summaryrefslogtreecommitdiff
path: root/Master/tlpkg/tlperl/lib/charnames.pm
blob: ce0938bee91a908ae59710a35e8716eb080efa34 (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
package charnames;
use strict;
use warnings;
use File::Spec;
our $VERSION = '1.07';

use bytes ();		# for $bytes::hint_bits

my %alias1 = (
		# Icky 3.2 names with parentheses.
		'LINE FEED'		=> 'LINE FEED (LF)',
		'FORM FEED'		=> 'FORM FEED (FF)',
		'CARRIAGE RETURN'	=> 'CARRIAGE RETURN (CR)',
		'NEXT LINE'		=> 'NEXT LINE (NEL)',
		# Convenience.
		'LF'			=> 'LINE FEED (LF)',
		'FF'			=> 'FORM FEED (FF)',
		'CR'			=> 'CARRIAGE RETURN (CR)',
		'NEL'			=> 'NEXT LINE (NEL)',
	        # More convenience.  For futher convencience,
	        # it is suggested some way using using the NamesList
		# aliases is implemented.
	        'ZWNJ'			=> 'ZERO WIDTH NON-JOINER',
	        'ZWJ'			=> 'ZERO WIDTH JOINER',
		'BOM'			=> 'BYTE ORDER MARK',
	    );

my %alias2 = (
		# Pre-3.2 compatibility (only for the first 256 characters).
		'HORIZONTAL TABULATION'	=> 'CHARACTER TABULATION',
		'VERTICAL TABULATION'	=> 'LINE TABULATION',
		'FILE SEPARATOR'	=> 'INFORMATION SEPARATOR FOUR',
		'GROUP SEPARATOR'	=> 'INFORMATION SEPARATOR THREE',
		'RECORD SEPARATOR'	=> 'INFORMATION SEPARATOR TWO',
		'UNIT SEPARATOR'	=> 'INFORMATION SEPARATOR ONE',
		'PARTIAL LINE DOWN'	=> 'PARTIAL LINE FORWARD',
		'PARTIAL LINE UP'	=> 'PARTIAL LINE BACKWARD',
	    );

my %alias3 = (
		# User defined aliasses. Even more convenient :)
	    );
my $txt;

sub croak
{
  require Carp; goto &Carp::croak;
} # croak

sub carp
{
  require Carp; goto &Carp::carp;
} # carp

sub alias (@)
{
  @_ or return %alias3;
  my $alias = ref $_[0] ? $_[0] : { @_ };
  @alias3{keys %$alias} = values %$alias;
} # alias

sub alias_file ($)
{
  my ($arg, $file) = @_;
  if (-f $arg && File::Spec->file_name_is_absolute ($arg)) {
    $file = $arg;
  }
  elsif ($arg =~ m/^\w+$/) {
    $file = "unicore/${arg}_alias.pl";
  }
  else {
    croak "Charnames alias files can only have identifier characters";
  }
  if (my @alias = do $file) {
    @alias == 1 && !defined $alias[0] and
      croak "$file cannot be used as alias file for charnames";
    @alias % 2 and
      croak "$file did not return a (valid) list of alias pairs";
    alias (@alias);
    return (1);
  }
  0;
} # alias_file

# This is not optimized in any way yet
sub charnames
{
  my $name = shift;

  if (exists $alias1{$name}) {
    $name = $alias1{$name};
  }
  elsif (exists $alias2{$name}) {
    require warnings;
    warnings::warnif('deprecated', qq{Unicode character name "$name" is deprecated, use "$alias2{$name}" instead});
    $name = $alias2{$name};
  }
  elsif (exists $alias3{$name}) {
    $name = $alias3{$name};
  }

  my $ord;
  my @off;
  my $fname;

  if ($name eq "BYTE ORDER MARK") {
    $fname = $name;
    $ord = 0xFEFF;
  } else {
    ## Suck in the code/name list as a big string.
    ## Lines look like:
    ##     "0052\t\tLATIN CAPITAL LETTER R\n"
    $txt = do "unicore/Name.pl" unless $txt;

