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("Prime",'\u2033'); // DOUBLE PRIME
        // SGML_MAP.put("prnap",'?'); // precedes, not approximately equal to
        // SGML_MAP.put("prnE",'?'); // precedes, not double equal
        SGML_MAP.put("prnsim",'\u22E8'); // PRECEDES BUT NOT EQUIVALENT TO
        SGML_MAP.put("prod",'\u220F'); // N-ARY PRODUCT
        SGML_MAP.put("prop",'\u221D'); // PROPORTIONAL TO
        SGML_MAP.put("prsim",'\u227E'); // PRECEDES OR EQUIVALENT TO
        SGML_MAP.put("PSgr",'\u03A8'); // GREEK CAPITAL LETTER PSI
        SGML_MAP.put("psgr",'\u03C8'); // GREEK SMALL LETTER PSI
        SGML_MAP.put("Psi",'\u03A8'); // GREEK CAPITAL LETTER PSI
        SGML_MAP.put("psi",'\u03C8'); // GREEK SMALL LETTER PSI
        SGML_MAP.put("puncsp",'\u2008'); // PUNCTUATION SPACE
        SGML_MAP.put("quest",'\u003F'); // QUESTION MARK
        SGML_MAP.put("quot",'\u0022'); // QUOTATION MARK
        SGML_MAP.put("rAarr",'\u21DB'); // RIGHTWARDS TRIPLE ARROW
        SGML_MAP.put("Racute",'\u0154'); // LATIN CAPITAL LETTER R WITH ACUTE
        SGML_MAP.put("racute",'\u0155'); // LATIN SMALL LETTER R WITH ACUTE
        SGML_MAP.put("radic",'\u221A'); // SQUARE ROOT
        SGML_MAP.put("rang",'\u232A'); // RIGHT-POINTING ANGLE BRACKET
        SGML_MAP.put("raquo",'\u00BB'); // RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
        SGML_MAP.put("Rarr",'\u21A0'); // RIGHTWARDS TWO HEADED ARROW
        SGML_MAP.put("rarr",'\u2192'); // RIGHTWARDS ARROW
        SGML_MAP.put("rArr",'\u21D2'); // RIGHTWARDS DOUBLE ARROW
        SGML_MAP.put("rarr2",'\u21C9'); // RIGHTWARDS PAIRED ARROWS
        SGML_MAP.put("rarrhk",'\u21AA'); // RIGHTWARDS ARROW WITH HOOK
        SGML_MAP.put("rarrlp",'\u21AC'); // RIGHTWARDS ARROW WITH LOOP
        SGML_MAP.put("rarrtl",'\u21A3'); // RIGHTWARDS ARROW WITH TAIL
        SGML_MAP.put("rarrw",'\u219D'); // RIGHTWARDS WAVE ARROW
        SGML_MAP.put("Rcaron",'\u0158'); // LATIN CAPITAL LETTER R WITH CARON
        SGML_MAP.put("rcaron",'\u0159'); // LATIN SMALL LETTER R WITH CARON
        SGML_MAP.put("Rcedil",'\u0156'); // LATIN CAPITAL LETTER R WITH CEDILLA
        SGML_MAP.put("rcedil",'\u0157'); // LATIN SMALL LETTER R WITH CEDILLA
        SGML_MAP.put("rceil",'\u2309'); // RIGHT CEILING
        SGML_MAP.put("rcub",'\u007D'); // RIGHT CURLY BRACKET
        SGML_MAP.put("Rcy",'\u0420'); // CYRILLIC CAPITAL LETTER ER
        SGML_MAP.put("rcy",'\u0440'); // CYRILLIC SMALL LETTER ER
        SGML_MAP.put("rdquo",'\u201D'); // RIGHT DOUBLE QUOTATION MARK
        SGML_MAP.put("rdquor",'\u201C'); // LEFT DOUBLE QUOTATION MARK
        SGML_MAP.put("real",'\u211C'); // BLACK-LETTER CAPITAL R
        SGML_MAP.put("rect",'\u25AD'); // WHITE RECTANGLE
        SGML_MAP.put("reg",'\u00AE'); // REGISTERED SIGN
        SGML_MAP.put("rfloor",'\u230B'); // RIGHT FLOOR
        SGML_MAP.put("Rgr",'\u03A1'); // GREEK CAPITAL LETTER RHO
        SGML_MAP.put("rgr",'\u03C1'); // GREEK SMALL LETTER RHO
        SGML_MAP.put("rhard",'\u21C1'); // RIGHTWARDS HARPOON WITH BARB DOWNWARDS
        SGML_MAP.put("rharu",'\u21C0'); // RIGHTWARDS HARPOON WITH BARB UPWARDS
        SGML_MAP.put("Rho",'\u03A1'); // GREEK CAPITAL LETTER RHO
        SGML_MAP.put("rho",'\u03C1'); // GREEK SMALL LETTER RHO
        SGML_MAP.put("rhov",'\u03F1'); // GREEK RHO SYMBOL
        SGML_MAP.put("ring",'\u02DA'); // RING ABOVE
        SGML_MAP.put("rlarr2",'\u21C4'); // RIGHTWARDS ARROW OVER LEFTWARDS ARROW
        SGML_MAP.put("rlhar2",'\u21CC'); // RIGHTWARDS HARPOON OVER LEFTWARDS HARPOON
        SGML_MAP.put("rlm",'\u200F'); // RIGHT-TO-LEFT MARK
        SGML_MAP.put("rpar",'\u0029'); // RIGHT PARENTHESIS
        // SGML_MAP.put("rpargt",'?'); // right parenthesis, greater-than
        SGML_MAP.put("rsaquo",'\u203A'); // SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
        SGML_MAP.put("rsh",'\u21B1'); // UPWARDS ARROW WITH TIP RIGHTWARDS
        SGML_MAP.put("rsqb",'\u005D'); // RIGHT SQUARE BRACKET
        SGML_MAP.put("rsquo",'\u2019'); // RIGHT SINGLE QUOTATION MARK
        SGML_MAP.put("rsquor",'\u2018'); // LEFT SINGLE QUOTATION MARK
        SGML_MAP.put("rthree",'\u22CC'); // RIGHT SEMIDIRECT PRODUCT
        SGML_MAP.put("rtimes",'\u22CA'); // RIGHT NORMAL FACTOR SEMIDIRECT PRODUCT
        SGML_MAP.put("rtri",'\u25B9'); // WHITE RIGHT-POINTING SMALL TRIANGLE
        SGML_MAP.put("rtrie",'\u22B5'); // CONTAINS AS NORMAL SUBGROUP OR EQUAL TO
        SGML_MAP.put("rtrif",'\u25B8'); // BLACK RIGHT-POINTING SMALL TRIANGLE
        SGML_MAP.put("rx",'\u211E'); // PRESCRIPTION TAKE
        SGML_MAP.put("Sacute",'\u015A'); // LATIN CAPITAL LETTER S WITH ACUTE
        SGML_MAP.put("sacute",'\u015B'); // LATIN SMALL LETTER S WITH ACUTE
        SGML_MAP.put("samalg",'\u2210'); // N-ARY COPRODUCT
        SGML_MAP.put("sbquo",'\u201A'); // SINGLE LOW-9 QUOTATION MARK
        // SGML_MAP.put("sbsol","005C"); // REVERSE SOLIDUS
        SGML_MAP.put("sc",'\u227B'); // SUCCEEDS
        // SGML_MAP.put("scap",'?'); // succeeds, approximately equal to
        SGML_MAP.put("Scaron",'\u0160'); // LATIN CAPITAL LETTER S WITH CARON
        SGML_MAP.put("scaron",'\u0161'); // LATIN SMALL LETTER S WITH CARON
        SGML_MAP.put("sccue",'\u227D'); // SUCCEEDS OR EQUAL TO
        SGML_MAP.put("sce",'\u227D'); // SUCCEEDS OR EQUAL TO
