📄 entities.lnx
字号:
/*# M.P.: entity to unicode table. I took this file from lynx.# lynx/WWW/Library/Implementation/entities.h*//* Entity Names to Unicode table** -----------------------------**** Whole entities[] thing (and much more) now present* in this kind of structure. The structured streams to which* the SGML modules sends its output could then easily have access* to both entity names and unicode values for each (special)* character. Probably the whole translation to display characters* should be done at that later stage (e.g. in HTML.c).* What's missing is a way for the later stage to return info* to SGML whether the entity could be displayed or not.* (like between SGML_character() and handle_entity() via FoundEntity.)* Well, trying to do that now.* Why keep two structures for entities? Backward compatibility..*/#ifndef ENTITIES_H#define ENTITIES_H 1#include <HTUtils.h>#include <SGML.h>/* UC_entity_info structure is defined in SGML.h. This has to be sorted alphabetically (case-sensitive), bear this in mind when you add some more entities.. *//*This table available from ftp://ftp.unicode.org/original comment follows:# Author: John Cowan <cowan@ccil.org># Date: 25 July 1997## The following table maps SGML character entities from various# public sets (namely, ISOamsa, ISOamsb, ISOamsc, ISOamsn, ISOamso,# ISOamsr, ISObox, ISOcyr1, ISOcyr2, ISOdia, ISOgrk1, ISOgrk2,# ISOgrk3, ISOgrk4, ISOlat1, ISOlat2, ISOnum, ISOpub, ISOtech,# HTMLspecial, HTMLsymbol) to corresponding Unicode characters.## The table has four tab-separated columns:# Column 1: SGML character entity name# Column 2: SGML public entity set# Column 3: Unicode 2.0 character code# Column 4: Unicode 2.0 character name (UPPER CASE)# Entries which don't have Unicode equivalents have "0x????"# in Column 3 and a lower case description (from the public entity# set DTD) in Column 4. The mapping is not reversible, because many# distinctions are unified away in Unicode, particularly between# mathematical symbols.## The table is sorted case-blind by SGML character entity name.## The contents of this table are drawn from various sources, and# are in the public domain.######################### We just sort it and move column 2 away (line too long, sorry; look at sgml.html in test/ directory for details). Also we add a few (obsolete) synonyms: "brkbar" for "brvbar" 0x00A6 "emdash" for "mdash" 0x2014 "endash" for "ndash" 0x2013 "hibar" for "macr" 0x00AF for exact compatibility with entities[] and previous bevavior. BTW, lots of synonyms found in this table, we shouldn't worry about...