diff options
author | karl williamson <public@khwilliamson.com> | 2008-12-03 12:51:54 -0700 |
---|---|---|
committer | Rafael Garcia-Suarez <rgarciasuarez@gmail.com> | 2008-12-06 14:14:43 +0000 |
commit | bf93f4a05f0579e8574b55f41f6d57efe6c606a6 (patch) | |
tree | 7790f8ce8ed69c759fd6eee367bd2b741d36e5d3 | |
parent | c754e9b52666e51b6d19b097e456068f4c4988ff (diff) | |
download | perl-bf93f4a05f0579e8574b55f41f6d57efe6c606a6.tar.gz |
PATCH [perl #58430] Unicode::UCD::casefold() does not work as documented,
Message-ID: <493745CA.6070300@khwilliamson.com>
And bump version to 0.27
p4raw-id: //depot/perl@35036
-rw-r--r-- | lib/Unicode/UCD.pm | 616 | ||||
-rw-r--r-- | lib/Unicode/UCD.t | 93 |
2 files changed, 516 insertions, 193 deletions
diff --git a/lib/Unicode/UCD.pm b/lib/Unicode/UCD.pm index a760d3c921..dc3fede659 100644 --- a/lib/Unicode/UCD.pm +++ b/lib/Unicode/UCD.pm @@ -3,7 +3,7 @@ package Unicode::UCD; use strict; use warnings; -our $VERSION = '0.26'; +our $VERSION = '0.27'; use Storable qw(dclone); @@ -61,9 +61,20 @@ Unicode::UCD - Unicode character database =head1 DESCRIPTION -The Unicode::UCD module offers a simple interface to the Unicode +The Unicode::UCD module offers a series of functions that +provide a simple interface to the Unicode Character Database. +=head2 code point argument + +Some of the functions are called with a I<code point argument>, which is either +a decimal or a hexadecimal scalar designating a Unicode code point, or C<U+> +followed by hexadecimals designating a Unicode code point. In other words, if +you want a code point to be interpreted as a hexadecimal number, you must +prefix it with either C<0x> or C<U+>, because a string like e.g. C<123> will be +interpreted as a decimal code point. Also note that Unicode is B<not> limited +to 16 bits (the number of Unicode code points is open-ended, in theory +unlimited): you may have more than 4 hexdigits. =cut my $UNICODEFH; @@ -92,46 +103,136 @@ sub openunicode { return $f; } -=head2 charinfo +=head2 B<charinfo()> use Unicode::UCD 'charinfo'; my $charinfo = charinfo(0x41); -charinfo() returns a reference to a hash that has the following fields -as defined by the Unicode standard: - - key - - code code point with at least four hexdigits - name name of the character IN UPPER CASE - category general category of the character - combining classes used in the Canonical Ordering Algorithm - bidi bidirectional type - decomposition character decomposition mapping - decimal if decimal digit this is the integer numeric value - digit if digit this is the numeric value - numeric if numeric is the integer or rational numeric value - mirrored if mirrored in bidirectional text - unicode10 Unicode 1.0 name if existed and different - comment ISO 10646 comment field - upper uppercase equivalent mapping - lower lowercase equivalent mapping - title titlecase equivalent mapping - - block block the character belongs to (used in \p{In...}) - script script the character belongs to - -If no match is found, a reference to an empty hash is returned. - -The C<block> property is the same as returned by charinfo(). It is -not defined in the Unicode Character Database proper (Chapter 4 of the -Unicode 3.0 Standard, aka TUS3) but instead in an auxiliary database -(Chapter 14 of TUS3). Similarly for the C<script> property. +This returns information about the input L</code point argument> +as a reference to a hash of fields as defined by the Unicode +standard. If the L</code point argument> is not assigned in the standard +(i.e., has the general category C<Cn> meaning C<Unassigned>) +or is a non-character (meaning it is guaranteed to never be assigned in +the standard), +B<undef> is returned. + +Fields that aren't applicable to the particular code point argument exist in the +returned hash, and are empty. + +The keys in the hash with the meanings of their values are: + +=over + +=item B<code> + +the input L</code point argument> expressed in hexadecimal, with leading zeros +added if necessary to make it contain at least four hexdigits + +=item B<name> + +name of I<code>, all IN UPPER CASE. +Some control-type code points do not have names. +This field will be empty for C<Surrogate> and C<Private Use> code points, +and for the others without a name, +it will contain a description enclosed in angle brackets, like +C<E<lt>controlE<gt>>. + + +=item B<category> + +The short name of the general category of I<code>. +This will match one of the keys