{ "content": [ { "type": "text", "text": "# Unicode::UCD (perldoc)\n\n## NAME\n\nUnicode::UCD - Unicode character database\n\n## SYNOPSIS\n\nuse Unicode::UCD 'charinfo';\nmy $charinfo = charinfo($codepoint);\nuse Unicode::UCD 'charprop';\nmy $value = charprop($codepoint, $property);\nuse Unicode::UCD 'charpropsall';\nmy $allvalueshashref = charpropsall($codepoint);\nuse Unicode::UCD 'casefold';\nmy $casefold = casefold($codepoint);\nuse Unicode::UCD 'allcasefolds';\nmy $allcasefoldsref = allcasefolds();\nuse Unicode::UCD 'casespec';\nmy $casespec = casespec($codepoint);\nuse Unicode::UCD 'charblock';\nmy $charblock = charblock($codepoint);\nuse Unicode::UCD 'charscript';\nmy $charscript = charscript($codepoint);\nuse Unicode::UCD 'charblocks';\nmy $charblocks = charblocks();\nuse Unicode::UCD 'charscripts';\nmy $charscripts = charscripts();\nuse Unicode::UCD qw(charscript charinrange);\nmy $range = charscript($script);\nprint \"looks like $script\\n\" if charinrange($range, $codepoint);\nuse Unicode::UCD qw(generalcategories biditypes);\nmy $categories = generalcategories();\nmy $types = biditypes();\nuse Unicode::UCD 'propaliases';\nmy @spacenames = propaliases(\"space\");\nuse Unicode::UCD 'propvaluealiases';\nmy @gcpunctnames = propvaluealiases(\"Gc\", \"Punct\");\nuse Unicode::UCD 'propvalues';\nmy @allEAshortnames = propvalues(\"EastAsianWidth\");\nuse Unicode::UCD 'propinvlist';\nmy @puncts = propinvlist(\"gc=punctuation\");\nuse Unicode::UCD 'propinvmap';\nmy ($listref, $mapref, $format, $missing)\n= propinvmap(\"General Category\");\nuse Unicode::UCD 'searchinvlist';\nmy $index = searchinvlist(\\@invlist, $codepoint);\n# The following function should be used only internally in\n# implementations of the Unicode Normalization Algorithm, and there\n# are better choices than it.\nuse Unicode::UCD 'compexcl';\nmy $compexcl = compexcl($codepoint);\nuse Unicode::UCD 'namedseq';\nmy $namedseq = namedseq($namedsequencename);\nmy $unicodeversion = Unicode::UCD::UnicodeVersion();\nmy $converttonumeric =\nUnicode::UCD::num(\"\\N{RUMI DIGIT ONE}\\N{RUMI DIGIT TWO}\");\n\n## DESCRIPTION\n\nThe Unicode::UCD module offers a series of functions that provide a simple interface to the\nUnicode Character Database.\n\n## Sections\n\n- **NAME**\n- **SYNOPSIS**\n- **DESCRIPTION** (8 subsections)\n- **AUTHOR**\n\nUse structuredContent.sections for detailed options, examples, and full documentation.\n" } ], "structuredContent": { "command": "Unicode::UCD", "section": "", "mode": "perldoc", "summary": "Unicode::UCD - Unicode character database", "synopsis": "use Unicode::UCD 'charinfo';\nmy $charinfo = charinfo($codepoint);\nuse Unicode::UCD 'charprop';\nmy $value = charprop($codepoint, $property);\nuse Unicode::UCD 'charpropsall';\nmy $allvalueshashref = charpropsall($codepoint);\nuse Unicode::UCD 'casefold';\nmy $casefold = casefold($codepoint);\nuse Unicode::UCD 'allcasefolds';\nmy $allcasefoldsref = allcasefolds();\nuse Unicode::UCD 'casespec';\nmy $casespec = casespec($codepoint);\nuse Unicode::UCD 'charblock';\nmy $charblock = charblock($codepoint);\nuse Unicode::UCD 'charscript';\nmy $charscript = charscript($codepoint);\nuse Unicode::UCD 'charblocks';\nmy $charblocks = charblocks();\nuse Unicode::UCD 'charscripts';\nmy $charscripts = charscripts();\nuse Unicode::UCD qw(charscript charinrange);\nmy $range = charscript($script);\nprint \"looks like $script\\n\" if charinrange($range, $codepoint);\nuse Unicode::UCD qw(generalcategories biditypes);\nmy $categories = generalcategories();\nmy $types = biditypes();\nuse Unicode::UCD 'propaliases';\nmy @spacenames = propaliases(\"space\");\nuse Unicode::UCD 'propvaluealiases';\nmy @gcpunctnames = propvaluealiases(\"Gc\", \"Punct\");\nuse Unicode::UCD 'propvalues';\nmy @allEAshortnames = propvalues(\"EastAsianWidth\");\nuse Unicode::UCD 'propinvlist';\nmy @puncts = propinvlist(\"gc=punctuation\");\nuse Unicode::UCD 'propinvmap';\nmy ($listref, $mapref, $format, $missing)\n= propinvmap(\"General Category\");\nuse Unicode::UCD 'searchinvlist';\nmy $index = searchinvlist(\\@invlist, $codepoint);\n# The following function should be used only internally in\n# implementations of the Unicode Normalization Algorithm, and there\n# are better choices than it.\nuse Unicode::UCD 'compexcl';\nmy $compexcl = compexcl($codepoint);\nuse Unicode::UCD 'namedseq';\nmy $namedseq = namedseq($namedsequencename);\nmy $unicodeversion = Unicode::UCD::UnicodeVersion();\nmy $converttonumeric =\nUnicode::UCD::num(\"\\N{RUMI DIGIT ONE}\\N{RUMI DIGIT TWO}\");", "tldr_summary": null, "tldr_examples": [], "tldr_source": null, "flags": [], "examples": [], "see_also": [], "section_outline": [ { "name": "NAME", "lines": 2, "subsections": [] }, { "name": "SYNOPSIS", "lines": 71, "subsections": [] }, { "name": "DESCRIPTION", "lines": 279, "subsections": [ { "name": "prop_invmap", "lines": 1 }, { "name": "prop_values", "lines": 12 }, { "name": "prop_invmap", "lines": 1080 }, { "name": "Unicode::UCD::UnicodeVersion", "lines": 4 }, { "name": "Blocks versus Scripts", "lines": 14 }, { "name": "Matching Scripts and Blocks", "lines": 4 }, { "name": "Old-style versus new-style block names", "lines": 31 }, { "name": "Use with older Unicode versions", "lines": 6 } ] }, { "name": "AUTHOR", "lines": 2, "subsections": [] } ], "sections": { "NAME": { "content": "Unicode::UCD - Unicode character database\n", "subsections": [] }, "SYNOPSIS": { "content": "use Unicode::UCD 'charinfo';\nmy $charinfo = charinfo($codepoint);\n\nuse Unicode::UCD 'charprop';\nmy $value = charprop($codepoint, $property);\n\nuse Unicode::UCD 'charpropsall';\nmy $allvalueshashref = charpropsall($codepoint);\n\nuse Unicode::UCD 'casefold';\nmy $casefold = casefold($codepoint);\n\nuse Unicode::UCD 'allcasefolds';\nmy $allcasefoldsref = allcasefolds();\n\nuse Unicode::UCD 'casespec';\nmy $casespec = casespec($codepoint);\n\nuse Unicode::UCD 'charblock';\nmy $charblock = charblock($codepoint);\n\nuse Unicode::UCD 'charscript';\nmy $charscript = charscript($codepoint);\n\nuse Unicode::UCD 'charblocks';\nmy $charblocks = charblocks();\n\nuse Unicode::UCD 'charscripts';\nmy $charscripts = charscripts();\n\nuse Unicode::UCD qw(charscript charinrange);\nmy $range = charscript($script);\nprint \"looks like $script\\n\" if charinrange($range, $codepoint);\n\nuse Unicode::UCD qw(generalcategories biditypes);\nmy $categories = generalcategories();\nmy $types = biditypes();\n\nuse Unicode::UCD 'propaliases';\nmy @spacenames = propaliases(\"space\");\n\nuse Unicode::UCD 'propvaluealiases';\nmy @gcpunctnames = propvaluealiases(\"Gc\", \"Punct\");\n\nuse Unicode::UCD 'propvalues';\nmy @allEAshortnames = propvalues(\"EastAsianWidth\");\n\nuse Unicode::UCD 'propinvlist';\nmy @puncts = propinvlist(\"gc=punctuation\");\n\nuse Unicode::UCD 'propinvmap';\nmy ($listref, $mapref, $format, $missing)\n= propinvmap(\"General Category\");\n\nuse Unicode::UCD 'searchinvlist';\nmy $index = searchinvlist(\\@invlist, $codepoint);\n\n# The following function should be used only internally in\n# implementations of the Unicode Normalization Algorithm, and there\n# are better choices than it.\nuse Unicode::UCD 'compexcl';\nmy $compexcl = compexcl($codepoint);\n\nuse Unicode::UCD 'namedseq';\nmy $namedseq = namedseq($namedsequencename);\n\nmy $unicodeversion = Unicode::UCD::UnicodeVersion();\n\nmy $converttonumeric =\nUnicode::UCD::num(\"\\N{RUMI DIGIT ONE}\\N{RUMI DIGIT TWO}\");\n", "subsections": [] }, "DESCRIPTION": { "content": "The Unicode::UCD module offers a series of functions that provide a simple interface to the\nUnicode Character Database.\n\ncode point argument\nSome of the functions are called with a *code point argument*, which is either a decimal or a\nhexadecimal scalar designating a code point in the platform's native character set (extended to\nUnicode), or a string containing \"U+\" followed by hexadecimals designating a Unicode code point.\nA leading 0 will force a hexadecimal interpretation, as will a hexadecimal digit that isn't a\ndecimal digit.\n\nExamples:\n\n223 # Decimal 223 in native character set\n0223 # Hexadecimal 223, native (= 547 decimal)\n0xDF # Hexadecimal DF, native (= 223 decimal)\n'0xDF' # String form of hexadecimal (= 223 decimal)\n'U+DF' # Hexadecimal DF, in Unicode's character set\n(= LATIN SMALL LETTER SHARP S)\n\nNote that the largest code point in Unicode is U+10FFFF.\n\ncharinfo()\nuse Unicode::UCD 'charinfo';\n\nmy $charinfo = charinfo(0x41);\n\nThis returns information about the input \"code point argument\" as a reference to a hash of\nfields as defined by the Unicode standard. If the \"code point argument\" is not assigned in the\nstandard (i.e., has the general category \"Cn\" meaning \"Unassigned\") or is a non-character\n(meaning it is guaranteed to never be assigned in the standard), \"undef\" is returned.\n\nFields that aren't applicable to the particular code point argument exist in the returned hash,\nand are empty.\n\nFor results that are less \"raw\" than this function returns, or to get the values for any\nproperty, not just the few covered by this function, use the \"charprop()\" function.