summaryrefslogtreecommitdiffstats
path: root/tools/genlang
blob: 010a2b1303b283ac7ef13ca3bff25d122fa038c8 (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
#!/usr/bin/perl -s
#             __________               __   ___.
#   Open      \______   \ ____   ____ |  | _\_ |__   _______  ___
#   Source     |       _//  _ \_/ ___\|  |/ /| __ \ /  _ \  \/  /
#   Jukebox    |    |   (  <_> )  \___|    < | \_\ (  <_> > <  <
#   Firmware   |____|_  /\____/ \___  >__|_ \|___  /\____/__/\_ \
#                     \/            \/     \/    \/            \/
# $Id$
#
# Copyright (C) 2006 - 2007 by Daniel Stenberg
#

# binary version for the binary lang file
my $langversion = 4; # 3 was the latest one used in the v1 format

# A note for future users and readers: The original v1 language system allowed
# the build to create and use a different language than english built-in. We
# removed that feature from our build-system, but the build scripts still had
# the ability. But, starting now, this ability is no longer provided since I
# figured it was boring and unnecessary to write support for now since we
# don't use it anymore.

if(!$ARGV[0]) {
    print <<MOO
Usage: genlang [options] <langv2 file>

 -p=<prefix>
    Make the tool create a [prefix].c and [prefix].h file.

 -b=<outfile>
    Make the tool create a binary language (.lng) file named [outfile].
    The use of this option requires that you also use -e, -t and -i.

 -u
    Update language file. Given the translated file and the most recent english
    file, you\'ll get an updated version sent to stdout. Suitable action to do
    when you intend to update a translation.

 -e=<english lang file>
    Point out the english (original source) file, to use that as master
    language template. Used in combination with -b or -u.

 -t=<target>
    Specify which target you want the translations/phrases for. Required when
    -b or -p is used.

    The target can in fact be specified as numerous different strings,
    separated with colons. This will make genlang to use all the specified
    strings when searching for a matching phrase.

 -i=<target id>
    The target id number, needed for -b.

 -o
    Voice mode output. Outputs all id: and voice: lines for the given target!

 -v
    Enables verbose (debug) output.
MOO
;
    exit;
}

# How update works:
#
# 1) scan the english file, keep the whole <phrase> for each phrase.
# 2) read the translated file, for each end of phrase, compare:
#  A) all source strings, if there's any change there should be a comment about
#     it output
#  B) the desc fields
#
# 3) output the phrase with the comments from above
# 4) check which phrases that the translated version didn't have, and spit out
#    the english version of those
#

my $prefix = $p;
my $binary = $b;
my $update = $u;

my $english = $e;
my $voiceout = $o;

my $check = ($binary?1:0) + ($prefix?1:0) + ($update?1:0) + ($voiceout?1:0);

if($check > 1) {
    print "Please use only one of -p, -u, -o and -b\n";
    exit;
}
if(!$check) {
    print "Please use at least one of -p, -u, -o and -b\n";
    exit;
}

if(($binary || $update || $voiceout) && !$english) {
    print "Please use -e too when you use -b, -o or -u\n";
    exit;
}

my $target_id = $i;
if($binary && !$target_id) {
    print "Please specify a target id number (with -i)!\n";
    exit;
}

my $target = $t;
if(!$target && !$update) {
    print "Please specify a target (with -t)!\n";
    exit;
}
my $verbose=$v;

my %id; # string to num hash
my @idnum; # num to string array

my %source; # id string to source phrase hash
my %dest; # id string to dest phrase hash
my %voice; # id string to voice phrase hash

my $input = $ARGV[0];

my @m;
my $m="blank";

sub match {
    my ($string, $pattern)=@_;

    $pattern =~ s/\*/.?*/g;
    $pattern =~ s/\?/./g;

    return ($string =~ /^$pattern\z/);
}

sub blank {
    # nothing to do
}

my %head;
sub header {
    my ($full, $n, $v)=@_;
    $head{$n}=$v;
}

my %phrase;
sub phrase {
    my ($full, $n, $v)=@_;
    $phrase{$n}=$v;
}

sub parsetarget {
    my ($debug, $strref, $full, $n, $v)=@_;
    my $string;
    my @all= split(" *, *", $n);
    my $test;
    for $test (@all) {
#        print "TEST ($debug) $target for $test\n";
        for my $part (split(":", $target)) {
            if(match($part, $test)) {
                $string = $v;
#                print "MATCH: $test => $v\n";
                $$strref = $string;
                return $string;
            }
        }
    }
}

my $src;
sub source {
    parsetarget("src", \$src, @_);
}

my $dest;
sub dest {
    parsetarget("dest", \$dest, @_);
}

my $voice;
sub voice {
    parsetarget("voice", \$voice, @_);
}

my %idmap;
my %english;
if($english) {
    # For the cases where the english file needs to be scanned/read, we do
    # it before we read the translated file. For -b it isn't necessary, but for
    # -u it is convenient.

    my $idnum=0; # start with a true number
    my $vidnum=0x8000; # first voice id
    open(ENG, "<$english") || die "can't open $english";
    my @phrase;
    my $id;
    my $maybeid;
    my $withindest;
    while(<ENG>) {

        # get rid of DOS newlines
        $_ =~ s/\r//g;

        if($_ =~ /^ *\<phrase\>/) {
            # this is the start of a phrase
        }
        elsif($_ =~ /^ *\<\/phrase\>/) {

            # if id is something, when we count and store this phrase
            if($id) {
                # voice-only entries get a difference range
                if($id =~ /^VOICE_/) {
                    # Assign an ID number to this entry
                    $idmap{$id}=$vidnum;
                    $vidnum++;
                }
                else {
                    # Assign an ID number to this entry
                    $idmap{$id}=$idnum;
                    $idnum++;
   #                 print STDERR "DEST: bumped idnum to $idnum\n";
                }

                # this is the end of a phrase, add it to the english hash
                $english{$id}=join("", @phrase);
            }
            undef @phrase;
            $id="";
        }
        elsif($_ ne "\n") {
            # gather everything related to this phrase
            push @phrase, $_;
            if($_ =~ /^ *\<dest\>/i) {
                $withindest=1;
                $deststr="";
            }
            elsif($withindest && ($_ =~ /^ *\<\/dest\>/i)) {
                $withindest=0;

                if($update || ($deststr && ($deststr !~ /^none\z/i))) {
                    # we unconditionally always use all IDs when the "update"
                    # feature is used
                    $id = $maybeid;
   #                 print STDERR "DEST: use this id $id\n";
                }
                else {
   #                 print "skip $maybeid for $name\n";
                }
            }
            elsif($withindest && ($_ =~ / *([^:]+): *(.*)/)) {
                my ($name, $val)=($1, $2);
                $dest=""; # in case it is left untouched for when the
                # model name isn't "our"
                dest($_, $name, $val);

                if($dest) {
                    # Store the current dest string. If this target matches
                    # multiple strings, it will get updated several times.
                    $deststr = $dest;
                }
            }
        }

        if($_ =~ /^ *id: ([^ \t\n]+)/i) {
            $maybeid=$1;
        }
    }
    close(ENG);
}

# a function that compares the english phrase with the translated one.
# compare source strings and desc

# Then output the updated version!
sub compare {
    my ($idstr, $engref, $locref)=@_;
    my ($edesc, $ldesc);
    my ($esource, $lsource);
    my $mode=0;
    
    for my $l (@$engref) {
        if($l =~ /^ *#/) {
            # comment
            next;
        }
        if($l =~ /^ *desc: (.*)/) {
            $edesc=$1;
        }
        elsif($l =~ / *\<source\>/i) {
            $mode=1;
        }
        elsif($mode) {
            if($l =~ / *\<\/source\>/i) {
                last;
            }
            $esource .= "$l\n";
        }
    }

    my @show;
    my @source;

    $mode = 0;
    for my $l (@$locref) {
        if($l =~ /^ *desc: (.*)/) {
            $ldesc=$1;
            if($edesc ne $ldesc) {
                $l = "### The 'desc' field differs from the english!\n### the previously used desc is commented below:\n### desc: $ldesc\n  desc: $edesc\n";
            }
            push @show, $l;
        }
        elsif($l =~ / *\<source\>/i) {
            $mode=1;
            push @show, $l;
        }
        elsif($mode) {
            if($l =~ / *\<\/source\>/i) {
                $mode = 0;
                print @show;
                if($esource ne $lsource) {
                    print "### The <source> section differs from the english!\n",
                    "### the previously used one is commented below:\n";
                    for(split("\n", $lsource)) {
                        print "### $_\n";
                    }
                    print $esource;
                }
                else {
                    print $lsource;
                }
                undef @show; # start over

                push @show, $l;
            }
            else {
                $lsource .= "$l";
            }
        }
        else {
            push @show, $l;
        }
    }


    print @show;
}

my $idcount;        # counter for lang ID numbers
my $voiceid=0x8000; # counter for voice-only ID numbers

#
# Now start the scanning of the selected language string
#

open(LANG, "<$input") || die "couldn't read language file named $input\n";
my @phrase;
while(<LANG>) {

    $line++;

    # get rid of DOS newlines
    $_ =~ s/\r//g;

    if($_ =~ /^( *\#|[ \t\n\r]*\z)/) {
        # comment or empty line
        next;
    }

    my $ll = $_;

    # print "M: $m\n";

    push @phrase, $ll;

    # this is an XML-lookalike tag
    if (/^(<|[^\"<]+<)([^>]*)>/) {
        my $part = $2;
        # print "P: $part\n";

        if($part =~ /^\//) {
            # this was a closing tag

            if($part eq "/phrase") {
                # closing the phrase

                my $idstr = $phrase{'id'};
                my $idnum;

                if($binary && !$english{$idstr}) {
                    # $idstr doesn't exist for english, skip it\n";
                }
                elsif($dest =~ /^none\z/i) {
                    # "none" as dest (without quotes) means that this entire
                    # phrase is to be ignored
                }
                elsif(!$update) {
                    # we don't do the fully detailed analysis when we "update"
                    # since we don't do it for a particular target etc

                    # allow the keyword 'deprecated' to be used on dest and
                    # voice strings to mark that as deprecated. It will then
                    # be replaced with "".

                    $dest =~ s/^deprecate(|d)\z/\"\"/i;
                    $voice =~ s/^deprecate(|d)\z/\"\"/i;

                    # basic syntax error alerts, if there are no quotes we
                    # will assume an empty string was intended
                    if($dest !~ /^\"/) {
                        print STDERR "Warning: dest before $input line $line lacks quotes ($dest)!\n";
                        $dest='""';
                    }
                    if($src !~ /^\"/) {
                        print STDERR "Warning: source before $input line $line lacks quotes ($src)!\n";
                        $src='""';
                    }
                    if($voice !~ /^\"/) {
                        print STDERR "Warning: voice before $input line $line lacks quotes ($voice)!\n";
                        $voice='""';
                    }

                    # Use the ID name to figure out which id number range we
                    # should use for this phrase. Voice-only strings are
                    # separated.

                    if($idstr =~ /^VOICE/) {
                        $idnum = $voiceid++;
                    }
                    else {
                        $idnum = $idcount++;
                    }
                    
                    $id{$idstr} = $idnum;
                    $idnum[$idnum]=$idstr;
                    
                    $source{$idstr}=$src;
                    $dest{$idstr}=$dest;
                    $voice{$idstr}=$voice;
                    
                    if($verbose) {
                        print "id: $phrase{id} ($idnum)\n";
                        print "source: $src\n";
                        print "dest: $dest\n";
                        print "voice: $voice\n";
                    }

                    undef $src;
                    undef $dest;
                    undef $voice;
                    undef %phrase;
                }

                if($update) {
                    my $e = $english{$idstr};

                    if($e) {
                        # compare original english with this!
                        my @eng = split("\n", $english{$idstr});

                        compare($idstr, \@eng, \@phrase);

                        $english{$idstr}=""; # clear it
                    }
                    else {
                        print "### $idstr: The phrase is not used. Skipped\n";
                    }
                }
                undef @phrase;

            } # end of </phrase>

            # starts with a slash, this _ends_ this section
            $m = pop @m; # get back old value, the previous level's tag
            next;
        } # end of tag close

        # This is an opening (sub) tag

        push @m, $m; # store old value
        $m = $part;
        next;
    }

    if(/^ *([^:]+): *(.*)/) {
        my ($name, $val)=($1, $2);
        &$m($_, $name, $val);
    }
}
close(LANG);

if($update) {
    my $any=0;
    for(keys %english) {
        if($english{$_}) {
            print "###\n",
            "### This phrase below was not present in the translated file\n",
            "<phrase>\n";
            print $english{$_};
            print "</phrase>\n";
        }
    }
}

if($prefix) {
    # We create a .c and .h file

    open(HFILE, ">$prefix.h") ||
        die "couldn't create file $prefix.h\n";
    open(CFILE, ">$prefix.c") ||
        die "couldn't create file $prefix.c\n";        

    print HFILE <<MOO
/* This file was automatically generated using genlang */
/*
 * The str() macro/functions is how to access strings that might be
 * translated. Use it like str(MACRO) and expect a string to be
 * returned!
 */
#define str(x) language_strings[x]

