summaryrefslogtreecommitdiff
path: root/src/strgen/strgen_base.cpp
blob: 84fc3537bee5b20d77eb00d94fac51a72cbb977a (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
/* $Id$ */

/*
 * This file is part of OpenTTD.
 * OpenTTD 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, version 2.
 * OpenTTD is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
 * See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with OpenTTD. If not, see <http://www.gnu.org/licenses/>.
 */

/** @file strgen_base.cpp Tool to create computer readable (stand-alone) translation files. */

#include "../stdafx.h"
#include "../core/endian_func.hpp"
#include "../string_func.h"
#include "../table/control_codes.h"

#include "strgen.h"


#include "../table/strgen_tables.h"

#include "../safeguards.h"

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

static bool _translated;              ///< Whether the current language is not the master language
static bool _translation;             ///< Is the current file actually a translation or not
const char *_file = "(unknown file)"; ///< The filename of the input, so we can refer to it in errors/warnings
int _cur_line;                        ///< The current line we're parsing in the input file
int _errors, _warnings, _show_todo;
LanguagePackHeader _lang;             ///< Header information about a language.

static const ptrdiff_t MAX_COMMAND_PARAM_SIZE = 100; ///< Maximum size of every command block, not counting the name of the command itself
static const CmdStruct *ParseCommandString(const char **str, char *param, int *argno, int *casei);

/**
 * Create a new case.
 * @param caseidx The index of the case.
 * @param string  The translation of the case.
 * @param next    The next chained case.
 */
Case::Case(int caseidx, const char *string, Case *next) :
		caseidx(caseidx), string(stredup(string)), next(next)
{
}

/** Free everything we allocated. */
Case::~Case()
{
	free(this->string);
	delete this->next;
}

/**
 * Create a new string.
 * @param name    The name of the string.
 * @param english The english "translation" of the string.
 * @param index   The index in the string table.
 * @param line    The line this string was found on.
 */
LangString::LangString(const char *name, const char *english, size_t index, int line) :
		name(stredup(name)), english(stredup(english)), translated(nullptr),
		hash_next(0), index(index), line(line), translated_case(nullptr)
{
}

/** Free everything we allocated. */
LangString::~LangString()
{
	free(this->name);
	free(this->english);
	free(this->translated);
	delete this->translated_case;
}

/** Free all data related to the translation. */
void LangString::FreeTranslation()
{
	free(this->translated);
	this->translated = nullptr;

	delete this->translated_case;
	this->translated_case = nullptr;
}

/**
 * Create a new string data container.
 * @param tabs The maximum number of strings.
 */
StringData::StringData(size_t tabs) : tabs(tabs), max_strings(tabs * TAB_SIZE)
{
	this->strings = CallocT<LangString *>(max_strings);
	this->hash_heads = CallocT<size_t>(max_strings);
	this->next_string_id = 0;
}

/** Free everything we allocated. */
StringData::~StringData()
{
	for (size_t i = 0; i < this->max_strings; i++) delete this->strings[i];
	free(this->strings);
	free(this->hash_heads);
}

/** Free all data related to the translation. */
void StringData::FreeTranslation()
{
	for (size_t i = 0; i < this->max_strings; i++) {
		LangString *ls = this->strings[i];
		if (ls != nullptr) ls->FreeTranslation();
	}
}

/**
 * Create a hash of the string for finding them back quickly.
 * @param s The string to hash.
 * @return The hashed string.
 */
uint StringData::HashStr(const char *s) const
{
	uint hash = 0;
	for (; *s != '\0'; s++) hash = ROL(hash, 3) ^ *s;
	return hash % this->max_strings;
}

/**
 * Add a newly created LangString.
 * @param s  The name of the string.
 * @param ls The string to add.
 */
void StringData::Add(const char *s, LangString *ls)
{
	uint hash = this->HashStr(s);
	ls->hash_next = this->hash_heads[hash];
	/* Off-by-one for hash find. */
	this->hash_heads[hash] = ls->index + 1;
	this->strings[ls->index] = ls;
}

/**
 * Find a LangString based on the string name.
 * @param s The string name to search on.
 * @return The LangString or nullptr if it is not known.
 */
LangString *StringData::Find(const char *s)
{
	size_t idx = this->hash_heads[this->HashStr(s)];

	while (idx-- > 0) {
		LangString *ls = this->strings[idx];

		if (strcmp(ls->name, s) == 0) return ls;
		idx = ls->hash_next;
	}
	return nullptr;
}