\n\nThe keys in the hash with the meanings of their values are:\n\ncode\nthe input native \"code point argument\" expressed in hexadecimal, with leading zeros added if\nnecessary to make it contain at least four hexdigits\n\nname\nname of *code*, all IN UPPER CASE. Some control-type code points do not have names. This\nfield will be empty for \"Surrogate\" and \"Private Use\" code points, and for the others\nwithout a name, it will contain a description enclosed in angle brackets, like \"\".\n\ncategory\nThe short name of the general category of *code*. This will match one of the keys in the\nhash returned by \"generalcategories()\".\n\nThe \"propvaluealiases()\" function can be used to get all the synonyms of the category\nname.\n\ncombining\nthe combining class number for *code* used in the Canonical Ordering Algorithm. For Unicode\n5.1, this is described in Section 3.11 \"Canonical Ordering Behavior\" available at\n\n\nThe \"propvaluealiases()\" function can be used to get all the synonyms of the combining\nclass number.\n\nbidi\nbidirectional type of *code*. This will match one of the keys in the hash returned by\n\"biditypes()\".\n\nThe \"propvaluealiases()\" function can be used to get all the synonyms of the bidi type\nname.\n\ndecomposition\nis empty if *code* has no decomposition; or is one or more codes (separated by spaces) that,\ntaken in order, represent a decomposition for *code*. Each has at least four hexdigits. The\ncodes may be preceded by a word enclosed in angle brackets, then a space, like \" \",\ngiving the type of decomposition\n\nThis decomposition may be an intermediate one whose components are also decomposable. Use\nUnicode::Normalize to get the final decomposition in one step.\n\ndecimal\nif *code* represents a decimal digit this is its integer numeric value\n\ndigit\nif *code* represents some other digit-like number, this is its integer numeric value\n\nnumeric\nif *code* represents a whole or rational number, this is its numeric value. Rational values\nare expressed as a string like \"1/4\".\n\nmirrored\n\"Y\" or \"N\" designating if *code* is mirrored in bidirectional text\n\nunicode10\nname of *code* in the Unicode 1.0 standard if one existed for this code point and is\ndifferent from the current name\n\ncomment\nAs of Unicode 6.0, this is always empty.\n\nupper\nis, if non-empty, the uppercase mapping for *code* expressed as at least four hexdigits.\nThis indicates that the full uppercase mapping is a single character, and is identical to\nthe simple (single-character only) mapping. When this field is empty, it means that the\nsimple uppercase mapping is *code* itself; you'll need some other means, (like \"charprop()\"\nor \"casespec()\" to get the full mapping.\n\nlower\nis, if non-empty, the lowercase mapping for *code* expressed as at least four hexdigits.\nThis indicates that the full lowercase mapping is a single character, and is identical to\nthe simple (single-character only) mapping. When this field is empty, it means that the\nsimple lowercase mapping is *code* itself; you'll need some other means, (like \"charprop()\"\nor \"casespec()\" to get the full mapping.\n\ntitle\nis, if non-empty, the titlecase mapping for *code* expressed as at least four hexdigits.\nThis indicates that the full titlecase mapping is a single character, and is identical to\nthe simple (single-character only) mapping. When this field is empty, it means that the\nsimple titlecase mapping is *code* itself; you'll need some other means, (like \"charprop()\"\nor \"casespec()\" to get the full mapping.\n\nblock\nthe block *code* belongs to (used in \"\\p{Blk=...}\"). The \"propvaluealiases()\" function can\nbe used to get all the synonyms of the block name.\n\nSee \"Blocks versus Scripts\".\n\nscript\nthe script *code* belongs to. The \"propvaluealiases()\" function can be used to get all the\nsynonyms of the script name. Note that this is the older \"Script\" property value, and not\nthe improved \"ScriptExtensions\" value.\n\nSee \"Blocks versus Scripts\".\n\nNote that you cannot do (de)composition and casing based solely on the *decomposition*,\n*combining*, *lower*, *upper*, and *title* fields; you will need also the \"casespec()\" function\nand the \"CompositionExclusion\" property. (Or you could just use the lc(), uc(), and ucfirst()\nfunctions, and the Unicode::Normalize module.)\n\ncharprop()\nuse Unicode::UCD 'charprop';\n\nprint charprop(0x41, \"Gc\"), \"\\n\";\nprint charprop(0x61, \"GeneralCategory\"), \"\\n\";\n\nprints\nLu\nLl\n\nThis returns the value of the Unicode property given by the second parameter for the \"code point\nargument\" given by the first.\n\nThe passed-in property may be specified as any of the synonyms returned by \"propaliases()\".\n\nThe return value is always a scalar, either a string or a number. For properties where there are\nsynonyms for the values, the synonym returned by this function is the longest, most descriptive\nform, the one returned by \"propvaluealiases()\" when called in a scalar context. Of course, you\ncan call \"propvaluealiases()\" on the result to get other synonyms.\n\nThe return values are more \"cooked\" than the \"charinfo()\" ones. For example, the \"uc\" property\nvalue is the actual string containing the full uppercase mapping of the input code point. You\nhave to go to extra trouble with \"charinfo\" to get this value from its \"upper\" hash element when\nthe full mapping differs from the simple one.\n\nSpecial note should be made of the return values for a few properties:\n\nBlock\nThe value returned is the new-style (see \"Old-style versus new-style block names\").\n\nDecompositionMapping\nLike \"charinfo()\", the result may be an intermediate decomposition whose components are also\ndecomposable. Use Unicode::Normalize to get the final decomposition in one step.\n\nUnlike \"charinfo()\", this does not include the decomposition type. Use the\n\"DecompositionType\" property to get that.\n\nNameAlias\nIf the input code point's name has more than one synonym, they are returned joined into a\nsingle comma-separated string.\n\nNumericValue\nIf the result is a fraction, it is converted into a floating point number to the accuracy of\nyour platform.\n\nScriptExtensions\nIf the result is multiple script names, they are returned joined into a single\ncomma-separated string.\n\nWhen called with a property that is a Perl extension that isn't expressible in a compound form,\nthis function currently returns \"undef\", as the only two possible values are *true* or *false*\n(1 or 0 I suppose). This behavior may change in the future, so don't write code that relies on\nit. \"PresentIn\" is a Perl extension that is expressible in a bipartite or compound form (for\nexample, \"\\p{PresentIn=4.0}\"), so \"charprop\" accepts it. But \"Any\" is a Perl extension that\nisn't expressible that way, so \"charprop\" returns \"undef\" for it. Also \"charprop\" returns\n\"undef\" for all Perl extensions that are internal-only.\n\ncharpropsall()\nuse Unicode::UCD 'charpropsall';\n\nmy $%propertiesofAhashref = charpropsall(\"U+41\");\n\nThis returns a reference to a hash whose keys are all the distinct Unicode (no Perl extension)\nproperties, and whose values are the respective values for those properties for the input \"code\npoint argument\".\n\nEach key is the property name in its longest, most descriptive form. The values are what\n\"charprop()\" would return.\n\nThis function is expensive in time and memory.\n\ncharblock()\nuse Unicode::UCD 'charblock';\n\nmy $charblock = charblock(0x41);\nmy $charblock = charblock(1234);\nmy $charblock = charblock(0x263a);\nmy $charblock = charblock(\"U+263a\");\n\nmy $range = charblock('Armenian');\n\nWith a \"code point argument\" \"charblock()\" returns the *block* the code point belongs to, e.g.\n\"Basic Latin\". The old-style block name is returned (see \"Old-style versus new-style block\nnames\"). The \"propvaluealiases()\" function can be used to get all the synonyms of the block\nname.\n\nIf the code point is unassigned, this returns the block it would belong to if it were assigned.\n(If the Unicode version being used is so early as to not have blocks, all code points are\nconsidered to be in \"NoBlock\".)\n\nSee also \"Blocks versus Scripts\".\n\nIf supplied with an argument that can't be a code point, \"charblock()\" tries to do the opposite\nand interpret the argument as an old-style block name. On an ASCII platform, the return value is\na *range set* with one range: an anonymous array with a single element that consists of another\nanonymous array whose first element is the first code point in the block, and whose second\nelement is the final code point in the block. On an EBCDIC platform, the first two Unicode\nblocks are not contiguous. Their range sets are lists containing *start-of-range*,\n*end-of-range* code point pairs. You can test whether a code point is in a range set using the\n\"charinrange()\" function. (To be precise, each *range set* contains a third array element, after\nthe range boundary ones: the oldstyle block name.)\n\nIf the argument to \"charblock()\" is not a known block, \"undef\" is returned.\n\ncharscript()\nuse Unicode::UCD 'charscript';\n\nmy $charscript = charscript(0x41);\nmy $charscript = charscript(1234);\nmy $charscript = charscript(\"U+263a\");\n\nmy $range = charscript('Thai');\n\nWith a \"code point argument\", \"charscript()\" returns the *script* the code point belongs to,\ne.g., \"Latin\", \"Greek\", \"Han\". If the code point is unassigned or the Unicode version being used\nis so early that it doesn't have scripts, this function returns \"Unknown\". The\n\"propvaluealiases()\" function can be used to get all the synonyms of the script name.