1 # !!!!!!! INTERNAL PERL USE ONLY !!!!!!!
2 # This helper module is for internal use by core Perl only. This module is
3 # subject to change or removal at any time without notice. Don't use it
4 # directly. Use the public <charnames> module instead.
10 use unicore::Name; # mktables-generated algorithmically-defined names
12 use bytes (); # for $bytes::hint_bits
13 use re "/aa"; # Everything in here should be ASCII
15 $Carp::Internal{ (__PACKAGE__) } = 1;
17 # Translate between Unicode character names and their code points. This is a
18 # submodule of package <charnames>, used to allow \N{...} to be autoloaded,
19 # but it was decided not to autoload the various functions in charnames; the
20 # splitting allows this behavior.
22 # The official names with their code points are stored in a table in
23 # lib/unicore/Name.pl which is read in as a large string (almost 3/4 Mb in
24 # Unicode 6.0). Each code point/name combination is separated by a \n in the
25 # string. (Some of the CJK and the Hangul syllable names are determined
26 # instead algorithmically via subroutines stored instead in
27 # lib/unicore/Name.pm). Because of the large size of this table, it isn't
28 # converted into hashes for faster lookup.
30 # But, user defined aliases are stored in their own hashes, as are Perl
31 # extensions to the official names. These are checked first before looking at
34 # Basically, the table is grepped for the input code point (viacode()) or
35 # name (the other functions), and the corresponding value on the same line is
36 # returned. The grepping is done by turning the input into a regular
37 # expression. Thus, the same table does double duty, used by both name and
38 # code point lookup. (If we were to have hashes, we would need two, one for
39 # each lookup direction.)
41 # For loose name matching, the logical thing would be to have a table
42 # with all the ignorable characters squeezed out, and then grep it with the
43 # similiarly-squeezed input name. (And this is in fact how the lookups are
44 # done with the small Perl extension hashes.) But since we need to be able to
45 # go from code point to official name, the original table would still need to
46 # exist. Due to the large size of the table, it was decided to not read
47 # another very large string into memory for a second table. Instead, the
48 # regular expression of the input name is modified to have optional spaces and
49 # dashes between characters. For example, in strict matching, the regular
50 # expression would be:
52 # Under loose matching, the blank would be squeezed out, and the re would be:
53 # qr/\tD[- ]?I[- ]?G[- ]?I[- ]?T[- ]?O[- ]?N[- ]?E$/m
54 # which matches a blank or dash between any characters in the official table.
56 # This is also how script lookup is done. Basically the re looks like
57 # qr/ (?:LATIN|GREEK|CYRILLIC) (?:SMALL )?LETTER $name/
58 # where $name is the loose or strict regex for the remainder of the name.
60 # The hashes are stored as utf8 strings. This makes it easier to deal with
61 # sequences. I (khw) also tried making Name.pl utf8, but it slowed things
62 # down by a factor of 7. I then tried making Name.pl store the ut8
63 # equivalents but not calling them utf8. That led to similar speed as leaving
64 # it alone, but since that is harder for a human to parse, I left it as-is.
66 my %system_aliases = (
68 'SINGLE-SHIFT 2' => chr utf8::unicode_to_native(0x8E),
69 'SINGLE-SHIFT 3' => chr utf8::unicode_to_native(0x8F),
70 'PRIVATE USE 1' => chr utf8::unicode_to_native(0x91),
71 'PRIVATE USE 2' => chr utf8::unicode_to_native(0x92),
74 # These are the aliases above that differ under :loose and :full matching
75 # because the :full versions have blanks or hyphens in them.
