htmlentitydefs.py

来自「mallet是自然语言处理、机器学习领域的一个开源项目。」· Python 代码 · 共 258 行 · 第 1/2 页

    'image':    'ℑ',      # blackletter capital I = imaginary part, U+2111 ISOamso
    'infin':    '∞',      # infinity, U+221E ISOtech
    'int':      '∫',      # integral, U+222B ISOtech
    'iota':     'ι',       # greek small letter iota, U+03B9 ISOgrk3
    'iquest':   '\277',         # inverted question mark = turned question mark, U+00BF ISOnum
    'isin':     '∈',      # element of, U+2208 ISOtech
    'iuml':     '\357',         # latin small letter i with diaeresis, U+00EF ISOlat1
    'kappa':    'κ',       # greek small letter kappa, U+03BA ISOgrk3
    'lArr':     '⇐',      # leftwards double arrow, U+21D0 ISOtech
    'lambda':   'λ',       # greek small letter lambda, U+03BB ISOgrk3
    'lang':     '〈',      # left-pointing angle bracket = bra, U+2329 ISOtech
    'laquo':    '\253',         # left-pointing double angle quotation mark = left pointing guillemet, U+00AB ISOnum
    'larr':     '←',      # leftwards arrow, U+2190 ISOnum
    'lceil':    '⌈',      # left ceiling = apl upstile, U+2308 ISOamsc
    'ldquo':    '“',      # left double quotation mark, U+201C ISOnum
    'le':       '≤',      # less-than or equal to, U+2264 ISOtech
    'lfloor':   '⌊',      # left floor = apl downstile, U+230A ISOamsc
    'lowast':   '∗',      # asterisk operator, U+2217 ISOtech
    'loz':      '◊',      # lozenge, U+25CA ISOpub
    'lrm':      '‎',      # left-to-right mark, U+200E NEW RFC 2070
    'lsaquo':   '‹',      # single left-pointing angle quotation mark, U+2039 ISO proposed
    'lsquo':    '‘',      # left single quotation mark, U+2018 ISOnum
    'lt':       '\74',          # less-than sign, U+003C ISOnum
    'macr':     '\257',         # macron = spacing macron = overline = APL overbar, U+00AF ISOdia
    'mdash':    '—',      # em dash, U+2014 ISOpub
    'micro':    '\265',         # micro sign, U+00B5 ISOnum
    'middot':   '\267',         # middle dot = Georgian comma = Greek middle dot, U+00B7 ISOnum
    'minus':    '−',      # minus sign, U+2212 ISOtech
    'mu':       'μ',       # greek small letter mu, U+03BC ISOgrk3
    'nabla':    '∇',      # nabla = backward difference, U+2207 ISOtech
    'nbsp':     '\240',         # no-break space = non-breaking space, U+00A0 ISOnum
    'ndash':    '–',      # en dash, U+2013 ISOpub
    'ne':       '≠',      # not equal to, U+2260 ISOtech
    'ni':       '∋',      # contains as member, U+220B ISOtech
    'not':      '\254',         # not sign, U+00AC ISOnum
    'notin':    '∉',      # not an element of, U+2209 ISOtech
    'nsub':     '⊄',      # not a subset of, U+2284 ISOamsn
    'ntilde':   '\361',         # latin small letter n with tilde, U+00F1 ISOlat1
    'nu':       'ν',       # greek small letter nu, U+03BD ISOgrk3
    'oacute':   '\363',         # latin small letter o with acute, U+00F3 ISOlat1
    'ocirc':    '\364',         # latin small letter o with circumflex, U+00F4 ISOlat1
    'oelig':    'œ',       # latin small ligature oe, U+0153 ISOlat2
    'ograve':   '\362',         # latin small letter o with grave, U+00F2 ISOlat1
    'oline':    '‾',      # overline = spacing overscore, U+203E NEW
    'omega':    'ω',       # greek small letter omega, U+03C9 ISOgrk3
    'omicron':  'ο',       # greek small letter omicron, U+03BF NEW
    'oplus':    '⊕',      # circled plus = direct sum, U+2295 ISOamsb
    'or':       '∨',      # logical or = vee, U+2228 ISOtech
    'ordf':     '\252',         # feminine ordinal indicator, U+00AA ISOnum
    'ordm':     '\272',         # masculine ordinal indicator, U+00BA ISOnum
    'oslash':   '\370',         # latin small letter o with stroke, = latin small letter o slash, U+00F8 ISOlat1
    'otilde':   '\365',         # latin small letter o with tilde, U+00F5 ISOlat1
    'otimes':   '⊗',      # circled times = vector product, U+2297 ISOamsb
    'ouml':     '\366',         # latin small letter o with diaeresis, U+00F6 ISOlat1
    'para':     '\266',         # pilcrow sign = paragraph sign, U+00B6 ISOnum
    'part':     '∂',      # partial differential, U+2202 ISOtech
    'permil':   '‰',      # per mille sign, U+2030 ISOtech
    'perp':     '⊥',      # up tack = orthogonal to = perpendicular, U+22A5 ISOtech
    'phi':      'φ',       # greek small letter phi, U+03C6 ISOgrk3
    'pi':       'π',       # greek small letter pi, U+03C0 ISOgrk3
    'piv':      'ϖ',       # greek pi symbol, U+03D6 ISOgrk3
    'plusmn':   '\261',         # plus-minus sign = plus-or-minus sign, U+00B1 ISOnum
    'pound':    '\243',         # pound sign, U+00A3 ISOnum
