[Python-Dev] New htmlentitydefs.py file
M.-A. Lemburg
mal@lemburg.com
Mon, 16 Aug 1999 22:22:12 +0200
This is a multi-part message in MIME format.
--------------3B4AC9E96FE0666068F893B2
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Attached you find a new HTML entity definitions file taken and
parsed from:
http://www.w3.org/TR/1998/REC-html40-19980424/HTMLlat1.ent
http://www.w3.org/TR/1998/REC-html40-19980424/HTMLsymbol.ent
http://www.w3.org/TR/1998/REC-html40-19980424/HTMLspecial.ent
The latter two contain Unicode charcodes which obviously cannot
(yet) be mapped to Unicode strings... perhaps Fredrik wants
to include a spiced up version in with his Unicode type.
--
Marc-Andre Lemburg
______________________________________________________________________
Y2000: 138 days left
Business: http://www.lemburg.com/
Python Pages: http://www.lemburg.com/python/
--------------3B4AC9E96FE0666068F893B2
Content-Type: text/plain; charset=us-ascii; name="htmlentitydefs.py"
Content-Transfer-Encoding: 7bit
Content-Disposition: inline; filename="htmlentitydefs.py"
"""
Entity definitions for HTML4.0. Taken and parsed from:
http://www.w3.org/TR/1998/REC-html40/HTMLlat1.ent
http://www.w3.org/TR/1998/REC-html40/HTMLsymbol.ent
http://www.w3.org/TR/1998/REC-html40/HTMLspecial.ent
"""
entitydefs = {
'AElig': chr(198), # latin capital letter AE = latin capital ligature AE, U+00C6 ISOlat1
'Aacute': chr(193), # latin capital letter A with acute, U+00C1 ISOlat1
'Acirc': chr(194), # latin capital letter A with circumflex, U+00C2 ISOlat1
'Agrave': chr(192), # latin capital letter A with grave = latin capital letter A grave, U+00C0 ISOlat1
'Alpha': 'Α', # greek capital letter alpha, U+0391
'Aring': chr(197), # latin capital letter A with ring above = latin capital letter A ring, U+00C5 ISOlat1
'Atilde': chr(195), # latin capital letter A with tilde, U+00C3 ISOlat1
'Auml': chr(196), # latin capital letter A with diaeresis, U+00C4 ISOlat1
'Beta': 'Β', # greek capital letter beta, U+0392
'Ccedil': chr(199), # latin capital letter C with cedilla, U+00C7 ISOlat1
'Chi': 'Χ', # greek capital letter chi, U+03A7
'Dagger': '‡', # double dagger, U+2021 ISOpub
'Delta': 'Δ', # greek capital letter delta, U+0394 ISOgrk3
'ETH': chr(208), # latin capital letter ETH, U+00D0 ISOlat1
'Eacute': chr(201), # latin capital letter E with acute, U+00C9 ISOlat1
'Ecirc': chr(202), # latin capital letter E with circumflex, U+00CA ISOlat1
'Egrave': chr(200), # latin capital letter E with grave, U+00C8 ISOlat1
'Epsilon': 'Ε', # greek capital letter epsilon, U+0395
'Eta': 'Η', # greek capital letter eta, U+0397
'Euml': chr(203), # latin capital letter E with diaeresis, U+00CB ISOlat1
'Gamma': 'Γ', # greek capital letter gamma, U+0393 ISOgrk3
'Iacute': chr(205), # latin capital letter I with acute, U+00CD ISOlat1
'Icirc': chr(206), # latin capital letter I with circumflex, U+00CE ISOlat1
'Igrave': chr(204), # latin capital letter I with grave, U+00CC ISOlat1
'Iota': 'Ι', # greek capital letter iota, U+0399
'Iuml': chr(207), # latin capital letter I with diaeresis, U+00CF ISOlat1
'Kappa': 'Κ', # greek capital letter kappa, U+039A
'Lambda': 'Λ', # greek capital letter lambda, U+039B ISOgrk3
'Mu': 'Μ', # greek capital letter mu, U+039C
'Ntilde': chr(209), # latin capital letter N with tilde, U+00D1 ISOlat1
'Nu': 'Ν', # greek capital letter nu, U+039D
'Oacute': chr(211), # latin capital letter O with acute, U+00D3 ISOlat1
'Ocirc': chr(212), # latin capital letter O with circumflex, U+00D4 ISOlat1
'Ograve': chr(210), # latin capital letter O with grave, U+00D2 ISOlat1
'Omega': 'Ω', # greek capital letter omega, U+03A9 ISOgrk3
'Omicron': 'Ο', # greek capital letter omicron, U+039F
'Oslash': chr(216), # latin capital letter O with stroke = latin capital letter O slash, U+00D8 ISOlat1
'Otilde': chr(213), # latin capital letter O with tilde, U+00D5 ISOlat1
'Ouml': chr(214), # latin capital letter O with diaeresis, U+00D6 ISOlat1
'Phi': 'Φ', # greek capital letter phi, U+03A6 ISOgrk3
'Pi': 'Π', # greek capital letter pi, U+03A0 ISOgrk3