76 #my %loose_system_aliases = (
79 #my %deprecated_aliases;
80 #$deprecated_aliases{'BELL'} = chr utf8::unicode_to_native(0x07) if $^V lt v5.17.0;
82 #my %loose_deprecated_aliases = (
85 # These are special cased in :loose matching, differing only in a medial
87 my $HANGUL_JUNGSEONG_O_E_utf8 = chr 0x1180;
88 my $HANGUL_JUNGSEONG_OE_utf8 = chr 0x116C;
91 my $txt; # The table of official character names
93 my %full_names_cache; # Holds already-looked-up names, so don't have to
94 # re-look them up again. The previous versions of charnames had scoping
95 # bugs. For example if we use script A in one scope and find and cache
96 # what Z resolves to, we can't use that cache in a different scope that
97 # uses script B instead of A, as Z might be an entirely different letter
98 # there; or there might be different aliases in effect in different
99 # scopes, or :short may be in effect or not effect in different scopes,
100 # or various combinations thereof. This was solved in this version
101 # mostly by moving things to %^H. But some things couldn't be moved
102 # there. One of them was the cache of runtime looked-up names, in part
103 # because %^H is read-only at runtime. I (khw) don't know why the cache
104 # was run-time only in the previous versions: perhaps oversight; perhaps
105 # that compile time looking doesn't happen in a loop so didn't think it
106 # was worthwhile; perhaps not wanting to make the cache too large. But
107 # I decided to make it compile time as well; this could easily be
109 # Anyway, this hash is not scoped, and is added to at runtime. It
110 # doesn't have scoping problems because the data in it is restricted to
111 # official names, which are always invariant, and we only set it and
112 # look at it at during :full lookups, so is unaffected by any other
113 # scoped options. I put this in to maintain parity with the older
114 # version. If desired, a %short_names cache could also be made, as well
115 # as one for each script, say in %script_names_cache, with each key
116 # being a hash for a script named in a 'use charnames' statement. I
117 # decided not to do that for now, just because it's added complication,
118 # and because I'm just trying to maintain parity, not extend it.
120 # Like %full_names_cache, but for use when :loose is in effect. There needs
121 # to be two caches because :loose may not be in effect for a scope, and a
122 # loose name could inappropriately be returned when only exact matching is
124 my %loose_names_cache;
126 # Designed so that test decimal first, and then hex. Leading zeros
127 # imply non-decimal, as do non-[0-9]
128 my $decimal_qr = qr/^[1-9]\d*$/;
130 # Returns the hex number in $1.
131 my $hex_qr = qr/^(?:[Uu]\+|0[xX])?([[:xdigit:]]+)$/;
135 require Carp; goto &Carp::croak;
140 require Carp; goto &Carp::carp;
143 sub alias (@) # Set up a single alias
146 my $nbsp = chr utf8::unicode_to_native(0xA0);
148 my $alias = ref $_[0] ? $_[0] : { @_ };
149 foreach my $name (sort keys %$alias) { # Sort only because it helps having
150 # deterministic output for
151 # t/lib/charnames/alias
152 my $value = $alias->{$name};
153 next unless defined $value; # Omit if screwed up.
155 # Is slightly slower to just after this statement see if it is
156 # decimal, since we already know it is after having converted from
157 # hex, but makes the code easier to maintain, and is called
158 # infrequently, only at compile-time
159 if ($value !~ $decimal_qr && $value =~ $hex_qr) {
160 my $temp = CORE::hex $1;
161 $temp = utf8::unicode_to_native($temp) if $value =~ /^[Uu]\+/;
164 if ($value =~ $decimal_qr) {
165 no warnings qw(non_unicode surrogate nonchar); # Allow any of these
166 $^H{charnames_ord_aliases}{$name} = chr $value;
168 # Use a canonical form.
