash ^= i * 0x717239;
			if (hash & 1) hash = (hash>>1) ^ 0xDEADBEEF; else hash >>= 1;
			hash = MyHashStr(hash, s + 1);

			s = ls->english;
			while ((cs = ParseCommandString((const char **)&s, buf, &argno, &casei)) != NULL) {
				if (cs->flags & C_DONTCOUNT)
					continue;

				hash ^= (cs - _cmd_structs) * 0x1234567;
				if (hash & 1) hash = (hash>>1) ^ 0xF00BAA4; else hash >>= 1;
			}
		}
	}
	_hash = hash;
}


static int CountInUse(int grp)
{
	int i;

	for(i = 0x800; --i >= 0;) {
		if (_strings[(grp<<11)+i] != NULL)
			break;
	}
	return i + 1;
}




bool CompareFiles(const char *n1, const char *n2)
{
	FILE *f1, *f2;
	char b1[4096];
	char b2[4096];
	size_t l1, l2;

	f2 = fopen(n2, "rb");
	if (f2 == NULL) return false;

	f1 = fopen(n1, "rb");
	if (f1 == NULL) Fatal("can't open %s", n1);

	do {
		l1 = fread(b1, 1, sizeof(b1), f1);
		l2 = fread(b2, 1, sizeof(b2), f2);

		if (l1 != l2 || memcmp(b1, b2, l1)) {
			fclose(f2);
			fclose(f1);
			return false;
		}
	} while (l1);

	fclose(f2);
	fclose(f1);
	return true;
}


static void WriteStringsH(const char *filename)
{
	FILE *out;
	int i;
	int next = -1;
	int lastgrp;

	out = fopen("tmp.xxx", "w");
	if (out == NULL) { Fatal("can't open tmp.xxx"); }

	fprintf(out, "enum {");

	lastgrp = 0;

	for(i = 0; i != 65536; i++) {
		if (_strings[i]) {
			if (lastgrp != (i >> 11)) {
				lastgrp = (i >> 11);
				fprintf(out, "};\n\nenum {");
			}

			fprintf(out, next == i ? "%s,\n" : "\n%s = 0x%X,\n", _strings[i]->name, i);
			next = i + 1;
		}
	}

	fprintf(out, "};\n");

	fprintf(out,
		"\nenum {\n"
		"\tLANGUAGE_PACK_IDENT = 0x474E414C, // Big Endian value for 'LANG' (LE is 0x 4C 41 4E 47)\n"
		"\tLANGUAGE_PACK_VERSION = 0x%X,\n"
		"};\n", (uint)_hash);


	fclose(out);

	if (CompareFiles("tmp.xxx", filename)) {
		// files are equal. tmp.xxx is not needed
		unlink("tmp.xxx");
	} else {
		// else rename tmp.xxx into filename
#if defined(WIN32) || defined(WIN64)
		unlink(filename);
#endif
		if (rename("tmp.xxx", filename) == -1) Fatal("rename() failed");
	}
}

static int TranslateArgumentIdx(int argidx)
{
	int i, sum;

	if (argidx < 0 || argidx >= lengthof(_cur_pcs.cmd))
		Fatal("invalid argidx %d", argidx);

	for(i = sum = 0; i < argidx; i++) {
		const CmdStruct *cs = _cur_pcs.cmd[i];
		sum += cs ? cs->consumes : 1;
	}

	return sum;
}

static void PutArgidxCommand(void)
{
	PutByte(0x8C);
	PutByte(TranslateArgumentIdx(_cur_argidx));
}


static void PutCommandString(const char *str)
{
	const CmdStruct *cs;
	char param[256];
	int argno;
	int casei;

	_cur_argidx = 0;

	while (*str != '\0') {
		// Process characters as they are until we encounter a {
		if (*str != '{') {
			PutByte(*str++);
			continue;
		}
		cs = ParseCommandString(&str, param, &argno, &casei);
		if (cs == NULL) break;

		if (casei != -1) {
			PutByte(0x9D); // {SETCASE}
			PutByte(casei);
		}

		// For params that consume values, we need to handle the argindex properly
		if (cs->consumes) {
			// Check if we need to output a move-param command
			if (argno!=-1 && argno != _cur_argidx) {
				_cur_argidx = argno;
				PutArgidxCommand();
			}

