summaryrefslogtreecommitdiffstats
path: root/tools/updatelang
blob: b67a28400cb78e497113d1df6c4c762f3c6f7354 (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
#!/usr/bin/perl -s -w
#             __________               __   ___.
#   Open      \______   \ ____   ____ |  | _\_ |__   _______  ___
#   Source     |       _//  _ \_/ ___\|  |/ /| __ \ /  _ \  \/  /
#   Jukebox    |    |   (  <_> )  \___|    < | \_\ (  <_> > <  <
#   Firmware   |____|_  /\____/ \___  >__|_ \|___  /\____/__/\_ \
#                     \/            \/     \/    \/            \/
#
# Copyright (C) 2020 Solomon Peachy
#

use utf8;
use File::Basename;

sub trim {
    my ($string) = @_;
    $string =~ s/^\s+//;
    $string =~ s/\s+$//;
    return $string;
}

sub parselangfile {
    my ($filename) = @_;
    my %phrases;
    my @order;
    my %empty = ( #'phrase' => {},
		  #'source' => {},
		  #'dest' => {},
		  #'voice' => {},
		  'notes' => "",
		  'new' => 0
	);
    my %thisphrase = %empty;

    open(FH, "<$filename") || die ("Can't open $filename");
    my @lines = <FH>;
    close(FH);

    my $pos = 'lang';
    my $id = '';
    my @comments;

    foreach my $line (@lines) {
	$line = trim($line);
        if($line =~ /^ *###/) {
	    # Filter out warnings from prior runs
	    next;
        } elsif($line =~ /^ *#/) {
	    push(@comments, "$line\n") if ($pos eq 'lang');
            # comments are ignored!
            next;
        } elsif ($pos eq 'phrase' && $line =~ /^([^:]+): ?(.*)$/) {
	    $thisphrase{$pos}->{$1} = $2;
	    if ($1 eq 'id') {
		push(@order, $2);
		$id = $2;
	    }
	} elsif ($pos ne 'phrase' && $line =~ /^([^:]+): ?\"?([^\"]*)\"?$/) {
	    my @targets = split(',', $1);
	    my $w = $2;

	    foreach (@targets) {
		my $l = trim($_);
		# Convert some obsolete keys
		if ($l eq "swcodec") {
		    $l = "*";
		} elsif ($l eq "lcd_bitmap") {
		    $l = "*";
		} elsif ($l eq "recording_swcodec") {
		    $l = "recording";
#		} elsif ($id =~ /USB_MODE/ && $l =~ /ibassodx/) {
#		    $l = "*";
		}

		$thisphrase{$pos}->{$l} = $w;
	    }
	}
	if ($line eq '</voice>' ||
	    $line eq '</dest>' ||
	    $line eq '</source>' ||
	    $line eq '<phrase>') {
	    $pos = 'phrase';
	} elsif ($line eq '</phrase>') {
	    my %copy = %thisphrase;
	    $phrases{$id} = \%copy;
	    %thisphrase = %empty;
	    $pos = 'lang';
	    $id = '';
	} elsif ($line eq '<source>') {
	    $pos = 'source';
	} elsif ($line eq '<dest>') {
	    $pos = 'dest';
	} elsif ($line eq '<voice>') {
	    $pos = 'voice';
	}
    }
    $phrases{'HEADER'} = \@comments;
    $phrases{'ORDER'} = \@order;
    return %phrases;
}

sub combinetgts {
    my (%tgtmap) = (@_);
    my %strmap;
    my %combined;

    # Reverse-map things
    foreach my $tgt (sort(keys(%tgtmap))) {
	next if ($tgt eq '*');  # Do not combine anything with fallback
	if (defined($strmap{$tgtmap{$tgt}})) {
	    $strmap{$tgtmap{$tgt}} .= ",$tgt";
	} else {
	    $strmap{$tgtmap{$tgt}} = "$tgt";
	}
    }