169 $^H{charnames_inverse_ords}{sprintf("%05X", $value)} = $name;
173 $ok_portion = $1 if $name =~ / ^ (
174 \p{_Perl_Charname_Begin}
175 \p{_Perl_Charname_Continue}*
178 # If the name was fully correct, the above should have matched all of
180 if (length $ok_portion < length $name) {
181 my $first_bad = substr($name, length($ok_portion), 1);
182 push @errors, "Invalid character in charnames alias definition; "
183 . "marked by <-- HERE in '$ok_portion$first_bad<-- HERE "
184 . substr($name, length($ok_portion) + 1)
188 if ($name =~ / ( .* \s ) ( \s* ) $ /x) {
189 push @errors, "charnames alias definitions may not contain "
190 . "trailing white-space; marked by <-- HERE in "
191 . "'$1 <-- HERE " . $2 . "'";
195 # Use '+' instead of '*' in this regex, because any trailing
196 # blanks have already been found
197 if ($name =~ / ( .*? \s{2} ) ( .+ ) /x) {
198 push @errors, "charnames alias definitions may not contain a "
199 . "sequence of multiple spaces; marked by <-- HERE "
200 . "in '$1 <-- HERE " . $2 . "'";
204 $^H{charnames_name_aliases}{$name} = $value;
205 if (warnings::enabled('deprecated')
206 && $name =~ / ( .* $nbsp ) ( .* ) $ /x)
208 carp "NO-BREAK SPACE in a charnames alias definition is "
209 . "deprecated; marked by <-- HERE in '$1 <-- HERE "
216 # We find and output all errors from this :alias definition, rather than
217 # failing on the first one, so fewer runs are needed to get it to compile
219 croak join "\n", @errors;
225 sub not_legal_use_bytes_msg {
226 my ($name, $utf8) = @_;
229 if (length($utf8) == 1) {
230 $return = sprintf("Character 0x%04x with name '%s' is", ord $utf8, $name);
232 $return = sprintf("String with name '%s' (and ordinals %s) contains character(s)", $name, join(" ", map { sprintf "0x%04X", ord $_ } split(//, $utf8)));
234 return $return . " above 0xFF with 'use bytes' in effect";
237 sub alias_file ($) # Reads a file containing alias definitions
240 my ($arg, $file) = @_;
241 if (-f $arg && File::Spec->file_name_is_absolute ($arg)) {
244 elsif ($arg =~ m/ ^ \p{_Perl_IDStart} \p{_Perl_IDCont}* $/x) {
245 $file = "unicore/${arg}_alias.pl";
248 croak "Charnames alias file names can only have identifier characters";
250 if (my @alias = do $file) {
251 @alias == 1 && !defined $alias[0] and
252 croak "$file cannot be used as alias file for charnames";
254 croak "$file did not return a (valid) list of alias pairs";
261 # For use when don't import anything. This structure must be kept in
262 # sync with the one that import() fills up.
264 charnames_stringified_names => "",
265 charnames_stringified_ords => "",
266 charnames_scripts => "",
268 charnames_loose => 0,
269 charnames_short => 0,
273 sub lookup_name ($$$) {
274 my ($name, $wants_ord, $runtime) = @_;
276 # Lookup the name or sequence $name in the tables. If $wants_ord is false,
277 # returns the string equivalent of $name; if true, returns the ordinal value
278 # instead, but in this case $name must not be a sequence; otherwise undef is
279 # returned and a warning raised. $runtime is 0 if compiletime, otherwise
280 # gives the number of stack frames to go back to get the application caller
282 # If $name is not found, returns undef in runtime with no warning; and in
283 # compiletime, the Unicode replacement character, with a warning.
285 # It looks first in the aliases, then in the large table of official Unicode
288 my $result; # The string result
293 my $hints_ref = (caller($runtime))[10];
295 # If we didn't import anything (which happens with 'use charnames ()',
296 # substitute a dummy structure.
297 $hints_ref = \%dummy_H if ! defined $hints_ref
298 || (! defined $hints_ref->{charnames_full}
299 && ! defined $hints_ref->{charnames_loose});
301 # At runtime, but currently not at compile time, %^H gets
302 # stringified, so un-stringify back to the original data structures.
303 # These get thrown away by perl before the next invocation
304 # Also fill in the hash with the non-stringified data.
305 # N.B. New fields must be also added to %dummy_H
307 %{$^H{charnames_name_aliases}} = split ',',
308 $hints_ref->{charnames_stringified_names};
309 %{$^H{charnames_ord_aliases}} = split ',',
310 $hints_ref->{charnames_stringified_ords};
311 $^H{charnames_scripts} = $hints_ref->{charnames_scripts};
312 $^H{charnames_full} = $hints_ref->{charnames_full};
313 $^H{charnames_loose} = $hints_ref->{charnames_loose};
314 $^H{charnames_short} = $hints_ref->{charnames_short};
317 my $loose = $^H{charnames_loose};
318 my $lookup_name; # Input name suitably modified for grepping for in the
321 # User alias should be checked first or else can't override ours, and if we
322 # were to add any, could conflict with theirs.
323 if (exists $^H{charnames_ord_aliases}{$name}) {
324 $result = $^H{charnames_ord_aliases}{$name};
326 elsif (exists $^H{charnames_name_aliases}{$name}) {
327 $name = $^H{charnames_name_aliases}{$name};
328 $save_input = $lookup_name = $name; # Cache the result for any error
330 # The aliases are documented to not match loosely, so change loose match
334 $^H{charnames_full} = 1;
339 # Here, not a user alias. That means that loose matching may be in
340 # effect; will have to modify the input name.
