;============================================================================================ ;DEFAULT DICTIONARY ;This dictionary is language-independent and may be used by any language. ;It must be loaded after the language specific dictionaries. ;Documentation available at http://www.unlweb.net/wiki/Default_dictionary ;============================================================================================ ;BLANK SPACE (BLK) [ ]{}""(PUT=BLK); ;PUNCTUATION (PUT) [‾]{}""(PUT=oline); [_]{}""(PUT=UNDERSCORE) ; [-]{}""(PUT=HYPHEN); [–]{}""(PUT=ndash); [—]{}""(PUT=mdash); [,]{}""(PUT=COMMA); [;]{}""(PUT=SEMICOLON); [:]{}""(PUT=COLON); [!]{}""(PUT=EMARK); [¡]{}""(PUT=iexcl); [?]{}""(PUT=QMARK); [¿]{}""(PUT=iquest); [؟]{}""(PUT=AQMARK); [‽]{}""(PUT=IBANG); [⸘]{}""(PUT=IIBANG); […]{}""(PUT=hellip); [.]{}""(PUT=PERIOD); [·]{}""(PUT=middot); [']{}""(PUT=APOSTROPHE); [‘]{}""(PUT=lsquo); [’]{}""(PUT=rsquo); [‚]{}""(PUT=sbquo); [‹]{}""(PUT=lsaquo); [›]{}""(PUT=rsaquo); ["]{}""(PUT=QUOTE); [“]{}""(PUT=ldquo); [”]{}""(PUT=rdquo); [„]{}""(PUT=bdquo); [«]{}""(PUT=laquo); [»]{}""(PUT=raquo); [(]{}""(PUT=OPARENTHESIS); [)]{}""(PUT=CPARENTHESIS); [[]{}""(PUT=OSBRACKET); []]{}""(PUT=CSBRACKET); [{]{}""(PUT=OCBRACE); [}]{}""(PUT=CCBRACE); [@]{}""(PUT=AT); [*]{}""(PUT=ASTERISK); [/]{}""(PUT=FSLASH); [\]{}""(PUT=BSLASH); [&]{}""(PUT=amp); [#]{}""(PUT=HASH); [%]{}""(PUT=PERCENTAGE); [‰]{}""(PUT=permil); [†]{}""(PUT=dagger); [‡]{}""(PUT=Dagger); [`]{}""(PUT=GRAVE); [´]{}""(PUT=ACUTE); [^]{}""(PUT=CIRCUMFLEX); [¯]{}""(PUT=macr); [¨]{}""(PUT=uml); [¸]{}""(PUT=cedil); [§]{}""(PUT=sect); [¶]{}""(PUT=para); [©]{}""(PUT=copy); [®]{}""(PUT=reg); [°]{}""(PUT=deg); [←]{}""(PUT=larr); [→]{}""(PUT=rarr); [↑]{}""(PUT=uarr); [↓]{}""(PUT=darr); [+]{}""(PUT=PLUS); [±]{}""(PUT=plusmn); [÷]{}""(PUT=divide); [×]{}""(PUT=times); [<]{}""(PUT=lt); [=]{}""(PUT=EQUAL); [>]{}""(PUT=gt); [¬]{}""(PUT=not); [|]{}""(PUT=VERTICALBAR) ); [¦]{}""(PUT=brvbar); [~]{}""(PUT=TILDE) ); [♠]{}""(PUT=spades); [♣]{}""(PUT=clubs); [♥]{}""(PUT=hearts); [♦]{}""(PUT=diams); [¤]{}""(PUT=curren); [¢]{}""(PUT=cent); [$]{}""(PUT=DOLLAR); [£]{}""(PUT=pound); [¥]{}""(PUT=yen); [€]{}""(PUT=EURO); [¹]{}""(PUT=sup1); [½]{}""(PUT=frac12); [¼]{}""(PUT=frac14); [²]{}""(PUT=sup2); [³]{}""(PUT=sup3); [¾]{}""(PUT=frac34); [؛]{}""(PUT=SEMICOLON); [ـ]{}""(PUT=HYPHEN); [،]{}""(PUT=COMMA); [//]{}""(PUT=BSLASH); [((]{}""(PUT=OPARENTHESIS); [))]{}""(PUT=CPARENTHESIS); [%]{}""(PUT=PERCENTAGE); ;URL's and EMAIL ADDRESSES [/(?i)(http\:\/\/[^ ]+)/]{}""(TEMP,LEX=N,POS=PPN,URL); [/(?i)(https\:\/\/[^ ]+)/]{}""(TEMP,LEX=N,POS=PPN,URL); [/(?i)(ftp\:\/\/[^ ]+)/]{}""(TEMP,LEX=N,POS=PPN,URL); [/(?i)(www\.[^ ]+)/]{}""(TEMP,LEX=N,POS=PPN,URL); [/(?i)([^ ]+@[^ ]+)/]{}""(TEMP,LEX=N,POS=PPN,EMAIL); ;DATES AND TIME [/(\d{1,2}\/)?\d{1,2}\/\d{2}(\d{2})?/]{}""(TEMP,LEX=N,POS=PPN,DATE); [/(\d{1,2}\-)?\d{1,2}\-\d{2}(\d{2})?/]{}""(TEMP,LEX=N,POS=PPN,DATE); [/(\d{1,2}\.)?\d{1,2}\.\d{2}(\d{2})?/]{}""(TEMP,LEX=N,POS=PPN,DATE); [/\d{1,2}\:\d{1,2}(\:\d{2})?/]{}""(TEMP,LEX=N,POS=PPN,TIME); [/(?i)(A\.?\s?M\.?)/]{}""(LEX=A,POS=AAV,TIME=AM); [/(?i)(P\.?\s?M\.?)/]{}""(LEX=A,POS=AAV,TIME=PM); ;CURRENCY [/(\$|¢|£|¥|£|€)(\s)?\d+([.,]\d+)?/]{}""(TEMP,LEX=N,POS=PPN,CURRENCY); [/(AFN|ALL|ANG|ARS|AUD|AWG|AZN|BAM|BBD|BGN|BMD|BND|BOB|BRL|Bs|BSD|BWP|BYR|BZD|CAD|CHF|CHF|CLP|CNY|COP|CRC|CUP|CZK|DKK|DOP|EEK|EGP|EUR|FJD|FKP|GBP|GGP|GHC|GIP|GTQ|GYD|HKD|HNL|HRK|HUF|IDR|ILS|IMP|INR|IRR|ISK|JEP|JMD|JPY|KGS|KHR|KM|KPW|KRW|KYD|KZT|LAK|LBP|LKR|LRD|LTL|LVL|MKD|MNT|MT|MUR|MXN|MYR|MZN|NAD|NGN|NIO|NOK|NPR|NZD|OMR|PAB|PEN|PHP|PKR|PLN|PYG|QAR|RON|RSD|RUB|SAR|SBD|SCR|SEK|SGD|SHP|SOS|SRD|SVC|SYP|THB|TRL|TRY|TTD|TVD|TWD|UAH|USD|UYU|UZS|VEF|VND|XCD|YER|ZAR|ZWD)(\s)?\d+([.,]\d+)?/]{}""(TEMP,LEX=N,POS=PPN,CURRENCY); ;ROMAN NUMBERS [/M{0,3}(C{1,3}|CD|DC{0,3}|CM)?(X{1,3}|XL|LX{0,3}|XC)?(I{1,3}|IV|VI{0,3}|IX)/]{}""(LEX=U,ROMAN); [/M{0,3}(C{1,3}|CD|DC{0,3}|CM)?(X{1,3}|XL|LX{0,3}|XC)/]{}""(LEX=U,ROMAN); [/M{0,3}(C{1,3}|CD|DC{0,3}|CM)/]{}""(LEX=U,ROMAN); ;PHONE NUMBERS [/(((\(\+?\d{1,3}\))|(\+?\(\d{1,3}\))|(\+?\d{1,3}\s))?/s?((\(\d{2,3}\))|(\d{2,3}))\s?)?\d{3,4}(\-|\s)\d{4}/]{}""(TEMP,LEX=N,POS=PPN,PHONENUMBER); ;FORMULA [/(\(*\s?[+-]?\d+([.,]\d+)?\s?\)*)(\s?[\+\-\*\/\=]\s?(\(*\s?[+-]?\d+([.,]\d+)?\s?\)*))+/]{}""(TEMP,LEX=N,POS=PPN,FORMULA);