'Prime': '″', # double prime = seconds = inches, U+2033 ISOtech
'Psi': 'Ψ', # greek capital letter psi, U+03A8 ISOgrk3
'Rho': 'Ρ', # greek capital letter rho, U+03A1
'Sigma': 'Σ', # greek capital letter sigma, U+03A3 ISOgrk3
'THORN': chr(222), # latin capital letter THORN, U+00DE ISOlat1
'Tau': 'Τ', # greek capital letter tau, U+03A4
'Theta': 'Θ', # greek capital letter theta, U+0398 ISOgrk3
'Uacute': chr(218), # latin capital letter U with acute, U+00DA ISOlat1
'Ucirc': chr(219), # latin capital letter U with circumflex, U+00DB ISOlat1
'Ugrave': chr(217), # latin capital letter U with grave, U+00D9 ISOlat1
'Upsilon': 'Υ', # greek capital letter upsilon, U+03A5 ISOgrk3
'Uuml': chr(220), # latin capital letter U with diaeresis, U+00DC ISOlat1
'Xi': 'Ξ', # greek capital letter xi, U+039E ISOgrk3
'Yacute': chr(221), # latin capital letter Y with acute, U+00DD ISOlat1
'Zeta': 'Ζ', # greek capital letter zeta, U+0396
'aacute': chr(225), # latin small letter a with acute, U+00E1 ISOlat1
'acirc': chr(226), # latin small letter a with circumflex, U+00E2 ISOlat1
'acute': chr(180), # acute accent = spacing acute, U+00B4 ISOdia
'aelig': chr(230), # latin small letter ae = latin small ligature ae, U+00E6 ISOlat1
'agrave': chr(224), # latin small letter a with grave = latin small letter a grave, U+00E0 ISOlat1
'alefsym': 'ℵ', # alef symbol = first transfinite cardinal, U+2135 NEW
'alpha': 'α', # greek small letter alpha, U+03B1 ISOgrk3
'and': '∧', # logical and = wedge, U+2227 ISOtech
'ang': '∠', # angle, U+2220 ISOamso
'aring': chr(229), # latin small letter a with ring above = latin small letter a ring, U+00E5 ISOlat1
'asymp': '≈', # almost equal to = asymptotic to, U+2248 ISOamsr
'atilde': chr(227), # latin small letter a with tilde, U+00E3 ISOlat1
'auml': chr(228), # latin small letter a with diaeresis, U+00E4 ISOlat1
'bdquo': '„', # double low-9 quotation mark, U+201E NEW
'beta': 'β', # greek small letter beta, U+03B2 ISOgrk3
'brvbar': chr(166), # broken bar = broken vertical bar, U+00A6 ISOnum
'bull': '•', # bullet = black small circle, U+2022 ISOpub
'cap': '∩', # intersection = cap, U+2229 ISOtech
'ccedil': chr(231), # latin small letter c with cedilla, U+00E7 ISOlat1
'cedil': chr(184), # cedilla = spacing cedilla, U+00B8 ISOdia
'cent': chr(162), # cent sign, U+00A2 ISOnum
'chi': 'χ', # greek small letter chi, U+03C7 ISOgrk3
'clubs': '♣', # black club suit = shamrock, U+2663 ISOpub
'cong': '≅', # approximately equal to, U+2245 ISOtech
'copy': chr(169), # copyright sign, U+00A9 ISOnum
'crarr': '↵', # downwards arrow with corner leftwards = carriage return, U+21B5 NEW
'cup': '∪', # union = cup, U+222A ISOtech
'curren': chr(164), # currency sign, U+00A4 ISOnum
'dArr': '⇓', # downwards double arrow, U+21D3 ISOamsa
'dagger': '†', # dagger, U+2020 ISOpub
'darr': '↓', # downwards arrow, U+2193 ISOnum
'deg': chr(176), # degree sign, U+00B0 ISOnum
'delta': 'δ', # greek small letter delta, U+03B4 ISOgrk3
'diams': '♦', # black diamond suit, U+2666 ISOpub
'divide': chr(247), # division sign, U+00F7 ISOnum
'eacute': chr(233), # latin small letter e with acute, U+00E9 ISOlat1
'ecirc': chr(234), # latin small letter e with circumflex, U+00EA ISOlat1
'egrave': chr(232), # latin small letter e with grave, U+00E8 ISOlat1
'empty': '∅', # empty set = null set = diameter, U+2205 ISOamso
'emsp': ' ', # em space, U+2003 ISOpub
'ensp': ' ', # en space, U+2002 ISOpub
'epsilon': 'ε', # greek small letter epsilon, U+03B5 ISOgrk3
'equiv': '≡', # identical to, U+2261 ISOtech
'eta': 'η', # greek small letter eta, U+03B7 ISOgrk3
'eth': chr(240), # latin small letter eth, U+00F0 ISOlat1
'euml': chr(235), # latin small letter e with diaeresis, U+00EB ISOlat1
'exist': '∃', # there exists, U+2203 ISOtech
'fnof': 'ƒ', # latin small f with hook = function = florin, U+0192 ISOtech
'forall': '∀', # for all, U+2200 ISOtech
'frac12': chr(189), # vulgar fraction one half = fraction one half, U+00BD ISOnum
'frac14': chr(188), # vulgar fraction one quarter = fraction one quarter, U+00BC ISOnum