341 $lookup_name = $name;
343 $lookup_name = uc $lookup_name;
345 # Squeeze out all underscores
346 $lookup_name =~ s/_//g;
348 # Remove all medial hyphens
349 $lookup_name =~ s/ (?<= \S ) - (?= \S )//gx;
351 # Squeeze out all spaces
352 $lookup_name =~ s/\s//g;
355 # Here, $lookup_name has been modified as necessary for looking in the
356 # hashes. Check the system alias files next. Most of these aliases are
357 # the same for both strict and loose matching. To save space, the ones
358 # which differ are in their own separate hash, which is checked if loose
359 # matching is selected and the regular match fails. To save time, the
360 # loose hashes could be expanded to include all aliases, and there would
361 # only have to be one check. But if someone specifies :loose, they are
362 # interested in convenience over speed, and the time for this second check
363 # is miniscule compared to the rest of the routine.
364 if (exists $system_aliases{$lookup_name}) {
365 $result = $system_aliases{$lookup_name};
367 # There are currently no entries in this hash, so don't waste time looking
368 # for them. But the code is retained for the unlikely possibility that
369 # some will be added in the future.
370 # elsif ($loose && exists $loose_system_aliases{$lookup_name}) {
371 # $result = $loose_system_aliases{$lookup_name};
373 # if (exists $deprecated_aliases{$lookup_name}) {
375 # warnings::warnif('deprecated',
376 # "Unicode character name \"$name\" is deprecated, use \""
377 # . viacode(ord $deprecated_aliases{$lookup_name})
379 # $result = $deprecated_aliases{$lookup_name};
381 # There are currently no entries in this hash, so don't waste time looking
382 # for them. But the code is retained for the unlikely possibility that
383 # some will be added in the future.
384 # elsif ($loose && exists $loose_deprecated_aliases{$lookup_name}) {
386 # warnings::warnif('deprecated',
387 # "Unicode character name \"$name\" is deprecated, use \""
388 # . viacode(ord $loose_deprecated_aliases{$lookup_name})
390 # $result = $loose_deprecated_aliases{$lookup_name};
394 my @off; # Offsets into table of pattern match begin and end
396 # If haven't found it yet...
397 if (! defined $result) {
399 # See if has looked this input up earlier.
400 if (! $loose && $^H{charnames_full} && exists $full_names_cache{$name}) {
401 $result = $full_names_cache{$name};
403 elsif ($loose && exists $loose_names_cache{$name}) {
404 $result = $loose_names_cache{$name};
406 else { # Here, must do a look-up
408 # If full or loose matching succeeded, points to where to cache the
412 ## Suck in the code/name list as a big string.
414 ## "00052\tLATIN CAPITAL LETTER R\n"
416 # "0052 0303\tLATIN CAPITAL LETTER R WITH TILDE\n"
417 $txt = do "unicore/Name.pl" unless $txt;
419 ## @off will hold the index into the code/name string of the start and
420 ## end of the name as we find it.
422 ## If :loose, look for a loose match; if :full, look for the name
424 # First, see if the name is one which is algorithmically determinable.
425 # The subroutine is included in Name.pl. The table contained in
426 # $txt doesn't contain these. Experiments show that checking
427 # for these before checking for the regular names has no
428 # noticeable impact on performance for the regular names, but
429 # the other way around slows down finding these immensely.
430 # Algorithmically determinables are not placed in the cache because
431 # that uses up memory, and finding these again is fast.
432 if (($loose || $^H{charnames_full})
433 && (defined (my $ord = charnames::name_to_code_point_special($lookup_name, $loose))))
439 # Not algorithmically determinable; look up in the table. The name
440 # will be turned into a regex, so quote any meta characters.
441 $lookup_name = quotemeta $lookup_name;
445 # For loose matches, $lookup_name has already squeezed out the
446 # non-essential characters. We have to add in code to make the
447 # squeezed version match the non-squeezed equivalent in the table.
