sgml.java

一个自然语言处理的Java开源工具包。LingPipe目前已有很丰富的功能

        SGML_MAP.put("lne",'\u2268'); // LESS-THAN BUT NOT EQUAL TO
        SGML_MAP.put("lnsim",'\u22E6'); // LESS-THAN BUT NOT EQUIVALENT TO
        SGML_MAP.put("lowast",'\u2217'); // ASTERISK OPERATOR
        SGML_MAP.put("lowbar",'\u005F'); // LOW LINE
        SGML_MAP.put("loz",'\u25CA'); // LOZENGE
        SGML_MAP.put("loz",'\u2727'); // WHITE FOUR POINTED STAR
        SGML_MAP.put("lozf",'\u2726'); // BLACK FOUR POINTED STAR
        SGML_MAP.put("lpar",'\u0028'); // LEFT PARENTHESIS
        // SGML_MAP.put("lpargt",'?'); // left parenthesis, greater-than
        SGML_MAP.put("lrarr2",'\u21C6'); // LEFTWARDS ARROW OVER RIGHTWARDS ARROW
        SGML_MAP.put("lrhar2",'\u21CB'); // LEFTWARDS HARPOON OVER RIGHTWARDS HARPOON
        SGML_MAP.put("lrm",'\u200E'); // LEFT-TO-RIGHT MARK
        SGML_MAP.put("lsaquo",'\u2039'); // SINGLE LEFT-POINTING ANGLE QUOTATION MARK
        SGML_MAP.put("lsh",'\u21B0'); // UPWARDS ARROW WITH TIP LEFTWARDS
        SGML_MAP.put("lsim",'\u2272'); // LESS-THAN OR EQUIVALENT TO
        SGML_MAP.put("lsqb",'\u005B'); // LEFT SQUARE BRACKET
        SGML_MAP.put("lsquo",'\u2018'); // LEFT SINGLE QUOTATION MARK
        SGML_MAP.put("lsquor",'\u201A'); // SINGLE LOW-9 QUOTATION MARK
        SGML_MAP.put("Lstrok",'\u0141'); // LATIN CAPITAL LETTER L WITH STROKE
        SGML_MAP.put("lstrok",'\u0142'); // LATIN SMALL LETTER L WITH STROKE
        SGML_MAP.put("Lt",'\u226A'); // MUCH LESS-THAN
        SGML_MAP.put("lt",'\u003C'); // LESS-THAN SIGN
        SGML_MAP.put("lthree",'\u22CB'); // LEFT SEMIDIRECT PRODUCT
        SGML_MAP.put("ltimes",'\u22C9'); // LEFT NORMAL FACTOR SEMIDIRECT PRODUCT
        SGML_MAP.put("ltri",'\u25C3'); // WHITE LEFT-POINTING SMALL TRIANGLE
        SGML_MAP.put("ltrie",'\u22B4'); // NORMAL SUBGROUP OF OR EQUAL TO
        SGML_MAP.put("ltrif",'\u25C2'); // BLACK LEFT-POINTING SMALL TRIANGLE
        SGML_MAP.put("lvnE",'\u2268'); // LESS-THAN BUT NOT EQUAL TO
        SGML_MAP.put("macr",'\u00AF'); // MACRON
        SGML_MAP.put("male",'\u2642'); // MALE SIGN
        SGML_MAP.put("malt",'\u2720'); // MALTESE CROSS
        SGML_MAP.put("map",'\u21A6'); // RIGHTWARDS ARROW FROM BAR
        SGML_MAP.put("marker",'\u25AE'); // BLACK VERTICAL RECTANGLE
        SGML_MAP.put("Mcy",'\u041C'); // CYRILLIC CAPITAL LETTER EM
        SGML_MAP.put("mcy",'\u043C'); // CYRILLIC SMALL LETTER EM
        SGML_MAP.put("mdash",'\u2014'); // EM DASH
        SGML_MAP.put("Mgr",'\u039C'); // GREEK CAPITAL LETTER MU
        SGML_MAP.put("mgr",'\u03BC'); // GREEK SMALL LETTER MU
        SGML_MAP.put("micro",'\u00B5'); // MICRO SIGN
        SGML_MAP.put("mid",'\u2223'); // DIVIDES
        SGML_MAP.put("middot",'\u00B7'); // MIDDLE DOT
        SGML_MAP.put("minus",'\u2212'); // MINUS SIGN
        SGML_MAP.put("minusb",'\u229F'); // SQUARED MINUS
        SGML_MAP.put("mldr",'\u2026'); // HORIZONTAL ELLIPSIS
        SGML_MAP.put("mnplus",'\u2213'); // MINUS-OR-PLUS SIGN
        SGML_MAP.put("models",'\u22A7'); // MODELS
        SGML_MAP.put("Mu",'\u039C'); // GREEK CAPITAL LETTER MU
        SGML_MAP.put("mu",'\u03BC'); // GREEK SMALL LETTER MU
        SGML_MAP.put("mumap",'\u22B8'); // MULTIMAP
        SGML_MAP.put("nabla",'\u2207'); // NABLA
        SGML_MAP.put("Nacute",'\u0143'); // LATIN CAPITAL LETTER N WITH ACUTE
        SGML_MAP.put("nacute",'\u0144'); // LATIN SMALL LETTER N WITH ACUTE
        SGML_MAP.put("nap",'\u2249'); // NOT ALMOST EQUAL TO
        SGML_MAP.put("napos",'\u0149'); // LATIN SMALL LETTER N PRECEDED BY APOSTROPHE
        SGML_MAP.put("natur",'\u266E'); // MUSIC NATURAL SIGN
        SGML_MAP.put("nbsp",'\u00A0'); // NO-BREAK SPACE
        SGML_MAP.put("Ncaron",'\u0147'); // LATIN CAPITAL LETTER N WITH CARON
        SGML_MAP.put("ncaron",'\u0148'); // LATIN SMALL LETTER N WITH CARON
        SGML_MAP.put("Ncedil",'\u0145'); // LATIN CAPITAL LETTER N WITH CEDILLA
        SGML_MAP.put("ncedil",'\u0146'); // LATIN SMALL LETTER N WITH CEDILLA
        SGML_MAP.put("ncong",'\u2247'); // NEITHER APPROXIMATELY NOR ACTUALLY EQUAL TO
        SGML_MAP.put("Ncy",'\u041D'); // CYRILLIC CAPITAL LETTER EN
        SGML_MAP.put("ncy",'\u043D'); // CYRILLIC SMALL LETTER EN
        SGML_MAP.put("ndash",'\u2013'); // EN DASH
        SGML_MAP.put("ne",'\u2260'); // NOT EQUAL TO
        SGML_MAP.put("nearr",'\u2197'); // NORTH EAST ARROW
        SGML_MAP.put("nequiv",'\u2262'); // NOT IDENTICAL TO
        SGML_MAP.put("nexist",'\u2204'); // THERE DOES NOT EXIST
        // SGML_MAP.put("ngE",'?'); // not greater-than, double equals
        SGML_MAP.put("nge",'\u2271'); // NEITHER GREATER-THAN NOR EQUAL TO
        SGML_MAP.put("nges",'\u2271'); // NEITHER GREATER-THAN NOR EQUAL TO
        SGML_MAP.put("Ngr",'\u039D'); // GREEK CAPITAL LETTER NU
        SGML_MAP.put("ngr",'\u03BD'); // GREEK SMALL LETTER NU
        SGML_MAP.put("ngt",'\u226F'); // NOT GREATER-THAN
        SGML_MAP.put("nharr",'\u21AE'); // LEFT RIGHT ARROW WITH STROKE
        SGML_MAP.put("nhArr",'\u21CE'); // LEFT RIGHT DOUBLE ARROW WITH STROKE
        SGML_MAP.put("ni",'\u220B'); // CONTAINS AS MEMBER
        SGML_MAP.put("NJcy",'\u040A'); // CYRILLIC CAPITAL LETTER NJE
        SGML_MAP.put("njcy",'\u045A'); // CYRILLIC SMALL LETTER NJE
        SGML_MAP.put("nlarr",'\u219A'); // LEFTWARDS ARROW WITH STROKE
        SGML_MAP.put("nlArr",'\u21CD'); // LEFTWARDS DOUBLE ARROW WITH STROKE
        SGML_MAP.put("nldr",'\u2025'); // TWO DOT LEADER
        // SGML_MAP.put("nlE",'?'); // not less-than, double equals
        SGML_MAP.put("nle",'\u2270'); // NEITHER LESS-THAN NOR EQUAL TO
        SGML_MAP.put("nles",'\u2270'); // NEITHER LESS-THAN NOR EQUAL TO
        SGML_MAP.put("nlt",'\u226E'); // NOT LESS-THAN
        SGML_MAP.put("nltri",'\u22EA'); // NOT NORMAL SUBGROUP OF
        SGML_MAP.put("nltrie",'\u22EC'); // NOT NORMAL SUBGROUP OF OR EQUAL TO
        SGML_MAP.put("nmid",'\u2224'); // DOES NOT DIVIDE
        SGML_MAP.put("not",'\u00AC'); // NOT SIGN
        SGML_MAP.put("notin",'\u2209'); // NOT AN ELEMENT OF
        SGML_MAP.put("npar",'\u2226'); // NOT PARALLEL TO
        SGML_MAP.put("npr",'\u2280'); // DOES NOT PRECEDE
        SGML_MAP.put("npre",'\u22E0'); // DOES NOT PRECEDE OR EQUAL
        SGML_MAP.put("nrarr",'\u219B'); // RIGHTWARDS ARROW WITH STROKE
        SGML_MAP.put("nrArr",'\u21CF'); // RIGHTWARDS DOUBLE ARROW WITH STROKE
        SGML_MAP.put("nrtri",'\u22EB'); // DOES NOT CONTAIN AS NORMAL SUBGROUP
        SGML_MAP.put("nrtrie",'\u22ED'); // DOES NOT CONTAIN AS NORMAL SUBGROUP OR EQUAL
        SGML_MAP.put("nsc",'\u2281'); // DOES NOT SUCCEED
        SGML_MAP.put("nsce",'\u22E1'); // DOES NOT SUCCEED OR EQUAL
        SGML_MAP.put("nsim",'\u2241'); // NOT TILDE
        SGML_MAP.put("nsime",'\u2244'); // NOT ASYMPTOTICALLY EQUAL TO
        // SGML_MAP.put("nsmid",'?'); // nshortmid
        SGML_MAP.put("nspar",'\u2226'); // NOT PARALLEL TO
        SGML_MAP.put("nsub",'\u2284'); // NOT A SUBSET OF
        SGML_MAP.put("nsubE",'\u2288'); // NEITHER A SUBSET OF NOR EQUAL TO
        SGML_MAP.put("nsube",'\u2288'); // NEITHER A SUBSET OF NOR EQUAL TO
        SGML_MAP.put("nsup",'\u2285'); // NOT A SUPERSET OF
        SGML_MAP.put("nsupE",'\u2289'); // NEITHER A SUPERSET OF NOR EQUAL TO
        SGML_MAP.put("nsupe",'\u2289'); // NEITHER A SUPERSET OF NOR EQUAL TO
        SGML_MAP.put("Ntilde",'\u00D1'); // LATIN CAPITAL LETTER N WITH TILDE
        SGML_MAP.put("ntilde",'\u00F1'); // LATIN SMALL LETTER N WITH TILDE
        SGML_MAP.put("Nu",'\u039D'); // GREEK CAPITAL LETTER NU
        SGML_MAP.put("nu",'\u03BD'); // GREEK SMALL LETTER NU
        SGML_MAP.put("num",'\u0023'); // NUMBER SIGN
        SGML_MAP.put("numero",'\u2116'); // NUMERO SIGN
        SGML_MAP.put("numsp",'\u2007'); // FIGURE SPACE
        SGML_MAP.put("nvdash",'\u22AC'); // DOES NOT PROVE
        SGML_MAP.put("nvDash",'\u22AD'); // NOT TRUE
        SGML_MAP.put("nVdash",'\u22AE'); // DOES NOT FORCE
        SGML_MAP.put("nVDash",'\u22AF'); // NEGATED DOUBLE VERTICAL BAR DOUBLE RIGHT
        SGML_MAP.put("nwarr",'\u2196'); // NORTH WEST ARROW
        SGML_MAP.put("Oacgr",'\u038C'); // GREEK CAPITAL LETTER OMICRON WITH TONOS
        SGML_MAP.put("oacgr",'\u03CC'); // GREEK SMALL LETTER OMICRON WITH TONOS
        SGML_MAP.put("Oacute",'\u00D3'); // LATIN CAPITAL LETTER O WITH ACUTE
        SGML_MAP.put("oacute",'\u00F3'); // LATIN SMALL LETTER O WITH ACUTE
        SGML_MAP.put("oast",'\u229B'); // CIRCLED ASTERISK OPERATOR
        SGML_MAP.put("ocir",'\u229A'); // CIRCLED RING OPERATOR
        SGML_MAP.put("Ocirc",'\u00D4'); // LATIN CAPITAL LETTER O WITH CIRCUMFLEX
        SGML_MAP.put("ocirc",'\u00F4'); // LATIN SMALL LETTER O WITH CIRCUMFLEX
        SGML_MAP.put("Ocy",'\u041E'); // CYRILLIC CAPITAL LETTER O
        SGML_MAP.put("ocy",'\u043E'); // CYRILLIC SMALL LETTER O
        SGML_MAP.put("odash",'\u229D'); // CIRCLED DASH
        SGML_MAP.put("Odblac",'\u0150'); // LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
        SGML_MAP.put("odblac",'\u0151'); // LATIN SMALL LETTER O WITH DOUBLE ACUTE
        SGML_MAP.put("odot",'\u2299'); // CIRCLED DOT OPERATOR
        SGML_MAP.put("OElig",'\u0152'); // LATIN CAPITAL LIGATURE OE
        SGML_MAP.put("oelig",'\u0153'); // LATIN SMALL LIGATURE OE
        SGML_MAP.put("ogon",'\u02DB'); // OGONEK
        SGML_MAP.put("Ogr",'\u039F'); // GREEK CAPITAL LETTER OMICRON
        SGML_MAP.put("ogr",'\u03BF'); // GREEK SMALL LETTER OMICRON
        SGML_MAP.put("Ograve",'\u00D2'); // LATIN CAPITAL LETTER O WITH GRAVE
        SGML_MAP.put("ograve",'\u00F2'); // LATIN SMALL LETTER O WITH GRAVE
        SGML_MAP.put("OHacgr",'\u038F'); // GREEK CAPITAL LETTER OMEGA WITH TONOS
        SGML_MAP.put("ohacgr",'\u03CE'); // GREEK SMALL LETTER OMEGA WITH TONOS
        SGML_MAP.put("OHgr",'\u03A9'); // GREEK CAPITAL LETTER OMEGA
        SGML_MAP.put("ohgr",'\u03C9'); // GREEK SMALL LETTER OMEGA
        SGML_MAP.put("ohm",'\u2126'); // OHM SIGN
        SGML_MAP.put("olarr",'\u21BA'); // ANTICLOCKWISE OPEN CIRCLE ARROW
        SGML_MAP.put("oline",'\u203E'); // OVERLINE
        SGML_MAP.put("Omacr",'\u014C'); // LATIN CAPITAL LETTER O WITH MACRON
        SGML_MAP.put("omacr",'\u014D'); // LATIN SMALL LETTER O WITH MACRON
        SGML_MAP.put("Omega",'\u03A9'); // GREEK CAPITAL LETTER OMEGA
        SGML_MAP.put("omega",'\u03C9'); // GREEK SMALL LETTER OMEGA
        SGML_MAP.put("Omicron",'\u039F'); // GREEK CAPITAL LETTER OMICRON
        SGML_MAP.put("omicron",'\u03BF'); // GREEK SMALL LETTER OMICRON
        SGML_MAP.put("ominus",'\u2296'); // CIRCLED MINUS
        SGML_MAP.put("oplus",'\u2295'); // CIRCLED PLUS
        SGML_MAP.put("or",'\u2228'); // LOGICAL OR
        SGML_MAP.put("orarr",'\u21BB'); // CLOCKWISE OPEN CIRCLE ARROW
        SGML_MAP.put("order",'\u2134'); // SCRIPT SMALL O
        SGML_MAP.put("ordf",'\u00AA'); // FEMININE ORDINAL INDICATOR
        SGML_MAP.put("ordm",'\u00BA'); // MASCULINE ORDINAL INDICATOR
        SGML_MAP.put("oS",'\u24C8'); // CIRCLED LATIN CAPITAL LETTER S
        SGML_MAP.put("Oslash",'\u00D8'); // LATIN CAPITAL LETTER O WITH STROKE
        SGML_MAP.put("oslash",'\u00F8'); // LATIN SMALL LETTER O WITH STROKE
        SGML_MAP.put("osol",'\u2298'); // CIRCLED DIVISION SLASH
        SGML_MAP.put("Otilde",'\u00D5'); // LATIN CAPITAL LETTER O WITH TILDE
        SGML_MAP.put("otilde",'\u00F5'); // LATIN SMALL LETTER O WITH TILDE
        SGML_MAP.put("otimes",'\u2297'); // CIRCLED TIMES
        SGML_MAP.put("Ouml",'\u00D6'); // LATIN CAPITAL LETTER O WITH DIAERESIS
        SGML_MAP.put("ouml",'\u00F6'); // LATIN SMALL LETTER O WITH DIAERESIS
        SGML_MAP.put("par",'\u2225'); // PARALLEL TO
        SGML_MAP.put("para",'\u00B6'); // PILCROW SIGN
        SGML_MAP.put("part",'\u2202'); // PARTIAL DIFFERENTIAL
        SGML_MAP.put("Pcy",'\u041F'); // CYRILLIC CAPITAL LETTER PE
        SGML_MAP.put("pcy",'\u043F'); // CYRILLIC SMALL LETTER PE
        SGML_MAP.put("percnt",'\u0025'); // PERCENT SIGN
        SGML_MAP.put("period",'\u002E'); // FULL STOP
        SGML_MAP.put("permil",'\u2030'); // PER MILLE SIGN
        SGML_MAP.put("perp",'\u22A5'); // UP TACK
        SGML_MAP.put("Pgr",'\u03A0'); // GREEK CAPITAL LETTER PI
        SGML_MAP.put("pgr",'\u03C0'); // GREEK SMALL LETTER PI
        SGML_MAP.put("PHgr",'\u03A6'); // GREEK CAPITAL LETTER PHI
        SGML_MAP.put("phgr",'\u03C6'); // GREEK SMALL LETTER PHI
        SGML_MAP.put("phi",'\u03C6'); // GREEK SMALL LETTER PHI
        SGML_MAP.put("Phi",'\u03A6'); // GREEK CAPITAL LETTER PHI
        SGML_MAP.put("phis",'\u03C6'); // GREEK SMALL LETTER PHI
        SGML_MAP.put("phiv",'\u03D5'); // GREEK PHI SYMBOL
        SGML_MAP.put("phmmat",'\u2133'); // SCRIPT CAPITAL M
        SGML_MAP.put("phone",'\u260E'); // BLACK TELEPHONE
        SGML_MAP.put("Pi",'\u03A0'); // GREEK CAPITAL LETTER PI
        SGML_MAP.put("pi",'\u03C0'); // GREEK SMALL LETTER PI
        SGML_MAP.put("piv",'\u03D6'); // GREEK PI SYMBOL
        SGML_MAP.put("planck",'\u210F'); // PLANCK CONSTANT OVER TWO PI
        SGML_MAP.put("plus",'\u002B'); // PLUS SIGN
        SGML_MAP.put("plusb",'\u229E'); // SQUARED PLUS
        SGML_MAP.put("plusdo",'\u2214'); // DOT PLUS
        SGML_MAP.put("plusmn",'\u00B1'); // PLUS-MINUS SIGN
        SGML_MAP.put("pound",'\u00A3'); // POUND SIGN
        SGML_MAP.put("pr",'\u227A'); // PRECEDES
        // SGML_MAP.put("prap",'?'); // precedes, approximately equal to
        SGML_MAP.put("pre",'\u227C'); // PRECEDES OR EQUAL TO
        SGML_MAP.put("prime",'\u2032'); // PRIME