        SGML_MAP.put("Scedil",'\u015E'); // LATIN CAPITAL LETTER S WITH CEDILLA
        SGML_MAP.put("scedil",'\u015F'); // LATIN SMALL LETTER S WITH CEDILLA
        SGML_MAP.put("Scirc",'\u015C'); // LATIN CAPITAL LETTER S WITH CIRCUMFLEX
        SGML_MAP.put("scirc",'\u015D'); // LATIN SMALL LETTER S WITH CIRCUMFLEX
        // SGML_MAP.put("scnap",'?'); // succeeds, not approximately equal to
        // SGML_MAP.put("scnE",'?'); // succeeds, not double equals
        SGML_MAP.put("scnsim",'\u22E9'); // SUCCEEDS BUT NOT EQUIVALENT TO
        SGML_MAP.put("scsim",'\u227F'); // SUCCEEDS OR EQUIVALENT TO
        SGML_MAP.put("Scy",'\u0421'); // CYRILLIC CAPITAL LETTER ES
        SGML_MAP.put("scy",'\u0441'); // CYRILLIC SMALL LETTER ES
        SGML_MAP.put("sdot",'\u22C5'); // DOT OPERATOR
        SGML_MAP.put("sdotb",'\u22A1'); // SQUARED DOT OPERATOR
        SGML_MAP.put("sect",'\u00A7'); // SECTION SIGN
        SGML_MAP.put("semi",'\u003B'); // SEMICOLON
        SGML_MAP.put("setmn",'\u2216'); // SET MINUS
        SGML_MAP.put("sext",'\u2736'); // SIX POINTED BLACK STAR
        SGML_MAP.put("sfgr",'\u03C2'); // GREEK SMALL LETTER FINAL SIGMA
        SGML_MAP.put("sfrown",'\u2322'); // FROWN
        SGML_MAP.put("Sgr",'\u03A3'); // GREEK CAPITAL LETTER SIGMA
        SGML_MAP.put("sgr",'\u03C3'); // GREEK SMALL LETTER SIGMA
        SGML_MAP.put("sharp",'\u266F'); // MUSIC SHARP SIGN
        SGML_MAP.put("SHCHcy",'\u0429'); // CYRILLIC CAPITAL LETTER SHCHA
        SGML_MAP.put("shchcy",'\u0449'); // CYRILLIC SMALL LETTER SHCHA
        SGML_MAP.put("SHcy",'\u0428'); // CYRILLIC CAPITAL LETTER SHA
        SGML_MAP.put("shcy",'\u0448'); // CYRILLIC SMALL LETTER SHA
        SGML_MAP.put("shy",'\u00AD'); // SOFT HYPHEN
        SGML_MAP.put("Sigma",'\u03A3'); // GREEK CAPITAL LETTER SIGMA
        SGML_MAP.put("sigma",'\u03C3'); // GREEK SMALL LETTER SIGMA
        SGML_MAP.put("sigmaf",'\u03C2'); // GREEK SMALL LETTER FINAL SIGMA
        SGML_MAP.put("sigmav",'\u03C2'); // GREEK SMALL LETTER FINAL SIGMA
        SGML_MAP.put("sim",'\u223C'); // TILDE OPERATOR
        SGML_MAP.put("sime",'\u2243'); // ASYMPTOTICALLY EQUAL TO
        // SGML_MAP.put("smid",'?'); // shortmid
        SGML_MAP.put("smile",'\u2323'); // SMILE
        SGML_MAP.put("SOFTcy",'\u042C'); // CYRILLIC CAPITAL LETTER SOFT SIGN
        SGML_MAP.put("softcy",'\u044C'); // CYRILLIC SMALL LETTER SOFT SIGN
        SGML_MAP.put("sol",'\u002F'); // SOLIDUS
        SGML_MAP.put("spades",'\u2660'); // BLACK SPADE SUIT
        SGML_MAP.put("spar",'\u2225'); // PARALLEL TO
        SGML_MAP.put("sqcap",'\u2293'); // SQUARE CAP
        SGML_MAP.put("sqcup",'\u2294'); // SQUARE CUP
        SGML_MAP.put("sqsub",'\u228F'); // SQUARE IMAGE OF
        SGML_MAP.put("sqsube",'\u2291'); // SQUARE IMAGE OF OR EQUAL TO
        SGML_MAP.put("sqsup",'\u2290'); // SQUARE ORIGINAL OF
        SGML_MAP.put("sqsupe",'\u2292'); // SQUARE ORIGINAL OF OR EQUAL TO
        SGML_MAP.put("squ",'\u25A1'); // WHITE SQUARE
        SGML_MAP.put("square",'\u25A1'); // WHITE SQUARE
        SGML_MAP.put("squf",'\u25AA'); // BLACK SMALL SQUARE
        SGML_MAP.put("ssetmn",'\u2216'); // SET MINUS
        SGML_MAP.put("ssmile",'\u2323'); // SMILE
        SGML_MAP.put("sstarf",'\u22C6'); // STAR OPERATOR
        SGML_MAP.put("star",'\u2606'); // WHITE STAR
        SGML_MAP.put("starf",'\u2605'); // BLACK STAR
        SGML_MAP.put("Sub",'\u22D0'); // DOUBLE SUBSET
        SGML_MAP.put("sub",'\u2282'); // SUBSET OF
        SGML_MAP.put("subE",'\u2286'); // SUBSET OF OR EQUAL TO
        SGML_MAP.put("sube",'\u2286'); // SUBSET OF OR EQUAL TO
        SGML_MAP.put("subnE",'\u228A'); // SUBSET OF WITH NOT EQUAL TO
        SGML_MAP.put("subne",'\u228A'); // SUBSET OF WITH NOT EQUAL TO
        SGML_MAP.put("sum",'\u2211'); // N-ARY SUMMATION
        SGML_MAP.put("sung",'\u266A'); // EIGHTH NOTE
        SGML_MAP.put("Sup",'\u22D1'); // DOUBLE SUPERSET
        SGML_MAP.put("sup",'\u2283'); // SUPERSET OF
        SGML_MAP.put("sup1",'\u00B9'); // SUPERSCRIPT ONE
        SGML_MAP.put("sup2",'\u00B2'); // SUPERSCRIPT TWO
        SGML_MAP.put("sup3",'\u00B3'); // SUPERSCRIPT THREE
        SGML_MAP.put("supE",'\u2287'); // SUPERSET OF OR EQUAL TO
        SGML_MAP.put("supe",'\u2287'); // SUPERSET OF OR EQUAL TO
        SGML_MAP.put("supnE",'\u228B'); // SUPERSET OF WITH NOT EQUAL TO
        SGML_MAP.put("supne",'\u228B'); // SUPERSET OF WITH NOT EQUAL TO
        SGML_MAP.put("szlig",'\u00DF'); // LATIN SMALL LETTER SHARP S
        SGML_MAP.put("target",'\u2316'); // POSITION INDICATOR
        SGML_MAP.put("Tau",'\u03A4'); // GREEK CAPITAL LETTER TAU
        SGML_MAP.put("tau",'\u03C4'); // GREEK SMALL LETTER TAU
        SGML_MAP.put("Tcaron",'\u0164'); // LATIN CAPITAL LETTER T WITH CARON
        SGML_MAP.put("tcaron",'\u0165'); // LATIN SMALL LETTER T WITH CARON
        SGML_MAP.put("Tcedil",'\u0162'); // LATIN CAPITAL LETTER T WITH CEDILLA
        SGML_MAP.put("tcedil",'\u0163'); // LATIN SMALL LETTER T WITH CEDILLA
        SGML_MAP.put("Tcy",'\u0422'); // CYRILLIC CAPITAL LETTER TE
        SGML_MAP.put("tcy",'\u0442'); // CYRILLIC SMALL LETTER TE
        SGML_MAP.put("tdot",'\u20DB'); // COMBINING THREE DOTS ABOVE
        SGML_MAP.put("telrec",'\u2315'); // TELEPHONE RECORDER
        SGML_MAP.put("Tgr",'\u03A4'); // GREEK CAPITAL LETTER TAU