448 # The only remaining hyphens are ones that start or end a word in
449 # the original. They have been quoted in $lookup_name so they look
450 # like "\-". Change all other characters except the backslash
451 # quotes for any metacharacters, and the final character, so that
452 # e.g., COLON gets transformed into: /C[- ]?O[- ]?L[- ]?O[- ]?N/
453 $lookup_name =~ s/ (?! \\ -) # Don't do this to the \- sequence
454 ( [^-\\] ) # Nor the "-" within that sequence,
455 # nor the "\" that quotes metachars,
456 # but otherwise put the char into $1
457 (?=.) # And don't do it for the final char
458 /$1\[- \]?/gx; # And add an optional blank or
459 # '-' after each $1 char
461 # Those remaining hyphens were originally at the beginning or end of
462 # a word, so they can match either a blank before or after, but not
463 # both. (Keep in mind that they have been quoted, so are a '\-'
465 $lookup_name =~ s/\\ -/(?:- | -)/xg;
468 # Do the lookup in the full table if asked for, and if succeeds
469 # save the offsets and set where to cache the result.
470 if (($loose || $^H{charnames_full}) && $txt =~ /\t$lookup_name$/m) {
471 @off = ($-[0] + 1, $+[0]); # The 1 is for the tab
472 $cache_ref = ($loose) ? \%loose_names_cache : \%full_names_cache;
476 # Here, didn't look for, or didn't find the name.
477 # If :short is allowed, see if input is like "greek:Sigma".
478 # Keep in mind that $lookup_name has had the metas quoted.
479 my $scripts_trie = "";
480 my $name_has_uppercase;
481 if (($^H{charnames_short})
482 && $lookup_name =~ /^ (?: \\ \s)* # Quoted space
483 (.+?) # $1 = the script
487 (.+?) # $2 = the name
491 # Even in non-loose matching, the script traditionally has been
493 $scripts_trie = "\U$1";
496 # Use original name to find its input casing, but ignore the
497 # script part of that to make the determination.
498 $save_input = $name if ! defined $save_input;
500 $name_has_uppercase = $name =~ /[[:upper:]]/;
502 else { # Otherwise look in allowed scripts
503 $scripts_trie = $^H{charnames_scripts};
505 # Use original name to find its input casing
506 $name_has_uppercase = $name =~ /[[:upper:]]/;
509 my $case = $name_has_uppercase ? "CAPITAL" : "SMALL";
510 return if (! $scripts_trie || $txt !~
511 /\t (?: $scripts_trie ) \ (?:$case\ )? LETTER \ \U$lookup_name $/xm);
513 # Here have found the input name in the table.
514 @off = ($-[0] + 1, $+[0]); # The 1 is for the tab
517 # Here, the input name has been found; we haven't set up the output,
518 # but we know where in the string
519 # the name starts. The string is set up so that for single characters
520 # (and not named sequences), the name is preceded immediately by a
521 # tab and 5 hex digits for its code, with a \n before those. Named
522 # sequences won't have the 7th preceding character be a \n.
523 # (Actually, for the very first entry in the table this isn't strictly
524 # true: subtracting 7 will yield -1, and the substr below will
525 # therefore yield the very last character in the table, which should
526 # also be a \n, so the statement works anyway.)
527 if (substr($txt, $off[0] - 7, 1) eq "\n") {
528 $result = chr CORE::hex substr($txt, $off[0] - 6, 5);
530 # Handle the single loose matching special case, in which two names
531 # differ only by a single medial hyphen. If the original had a
532 # hyphen (or more) in the right place, then it is that one.
533 $result = $HANGUL_JUNGSEONG_O_E_utf8
535 && $result eq $HANGUL_JUNGSEONG_OE_utf8
536 && $name =~ m/O \s* - [-\s]* E/ix;
537 # Note that this wouldn't work if there were a 2nd
542 # Here, is a named sequence. Need to go looking for the beginning,
543 # which is just after the \n from the previous entry in the table.
544 # The +1 skips past that newline, or, if the rindex() fails, to put
545 # us to an offset of zero.
546 my $charstart = rindex($txt, "\n", $off[0] - 7) + 1;
547 $result = pack("W*", map { CORE::hex }
548 split " ", substr($txt, $charstart, $off[0] - $charstart - 1));
552 # Cache the input so as to not have to search the large table
553 # again, but only if it came from the one search that we cache.
554 # (Haven't bothered with the pain of sorting out scoping issues for the
556 $cache_ref->{$name} = $result if defined $cache_ref;
560 # Here, have the result character. If the return is to be an ord, must be
561 # any single character.
563 return ord($result) if length $result == 1;
565 elsif (! utf8::is_utf8($result)) {
567 # Here isn't UTF-8. That's OK if it is all ASCII, or we are being called
568 # at compile time where we know we can guarantee that Unicode rules are
569 # correctly imposed on the result, or under 'bytes' where we don't want
570 # those rules. But otherwise we have to make it UTF8 to guarantee Unicode
571 # rules on the returned string.
572 return $result if ! $runtime
573 || (caller $runtime)[8] & $bytes::hint_bits
574 || $result !~ /[[:^ascii:]]/;
575 utf8::upgrade($result);
580 # Here, wants string output. If utf8 is acceptable, just return what
581 # we've got; otherwise attempt to convert it to non-utf8 and return that.
582 my $in_bytes = ($runtime)
583 ? (caller $runtime)[8] & $bytes::hint_bits
584 : $^H & $bytes::hint_bits;
585 return $result if (! $in_bytes || utf8::downgrade($result, 1)) # The 1 arg
586 # means don't die on failure
589 # Here, there is an error: either there are too many characters, or the
590 # result string needs to be non-utf8, and at least one character requires
591 # utf8. Prefer any official name over the input one for the error message.
593 $name = substr($txt, $off[0], $off[1] - $off[0]) if @off;
596 $name = (defined $save_input) ? $save_input : $_[0];
600 # Only way to get here in this case is if result too long. Message
601 # assumes that our only caller that requires single char result is
603 carp "charnames::vianame() doesn't handle named sequences ($name). Use charnames::string_vianame() instead";
607 # Only other possible failure here is from use bytes.
609 carp not_legal_use_bytes_msg($name, $result);
612 croak not_legal_use_bytes_msg($name, $result);
619 # For \N{...}. Looks up the character name and returns the string
620 # representation of it.
622 # The first 0 arg means wants a string returned; the second that we are in
624 return lookup_name($_[0], 0, 0);
629 shift; ## ignore class name
632 carp("'use charnames' needs explicit imports list");
634 $^H{charnames} = \&charnames ;
635 $^H{charnames_ord_aliases} = {};
636 $^H{charnames_name_aliases} = {};
637 $^H{charnames_inverse_ords} = {};
638 # New fields must be added to %dummy_H, and the code in lookup_name()
639 # that copies fields from the runtime structure
642 ## fill %h keys with our @_ args.
644 my ($promote, %h, @args) = (0);
645 while (my $arg = shift) {
646 if ($arg eq ":alias") {
648 croak ":alias needs an argument in charnames";
651 ref $alias eq "HASH" or
652 croak "Only HASH reference supported as argument to :alias";
657 if ($alias =~ m{:(\w+)$}) {
658 $1 eq "full" || $1 eq "loose" || $1 eq "short" and
659 croak ":alias cannot use existing pragma :$1 (reversed order?)";
660 alias_file ($1) and $promote = 1;
663 alias_file ($alias) and $promote = 1;
666 if (substr($arg, 0, 1) eq ':'
667 and ! ($arg eq ":full" || $arg eq ":short" || $arg eq ":loose"))
669 warn "unsupported special '$arg' in charnames";
675 @args == 0 && $promote and @args = (":full");
676 @h{@args} = (1) x @args;
678 # Don't leave these undefined as are tested for in lookup_names
679 $^H{charnames_full} = delete $h{':full'} || 0;
680 $^H{charnames_loose} = delete $h{':loose'} || 0;
681 $^H{charnames_short} = delete $h{':short'} || 0;
682 my @scripts = map { uc quotemeta } keys %h;
685 ## If utf8? warnings are enabled, and some scripts were given,
686 ## see if at least we can find one letter from each script.
688 if (warnings::enabled('utf8') && @scripts) {
689 $txt = do "unicore/Name.pl" unless $txt;
691 for my $script (@scripts) {
692 if (not $txt =~ m/\t$script (?:CAPITAL |SMALL )?LETTER /) {
693 warnings::warn('utf8', "No such script: '$script'");
694 $script = quotemeta $script; # Escape it, for use in the re.
699 # %^H gets stringified, so serialize it ourselves so can extract the
700 # real data back later.