    ## @off will hold the index into the code/name string of the start and
    ## end of the name as we find it.

    ## If :full, look for the name exactly
    if ($^H{charnames_full} and $txt =~ /\t\t\Q$name\E$/m) {
      @off = ($-[0], $+[0]);
    }

    ## If we didn't get above, and :short allowed, look for the short name.
    ## The short name is like "greek:Sigma"
    unless (@off) {
      if ($^H{charnames_short} and $name =~ /^(.+?):(.+)/s) {
	my ($script, $cname) = ($1, $2);
	my $case = $cname =~ /[[:upper:]]/ ? "CAPITAL" : "SMALL";
	if ($txt =~ m/\t\t\U$script\E (?:$case )?LETTER \U\Q$cname\E$/m) {
	  @off = ($-[0], $+[0]);
	}
      }
    }

    ## If we still don't have it, check for the name among the loaded
    ## scripts.
    if (not @off) {
      my $case = $name =~ /[[:upper:]]/ ? "CAPITAL" : "SMALL";
      for my $script (@{$^H{charnames_scripts}}) {
	if ($txt =~ m/\t\t$script (?:$case )?LETTER \U\Q$name\E$/m) {
	  @off = ($-[0], $+[0]);
	  last;
	}
      }
    }

    ## If we don't have it by now, give up.
    unless (@off) {
      carp "Unknown charname '$name'";
      return "\x{FFFD}";
    }

    ##
    ## Now know where in the string the name starts.
    ## The code, in hex, is before that.
    ##
    ## The code can be 4-6 characters long, so we've got to sort of
    ## go look for it, just after the newline that comes before $off[0].
    ##
    ## This would be much easier if unicore/Name.pl had info in
    ## a name/code order, instead of code/name order.
    ##
    ## The +1 after the rindex() is to skip past the newline we're finding,
    ## or, if the rindex() fails, to put us to an offset of zero.
    ##
    my $hexstart = rindex($txt, "\n", $off[0]) + 1;

    ## we know where it starts, so turn into number -
    ## the ordinal for the char.
    $ord = CORE::hex substr($txt, $hexstart, $off[0] - $hexstart);
  }

  if ($^H & $bytes::hint_bits) {	# "use bytes" in effect?
    use bytes;
    return chr $ord if $ord <= 255;
    my $hex = sprintf "%04x", $ord;
    if (not defined $fname) {
      $fname = substr $txt, $off[0] + 2, $off[1] - $off[0] - 2;
    }
    croak "Character 0x$hex with name '$fname' is above 0xFF";
  }

  no warnings 'utf8'; # allow even illegal characters
  return pack "U", $ord;
} # charnames

sub import
{
  shift; ## ignore class name

  if (not @_) {
    carp("`use charnames' needs explicit imports list");
  }
  $^H{charnames} = \&charnames ;

  ##
  ## fill %h keys with our @_ args.
  ##
  my ($promote, %h, @args) = (0);
  while (my $arg = shift) {
    if ($arg eq ":alias") {
      @_ or
	croak ":alias needs an argument in charnames";
      my $alias = shift;
      if (ref $alias) {
	ref $alias eq "HASH" or
	  croak "Only HASH reference supported as argument to :alias";
	alias ($alias);
	next;
      }
      if ($alias =~ m{:(\w+)$}) {
	$1 eq "full" || $1 eq "short" and
	  croak ":alias cannot use existing pragma :$1 (reversed order?)";
	alias_file ($1) and $promote = 1;
	next;
      }
      alias_file ($alias);
      next;
    }
    if (substr($arg, 0, 1) eq ':' and ! ($arg eq ":full" || $arg eq ":short")) {
      warn "unsupported special '$arg' in charnames";
      next;
    }
    push @args, $arg;
  }
  @args == 0 && $promote and @args = (":full");
  @h{@args} = (1) x @args;

  $^H{charnames_full} = delete $h{':full'};
  $^H{charnames_short} = delete $h{':short'};
  $^H{charnames_scripts} = [map uc, keys %h];

  ##
  ## If utf8? warnings are enabled, and some scripts were given,
  ## see if at least we can find one letter of each script.
  ##
  if (warnings::enabled('utf8') && @{$^H{charnames_scripts}}) {
    $txt = do "unicore/Name.pl" unless $txt;

    for my $script (@{$^H{charnames_scripts}}) {
      if (not $txt =~ m/\t\t$script (?:CAPITAL |SMALL )?LETTER /) {
	warnings::warn('utf8',  "No such script: '$script'");
      }
    }
  }
} # import

my %viacode;

sub viacode
{
  if (@_ != 1) {
    carp "charnames::viacode() expects one argument";
    return;
  }

  my $arg = shift;

  # this comes actually from Unicode::UCD, where it is the named
  # function _getcode (), but it avoids the overhead of loading it
  my $hex;
  if ($arg =~ /^[1-9]\d*$/) {
    $hex = sprintf "%04X", $arg;
  } elsif ($arg =~ /^(?:[Uu]\+|0[xX])?([[:xdigit:]]+)$/) {
    $hex = $1;
  } else {
    carp("unexpected arg \"$arg\" to charnames::viacode()");
    return;
  }

  # checking the length first is slightly faster
  if (length($hex) > 5 && hex($hex) > 0x10FFFF) {
    carp "Unicode characters only allocated up to U+10FFFF (you asked for U+$hex)";
    return;
  }

  return $viacode{$hex} if exists $viacode{$hex};

  $txt = do "unicore/Name.pl" unless $txt;

  return unless $txt =~ m/^$hex\t\t(.+)/m;

  $viacode{$hex} = $1;
} # viacode

my %vianame;

sub vianame
{
  if (@_ != 1) {
    carp "charnames::vianame() expects one name argument";
    return ()
  }

  my $arg = shift;

  return chr CORE::hex $1 if $arg =~ /^U\+([0-9a-fA-F]+)$/;

  return $vianame{$arg} if exists $vianame{$arg};

  $txt = do "unicore/Name.pl" unless $txt;

  my $pos = index $txt, "\t\t$arg\n";
  if ($[ <= $pos) {
    my $posLF = rindex $txt, "\n", $pos;
    (my $code = substr $txt, $posLF + 1, 6) =~ tr/\t//d;
    return $vianame{$arg} = CORE::hex $code;

    # If $pos is at the 1st line, $posLF must be $[ - 1 (not found);
    # then $posLF + 1 equals to $[ (at the beginning of $txt).
    # Otherwise $posLF is the position of "\n";
    # then $posLF + 1 must be the position of the next to "\n"
    # (the beginning of the line).
    # substr($txt, $posLF + 1, 6) may be "0000\t\t", "00A1\t\t",
    # "10300\t", "100000", etc. So we can get the code via removing TAB.
  } else {
    return;
  }
} # vianame


1;
__END__

=head1 NAME

charnames - define character names for C<\N{named}> string literal escapes

=head1 SYNOPSIS

  use charnames ':full';
  print "\N{GREEK SMALL LETTER SIGMA} is called sigma.\n";

  use charnames ':short';
  print "\N{greek:Sigma} is an upper-case sigma.\n";

  use charnames qw(cyrillic greek);
  print "\N{sigma} is Greek sigma, and \N{be} is Cyrillic b.\n";

  use charnames ":full", ":alias" => {
    e_ACUTE => "LATIN SMALL LETTER E WITH ACUTE",
  };
  print "\N{e_ACUTE} is a small letter e with an acute.\n";

  use charnames ();
  print charnames::viacode(0x1234); # prints "ETHIOPIC SYLLABLE SEE"
  printf "%04X", charnames::vianame("GOTHIC LETTER AHSA"); # prints "10330"

=head1 DESCRIPTION

Pragma C<use charnames> supports arguments C<:full>, C<:short>, script
names and customized aliases.  If C<:full> is present, for expansion of
C<\N{CHARNAME}>, the string C<CHARNAME> is first looked up in the list of
standard Unicode character names.  If C<:short> is present, and
C<CHARNAME> has the form C<SCRIPT:CNAME>, then C<CNAME> is looked up
as a letter in script C<SCRIPT>.  If pragma C<use charnames> is used
with script name arguments, then for C<\N{CHARNAME}> the name
C<CHARNAME> is looked up as a letter in the given scripts (in the
specified order). Customized aliases are explained in L</CUSTOM ALIASES>.

For lookup of C<CHARNAME> inside a given script C<SCRIPTNAME>
this pragma looks for the names

  SCRIPTNAME CAPITAL LETTER CHARNAME
  SCRIPTNAME SMALL LETTER CHARNAME
  SCRIPTNAME LETTER CHARNAME

in the table of standard Unicode names.  If C<CHARNAME> is lowercase,
then the C<CAPITAL> variant is ignored, otherwise the C<SMALL> variant
is ignored.

Note that C<\N{...}> is compile-time, it's a special form of string
constant used inside double-quoted strings: in other words, you cannot
use variables inside the C<\N{...}>.  If you want similar run-time
functionality, use charnames::vianame().

For the C0 and C1 control characters (U+0000..U+001F, U+0080..U+009F)
as of Unicode 3.1, there are no official Unicode names but you can use
instead the ISO 6429 names (LINE FEED, ESCAPE, and so forth).  In
Unicode 3.2 (as of Perl 5.8) some naming changes take place ISO 6429
has been updated, see L</ALIASES>.  Also note that the U+UU80, U+0081,
U+0084, and U+0099 do not have names even in ISO 6429.

Since the Unicode standard uses "U+HHHH", so can you: "\N{U+263a}"
is the Unicode smiley face, or "\N{WHITE SMILING FACE}".

=head1 ALIASES

A few aliases have been defined for convenience: instead of having
to use the official names

    LINE FEED (LF)
    FORM FEED (FF)
    CARRIAGE RETURN (CR)
    NEXT LINE (NEL)

(yes, with parentheses) one can use

    LINE FEED
    FORM FEED
    CARRIAGE RETURN
    NEXT LINE
    LF
    FF
    CR
    NEL

One can also use

    BYTE ORDER MARK
    BOM

and

    ZWNJ
    ZWJ

for ZERO WIDTH NON-JOINER and ZERO WIDTH JOINER.

For backward compatibility one can use the old names for
certain C0 and C1 controls

    old                         new

    HORIZONTAL TABULATION       CHARACTER TABULATION
    VERTICAL TABULATION         LINE TABULATION
    FILE SEPARATOR              INFORMATION SEPARATOR FOUR
    GROUP SEPARATOR             INFORMATION SEPARATOR THREE
    RECORD SEPARATOR            INFORMATION SEPARATOR TWO
    UNIT SEPARATOR              INFORMATION SEPARATOR ONE
    PARTIAL LINE DOWN           PARTIAL LINE FORWARD
    PARTIAL LINE UP             PARTIAL LINE BACKWARD

but the old names in addition to giving the character
will also give a warning about being deprecated.

=head1 CUSTOM ALIASES

This version of charnames supports three mechanisms of adding local
or customized aliases to standard Unicode naming conventions (:full).

Note that an alias should not be something that is a legal curly
brace-enclosed quantifier (see L<perlreref/QUANTIFIERS>).  For example
C<\N{123}> means to match 123 non-newline characters, and is not treated as an
alias.  Aliases are discouraged from beginning with anything other than an
alphabetic character and from containing anything other than alphanumerics,
spaces, dashes, colons, parentheses, and underscores.  Currently they must be
ASCII.

=head2 Anonymous hashes

    use charnames ":full", ":alias" => {
        e_ACUTE => "LATIN SMALL LETTER E WITH ACUTE",
        };
    my $str = "\N{e_ACUTE}";

=head2 Alias file

    use charnames ":full", ":alias" => "pro";

    will try to read "unicore/pro_alias.pl" from the @INC path. This
    file should return a list in plain perl:

    (
    A_GRAVE         => "LATIN CAPITAL LETTER A WITH GRAVE",
    A_CIRCUM        => "LATIN CAPITAL LETTER A WITH CIRCUMFLEX",
    A_DIAERES       => "LATIN CAPITAL LETTER A WITH DIAERESIS",
    A_TILDE         => "LATIN CAPITAL LETTER A WITH TILDE",
    A_BREVE         => "LATIN CAPITAL LETTER A WITH BREVE",
    A_RING          => "LATIN CAPITAL LETTER A WITH RING ABOVE",
    A_MACRON        => "LATIN CAPITAL LETTER A WITH MACRON",
    );

=head2 Alias shortcut

    use charnames ":alias" => ":pro";

    works exactly the same as the alias pairs, only this time,
    ":full" is inserted automatically as first argument (if no
    other argument is given).

=head1 charnames::viacode(code)

Returns the full name of the character indicated by the numeric code.
The example

    print charnames::viacode(0x2722);

prints "FOUR TEARDROP-SPOKED ASTERISK".

Returns undef if no name is known for the code.

This works only for the standard names, and does not yet apply
to custom translators.

Notice that the name returned for of U+FEFF is "ZERO WIDTH NO-BREAK
SPACE", not "BYTE ORDER MARK".

=head1 charnames::vianame(name)

Returns the code point indicated by the name.
The example

    printf "%04X", charnames::vianame("FOUR TEARDROP-SPOKED ASTERISK");

prints "2722".

Returns undef if the name is unknown.

This works only for the standard names, and does not yet apply
to custom translators.

=head1 CUSTOM TRANSLATORS

The mechanism of translation of C<\N{...}> escapes is general and not
hardwired into F<charnames.pm>.  A module can install custom
translations (inside the scope which C<use>s the module) with the
following magic incantation:

    sub import {
	shift;
	$^H{charnames} = \&translator;
    }

Here translator() is a subroutine which takes C<CHARNAME> as an
argument, and returns text to insert into the string instead of the
C<\N{CHARNAME}> escape.  Since the text to insert should be different
in C<bytes> mode and out of it, the function should check the current
state of C<bytes>-flag as in:

    use bytes ();			# for $bytes::hint_bits
    sub translator {
	if ($^H & $bytes::hint_bits) {
	    return bytes_translator(@_);
	}
	else {
	    return utf8_translator(@_);
	}
    }

See L</CUSTOM ALIASES> above for restrictions on C<CHARNAME>.

=head1 ILLEGAL CHARACTERS

If you ask by name for a character that does not exist, a warning is given and
the Unicode I<replacement character> "\x{FFFD}" is returned.

If you ask by code for a character that is unassigned, no warning is
given and C<undef> is returned.  (Though if you ask for a code point
past U+10FFFF you do get a warning.)  See L</BUGS> below.

=head1 BUGS

viacode should return an empty string for unassigned in-range Unicode code
points, as that is their correct current name.

viacode(0) doesn't return C<NULL>, but C<undef>

vianame returns a chr if the input name is of the form C<U+...>, and an ord
otherwise.  It is planned to change this to always return an ord.

None of the functions work on almost all the Hangul syllable and CJK Unicode
characters that have their code points as part of their names.

Names must be ASCII characters only.

Unicode standard named sequences are not recognized, such as
C<LATIN CAPITAL LETTER A WITH MACRON AND GRAVE>
(which should mean C<LATIN CAPITAL LETTER A WITH MACRON> with an additional
C<COMBINING GRAVE ACCENT>).

Since evaluation of the translation function happens in the middle of
compilation (of a string literal), the translation function should not
do any C<eval>s or C<require>s.  This restriction should be lifted in
a future version of Perl.

=cut