in the hash returned by L</general_categories()>. + +=item B<combining> + +the combining class number for I<code> used in the Canonical Ordering Algorithm. +For Unicode 5.1, this is described in Section 3.11 C<Canonical Ordering Behavior> +available at +L<http://www.unicode.org/versions/Unicode5.1.0/> + +=item B<bidi> + +bidirectional type of I<code>. +This will match one of the keys in the hash returned by L</bidi_types()>. + +=item B<decomposition> + +is empty if I<code> has no decomposition; or is one or more codes +(separated by spaces) that taken in order represent a decomposition for +I<code>. Each has at least four hexdigits. +The codes may be preceded by a word enclosed in angle brackets then a space, +like C<E<lt>compatE<gt> >, giving the type of decomposition + +=item B<decimal> + +if I<code> is a decimal digit this is its integer numeric value + +=item B<digit> + +if I<code> represents a whole number, this is its integer numeric value + +=item B<numeric> + +if I<code> represents a whole or rational number, this is its numeric value. +Rational values are expressed as a string like C<1/4>. + +=item B<mirrored> + +C<Y> or C<N> designating if I<code> is mirrored in bidirectional text + +=item B<unicode10> + +name of I<code> in the Unicode 1.0 standard if one +existed for this code point and is different from the current name + +=item B<comment> + +ISO 10646 comment field. +It appears in parentheses in the ISO 10646 names list, +or contains an asterisk to indicate there is +a note for this code point in Annex P of that standard. + +=item B<upper> + +is empty if there is no single code point uppercase mapping for I<code>; +otherwise it is that mapping expressed as at least four hexdigits. +(L</casespec()> should be used in addition to B<charinfo()> +for case mappings when the calling program can cope with multiple code point +mappings.) + +=item B<lower> + +is empty if there is no single code point lowercase mapping for I<code>; +otherwise it is that mapping expressed as at least four hexdigits. +(L</casespec()> should be used in addition to B<charinfo()> +for case mappings when the calling program can cope with multiple code point +mappings.) + +=item B<title> + +is empty if there is no single code point titlecase mapping for I<code>; +otherwise it is that mapping expressed as at least four hexdigits. +(L</casespec()> should be used in addition to B<charinfo()> +for case mappings when the calling program can cope with multiple code point +mappings.) + +=item B<block> + +block I<code> belongs to (used in \p{In...}). +See L</Blocks versus Scripts>. + + +=item B<script> + +script I<code> belongs to. +See L</Blocks versus Scripts>. + +=back Note that you cannot do (de)composition and casing based solely on the -above C<decomposition> and C<lower>, C<upper>, C<title>, properties, -you will need also the compexcl(), casefold(), and casespec() functions. +I<decomposition>, I<combining>, I<lower>, I<upper>, and I<title> fields; +you will need also the L</compexcl()>, and L</casespec()> functions. =cut @@ -305,29 +406,30 @@ sub charinrange { _search($range, 0, $#$range, $code); } -=head2 charblock +=head2 B<charblock()> use Unicode::UCD 'charblock'; my $charblock = charblock(0x41); my $charblock = charblock(1234); - my $charblock = charblock("0x263a"); + my $charblock = charblock(0x263a); my $charblock = charblock("U+263a"); my $range = charblock('Armenian'); -With a B<code point argument> charblock() returns the I<block> the character -belongs to, e.g. C<Basic Latin>. Note that not all the character -positions within all blocks are defined. +With a L</code point argument> charblock() returns the I<block> the code point +belongs to, e.g. C<Basic Latin>. +If the code point is unassigned, this returns the block it would belong to if +it were assigned (which it may in future versions of the Unicode Standard). See also L</Blocks versus Scripts>. If supplied with an argument that can't be a code point, charblock() tries -to do the opposite and interpret the argument as a character block. The +to do the opposite and interpret the argument as a code point block. The return value is a I<range>: an anonymous list of lists that contain I<start-of-range>, I<end-of-range> code point pairs. You can test whether -a code point is in a range using the L</charinrange> function. If the -argument is not a known character block, C<undef> is returned. +a code point is in a range using the