*/static CONST UC_entity_info unicode_entities[] = { {"AElig", 0x00C6}, /* LATIN CAPITAL LETTER AE */ {"Aacgr", 0x0386}, /* GREEK CAPITAL LETTER ALPHA WITH TONOS */ {"Aacute", 0x00C1}, /* LATIN CAPITAL LETTER A WITH ACUTE */ {"Abreve", 0x0102}, /* LATIN CAPITAL LETTER A WITH BREVE */ {"Acirc", 0x00C2}, /* LATIN CAPITAL LETTER A WITH CIRCUMFLEX */ {"Acy", 0x0410}, /* CYRILLIC CAPITAL LETTER A */ {"Agr", 0x0391}, /* GREEK CAPITAL LETTER ALPHA */ {"Agrave", 0x00C0}, /* LATIN CAPITAL LETTER A WITH GRAVE */ {"Alpha", 0x0391}, /* GREEK CAPITAL LETTER ALPHA */ {"Amacr", 0x0100}, /* LATIN CAPITAL LETTER A WITH MACRON */ {"Aogon", 0x0104}, /* LATIN CAPITAL LETTER A WITH OGONEK */ {"Aring", 0x00C5}, /* LATIN CAPITAL LETTER A WITH RING ABOVE */ {"Atilde", 0x00C3}, /* LATIN CAPITAL LETTER A WITH TILDE */ {"Auml", 0x00C4}, /* LATIN CAPITAL LETTER A WITH DIAERESIS */ {"Barwed", 0x2306}, /* PERSPECTIVE */ {"Bcy", 0x0411}, /* CYRILLIC CAPITAL LETTER BE */ {"Beta", 0x0392}, /* GREEK CAPITAL LETTER BETA */ {"Bgr", 0x0392}, /* GREEK CAPITAL LETTER BETA */ {"CHcy", 0x0427}, /* CYRILLIC CAPITAL LETTER CHE */ {"Cacute", 0x0106}, /* LATIN CAPITAL LETTER C WITH ACUTE */ {"Cap", 0x22D2}, /* DOUBLE INTERSECTION */ {"Ccaron", 0x010C}, /* LATIN CAPITAL LETTER C WITH CARON */ {"Ccedil", 0x00C7}, /* LATIN CAPITAL LETTER C WITH CEDILLA */ {"Ccirc", 0x0108}, /* LATIN CAPITAL LETTER C WITH CIRCUMFLEX */ {"Cdot", 0x010A}, /* LATIN CAPITAL LETTER C WITH DOT ABOVE */ {"Chi", 0x03A7}, /* GREEK CAPITAL LETTER CHI */ {"Cup", 0x22D3}, /* DOUBLE UNION */ {"DJcy", 0x0402}, /* CYRILLIC CAPITAL LETTER DJE */ {"DScy", 0x0405}, /* CYRILLIC CAPITAL LETTER DZE */ {"DZcy", 0x040F}, /* CYRILLIC CAPITAL LETTER DZHE */ {"Dagger", 0x2021}, /* DOUBLE DAGGER */ {"Dcaron", 0x010E}, /* LATIN CAPITAL LETTER D WITH CARON */ {"Dcy", 0x0414}, /* CYRILLIC CAPITAL LETTER DE */ {"Delta", 0x0394}, /* GREEK CAPITAL LETTER DELTA */ {"Dgr", 0x0394}, /* GREEK CAPITAL LETTER DELTA */ {"Dot", 0x00A8}, /* DIAERESIS */ {"DotDot", 0x20DC}, /* COMBINING FOUR DOTS ABOVE */ {"Dstrok", 0x0110}, /* LATIN CAPITAL LETTER D WITH STROKE */ {"EEacgr", 0x0389}, /* GREEK CAPITAL LETTER ETA WITH TONOS */ {"EEgr", 0x0397}, /* GREEK CAPITAL LETTER ETA */ {"ENG", 0x014A}, /* LATIN CAPITAL LETTER ENG */ {"ETH", 0x00D0}, /* LATIN CAPITAL LETTER ETH */ {"Eacgr", 0x0388}, /* GREEK CAPITAL LETTER EPSILON WITH TONOS */ {"Eacute", 0x00C9}, /* LATIN CAPITAL LETTER E WITH ACUTE */ {"Ecaron", 0x011A}, /* LATIN CAPITAL LETTER E WITH CARON */ {"Ecirc", 0x00CA}, /* LATIN CAPITAL LETTER E WITH CIRCUMFLEX */ {"Ecy", 0x042D}, /* CYRILLIC CAPITAL LETTER E */ {"Edot", 0x0116}, /* LATIN CAPITAL LETTER E WITH DOT ABOVE */ {"Egr", 0x0395}, /* GREEK CAPITAL LETTER EPSILON */ {"Egrave", 0x00C8}, /* LATIN CAPITAL LETTER E WITH GRAVE */ {"Emacr", 0x0112}, /* LATIN CAPITAL LETTER E WITH MACRON */ {"Eogon", 0x0118}, /* LATIN CAPITAL LETTER E WITH OGONEK */ {"Epsilon", 0x0395}, /* GREEK CAPITAL LETTER EPSILON */ {"Eta", 0x0397}, /* GREEK CAPITAL LETTER ETA */ {"Euml", 0x00CB}, /* LATIN CAPITAL LETTER E WITH DIAERESIS */ {"Euro", 0x20AC}, /* EURO SYMBOL */ {"Fcy", 0x0424}, /* CYRILLIC CAPITAL LETTER EF */ {"GJcy", 0x0403}, /* CYRILLIC CAPITAL LETTER GJE */ {"Gamma", 0x0393}, /* GREEK CAPITAL LETTER GAMMA */ {"Gbreve", 0x011E}, /* LATIN CAPITAL LETTER G WITH BREVE */ {"Gcedil", 0x0122}, /* LATIN CAPITAL LETTER G WITH CEDILLA */ {"Gcirc", 0x011C}, /* LATIN CAPITAL LETTER G WITH CIRCUMFLEX */ {"Gcy", 0x0413}, /* CYRILLIC CAPITAL LETTER GHE */ {"Gdot", 0x0120}, /* LATIN CAPITAL LETTER G WITH DOT ABOVE */ {"Gg", 0x22D9}, /* VERY MUCH GREATER-THAN */ {"Ggr", 0x0393}, /* GREEK CAPITAL LETTER GAMMA */ {"Gt", 0x226B}, /* MUCH GREATER-THAN */ {"HARDcy", 0x042A}, /* CYRILLIC CAPITAL LETTER HARD SIGN */ {"Hcirc", 0x0124}, /* LATIN CAPITAL LETTER H WITH CIRCUMFLEX */ {"Hstrok", 0x0126}, /* LATIN CAPITAL LETTER H WITH STROKE */ {"IEcy", 0x0415}, /* CYRILLIC CAPITAL LETTER IE */ {"IJlig", 0x0132}, /* LATIN CAPITAL LIGATURE IJ */ {"IOcy", 0x0401}, /* CYRILLIC CAPITAL LETTER IO */ {"Iacgr", 0x038A}, /* GREEK CAPITAL LETTER IOTA WITH TONOS */ {"Iacute", 0x00CD}, /* LATIN CAPITAL LETTER I WITH ACUTE */ {"Icirc", 0x00CE}, /* LATIN CAPITAL LETTER I WITH CIRCUMFLEX */ {"Icy", 0x0418}, /* CYRILLIC CAPITAL LETTER I */ {"Idigr", 0x03AA}, /* GREEK CAPITAL LETTER IOTA WITH DIALYTIKA */ {"Idot", 0x0130}, /* LATIN CAPITAL LETTER I WITH DOT ABOVE */ {"Igr", 0x0399}, /* GREEK CAPITAL LETTER IOTA */ {"Igrave", 0x00CC}, /* LATIN CAPITAL LETTER I WITH GRAVE */ {"Imacr", 0x012A}, /* LATIN CAPITAL LETTER I WITH MACRON */ {"Iogon", 0x012E}, /* LATIN CAPITAL LETTER I WITH OGONEK */ {"Iota", 0x0399}, /* GREEK CAPITAL LETTER IOTA */ {"Itilde", 0x0128}, /* LATIN CAPITAL LETTER I WITH TILDE */ {"Iukcy", 0x0406}, /* CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN*/ {"Iuml", 0x00CF}, /* LATIN CAPITAL LETTER I WITH DIAERESIS */ {"Jcirc", 0x0134}, /* LATIN CAPITAL LETTER J WITH CIRCUMFLEX */ {"Jcy", 0x0419}, /* CYRILLIC CAPITAL LETTER SHORT I */ {"Jsercy", 0x0408}, /* CYRILLIC CAPITAL LETTER JE */ {"Jukcy", 0x0404}, /* CYRILLIC CAPITAL LETTER UKRAINIAN IE */ {"KHcy", 0x0425}, /* CYRILLIC CAPITAL LETTER HA */ {"KHgr", 0x03A7}, /* GREEK CAPITAL LETTER CHI */ {"KJcy", 0x040C}, /* CYRILLIC CAPITAL LETTER KJE */ {"Kappa", 0x039A}, /* GREEK CAPITAL LETTER KAPPA */ {"Kcedil", 0x0136}, /* LATIN CAPITAL LETTER K WITH