/**
 * Create a compound hash.
 * @param hash The hash to add the string hash to.
 * @param s    The string hash.
 * @return The new hash.
 */
uint StringData::VersionHashStr(uint hash, const char *s) const
{
	for (; *s != '\0'; s++) {
		hash = ROL(hash, 3) ^ *s;
		hash = (hash & 1 ? hash >> 1 ^ 0xDEADBEEF : hash >> 1);
	}
	return hash;
}

/**
 * Make a hash of the file to get a unique "version number"
 * @return The version number.
 */
uint StringData::Version() const
{
	uint hash = 0;

	for (size_t i = 0; i < this->max_strings; i++) {
		const LangString *ls = this->strings[i];

		if (ls != nullptr) {
			const CmdStruct *cs;
			const char *s;
			char buf[MAX_COMMAND_PARAM_SIZE];
			int argno;
			int casei;

			s = ls->name;
			hash ^= i * 0x717239;
			hash = (hash & 1 ? hash >> 1 ^ 0xDEADBEEF : hash >> 1);
			hash = this->VersionHashStr(hash, s + 1);

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

				hash ^= (cs - _cmd_structs) * 0x1234567;
				hash = (hash & 1 ? hash >> 1 ^ 0xF00BAA4 : hash >> 1);
			}
		}
	}

	return hash;
}

/**
 * Count the number of tab elements that are in use.
 * @param tab The tab to count the elements of.
 */
uint StringData::CountInUse(uint tab) const
{
	int i;
	for (i = TAB_SIZE; --i >= 0;) if (this->strings[(tab * TAB_SIZE) + i] != nullptr) break;
	return i + 1;
}

static const char *_cur_ident;

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

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

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

/** The buffer for writing a single string. */
struct Buffer : std::vector<byte> {
	/**
	 * Convenience method for adding a byte.
	 * @param value The value to add.
	 */
	void AppendByte(byte value)
	{
		this->push_back(value);
	}

	/**
	 * Add an Unicode character encoded in UTF-8 to the buffer.
	 * @param value The character to add.
	 */
	void AppendUtf8(uint32 value)
	{
		if (value < 0x80) {
			this->push_back(value);
		} else if (value < 0x800) {
			this->push_back(0xC0 + GB(value,  6, 5));
			this->push_back(0x80 + GB(value,  0, 6));
		} else if (value < 0x10000) {
			this->push_back(0xE0 + GB(value, 12, 4));
			this->push_back(0x80 + GB(value,  6, 6));
			this->push_back(0x80 + GB(value,  0, 6));
		} else if (value < 0x110000) {
			this->push_back(0xF0 + GB(value, 18, 3));
			this->push_back(0x80 + GB(value, 12, 6));
			this->push_back(0x80 + GB(value,  6, 6));
			this->push_back(0x80 + GB(value,  0, 6));
		} else {
			strgen_warning("Invalid unicode value U+0x%X", value);
		}
	}
};

size_t Utf8Validate(const char *s)
{
	uint32 c;

	if (!HasBit(s[0], 7)) {
		/* 1 byte */
		return 1;
	} else if (GB(s[0], 5, 3) == 6 && IsUtf8Part(s[1])) {
		/* 2 bytes */
		c = GB(s[0], 0, 5) << 6 | GB(s[1], 0, 6);
		if (c >= 0x80) return 2;
	} else if (GB(s[0], 4, 4) == 14 && IsUtf8Part(s[1]) && IsUtf8Part(s[2])) {
		/* 3 bytes */
		c = GB(s[0], 0, 4) << 12 | GB(s[1], 0, 6) << 6 | GB(s[2], 0, 6);
		if (c >= 0x800) return 3;
	} else if (GB(s[0], 3, 5) == 30 && IsUtf8Part(s[1]) && IsUtf8Part(s[2]) && IsUtf8Part(s[3])) {
		/* 4 bytes */
		c = GB(s[0], 0, 3) << 18 | GB(s[1], 0, 6) << 12 | GB(s[2], 0, 6) << 6 | GB(s[3], 0, 6);
		if (c >= 0x10000 && c <= 0x10FFFF) return 4;
	}

	return 0;
}


void EmitSingleChar(Buffer *buffer, char *buf, int value)
{
	if (*buf != '\0') strgen_warning("Ignoring trailing letters in command");
	buffer->AppendUtf8(value);
}