/* this is the array for holding the string pointers.
   It will be initialized at runtime. */
extern unsigned char *language_strings[];
/* this contains the concatenation of all strings, separated by \\0 chars */
extern const unsigned char language_builtin[];

/* The enum below contains all available strings */
enum \{
MOO
    ;

    print CFILE <<MOO
/* This file was automaticly generated using genlang, the strings come
   from "$input" */
   
#include "$prefix.h"

unsigned char *language_strings[LANG_LAST_INDEX_IN_ARRAY];
const unsigned char language_builtin[] =
MOO
;

    # Output the ID names for the enum in the header file
    my $i;
    for $i (1 .. $idcount) {
        my $name=$idnum[$i - 1]; # get the ID name
        
        $name =~ s/\"//g; # cut off the quotes
        
        printf HFILE ("    %s, /* %d */\n", $name, $i-1);
    }

# Output separation marker for last string ID and the upcoming voice IDs

    print HFILE <<MOO
    LANG_LAST_INDEX_IN_ARRAY, /* this is not a string, this is a marker */
    /* --- below this follows voice-only strings --- */
    VOICEONLY_DELIMITER = 0x8000,
MOO
    ;

# Output the ID names for the enum in the header file
    for $i (0x8000 .. ($voiceid-1)) {
        my $name=$idnum[$i]; # get the ID name
        
        $name =~ s/\"//g; # cut off the quotes
        
        printf HFILE ("    %s,\n", $name);
    }

    # Output end of enum
    print HFILE "\n};\n/* end of generated enum list */\n";

    # Output the target phrases for the source file
    for $i (1 .. $idcount) {
        my $name=$idnum[$i - 1]; # get the ID
        my $dest = $dest{$name}; # get the destination phrase
        
        $dest =~ s:\"$:\\0\":; # insert a \0 before the second quote

        if(!$dest) {
            # this is just to be on the safe side
            $dest = '"\0"';
        }

        printf CFILE ("    %s\n", $dest);
    }

# Output end of string chunk
    print CFILE <<MOO
;
/* end of generated string list */
MOO
;

    close(HFILE);
    close(CFILE);
} # end of the c/h file generation
elsif($binary) {
    # Creation of a binary lang file was requested

    # We must first scan the english file to get the correct order of the id
    # numbers used there, as that is what sets the id order for all language
    # files. The english file is scanned before the translated file was
    # scanned.

    open(OUTF, ">$binary") or die "Can't create $binary";
    binmode OUTF;
    printf OUTF ("\x1a%c%c", $langversion, $target_id); # magic lang file header

    # loop over the target phrases
    for $i (1 .. $idcount) {
        my $name=$idnum[$i - 1]; # get the ID
        my $dest = $dest{$name}; # get the destination phrase

        if($dest) {
            $dest =~ s/^\"(.*)\"\s*$/$1/g; # cut off quotes

            # Now, make sure we get the number from the english sort order:
            $idnum = $idmap{$name};

            printf OUTF ("%c%c%s\x00", ($idnum>>8), ($idnum&0xff), $dest);
        }
    }
}
elsif($voiceout) {
    # voice output requested, display id: and voice: strings in a v1-like
    # fashion

    my @engl;

    # This loops over the strings in the translated language file order
    my @ids = ((0 .. ($idcount-1)));
    push @ids, (0x8000 .. ($voiceid-1));

    #for my $id (@ids) {
    #    print "$id\n";
    #}

    for $i (@ids) {
        my $name=$idnum[$i]; # get the ID
        my $dest = $voice{$name}; # get the destination voice string

        if($dest) {
            $dest =~ s/^\"(.*)\"\s*$/$1/g; # cut off quotes

            # Now, make sure we get the number from the english sort order:
            $idnum = $idmap{$name};

            $engl[$idnum] = $i;

           # print "Input index $i output index $idnum\n";

        }
    }
    for my $i (@ids) {

        my $o = $engl[$i];

        my $name=$idnum[$o]; # get the ID
        my $dest = $voice{$name}; # get the destination voice string
        
        print "#$i\nid: $name\nvoice: $dest\n";
    }
    
}


if($verbose) {
    printf("%d ID strings scanned\n", $idcount);

    print "* head *\n";
    for(keys %head) {
        printf "$_: %s\n", $head{$_};
    }
}