CEDILLA */ {"Kcy", 0x041A}, /* CYRILLIC CAPITAL LETTER KA */ {"Kgr", 0x039A}, /* GREEK CAPITAL LETTER KAPPA */ {"LJcy", 0x0409}, /* CYRILLIC CAPITAL LETTER LJE */ {"Lacute", 0x0139}, /* LATIN CAPITAL LETTER L WITH ACUTE */ {"Lambda", 0x039B}, /* GREEK CAPITAL LETTER LAMDA */ {"Larr", 0x219E}, /* LEFTWARDS TWO HEADED ARROW */ {"Lcaron", 0x013D}, /* LATIN CAPITAL LETTER L WITH CARON */ {"Lcedil", 0x013B}, /* LATIN CAPITAL LETTER L WITH CEDILLA */ {"Lcy", 0x041B}, /* CYRILLIC CAPITAL LETTER EL */ {"Lgr", 0x039B}, /* GREEK CAPITAL LETTER LAMDA */ {"Ll", 0x22D8}, /* VERY MUCH LESS-THAN */ {"Lmidot", 0x013F}, /* LATIN CAPITAL LETTER L WITH MIDDLE DOT */ {"Lstrok", 0x0141}, /* LATIN CAPITAL LETTER L WITH STROKE */ {"Lt", 0x226A}, /* MUCH LESS-THAN */ {"Mcy", 0x041C}, /* CYRILLIC CAPITAL LETTER EM */ {"Mgr", 0x039C}, /* GREEK CAPITAL LETTER MU */ {"Mu", 0x039C}, /* GREEK CAPITAL LETTER MU */ {"NJcy", 0x040A}, /* CYRILLIC CAPITAL LETTER NJE */ {"Nacute", 0x0143}, /* LATIN CAPITAL LETTER N WITH ACUTE */ {"Ncaron", 0x0147}, /* LATIN CAPITAL LETTER N WITH CARON */ {"Ncedil", 0x0145}, /* LATIN CAPITAL LETTER N WITH CEDILLA */ {"Ncy", 0x041D}, /* CYRILLIC CAPITAL LETTER EN */ {"Ngr", 0x039D}, /* GREEK CAPITAL LETTER NU */ {"Ntilde", 0x00D1}, /* LATIN CAPITAL LETTER N WITH TILDE */ {"Nu", 0x039D}, /* GREEK CAPITAL LETTER NU */ {"OElig", 0x0152}, /* LATIN CAPITAL LIGATURE OE */ {"OHacgr", 0x038F}, /* GREEK CAPITAL LETTER OMEGA WITH TONOS */ {"OHgr", 0x03A9}, /* GREEK CAPITAL LETTER OMEGA */ {"Oacgr", 0x038C}, /* GREEK CAPITAL LETTER OMICRON WITH TONOS */ {"Oacute", 0x00D3}, /* LATIN CAPITAL LETTER O WITH ACUTE */ {"Ocirc", 0x00D4}, /* LATIN CAPITAL LETTER O WITH CIRCUMFLEX */ {"Ocy", 0x041E}, /* CYRILLIC CAPITAL LETTER O */ {"Odblac", 0x0150}, /* LATIN CAPITAL LETTER O WITH DOUBLE ACUTE */ {"Ogr", 0x039F}, /* GREEK CAPITAL LETTER OMICRON */ {"Ograve", 0x00D2}, /* LATIN CAPITAL LETTER O WITH GRAVE */ {"Omacr", 0x014C}, /* LATIN CAPITAL LETTER O WITH MACRON */ {"Omega", 0x03A9}, /* GREEK CAPITAL LETTER OMEGA */ {"Omicron", 0x039F}, /* GREEK CAPITAL LETTER OMICRON */ {"Oslash", 0x00D8}, /* LATIN CAPITAL LETTER O WITH STROKE */ {"Otilde", 0x00D5}, /* LATIN CAPITAL LETTER O WITH TILDE */ {"Ouml", 0x00D6}, /* LATIN CAPITAL LETTER O WITH DIAERESIS */ {"PHgr", 0x03A6}, /* GREEK CAPITAL LETTER PHI */ {"PSgr", 0x03A8}, /* GREEK CAPITAL LETTER PSI */ {"Pcy", 0x041F}, /* CYRILLIC CAPITAL LETTER PE */ {"Pgr", 0x03A0}, /* GREEK CAPITAL LETTER PI */ {"Phi", 0x03A6}, /* GREEK CAPITAL LETTER PHI */ {"Pi", 0x03A0}, /* GREEK CAPITAL LETTER PI */ {"Prime", 0x2033}, /* DOUBLE PRIME */
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -