summaryrefslogtreecommitdiff
path: root/src/strgen/strgen.cpp
blob: a905a599b5962df6c72b400b0a0121c32eb7730b (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
/* $Id$ */

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

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

#include "strgen.h"

#include <stdarg.h>
#include <exception>

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

#if defined WIN32 || defined __WATCOMC__
#include <direct.h>
#endif /* WIN32 || __WATCOMC__ */

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

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


#ifdef _MSC_VER
# define LINE_NUM_FMT(s) "%s (%d): warning: %s (" s ")\n"
#else
# define LINE_NUM_FMT(s) "%s:%d: " s ": %s\n"
#endif

void CDECL strgen_warning(const char *s, ...)
{
	char buf[1024];
	va_list va;
	va_start(va, s);
	vsnprintf(buf, lengthof(buf), s, va);
	va_end(va);
	fprintf(stderr, LINE_NUM_FMT("warning"), _file, _cur_line, buf);
	_warnings++;
}

void CDECL strgen_error(const char *s, ...)
{
	char buf[1024];
	va_list va;
	va_start(va, s);
	vsnprintf(buf, lengthof(buf), s, va);
	va_end(va);
	fprintf(stderr, LINE_NUM_FMT("error"), _file, _cur_line, buf);
	_errors++;
}

void NORETURN CDECL strgen_fatal(const char *s, ...)
{
	char buf[1024];
	va_list va;
	va_start(va, s);
	vsnprintf(buf, lengthof(buf), s, va);
	va_end(va);
	fprintf(stderr, LINE_NUM_FMT("FATAL"), _file, _cur_line, buf);
#ifdef _MSC_VER
	fprintf(stderr, LINE_NUM_FMT("warning"), _file, _cur_line, "language is not compiled");
#endif
	throw std::exception();
}

void NORETURN CDECL error(const char *s, ...)
{
	char buf[1024];
	va_list va;
	va_start(va, s);
	vsnprintf(buf, lengthof(buf), s, va);
	va_end(va);
	fprintf(stderr, LINE_NUM_FMT("FATAL"), _file, _cur_line, buf);
#ifdef _MSC_VER
	fprintf(stderr, LINE_NUM_FMT("warning"), _file, _cur_line, "language is not compiled");
#endif
	exit(2);
}

/** A reader that simply reads using fopen. */
struct FileStringReader : StringReader {
	FILE *fh; ///< The file we are reading.

	/**
	 * Create the reader.
	 * @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?
	 */
	FileStringReader(StringData &data, const char *file, bool master, bool translation) :
			StringReader(data, file, master, translation)
	{
		this->fh = fopen(file, "rb");
		if (this->fh == NULL) error("Could not open %s", file);
	}

	/** Free/close the file. */
	virtual ~FileStringReader()
	{
		fclose(this->fh);
	}

	/* virtual */ char *ReadLine(char *buffer, size_t size)
	{
		return fgets(buffer, size, this->fh);
	}

	/* virtual */ void HandlePragma(char *str);

	/* virtual */ void ParseFile()
	{
		this->StringReader::ParseFile();

		if (StrEmpty(_lang.name) || StrEmpty(_lang.own_name) || StrEmpty(_lang.isocode)) {
			error("Language must include ##name, ##ownname and ##isocode");
		}
	}
};

void FileStringReader::HandlePragma(char *str)
{
	if (!memcmp(str, "id ", 3)) {
		this->data.next_string_id = strtoul(str + 3, NULL, 0);
	} else if (!memcmp(str, "name ", 5)) {
		strecpy(_lang.name, str + 5, lastof(_lang.name));
	} else if (!memcmp(str, "ownname ", 8)) {
		strecpy(_lang.own_name, str + 8, lastof(_lang.own_name));
	} else if (!memcmp(str, "isocode ", 8)) {
		strecpy(_lang.isocode, str + 8, lastof(_lang.isocode));
	} else if (!memcmp(str, "plural ", 7)) {
		_lang.plural_form = atoi(str + 7);
		if (_lang.plural_form >= lengthof(_plural_forms)) {
			error("Invalid pluralform %d", _lang.plural_form);
		}
	} else if (!memcmp(str, "textdir ", 8)) {
		if (!memcmp(str + 8, "ltr", 3)) {
			_lang.text_dir = TD_LTR;
		} else if (!memcmp(str + 8, "rtl", 3)) {
			_lang.text_dir = TD_RTL;
		} else {
			error("Invalid textdir %s", str + 8);
		}
	} else if (!memcmp(str, "digitsep ", 9)) {
		str += 9;
		strecpy(_lang.digit_group_separator, strcmp(str, "{NBSP}") == 0 ? NBSP : str, lastof(_lang.digit_group_separator));
	} else if (!memcmp(str, "digitsepcur ", 12)) {
		str += 12;
		strecpy(_lang.digit_group_separator_currency, strcmp(str, "{NBSP}") == 0 ? NBSP : str, lastof(_lang.digit_group_separator_currency));
	} else if (!memcmp(str, "decimalsep ", 11)) {
		str += 11;
		strecpy(_lang.digit_decimal_separator, strcmp(str, "{NBSP}") == 0 ? NBSP : str, lastof(_lang.digit_decimal_separator));
	} else if (!memcmp(str, "winlangid ", 10)) {
		const char *buf = str + 10;
		long langid = strtol(buf, NULL, 16);
		if (langid > (long)UINT16_MAX || langid < 0) {
			error("Invalid winlangid %s", buf);
		}
		_lang.winlangid = (uint16)langid;
	} else if (!memcmp(str, "grflangid ", 10)) {
		const char *buf = str + 10;
		long langid = strtol(buf, NULL, 16);
		if (langid >= 0x7F || langid < 0) {
			error("Invalid grflangid %s", buf);
		}
		_lang.newgrflangid = (uint8)langid;
	} else if (!memcmp(str, "gender ", 7)) {
		if (this->master) error("Genders are not allowed in the base translation.");
		char *buf = str + 7;

		for (;;) {
			const char *s = ParseWord(&buf);

			if (s == NULL) break;
			if (_lang.num_genders >= MAX_NUM_GENDERS) error("Too many genders, max %d", MAX_NUM_GENDERS);
			strecpy(_lang.genders[_lang.num_genders], s, lastof(_lang.genders[_lang.num_genders]));
			_lang.num_genders++;
		}
	} else if (!memcmp(str, "case ", 5)) {
		if (this->master) error("Cases are not allowed in the base translation.");
		char *buf = str + 5;

		for (;;) {
			const char *s = ParseWord(&buf);

			if (s == NULL) break;
			if (_lang.num_cases >= MAX_NUM_CASES) error("Too many cases, max %d", MAX_NUM_CASES);
			strecpy(_lang.cases[_lang.num_cases], s, lastof(_lang.cases[_lang.num_cases]));
			_lang.num_cases++;
		}
	} else {
		error("unknown pragma '%s'", str);
	}
}

bool CompareFiles(const char *n1, const char *n2)
{
	FILE *f2 = fopen(n2, "rb");
	if (f2 == NULL) return false;

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

	size_t l1, l2;
	do {
		char b1[4096];
		char b2[4096];
		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 != 0);

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

/** Base class for writing data to disk. */
struct FileWriter {
	FILE *fh;             ///< The file handle we're writing to.
	const char *filename; ///< The file name we're writing to.

	/**
	 * Open a file to write to.
	 * @param filename The file to open.
	 */
	FileWriter(const char *filename)
	{
		this->filename = strdup(filename);
		this->fh = fopen(this->filename, "wb");

		if (this->fh == NULL) {
			error("Could not open %s", this->filename);
		}
	}

	/** Finalise the writing. */
	void Finalise()
	{
		fclose(this->fh);
		this->fh = NULL;
	}

	/** Make sure the file is closed. */
	virtual ~FileWriter()
	{
		/* If we weren't closed an exception was thrown, so remove the termporary file. */
		if (fh != NULL) {
			fclose(this->fh);
			unlink(this->filename);
		}
		free(this->filename);
	}
};

struct HeaderFileWriter : HeaderWriter, FileWriter {
	/** The real file name we eventually want to write to. */
	const char *real_filename;
	/** The previous string ID that was printed. */
	int prev;

	/**
	 * Open a file to write to.
	 * @param filename The file to open.
	 */
	HeaderFileWriter(const char *filename) : FileWriter("tmp.xxx"),
		real_filename(strdup(filename)), prev(0)
	{
		fprintf(this->fh, "/* This file is automatically generated. Do not modify */\n\n");
		fprintf(this->fh, "#ifndef TABLE_STRINGS_H\n");
		fprintf(this->fh, "#define TABLE_STRINGS_H\n");
	}

	void WriteStringID(const char *name, int stringid)
	{
		if (prev + 1 != stringid) fprintf(this->fh, "\n");
		fprintf(this->fh, "static const StringID %s = 0x%X;\n", name, stringid);
		prev = stringid;
	}

	void Finalise(const StringData &data)
	{
		/* Find the plural form with the most amount of cases. */
		int max_plural_forms = 0;
		for (uint i = 0; i < lengthof(_plural_forms); i++) {
			max_plural_forms = max(max_plural_forms, _plural_forms[i].plural_count);
		}

		fprintf(this->fh,
			"\n"
			"static const uint LANGUAGE_PACK_VERSION     = 0x%X;\n"
			"static const uint LANGUAGE_MAX_PLURAL       = %d;\n"
			"static const uint LANGUAGE_MAX_PLURAL_FORMS = %d;\n\n",
			(uint)data.Version(), (uint)lengthof(_plural_forms), max_plural_forms
		);

		fprintf(this->fh, "#endif /* TABLE_STRINGS_H */\n");

		this->FileWriter::Finalise();