'frac34': chr(190), # vulgar fraction three quarters = fraction three quarters, U+00BE ISOnum
'frasl': '⁄', # fraction slash, U+2044 NEW
'gamma': 'γ', # greek small letter gamma, U+03B3 ISOgrk3
'ge': '≥', # greater-than or equal to, U+2265 ISOtech
'hArr': '⇔', # left right double arrow, U+21D4 ISOamsa
'harr': '↔', # left right arrow, U+2194 ISOamsa
'hearts': '♥', # black heart suit = valentine, U+2665 ISOpub
'hellip': '…', # horizontal ellipsis = three dot leader, U+2026 ISOpub
'iacute': chr(237), # latin small letter i with acute, U+00ED ISOlat1
'icirc': chr(238), # latin small letter i with circumflex, U+00EE ISOlat1
'iexcl': chr(161), # inverted exclamation mark, U+00A1 ISOnum
'igrave': chr(236), # latin small letter i with grave, U+00EC ISOlat1
'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': chr(191), # inverted question mark = turned question mark, U+00BF ISOnum
'isin': '∈', # element of, U+2208 ISOtech
'iuml': chr(239), # 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': chr(171), # 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
'macr': chr(175), # macron = spacing macron = overline = APL overbar, U+00AF ISOdia
'mdash': '—', # em dash, U+2014 ISOpub
'micro': chr(181), # micro sign, U+00B5 ISOnum
'middot': chr(183), # 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': chr(160), # 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': chr(172), # not sign, U+00AC ISOnum
'notin': '∉', # not an element of, U+2209 ISOtech
'nsub': '⊄', # not a subset of, U+2284 ISOamsn
'ntilde': chr(241), # latin small letter n with tilde, U+00F1 ISOlat1
'nu': 'ν', # greek small letter nu, U+03BD ISOgrk3
'oacute': chr(243), # latin small letter o with acute, U+00F3 ISOlat1
'ocirc': chr(244), # latin small letter o with circumflex, U+00F4 ISOlat1
'ograve': chr(242), # 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': chr(170), # feminine ordinal indicator, U+00AA ISOnum
'ordm': chr(186), # masculine ordinal indicator, U+00BA ISOnum
'oslash': chr(248), # latin small letter o with stroke, = latin small letter o slash, U+00F8 ISOlat1
'otilde': chr(245), # latin small letter o with tilde, U+00F5 ISOlat1
'otimes': '⊗', # circled times = vector product, U+2297 ISOamsb
'ouml': chr(246), # latin small letter o with diaeresis, U+00F6 ISOlat1
'para': chr(182), # 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': chr(177), # plus-minus sign = plus-or-minus sign, U+00B1 ISOnum
'pound': chr(163), # 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
'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': chr(187), # 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': chr(174), # 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
'sdot': '⋅', # dot operator, U+22C5 ISOamsb
'sect': chr(167), # section sign, U+00A7 ISOnum
'shy': chr(173), # 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': chr(185), # superscript one = superscript digit one, U+00B9 ISOnum
'sup2': chr(178), # superscript two = superscript digit two = squared, U+00B2 ISOnum
'sup3': chr(179), # superscript three = superscript digit three = cubed, U+00B3 ISOnum
'supe': '⊇', # superset of or equal to, U+2287 ISOtech
'szlig': chr(223), # 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': chr(254), # latin small letter thorn with, U+00FE ISOlat1
'times': chr(215), # multiplication sign, U+00D7 ISOnum
'trade': '™', # trade mark sign, U+2122 ISOnum
'uArr': '⇑', # upwards double arrow, U+21D1 ISOamsa
'uacute': chr(250), # latin small letter u with acute, U+00FA ISOlat1
'uarr': '↑', # upwards arrow, U+2191 ISOnum
'ucirc': chr(251), # latin small letter u with circumflex, U+00FB ISOlat1
'ugrave': chr(249), # latin small letter u with grave, U+00F9 ISOlat1
'uml': chr(168), # 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': chr(252), # 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': chr(253), # latin small letter y with acute, U+00FD ISOlat1
'yen': chr(165), # yen sign = yuan sign, U+00A5 ISOnum
'yuml': chr(255), # 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
}
--------------3B4AC9E96FE0666068F893B2--