\n\nNote that the ScriptExtensions property is an improved version of the Script property, and you\nshould probably be using that instead, with the \"charprop()\" function.\n\nIf supplied with an argument that can't be a code point, charscript() tries to do the opposite\nand interpret the argument as a script name. The return value is a *range set*: an anonymous\narray of arrays that contain *start-of-range*, *end-of-range* code point pairs. You can test\nwhether a code point is in a range set using the \"charinrange()\" function. (To be precise, each\n*range set* contains a third array element, after the range boundary ones: the script name.)\n\nIf the \"charscript()\" argument is not a known script, \"undef\" is returned.\n\nSee also \"Blocks versus Scripts\".\n\ncharblocks()\nuse Unicode::UCD 'charblocks';\n\nmy $charblocks = charblocks();\n\n\"charblocks()\" returns a reference to a hash with the known block names as the keys, and the\ncode point ranges (see \"charblock()\") as the values.\n\nThe names are in the old-style (see \"Old-style versus new-style block names\").\n", "subsections": [ { "name": "prop_invmap", "content": "" }, { "name": "prop_values", "content": "the code point ranges.\n\nSee also \"Blocks versus Scripts\".\n\ncharscripts()\nuse Unicode::UCD 'charscripts';\n\nmy $charscripts = charscripts();\n\n\"charscripts()\" returns a reference to a hash with the known script names as the keys, and the\ncode point ranges (see \"charscript()\") as the values.\n" }, { "name": "prop_invmap", "content": "Since the ScriptExtensions property is an improved version of the Script property, you should\ninstead use propinvmap(\"scx\").\n\n\"propvalues(\"Script\")\" can be used to get all the known script names as a list, without the\ncode point ranges.\n\nSee also \"Blocks versus Scripts\".\n\ncharinrange()\nIn addition to using the \"\\p{Blk=...}\" and \"\\P{Blk=...}\" constructs, you can also test whether a\ncode point is in the *range* as returned by \"charblock()\" and \"charscript()\" or as the values of\nthe hash returned by \"charblocks()\" and \"charscripts()\" by using \"charinrange()\":\n\nuse Unicode::UCD qw(charscript charinrange);\n\n$range = charscript('Hiragana');\nprint \"looks like hiragana\\n\" if charinrange($range, $codepoint);\n\ngeneralcategories()\nuse Unicode::UCD 'generalcategories';\n\nmy $categories = generalcategories();\n\nThis returns a reference to a hash which has short general category names (such as \"Lu\", \"Nd\",\n\"Zs\", \"S\") as keys and long names (such as \"UppercaseLetter\", \"DecimalNumber\", \"SpaceSeparator\",\n\"Symbol\") as values. The hash is reversible in case you need to go from the long names to the\nshort names. The general category is the one returned from \"charinfo()\" under the \"category\"\nkey.\n\nThe \"propvalues()\" and \"propvaluealiases()\" functions can be used as an alternative to this\nfunction; the first returning a simple list of the short category names; and the second gets all\nthe synonyms of a given category name.\n\nbiditypes()\nuse Unicode::UCD 'biditypes';\n\nmy $categories = biditypes();\n\nThis returns a reference to a hash which has the short bidi (bidirectional) type names (such as\n\"L\", \"R\") as keys and long names (such as \"Left-to-Right\", \"Right-to-Left\") as values. The hash\nis reversible in case you need to go from the long names to the short names. The bidi type is\nthe one returned from \"charinfo()\" under the \"bidi\" key. For the exact meaning of the various\nbidi classes the Unicode TR9 is recommended reading: (as\nof Unicode 5.0.0)\n\nThe \"propvalues()\" and \"propvaluealiases()\" functions can be used as an alternative to this\nfunction; the first returning a simple list of the short bidi type names; and the second gets\nall the synonyms of a given bidi type name.\n\ncompexcl()\nWARNING: Unicode discourages the use of this function or any of the alternative mechanisms\nlisted in this section (the documentation of \"compexcl()\"), except internally in implementations\nof the Unicode Normalization Algorithm. You should be using Unicode::Normalize directly instead\nof these. Using these will likely lead to half-baked results.\n\nuse Unicode::UCD 'compexcl';\n\nmy $compexcl = compexcl(0x09dc);\n\nThis routine returns \"undef\" if the Unicode version being used is so early that it doesn't have\nthis property.\n\n\"compexcl()\" is included for backwards compatibility, but as of Perl 5.12 and more modern\nUnicode versions, for most purposes it is probably more convenient to use one of the following\ninstead:\n\nmy $compexcl = chr(0x09dc) =~ /\\p{CompEx};\nmy $compexcl = chr(0x09dc) =~ /\\p{FullCompositionExclusion};\n\nor even\n\nmy $compexcl = chr(0x09dc) =~ /\\p{CE};\nmy $compexcl = chr(0x09dc) =~ /\\p{CompositionExclusion};\n\nThe first two forms return true if the \"code point argument\" should not be produced by\ncomposition normalization. For the final two forms to return true, it is additionally required\nthat this fact not otherwise be determinable from the Unicode data base.\n\nThis routine behaves identically to the final two forms. That is, it does not return true if the\ncode point has a decomposition consisting of another single code point, nor if its decomposition\nstarts with a code point whose combining class is non-zero. Code points that meet either of\nthese conditions should also not be produced by composition normalization, which is probably why\nyou should use the \"FullCompositionExclusion\" property instead, as shown above.\n\nThe routine returns false otherwise.\n\ncasefold()\nuse Unicode::UCD 'casefold';\n\nmy $casefold = casefold(0xDF);\nif (defined $casefold) {\nmy @fullfoldhex = split / /, $casefold->{'full'};\nmy $fullfoldstring =\njoin \"\", map {chr(hex($))} @fullfoldhex;\nmy @turkicfoldhex =\nsplit / /, ($casefold->{'turkic'} ne \"\")\n? $casefold->{'turkic'}\n: $casefold->{'full'};\nmy $turkicfoldstring =\njoin \"\", map {chr(hex($))} @turkicfoldhex;\n}\nif (defined $casefold && $casefold->{'simple'} ne \"\") {\nmy $simplefoldhex = $casefold->{'simple'};\nmy $simplefoldstring = chr(hex($simplefoldhex));\n}\n\nThis returns the (almost) locale-independent case folding of the character specified by the\n\"code point argument\". (Starting in Perl v5.16, the core function \"fc()\" returns the \"full\"\nmapping (described below) faster than this does, and for entire strings.)\n\nIf there is no case folding for the input code point, \"undef\" is returned.\n\nIf there is a case folding for that code point, a reference to a hash with the following fields\nis returned:\n\ncode\nthe input native \"code point argument\" expressed in hexadecimal, with leading zeros added if\nnecessary to make it contain at least four hexdigits\n\nfull\none or more codes (separated by spaces) that, taken in order, give the code points for the\ncase folding for *code*. Each has at least four hexdigits.\n\nsimple\nis empty, or is exactly one code with at least four hexdigits which can be used as an\nalternative case folding when the calling program cannot cope with the fold being a sequence\nof multiple code points. If *full* is just one code point, then *simple* equals *full*. If\nthere is no single code point folding defined for *code*, then *simple* is the empty string.\nOtherwise, it is an inferior, but still better-than-nothing alternative folding to *full*.\n\nmapping\nis the same as *simple* if *simple* is not empty, and it is the same as *full* otherwise. It\ncan be considered to be the simplest possible folding for *code*. It is defined primarily\nfor backwards compatibility.\n\nstatus\nis \"C\" (for \"common\") if the best possible fold is a single code point (*simple* equals\n*full* equals *mapping*). It is \"S\" if there are distinct folds, *simple* and *full*\n(*mapping* equals *simple*). And it is \"F\" if there is only a *full* fold (*mapping* equals\n*full*; *simple* is empty). Note that this describes the contents of *mapping*. It is\ndefined primarily for backwards compatibility.\n\nFor Unicode versions between 3.1 and 3.1.1 inclusive, *status* can also be \"I\" which is the\nsame as \"C\" but is a special case for dotted uppercase I and dotless lowercase i:\n\n* If you use this \"I\" mapping\nthe result is case-insensitive, but dotless and dotted I's are not distinguished\n\n* If you exclude this \"I\" mapping\nthe result is not fully case-insensitive, but dotless and dotted I's are distinguished\n\nturkic\ncontains any special folding for Turkic languages. For versions of Unicode starting with\n3.2, this field is empty unless *code* has a different folding in Turkic languages, in which\ncase it is one or more codes (separated by spaces) that, taken in order, give the code\npoints for the case folding for *code* in those languages. Each code has at least four\nhexdigits. Note that this folding does not maintain canonical equivalence without additional\nprocessing.