L</charinrange()> function. If the +argument is not a known code point block, B<undef> is returned. =cut @@ -369,7 +471,7 @@ sub charblock { } } -=head2 charscript +=head2 B<charscript()> use Unicode::UCD 'charscript'; @@ -379,17 +481,18 @@ sub charblock { my $range = charscript('Thai'); -With a B<code point argument> charscript() returns the I<script> the -character belongs to, e.g. C<Latin>, C<Greek>, C<Han>. - -See also L</Blocks versus Scripts>. +With a L</code point argument> charscript() returns the I<script> the +code point belongs to, e.g. C<Latin>, C<Greek>, C<Han>. +If the code point is unassigned, it returns B<undef> If supplied with an argument that can't be a code point, charscript() tries -to do the opposite and interpret the argument as a character script. The +to do the opposite and interpret the argument as a code point script. The return value is a I<range>: an anonymous list of lists that contain I<start-of-range>, I<end-of-range> code point pairs. You can test whether a -code point is in a range using the L</charinrange> function. If the -argument is not a known character script, C<undef> is returned. +code point is in a range using the L</charinrange()> function. If the +argument is not a known code point script, B<undef> is returned. + +See also L</Blocks versus Scripts>. =cut @@ -434,14 +537,14 @@ sub charscript { } } -=head2 charblocks +=head2 B<charblocks()> use Unicode::UCD 'charblocks'; my $charblocks = charblocks(); charblocks() returns a reference to a hash with the known block names -as the keys, and the code point ranges (see L</charblock>) as the values. +as the keys, and the code point ranges (see L</charblock()>) as the values. See also L</Blocks versus Scripts>. @@ -452,14 +555,14 @@ sub charblocks { return dclone \%BLOCKS; } -=head2 charscripts +=head2 B<charscripts()> use Unicode::UCD 'charscripts'; my $charscripts = charscripts(); charscripts() returns a reference to a hash with the known script -names as the keys, and the code point ranges (see L</charscript>) as +names as the keys, and the code point ranges (see L</charscript()>) as the values. See also L</Blocks versus Scripts>. @@ -471,48 +574,12 @@ sub charscripts { return dclone \%SCRIPTS; } -=head2 Blocks versus Scripts - -The difference between a block and a script is that scripts are closer -to the linguistic notion of a set of characters required to present -languages, while block is more of an artifact of the Unicode character -numbering and separation into blocks of (mostly) 256 characters. - -For example the Latin B<script> is spread over several B<blocks>, such -as C<Basic Latin>, C<Latin 1 Supplement>, C<Latin Extended-A>, and -C<Latin Extended-B>. On the other hand, the Latin script does not -contain all the characters of the C<Basic Latin> block (also known as -the ASCII): it includes only the letters, and not, for example, the digits -or the punctuation. - -For blocks see http://www.unicode.org/Public/UNIDATA/Blocks.txt - -For scripts see UTR #24: http://www.unicode.org/unicode/reports/tr24/ - -=head2 Matching Scripts and Blocks - -Scripts are matched with the regular-expression construct -C<\p{...}> (e.g. C<\p{Tibetan}> matches characters of the Tibetan script), -while C<\p{In...}> is used for blocks (e.g. C<\p{InTibetan}> matches -any of the 256 code points in the Tibetan block). - -=head2 Code Point Arguments - -A I<code point argument> is either a decimal or a hexadecimal scalar -designating a Unicode character, or C<U+> followed by hexadecimals -designating a Unicode character. In other words, if you want a code -point to be interpreted as a hexadecimal number, you must prefix it -with either C<0x> or C<U+>, because a string like e.g. C<123> will -be interpreted as a decimal code point. Also note that Unicode is -B<not> limited to 16 bits (the number of Unicode characters is -open-ended, in theory unlimited): you may have more than 4 hexdigits. - -=head2 charinrange +=head2 B<charinrange()> In addition to using the C<\p{In...}> and C<\P{In...}> constructs, you can also test whether a code point is in the I<range> as returned by -L</charblock> and L</charscript> or as the values of the hash returned -by L</charblocks> and L</charscripts> by using charinrange(): +L</charblock()> and L</charscript()> or as the values of the hash returned +by L</charblocks()> and L</charscripts()> by using charinrange(): use Unicode::UCD qw(charscript charinrange); @@ -567,18 +634,19 @@ sub general_categories { return dclone \%GENERAL_CATEGORIES; } -=head2 general_categories +=head2 B<general_categories()> use Unicode::UCD 'general_categories'; my $categories = general_categories(); -The general_categories() returns a reference to a hash which has short +This returns a reference to a hash which has short general category names (such as C<Lu>, C<Nd>, C<Zs>, C<S>) as keys and long names (such as C<UppercaseLetter>, C<DecimalNumber>, C<SpaceSeparator>, C<Symbol>) as values. The hash is reversible in case you need to go from the long names to the short names. The general category is the -one returned from charinfo() under the C<category> key. +one returned from +L</charinfo()> under the C<category> key. =cut @@ -605,40 +673,45 @@ my %BIDI_TYPES = 'ON' => 'Other Neutrals', ); -sub bidi_types { - return dclone \%BIDI_TYPES; -} - -=head2 bidi_types +=head2 B<bidi_types()> use Unicode::UCD 'bidi_types'; my $categories = bidi_types(); -The bidi_types() returns a reference to a hash which has the short +This returns a reference to a hash which has the short bidi (bidirectional) type names (such as C<L>, C<R>) as keys and long names (such as C<Left-to-Right>, C<Right-to-Left>) as values. The hash is reversible in case you need to go from the long names to the -short names. The bidi type is the one returned from charinfo() +short names. The bidi type is the one returned from +L</charinfo()> under the C<bidi> key. For the exact meaning of the various bidi classes the Unicode TR9 is recommended reading: -http://www.unicode.org/reports/tr9/tr9-17.html +L<http://www.unicode.org/reports/tr9/> (as of Unicode 5.0.0) =cut -=head2 compexcl +sub bidi_types { + return dclone \%BIDI_TYPES; +} + +=head2 B<compexcl()> use Unicode::UCD 'compexcl'; - my $compexcl = compexcl("09dc"); + my $compexcl = compexcl(0x09dc); -The compexcl() returns the composition exclusion (that is, if the -character should not be produced during a precomposition) of the -character specified by a B<code point argument>. +This returns B<true> if the +L</code point argument> should not be produced by composition normalization, +B<AND> if that fact is not otherwise determinable from the Unicode data base. +It currently does not return B<true> if the code point has a decomposition +consisting of another single code point, nor if its decomposition starts +with a code point whose combining class is non-zero. Code points that meet +either of these conditions should also not be produced by composition +normalization. -If there is a composition exclusion for the character, true is -returned. Otherwise, false is returned. +It returns B<false> otherwise. =cut @@ -670,46 +743,126 @@ sub compexcl { return exists $COMPEXCL{$code}; } -=head2 casefold +=head2 B<casefold()> use Unicode::UCD 'casefold'; - my $casefold = casefold("00DF"); + my $casefold = casefold(0xDF); + if (defined $casefold) { + my @full_fold_hex = split / /, $casefold->{'full'}; + my $full_fold_string = + join "", map {chr(hex($_))} @full_fold_hex; + my @turkic_fold_hex = + split / /, ($casefold->{'turkic'} ne "") + ? $casefold->{'turkic'} + : $casefold->{'full'}; + my $turkic_fold_string = + join "", map {chr(hex($_))} @turkic_fold_hex; + } + if (defined $casefold && $casefold->{'simple'} ne "") { + my $simple_fold_hex = $casefold->{'simple'}; + my $simple_fold_string = chr(hex($simple_fold_hex)); + } -The casefold() returns the locale-independent case folding of the -character specified by a B<code point argument>. +This returns the (almost) locale-independent case folding of the +character specified by the L</code point argument>. -If there is a case folding for that character, a reference to a hash +If there is no case folding for that code point, B<undef> is returned. + +If there is a case folding for that code point, a reference to a hash with the following fields is returned: - key +=over + +=item B<code> + +the input L</code point argument> expressed in hexadecimal, with leading zeros +added if necessary to make it contain at least four hexdigits + +=item B<full> + +one or more codes (separated by spaces) that taken in order give the +code points for the case folding for I<code>. +Each has at least four hexdigits. + +=item B<simple> + +is empty, or is exactly one code with at least four hexdigits which can be used +as an alternative case folding when the calling program cannot cope with the +fold being a sequence of multiple code points. If I<full> is just one code +point, then I<simple> equals I<full>. If there is no single code point folding +defined for I<code>, then I<simple> is the empty string. Otherwise, it is an +inferior, but still better-than-nothing alternative folding to I<full>. + +=item B<mapping> + +is the same as I<simple> if I<simple> is not empty, and it is the same as I<full> +otherwise. It can be considered to be the simplest possible folding for +I<code>. It is defined primarily for backwards compatibility. + +=item B<status> - code code point with at least four hexdigits - status "C", "F", "S", or "I" - mapping one or more codes separated by spaces +is C<C> (for C<common>) if the best possible fold is a single code point +(I<simple> equals I<full> equals I<mapping>). It is C<S> if there are distinct +folds, I<simple> and I<full> (I<mapping> equals I<simple>). And it is C<F> if +there only a I<full> fold (I<mapping> equals I<full>; I<simple> is empty). Note +that this +describes the contents of I<mapping>. It is defined primarily for backwards +compatibility. -The meaning of the I<status> is as follows: +On versions 3.1 and earlier of Unicode, I<status> can also be +C<I> which is the same as C<C> but is a special case for dotted uppercase I and +dotless lowercase i: - C common case folding, common mappings shared - by both simple and full mappings - F full case folding, mappings that cause strings - to grow in length. Multiple characters are separated - by spaces - S simple case folding, mappings to single characters - where different from F - I special case for dotted uppercase I and - dotless lowercase i - - If this mapping is included, the result is - case-insensitive, but dotless and dotted I's - are not distinguished - - If this mapping is excluded, the result is not - fully case-insensitive, but dotless and dotted - I's are distinguished +=over -If there is no case folding for that character, C<undef> is returned. +=item B<*> + +If you use this C<I> mapping, the result is case-insensitive, +but dotless and dotted I's are not distinguished + +=item B<*> + +If you exclude this C<I> mapping, the result is not fully case-insensitive, but +dotless and dotted I's are distinguished + +=back + +=item B<turkic> + +contains any special folding for Turkic languages. For versions of Unicode +starting with 3.2, this field is empty unless I<code> has a different folding +in Turkic languages, in which case it is one or more codes (separated by +spaces) that taken in order give the code points for the case folding for +I<code> in those languages. +Each code has at least four hexdigits. +Note that this folding does not maintain canonical equivalence without +additional processing. + +For versions of Unicode 3.1 and earlier, this field is empty unless there is a +special folding for Turkic languages, in which case I<status> is C<I>, and +I<mapping>, I<full>, I<simple>, and I<turkic> are all equal. + +=back + +Programs that want complete generality and the best folding results should use +the folding contained in the I<full> field. But note that the fold for some +code points will be a sequence of multiple code points. + +Programs that can't cope with the fold mapping being multiple code points can +use the folding contained in the I<simple> field, with the loss of some +generality. In Unicode 5.1, about 7% of the defined foldings have no single +code point folding. + +The I<mapping> and I<status> fields are provided for backwards compatibility for +existing programs. They contain the same values as in previous versions of +this function. + +Locale is not completely independent. The I<turkic> field contains results to +use when the locale is a Turkic language. For more information about case mappings see -http://www.unicode.org/unicode/reports/tr21/ +L<http://www.unicode.org/unicode/reports/tr21> =cut @@ -720,11 +873,45 @@ sub _casefold { if (openunicode(\$CASEFOLDFH, "CaseFolding.txt")) { local $_; while (<$CASEFOLDFH>) { - if (/^([0-9A-F]+); ([CFSI]); ([0-9A-F]+(?: [0-9A-F]+)*);/) { + if (/^([0-9A-F]+); ([CFIST]); ([0-9A-F]+(?: [0-9A-F]+)*);/) { my $code = hex($1); - $CASEFOLD{$code} = { code => $1, - status => $2, - mapping => $3 }; + $CASEFOLD{$code}{'code'} = $1; + $CASEFOLD{$code}{'turkic'} = "" unless + defined $CASEFOLD{$code}{'turkic'}; + if ($2 eq 'C' || $2 eq 'I') { # 'I' is only on 3.1 and + # earlier Unicodes + # Both entries there (I + # only checked 3.1) are + # the same as C, and + # there are no other + # entries for those + # codepoints, so treat + # as if C, but override + # the turkic one for + # 'I'. + $CASEFOLD{$code}{'status'} = $2; + $CASEFOLD{$code}{'full'} = $CASEFOLD{$code}{'simple'} = + $CASEFOLD{$code}{'mapping'} = $3; + $CASEFOLD{$code}{'turkic'} = $3 if $2 eq 'I'; + } elsif ($2 eq 'F') { + $CASEFOLD{$code}{'full'} = $3; + unless (defined $CASEFOLD{$code}{'simple'}) { + $CASEFOLD{$code}{'simple'} = ""; + $CASEFOLD{$code}{'mapping'} = $3; + $CASEFOLD{$code}{'status'} = $2; + } + } elsif ($2 eq 'S') { + + + # There can't be a simple without a full, and simple + # overrides all but full + + $CASEFOLD{$code}{'simple'} = $3; + $CASEFOLD{$code}{'mapping'} = $3; + $CASEFOLD{$code}{'status'} = $2; + } elsif ($2 eq 'T') { + $CASEFOLD{$code}{'turkic'} = $3; + } # else can't happen because only [CIFST] are possible } } close($CASEFOLDFH); @@ -743,54 +930,85 @@ sub casefold { return $CASEFOLD{$code}; } -=head2 casespec +=head2 B<casespec()> use Unicode::UCD 'casespec'; - my $casespec = casespec("FB00"); + my $casespec = casespec(0xFB00); -The casespec() returns the potentially locale-dependent case mapping -of the character specified by a B<code point argument>. The mapping -may change the length of the string (which the basic Unicode case -mappings as returned by charinfo() never do). +This returns the potentially locale-dependent case mappings of the L</code point +argument>. The mappings may be longer than a single code point (which the basic +Unicode case mappings as returned by L</charinfo()> never are). -If there is a case folding for that character, a reference to a hash -with the following fields is returned: +If there are no case mappings for the L</code point argument>, or if all three +possible mappings (I<lower>, I<title> and I<upper>) result in single code +points and are locale independent and uncondtional, B<undef> is returned. + +Otherwise, a reference to a hash giving the mappings (or a reference to a hash +of such hashes, explained below) is returned. + +The keys in the bottom layer hash with the meanings of their values are: + +=over + +=item B<code> + +the input L</code point argument> expressed in hexadecimal, with leading zeros +added if necessary to make it contain at least four hexdigits + +=item B<lower> + +one or more codes (separated by spaces) that taken in order give the +code points for the lower case of I<code>. +Each has at least four hexdigits. + +=item B<title> - key +one or more codes (separated by spaces) that taken in order give the +code points for the title case of I<code>. +Each has at least four hexdigits. - code code point with at least four hexdigits - lower lowercase - title titlecase - upper uppercase - condition condition list (may be undef) +=item B<lower> -The C<condition> is optional. Where present, it consists of one or -more I<locales> or I<contexts>, separated by spaces (other than as -used to separate elements, spaces are to be ignored). A condition -list overrides the normal behavior if all of the listed conditions are -true. Case distinctions in the condition list are not significant. +one or more codes (separated by spaces) that taken in order give the +code points for the upper case of I<code>. +Each has at least four hexdigits. + +=item B<condition> + +the conditions for the mappings to be valid. +If B<undef>, the mappings are always valid. +When defined, this field is a list of conditions, +all of which must be true for the mappings to be valid. +The list consists of one or more +I<locales> (see below) +and/or I<contexts> (explained in the next paragraph), +separated by spaces. +(Other than as used to separate elements, spaces are to be ignored.) +Case distinctions in the condition list are not significant. Conditions preceded by "NON_" represent the negation of the condition. -Note that when there are multiple case folding definitions for a -single code point because of different locales, the value returned by -casespec() is a hash reference which has the locales as the keys and -hash references as described above as the values. +A I<context> is one of those defined in the Unicode standard. +For Unicode 5.1, they are defined in Section 3.13 C<Default Case Operations> +available at +L<http://www.unicode.org/versions/Unicode5.1.0/> -A I<locale> is defined as a 2-letter ISO 3166 country code, possibly +=back + +If the return value is to a hash of hashes, it is because there are multiple +case mapping definitions for a single code