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

/** Class for writing a language to disk. */
struct LanguageFileWriter : LanguageWriter, FileWriter {
	/**
	 * Open a file to write to.
	 * @param filename The file to open.
	 */
	LanguageFileWriter(const char *filename) : FileWriter(filename)
	{
	}

	void WriteHeader(const LanguagePackHeader *header)
	{
		this->Write((const byte *)header, sizeof(*header));
	}

	void Finalise()
	{
		fputc(0, this->fh);
		this->FileWriter::Finalise();
	}

	void Write(const byte *buffer, size_t length)
	{
		if (fwrite(buffer, sizeof(*buffer), length, this->fh) != length) {
			error("Could not write to %s", this->filename);
		}
	}
};

/** Multi-OS mkdirectory function */
static inline void ottd_mkdir(const char *directory)
{
#if defined(WIN32) || defined(__WATCOMC__)
		mkdir(directory);
#else
		mkdir(directory, 0755);
#endif
}

/**
 * Create a path consisting of an already existing path, a possible
 * path seperator and the filename. The seperator is only appended if the path
 * does not already end with a seperator
 */
static inline char *mkpath(char *buf, size_t buflen, const char *path, const char *file)
{
	ttd_strlcpy(buf, path, buflen); // copy directory into buffer

	char *p = strchr(buf, '\0'); // add path seperator if necessary
	if (p[-1] != PATHSEPCHAR && (size_t)(p - buf) + 1 < buflen) *p++ = PATHSEPCHAR;
	ttd_strlcpy(p, file, buflen - (size_t)(p - buf)); // catenate filename at end of buffer
	return buf;
}

#if defined(__MINGW32__)
/**
 * On MingW, it is common that both / as \ are accepted in the
 * params. To go with those flow, we rewrite all incoming /
 * simply to \, so internally we can safely assume \.
 */
static inline char *replace_pathsep(char *s)
{
	for (char *c = s; *c != '\0'; c++) if (*c == '/') *c = '\\';
	return s;
}
#else
static inline char *replace_pathsep(char *s) { return s; }
#endif

/** Options of strgen. */
static const OptionData _opts[] = {
	  GETOPT_NOVAL(     'v',  "--version"),
	GETOPT_GENERAL('C', '\0', "-export-commands", ODF_NO_VALUE),
	GETOPT_GENERAL('L', '\0', "-export-plurals",  ODF_NO_VALUE),
	GETOPT_GENERAL('P', '\0', "-export-pragmas",  ODF_NO_VALUE),
	  GETOPT_NOVAL(     't',  "--todo"),
	  GETOPT_NOVAL(     'w',  "--warning"),
	  GETOPT_NOVAL(     'h',  "--help"),
	GETOPT_GENERAL('h', '?',  NULL,               ODF_NO_VALUE),
	  GETOPT_VALUE(     's',  "--source_dir"),
	  GETOPT_VALUE(     'd',  "--dest_dir"),
	GETOPT_END(),
};

int CDECL main(int argc, char *argv[])
{
	char pathbuf[MAX_PATH];
	const char *src_dir = ".";
	const char *dest_dir = NULL;

	GetOptData mgo(argc - 1, argv + 1, _opts);
	for (;;) {
		int i = mgo.GetOpt();
		if (i == -1) break;

		switch (i) {
			case 'v':
				puts("$Revision$");
				return 0;

			case 'C':
				printf("args\tflags\tcommand\treplacement\n");
				for (const CmdStruct *cs = _cmd_structs; cs < endof(_cmd_structs); cs++) {
					char flags;
					switch (cs->value) {
						case 0x200E: case 0x200F: // Implicit BIDI controls
						case 0x202A: case 0x202B: case 0x202C: case 0x202D: case 0x202E: // Explicit BIDI controls
						case 0xA0: // Non breaking space
						case '\n': // Newlines may be added too
						case '{':  // This special
							/* This command may be in the translation when it is not in base */
							flags = 'i';
							break;

						default:
							if (cs->proc == EmitGender) {
								flags = 'g'; // Command needs number of parameters defined by number of genders
							} else if (cs->proc == EmitPlural) {
								flags = 'p'; // Command needs number of parameters defined by plural value
							} else {
								flags = '0'; // Command needs no parameters
							}
					}
					printf("%i\t%c\t\"%s\"\t\"%s\"\n", cs->consumes, flags, cs->cmd, strstr(cs->cmd, "STRING") ? "STRING" : cs->cmd);
				}
				return 0;

			case 'L':
				printf("count\tdescription\n");
				for (const PluralForm *pf = _plural_forms; pf < endof(_plural_forms); pf++) {
					printf("%i\t\"%s\"\n", pf->plural_count, pf->description);
				}
				return 0;

			case 'P':
				printf("name\tflags\tdefault\tdescription\n");
				for (size_t i = 0; i < lengthof(_pragmas); i++) {
					printf("\"%s\"\t%s\t\"%s\"\t\"%s\"\n",
							_pragmas[i][0], _pragmas[i][1], _pragmas[i][2], _pragmas[i][3]);
				}
				return 0;

			case 't':
				_show_todo |= 1;
				break;

			case 'w':
				_show_todo |= 2;
				break;

			case 'h':
				puts(
					"strgen - $Revision$\n"
					" -v | --version    print version information and exit\n"
					" -t | --todo       replace any untranslated strings with '<TODO>'\n"
					" -w | --warning    print a warning for any untranslated strings\n"
					" -h | -? | --help  print this help message and exit\n"
					" -s | --source_dir search for english.txt in the specified directory\n"
					" -d | --dest_dir   put output file in the specified directory, create if needed\n"
					" -export-commands  export all commands and exit\n"
					" -export-plurals   export all plural forms and exit\n"
					" -export-pragmas   export all pragmas and exit\n"
					" Run without parameters and strgen will search for english.txt and parse it,\n"
					" creating strings.h. Passing an argument, strgen will translate that language\n"
					" file using english.txt as a reference and output <language>.lng."
				);
				return 0;

			case 's':
				src_dir = replace_pathsep(mgo.opt);
				break;

			case 'd':
				dest_dir = replace_pathsep(mgo.opt);
				break;

			case -2:
				fprintf(stderr, "Invalid arguments\n");
				return 0;
		}
	}

	if (dest_dir == NULL) dest_dir = src_dir; // if dest_dir is not specified, it equals src_dir

	try {
		/* strgen has two modes of operation. If no (free) arguments are passed
		 * strgen generates strings.h to the destination directory. If it is supplied
		 * with a (free) parameter the program will translate that language to destination
		 * directory. As input english.txt is parsed from the source directory */
		if (mgo.numleft == 0) {
			mkpath(pathbuf, lengthof(pathbuf), src_dir, "english.txt");

			/* parse master file */
			StringData data(TAB_COUNT);
			FileStringReader master_reader(data, pathbuf, true, false);
			master_reader.ParseFile();
			if (_errors != 0) return 1;

			/* write strings.h */
			ottd_mkdir(dest_dir);
			mkpath(pathbuf, lengthof(pathbuf), dest_dir, "strings.h");

			HeaderFileWriter writer(pathbuf);
			writer.WriteHeader(data);
			writer.Finalise(data);
		} else if (mgo.numleft >= 1) {
			char *r;

			mkpath(pathbuf, lengthof(pathbuf), src_dir, "english.txt");

			StringData data(TAB_COUNT);
			/* parse master file and check if target file is correct */
			FileStringReader master_reader(data, pathbuf, true, false);
			master_reader.ParseFile();

			for (int i = 0; i < mgo.numleft; i++) {
				data.FreeTranslation();

				const char *translation = replace_pathsep(mgo.argv[i]);
				const char *file = strrchr(translation, PATHSEPCHAR);
				FileStringReader translation_reader(data, translation, false, file == NULL || strcmp(file + 1, "english.txt") != 0);
				translation_reader.ParseFile(); // target file
				if (_errors != 0) return 1;

				/* get the targetfile, strip any directories and append to destination path */
				r = strrchr(mgo.argv[i], PATHSEPCHAR);
				mkpath(pathbuf, lengthof(pathbuf), dest_dir, (r != NULL) ? &r[1] : mgo.argv[i]);

				/* rename the .txt (input-extension) to .lng */
				r = strrchr(pathbuf, '.');
				if (r == NULL || strcmp(r, ".txt") != 0) r = strchr(pathbuf, '\0');
				ttd_strlcpy(r, ".lng", (size_t)(r - pathbuf));

				LanguageFileWriter writer(pathbuf);
				writer.WriteLang(data);
				writer.Finalise();

				/* if showing warnings, print a summary of the language */
				if ((_show_todo & 2) != 0) {
					fprintf(stdout, "%d warnings and %d errors for %s\n", _warnings, _errors, pathbuf);
				}
			}
		}
	} catch (...) {
		return 2;
	}

	return 0;
}