\n\nFor Unicode versions between 3.1 and 3.1.1 inclusive, this field is empty unless there is a\nspecial folding for Turkic languages, in which case *status* is \"I\", and *mapping*, *full*,\n*simple*, and *turkic* are all equal.\n\nPrograms that want complete generality and the best folding results should use the folding\ncontained in the *full* field. But note that the fold for some code points will be a sequence of\nmultiple code points.\n\nPrograms that can't cope with the fold mapping being multiple code points can use the folding\ncontained in the *simple* field, with the loss of some generality. In Unicode 5.1, about 7% of\nthe defined foldings have no single code point folding.\n\nThe *mapping* and *status* fields are provided for backwards compatibility for existing\nprograms. They contain the same values as in previous versions of this function.\n\nLocale is not completely independent. The *turkic* field contains results to use when the locale\nis a Turkic language.\n\nFor more information about case mappings see \n\nallcasefolds()\nuse Unicode::UCD 'allcasefolds';\n\nmy $allfoldsref = allcasefolds();\nforeach my $charwithcasefold (sort { $a <=> $b }\nkeys %$allfoldsref)\n{\nprintf \"%04X:\", $charwithcasefold;\nmy $casefold = $allfoldsref->{$charwithcasefold};\n\n# Get folds for $charwithcasefold\n\nmy @fullfoldhex = split / /, $casefold->{'full'};\nmy $fullfoldstring =\njoin \"\", map {chr(hex($))} @fullfoldhex;\nprint \" full=\", join \" \", @fullfoldhex;\nmy @turkicfoldhex =\nsplit / /, ($casefold->{'turkic'} ne \"\")\n? $casefold->{'turkic'}\n: $casefold->{'full'};\nmy $turkicfoldstring =\njoin \"\", map {chr(hex($))} @turkicfoldhex;\nprint \"; turkic=\", join \" \", @turkicfoldhex;\nif (defined $casefold && $casefold->{'simple'} ne \"\") {\nmy $simplefoldhex = $casefold->{'simple'};\nmy $simplefoldstring = chr(hex($simplefoldhex));\nprint \"; simple=$simplefoldhex\";\n}\nprint \"\\n\";\n}\n\nThis returns all the case foldings in the current version of Unicode in the form of a reference\nto a hash. Each key to the hash is the decimal representation of a Unicode character that has a\ncasefold to other than itself. The casefold of a semi-colon is itself, so it isn't in the hash;\nlikewise for a lowercase \"a\", but there is an entry for a capital \"A\". The hash value for each\nkey is another hash, identical to what is returned by \"casefold()\" if called with that code\npoint as its argument. So the value \"allcasefolds()->{ord(\"A\")}'\" is equivalent to\n\"casefold(ord(\"A\"))\";\n\ncasespec()\nuse Unicode::UCD 'casespec';\n\nmy $casespec = casespec(0xFB00);\n\nThis returns the potentially locale-dependent case mappings of the \"code point argument\". The\nmappings may be longer than a single code point (which the basic Unicode case mappings as\nreturned by \"charinfo()\" never are).\n\nIf there are no case mappings for the \"code point argument\", or if all three possible mappings\n(*lower*, *title* and *upper*) result in single code points and are locale independent and\nunconditional, \"undef\" is returned (which means that the case mappings, if any, for the code\npoint are those returned by \"charinfo()\").\n\nOtherwise, a reference to a hash giving the mappings (or a reference to a hash of such hashes,\nexplained below) is returned with the following keys and their meanings:\n\nThe keys in the bottom layer hash with the meanings of their values are:\n\ncode\nthe input native \"code point argument\" expressed in hexadecimal, with leading zeros added if\nnecessary to make it contain at least four hexdigits\n\nlower\none or more codes (separated by spaces) that, taken in order, give the code points for the\nlower case of *code*. Each has at least four hexdigits.\n\ntitle\none or more codes (separated by spaces) that, taken in order, give the code points for the\ntitle case of *code*. Each has at least four hexdigits.\n\nupper\none or more codes (separated by spaces) that, taken in order, give the code points for the\nupper case of *code*. Each has at least four hexdigits.\n\ncondition\nthe conditions for the mappings to be valid. If \"undef\", the mappings are always valid. When\ndefined, this field is a list of conditions, all of which must be true for the mappings to\nbe valid. The list consists of one or more *locales* (see below) and/or *contexts*\n(explained in the next paragraph), separated by spaces. (Other than as used to separate\nelements, spaces are to be ignored.) Case distinctions in the condition list are not\nsignificant. Conditions preceded by \"NON\" represent the negation of the condition.\n\nA *context* is one of those defined in the Unicode standard. For Unicode 5.1, they are\ndefined in Section 3.13 \"Default Case Operations\" available at\n. These are for context-sensitive casing.\n\nThe hash described above is returned for locale-independent casing, where at least one of the\nmappings has length longer than one. If \"undef\" is returned, the code point may have mappings,\nbut if so, all are length one, and are returned by \"charinfo()\". Note that when this function\ndoes return a value, it will be for the complete set of mappings for a code point, even those\nwhose length is one.\n\nIf there are additional casing rules that apply only in certain locales, an additional key for\neach will be defined in the returned hash. Each such key will be its locale name, defined as a\n2-letter ISO 3166 country code, possibly followed by a \"\" and a 2-letter ISO language code\n(possibly followed by a \"\" and a variant code). You can find the lists of all possible locales,\nsee Locale::Country and Locale::Language. (In Unicode 6.0, the only locales returned by this\nfunction are \"lt\", \"tr\", and \"az\".)\n\nEach locale key is a reference to a hash that has the form above, and gives the casing rules for\nthat particular locale, which take precedence over the locale-independent ones when in that\nlocale.\n\nIf the only casing for a code point is locale-dependent, then the returned hash will not have\nany of the base keys, like \"code\", \"upper\", etc., but will contain only locale keys.\n\nFor more information about case mappings see \n\nnamedseq()\nuse Unicode::UCD 'namedseq';\n\nmy $namedseq = namedseq(\"KATAKANA LETTER AINU P\");\nmy @namedseq = namedseq(\"KATAKANA LETTER AINU P\");\nmy %namedseq = namedseq();\n\nIf used with a single argument in a scalar context, returns the string consisting of the code\npoints of the named sequence, or \"undef\" if no named sequence by that name exists. If used with\na single argument in a list context, it returns the list of the ordinals of the code points.\n\nIf used with no arguments in a list context, it returns a hash with the names of all the named\nsequences as the keys and their sequences as strings as the values. Otherwise, it returns\n\"undef\" or an empty list depending on the context.\n\nThis function only operates on officially approved (not provisional) named sequences.\n\nNote that as of Perl 5.14, \"\\N{KATAKANA LETTER AINU P}\" will insert the named sequence into\ndouble-quoted strings, and \"charnames::stringvianame(\"KATAKANA LETTER AINU P\")\" will return the\nsame string this function does, but will also operate on character names that aren't named\nsequences, without you having to know which are which. See charnames.\n\nnum()\nuse Unicode::UCD 'num';\n\nmy $val = num(\"123\");\nmy $onequarter = num(\"\\N{VULGAR FRACTION 1/4}\");\nmy $val = num(\"12a\", \\$validlength); # $validlength contains 2\n\n\"num()\" returns the numeric value of the input Unicode string; or \"undef\" if it doesn't think\nthe entire string has a completely valid, safe numeric value. If called with an optional second\nparameter, a reference to a scalar, \"num()\" will set the scalar to the length of any valid\ninitial substring; or to 0 if none.\n\nIf the string is just one character in length, the Unicode numeric value is returned if it has\none, or \"undef\" otherwise. If the optional scalar ref is passed, it would be set to 1 if the\nreturn is valid; or 0 if the return is \"undef\". Note that the numeric value returned need not be\na whole number. \"num(\"\\N{TIBETAN DIGIT HALF ZERO}\")\", for example returns -0.5.\n\nIf the string is more than one character, \"undef\" is returned unless all its characters are\ndecimal digits (that is, they would match \"\\d+\"), from the same script. For example if you have\nan ASCII '0' and a Bengali '3', mixed together, they aren't considered a valid number, and\n\"undef\" is returned. A further restriction is that the digits all have to be of the same form. A\nhalf-width digit mixed with a full-width one will return \"undef\". The Arabic script has two sets\nof digits; \"num\" will return \"undef\" unless all the digits in the string come from the same set.\nIn all cases, the optional scalar ref parameter is set to how long any valid initial substring\nof digits is; hence it will be set to the entire string length if the main return value is not\n\"undef\".