        SGML_MAP.put("tgr",'\u03C4'); // GREEK SMALL LETTER TAU
        SGML_MAP.put("there4",'\u2234'); // THEREFORE
        SGML_MAP.put("theta",'\u03B8'); // GREEK SMALL LETTER THETA
        SGML_MAP.put("Theta",'\u0398'); // GREEK CAPITAL LETTER THETA
        SGML_MAP.put("thetas",'\u03B8'); // GREEK SMALL LETTER THETA
        SGML_MAP.put("thetasym",'\u03D1'); // GREEK THETA SYMBOL
        SGML_MAP.put("thetav",'\u03D1'); // GREEK THETA SYMBOL
        SGML_MAP.put("THgr",'\u0398'); // GREEK CAPITAL LETTER THETA
        SGML_MAP.put("thgr",'\u03B8'); // GREEK SMALL LETTER THETA
        SGML_MAP.put("thinsp",'\u2009'); // THIN SPACE
        SGML_MAP.put("thkap",'\u2248'); // ALMOST EQUAL TO
        SGML_MAP.put("thksim",'\u223C'); // TILDE OPERATOR
        SGML_MAP.put("THORN",'\u00DE'); // LATIN CAPITAL LETTER THORN
        SGML_MAP.put("thorn",'\u00FE'); // LATIN SMALL LETTER THORN
        SGML_MAP.put("tilde",'\u02DC'); // SMALL TILDE
        SGML_MAP.put("times",'\u00D7'); // MULTIPLICATION SIGN
        SGML_MAP.put("timesb",'\u22A0'); // SQUARED TIMES
        SGML_MAP.put("top",'\u22A4'); // DOWN TACK
        SGML_MAP.put("tprime",'\u2034'); // TRIPLE PRIME
        SGML_MAP.put("trade",'\u2122'); // TRADE MARK SIGN
        SGML_MAP.put("trie",'\u225C'); // DELTA EQUAL TO
        SGML_MAP.put("TScy",'\u0426'); // CYRILLIC CAPITAL LETTER TSE
        SGML_MAP.put("tscy",'\u0446'); // CYRILLIC SMALL LETTER TSE
        SGML_MAP.put("TSHcy",'\u040B'); // CYRILLIC CAPITAL LETTER TSHE
        SGML_MAP.put("tshcy",'\u045B'); // CYRILLIC SMALL LETTER TSHE
        SGML_MAP.put("Tstrok",'\u0166'); // LATIN CAPITAL LETTER T WITH STROKE
        SGML_MAP.put("tstrok",'\u0167'); // LATIN SMALL LETTER T WITH STROKE
        SGML_MAP.put("twixt",'\u226C'); // BETWEEN
        SGML_MAP.put("Uacgr",'\u038E'); // GREEK CAPITAL LETTER UPSILON WITH TONOS
        SGML_MAP.put("uacgr",'\u03CD'); // GREEK SMALL LETTER UPSILON WITH TONOS
        SGML_MAP.put("Uacute",'\u00DA'); // LATIN CAPITAL LETTER U WITH ACUTE
        SGML_MAP.put("uacute",'\u00FA'); // LATIN SMALL LETTER U WITH ACUTE
        SGML_MAP.put("uArr",'\u21D1'); // UPWARDS DOUBLE ARROW
        SGML_MAP.put("uarr",'\u2191'); // UPWARDS ARROW
        SGML_MAP.put("uarr2",'\u21C8'); // UPWARDS PAIRED ARROWS
        SGML_MAP.put("Ubrcy",'\u040E'); // CYRILLIC CAPITAL LETTER SHORT U
        SGML_MAP.put("ubrcy",'\u045E'); // CYRILLIC SMALL LETTER SHORT U
        SGML_MAP.put("Ubreve",'\u016C'); // LATIN CAPITAL LETTER U WITH BREVE
        SGML_MAP.put("ubreve",'\u016D'); // LATIN SMALL LETTER U WITH BREVE
        SGML_MAP.put("Ucirc",'\u00DB'); // LATIN CAPITA