/* 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, int *offset)
{
	const char *s = *buf;
	char *end;
	bool rel = false;

	while (*s == ' ' || *s == '\t') s++;
	if (*s == '+') {
		rel = true;
		s++;
	}
	int v = strtol(s, &end, 0);
	if (end == s) return false;
	if (rel || v < 0) {
		*value += v;
	} else {
		*value = v;
	}
	if (offset != nullptr && *end == ':') {
		/* Take the Nth within */
		s = end + 1;
		*offset = strtol(s, &end, 0);
		if (end == s) return false;
	}
	*buf = end;
	return true;
}

/* Parse out the next word, or nullptr */
char *ParseWord(char **buf)
{
	char *s = *buf, *r;

	while (*s == ' ' || *s == '\t') s++;
	if (*s == '\0') return nullptr;

	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, int offset = 0);

static void EmitWordList(Buffer *buffer, const char * const *words, uint nw)
{
	buffer->AppendByte(nw);
	for (uint i = 0; i < nw; i++) buffer->AppendByte((byte)strlen(words[i]) + 1);
	for (uint i = 0; i < nw; i++) {
		for (uint j = 0; words[i][j] != '\0'; j++) buffer->AppendByte(words[i][j]);
		buffer->AppendByte(0);
	}
}

void EmitPlural(Buffer *buffer, char *buf, int value)
{
	int argidx = _cur_argidx;
	int offset = -1;
	int expected = _plural_forms[_lang.plural_form].plural_count;
	const char **words = AllocaM(const char *, max(expected, MAX_PLURALS));
	int nw = 0;

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

	const CmdStruct *cmd = _cur_pcs.cmd[argidx];
	if (offset == -1) {
		/* Use default offset */
		if (cmd == nullptr || cmd->default_plural_offset < 0) {
			strgen_fatal("Command '%s' has no (default) plural position", cmd == nullptr ? "<empty>" : cmd->cmd);
		}
		offset = cmd->default_plural_offset;
	}

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

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

	if (expected != nw) {
		if (_translated) {
			strgen_fatal("%s: Invalid number of plural forms. Expecting %d, found %d.", _cur_ident,
				expected, nw);
		} else {
			if ((_show_todo & 2) != 0) strgen_warning("'%s' is untranslated. Tweaking english string to allow compilation for plural forms", _cur_ident);
			if (nw > expected) {
				nw = expected;
			} else {
				for (; nw < expected; nw++) {
					words[nw] = words[nw - 1];
				}
			}
		}
	}

	buffer->AppendUtf8(SCC_PLURAL_LIST);
	buffer->AppendByte(_lang.plural_form);
	buffer->AppendByte(TranslateArgumentIdx(argidx, offset));
	EmitWordList(buffer, words, nw);
}


void EmitGender(Buffer *buffer, char *buf, int value)
{
	int argidx = _cur_argidx;
	int offset = 0;
	uint nw;

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

		/* This is a {G=DER} command */
		nw = _lang.GetGenderIndex(buf);
		if (nw >= MAX_NUM_GENDERS) strgen_fatal("G argument '%s' invalid", buf);

		/* now nw contains the gender index */
		buffer->AppendUtf8(SCC_GENDER_INDEX);
		buffer->AppendByte(nw);
	} else {
		const char *words[MAX_NUM_GENDERS];

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

		const CmdStruct *cmd = _cur_pcs.cmd[argidx];
		if (cmd == nullptr || (cmd->flags & C_GENDER) == 0) {
			strgen_fatal("Command '%s' can't have a gender", cmd == nullptr ? "<empty>" : cmd->cmd);
		}

		for (nw = 0; nw < MAX_NUM_GENDERS; nw++) {
			words[nw] = ParseWord(&buf);
			if (words[nw] == nullptr) break;
		}
		if (nw != _lang.num_genders) strgen_fatal("Bad # of arguments for gender command");

		assert(IsInsideBS(cmd->value, SCC_CONTROL_START, UINT8_MAX));
		buffer->AppendUtf8(SCC_GENDER_LIST);
		buffer->AppendByte(TranslateArgumentIdx(argidx, offset));
		EmitWordList(buffer, words, nw);
	}
}

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

static uint ResolveCaseName(const char *str, size_t len)
{
	/* First get a clean copy of only the case name, then resolve it. */
	char case_str[CASE_GENDER_LEN];
	len = min(lengthof(case_str) - 1, len);
	memcpy(case_str, str, len);
	case_str[len] = '\0';

	uint8 case_idx = _lang.GetCaseIndex(case_str);
	if (case_idx >= MAX_NUM_CASES) strgen_fatal("Invalid case-name '%s'", case_str);
	return case_idx + 1;
}