\n\n\"num\" errs on the side of safety, and there may be valid strings of decimal digits that it\ndoesn't recognize. Note that Unicode defines a number of \"digit\" characters that aren't \"decimal\ndigit\" characters. \"Decimal digits\" have the property that they have a positional value, i.e.,\nthere is a units position, a 10's position, a 100's, etc, AND they are arranged in Unicode in\nblocks of 10 contiguous code points. The Chinese digits, for example, are not in such a\ncontiguous block, and so Unicode doesn't view them as decimal digits, but merely digits, and so\n\"\\d\" will not match them. A single-character string containing one of these digits will have its\ndecimal value returned by \"num\", but any longer string containing only these digits will return\n\"undef\".\n\nStrings of multiple sub- and superscripts are not recognized as numbers. You can use either of\nthe compatibility decompositions in Unicode::Normalize to change these into digits, and then\ncall \"num\" on the result.\n\npropaliases()\nuse Unicode::UCD 'propaliases';\n\nmy ($shortname, $fullname, @othernames) = propaliases(\"space\");\nmy $samefullname = propaliases(\"Space\"); # Scalar context\nmy ($sameshortname) = propaliases(\"Space\"); # gets 0th element\nprint \"The full name is $fullname\\n\";\nprint \"The short name is $shortname\\n\";\nprint \"The other aliases are: \", join(\", \", @othernames), \"\\n\";\n\nprints:\nThe full name is WhiteSpace\nThe short name is WSpace\nThe other aliases are: Space\n\nMost Unicode properties have several synonymous names. Typically, there is at least a short\nname, convenient to type, and a long name that more fully describes the property, and hence is\nmore easily understood.\n\nIf you know one name for a Unicode property, you can use \"propaliases\" to find either the long\nname (when called in scalar context), or a list of all of the names, somewhat ordered so that\nthe short name is in the 0th element, the long name in the next element, and any other synonyms\nare in the remaining elements, in no particular order.\n\nThe long name is returned in a form nicely capitalized, suitable for printing.\n\nThe input parameter name is loosely matched, which means that white space, hyphens, and\nunderscores are ignored (except for the trailing underscore in the oldform grandfathered-in\n\"L\", which is better written as \"LC\", and both of which mean \"GeneralCategory=Cased Letter\").\n\nIf the name is unknown, \"undef\" is returned (or an empty list in list context). Note that Perl\ntypically recognizes property names in regular expressions with an optional \"\"Is\"\" (with or\nwithout the underscore) prefixed to them, such as \"\\p{isgc=punct}\". This function does not\nrecognize those in the input, returning \"undef\". Nor are they included in the output as possible\nsynonyms.\n\n\"propaliases\" does know about the Perl extensions to Unicode properties, such as \"Any\" and\n\"XPosixAlpha\", and the single form equivalents to Unicode properties such as \"XDigit\", \"Greek\",\n\"InGreek\", and \"IsGreek\". The final example demonstrates that the \"Is\" prefix is recognized\nfor these extensions; it is needed to resolve ambiguities. For example, \"propaliases('lc')\"\nreturns the list \"(lc, LowercaseMapping)\", but \"propaliases('islc')\" returns \"(IsLC,\nCasedLetter)\". This is because \"islc\" is a Perl extension which is short for\n\"GeneralCategory=Cased Letter\". The lists returned for the Perl extensions will not include the\n\"Is\" prefix (whether or not the input had it) unless needed to resolve ambiguities, as shown in\nthe \"islc\" example, where the returned list had one element containing \"Is\", and the other\nwithout.\n\nIt is also possible for the reverse to happen: \"propaliases('isc')\" returns the list \"(isc,\nISOComment)\"; whereas \"propaliases('c')\" returns \"(C, Other)\" (the latter being a Perl\nextension meaning \"GeneralCategory=Other\". \"Properties accessible through Unicode::UCD\" in\nperluniprops lists the available forms, including which ones are discouraged from use.\n\nThose discouraged forms are accepted as input to \"propaliases\", but are not returned in the\nlists. \"propaliases('isL&')\" and \"propaliases('isL')\", which are old synonyms for \"IsLC\" and\nshould not be used in new code, are examples of this. These both return \"(IsLC, CasedLetter)\".\nThus this function allows you to take a discouraged form, and find its acceptable alternatives.\nThe same goes with single-form Block property equivalences. Only the forms that begin with \"In\"\nare not discouraged; if you pass \"propaliases\" a discouraged form, you will get back the\nequivalent ones that begin with \"In\". It will otherwise look like a new-style block name (see.\n\"Old-style versus new-style block names\").\n\n\"propaliases\" does not know about any user-defined properties, and will return \"undef\" if\ncalled with one of those. Likewise for Perl internal properties, with the exception of\n\"PerlDecimalDigit\" which it does know about (and which is documented below in\n\"propinvmap()\").\n\npropvalues()\nuse Unicode::UCD 'propvalues';\n\nprint \"AHex values are: \", join(\", \", propvalues(\"AHex\")),\n\"\\n\";\nprints:\nAHex values are: N, Y\n\nSome Unicode properties have a restricted set of legal values. For example, all binary\nproperties are restricted to just \"true\" or \"false\"; and there are only a few dozen possible\nGeneral Categories. Use \"propvalues\" to find out if a given property is one such, and if so, to\nget a list of the values:\n\nprint join \", \", propvalues(\"NFCQuickCheck\");\nprints:\nM, N, Y\n\nIf the property doesn't have such a restricted set, \"undef\" is returned.\n\nThere are usually several synonyms for each possible value. Use \"propvaluealiases()\" to access\nthose.\n\nCase, white space, hyphens, and underscores are ignored in the input property name (except for\nthe trailing underscore in the old-form grandfathered-in general category property value \"L\",\nwhich is better written as \"LC\").\n\nIf the property name is unknown, \"undef\" is returned. Note that Perl typically recognizes\nproperty names in regular expressions with an optional \"\"Is\"\" (with or without the underscore)\nprefixed to them, such as \"\\p{isgc=punct}\". This function does not recognize those in the\nproperty parameter, returning \"undef\".\n\nFor the block property, new-style block names are returned (see \"Old-style versus new-style\nblock names\").\n\n\"propvalues\" does not know about any user-defined properties, and will return \"undef\" if called\nwith one of those.\n\npropvaluealiases()\nuse Unicode::UCD 'propvaluealiases';\n\nmy ($shortname, $fullname, @othernames)\n= propvaluealiases(\"Gc\", \"Punct\");\nmy $samefullname = propvaluealiases(\"Gc\", \"P\"); # Scalar cntxt\nmy ($sameshortname) = propvaluealiases(\"Gc\", \"P\"); # gets 0th\n# element\nprint \"The full name is $fullname\\n\";\nprint \"The short name is $shortname\\n\";\nprint \"The other aliases are: \", join(\", \", @othernames), \"\\n\";\n\nprints:\nThe full name is Punctuation\nThe short name is P\nThe other aliases are: Punct\n\nSome Unicode properties have a restricted set of legal values. For example, all binary\nproperties are restricted to just \"true\" or \"false\"; and there are only a few dozen possible\nGeneral Categories.\n\nYou can use \"propvalues()\" to find out if a given property is one which has a restricted set of\nvalues, and if so, what those values are. But usually each value actually has several synonyms.\nFor example, in Unicode binary properties, *truth* can be represented by any of the strings \"Y\",\n\"Yes\", \"T\", or \"True\"; and the General Category \"Punctuation\" by that string, or \"Punct\", or\nsimply \"P\".\n\nLike property names, there is typically at least a short name for each such property-value, and\na long name. If you know any name of the property-value (which you can get by \"propvalues()\",\nyou can use \"propvaluealiases\"() to get the long name (when called in scalar context), or a\nlist of all the names, with the short name in the 0th element, the long name in the next\nelement, and any other synonyms in the remaining elements, in no particular order, except that\nany all-numeric synonyms will be last.\n\nThe long name is returned in a form nicely capitalized, suitable for printing.\n\nCase, white space, hyphens, and underscores are ignored in the input parameters (except for the\ntrailing underscore in the old-form grandfathered-in general category property value \"L\", which\nis better written as \"LC\").\n\nIf either name is unknown, \"undef\" is returned. Note that Perl typically recognizes property\nnames in regular expressions with an optional \"\"Is\"\" (with or without the underscore) prefixed\nto them, such as \"\\p{isgc=punct}\". This function does not recognize those in the property\nparameter, returning \"undef\".\n\nIf called with a property that doesn't have synonyms for its values, it returns the input value,\npossibly normalized with capitalization and underscores, but not necessarily checking that the\ninput value is valid.\n\nFor the block property, new-style block names are returned (see \"Old-style versus new-style\nblock names\").\n\nTo find the synonyms for single-forms, such as \"\\p{Any}\", use \"propaliases()\" instead.\n\n\"propvaluealiases\" does not know about any user-defined properties, and will return \"undef\" if\ncalled with one of those.\n\npropinvlist()\n\"propinvlist\" returns an inversion list (described below) that defines all the code points for\nthe binary Unicode property (or \"property=value\" pair) given by the input parameter string:\n\nuse feature 'say';\nuse Unicode::UCD 'propinvlist';\nsay join \", \", propinvlist(\"Any\");\n\nprints:\n0, 1114112\n\nIf the input is unknown \"undef\" is returned in scalar context; an empty-list in list context. If\nthe input is known, the number of elements in the list is returned if called in scalar context.\n\nperluniprops gives the list of properties that this function accepts, as well as all the\npossible forms for them (including with the optional \"Is\" prefixes). (Except this function\ndoesn't accept any Perl-internal properties, some of which are listed there.) This function uses\nthe same loose or tighter matching rules for resolving the input property's name as is done for\nregular expressions. These are also specified in perluniprops. Examples of using the\n\"property=value\" form are:\n\nsay join \", \", propinvlist(\"ScriptExtensions=Shavian\");\n\nprints:\n66640, 66688\n\nsay join \", \", propinvlist(\"ASCIIHexDigit=No\");\n\nprints:\n0, 48, 58, 65, 71, 97, 103\n\nsay join \", \", propinvlist(\"ASCIIHexDigit=Yes\");\n\nprints:\n48, 58, 65, 71, 97, 103\n\nInversion lists are a compact way of specifying Unicode property-value definitions. The 0th item\nin the list is the lowest code point that has the property-value. The next item (item [1]) is\nthe lowest code point beyond that one that does NOT have the property-value. And the next item\nbeyond that ([2]) is the lowest code point beyond that one that does have the property-value,\nand so on. Put another way, each element in the list gives the beginning of a range that has the\nproperty-value (for even numbered elements), or doesn't have the property-value (for odd\nnumbered elements). The name for this data structure stems from the fact that each element in\nthe list toggles (or inverts) whether the corresponding range is or isn't on the list.\n\nIn the final example above, the first ASCII Hex digit is code point 48, the character \"0\", and\nall code points from it through 57 (a \"9\") are ASCII hex digits. Code points 58 through 64\naren't, but 65 (an \"A\") through 70 (an \"F\") are, as are 97 (\"a\") through 102 (\"f\"). 103 starts a\nrange of code points that aren't ASCII hex digits. That range extends to infinity, which on your\ncomputer can be found in the variable $Unicode::UCD::MAXCP. (This variable is as close to\ninfinity as Perl can get on your platform, and may be too high for some operations to work; you\nmay wish to use a smaller number for your purposes.)\n\nNote that the inversion lists returned by this function can possibly include non-Unicode code\npoints, that is anything above 0x10FFFF. Unicode properties are not defined on such code points.\nYou might wish to change the output to not include these. Simply add 0x110000 at the end of the\nnon-empty returned list if it isn't already that value; and pop that value if it is; like:\n\nmy @list = propinvlist(\"foo\");\nif (@list) {\nif ($list[-1] == 0x110000) {\npop @list; # Defeat the turning on for above Unicode\n}\nelse {\npush @list, 0x110000; # Turn off for above Unicode\n}\n}\n\nIt is a simple matter to expand out an inversion list to a full list of all code points that\nhave the property-value:\n\nmy @invlist = propinvlist($propertyname);\ndie \"empty\" unless @invlist;\nmy @fulllist;\nfor (my $i = 0; $i < @invlist; $i += 2) {\nmy $upper = ($i + 1) < @invlist\n? $invlist[$i+1] - 1 # In range\n: $Unicode::UCD::MAXCP; # To infinity.\nfor my $j ($invlist[$i] .. $upper) {\npush @fulllist, $j;\n}\n}\n\n\"propinvlist\" does not know about any user-defined nor Perl internal-only properties, and will\nreturn \"undef\" if called with one of those.\n\nThe \"searchinvlist()\" function is provided for finding a code point within an inversion list.\n\npropinvmap()\nuse Unicode::UCD 'propinvmap';\nmy ($listref, $mapref, $format, $default)\n= propinvmap(\"General Category\");\n\n\"propinvmap\" is used to get the complete mapping definition for a property, in the form of an\ninversion map. An inversion map consists of two parallel arrays. One is an ordered list of code\npoints that mark range beginnings, and the other gives the value (or mapping) that all code\npoints in the corresponding range have.\n\n\"propinvmap\" is called with the name of the desired property. The name is loosely matched,\nmeaning that differences in case, white-space, hyphens, and underscores are not meaningful\n(except for the trailing underscore in the old-form grandfathered-in property \"L\", which is\nbetter written as \"LC\", or even better, \"Gc=LC\").\n\nMany Unicode properties have more than one name (or alias). \"propinvmap\" understands all of\nthese, including Perl extensions to them. Ambiguities are resolved as described above for\n\"propaliases()\" (except if a property has both a complete mapping, and a binary \"Y\"/\"N\"\nmapping, then specifying the property name prefixed by \"is\" causes the binary one to be\nreturned). The Perl internal property \"PerlDecimalDigit, described below, is also accepted. An\nempty list is returned if the property name is unknown. See \"Properties accessible through\nUnicode::UCD\" in perluniprops for the properties acceptable as inputs to this function.\n\nIt is a fatal error to call this function except in list context.\n\nIn addition to the two arrays that form the inversion map, \"propinvmap\" returns two other\nvalues; one is a scalar that gives some details as to the format of the entries of the map\narray; the other is a default value, useful in maps whose format name begins with the letter\n\"a\", as described below in its subsection; and for specialized purposes, such as converting to\nanother data structure, described at the end of this main section.\n\nThis means that \"propinvmap\" returns a 4 element list. For example,\n\nmy ($blocksrangesref, $blocksmapsref, $format, $default)\n= propinvmap(\"Block\");\n\nIn this call, the two arrays will be populated as shown below (for Unicode 6.0):\n\nIndex @blocksranges @blocksmaps\n0 0x0000 Basic Latin\n1 0x0080 Latin-1 Supplement\n2 0x0100 Latin Extended-A\n3 0x0180 Latin Extended-B\n4 0x0250 IPA Extensions\n5 0x02B0 Spacing Modifier Letters\n6 0x0300 Combining Diacritical Marks\n7 0x0370 Greek and Coptic\n8 0x0400 Cyrillic\n...\n233 0x2B820 NoBlock\n234 0x2F800 CJK Compatibility Ideographs Supplement\n235 0x2FA20 NoBlock\n236 0xE0000 Tags\n237 0xE0080 NoBlock\n238 0xE0100 Variation Selectors Supplement\n239 0xE01F0 NoBlock\n240 0xF0000 Supplementary Private Use Area-A\n241 0x100000 Supplementary Private Use Area-B\n242 0x110000 NoBlock\n\nThe first line (with Index [0]) means that the value for code point 0 is \"Basic Latin\". The\nentry \"0x0080\" in the @blocksranges column in the second line means that the value from the\nfirst line, \"Basic Latin\", extends to all code points in the range from 0 up to but not\nincluding 0x0080, that is, through 127. In other words, the code points from 0 to 127 are all in\nthe \"Basic Latin\" block. Similarly, all code points in the range from 0x0080 up to (but not\nincluding) 0x0100 are in the block named \"Latin-1 Supplement\", etc. (Notice that the return is\nthe old-style block names; see \"Old-style versus new-style block names\").\n\nThe final line (with Index [242]) means that the value for all code points above the legal\nUnicode maximum code point have the value \"NoBlock\", which is the term Unicode uses for a\nnon-existing block.\n\nThe arrays completely specify the mappings for all possible code points. The final element in an\ninversion map returned by this function will always be for the range that consists of all the\ncode points that aren't legal Unicode, but that are expressible on the platform. (That is, it\nstarts with code point 0x110000, the first code point above the legal Unicode maximum, and\nextends to infinity.) The value for that range will be the same that any typical unassigned code\npoint has for the specified property. (Certain unassigned code points are not \"typical\"; for\nexample the non-character code points, or those in blocks that are to be written right-to-left.\nThe above-Unicode range's value is not based on these atypical code points.) It could be argued\nthat, instead of treating these as unassigned Unicode code points, the value for this range\nshould be \"undef\". If you wish, you can change the returned arrays accordingly.\n\nThe maps for almost all properties are simple scalars that should be interpreted as-is. These\nvalues are those given in the Unicode-supplied data files, which may be inconsistent as to\ncapitalization and as to which synonym for a property-value is given. The results may be\nnormalized by using the \"propvaluealiases()\" function.\n\nThere are exceptions to the simple scalar maps. Some properties have some elements in their map\nlist that are themselves lists of scalars; and some special strings are returned that are not to\nbe interpreted as-is. Element [2] (placed into $format in the example above) of the returned\nfour element list tells you if the map has any of these special elements or not, as follows:\n\n\"s\" means all the elements of the map array are simple scalars, with no special elements. Almost\nall properties are like this, like the \"block\" example above.\n\n\"sl\"\nmeans that some of the map array elements have the form given by \"s\", and the rest are lists\nof scalars. For example, here is a portion of the output of calling \"propinvmap\"() with the\n\"Script Extensions\" property:\n\n@scriptsranges @scriptsmaps\n...\n0x0953 Devanagari\n0x0964 [ Bengali, Devanagari, Gurumukhi, Oriya ]\n0x0966 Devanagari\n0x0970 Common\n\nHere, the code points 0x964 and 0x965 are both used in Bengali, Devanagari, Gurmukhi, and\nOriya, but no other scripts.\n\nThe NameAlias property is also of this form. But each scalar consists of two components: 1)\nthe name, and 2) the type of alias this is. They are separated by a colon and a space. In\nUnicode 6.1, there are several alias types:\n\n\"correction\"\nindicates that the name is a corrected form for the original name (which remains valid)\nfor the same code point.\n\n\"control\"\nadds a new name for a control character.\n\n\"alternate\"\nis an alternate name for a character\n\n\"figment\"\nis a name for a character that has been documented but was never in any actual standard.\n\n\"abbreviation\"\nis a common abbreviation for a character\n\nThe lists are ordered (roughly) so the most preferred names come before less preferred ones.\n\nFor example,\n\n@aliasesranges @aliasmaps\n...\n0x009E [ 'PRIVACY MESSAGE: control', 'PM: abbreviation' ]\n0x009F [ 'APPLICATION PROGRAM COMMAND: control',\n'APC: abbreviation'\n]\n0x00A0 'NBSP: abbreviation'\n0x00A1 \"\"\n0x00AD 'SHY: abbreviation'\n0x00AE \"\"\n0x01A2 'LATIN CAPITAL LETTER GHA: correction'\n0x01A3 'LATIN SMALL LETTER GHA: correction'\n0x01A4 \"\"\n...\n\nA map to the empty string means that there is no alias defined for the code point.\n\n\"a\" is like \"s\" in that all the map array elements are scalars, but here they are restricted to\nall being integers, and some have to be adjusted (hence the name \"a\") to get the correct\nresult. For example, in:\n\nmy ($uppersrangesref, $uppersmapsref, $format, $default)\n= propinvmap(\"SimpleUppercaseMapping\");\n\nthe returned arrays look like this:\n\n@$uppersrangesref @$uppersmapsref Note\n0 0\n97 65 'a' maps to 'A', b => B ...\n123 0\n181 924 MICRO SIGN => Greek Cap MU\n182 0\n...\n\nand $default is 0.\n\nLet's start with the second line. It says that the uppercase of code point 97 is 65; or\n\"uc(\"a\")\" == \"A\". But the line is for the entire range of code points 97 through 122. To get\nthe mapping for any code point in this range, you take the offset it has from the beginning\ncode point of the range, and add that to the mapping for that first code point. So, the\nmapping for 122 (\"z\") is derived by taking the offset of 122 from 97 (=25) and adding that\nto 65, yielding 90 (\"z\"). Likewise for everything in between.\n\nRequiring this simple adjustment allows the returned arrays to be significantly smaller than\notherwise, up to a factor of 10, speeding up searching through them.\n\nRanges that map to $default, \"0\", behave somewhat differently. For these, each code point\nmaps to itself. So, in the first line in the example, \"ord(uc(chr(0)))\" is 0,\n\"ord(uc(chr(1)))\" is 1, .. \"ord(uc(chr(96)))\" is 96.\n\n\"al\"\nmeans that some of the map array elements have the form given by \"a\", and the rest are\nordered lists of code points. For example, in:\n\nmy ($uppersrangesref, $uppersmapsref, $format, $default)\n= propinvmap(\"UppercaseMapping\");\n\nthe returned arrays look like this:\n\n@$uppersrangesref @$uppersmapsref\n0 0\n97 65\n123 0\n181 924\n182 0\n...\n0x0149 [ 0x02BC 0x004E ]\n0x014A 0\n0x014B 330\n...\n\nThis is the full UppercaseMapping property (as opposed to the SimpleUppercaseMapping\ngiven in the example for format \"a\"). The only difference between the two in the ranges\nshown is that the code point at 0x0149 (LATIN SMALL LETTER N PRECEDED BY APOSTROPHE) maps to\na string of two characters, 0x02BC (MODIFIER LETTER APOSTROPHE) followed by 0x004E (LATIN\nCAPITAL LETTER N).\n\nNo adjustments are needed to entries that are references to arrays; each such entry will\nhave exactly one element in its range, so the offset is always 0.\n\nThe fourth (index [3]) element ($default) in the list returned for this format is 0.\n\n\"ae\"\nThis is like \"a\", but some elements are the empty string, and should not be adjusted. The\none internal Perl property accessible by \"propinvmap\" is of this type: \"PerlDecimalDigit\"\nreturns an inversion map which gives the numeric values that are represented by the Unicode\ndecimal digit characters. Characters that don't represent decimal digits map to the empty\nstring, like so:\n\n@digits @values\n0x0000 \"\"\n0x0030 0\n0x003A: \"\"\n0x0660: 0\n0x066A: \"\"\n0x06F0: 0\n0x06FA: \"\"\n0x07C0: 0\n0x07CA: \"\"\n0x0966: 0\n...\n\nThis means that the code points from 0 to 0x2F do not represent decimal digits; the code\npoint 0x30 (DIGIT ZERO) represents 0; code point 0x31, (DIGIT ONE), represents 0+1-0 = 1;\n... code point 0x39, (DIGIT NINE), represents 0+9-0 = 9; ... code points 0x3A through 0x65F\ndo not represent decimal digits; 0x660 (ARABIC-INDIC DIGIT ZERO), represents 0; ... 0x07C1\n(NKO DIGIT ONE), represents 0+1-0 = 1 ...\n\nThe fourth (index [3]) element ($default) in the list returned for this format is the empty\nstring.\n\n\"ale\"\nis a combination of the \"al\" type and the \"ae\" type. Some of the map array elements have the\nforms given by \"al\", and the rest are the empty string. The property \"NFKCCasefold\" has\nthis form. An example slice is:\n\n@$rangesref @$mapsref Note\n...\n0x00AA 97 FEMININE ORDINAL INDICATOR => 'a'\n0x00AB 0\n0x00AD SOFT HYPHEN => \"\"\n0x00AE 0\n0x00AF [ 0x0020, 0x0304 ] MACRON => SPACE . COMBINING MACRON\n0x00B0 0\n...\n\nThe fourth (index [3]) element ($default) in the list returned for this format is 0.\n\n\"ar\"\nmeans that all the elements of the map array are either rational numbers or the string\n\"NaN\", meaning \"Not a Number\". A rational number is either an integer, or two integers\nseparated by a solidus (\"/\"). The second integer represents the denominator of the division\nimplied by the solidus, and is actually always positive, so it is guaranteed not to be 0 and\nto not be signed. When the element is a plain integer (without the solidus), it may need to\nbe adjusted to get the correct value by adding the offset, just as other \"a\" properties. No\nadjustment is needed for fractions, as the range is guaranteed to have just a single\nelement, and so the offset is always 0.\n\nIf you want to convert the returned map to entirely scalar numbers, you can use something\nlike this:\n\nmy ($invlistref, $invmapref, $format) = propinvmap($property);\nif ($format && $format eq \"ar\") {\nmap { $ = eval $ if $ ne 'NaN' } @$mapref;\n}\n\nHere's some entries from the output of the property \"Nv\", which has format \"ar\".\n\n@numericsranges @numericsmaps Note\n0x00 \"NaN\"\n0x30 0 DIGIT 0 .. DIGIT 9\n0x3A \"NaN\"\n0xB2 2 SUPERSCRIPTs 2 and 3\n0xB4 \"NaN\"\n0xB9 1 SUPERSCRIPT 1\n0xBA \"NaN\"\n0xBC 1/4 VULGAR FRACTION 1/4\n0xBD 1/2 VULGAR FRACTION 1/2\n0xBE 3/4 VULGAR FRACTION 3/4\n0xBF \"NaN\"\n0x660 0 ARABIC-INDIC DIGIT ZERO .. NINE\n0x66A \"NaN\"\n\nThe fourth (index [3]) element ($default) in the list returned for this format is \"NaN\".\n\n\"n\" means the Name property. All the elements of the map array are simple scalars, but some of\nthem contain special strings that require more work to get the actual name.\n\nEntries such as:\n\nCJK UNIFIED IDEOGRAPH-\n\nmean that the name for the code point is \"CJK UNIFIED IDEOGRAPH-\" with the code point\n(expressed in hexadecimal) appended to it, like \"CJK UNIFIED IDEOGRAPH-3403\" (similarly for\n\"CJK COMPATIBILITY IDEOGRAPH-\").\n\nAlso, entries like\n\n\n\nmeans that the name is algorithmically calculated. This is easily done by the function\n\"charnames::viacode(code)\" in charnames.\n\nNote that for control characters (\"Gc=cc\"), Unicode's data files have the string\n\"\"\"\", but the real name of each of these characters is the empty string. This\nfunction returns that real name, the empty string. (There are names for these characters,\nbut they are considered aliases, not the Name property name, and are contained in the\n\"NameAlias\" property.)\n\n\"ad\"\nmeans the DecompositionMapping property. This property is like \"al\" properties, except that\none of the scalar elements is of the form:\n\n\n\nThis signifies that this entry should be replaced by the decompositions for all the code\npoints whose decomposition is algorithmically calculated. (All of them are currently in one\nrange and no others outside the range are likely to ever be added to Unicode; the \"n\" format\nhas this same entry.) These can be generated via the function Unicode::Normalize::NFD().\n\nNote that the mapping is the one that is specified in the Unicode data files, and to get the\nfinal decomposition, it may need to be applied recursively. Unicode in fact discourages use\nof this property except internally in implementations of the Unicode Normalization\nAlgorithm.\n\nThe fourth (index [3]) element ($default) in the list returned for this format is 0.