    'prime':    '′',      # prime = minutes = feet, U+2032 ISOtech
    'prod':     '∏',      # n-ary product = product sign, U+220F ISOamsb
    'prop':     '∝',      # proportional to, U+221D ISOtech
    'psi':      'ψ',       # greek small letter psi, U+03C8 ISOgrk3
    'quot':     '\42',          # quotation mark = APL quote, U+0022 ISOnum
    'rArr':     '⇒',      # rightwards double arrow, U+21D2 ISOtech
    'radic':    '√',      # square root = radical sign, U+221A ISOtech
    'rang':     '〉',      # right-pointing angle bracket = ket, U+232A ISOtech
    'raquo':    '\273',         # right-pointing double angle quotation mark = right pointing guillemet, U+00BB ISOnum
    'rarr':     '→',      # rightwards arrow, U+2192 ISOnum
    'rceil':    '⌉',      # right ceiling, U+2309 ISOamsc
    'rdquo':    '”',      # right double quotation mark, U+201D ISOnum
    'real':     'ℜ',      # blackletter capital R = real part symbol, U+211C ISOamso
    'reg':      '\256',         # registered sign = registered trade mark sign, U+00AE ISOnum
    'rfloor':   '⌋',      # right floor, U+230B ISOamsc
    'rho':      'ρ',       # greek small letter rho, U+03C1 ISOgrk3
    'rlm':      '‏',      # right-to-left mark, U+200F NEW RFC 2070
    'rsaquo':   '›',      # single right-pointing angle quotation mark, U+203A ISO proposed
    'rsquo':    '’',      # right single quotation mark, U+2019 ISOnum
    'sbquo':    '‚',      # single low-9 quotation mark, U+201A NEW
    'scaron':   'š',       # latin small letter s with caron, U+0161 ISOlat2
    'sdot':     '⋅',      # dot operator, U+22C5 ISOamsb
    'sect':     '\247',         # section sign, U+00A7 ISOnum
    'shy':      '\255',         # soft hyphen = discretionary hyphen, U+00AD ISOnum
    'sigma':    'σ',       # greek small letter sigma, U+03C3 ISOgrk3
    'sigmaf':   'ς',       # greek small letter final sigma, U+03C2 ISOgrk3
    'sim':      '∼',      # tilde operator = varies with = similar to, U+223C ISOtech
    'spades':   '♠',      # black spade suit, U+2660 ISOpub
    'sub':      '⊂',      # subset of, U+2282 ISOtech
    'sube':     '⊆',      # subset of or equal to, U+2286 ISOtech
    'sum':      '∑',      # n-ary sumation, U+2211 ISOamsb
    'sup':      '⊃',      # superset of, U+2283 ISOtech
    'sup1':     '\271',         # superscript one = superscript digit one, U+00B9 ISOnum
    'sup2':     '\262',         # superscript two = superscript digit two = squared, U+00B2 ISOnum
    'sup3':     '\263',         # superscript three = superscript digit three = cubed, U+00B3 ISOnum
    'supe':     '⊇',      # superset of or equal to, U+2287 ISOtech
    'szlig':    '\337',         # latin small letter sharp s = ess-zed, U+00DF ISOlat1
    'tau':      'τ',       # greek small letter tau, U+03C4 ISOgrk3
    'there4':   '∴',      # therefore, U+2234 ISOtech
    'theta':    'θ',       # greek small letter theta, U+03B8 ISOgrk3
    'thetasym': 'ϑ',       # greek small letter theta symbol, U+03D1 NEW
    'thinsp':   ' ',      # thin space, U+2009 ISOpub
    'thorn':    '\376',         # latin small letter thorn with, U+00FE ISOlat1
    'tilde':    '˜',       # small tilde, U+02DC ISOdia
    'times':    '\327',         # multiplication sign, U+00D7 ISOnum
    'trade':    '™',      # trade mark sign, U+2122 ISOnum
    'uArr':     '⇑',      # upwards double arrow, U+21D1 ISOamsa
    'uacute':   '\372',         # latin small letter u with acute, U+00FA ISOlat1
    'uarr':     '↑',      # upwards arrow, U+2191 ISOnum
    'ucirc':    '\373',         # latin small letter u with circumflex, U+00FB ISOlat1
    'ugrave':   '\371',         # latin small letter u with grave, U+00F9 ISOlat1
    'uml':      '\250',         # diaeresis = spacing diaeresis, U+00A8 ISOdia
    'upsih':    'ϒ',       # greek upsilon with hook symbol, U+03D2 NEW
    'upsilon':  'υ',       # greek small letter upsilon, U+03C5 ISOgrk3
    'uuml':     '\374',         # latin small letter u with diaeresis, U+00FC ISOlat1
    'weierp':   '℘',      # script capital P = power set = Weierstrass p, U+2118 ISOamso
    'xi':       'ξ',       # greek small letter xi, U+03BE ISOgrk3
    'yacute':   '\375',         # latin small letter y with acute, U+00FD ISOlat1
    'yen':      '\245',         # yen sign = yuan sign, U+00A5 ISOnum
    'yuml':     '\377',         # latin small letter y with diaeresis, U+00FF ISOlat1
    'zeta':     'ζ',       # greek small letter zeta, U+03B6 ISOgrk3
    'zwj':      '‍',      # zero width joiner, U+200D NEW RFC 2070
    'zwnj':     '‌',      # zero width non-joiner, U+200C NEW RFC 2070

}