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

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

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

	if (*s >= '0' && *s <= '9') {
		char *end;

		*argno = strtoul(s, &end, 0);
		if (*end != ':') strgen_fatal("missing arg #");
		s = end + 1;
	}

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

	const CmdStruct *cmd = FindCmd(start, s - start - 1);
	if (cmd == nullptr) {
		strgen_error("Undefined command '%.*s'", (int)(s - start - 1), start);
		return nullptr;
	}

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

		if (!(cmd->flags & C_CASE)) {
			strgen_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') {
		strgen_error("Missing } from command '%s'", start);
		return nullptr;
	}


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

	*str = s;

	return cmd;
}

/**
 * Prepare reading.
 * @param data        The data to fill during reading.
 * @param file        The file we are reading.
 * @param master      Are we reading the master file?
 * @param translation Are we reading a translation?
 */
StringReader::StringReader(StringData &data, const char *file, bool master, bool translation) :
		data(data), file(stredup(file)), master(master), translation(translation)
{
}

/** Make sure the right reader gets freed. */
StringReader::~StringReader()
{
	free(file);
}

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

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

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

		if (ar == nullptr) break;

		/* Sanity checking */
		if (argno != -1 && ar->consumes == 0) strgen_fatal("Non consumer param can't have a paramindex");

		if (ar->consumes) {
			if (argno != -1) argidx = argno;
			if (argidx < 0 || (uint)argidx >= lengthof(p->cmd)) strgen_fatal("invalid param idx %d", argidx);
			if (p->cmd[argidx] != nullptr && p->cmd[argidx] != ar) strgen_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)) strgen_fatal("too many commands in string, max " PRINTF_SIZE, lengthof(p->pairs));
			p->pairs[p->np].a = ar;
			p->pairs[p->np].v = param[0] != '\0' ? stredup(param) : "";
			p->np++;
		}
	}
}


static const CmdStruct *TranslateCmdForCompare(const CmdStruct *a)
{
	if (a == nullptr) return nullptr;

	if (strcmp(a->cmd, "STRING1") == 0 ||
			strcmp(a->cmd, "STRING2") == 0 ||
			strcmp(a->cmd, "STRING3") == 0 ||
			strcmp(a->cmd, "STRING4") == 0 ||
			strcmp(a->cmd, "STRING5") == 0 ||
			strcmp(a->cmd, "STRING6") == 0 ||
			strcmp(a->cmd, "STRING7") == 0 ||
			strcmp(a->cmd, "RAW_STRING") == 0) {
		return FindCmd("STRING", 6);
	}

	return a;
}


static bool CheckCommandsMatch(char *a, char *b, const char *name)
{
	/* If we're not translating, i.e. we're compiling the base language,
	 * it is pointless to do all these checks as it'll always be correct.
	 * After all, all checks are based on the base language.
	 */
	if (!_translation) return true;

	ParsedCommandStruct templ;
	ParsedCommandStruct lang;
	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) {
		strgen_warning("%s: template string and language string have a different # of commands", name);
		result = false;
	}

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

		if (!found) {
			strgen_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 (uint i = 0; i < lengthof(templ.cmd); i++) {
		if (TranslateCmdForCompare(templ.cmd[i]) != lang.cmd[i]) {
			strgen_warning("%s: Param idx #%d '%s' doesn't match with template command '%s'", name, i,
				lang.cmd[i]  == nullptr ? "<empty>" : TranslateCmdForCompare(lang.cmd[i])->cmd,
				templ.cmd[i] == nullptr ? "<empty>" : templ.cmd[i]->cmd);
			result = false;
		}
	}

	return result;
}

void StringReader::HandleString(char *str)
{
	if (*str == '#') {
		if (str[1] == '#' && str[2] != '#') this->HandlePragma(str + 2);
		return;
	}

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

	char *s = strchr(str, ':');
	if (s == nullptr) {
		strgen_error("Line has no ':' delimiter");
		return;
	}

	char *t;
	/* 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 string is valid UTF-8 */
	const char *tmp;
	for (tmp = s; *tmp != '\0';) {
		size_t len = Utf8Validate(tmp);
		if (len == 0) strgen_fatal("Invalid UTF-8 sequence in '%s'", s);

		WChar c;
		Utf8Decode(&c, tmp);
		if (c <= 0x001F || // ASCII control character range
				c == 0x200B || // Zero width space
				(c >= 0xE000 && c <= 0xF8FF) || // Private range
				(c >= 0xFFF0 && c <= 0xFFFF)) { // Specials range
			strgen_fatal("Unwanted UTF-8 character U+%04X in sequence '%s'", c, s);
		}

		tmp += len;
	}

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

	/* Check if this string already exists.. */
	LangString *ent = this->data.Find(str);

	if (this->master) {
		if (casep != nullptr) {
			strgen_error("Cases in the base translation are not supported.");
			return;
		}

		if (ent != nullptr) {
			strgen_error("String name '%s' is used multiple times", str);
			return;
		}

		if (this->data.strings[this->data.next_string_id] != nullptr) {
			strgen_error("String ID 0x" PRINTF_SIZEX " for '%s' already in use by '%s'", this->data.next_string_id, str, this->data.strings[this->data.next_string_id]->name);
			return;
		}

		/* Allocate a new LangString */
		this->data.Add(str, new LangString(str, s, this->data.next_string_id++, _cur_line));
	} else {
		if (ent == nullptr) {
			strgen_warning("String name '%s' does not exist in master file", str);
			return;
		}

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

		/* make sure that the commands match */
		if (!CheckCommandsMatch(s, ent->english, str)) return;

		if (casep != nullptr) {
			ent->translated_case = new Case(ResolveCaseName(casep, strlen(casep)), s, ent->translated_case);
		} else {
			ent->translated = stredup(s);
			/* If the string was translated, use the line from the
			 * translated language so errors in the translated file
			 * are properly referenced to. */
			ent->line = _cur_line;
		}
	}
}

void StringReader::HandlePragma(char *str)
{
	if (!memcmp(str, "plural ", 7)) {
		_lang.plural_form = atoi(str + 7);
		if (_lang.plural_form >= lengthof(_plural_forms)) {
			strgen_fatal("Invalid pluralform %d", _lang.plural_form);
		}
	} else {
		strgen_fatal("unknown pragma '%s'", str);
	}
}

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

void StringReader::ParseFile()
{
	char buf[2048];
	_warnings = _errors = 0;

	_translation = this->master || this->translation;
	_file = this->file;

	/* For each new file we parse, reset the genders, and language codes. */
	MemSetT(&_lang, 0);
	strecpy(_lang.digit_group_separator, ",", lastof(_lang.digit_group_separator));
	strecpy(_lang.digit_group_separator_currency, ",", lastof(_lang.digit_group_separator_currency));
	strecpy(_lang.digit_decimal_separator, ".", lastof(_lang.digit_decimal_separator));

	_cur_line = 1;
	while (this->data.next_string_id < this->data.max_strings && this->ReadLine(buf, lastof(buf)) != nullptr) {
		rstrip(buf);
		this->HandleString(buf);
		_cur_line++;
	}

	if (this->data.next_string_id == this->data.max_strings) {
		strgen_error("Too many strings, maximum allowed is " PRINTF_SIZE, this->data.max_strings);
	}
}

/**
 * Write the header information.
 * @param data The data about the string.
 */
void HeaderWriter::WriteHeader(const StringData &data)
{
	int last = 0;
	for (size_t i = 0; i < data.max_strings; i++) {
		if (data.strings[i] != nullptr) {
			this->WriteStringID(data.strings[i]->name, (int)i);
			last = (int)i;
		}
	}

	this->WriteStringID("STR_LAST_STRINGID", last);
}

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

	if (argidx < 0 || (uint)argidx >= lengthof(_cur_pcs.cmd)) {
		strgen_fatal("invalid argidx %d", argidx);
	}
	const CmdStruct *cs = _cur_pcs.cmd[argidx];
	if (cs != nullptr && cs->consumes <= offset) {
		strgen_fatal("invalid argidx offset %d:%d", argidx, offset);
	}

	if (_cur_pcs.cmd[argidx] == nullptr) {
		strgen_fatal("no command for this argidx %d", argidx);
	}

	for (int i = sum = 0; i < argidx; i++) {
		const CmdStruct *cs = _cur_pcs.cmd[i];

		sum += (cs != nullptr) ? cs->consumes : 1;
	}

	return sum + offset;
}

static void PutArgidxCommand(Buffer *buffer)
{
	buffer->AppendUtf8(SCC_ARG_INDEX);
	buffer->AppendByte(TranslateArgumentIdx(_cur_argidx));
}