\n\nNote that a format begins with the letter \"a\" if and only the property it is for requires\nadjustments by adding the offsets in multi-element ranges. For all these properties, an entry\nshould be adjusted only if the map is a scalar which is an integer. That is, it must match the\nregular expression:\n\n/ ^ -? \\d+ $ /xa\n\nFurther, the first element in a range never needs adjustment, as the adjustment would be just\nadding 0.\n\nA binary search such as that provided by \"searchinvlist()\", can be used to quickly find a code\npoint in the inversion list, and hence its corresponding mapping.\n\nThe final, fourth element (index [3], assigned to $default in the \"block\" example) in the four\nelement list returned by this function is used with the \"a\" format types; it may also be useful\nfor applications that wish to convert the returned inversion map data structure into some other,\nsuch as a hash. It gives the mapping that most code points map to under the property. If you\nestablish the convention that any code point not explicitly listed in your data structure maps\nto this value, you can potentially make your data structure much smaller. As you construct your\ndata structure from the one returned by this function, simply ignore those ranges that map to\nthis value. For example, to convert to the data structure searchable by \"charinrange()\", you can\nfollow this recipe for properties that don't require adjustments:\n\nmy ($listref, $mapref, $format, $default) = propinvmap($property);\nmy @rangelist;\n\n# Look at each element in the list, but the -2 is needed because we\n# look at $i+1 in the loop, and the final element is guaranteed to map\n# to $default by propinvmap(), so we would skip it anyway.\nfor my $i (0 .. @$listref - 2) {\nnext if $mapref->[$i] eq $default;\npush @rangelist, [ $listref->[$i],\n$listref->[$i+1],\n$mapref->[$i]\n];\n}\n\nprint charinrange(\\@rangelist, $codepoint), \"\\n\";\n\nWith this, \"charinrange()\" will return \"undef\" if its input code point maps to $default. You can\navoid this by omitting the \"next\" statement, and adding a line after the loop to handle the\nfinal element of the inversion map.\n\nSimilarly, this recipe can be used for properties that do require adjustments:\n\nfor my $i (0 .. @$listref - 2) {\nnext if $mapref->[$i] eq $default;\n\n# propinvmap() guarantees that if the mapping is to an array, the\n# range has just one element, so no need to worry about adjustments.\nif (ref $mapref->[$i]) {\npush @rangelist,\n[ $listref->[$i], $listref->[$i], $mapref->[$i] ];\n}\nelse { # Otherwise each element is actually mapped to a separate\n# value, so the range has to be split into single code point\n# ranges.\n\nmy $adjustment = 0;\n\n# For each code point that gets mapped to something...\nfor my $j ($listref->[$i] .. $listref->[$i+1] -1 ) {\n\n# ... add a range consisting of just it mapping to the\n# original plus the adjustment, which is incremented for the\n# next time through the loop, as the offset increases by 1\n# for each element in the range\npush @rangelist,\n[ $j, $j, $mapref->[$i] + $adjustment++ ];\n}\n}\n}\n\nNote that the inversion maps returned for the \"CaseFolding\" and \"SimpleCaseFolding\"\nproperties do not include the Turkic-locale mappings. Use \"casefold()\" for these.\n\n\"propinvmap\" does not know about any user-defined properties, and will return \"undef\" if called\nwith one of those.\n\nThe returned values for the Perl extension properties, such as \"Any\" and \"Greek\" are somewhat\nmisleading. The values are either \"Y\" or \"\"N\"\". All Unicode properties are bipartite, so you can\nactually use the \"Y\" or \"\"N\"\" in a Perl regular expression for these, like \"qr/\\p{IDStart=Y/}\"\nor \"qr/\\p{Upper=N/}\". But the Perl extensions aren't specified this way, only like\n\"/qr/\\p{Any}\", *etc*. You can't actually use the \"Y\" and \"\"N\"\" in them.\n\nGetting every available name\nInstead of reading the Unicode Database directly from files, as you were able to do for a long\ntime, you are encouraged to use the supplied functions. So, instead of reading \"Name.pl\"\ndirectly, which changed formats in 5.32, and may do so again without notice in the future or\neven disappear, you ought to use \"propinvmap()\" like this:\n\nmy (%name, %cp, %cps, $n);\n# All codepoints\nforeach my $cat (qw( Name NameAlias )) {\nmy ($codepoints, $names, $format, $default) = propinvmap($cat);\n# $format => \"n\", $default => \"\"\nforeach my $i (0 .. @$codepoints - 2) {\nmy ($cp, $n) = ($codepoints->[$i], $names->[$i]);\n# If $n is a ref, the same codepoint has multiple names\nforeach my $name (ref $n ? @$n : $n) {\n$name{$cp} //= $name;\n$cp{$name} //= $cp;\n}\n}\n}\n# Named sequences\n{ my %ns = namedseq();\nforeach my $name (sort { $ns{$a} cmp $ns{$b} } keys %ns) {\n$cp{$name} //= [ map { ord } split \"\" => $ns{$name} ];\n}\n}\n\nsearchinvlist()\nuse Unicode::UCD qw(propinvmap propinvlist);\nuse Unicode::UCD 'searchinvlist';\n\nmy @invlist = propinvlist($propertyname);\nprint $codepoint, ((searchinvlist(\\@invlist, $codepoint) // -1) % 2)\n? \" isn't\"\n: \" is\",\n\" in $propertyname\\n\";\n\nmy ($blocksrangesref, $blocksmapref) = propinvmap(\"Block\");\nmy $index = searchinvlist($blocksrangesref, $codepoint);\nprint \"$codepoint is in block \", $blocksmapref->[$index], \"\\n\";\n\n\"searchinvlist\" is used to search an inversion list returned by \"propinvlist\" or \"propinvmap\"\nfor a particular \"code point argument\". \"undef\" is returned if the code point is not found in\nthe inversion list (this happens only when it is not a legal \"code point argument\", or is less\nthan the list's first element). A warning is raised in the first instance.\n\nOtherwise, it returns the index into the list of the range that contains the code point.; that\nis, find \"i\" such that\n\nlist[i]<= codepoint < list[i+1].\n\nAs explained in \"propinvlist()\", whether a code point is in the list or not depends on if the\nindex is even (in) or odd (not in). And as explained in \"propinvmap()\", the index is used with\nthe returned parallel array to find the mapping.\n" }, { "name": "Unicode::UCD::UnicodeVersion", "content": "This returns the version of the Unicode Character Database, in other words, the version of the\nUnicode standard the database implements. The version is a string of numbers delimited by dots\n('.').\n" }, { "name": "Blocks versus Scripts", "content": "The difference between a block and a script is that scripts are closer to the linguistic notion\nof a set of code points required to represent languages, while block is more of an artifact of\nthe Unicode code point numbering and separation into blocks of consecutive code points (so far\nthe size of a block is some multiple of 16, like 128 or 256).\n\nFor example the Latin script is spread over several blocks, such as \"Basic Latin\", \"Latin 1\nSupplement\", \"Latin Extended-A\", and \"Latin Extended-B\". On the other hand, the Latin script\ndoes not contain all the characters of the \"Basic Latin\" block (also known as ASCII): it\nincludes only the letters, and not, for example, the digits nor the punctuation.\n\nFor blocks see \n\nFor scripts see UTR #24: \n" }, { "name": "Matching Scripts and Blocks", "content": "Scripts are matched with the regular-expression construct \"\\p{...}\" (e.g. \"\\p{Tibetan}\" matches\ncharacters of the Tibetan script), while \"\\p{Blk=...}\" is used for blocks (e.g.\n\"\\p{Blk=Tibetan}\" matches any of the 256 code points in the Tibetan block).\n" }, { "name": "Old-style versus new-style block names", "content": "Unicode publishes the names of blocks in two different styles, though the two are equivalent\nunder Unicode's loose matching rules.\n\nThe original style uses blanks and hyphens in the block names (except for \"NoBlock\"), like so:\n\nMiscellaneous Mathematical Symbols-B\n\nThe newer style replaces these with underscores, like this:\n\nMiscellaneousMathematicalSymbolsB\n\nThis newer style is consistent with the values of other Unicode properties. To preserve backward\ncompatibility, all the functions in Unicode::UCD that return block names (except as noted)\nreturn the old-style ones. \"propvaluealiases()\" returns the new-style and can be used to\nconvert from old-style to new-style:\n\nmy $newstyle = propvaluesaliases(\"block\", $oldstyle);\n\nPerl also has single-form extensions that refer to blocks, \"InCyrillic\", meaning\n\"Block=Cyrillic\". These have always been written in the new style.\n\nTo convert from new-style to old-style, follow this recipe:\n\n$oldstyle = charblock((propinvlist(\"block=$newstyle\"))[0]);\n\n(which finds the range of code points in the block using \"propinvlist\", gets the lower end of\nthe range (0th element) and then looks up the old name for its block using \"charblock\").\n\nNote that starting in Unicode 6.1, many of the block names have shorter synonyms. These are\nalways given in the new style.\n" }, { "name": "Use with older Unicode versions", "content": "The functions in this module work as well as can be expected when used on earlier Unicode\nversions. But, obviously, they use the available data from that Unicode version. For example, if\nthe Unicode version predates the definition of the script property (Unicode 3.1), then any\nfunction that deals with scripts is going to return \"undef\" for the script portion of the return\nvalue.\n" } ] }, "AUTHOR": { "content": "Jarkko Hietaniemi. Now maintained by perl5 porters.\n", "subsections": [] } } } }