			// Output the one from the master string... it's always accurate.
			cs = _cur_pcs.cmd[_cur_argidx++];
			if (!cs)
				Fatal("%s: No argument exists at posision %d", _cur_ident, _cur_argidx-1);
		}

		cs->proc(param, cs->value);
	}
}

static void WriteLength(FILE *f, uint length)
{
	if (length < 0xC0) {
		fputc(length, f);
	} else if (length < 0x4000) {
		fputc((length >> 8) | 0xC0, f);
		fputc(length & 0xFF, f);
	} else {
		Fatal("string too long");
	}
}


static void WriteLangfile(const char *filename, int show_todo)
{
	FILE *f;
	int in_use[32];
	LanguagePackHeader hdr;
	int i,j;

	f = fopen(filename, "wb");
	if (f == NULL) Fatal("can't open %s", filename);

	memset(&hdr, 0, sizeof(hdr));
	for(i = 0; i != 32; i++) {
		int n = CountInUse(i);
		in_use[i] = n;
		hdr.offsets[i] = TO_LE16(n);
	}

	// see line 655: fprintf(..."\tLANGUAGE_PACK_IDENT = 0x474E414C,...)
	hdr.ident = TO_LE32(0x474E414C); // Big Endian value for 'LANG'
	hdr.version = TO_LE32(_hash);
	hdr.plural_form = _lang_pluralform;
	strcpy(hdr.name, _lang_name);
	strcpy(hdr.own_name, _lang_ownname);
	strcpy(hdr.isocode, _lang_isocode);

	fwrite(&hdr, sizeof(hdr), 1, f);

	for(i = 0; i != 32; i++) {
		for(j = 0; j != in_use[i]; j++) {
			LangString *ls = _strings[(i<<11)+j];

			Case *casep;
			char *cmdp;

			// For undefined strings, just set that it's an empty string
			if (ls == NULL) {
				WriteLength(f, 0);
				continue;
			}

			_cur_ident = ls->name;
			_cur_line = ls->line;

			// Produce a message if a string doesn't have a translation.
			if (show_todo && ls->translated == NULL) {
				if (show_todo == 2) {
					Warning("'%s' is untranslated", ls->name);
				} else {
					const char *s = "<TODO> ";
					while(*s) PutByte(*s++);
				}
			}

			// Extract the strings and stuff from the english command string
			ExtractCommandString(&_cur_pcs, ls->english, false);

			if (ls->translated_case || ls->translated) {
				casep = ls->translated_case;
				cmdp = ls->translated;
			} else {
				casep = ls->english_case;
				cmdp = ls->english;
			}

			_translated = _masterlang || (cmdp != ls->english);

			if (casep) {
				Case *c;
				int num;
				// Need to output a case-switch.
				// It has this format
				// <0x9E> <NUM CASES> <CASE1> <LEN1> <STRING1> <CASE2> <LEN2> <STRING2> <CASE3> <LEN3> <STRING3> <STRINGDEFAULT>
				// Each LEN is printed using 2 bytes in big endian order.
				PutByte(0x9E);
				// Count the number of cases
				for(num=0,c=casep; c; c=c->next) num++;
				PutByte(num);

				// Write each case
				for(c=casep; c; c=c->next) {
					int pos;
					PutByte(c->caseidx);
					// Make some space for the 16-bit length
					pos = _put_pos;
					PutByte(0);
					PutByte(0);
					// Write string
					PutCommandString(c->string);
					PutByte(0); // terminate with a zero
					// Fill in the length
					_put_buf[pos] = (_put_pos - (pos + 2)) >> 8;
					_put_buf[pos+1] = (_put_pos - (pos + 2)) & 0xFF;
				}
			}

			if (cmdp)
				PutCommandString(cmdp);

			WriteLength(f, _put_pos);
			fwrite(_put_buf, 1, _put_pos, f);
			_put_pos = 0;
		}
	}

	fputc(0, f);

	fclose(f);
}


int CDECL main(int argc, char* argv[])
{
	char *r;
	char buf[256];
	int show_todo = 0;

	if (argc > 1 && (!strcmp(argv[1], "-v") || !strcmp(argv[1], "--version"))) {
		puts("$Revision$");
		return 0;
	}

	if (argc > 1 && !strcmp(argv[1], "-t")) {
		show_todo = 1;
		argc--, argv++;
	}

	if (argc > 1 && !strcmp(argv[1], "-w")) {
		show_todo = 2;
		argc--, argv++;
	}


	if (argc == 1) {
		_masterlang = true;
		// parse master file
		ParseFile("lang/english.txt", true);
		MakeHashOfStrings();
		if (_errors) return 1;

		// write english.lng and strings.h

		WriteLangfile("lang/english.lng", 0);
		WriteStringsH("table/strings.h");

	} else if (argc == 2) {
		_masterlang = false;
		ParseFile("lang/english.txt", true);
		MakeHashOfStrings();
		ParseFile(argv[1], false);

		if (_errors) return 1;

		strcpy(buf, argv[1]);
		r = strrchr(buf, '.');
		if (!r || strcmp(r, ".txt")) r = strchr(buf, 0);
		strcpy(r, ".lng");
		WriteLangfile(buf, show_todo);
	} else {
		fprintf(stderr, "invalid arguments\n");
	}

	return 0;
}