point +(because of different rules for different locales). +Each sub-hash is of the form above, and the keys of the outer hash are +the locales, which are +defined as 2-letter ISO 3166 country codes, possibly followed by a "_" and a 2-letter ISO language code (possibly followed -by a "_" and a variant code). You can find the lists of those codes, +by a "_" and a variant code). You can find the lists of all possible locales, see L<Locale::Country> and L<Locale::Language>. - -A I<context> is one of the following choices: - - FINAL The letter is not followed by a letter of - general category L (e.g. Ll, Lt, Lu, Lm, or Lo) - MODERN The mapping is only used for modern text - AFTER_i The last base character was "i" (U+0069) +(In Unicode 5.1, the only locales returned by this function +are C<lt>, C<tr>, and C<az>.) For more information about case mappings see -http://www.unicode.org/unicode/reports/tr21/ +L<http://www.unicode.org/unicode/reports/tr21/> =cut @@ -861,7 +1079,7 @@ sub casespec { return ref $CASESPEC{$code} ? dclone $CASESPEC{$code} : $CASESPEC{$code}; } -=head2 namedseq() +=head2 B<namedseq()> use Unicode::UCD 'namedseq'; @@ -870,15 +1088,16 @@ sub casespec { my %namedseq = namedseq(); If used with a single argument in a scalar context, returns the string -consisting of the code points of the named sequence, or C<undef> if no +consisting of the code points of the named sequence, or B<undef> if no named sequence by that name exists. If used with a single argument in -a list context, returns list of the code points. If used with no +a list context, it returns the list of the code points. If used with no arguments in a list context, returns a hash with the names of the named sequences as the keys and the named sequences as strings as -the values. Otherwise, returns C<undef> or empty list depending +the values. Otherwise, it returns B<undef> or an empty list depending on the context. -(New from Unicode 4.1.0) +This function only operates on officially approved (not provisional) named +sequences. =cut @@ -920,10 +1139,9 @@ sub namedseq { =head2 Unicode::UCD::UnicodeVersion -Unicode::UCD::UnicodeVersion() returns the version of the Unicode -Character Database, in other words, the version of the Unicode -standard the database implements. The version is a string -of numbers delimited by dots (C<'.'>). +This returns the version of the Unicode Character Database, in other words, the +version of the Unicode standard the database implements. The version is a +string of numbers delimited by dots (C<'.'>). =cut @@ -940,6 +1158,32 @@ sub UnicodeVersion { return $UNICODEVERSION; } +=head2 B<Blocks versus Scripts> + +The difference between a block and a script is that scripts are closer +to the linguistic notion of a set of code points required to present +languages, while block is more of an artifact of the Unicode code point +numbering and separation into blocks of (mostly) 256 code points. + +For example the Latin B<script> is spread over several B<blocks>, such +as C<Basic Latin>, C<Latin 1 Supplement>, C<Latin Extended-A>, and +C<Latin Extended-B>. On the other hand, the Latin script does not +contain all the characters of the C<Basic Latin> block (also known as +ASCII): it includes only the letters, and not, for example, the digits +or the punctuation. + +For blocks see L<http://www.unicode.org/Public/UNIDATA/Blocks.txt> + +For scripts see UTR #24: L<http://www.unicode.org/unicode/reports/tr24/> + +=head2 B<Matching Scripts and Blocks> + +Scripts are matched with the regular-expression construct +C<\p{...}> (e.g. C<\p{Tibetan}> matches characters of the Tibetan script), +while C<\p{In...}> is used for blocks (e.g. C<\p{InTibetan}> matches +any of the 256 code points in the Tibetan block). + + =head2 Implementation Note The first use of charinfo() opens a read-only filehandle to the Unicode @@ -951,6 +1195,8 @@ if you are wondering where one of your filehandles went, that's where. Does not yet support EBCDIC platforms. +L</compexcl()> should give a complete list of excluded code points. + =head1 AUTHOR Jarkko Hietaniemi diff --git a/lib/Unicode/UCD.t b/lib/Unicode/UCD.t index 336254300f..d64c932e34 100644 --- a/lib/Unicode/UCD.t +++ b/lib/Unicode/UCD.t @@ -1,6 +1,6 @@ #!perl -w BEGIN { - if (ord("A") == 193) { + if (ord("A") != 65) { print "1..0 # Skip: EBCDIC\n"; exit 0; } @@ -18,7 +18,7 @@ use strict; use Unicode::UCD; use Test::More; -BEGIN { plan tests => 194 }; +BEGIN { plan tests => 239 }; use Unicode::UCD 'charinfo'; @@ -172,6 +172,26 @@ is($charinfo->{title}, ''); is($charinfo->{block}, 'Mathematical Alphanumeric Symbols'); is($charinfo->{script}, 'Common'); +$charinfo = charinfo(0x9FBA); #Bug 58428 + +is($charinfo->{code}, '9FBA', 'U+9FBA'); +is($charinfo->{name}, 'CJK UNIFIED IDEOGRAPH-9FBA'); +is($charinfo->{category}, 'Lo'); +is($charinfo->{combining}, '0'); +is($charinfo->{bidi}, 'L'); +is($charinfo->{decomposition}, ''); +is($charinfo->{decimal}, ''); +is($charinfo->{digit}, ''); +is($charinfo->{numeric}, ''); +is($charinfo->{mirrored}, 'N'); +is($charinfo->{unicode10}, ''); +is($charinfo->{comment}, ''); +is($charinfo->{upper}, ''); +is($charinfo->{lower}, ''); +is($charinfo->{title}, ''); +is($charinfo->{block}, 'CJK Unified Ideographs'); +is($charinfo->{script}, 'Han'); + use Unicode::UCD qw(charblock charscript); # 0x0590 is in the Hebrew block but unused. @@ -254,6 +274,8 @@ ok(exists $bt->{L}, 'has L'); is($bt->{L}, 'Left-to-Right', 'L is Left-to-Right'); is($bt->{AL}, 'Right-to-Left Arabic', 'AL is Right-to-Left Arabic'); +# If this fails, then maybe one should look at the Unicode changes to see +# what else might need to be updated. is(Unicode::UCD::UnicodeVersion, '5.1.0', 'UnicodeVersion'); use Unicode::UCD qw(compexcl); @@ -267,15 +289,70 @@ my $casefold; $casefold = casefold(0x41); -ok($casefold->{code} eq '0041' && - $casefold->{status} eq 'C' && - $casefold->{mapping} eq '0061', 'casefold 0x41'); +is($casefold->{code}, '0041', 'casefold 0x41 code'); +is($casefold->{status}, 'C', 'casefold 0x41 status'); +is($casefold->{mapping}, '0061', 'casefold 0x41 mapping'); +is($casefold->{full}, '0061', 'casefold 0x41 full'); +is($casefold->{simple}, '0061', 'casefold 0x41 simple'); +is($casefold->{turkic}, "", 'casefold 0x41 turkic'); $casefold = casefold(0xdf); -ok($casefold->{code} eq '00DF' && - $casefold->{status} eq 'F' && - $casefold->{mapping} eq '0073 0073', 'casefold 0xDF'); +is($casefold->{code}, '00DF', 'casefold 0xDF code'); +is($casefold->{status}, 'F', 'casefold 0xDF status'); +is($casefold->{mapping}, '0073 0073', 'casefold 0xDF mapping'); +is($casefold->{full}, '0073 0073', 'casefold 0xDF full'); +is($casefold->{simple}, "", 'casefold 0xDF simple'); +is($casefold->{turkic}, "", 'casefold 0xDF turkic'); + +# Do different tests depending on if version <= 3.1, or not. +(my $version = Unicode::UCD::UnicodeVersion) =~ /^(\d+)\.(\d+)/; +if (defined $1 && ($1 <= 2 || $1 == 3 && defined $2 && $2 <= 1)) { + $casefold = casefold(0x130); + + is($casefold->{code}, '0130', 'casefold 0x130 code'); + is($casefold->{status}, 'I' , 'casefold 0x130 status'); + is($casefold->{mapping}, '0069', 'casefold 0x130 mapping'); + is($casefold->{full}, '0069', 'casefold 0x130 full'); + is($casefold->{simple}, "0069", 'casefold 0x130 simple'); + is($casefold->{turkic}, "0069", 'casefold 0x130 turkic'); + + $casefold = casefold(0x131); + + is($casefold->{code}, '0131', 'casefold 0x131 code'); + is($casefold->{status}, 'I' , 'casefold 0x131 status'); + is($casefold->{mapping}, '0069', 'casefold 0x131 mapping'); + is($casefold->{full}, '0069', 'casefold 0x131 full'); + is($casefold->{simple}, "0069", 'casefold 0x131 simple'); + is($casefold->{turkic}, "0069", 'casefold 0x131 turkic'); +} else { + $casefold = casefold(0x49); + + is($casefold->{code}, '0049', 'casefold 0x49 code'); + is($casefold->{status}, 'C' , 'casefold 0x49 status'); + is($casefold->{mapping}, '0069', 'casefold 0x49 mapping'); + is($casefold->{full}, '0069', 'casefold 0x49 full'); + is($casefold->{simple}, "0069", 'casefold 0x49 simple'); + is($casefold->{turkic}, "0131", 'casefold 0x49 turkic'); + + $casefold = casefold(0x130); + + is($casefold->{code}, '0130', 'casefold 0x130 code'); + is($casefold->{status}, 'F' , 'casefold 0x130 status'); + is($casefold->{mapping}, '0069 0307', 'casefold 0x130 mapping'); + is($casefold->{full}, '0069 0307', 'casefold 0x130 full'); + is($casefold->{simple}, "", 'casefold 0x130 simple'); + is($casefold->{turkic}, "0069", 'casefold 0x130 turkic'); +} + +$casefold = casefold(0x1F88); + +is($casefold->{code}, '1F88', 'casefold 0x1F88 code'); +is($casefold->{status}, 'S' , 'casefold 0x1F88 status'); +is($casefold->{mapping}, '1F80', 'casefold 0x1F88 mapping'); +is($casefold->{full}, '1F00 03B9', 'casefold 0x1F88 full'); +is($casefold->{simple}, '1F80', 'casefold 0x1F88 simple'); +is($casefold->{turkic}, "", 'casefold 0x1F88 turkic'); ok(!casefold(0x20)); |