    # Copy over default/fallback as it was skipped
    $combined{'*'} = $tgtmap{'*'};

    foreach my $str (keys(%strmap)) {
	$combined{$strmap{$str}} = $str;
    }

    return %combined;
}

##################

if($#ARGV != 2) {
    print "Usage: updatelang <english.lang> <otherlang> <outfile|->\n";
    exit;
}

# Parse master file
my %english = parselangfile($ARGV[0]);
my @englishorder = @{$english{'ORDER'}};

# Parse secondary file
my %lang = parselangfile($ARGV[1]);
my @langorder = @{$lang{'ORDER'}};
my @langheader = @{$lang{'HEADER'}};

# Clean up
delete $english{'ORDER'};
delete $english{'HEADER'};
delete $lang{'ORDER'};
delete $lang{'HEADER'};

# Extract language names
my @tmp = split(/\./, basename($ARGV[0]));
my $f1 = $tmp[0];
@tmp = split(/\./, basename($ARGV[1]));
my $f2 = $tmp[0];
undef @tmp;

# Read in ignore list
my $igname = dirname($0) . "/langignorelist.txt";
open (FH, "<$igname") || die ("Can't open $igname!");
my @ignorelist = <FH>;
close (FH);
sub not_ignorelist {
    my ($key) = @_;
    foreach (@ignorelist) {
	chomp;
	if ($_ eq $key) {
	    return 0;
	}
    }
    return 1;
}
undef $igname;

# Do we care about notes?
my $printnotes = 1;
my $ignoredups = 0;

if ($f1 eq $f2) {
    # Ignore all notes for master language
    $printnotes = 0;
}

if (index($f2, $f1) > -1) {
    # Ignore duplicates for sub-languages
    $ignoredups = 1;
}

# work out the missing phrases
my %missing;
my @missingorder;

foreach (@englishorder) {
    $missing{$_} = 1;
}
foreach (@langorder) {
    if (!defined($english{$_})) {
	delete($lang{$_});
#	print "#!! '$_' no longer needed\n";
	next;
    }
    delete $missing{$_};
}
foreach (@englishorder) {
    push(@missingorder, $_) if defined($missing{$_});
}
# And add them to the phrase list.
foreach (@missingorder) {
#    print "#!! '$_' missing\n";
    push(@langorder, $_);
    $lang{$_} = $english{$_};
    $lang{$_}{'notes'} .= "### This phrase is missing entirely, copying from english!\n";
    $lang{$_}{'new'} = 1;
}
undef @missingorder;
undef %missing;

# Sanity-check a few things
foreach my $id (@langorder) {
    if (!defined($english{$id})) {
	next;
    }
    my %ep = %{$english{$id}{'phrase'}};
    my %lp = %{$lang{$id}{'phrase'}};

    if ($lp{'desc'} ne $ep{'desc'} || $ep{'desc'} eq 'deprecated') {
	if ($ep{'desc'} eq 'deprecated') {
	    # Nuke all deprecated targets; just copy from English
#	    print "#!! '$id' deprecated, deleting\n";
	    $lang{$id} = $english{$id};
	} else {
	    $lang{$id}{'notes'} .= "### The 'desc' field for '$id' differs from the english!\n### the previously used desc is commented below:\n### desc: $lp{desc}\n";
	    $lang{$id}{'phrase'}{'desc'} = 	$english{$id}{'phrase'}{'desc'};
	    #	print "#!! '$id' changed description\n";
	}
    }

    if (!defined($ep{'user'}) || length($ep{'user'}) == 0) {
	$lp{'user'} = 'core';
    }

    if (!defined($lp{'user'}) || $lp{'user'} ne $ep{'user'}) {
	$lang{$id}{'notes'} .= "### The 'user' field for '$id' differs from the english!\n### the previously used desc is commented below:\n### desc: $lp{user}\n";
	if (!defined($lp{'user'}) || length($lp{'user'}) == 0) {
	    $lp{'user'} = $ep{'user'};
	}
	$lang{$id}{'phrase'}{'user'} = $english{$id}{'phrase'}{'user'};
#	print "#!! '$id' changed user\n";
    }
}

# Check sources
foreach my $id (@langorder) {
    if (!defined($english{$id})) {
	next;
    }
    my %ep = %{$english{$id}{'source'}};
    my %lp;

    if (defined($lang{$id}{'source'})) {
	%lp = %{$lang{$id}{'source'}};
    } else {
	%lp = ();
    }

    foreach my $tgt (keys(%lp)) {
	if (!defined($ep{$tgt})) {
	    # Delete any targets that have been nuked in master
	    delete($lang{$id}{'source'}{$tgt});
	}
    }
    foreach my $tgt (keys(%ep)) {
	if (!defined($lp{$tgt})) {
	    # If it doesn't exist in the language, copy it from English
	    if ($ep{$tgt} ne 'none' && $ep{$tgt} ne '' ) {
		$lang{$id}{'notes'} .= "### The <source> section for '$id:$tgt' is missing! Copying from english!\n";
#		print "#!! '$id:$tgt' source missing\n";
	    }
	    $lang{$id}{'source'}{$tgt} = $english{$id}{'source'}{$tgt};
	} elsif ($lp{$tgt} ne $ep{$tgt}) {
	    # If the source string differs, complain, and copy from English
	    $lang{$id}{'notes'} .= "### The <source> section for '$id:$tgt' differs from the english!\n";
	    $lang{$id}{'notes'} .= "### the previously used one is commented below:\n";
            $lang{$id}{'notes'} .= "### $english{$id}{source}{$tgt}\n";
#	    print "#!! '$id:$tgt' source changed ('$lp{$tgt}' vs '$ep{$tgt}')\n";
	    $lang{$id}{'source'}{$tgt} = $english{$id}{'source'}{$tgt};
	}
    }
}

# Check dests
foreach my $id (@langorder) {
    if (!defined($english{$id})) {
	next;
    }
    my %ep = %{$english{$id}{'dest'}};
    my %lp;

    if (defined($lang{$id}{'dest'})) {
	%lp = %{$lang{$id}{'dest'}};
    } else {
	%lp = ();
    }

    foreach my $tgt (keys(%lp)) {
	if (!defined($ep{$tgt})) {
	    # Delete any targets that have been nuked in master
	    delete($lang{$id}{'dest'}{$tgt});
	}
    }
    foreach my $tgt (keys(%ep)) {
	if (!defined($lp{$tgt}) || ($lp{$tgt} eq 'none')) {
	    # If it doesn't exist in the language, copy it from English
	    if ($ep{$tgt} ne 'none' && $ep{$tgt} ne '' ) {
		$lang{$id}{'notes'} .= "### The <dest> section for '$id:$tgt' is missing! Copying from english!\n";
#		print "#!! '$id:$tgt' dest missing\n";
	    }
	    $lang{$id}{'dest'}{$tgt} = $english{$id}{'dest'}{$tgt};
	} elsif ($lp{$tgt} ne $ep{$tgt}) {
	    # If the source string differs, complain, and copy from English
	    if ($lp{$tgt} eq '' && $ep{$tgt} ne '') {
		$lang{$id}{'notes'} .= "### The <dest> section for '$id:$tgt' is blank! Copying from english!\n";
#		print "#!! '$id:$tgt' dest is blank ('$lp{$tgt}' vs '$ep{$tgt}')\n";
		$lang{$id}{'dest'}{$tgt} = $english{$id}{'dest'}{$tgt};
	    } elsif ($lp{$tgt} ne '' && $ep{$tgt} eq '') {
		# It should be kept blank!
		$lang{$id}{'notes'} .= "### The <dest> section for '$id:$tgt' is not blank!\n";
		$lang{$id}{'notes'} .= "### the previously used one is commented below:\n";
		$lang{$id}{'notes'} .= "### $english{$id}{dest}{$tgt}\n";
#		print "#!! '$id:$tgt' dest not blank ('$lp{$tgt}' vs '$ep{$tgt}')\n";
		$lang{$id}{'dest'}{$tgt} = $english{$id}{'dest'}{$tgt};
	    }
	} elsif ($lp{$tgt} ne 'none' && $lp{$tgt} ne '' && not_ignorelist($id) && !$lang{$id}{'new'} && !$ignoredups) {
	    $lang{$id}{'notes'} .= "### The <dest> section for '$id:$tgt' is identical to english!\n";
#	    print "#!! '$id:$tgt' dest identical ('$lp{$tgt}')\n";
	}
    }
}

# Check voices
foreach my $id (@langorder) {
    if (!defined($english{$id})) {
	next;
    }
    my %ep = %{$english{$id}{'voice'}};
    my %lp;

    if (defined($lang{$id}{'voice'})) {
	%lp = %{$lang{$id}{'voice'}};
    } else {
	%lp = ();
    }

    foreach my $tgt (keys(%lp)) {
	if (!defined($ep{$tgt})) {
	    # Delete any targets that have been nuked in master
	    delete($lang{$id}{'voice'}{$tgt});
	}
    }
    foreach my $tgt (keys(%ep)) {
	if (!defined($lp{$tgt}) || ($lp{$tgt} eq 'none')) {
	    # If it doesn't exist in the language, copy it from English
	    if ($ep{$tgt} ne 'none' && $ep{$tgt} ne '' ) {
		$lang{$id}{'notes'} .= "### The <voice> section for '$id:$tgt' is missing! Copying from english!\n";
#		print "#!! '$id:$tgt' voice missing\n";
	    }
	    $lang{$id}{'voice'}{$tgt} = $english{$id}{'voice'}{$tgt};
	} elsif ($lp{$tgt} ne $ep{$tgt}) {
	    if ($lp{$tgt} eq '' && $ep{$tgt} ne '') {
		# If the lang voice string is blank, complain, and copy from English
#		print "#!! '$id:$tgt' voice is blank ('$lp{$tgt}' vs '$ep{$tgt}')\n";
		if ($lang{$id}{'dest'}{$tgt} ne '' &&
		    $lang{$id}{'dest'}{$tgt} ne $english{$id}{'dest'}{$tgt}) {
		    $lang{$id}{'notes'} .= "### The <voice> section for '$id:$tgt' is blank! Copying from translated <dest>!\n";
		    $lang{$id}{'voice'}{$tgt} = $lang{$id}{'dest'}{$tgt};
		    if ($lang{$id}{'voice'}{$tgt} =~ /%/) {
	                # If it has suspicious characters that are not normally voiced..
		        $lang{$id}{'notes'} .= "### The <voice> section for '$id:$tgt' has some suspicious characters, please double-check!\n";
			#print "#!! '$id:$tgt' suspicious characters\n";
		    }
		} else {
		    $lang{$id}{'notes'} .= "### The <voice> section for '$id:$tgt' is blank! Copying from english!\n";

		    $lang{$id}{'voice'}{$tgt} = $english{$id}{'voice'}{$tgt};
		}
	    } elsif ($lp{$tgt} ne '' && $ep{$tgt} eq '') {
		if ($id ne 'VOICE_NUMERIC_TENS_SWAP_SEPARATOR') {
		    # If it's not blank, clear it and complain!
		    $lang{$id}{'notes'} .= "### The <voice> section for '$id:$tgt' is not blank!\n";
		    $lang{$id}{'notes'} .= "### the previously used one is commented below:\n";
		    $lang{$id}{'notes'} .= "### $english{$id}{voice}{$tgt}\n";
		    #		print "#!! '$id:$tgt' voice not blank ('$lp{$tgt}' vs '$ep{$tgt}')\n";
		    $lang{$id}{'voice'}{$tgt} = $english{$id}{'voice'}{$tgt};
		}
	    }
	} elsif ($lp{$tgt} ne 'none' && $lp{$tgt} ne '' && not_ignorelist($id) && !$lang{$id}{'new'} && !$ignoredups) {
#	    print "#!! '$id:$tgt' voice identical ('$lp{$tgt}')\n";
	    if ($lang{$id}{'dest'}{$tgt} ne '' &&
		$lang{$id}{'dest'}{$tgt} ne $english{$id}{'dest'}{$tgt}) {
		$lang{$id}{'notes'} .= "### The <voice> section for '$id:$tgt' is identical to english, copying translated <dest>\n";
		    $lang{$id}{'voice'}{$tgt} = $lang{$id}{'dest'}{$tgt};
	    } else {
		$lang{$id}{'notes'} .= "### The <voice> section for '$id:$tgt' is identical to english!\n";
	    }
	}
        if ($lp{$tgt} =~ /%/) {
            # If it has suspicious characters that are not normally voiced..
            $lang{$id}{'notes'} .= "### The <voice> section for '$id:$tgt' has some suspicious characters, please double-check!\n";
#            print "#!! '$id:$tgt' suspicious characters\n";
        }
    }
}

########## Write new language file
my $fh;
if ($ARGV[2] ne '-') {
    open(FH, ">$ARGV[2]") || die ("Can't open $ARGV[2]");
    $fh = *FH;
} else {
    $fh = *STDOUT;
}

foreach (@langheader) {
    print $fh $_;
}

my @finalorder = @langorder;  # TODO make configurable vs @englishorder
foreach my $id (@finalorder) {
    if (!defined($english{$id})) {
	next;
    }
    my %lp;

    # phrase
    %lp = %{$lang{$id}{'phrase'}};

    # Drop all deprecated phrases?
#    next if ($lp{'desc'} eq 'deprecated');

    if (length($lang{$id}{'notes'}) && $printnotes) {
	print $fh "$lang{$id}{notes}";
    }
    print $fh "<phrase>\n";
    print $fh "  id: $lp{id}\n";
    if ($lp{'desc'} ne '') {
	print $fh "  desc: $lp{desc}\n";
    } else {
	print $fh "  desc:\n";
    }
    print $fh "  user: $lp{user}\n";

    # source
    %lp = combinetgts(%{$lang{$id}{'source'}});
    print $fh "  <source>\n";
    foreach my $tgt (sort(keys(%lp))) {
	if ($lp{$tgt} eq 'none') {
	    print $fh "    $tgt: $lp{$tgt}\n";
	} else {
	    print $fh "    $tgt: \"$lp{$tgt}\"\n";
	}
    }
    print $fh "  </source>\n";

    # dest
    %lp = combinetgts(%{$lang{$id}{'dest'}});
    print $fh "  <dest>\n";
    foreach my $tgt (sort(keys(%lp))) {
	if ($lp{$tgt} eq 'none') {
	    print $fh "    $tgt: $lp{$tgt}\n";
	} else {
	    print $fh "    $tgt: \"$lp{$tgt}\"\n";
	}
    }
    print $fh "  </dest>\n";

    # voice
    %lp = combinetgts(%{$lang{$id}{'voice'}});
    print $fh "  <voice>\n";
    foreach my $tgt (sort(keys(%lp))) {
	if ($lp{$tgt} eq 'none') {
	    print $fh "    $tgt: $lp{$tgt}\n";
	} else {
	    print $fh "    $tgt: \"$lp{$tgt}\"\n";
	}
    }
    print $fh "  </voice>\n";

    # FiN
    print $fh "</phrase>\n";
}

if ($ARGV[2] ne '-') {
    close(FH);
}