static void PutCommandString(Buffer *buffer, const char *str)
{
	_cur_argidx = 0;

	while (*str != '\0') {
		/* Process characters as they are until we encounter a { */
		if (*str != '{') {
			buffer->AppendByte(*str++);
			continue;
		}

		char param[MAX_COMMAND_PARAM_SIZE];
		int argno;
		int casei;
		const CmdStruct *cs = ParseCommandString(&str, param, &argno, &casei);
		if (cs == nullptr) break;

		if (casei != -1) {
			buffer->AppendUtf8(SCC_SET_CASE); // {SET_CASE}
			buffer->AppendByte(casei);
		}

		/* For params that consume values, we need to handle the argindex properly */
		if (cs->consumes > 0) {
			/* Check if we need to output a move-param command */
			if (argno != -1 && argno != _cur_argidx) {
				_cur_argidx = argno;
				PutArgidxCommand(buffer);
			}

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

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

/**
 * Write the length as a simple gamma.
 * @param length The number to write.
 */
void LanguageWriter::WriteLength(uint length)
{
	char buffer[2];
	int offs = 0;
	if (length >= 0x4000) {
		strgen_fatal("string too long");
	}

	if (length >= 0xC0) {
		buffer[offs++] = (length >> 8) | 0xC0;
	}
	buffer[offs++] = length & 0xFF;
	this->Write((byte*)buffer, offs);
}

/**
 * Actually write the language.
 * @param data The data about the string.
 */
void LanguageWriter::WriteLang(const StringData &data)
{
	uint *in_use = AllocaM(uint, data.tabs);
	for (size_t tab = 0; tab < data.tabs; tab++) {
		uint n = data.CountInUse((uint)tab);

		in_use[tab] = n;
		_lang.offsets[tab] = TO_LE16(n);

		for (uint j = 0; j != in_use[tab]; j++) {
			const LangString *ls = data.strings[(tab * TAB_SIZE) + j];
			if (ls != nullptr && ls->translated == nullptr) _lang.missing++;
		}
	}

	_lang.ident = TO_LE32(LanguagePackHeader::IDENT);
	_lang.version = TO_LE32(data.Version());
	_lang.missing = TO_LE16(_lang.missing);
	_lang.winlangid = TO_LE16(_lang.winlangid);

	this->WriteHeader(&_lang);
	Buffer buffer;

	for (size_t tab = 0; tab < data.tabs; tab++) {
		for (uint j = 0; j != in_use[tab]; j++) {
			const LangString *ls = data.strings[(tab * TAB_SIZE) + j];
			const Case *casep;
			const char *cmdp;

			/* For undefined strings, just set that it's an empty string */
			if (ls == nullptr) {
				this->WriteLength(0);
				continue;
			}

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

			/* Produce a message if a string doesn't have a translation. */
			if (_show_todo > 0 && ls->translated == nullptr) {
				if ((_show_todo & 2) != 0) {
					strgen_warning("'%s' is untranslated", ls->name);
				}
				if ((_show_todo & 1) != 0) {
					const char *s = "<TODO> ";
					while (*s != '\0') buffer.AppendByte(*s++);
				}
			}

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

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

			_translated = cmdp != ls->english;

			if (casep != nullptr) {
				const Case *c;
				uint 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. */
				buffer.AppendUtf8(SCC_SWITCH_CASE);
				/* Count the number of cases */
				for (num = 0, c = casep; c; c = c->next) num++;
				buffer.AppendByte(num);

				/* Write each case */
				for (c = casep; c != nullptr; c = c->next) {
					buffer.AppendByte(c->caseidx);
					/* Make some space for the 16-bit length */
					uint pos = (uint)buffer.size();
					buffer.AppendByte(0);
					buffer.AppendByte(0);
					/* Write string */
					PutCommandString(&buffer, c->string);
					buffer.AppendByte(0); // terminate with a zero
					/* Fill in the length */
					uint size = (uint)buffer.size() - (pos + 2);
					buffer[pos + 0] = GB(size, 8, 8);
					buffer[pos + 1] = GB(size, 0, 8);
				}
			}

			if (cmdp != nullptr) PutCommandString(&buffer, cmdp);

			this->WriteLength((uint)buffer.size());
			this->Write(buffer.data(), buffer.size());
			buffer.clear();
		}
	}
}