701 $^H{charnames_stringified_ords} = join ",", %{$^H{charnames_ord_aliases}};
702 $^H{charnames_stringified_names} = join ",", %{$^H{charnames_name_aliases}};
703 $^H{charnames_stringified_inverse_ords} = join ",", %{$^H{charnames_inverse_ords}};
705 # Modify the input script names for loose name matching if that is also
706 # specified, similar to the way the base character name is prepared. They
707 # don't (currently, and hopefully never will) have dashes. These go into a
708 # regex, and have already been uppercased and quotemeta'd. Squeeze out all
709 # input underscores, blanks, and dashes. Then convert so will match a blank
710 # between any characters.
711 if ($^H{charnames_loose}) {
712 for (my $i = 0; $i < @scripts; $i++) {
713 $scripts[$i] =~ s/[_ -]//g;
714 $scripts[$i] =~ s/ ( [^\\] ) (?= . ) /$1\\ ?/gx;
718 $^H{charnames_scripts} = join "|", @scripts; # Stringifiy them as a trie
721 # Cache of already looked-up values. This is set to only contain
722 # official values, and user aliases can't override them, so scoping is
726 my $no_name_code_points_re = join "|", map { sprintf("%05X",
727 utf8::unicode_to_native($_)) }
728 0x80, 0x81, 0x84, 0x99;
729 $no_name_code_points_re = qr/$no_name_code_points_re/;
733 # Returns the name of the code point argument
736 carp "charnames::viacode() expects one argument";
742 # This is derived from Unicode::UCD, where it is nearly the same as the
743 # function _getcode(), but here it makes sure that even a hex argument
744 # has the proper number of leading zeros, which is critical in
745 # matching against $txt below
746 # Must check if decimal first; see comments at that definition
748 if ($arg =~ $decimal_qr) {
749 $hex = sprintf "%05X", $arg;
750 } elsif ($arg =~ $hex_qr) {
752 $hex = utf8::unicode_to_native($hex) if $arg =~ /^[Uu]\+/;
753 # Below is the line that differs from the _getcode() source
754 $hex = sprintf "%05X", $hex;
756 carp("unexpected arg \"$arg\" to charnames::viacode()");
760 return $viacode{$hex} if exists $viacode{$hex};
764 # If the code point is above the max in the table, there's no point
765 # looking through it. Checking the length first is slightly faster
766 if (length($hex) <= 5 || CORE::hex($hex) <= 0x10FFFF) {
767 $txt = do "unicore/Name.pl" unless $txt;
769 # See if the name is algorithmically determinable.
770 my $algorithmic = charnames::code_point_to_name_special(CORE::hex $hex);
771 if (defined $algorithmic) {
772 $viacode{$hex} = $algorithmic;
776 # Return the official name, if exists. It's unclear to me (khw) at
777 # this juncture if it is better to return a user-defined override, so
778 # leaving it as is for now.
779 if ($txt =~ m/^$hex\t/m) {
781 # The name starts with the next character and goes up to the
782 # next new-line. Using capturing parentheses above instead of
783 # @+ more than doubles the execution time in Perl 5.13
784 $return = substr($txt, $+[0], index($txt, "\n", $+[0]) - $+[0]);
786 # If not one of these 4 code points, return what we've found.
787 if ($hex !~ / ^ $no_name_code_points_re $ /x) {
788 $viacode{$hex} = $return;
792 # For backwards compatibility, we don't return the official name of
793 # the 4 code points if there are user-defined aliases for them -- so
798 # See if there is a user name for it, before giving up completely.
799 # First get the scoped aliases, give up if have none.
800 my $H_ref = (caller(1))[10];
801 return if ! defined $return
803 || ! exists $H_ref->{charnames_stringified_inverse_ords});
805 my %code_point_aliases;
806 if (defined $H_ref->{charnames_stringified_inverse_ords}) {
807 %code_point_aliases = split ',',
808 $H_ref->{charnames_stringified_inverse_ords};
809 return $code_point_aliases{$hex} if exists $code_point_aliases{$hex};
812 # Here there is no user-defined alias, return any official one.
813 return $return if defined $return;
815 if (CORE::hex($hex) > 0x10FFFF
816 && warnings::enabled('non_unicode'))
818 carp "Unicode characters only allocated up to U+10FFFF (you asked for U+$hex)";
826 # ex: set ts=8 sts=2 sw=2 et: