From a392e545be782be90ff8df5eaaff12e879fe6fa1 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Thu, 5 Jun 2008 16:09:50 -0700 Subject: [PATCH] Add support for creating codepage/Unicode mapping tables Add support for creating codepage/Unicode mapping tables; this is a step toward VFAT long filename support. --- Makefile | 2 +- codepage/Makefile | 17 +++ codepage/UnicodeData | 301 ++++++++++++++++++++++++++++++++++++++++++++++++++ codepage/cp437.txt | 273 +++++++++++++++++++++++++++++++++++++++++++++ codepage/cp850.txt | 273 +++++++++++++++++++++++++++++++++++++++++++++ codepage/cp865.txt | 274 +++++++++++++++++++++++++++++++++++++++++++++ codepage/cptable.pl | 58 ++++++++++ codepage/gensubset.pl | 38 +++++++ 8 files changed, 1235 insertions(+), 1 deletion(-) create mode 100644 codepage/Makefile create mode 100644 codepage/UnicodeData create mode 100644 codepage/cp437.txt create mode 100644 codepage/cp850.txt create mode 100644 codepage/cp865.txt create mode 100755 codepage/cptable.pl create mode 100755 codepage/gensubset.pl diff --git a/Makefile b/Makefile index e436489..fa49c2c 100644 --- a/Makefile +++ b/Makefile @@ -40,7 +40,7 @@ BOBJECTS = $(BTARGET) \ # BESUBDIRS and IESUBDIRS are "early", i.e. before the root; BSUBDIRS # and ISUBDIRS are "late", after the root. BESUBDIRS = -BSUBDIRS = core memdisk mbr memdump gpxe dos win32 +BSUBDIRS = codepage core memdisk mbr memdump gpxe dos win32 ITARGET = IOBJECTS = $(ITARGET) dos/copybs.com utils/gethostip utils/mkdiskimage \ mtools/syslinux linux/syslinux extlinux/extlinux diff --git a/codepage/Makefile b/codepage/Makefile new file mode 100644 index 0000000..70e2cf0 --- /dev/null +++ b/codepage/Makefile @@ -0,0 +1,17 @@ +PERL = perl +CPSRC = $(wildcard *.txt) +GENFILES = $(patsubst %.txt,%.bin,$(CPSRC)) + +.SUFFIXES: .txt .bin + +all: $(GENFILES) + +tidy: + +clean: + rm -f $(GENFILES) + +dist: tidy + +%.bin: %.txt cptable.pl UnicodeData + $(PERL) cptable.pl UnicodeData $< $@ diff --git a/codepage/UnicodeData b/codepage/UnicodeData new file mode 100644 index 0000000..3eb8eb7 --- /dev/null +++ b/codepage/UnicodeData @@ -0,0 +1,301 @@ +0000;;Cc;0;BN;;;;;N;NULL;;;; +0001;;Cc;0;BN;;;;;N;START OF HEADING;;;; +0002;;Cc;0;BN;;;;;N;START OF TEXT;;;; +0003;;Cc;0;BN;;;;;N;END OF TEXT;;;; +0004;;Cc;0;BN;;;;;N;END OF TRANSMISSION;;;; +0005;;Cc;0;BN;;;;;N;ENQUIRY;;;; +0006;;Cc;0;BN;;;;;N;ACKNOWLEDGE;;;; +0007;;Cc;0;BN;;;;;N;BELL;;;; +0008;;Cc;0;BN;;;;;N;BACKSPACE;;;; +0009;;Cc;0;S;;;;;N;CHARACTER TABULATION;;;; +000A;;Cc;0;B;;;;;N;LINE FEED (LF);;;; +000B;;Cc;0;S;;;;;N;LINE TABULATION;;;; +000C;;Cc;0;WS;;;;;N;FORM FEED (FF);;;; +000D;;Cc;0;B;;;;;N;CARRIAGE RETURN (CR);;;; +000E;;Cc;0;BN;;;;;N;SHIFT OUT;;;; +000F;;Cc;0;BN;;;;;N;SHIFT IN;;;; +0010;;Cc;0;BN;;;;;N;DATA LINK ESCAPE;;;; +0011;;Cc;0;BN;;;;;N;DEVICE CONTROL ONE;;;; +0012;;Cc;0;BN;;;;;N;DEVICE CONTROL TWO;;;; +0013;;Cc;0;BN;;;;;N;DEVICE CONTROL THREE;;;; +0014;;Cc;0;BN;;;;;N;DEVICE CONTROL FOUR;;;; +0015;;Cc;0;BN;;;;;N;NEGATIVE ACKNOWLEDGE;;;; +0016;;Cc;0;BN;;;;;N;SYNCHRONOUS IDLE;;;; +0017;;Cc;0;BN;;;;;N;END OF TRANSMISSION BLOCK;;;; +0018;;Cc;0;BN;;;;;N;CANCEL;;;; +0019;;Cc;0;BN;;;;;N;END OF MEDIUM;;;; +001A;;Cc;0;BN;;;;;N;SUBSTITUTE;;;; +001B;;Cc;0;BN;;;;;N;ESCAPE;;;; +001C;;Cc;0;B;;;;;N;INFORMATION SEPARATOR FOUR;;;; +001D;;Cc;0;B;;;;;N;INFORMATION SEPARATOR THREE;;;; +001E;;Cc;0;B;;;;;N;INFORMATION SEPARATOR TWO;;;; +001F;;Cc;0;S;;;;;N;INFORMATION SEPARATOR ONE;;;; +0020;SPACE;Zs;0;WS;;;;;N;;;;; +0021;EXCLAMATION MARK;Po;0;ON;;;;;N;;;;; +0022;QUOTATION MARK;Po;0;ON;;;;;N;;;;; +0023;NUMBER SIGN;Po;0;ET;;;;;N;;;;; +0024;DOLLAR SIGN;Sc;0;ET;;;;;N;;;;; +0025;PERCENT SIGN;Po;0;ET;;;;;N;;;;; +0026;AMPERSAND;Po;0;ON;;;;;N;;;;; +0027;APOSTROPHE;Po;0;ON;;;;;N;APOSTROPHE-QUOTE;;;; +0028;LEFT PARENTHESIS;Ps;0;ON;;;;;Y;OPENING PARENTHESIS;;;; +0029;RIGHT PARENTHESIS;Pe;0;ON;;;;;Y;CLOSING PARENTHESIS;;;; +002A;ASTERISK;Po;0;ON;;;;;N;;;;; +002B;PLUS SIGN;Sm;0;ES;;;;;N;;;;; +002C;COMMA;Po;0;CS;;;;;N;;;;; +002D;HYPHEN-MINUS;Pd;0;ES;;;;;N;;;;; +002E;FULL STOP;Po;0;CS;;;;;N;PERIOD;;;; +002F;SOLIDUS;Po;0;CS;;;;;N;SLASH;;;; +0030;DIGIT ZERO;Nd;0;EN;;0;0;0;N;;;;; +0031;DIGIT ONE;Nd;0;EN;;1;1;1;N;;;;; +0032;DIGIT TWO;Nd;0;EN;;2;2;2;N;;;;; +0033;DIGIT THREE;Nd;0;EN;;3;3;3;N;;;;; +0034;DIGIT FOUR;Nd;0;EN;;4;4;4;N;;;;; +0035;DIGIT FIVE;Nd;0;EN;;5;5;5;N;;;;; +0036;DIGIT SIX;Nd;0;EN;;6;6;6;N;;;;; +0037;DIGIT SEVEN;Nd;0;EN;;7;7;7;N;;;;; +0038;DIGIT EIGHT;Nd;0;EN;;8;8;8;N;;;;; +0039;DIGIT NINE;Nd;0;EN;;9;9;9;N;;;;; +003A;COLON;Po;0;CS;;;;;N;;;;; +003B;SEMICOLON;Po;0;ON;;;;;N;;;;; +003C;LESS-THAN SIGN;Sm;0;ON;;;;;Y;;;;; +003D;EQUALS SIGN;Sm;0;ON;;;;;N;;;;; +003E;GREATER-THAN SIGN;Sm;0;ON;;;;;Y;;;;; +003F;QUESTION MARK;Po;0;ON;;;;;N;;;;; +0040;COMMERCIAL AT;Po;0;ON;;;;;N;;;;; +0041;LATIN CAPITAL LETTER A;Lu;0;L;;;;;N;;;;0061; +0042;LATIN CAPITAL LETTER B;Lu;0;L;;;;;N;;;;0062; +0043;LATIN CAPITAL LETTER C;Lu;0;L;;;;;N;;;;0063; +0044;LATIN CAPITAL LETTER D;Lu;0;L;;;;;N;;;;0064; +0045;LATIN CAPITAL LETTER E;Lu;0;L;;;;;N;;;;0065; +0046;LATIN CAPITAL LETTER F;Lu;0;L;;;;;N;;;;0066; +0047;LATIN CAPITAL LETTER G;Lu;0;L;;;;;N;;;;0067; +0048;LATIN CAPITAL LETTER H;Lu;0;L;;;;;N;;;;0068; +0049;LATIN CAPITAL LETTER I;Lu;0;L;;;;;N;;;;0069; +004A;LATIN CAPITAL LETTER J;Lu;0;L;;;;;N;;;;006A; +004B;LATIN CAPITAL LETTER K;Lu;0;L;;;;;N;;;;006B; +004C;LATIN CAPITAL LETTER L;Lu;0;L;;;;;N;;;;006C; +004D;LATIN CAPITAL LETTER M;Lu;0;L;;;;;N;;;;006D; +004E;LATIN CAPITAL LETTER N;Lu;0;L;;;;;N;;;;006E; +004F;LATIN CAPITAL LETTER O;Lu;0;L;;;;;N;;;;006F; +0050;LATIN CAPITAL LETTER P;Lu;0;L;;;;;N;;;;0070; +0051;LATIN CAPITAL LETTER Q;Lu;0;L;;;;;N;;;;0071; +0052;LATIN CAPITAL LETTER R;Lu;0;L;;;;;N;;;;0072; +0053;LATIN CAPITAL LETTER S;Lu;0;L;;;;;N;;;;0073; +0054;LATIN CAPITAL LETTER T;Lu;0;L;;;;;N;;;;0074; +0055;LATIN CAPITAL LETTER U;Lu;0;L;;;;;N;;;;0075; +0056;LATIN CAPITAL LETTER V;Lu;0;L;;;;;N;;;;0076; +0057;LATIN CAPITAL LETTER W;Lu;0;L;;;;;N;;;;0077; +0058;LATIN CAPITAL LETTER X;Lu;0;L;;;;;N;;;;0078; +0059;LATIN CAPITAL LETTER Y;Lu;0;L;;;;;N;;;;0079; +005A;LATIN CAPITAL LETTER Z;Lu;0;L;;;;;N;;;;007A; +005B;LEFT SQUARE BRACKET;Ps;0;ON;;;;;Y;OPENING SQUARE BRACKET;;;; +005C;REVERSE SOLIDUS;Po;0;ON;;;;;N;BACKSLASH;;;; +005D;RIGHT SQUARE BRACKET;Pe;0;ON;;;;;Y;CLOSING SQUARE BRACKET;;;; +005E;CIRCUMFLEX ACCENT;Sk;0;ON;;;;;N;SPACING CIRCUMFLEX;;;; +005F;LOW LINE;Pc;0;ON;;;;;N;SPACING UNDERSCORE;;;; +0060;GRAVE ACCENT;Sk;0;ON;;;;;N;SPACING GRAVE;;;; +0061;LATIN SMALL LETTER A;Ll;0;L;;;;;N;;;0041;;0041 +0062;LATIN SMALL LETTER B;Ll;0;L;;;;;N;;;0042;;0042 +0063;LATIN SMALL LETTER C;Ll;0;L;;;;;N;;;0043;;0043 +0064;LATIN SMALL LETTER D;Ll;0;L;;;;;N;;;0044;;0044 +0065;LATIN SMALL LETTER E;Ll;0;L;;;;;N;;;0045;;0045 +0066;LATIN SMALL LETTER F;Ll;0;L;;;;;N;;;0046;;0046 +0067;LATIN SMALL LETTER G;Ll;0;L;;;;;N;;;0047;;0047 +0068;LATIN SMALL LETTER H;Ll;0;L;;;;;N;;;0048;;0048 +0069;LATIN SMALL LETTER I;Ll;0;L;;;;;N;;;0049;;0049 +006A;LATIN SMALL LETTER J;Ll;0;L;;;;;N;;;004A;;004A +006B;LATIN SMALL LETTER K;Ll;0;L;;;;;N;;;004B;;004B +006C;LATIN SMALL LETTER L;Ll;0;L;;;;;N;;;004C;;004C +006D;LATIN SMALL LETTER M;Ll;0;L;;;;;N;;;004D;;004D +006E;LATIN SMALL LETTER N;Ll;0;L;;;;;N;;;004E;;004E +006F;LATIN SMALL LETTER O;Ll;0;L;;;;;N;;;004F;;004F +0070;LATIN SMALL LETTER P;Ll;0;L;;;;;N;;;0050;;0050 +0071;LATIN SMALL LETTER Q;Ll;0;L;;;;;N;;;0051;;0051 +0072;LATIN SMALL LETTER R;Ll;0;L;;;;;N;;;0052;;0052 +0073;LATIN SMALL LETTER S;Ll;0;L;;;;;N;;;0053;;0053 +0074;LATIN SMALL LETTER T;Ll;0;L;;;;;N;;;0054;;0054 +0075;LATIN SMALL LETTER U;Ll;0;L;;;;;N;;;0055;;0055 +0076;LATIN SMALL LETTER V;Ll;0;L;;;;;N;;;0056;;0056 +0077;LATIN SMALL LETTER W;Ll;0;L;;;;;N;;;0057;;0057 +0078;LATIN SMALL LETTER X;Ll;0;L;;;;;N;;;0058;;0058 +0079;LATIN SMALL LETTER Y;Ll;0;L;;;;;N;;;0059;;0059 +007A;LATIN SMALL LETTER Z;Ll;0;L;;;;;N;;;005A;;005A +007B;LEFT CURLY BRACKET;Ps;0;ON;;;;;Y;OPENING CURLY BRACKET;;;; +007C;VERTICAL LINE;Sm;0;ON;;;;;N;VERTICAL BAR;;;; +007D;RIGHT CURLY BRACKET;Pe;0;ON;;;;;Y;CLOSING CURLY BRACKET;;;; +007E;TILDE;Sm;0;ON;;;;;N;;;;; +007F;;Cc;0;BN;;;;;N;DELETE;;;; +00A0;NO-BREAK SPACE;Zs;0;CS; 0020;;;;N;NON-BREAKING SPACE;;;; +00A1;INVERTED EXCLAMATION MARK;Po;0;ON;;;;;N;;;;; +00A2;CENT SIGN;Sc;0;ET;;;;;N;;;;; +00A3;POUND SIGN;Sc;0;ET;;;;;N;;;;; +00A4;CURRENCY SIGN;Sc;0;ET;;;;;N;;;;; +00A5;YEN SIGN;Sc;0;ET;;;;;N;;;;; +00A6;BROKEN BAR;So;0;ON;;;;;N;BROKEN VERTICAL BAR;;;; +00A7;SECTION SIGN;So;0;ON;;;;;N;;;;; +00A8;DIAERESIS;Sk;0;ON; 0020 0308;;;;N;SPACING DIAERESIS;;;; +00A9;COPYRIGHT SIGN;So;0;ON;;;;;N;;;;; +00AA;FEMININE ORDINAL INDICATOR;Ll;0;L; 0061;;;;N;;;;; +00AB;LEFT-POINTING DOUBLE ANGLE QUOTATION MARK;Pi;0;ON;;;;;Y;LEFT POINTING GUILLEMET;*;;; +00AC;NOT SIGN;Sm;0;ON;;;;;N;;;;; +00AD;SOFT HYPHEN;Cf;0;BN;;;;;N;;;;; +00AE;REGISTERED SIGN;So;0;ON;;;;;N;REGISTERED TRADE MARK SIGN;;;; +00AF;MACRON;Sk;0;ON; 0020 0304;;;;N;SPACING MACRON;;;; +00B0;DEGREE SIGN;So;0;ET;;;;;N;;;;; +00B1;PLUS-MINUS SIGN;Sm;0;ET;;;;;N;PLUS-OR-MINUS SIGN;;;; +00B2;SUPERSCRIPT TWO;No;0;EN; 0032;;2;2;N;SUPERSCRIPT DIGIT TWO;;;; +00B3;SUPERSCRIPT THREE;No;0;EN; 0033;;3;3;N;SUPERSCRIPT DIGIT THREE;;;; +00B4;ACUTE ACCENT;Sk;0;ON; 0020 0301;;;;N;SPACING ACUTE;;;; +00B5;MICRO SIGN;Ll;0;L; 03BC;;;;N;;;039C;;039C +00B6;PILCROW SIGN;So;0;ON;;;;;N;PARAGRAPH SIGN;;;; +00B7;MIDDLE DOT;Po;0;ON;;;;;N;;;;; +00B8;CEDILLA;Sk;0;ON; 0020 0327;;;;N;SPACING CEDILLA;;;; +00B9;SUPERSCRIPT ONE;No;0;EN; 0031;;1;1;N;SUPERSCRIPT DIGIT ONE;;;; +00BA;MASCULINE ORDINAL INDICATOR;Ll;0;L; 006F;;;;N;;;;; +00BB;RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK;Pf;0;ON;;;;;Y;RIGHT POINTING GUILLEMET;*;;; +00BC;VULGAR FRACTION ONE QUARTER;No;0;ON; 0031 2044 0034;;;1/4;N;FRACTION ONE QUARTER;;;; +00BD;VULGAR FRACTION ONE HALF;No;0;ON; 0031 2044 0032;;;1/2;N;FRACTION ONE HALF;;;; +00BE;VULGAR FRACTION THREE QUARTERS;No;0;ON; 0033 2044 0034;;;3/4;N;FRACTION THREE QUARTERS;;;; +00BF;INVERTED QUESTION MARK;Po;0;ON;;;;;N;;;;; +00C0;LATIN CAPITAL LETTER A WITH GRAVE;Lu;0;L;0041 0300;;;;N;LATIN CAPITAL LETTER A GRAVE;;;00E0; +00C1;LATIN CAPITAL LETTER A WITH ACUTE;Lu;0;L;0041 0301;;;;N;LATIN CAPITAL LETTER A ACUTE;;;00E1; +00C2;LATIN CAPITAL LETTER A WITH CIRCUMFLEX;Lu;0;L;0041 0302;;;;N;LATIN CAPITAL LETTER A CIRCUMFLEX;;;00E2; +00C3;LATIN CAPITAL LETTER A WITH TILDE;Lu;0;L;0041 0303;;;;N;LATIN CAPITAL LETTER A TILDE;;;00E3; +00C4;LATIN CAPITAL LETTER A WITH DIAERESIS;Lu;0;L;0041 0308;;;;N;LATIN CAPITAL LETTER A DIAERESIS;;;00E4; +00C5;LATIN CAPITAL LETTER A WITH RING ABOVE;Lu;0;L;0041 030A;;;;N;LATIN CAPITAL LETTER A RING;;;00E5; +00C6;LATIN CAPITAL LETTER AE;Lu;0;L;;;;;N;LATIN CAPITAL LETTER A E;ash *;;00E6; +00C7;LATIN CAPITAL LETTER C WITH CEDILLA;Lu;0;L;0043 0327;;;;N;LATIN CAPITAL LETTER C CEDILLA;;;00E7; +00C8;LATIN CAPITAL LETTER E WITH GRAVE;Lu;0;L;0045 0300;;;;N;LATIN CAPITAL LETTER E GRAVE;;;00E8; +00C9;LATIN CAPITAL LETTER E WITH ACUTE;Lu;0;L;0045 0301;;;;N;LATIN CAPITAL LETTER E ACUTE;;;00E9; +00CA;LATIN CAPITAL LETTER E WITH CIRCUMFLEX;Lu;0;L;0045 0302;;;;N;LATIN CAPITAL LETTER E CIRCUMFLEX;;;00EA; +00CB;LATIN CAPITAL LETTER E WITH DIAERESIS;Lu;0;L;0045 0308;;;;N;LATIN CAPITAL LETTER E DIAERESIS;;;00EB; +00CC;LATIN CAPITAL LETTER I WITH GRAVE;Lu;0;L;0049 0300;;;;N;LATIN CAPITAL LETTER I GRAVE;;;00EC; +00CD;LATIN CAPITAL LETTER I WITH ACUTE;Lu;0;L;0049 0301;;;;N;LATIN CAPITAL LETTER I ACUTE;;;00ED; +00CE;LATIN CAPITAL LETTER I WITH CIRCUMFLEX;Lu;0;L;0049 0302;;;;N;LATIN CAPITAL LETTER I CIRCUMFLEX;;;00EE; +00CF;LATIN CAPITAL LETTER I WITH DIAERESIS;Lu;0;L;0049 0308;;;;N;LATIN CAPITAL LETTER I DIAERESIS;;;00EF; +00D0;LATIN CAPITAL LETTER ETH;Lu;0;L;;;;;N;;Icelandic;;00F0; +00D1;LATIN CAPITAL LETTER N WITH TILDE;Lu;0;L;004E 0303;;;;N;LATIN CAPITAL LETTER N TILDE;;;00F1; +00D2;LATIN CAPITAL LETTER O WITH GRAVE;Lu;0;L;004F 0300;;;;N;LATIN CAPITAL LETTER O GRAVE;;;00F2; +00D3;LATIN CAPITAL LETTER O WITH ACUTE;Lu;0;L;004F 0301;;;;N;LATIN CAPITAL LETTER O ACUTE;;;00F3; +00D4;LATIN CAPITAL LETTER O WITH CIRCUMFLEX;Lu;0;L;004F 0302;;;;N;LATIN CAPITAL LETTER O CIRCUMFLEX;;;00F4; +00D5;LATIN CAPITAL LETTER O WITH TILDE;Lu;0;L;004F 0303;;;;N;LATIN CAPITAL LETTER O TILDE;;;00F5; +00D6;LATIN CAPITAL LETTER O WITH DIAERESIS;Lu;0;L;004F 0308;;;;N;LATIN CAPITAL LETTER O DIAERESIS;;;00F6; +00D7;MULTIPLICATION SIGN;Sm;0;ON;;;;;N;;;;; +00D8;LATIN CAPITAL LETTER O WITH STROKE;Lu;0;L;;;;;N;LATIN CAPITAL LETTER O SLASH;;;00F8; +00D9;LATIN CAPITAL LETTER U WITH GRAVE;Lu;0;L;0055 0300;;;;N;LATIN CAPITAL LETTER U GRAVE;;;00F9; +00DA;LATIN CAPITAL LETTER U WITH ACUTE;Lu;0;L;0055 0301;;;;N;LATIN CAPITAL LETTER U ACUTE;;;00FA; +00DB;LATIN CAPITAL LETTER U WITH CIRCUMFLEX;Lu;0;L;0055 0302;;;;N;LATIN CAPITAL LETTER U CIRCUMFLEX;;;00FB; +00DC;LATIN CAPITAL LETTER U WITH DIAERESIS;Lu;0;L;0055 0308;;;;N;LATIN CAPITAL LETTER U DIAERESIS;;;00FC; +00DD;LATIN CAPITAL LETTER Y WITH ACUTE;Lu;0;L;0059 0301;;;;N;LATIN CAPITAL LETTER Y ACUTE;;;00FD; +00DE;LATIN CAPITAL LETTER THORN;Lu;0;L;;;;;N;;Icelandic;;00FE; +00DF;LATIN SMALL LETTER SHARP S;Ll;0;L;;;;;N;;German;;; +00E0;LATIN SMALL LETTER A WITH GRAVE;Ll;0;L;0061 0300;;;;N;LATIN SMALL LETTER A GRAVE;;00C0;;00C0 +00E1;LATIN SMALL LETTER A WITH ACUTE;Ll;0;L;0061 0301;;;;N;LATIN SMALL LETTER A ACUTE;;00C1;;00C1 +00E2;LATIN SMALL LETTER A WITH CIRCUMFLEX;Ll;0;L;0061 0302;;;;N;LATIN SMALL LETTER A CIRCUMFLEX;;00C2;;00C2 +00E3;LATIN SMALL LETTER A WITH TILDE;Ll;0;L;0061 0303;;;;N;LATIN SMALL LETTER A TILDE;;00C3;;00C3 +00E4;LATIN SMALL LETTER A WITH DIAERESIS;Ll;0;L;0061 0308;;;;N;LATIN SMALL LETTER A DIAERESIS;;00C4;;00C4 +00E5;LATIN SMALL LETTER A WITH RING ABOVE;Ll;0;L;0061 030A;;;;N;LATIN SMALL LETTER A RING;;00C5;;00C5 +00E6;LATIN SMALL LETTER AE;Ll;0;L;;;;;N;LATIN SMALL LETTER A E;ash *;00C6;;00C6 +00E7;LATIN SMALL LETTER C WITH CEDILLA;Ll;0;L;0063 0327;;;;N;LATIN SMALL LETTER C CEDILLA;;00C7;;00C7 +00E8;LATIN SMALL LETTER E WITH GRAVE;Ll;0;L;0065 0300;;;;N;LATIN SMALL LETTER E GRAVE;;00C8;;00C8 +00E9;LATIN SMALL LETTER E WITH ACUTE;Ll;0;L;0065 0301;;;;N;LATIN SMALL LETTER E ACUTE;;00C9;;00C9 +00EA;LATIN SMALL LETTER E WITH CIRCUMFLEX;Ll;0;L;0065 0302;;;;N;LATIN SMALL LETTER E CIRCUMFLEX;;00CA;;00CA +00EB;LATIN SMALL LETTER E WITH DIAERESIS;Ll;0;L;0065 0308;;;;N;LATIN SMALL LETTER E DIAERESIS;;00CB;;00CB +00EC;LATIN SMALL LETTER I WITH GRAVE;Ll;0;L;0069 0300;;;;N;LATIN SMALL LETTER I GRAVE;;00CC;;00CC +00ED;LATIN SMALL LETTER I WITH ACUTE;Ll;0;L;0069 0301;;;;N;LATIN SMALL LETTER I ACUTE;;00CD;;00CD +00EE;LATIN SMALL LETTER I WITH CIRCUMFLEX;Ll;0;L;0069 0302;;;;N;LATIN SMALL LETTER I CIRCUMFLEX;;00CE;;00CE +00EF;LATIN SMALL LETTER I WITH DIAERESIS;Ll;0;L;0069 0308;;;;N;LATIN SMALL LETTER I DIAERESIS;;00CF;;00CF +00F0;LATIN SMALL LETTER ETH;Ll;0;L;;;;;N;;Icelandic;00D0;;00D0 +00F1;LATIN SMALL LETTER N WITH TILDE;Ll;0;L;006E 0303;;;;N;LATIN SMALL LETTER N TILDE;;00D1;;00D1 +00F2;LATIN SMALL LETTER O WITH GRAVE;Ll;0;L;006F 0300;;;;N;LATIN SMALL LETTER O GRAVE;;00D2;;00D2 +00F3;LATIN SMALL LETTER O WITH ACUTE;Ll;0;L;006F 0301;;;;N;LATIN SMALL LETTER O ACUTE;;00D3;;00D3 +00F4;LATIN SMALL LETTER O WITH CIRCUMFLEX;Ll;0;L;006F 0302;;;;N;LATIN SMALL LETTER O CIRCUMFLEX;;00D4;;00D4 +00F5;LATIN SMALL LETTER O WITH TILDE;Ll;0;L;006F 0303;;;;N;LATIN SMALL LETTER O TILDE;;00D5;;00D5 +00F6;LATIN SMALL LETTER O WITH DIAERESIS;Ll;0;L;006F 0308;;;;N;LATIN SMALL LETTER O DIAERESIS;;00D6;;00D6 +00F7;DIVISION SIGN;Sm;0;ON;;;;;N;;;;; +00F8;LATIN SMALL LETTER O WITH STROKE;Ll;0;L;;;;;N;LATIN SMALL LETTER O SLASH;;00D8;;00D8 +00F9;LATIN SMALL LETTER U WITH GRAVE;Ll;0;L;0075 0300;;;;N;LATIN SMALL LETTER U GRAVE;;00D9;;00D9 +00FA;LATIN SMALL LETTER U WITH ACUTE;Ll;0;L;0075 0301;;;;N;LATIN SMALL LETTER U ACUTE;;00DA;;00DA +00FB;LATIN SMALL LETTER U WITH CIRCUMFLEX;Ll;0;L;0075 0302;;;;N;LATIN SMALL LETTER U CIRCUMFLEX;;00DB;;00DB +00FC;LATIN SMALL LETTER U WITH DIAERESIS;Ll;0;L;0075 0308;;;;N;LATIN SMALL LETTER U DIAERESIS;;00DC;;00DC +00FD;LATIN SMALL LETTER Y WITH ACUTE;Ll;0;L;0079 0301;;;;N;LATIN SMALL LETTER Y ACUTE;;00DD;;00DD +00FE;LATIN SMALL LETTER THORN;Ll;0;L;;;;;N;;Icelandic;00DE;;00DE +00FF;LATIN SMALL LETTER Y WITH DIAERESIS;Ll;0;L;0079 0308;;;;N;LATIN SMALL LETTER Y DIAERESIS;;0178;;0178 +0131;LATIN SMALL LETTER DOTLESS I;Ll;0;L;;;;;N;;;0049;;0049 +0192;LATIN SMALL LETTER F WITH HOOK;Ll;0;L;;;;;N;LATIN SMALL LETTER SCRIPT F;;0191;;0191 +0393;GREEK CAPITAL LETTER GAMMA;Lu;0;L;;;;;N;;;;03B3; +0398;GREEK CAPITAL LETTER THETA;Lu;0;L;;;;;N;;;;03B8; +03A3;GREEK CAPITAL LETTER SIGMA;Lu;0;L;;;;;N;;;;03C3; +03A6;GREEK CAPITAL LETTER PHI;Lu;0;L;;;;;N;;;;03C6; +03A9;GREEK CAPITAL LETTER OMEGA;Lu;0;L;;;;;N;;;;03C9; +03B1;GREEK SMALL LETTER ALPHA;Ll;0;L;;;;;N;;;0391;;0391 +03B4;GREEK SMALL LETTER DELTA;Ll;0;L;;;;;N;;;0394;;0394 +03B5;GREEK SMALL LETTER EPSILON;Ll;0;L;;;;;N;;;0395;;0395 +03C0;GREEK SMALL LETTER PI;Ll;0;L;;;;;N;;;03A0;;03A0 +03C3;GREEK SMALL LETTER SIGMA;Ll;0;L;;;;;N;;;03A3;;03A3 +03C4;GREEK SMALL LETTER TAU;Ll;0;L;;;;;N;;;03A4;;03A4 +03C6;GREEK SMALL LETTER PHI;Ll;0;L;;;;;N;;;03A6;;03A6 +2017;DOUBLE LOW LINE;Po;0;ON; 0020 0333;;;;N;SPACING DOUBLE UNDERSCORE;;;; +207F;SUPERSCRIPT LATIN SMALL LETTER N;Ll;0;L; 006E;;;;N;;;;; +20A7;PESETA SIGN;Sc;0;ET;;;;;N;;;;; +2219;BULLET OPERATOR;Sm;0;ON;;;;;N;;;;; +221A;SQUARE ROOT;Sm;0;ON;;;;;Y;;;;; +221E;INFINITY;Sm;0;ON;;;;;N;;;;; +2229;INTERSECTION;Sm;0;ON;;;;;N;;;;; +2248;ALMOST EQUAL TO;Sm;0;ON;;;;;Y;;;;; +2261;IDENTICAL TO;Sm;0;ON;;;;;N;;;;; +2264;LESS-THAN OR EQUAL TO;Sm;0;ON;;;;;Y;LESS THAN OR EQUAL TO;;;; +2265;GREATER-THAN OR EQUAL TO;Sm;0;ON;;;;;Y;GREATER THAN OR EQUAL TO;;;; +2310;REVERSED NOT SIGN;So;0;ON;;;;;N;;;;; +2320;TOP HALF INTEGRAL;Sm;0;ON;;;;;Y;;;;; +2321;BOTTOM HALF INTEGRAL;Sm;0;ON;;;;;Y;;;;; +2500;BOX DRAWINGS LIGHT HORIZONTAL;So;0;ON;;;;;N;FORMS LIGHT HORIZONTAL;;;; +2502;BOX DRAWINGS LIGHT VERTICAL;So;0;ON;;;;;N;FORMS LIGHT VERTICAL;;;; +250C;BOX DRAWINGS LIGHT DOWN AND RIGHT;So;0;ON;;;;;N;FORMS LIGHT DOWN AND RIGHT;;;; +2510;BOX DRAWINGS LIGHT DOWN AND LEFT;So;0;ON;;;;;N;FORMS LIGHT DOWN AND LEFT;;;; +2514;BOX DRAWINGS LIGHT UP AND RIGHT;So;0;ON;;;;;N;FORMS LIGHT UP AND RIGHT;;;; +2518;BOX DRAWINGS LIGHT UP AND LEFT;So;0;ON;;;;;N;FORMS LIGHT UP AND LEFT;;;; +251C;BOX DRAWINGS LIGHT VERTICAL AND RIGHT;So;0;ON;;;;;N;FORMS LIGHT VERTICAL AND RIGHT;;;; +2524;BOX DRAWINGS LIGHT VERTICAL AND LEFT;So;0;ON;;;;;N;FORMS LIGHT VERTICAL AND LEFT;;;; +252C;BOX DRAWINGS LIGHT DOWN AND HORIZONTAL;So;0;ON;;;;;N;FORMS LIGHT DOWN AND HORIZONTAL;;;; +2534;BOX DRAWINGS LIGHT UP AND HORIZONTAL;So;0;ON;;;;;N;FORMS LIGHT UP AND HORIZONTAL;;;; +253C;BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL;So;0;ON;;;;;N;FORMS LIGHT VERTICAL AND HORIZONTAL;;;; +2550;BOX DRAWINGS DOUBLE HORIZONTAL;So;0;ON;;;;;N;FORMS DOUBLE HORIZONTAL;;;; +2551;BOX DRAWINGS DOUBLE VERTICAL;So;0;ON;;;;;N;FORMS DOUBLE VERTICAL;;;; +2552;BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE;So;0;ON;;;;;N;FORMS DOWN SINGLE AND RIGHT DOUBLE;;;; +2553;BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE;So;0;ON;;;;;N;FORMS DOWN DOUBLE AND RIGHT SINGLE;;;; +2554;BOX DRAWINGS DOUBLE DOWN AND RIGHT;So;0;ON;;;;;N;FORMS DOUBLE DOWN AND RIGHT;;;; +2555;BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE;So;0;ON;;;;;N;FORMS DOWN SINGLE AND LEFT DOUBLE;;;; +2556;BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE;So;0;ON;;;;;N;FORMS DOWN DOUBLE AND LEFT SINGLE;;;; +2557;BOX DRAWINGS DOUBLE DOWN AND LEFT;So;0;ON;;;;;N;FORMS DOUBLE DOWN AND LEFT;;;; +2558;BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE;So;0;ON;;;;;N;FORMS UP SINGLE AND RIGHT DOUBLE;;;; +2559;BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE;So;0;ON;;;;;N;FORMS UP DOUBLE AND RIGHT SINGLE;;;; +255A;BOX DRAWINGS DOUBLE UP AND RIGHT;So;0;ON;;;;;N;FORMS DOUBLE UP AND RIGHT;;;; +255B;BOX DRAWINGS UP SINGLE AND LEFT DOUBLE;So;0;ON;;;;;N;FORMS UP SINGLE AND LEFT DOUBLE;;;; +255C;BOX DRAWINGS UP DOUBLE AND LEFT SINGLE;So;0;ON;;;;;N;FORMS UP DOUBLE AND LEFT SINGLE;;;; +255D;BOX DRAWINGS DOUBLE UP AND LEFT;So;0;ON;;;;;N;FORMS DOUBLE UP AND LEFT;;;; +255E;BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE;So;0;ON;;;;;N;FORMS VERTICAL SINGLE AND RIGHT DOUBLE;;;; +255F;BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE;So;0;ON;;;;;N;FORMS VERTICAL DOUBLE AND RIGHT SINGLE;;;; +2560;BOX DRAWINGS DOUBLE VERTICAL AND RIGHT;So;0;ON;;;;;N;FORMS DOUBLE VERTICAL AND RIGHT;;;; +2561;BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE;So;0;ON;;;;;N;FORMS VERTICAL SINGLE AND LEFT DOUBLE;;;; +2562;BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE;So;0;ON;;;;;N;FORMS VERTICAL DOUBLE AND LEFT SINGLE;;;; +2563;BOX DRAWINGS DOUBLE VERTICAL AND LEFT;So;0;ON;;;;;N;FORMS DOUBLE VERTICAL AND LEFT;;;; +2564;BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE;So;0;ON;;;;;N;FORMS DOWN SINGLE AND HORIZONTAL DOUBLE;;;; +2565;BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE;So;0;ON;;;;;N;FORMS DOWN DOUBLE AND HORIZONTAL SINGLE;;;; +2566;BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL;So;0;ON;;;;;N;FORMS DOUBLE DOWN AND HORIZONTAL;;;; +2567;BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE;So;0;ON;;;;;N;FORMS UP SINGLE AND HORIZONTAL DOUBLE;;;; +2568;BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE;So;0;ON;;;;;N;FORMS UP DOUBLE AND HORIZONTAL SINGLE;;;; +2569;BOX DRAWINGS DOUBLE UP AND HORIZONTAL;So;0;ON;;;;;N;FORMS DOUBLE UP AND HORIZONTAL;;;; +256A;BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE;So;0;ON;;;;;N;FORMS VERTICAL SINGLE AND HORIZONTAL DOUBLE;;;; +256B;BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE;So;0;ON;;;;;N;FORMS VERTICAL DOUBLE AND HORIZONTAL SINGLE;;;; +256C;BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL;So;0;ON;;;;;N;FORMS DOUBLE VERTICAL AND HORIZONTAL;;;; +2580;UPPER HALF BLOCK;So;0;ON;;;;;N;;;;; +2584;LOWER HALF BLOCK;So;0;ON;;;;;N;;;;; +2588;FULL BLOCK;So;0;ON;;;;;N;;;;; +258C;LEFT HALF BLOCK;So;0;ON;;;;;N;;;;; +2590;RIGHT HALF BLOCK;So;0;ON;;;;;N;;;;; +2591;LIGHT SHADE;So;0;ON;;;;;N;;;;; +2592;MEDIUM SHADE;So;0;ON;;;;;N;;;;; +2593;DARK SHADE;So;0;ON;;;;;N;;;;; +25A0;BLACK SQUARE;So;0;ON;;;;;N;;;;; diff --git a/codepage/cp437.txt b/codepage/cp437.txt new file mode 100644 index 0000000..aa5a53b --- /dev/null +++ b/codepage/cp437.txt @@ -0,0 +1,273 @@ +# +# Name: cp437_DOSLatinUS to Unicode table +# Unicode version: 2.0 +# Table version: 2.00 +# Table format: Format A +# Date: 04/24/96 +# Contact: Shawn.Steele@microsoft.com +# +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp437_DOSLatinUS code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp437_DOSLatinUS order +# +0x00 0x0000 #NULL +0x01 0x0001 #START OF HEADING +0x02 0x0002 #START OF TEXT +0x03 0x0003 #END OF TEXT +0x04 0x0004 #END OF TRANSMISSION +0x05 0x0005 #ENQUIRY +0x06 0x0006 #ACKNOWLEDGE +0x07 0x0007 #BELL +0x08 0x0008 #BACKSPACE +0x09 0x0009 #HORIZONTAL TABULATION +0x0a 0x000a #LINE FEED +0x0b 0x000b #VERTICAL TABULATION +0x0c 0x000c #FORM FEED +0x0d 0x000d #CARRIAGE RETURN +0x0e 0x000e #SHIFT OUT +0x0f 0x000f #SHIFT IN +0x10 0x0010 #DATA LINK ESCAPE +0x11 0x0011 #DEVICE CONTROL ONE +0x12 0x0012 #DEVICE CONTROL TWO +0x13 0x0013 #DEVICE CONTROL THREE +0x14 0x0014 #DEVICE CONTROL FOUR +0x15 0x0015 #NEGATIVE ACKNOWLEDGE +0x16 0x0016 #SYNCHRONOUS IDLE +0x17 0x0017 #END OF TRANSMISSION BLOCK +0x18 0x0018 #CANCEL +0x19 0x0019 #END OF MEDIUM +0x1a 0x001a #SUBSTITUTE +0x1b 0x001b #ESCAPE +0x1c 0x001c #FILE SEPARATOR +0x1d 0x001d #GROUP SEPARATOR +0x1e 0x001e #RECORD SEPARATOR +0x1f 0x001f #UNIT SEPARATOR +0x20 0x0020 #SPACE +0x21 0x0021 #EXCLAMATION MARK +0x22 0x0022 #QUOTATION MARK +0x23 0x0023 #NUMBER SIGN +0x24 0x0024 #DOLLAR SIGN +0x25 0x0025 #PERCENT SIGN +0x26 0x0026 #AMPERSAND +0x27 0x0027 #APOSTROPHE +0x28 0x0028 #LEFT PARENTHESIS +0x29 0x0029 #RIGHT PARENTHESIS +0x2a 0x002a #ASTERISK +0x2b 0x002b #PLUS SIGN +0x2c 0x002c #COMMA +0x2d 0x002d #HYPHEN-MINUS +0x2e 0x002e #FULL STOP +0x2f 0x002f #SOLIDUS +0x30 0x0030 #DIGIT ZERO +0x31 0x0031 #DIGIT ONE +0x32 0x0032 #DIGIT TWO +0x33 0x0033 #DIGIT THREE +0x34 0x0034 #DIGIT FOUR +0x35 0x0035 #DIGIT FIVE +0x36 0x0036 #DIGIT SIX +0x37 0x0037 #DIGIT SEVEN +0x38 0x0038 #DIGIT EIGHT +0x39 0x0039 #DIGIT NINE +0x3a 0x003a #COLON +0x3b 0x003b #SEMICOLON +0x3c 0x003c #LESS-THAN SIGN +0x3d 0x003d #EQUALS SIGN +0x3e 0x003e #GREATER-THAN SIGN +0x3f 0x003f #QUESTION MARK +0x40 0x0040 #COMMERCIAL AT +0x41 0x0041 #LATIN CAPITAL LETTER A +0x42 0x0042 #LATIN CAPITAL LETTER B +0x43 0x0043 #LATIN CAPITAL LETTER C +0x44 0x0044 #LATIN CAPITAL LETTER D +0x45 0x0045 #LATIN CAPITAL LETTER E +0x46 0x0046 #LATIN CAPITAL LETTER F +0x47 0x0047 #LATIN CAPITAL LETTER G +0x48 0x0048 #LATIN CAPITAL LETTER H +0x49 0x0049 #LATIN CAPITAL LETTER I +0x4a 0x004a #LATIN CAPITAL LETTER J +0x4b 0x004b #LATIN CAPITAL LETTER K +0x4c 0x004c #LATIN CAPITAL LETTER L +0x4d 0x004d #LATIN CAPITAL LETTER M +0x4e 0x004e #LATIN CAPITAL LETTER N +0x4f 0x004f #LATIN CAPITAL LETTER O +0x50 0x0050 #LATIN CAPITAL LETTER P +0x51 0x0051 #LATIN CAPITAL LETTER Q +0x52 0x0052 #LATIN CAPITAL LETTER R +0x53 0x0053 #LATIN CAPITAL LETTER S +0x54 0x0054 #LATIN CAPITAL LETTER T +0x55 0x0055 #LATIN CAPITAL LETTER U +0x56 0x0056 #LATIN CAPITAL LETTER V +0x57 0x0057 #LATIN CAPITAL LETTER W +0x58 0x0058 #LATIN CAPITAL LETTER X +0x59 0x0059 #LATIN CAPITAL LETTER Y +0x5a 0x005a #LATIN CAPITAL LETTER Z +0x5b 0x005b #LEFT SQUARE BRACKET +0x5c 0x005c #REVERSE SOLIDUS +0x5d 0x005d #RIGHT SQUARE BRACKET +0x5e 0x005e #CIRCUMFLEX ACCENT +0x5f 0x005f #LOW LINE +0x60 0x0060 #GRAVE ACCENT +0x61 0x0061 #LATIN SMALL LETTER A +0x62 0x0062 #LATIN SMALL LETTER B +0x63 0x0063 #LATIN SMALL LETTER C +0x64 0x0064 #LATIN SMALL LETTER D +0x65 0x0065 #LATIN SMALL LETTER E +0x66 0x0066 #LATIN SMALL LETTER F +0x67 0x0067 #LATIN SMALL LETTER G +0x68 0x0068 #LATIN SMALL LETTER H +0x69 0x0069 #LATIN SMALL LETTER I +0x6a 0x006a #LATIN SMALL LETTER J +0x6b 0x006b #LATIN SMALL LETTER K +0x6c 0x006c #LATIN SMALL LETTER L +0x6d 0x006d #LATIN SMALL LETTER M +0x6e 0x006e #LATIN SMALL LETTER N +0x6f 0x006f #LATIN SMALL LETTER O +0x70 0x0070 #LATIN SMALL LETTER P +0x71 0x0071 #LATIN SMALL LETTER Q +0x72 0x0072 #LATIN SMALL LETTER R +0x73 0x0073 #LATIN SMALL LETTER S +0x74 0x0074 #LATIN SMALL LETTER T +0x75 0x0075 #LATIN SMALL LETTER U +0x76 0x0076 #LATIN SMALL LETTER V +0x77 0x0077 #LATIN SMALL LETTER W +0x78 0x0078 #LATIN SMALL LETTER X +0x79 0x0079 #LATIN SMALL LETTER Y +0x7a 0x007a #LATIN SMALL LETTER Z +0x7b 0x007b #LEFT CURLY BRACKET +0x7c 0x007c #VERTICAL LINE +0x7d 0x007d #RIGHT CURLY BRACKET +0x7e 0x007e #TILDE +0x7f 0x007f #DELETE +0x80 0x00c7 #LATIN CAPITAL LETTER C WITH CEDILLA +0x81 0x00fc #LATIN SMALL LETTER U WITH DIAERESIS +0x82 0x00e9 #LATIN SMALL LETTER E WITH ACUTE +0x83 0x00e2 #LATIN SMALL LETTER A WITH CIRCUMFLEX +0x84 0x00e4 #LATIN SMALL LETTER A WITH DIAERESIS +0x85 0x00e0 #LATIN SMALL LETTER A WITH GRAVE +0x86 0x00e5 #LATIN SMALL LETTER A WITH RING ABOVE +0x87 0x00e7 #LATIN SMALL LETTER C WITH CEDILLA +0x88 0x00ea #LATIN SMALL LETTER E WITH CIRCUMFLEX +0x89 0x00eb #LATIN SMALL LETTER E WITH DIAERESIS +0x8a 0x00e8 #LATIN SMALL LETTER E WITH GRAVE +0x8b 0x00ef #LATIN SMALL LETTER I WITH DIAERESIS +0x8c 0x00ee #LATIN SMALL LETTER I WITH CIRCUMFLEX +0x8d 0x00ec #LATIN SMALL LETTER I WITH GRAVE +0x8e 0x00c4 #LATIN CAPITAL LETTER A WITH DIAERESIS +0x8f 0x00c5 #LATIN CAPITAL LETTER A WITH RING ABOVE +0x90 0x00c9 #LATIN CAPITAL LETTER E WITH ACUTE +0x91 0x00e6 #LATIN SMALL LIGATURE AE +0x92 0x00c6 #LATIN CAPITAL LIGATURE AE +0x93 0x00f4 #LATIN SMALL LETTER O WITH CIRCUMFLEX +0x94 0x00f6 #LATIN SMALL LETTER O WITH DIAERESIS +0x95 0x00f2 #LATIN SMALL LETTER O WITH GRAVE +0x96 0x00fb #LATIN SMALL LETTER U WITH CIRCUMFLEX +0x97 0x00f9 #LATIN SMALL LETTER U WITH GRAVE +0x98 0x00ff #LATIN SMALL LETTER Y WITH DIAERESIS +0x99 0x00d6 #LATIN CAPITAL LETTER O WITH DIAERESIS +0x9a 0x00dc #LATIN CAPITAL LETTER U WITH DIAERESIS +0x9b 0x00a2 #CENT SIGN +0x9c 0x00a3 #POUND SIGN +0x9d 0x00a5 #YEN SIGN +0x9e 0x20a7 #PESETA SIGN +0x9f 0x0192 #LATIN SMALL LETTER F WITH HOOK +0xa0 0x00e1 #LATIN SMALL LETTER A WITH ACUTE +0xa1 0x00ed #LATIN SMALL LETTER I WITH ACUTE +0xa2 0x00f3 #LATIN SMALL LETTER O WITH ACUTE +0xa3 0x00fa #LATIN SMALL LETTER U WITH ACUTE +0xa4 0x00f1 #LATIN SMALL LETTER N WITH TILDE +0xa5 0x00d1 #LATIN CAPITAL LETTER N WITH TILDE +0xa6 0x00aa #FEMININE ORDINAL INDICATOR +0xa7 0x00ba #MASCULINE ORDINAL INDICATOR +0xa8 0x00bf #INVERTED QUESTION MARK +0xa9 0x2310 #REVERSED NOT SIGN +0xaa 0x00ac #NOT SIGN +0xab 0x00bd #VULGAR FRACTION ONE HALF +0xac 0x00bc #VULGAR FRACTION ONE QUARTER +0xad 0x00a1 #INVERTED EXCLAMATION MARK +0xae 0x00ab #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xaf 0x00bb #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xb0 0x2591 #LIGHT SHADE +0xb1 0x2592 #MEDIUM SHADE +0xb2 0x2593 #DARK SHADE +0xb3 0x2502 #BOX DRAWINGS LIGHT VERTICAL +0xb4 0x2524 #BOX DRAWINGS LIGHT VERTICAL AND LEFT +0xb5 0x2561 #BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE +0xb6 0x2562 #BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE +0xb7 0x2556 #BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE +0xb8 0x2555 #BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE +0xb9 0x2563 #BOX DRAWINGS DOUBLE VERTICAL AND LEFT +0xba 0x2551 #BOX DRAWINGS DOUBLE VERTICAL +0xbb 0x2557 #BOX DRAWINGS DOUBLE DOWN AND LEFT +0xbc 0x255d #BOX DRAWINGS DOUBLE UP AND LEFT +0xbd 0x255c #BOX DRAWINGS UP DOUBLE AND LEFT SINGLE +0xbe 0x255b #BOX DRAWINGS UP SINGLE AND LEFT DOUBLE +0xbf 0x2510 #BOX DRAWINGS LIGHT DOWN AND LEFT +0xc0 0x2514 #BOX DRAWINGS LIGHT UP AND RIGHT +0xc1 0x2534 #BOX DRAWINGS LIGHT UP AND HORIZONTAL +0xc2 0x252c #BOX DRAWINGS LIGHT DOWN AND HORIZONTAL +0xc3 0x251c #BOX DRAWINGS LIGHT VERTICAL AND RIGHT +0xc4 0x2500 #BOX DRAWINGS LIGHT HORIZONTAL +0xc5 0x253c #BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL +0xc6 0x255e #BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE +0xc7 0x255f #BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE +0xc8 0x255a #BOX DRAWINGS DOUBLE UP AND RIGHT +0xc9 0x2554 #BOX DRAWINGS DOUBLE DOWN AND RIGHT +0xca 0x2569 #BOX DRAWINGS DOUBLE UP AND HORIZONTAL +0xcb 0x2566 #BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL +0xcc 0x2560 #BOX DRAWINGS DOUBLE VERTICAL AND RIGHT +0xcd 0x2550 #BOX DRAWINGS DOUBLE HORIZONTAL +0xce 0x256c #BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL +0xcf 0x2567 #BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE +0xd0 0x2568 #BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE +0xd1 0x2564 #BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE +0xd2 0x2565 #BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE +0xd3 0x2559 #BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE +0xd4 0x2558 #BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE +0xd5 0x2552 #BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE +0xd6 0x2553 #BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE +0xd7 0x256b #BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE +0xd8 0x256a #BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE +0xd9 0x2518 #BOX DRAWINGS LIGHT UP AND LEFT +0xda 0x250c #BOX DRAWINGS LIGHT DOWN AND RIGHT +0xdb 0x2588 #FULL BLOCK +0xdc 0x2584 #LOWER HALF BLOCK +0xdd 0x258c #LEFT HALF BLOCK +0xde 0x2590 #RIGHT HALF BLOCK +0xdf 0x2580 #UPPER HALF BLOCK +0xe0 0x03b1 #GREEK SMALL LETTER ALPHA +0xe1 0x00df #LATIN SMALL LETTER SHARP S +0xe2 0x0393 #GREEK CAPITAL LETTER GAMMA +0xe3 0x03c0 #GREEK SMALL LETTER PI +0xe4 0x03a3 #GREEK CAPITAL LETTER SIGMA +0xe5 0x03c3 #GREEK SMALL LETTER SIGMA +0xe6 0x00b5 #MICRO SIGN +0xe7 0x03c4 #GREEK SMALL LETTER TAU +0xe8 0x03a6 #GREEK CAPITAL LETTER PHI +0xe9 0x0398 #GREEK CAPITAL LETTER THETA +0xea 0x03a9 #GREEK CAPITAL LETTER OMEGA +0xeb 0x03b4 #GREEK SMALL LETTER DELTA +0xec 0x221e #INFINITY +0xed 0x03c6 #GREEK SMALL LETTER PHI +0xee 0x03b5 #GREEK SMALL LETTER EPSILON +0xef 0x2229 #INTERSECTION +0xf0 0x2261 #IDENTICAL TO +0xf1 0x00b1 #PLUS-MINUS SIGN +0xf2 0x2265 #GREATER-THAN OR EQUAL TO +0xf3 0x2264 #LESS-THAN OR EQUAL TO +0xf4 0x2320 #TOP HALF INTEGRAL +0xf5 0x2321 #BOTTOM HALF INTEGRAL +0xf6 0x00f7 #DIVISION SIGN +0xf7 0x2248 #ALMOST EQUAL TO +0xf8 0x00b0 #DEGREE SIGN +0xf9 0x2219 #BULLET OPERATOR +0xfa 0x00b7 #MIDDLE DOT +0xfb 0x221a #SQUARE ROOT +0xfc 0x207f #SUPERSCRIPT LATIN SMALL LETTER N +0xfd 0x00b2 #SUPERSCRIPT TWO +0xfe 0x25a0 #BLACK SQUARE +0xff 0x00a0 #NO-BREAK SPACE diff --git a/codepage/cp850.txt b/codepage/cp850.txt new file mode 100644 index 0000000..26a4232 --- /dev/null +++ b/codepage/cp850.txt @@ -0,0 +1,273 @@ +# +# Name: cp850_DOSLatin1 to Unicode table +# Unicode version: 2.0 +# Table version: 2.00 +# Table format: Format A +# Date: 04/24/96 +# Contact: Shawn.Steele@microsoft.com +# +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp850_DOSLatin1 code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp850_DOSLatin1 order +# +0x00 0x0000 #NULL +0x01 0x0001 #START OF HEADING +0x02 0x0002 #START OF TEXT +0x03 0x0003 #END OF TEXT +0x04 0x0004 #END OF TRANSMISSION +0x05 0x0005 #ENQUIRY +0x06 0x0006 #ACKNOWLEDGE +0x07 0x0007 #BELL +0x08 0x0008 #BACKSPACE +0x09 0x0009 #HORIZONTAL TABULATION +0x0a 0x000a #LINE FEED +0x0b 0x000b #VERTICAL TABULATION +0x0c 0x000c #FORM FEED +0x0d 0x000d #CARRIAGE RETURN +0x0e 0x000e #SHIFT OUT +0x0f 0x000f #SHIFT IN +0x10 0x0010 #DATA LINK ESCAPE +0x11 0x0011 #DEVICE CONTROL ONE +0x12 0x0012 #DEVICE CONTROL TWO +0x13 0x0013 #DEVICE CONTROL THREE +0x14 0x0014 #DEVICE CONTROL FOUR +0x15 0x0015 #NEGATIVE ACKNOWLEDGE +0x16 0x0016 #SYNCHRONOUS IDLE +0x17 0x0017 #END OF TRANSMISSION BLOCK +0x18 0x0018 #CANCEL +0x19 0x0019 #END OF MEDIUM +0x1a 0x001a #SUBSTITUTE +0x1b 0x001b #ESCAPE +0x1c 0x001c #FILE SEPARATOR +0x1d 0x001d #GROUP SEPARATOR +0x1e 0x001e #RECORD SEPARATOR +0x1f 0x001f #UNIT SEPARATOR +0x20 0x0020 #SPACE +0x21 0x0021 #EXCLAMATION MARK +0x22 0x0022 #QUOTATION MARK +0x23 0x0023 #NUMBER SIGN +0x24 0x0024 #DOLLAR SIGN +0x25 0x0025 #PERCENT SIGN +0x26 0x0026 #AMPERSAND +0x27 0x0027 #APOSTROPHE +0x28 0x0028 #LEFT PARENTHESIS +0x29 0x0029 #RIGHT PARENTHESIS +0x2a 0x002a #ASTERISK +0x2b 0x002b #PLUS SIGN +0x2c 0x002c #COMMA +0x2d 0x002d #HYPHEN-MINUS +0x2e 0x002e #FULL STOP +0x2f 0x002f #SOLIDUS +0x30 0x0030 #DIGIT ZERO +0x31 0x0031 #DIGIT ONE +0x32 0x0032 #DIGIT TWO +0x33 0x0033 #DIGIT THREE +0x34 0x0034 #DIGIT FOUR +0x35 0x0035 #DIGIT FIVE +0x36 0x0036 #DIGIT SIX +0x37 0x0037 #DIGIT SEVEN +0x38 0x0038 #DIGIT EIGHT +0x39 0x0039 #DIGIT NINE +0x3a 0x003a #COLON +0x3b 0x003b #SEMICOLON +0x3c 0x003c #LESS-THAN SIGN +0x3d 0x003d #EQUALS SIGN +0x3e 0x003e #GREATER-THAN SIGN +0x3f 0x003f #QUESTION MARK +0x40 0x0040 #COMMERCIAL AT +0x41 0x0041 #LATIN CAPITAL LETTER A +0x42 0x0042 #LATIN CAPITAL LETTER B +0x43 0x0043 #LATIN CAPITAL LETTER C +0x44 0x0044 #LATIN CAPITAL LETTER D +0x45 0x0045 #LATIN CAPITAL LETTER E +0x46 0x0046 #LATIN CAPITAL LETTER F +0x47 0x0047 #LATIN CAPITAL LETTER G +0x48 0x0048 #LATIN CAPITAL LETTER H +0x49 0x0049 #LATIN CAPITAL LETTER I +0x4a 0x004a #LATIN CAPITAL LETTER J +0x4b 0x004b #LATIN CAPITAL LETTER K +0x4c 0x004c #LATIN CAPITAL LETTER L +0x4d 0x004d #LATIN CAPITAL LETTER M +0x4e 0x004e #LATIN CAPITAL LETTER N +0x4f 0x004f #LATIN CAPITAL LETTER O +0x50 0x0050 #LATIN CAPITAL LETTER P +0x51 0x0051 #LATIN CAPITAL LETTER Q +0x52 0x0052 #LATIN CAPITAL LETTER R +0x53 0x0053 #LATIN CAPITAL LETTER S +0x54 0x0054 #LATIN CAPITAL LETTER T +0x55 0x0055 #LATIN CAPITAL LETTER U +0x56 0x0056 #LATIN CAPITAL LETTER V +0x57 0x0057 #LATIN CAPITAL LETTER W +0x58 0x0058 #LATIN CAPITAL LETTER X +0x59 0x0059 #LATIN CAPITAL LETTER Y +0x5a 0x005a #LATIN CAPITAL LETTER Z +0x5b 0x005b #LEFT SQUARE BRACKET +0x5c 0x005c #REVERSE SOLIDUS +0x5d 0x005d #RIGHT SQUARE BRACKET +0x5e 0x005e #CIRCUMFLEX ACCENT +0x5f 0x005f #LOW LINE +0x60 0x0060 #GRAVE ACCENT +0x61 0x0061 #LATIN SMALL LETTER A +0x62 0x0062 #LATIN SMALL LETTER B +0x63 0x0063 #LATIN SMALL LETTER C +0x64 0x0064 #LATIN SMALL LETTER D +0x65 0x0065 #LATIN SMALL LETTER E +0x66 0x0066 #LATIN SMALL LETTER F +0x67 0x0067 #LATIN SMALL LETTER G +0x68 0x0068 #LATIN SMALL LETTER H +0x69 0x0069 #LATIN SMALL LETTER I +0x6a 0x006a #LATIN SMALL LETTER J +0x6b 0x006b #LATIN SMALL LETTER K +0x6c 0x006c #LATIN SMALL LETTER L +0x6d 0x006d #LATIN SMALL LETTER M +0x6e 0x006e #LATIN SMALL LETTER N +0x6f 0x006f #LATIN SMALL LETTER O +0x70 0x0070 #LATIN SMALL LETTER P +0x71 0x0071 #LATIN SMALL LETTER Q +0x72 0x0072 #LATIN SMALL LETTER R +0x73 0x0073 #LATIN SMALL LETTER S +0x74 0x0074 #LATIN SMALL LETTER T +0x75 0x0075 #LATIN SMALL LETTER U +0x76 0x0076 #LATIN SMALL LETTER V +0x77 0x0077 #LATIN SMALL LETTER W +0x78 0x0078 #LATIN SMALL LETTER X +0x79 0x0079 #LATIN SMALL LETTER Y +0x7a 0x007a #LATIN SMALL LETTER Z +0x7b 0x007b #LEFT CURLY BRACKET +0x7c 0x007c #VERTICAL LINE +0x7d 0x007d #RIGHT CURLY BRACKET +0x7e 0x007e #TILDE +0x7f 0x007f #DELETE +0x80 0x00c7 #LATIN CAPITAL LETTER C WITH CEDILLA +0x81 0x00fc #LATIN SMALL LETTER U WITH DIAERESIS +0x82 0x00e9 #LATIN SMALL LETTER E WITH ACUTE +0x83 0x00e2 #LATIN SMALL LETTER A WITH CIRCUMFLEX +0x84 0x00e4 #LATIN SMALL LETTER A WITH DIAERESIS +0x85 0x00e0 #LATIN SMALL LETTER A WITH GRAVE +0x86 0x00e5 #LATIN SMALL LETTER A WITH RING ABOVE +0x87 0x00e7 #LATIN SMALL LETTER C WITH CEDILLA +0x88 0x00ea #LATIN SMALL LETTER E WITH CIRCUMFLEX +0x89 0x00eb #LATIN SMALL LETTER E WITH DIAERESIS +0x8a 0x00e8 #LATIN SMALL LETTER E WITH GRAVE +0x8b 0x00ef #LATIN SMALL LETTER I WITH DIAERESIS +0x8c 0x00ee #LATIN SMALL LETTER I WITH CIRCUMFLEX +0x8d 0x00ec #LATIN SMALL LETTER I WITH GRAVE +0x8e 0x00c4 #LATIN CAPITAL LETTER A WITH DIAERESIS +0x8f 0x00c5 #LATIN CAPITAL LETTER A WITH RING ABOVE +0x90 0x00c9 #LATIN CAPITAL LETTER E WITH ACUTE +0x91 0x00e6 #LATIN SMALL LIGATURE AE +0x92 0x00c6 #LATIN CAPITAL LIGATURE AE +0x93 0x00f4 #LATIN SMALL LETTER O WITH CIRCUMFLEX +0x94 0x00f6 #LATIN SMALL LETTER O WITH DIAERESIS +0x95 0x00f2 #LATIN SMALL LETTER O WITH GRAVE +0x96 0x00fb #LATIN SMALL LETTER U WITH CIRCUMFLEX +0x97 0x00f9 #LATIN SMALL LETTER U WITH GRAVE +0x98 0x00ff #LATIN SMALL LETTER Y WITH DIAERESIS +0x99 0x00d6 #LATIN CAPITAL LETTER O WITH DIAERESIS +0x9a 0x00dc #LATIN CAPITAL LETTER U WITH DIAERESIS +0x9b 0x00f8 #LATIN SMALL LETTER O WITH STROKE +0x9c 0x00a3 #POUND SIGN +0x9d 0x00d8 #LATIN CAPITAL LETTER O WITH STROKE +0x9e 0x00d7 #MULTIPLICATION SIGN +0x9f 0x0192 #LATIN SMALL LETTER F WITH HOOK +0xa0 0x00e1 #LATIN SMALL LETTER A WITH ACUTE +0xa1 0x00ed #LATIN SMALL LETTER I WITH ACUTE +0xa2 0x00f3 #LATIN SMALL LETTER O WITH ACUTE +0xa3 0x00fa #LATIN SMALL LETTER U WITH ACUTE +0xa4 0x00f1 #LATIN SMALL LETTER N WITH TILDE +0xa5 0x00d1 #LATIN CAPITAL LETTER N WITH TILDE +0xa6 0x00aa #FEMININE ORDINAL INDICATOR +0xa7 0x00ba #MASCULINE ORDINAL INDICATOR +0xa8 0x00bf #INVERTED QUESTION MARK +0xa9 0x00ae #REGISTERED SIGN +0xaa 0x00ac #NOT SIGN +0xab 0x00bd #VULGAR FRACTION ONE HALF +0xac 0x00bc #VULGAR FRACTION ONE QUARTER +0xad 0x00a1 #INVERTED EXCLAMATION MARK +0xae 0x00ab #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xaf 0x00bb #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +0xb0 0x2591 #LIGHT SHADE +0xb1 0x2592 #MEDIUM SHADE +0xb2 0x2593 #DARK SHADE +0xb3 0x2502 #BOX DRAWINGS LIGHT VERTICAL +0xb4 0x2524 #BOX DRAWINGS LIGHT VERTICAL AND LEFT +0xb5 0x00c1 #LATIN CAPITAL LETTER A WITH ACUTE +0xb6 0x00c2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX +0xb7 0x00c0 #LATIN CAPITAL LETTER A WITH GRAVE +0xb8 0x00a9 #COPYRIGHT SIGN +0xb9 0x2563 #BOX DRAWINGS DOUBLE VERTICAL AND LEFT +0xba 0x2551 #BOX DRAWINGS DOUBLE VERTICAL +0xbb 0x2557 #BOX DRAWINGS DOUBLE DOWN AND LEFT +0xbc 0x255d #BOX DRAWINGS DOUBLE UP AND LEFT +0xbd 0x00a2 #CENT SIGN +0xbe 0x00a5 #YEN SIGN +0xbf 0x2510 #BOX DRAWINGS LIGHT DOWN AND LEFT +0xc0 0x2514 #BOX DRAWINGS LIGHT UP AND RIGHT +0xc1 0x2534 #BOX DRAWINGS LIGHT UP AND HORIZONTAL +0xc2 0x252c #BOX DRAWINGS LIGHT DOWN AND HORIZONTAL +0xc3 0x251c #BOX DRAWINGS LIGHT VERTICAL AND RIGHT +0xc4 0x2500 #BOX DRAWINGS LIGHT HORIZONTAL +0xc5 0x253c #BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL +0xc6 0x00e3 #LATIN SMALL LETTER A WITH TILDE +0xc7 0x00c3 #LATIN CAPITAL LETTER A WITH TILDE +0xc8 0x255a #BOX DRAWINGS DOUBLE UP AND RIGHT +0xc9 0x2554 #BOX DRAWINGS DOUBLE DOWN AND RIGHT +0xca 0x2569 #BOX DRAWINGS DOUBLE UP AND HORIZONTAL +0xcb 0x2566 #BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL +0xcc 0x2560 #BOX DRAWINGS DOUBLE VERTICAL AND RIGHT +0xcd 0x2550 #BOX DRAWINGS DOUBLE HORIZONTAL +0xce 0x256c #BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL +0xcf 0x00a4 #CURRENCY SIGN +0xd0 0x00f0 #LATIN SMALL LETTER ETH +0xd1 0x00d0 #LATIN CAPITAL LETTER ETH +0xd2 0x00ca #LATIN CAPITAL LETTER E WITH CIRCUMFLEX +0xd3 0x00cb #LATIN CAPITAL LETTER E WITH DIAERESIS +0xd4 0x00c8 #LATIN CAPITAL LETTER E WITH GRAVE +0xd5 0x0131 #LATIN SMALL LETTER DOTLESS I +0xd6 0x00cd #LATIN CAPITAL LETTER I WITH ACUTE +0xd7 0x00ce #LATIN CAPITAL LETTER I WITH CIRCUMFLEX +0xd8 0x00cf #LATIN CAPITAL LETTER I WITH DIAERESIS +0xd9 0x2518 #BOX DRAWINGS LIGHT UP AND LEFT +0xda 0x250c #BOX DRAWINGS LIGHT DOWN AND RIGHT +0xdb 0x2588 #FULL BLOCK +0xdc 0x2584 #LOWER HALF BLOCK +0xdd 0x00a6 #BROKEN BAR +0xde 0x00cc #LATIN CAPITAL LETTER I WITH GRAVE +0xdf 0x2580 #UPPER HALF BLOCK +0xe0 0x00d3 #LATIN CAPITAL LETTER O WITH ACUTE +0xe1 0x00df #LATIN SMALL LETTER SHARP S +0xe2 0x00d4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX +0xe3 0x00d2 #LATIN CAPITAL LETTER O WITH GRAVE +0xe4 0x00f5 #LATIN SMALL LETTER O WITH TILDE +0xe5 0x00d5 #LATIN CAPITAL LETTER O WITH TILDE +0xe6 0x00b5 #MICRO SIGN +0xe7 0x00fe #LATIN SMALL LETTER THORN +0xe8 0x00de #LATIN CAPITAL LETTER THORN +0xe9 0x00da #LATIN CAPITAL LETTER U WITH ACUTE +0xea 0x00db #LATIN CAPITAL LETTER U WITH CIRCUMFLEX +0xeb 0x00d9 #LATIN CAPITAL LETTER U WITH GRAVE +0xec 0x00fd #LATIN SMALL LETTER Y WITH ACUTE +0xed 0x00dd #LATIN CAPITAL LETTER Y WITH ACUTE +0xee 0x00af #MACRON +0xef 0x00b4 #ACUTE ACCENT +0xf0 0x00ad #SOFT HYPHEN +0xf1 0x00b1 #PLUS-MINUS SIGN +0xf2 0x2017 #DOUBLE LOW LINE +0xf3 0x00be #VULGAR FRACTION THREE QUARTERS +0xf4 0x00b6 #PILCROW SIGN +0xf5 0x00a7 #SECTION SIGN +0xf6 0x00f7 #DIVISION SIGN +0xf7 0x00b8 #CEDILLA +0xf8 0x00b0 #DEGREE SIGN +0xf9 0x00a8 #DIAERESIS +0xfa 0x00b7 #MIDDLE DOT +0xfb 0x00b9 #SUPERSCRIPT ONE +0xfc 0x00b3 #SUPERSCRIPT THREE +0xfd 0x00b2 #SUPERSCRIPT TWO +0xfe 0x25a0 #BLACK SQUARE +0xff 0x00a0 #NO-BREAK SPACE diff --git a/codepage/cp865.txt b/codepage/cp865.txt new file mode 100644 index 0000000..f3d6fef --- /dev/null +++ b/codepage/cp865.txt @@ -0,0 +1,274 @@ +# +# Name: cp865_DOSNordic to Unicode table +# Unicode version: 2.0 +# Table version: 2.00 +# Table format: Format A +# Date: 04/24/96 +# Contact: Shawn.Steele@microsoft.com +# +# General notes: none +# +# Format: Three tab-separated columns +# Column #1 is the cp865_DOSNordic code (in hex) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 is the Unicode name (follows a comment sign, '#') +# +# The entries are in cp865_DOSNordic order +# +0x00 0x0000 #NULL +0x01 0x0001 #START OF HEADING +0x02 0x0002 #START OF TEXT +0x03 0x0003 #END OF TEXT +0x04 0x0004 #END OF TRANSMISSION +0x05 0x0005 #ENQUIRY +0x06 0x0006 #ACKNOWLEDGE +0x07 0x0007 #BELL +0x08 0x0008 #BACKSPACE +0x09 0x0009 #HORIZONTAL TABULATION +0x0a 0x000a #LINE FEED +0x0b 0x000b #VERTICAL TABULATION +0x0c 0x000c #FORM FEED +0x0d 0x000d #CARRIAGE RETURN +0x0e 0x000e #SHIFT OUT +0x0f 0x000f #SHIFT IN +0x10 0x0010 #DATA LINK ESCAPE +0x11 0x0011 #DEVICE CONTROL ONE +0x12 0x0012 #DEVICE CONTROL TWO +0x13 0x0013 #DEVICE CONTROL THREE +0x14 0x0014 #DEVICE CONTROL FOUR +0x15 0x0015 #NEGATIVE ACKNOWLEDGE +0x16 0x0016 #SYNCHRONOUS IDLE +0x17 0x0017 #END OF TRANSMISSION BLOCK +0x18 0x0018 #CANCEL +0x19 0x0019 #END OF MEDIUM +0x1a 0x001a #SUBSTITUTE +0x1b 0x001b #ESCAPE +0x1c 0x001c #FILE SEPARATOR +0x1d 0x001d #GROUP SEPARATOR +0x1e 0x001e #RECORD SEPARATOR +0x1f 0x001f #UNIT SEPARATOR +0x20 0x0020 #SPACE +0x21 0x0021 #EXCLAMATION MARK +0x22 0x0022 #QUOTATION MARK +0x23 0x0023 #NUMBER SIGN +0x24 0x0024 #DOLLAR SIGN +0x25 0x0025 #PERCENT SIGN +0x26 0x0026 #AMPERSAND +0x27 0x0027 #APOSTROPHE +0x28 0x0028 #LEFT PARENTHESIS +0x29 0x0029 #RIGHT PARENTHESIS +0x2a 0x002a #ASTERISK +0x2b 0x002b #PLUS SIGN +0x2c 0x002c #COMMA +0x2d 0x002d #HYPHEN-MINUS +0x2e 0x002e #FULL STOP +0x2f 0x002f #SOLIDUS +0x30 0x0030 #DIGIT ZERO +0x31 0x0031 #DIGIT ONE +0x32 0x0032 #DIGIT TWO +0x33 0x0033 #DIGIT THREE +0x34 0x0034 #DIGIT FOUR +0x35 0x0035 #DIGIT FIVE +0x36 0x0036 #DIGIT SIX +0x37 0x0037 #DIGIT SEVEN +0x38 0x0038 #DIGIT EIGHT +0x39 0x0039 #DIGIT NINE +0x3a 0x003a #COLON +0x3b 0x003b #SEMICOLON +0x3c 0x003c #LESS-THAN SIGN +0x3d 0x003d #EQUALS SIGN +0x3e 0x003e #GREATER-THAN SIGN +0x3f 0x003f #QUESTION MARK +0x40 0x0040 #COMMERCIAL AT +0x41 0x0041 #LATIN CAPITAL LETTER A +0x42 0x0042 #LATIN CAPITAL LETTER B +0x43 0x0043 #LATIN CAPITAL LETTER C +0x44 0x0044 #LATIN CAPITAL LETTER D +0x45 0x0045 #LATIN CAPITAL LETTER E +0x46 0x0046 #LATIN CAPITAL LETTER F +0x47 0x0047 #LATIN CAPITAL LETTER G +0x48 0x0048 #LATIN CAPITAL LETTER H +0x49 0x0049 #LATIN CAPITAL LETTER I +0x4a 0x004a #LATIN CAPITAL LETTER J +0x4b 0x004b #LATIN CAPITAL LETTER K +0x4c 0x004c #LATIN CAPITAL LETTER L +0x4d 0x004d #LATIN CAPITAL LETTER M +0x4e 0x004e #LATIN CAPITAL LETTER N +0x4f 0x004f #LATIN CAPITAL LETTER O +0x50 0x0050 #LATIN CAPITAL LETTER P +0x51 0x0051 #LATIN CAPITAL LETTER Q +0x52 0x0052 #LATIN CAPITAL LETTER R +0x53 0x0053 #LATIN CAPITAL LETTER S +0x54 0x0054 #LATIN CAPITAL LETTER T +0x55 0x0055 #LATIN CAPITAL LETTER U +0x56 0x0056 #LATIN CAPITAL LETTER V +0x57 0x0057 #LATIN CAPITAL LETTER W +0x58 0x0058 #LATIN CAPITAL LETTER X +0x59 0x0059 #LATIN CAPITAL LETTER Y +0x5a 0x005a #LATIN CAPITAL LETTER Z +0x5b 0x005b #LEFT SQUARE BRACKET +0x5c 0x005c #REVERSE SOLIDUS +0x5d 0x005d #RIGHT SQUARE BRACKET +0x5e 0x005e #CIRCUMFLEX ACCENT +0x5f 0x005f #LOW LINE +0x60 0x0060 #GRAVE ACCENT +0x61 0x0061 #LATIN SMALL LETTER A +0x62 0x0062 #LATIN SMALL LETTER B +0x63 0x0063 #LATIN SMALL LETTER C +0x64 0x0064 #LATIN SMALL LETTER D +0x65 0x0065 #LATIN SMALL LETTER E +0x66 0x0066 #LATIN SMALL LETTER F +0x67 0x0067 #LATIN SMALL LETTER G +0x68 0x0068 #LATIN SMALL LETTER H +0x69 0x0069 #LATIN SMALL LETTER I +0x6a 0x006a #LATIN SMALL LETTER J +0x6b 0x006b #LATIN SMALL LETTER K +0x6c 0x006c #LATIN SMALL LETTER L +0x6d 0x006d #LATIN SMALL LETTER M +0x6e 0x006e #LATIN SMALL LETTER N +0x6f 0x006f #LATIN SMALL LETTER O +0x70 0x0070 #LATIN SMALL LETTER P +0x71 0x0071 #LATIN SMALL LETTER Q +0x72 0x0072 #LATIN SMALL LETTER R +0x73 0x0073 #LATIN SMALL LETTER S +0x74 0x0074 #LATIN SMALL LETTER T +0x75 0x0075 #LATIN SMALL LETTER U +0x76 0x0076 #LATIN SMALL LETTER V +0x77 0x0077 #LATIN SMALL LETTER W +0x78 0x0078 #LATIN SMALL LETTER X +0x79 0x0079 #LATIN SMALL LETTER Y +0x7a 0x007a #LATIN SMALL LETTER Z +0x7b 0x007b #LEFT CURLY BRACKET +0x7c 0x007c #VERTICAL LINE +0x7d 0x007d #RIGHT CURLY BRACKET +0x7e 0x007e #TILDE +0x7f 0x007f #DELETE +0x80 0x00c7 #LATIN CAPITAL LETTER C WITH CEDILLA +0x81 0x00fc #LATIN SMALL LETTER U WITH DIAERESIS +0x82 0x00e9 #LATIN SMALL LETTER E WITH ACUTE +0x83 0x00e2 #LATIN SMALL LETTER A WITH CIRCUMFLEX +0x84 0x00e4 #LATIN SMALL LETTER A WITH DIAERESIS +0x85 0x00e0 #LATIN SMALL LETTER A WITH GRAVE +0x86 0x00e5 #LATIN SMALL LETTER A WITH RING ABOVE +0x87 0x00e7 #LATIN SMALL LETTER C WITH CEDILLA +0x88 0x00ea #LATIN SMALL LETTER E WITH CIRCUMFLEX +0x89 0x00eb #LATIN SMALL LETTER E WITH DIAERESIS +0x8a 0x00e8 #LATIN SMALL LETTER E WITH GRAVE +0x8b 0x00ef #LATIN SMALL LETTER I WITH DIAERESIS +0x8c 0x00ee #LATIN SMALL LETTER I WITH CIRCUMFLEX +0x8d 0x00ec #LATIN SMALL LETTER I WITH GRAVE +0x8e 0x00c4 #LATIN CAPITAL LETTER A WITH DIAERESIS +0x8f 0x00c5 #LATIN CAPITAL LETTER A WITH RING ABOVE +0x90 0x00c9 #LATIN CAPITAL LETTER E WITH ACUTE +0x91 0x00e6 #LATIN SMALL LIGATURE AE +0x92 0x00c6 #LATIN CAPITAL LIGATURE AE +0x93 0x00f4 #LATIN SMALL LETTER O WITH CIRCUMFLEX +0x94 0x00f6 #LATIN SMALL LETTER O WITH DIAERESIS +0x95 0x00f2 #LATIN SMALL LETTER O WITH GRAVE +0x96 0x00fb #LATIN SMALL LETTER U WITH CIRCUMFLEX +0x97 0x00f9 #LATIN SMALL LETTER U WITH GRAVE +0x98 0x00ff #LATIN SMALL LETTER Y WITH DIAERESIS +0x99 0x00d6 #LATIN CAPITAL LETTER O WITH DIAERESIS +0x9a 0x00dc #LATIN CAPITAL LETTER U WITH DIAERESIS +0x9b 0x00f8 #LATIN SMALL LETTER O WITH STROKE +0x9c 0x00a3 #POUND SIGN +0x9d 0x00d8 #LATIN CAPITAL LETTER O WITH STROKE +0x9e 0x20a7 #PESETA SIGN +0x9f 0x0192 #LATIN SMALL LETTER F WITH HOOK +0xa0 0x00e1 #LATIN SMALL LETTER A WITH ACUTE +0xa1 0x00ed #LATIN SMALL LETTER I WITH ACUTE +0xa2 0x00f3 #LATIN SMALL LETTER O WITH ACUTE +0xa3 0x00fa #LATIN SMALL LETTER U WITH ACUTE +0xa4 0x00f1 #LATIN SMALL LETTER N WITH TILDE +0xa5 0x00d1 #LATIN CAPITAL LETTER N WITH TILDE +0xa6 0x00aa #FEMININE ORDINAL INDICATOR +0xa7 0x00ba #MASCULINE ORDINAL INDICATOR +0xa8 0x00bf #INVERTED QUESTION MARK +0xa9 0x2310 #REVERSED NOT SIGN +0xaa 0x00ac #NOT SIGN +0xab 0x00bd #VULGAR FRACTION ONE HALF +0xac 0x00bc #VULGAR FRACTION ONE QUARTER +0xad 0x00a1 #INVERTED EXCLAMATION MARK +0xae 0x00ab #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +0xaf 0x00a4 #CURRENCY SIGN +0xb0 0x2591 #LIGHT SHADE +0xb1 0x2592 #MEDIUM SHADE +0xb2 0x2593 #DARK SHADE +0xb3 0x2502 #BOX DRAWINGS LIGHT VERTICAL +0xb4 0x2524 #BOX DRAWINGS LIGHT VERTICAL AND LEFT +0xb5 0x2561 #BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE +0xb6 0x2562 #BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE +0xb7 0x2556 #BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE +0xb8 0x2555 #BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE +0xb9 0x2563 #BOX DRAWINGS DOUBLE VERTICAL AND LEFT +0xba 0x2551 #BOX DRAWINGS DOUBLE VERTICAL +0xbb 0x2557 #BOX DRAWINGS DOUBLE DOWN AND LEFT +0xbc 0x255d #BOX DRAWINGS DOUBLE UP AND LEFT +0xbd 0x255c #BOX DRAWINGS UP DOUBLE AND LEFT SINGLE +0xbe 0x255b #BOX DRAWINGS UP SINGLE AND LEFT DOUBLE +0xbf 0x2510 #BOX DRAWINGS LIGHT DOWN AND LEFT +0xc0 0x2514 #BOX DRAWINGS LIGHT UP AND RIGHT +0xc1 0x2534 #BOX DRAWINGS LIGHT UP AND HORIZONTAL +0xc2 0x252c #BOX DRAWINGS LIGHT DOWN AND HORIZONTAL +0xc3 0x251c #BOX DRAWINGS LIGHT VERTICAL AND RIGHT +0xc4 0x2500 #BOX DRAWINGS LIGHT HORIZONTAL +0xc5 0x253c #BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL +0xc6 0x255e #BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE +0xc7 0x255f #BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE +0xc8 0x255a #BOX DRAWINGS DOUBLE UP AND RIGHT +0xc9 0x2554 #BOX DRAWINGS DOUBLE DOWN AND RIGHT +0xca 0x2569 #BOX DRAWINGS DOUBLE UP AND HORIZONTAL +0xcb 0x2566 #BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL +0xcc 0x2560 #BOX DRAWINGS DOUBLE VERTICAL AND RIGHT +0xcd 0x2550 #BOX DRAWINGS DOUBLE HORIZONTAL +0xce 0x256c #BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL +0xcf 0x2567 #BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE +0xd0 0x2568 #BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE +0xd1 0x2564 #BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE +0xd2 0x2565 #BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE +0xd3 0x2559 #BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE +0xd4 0x2558 #BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE +0xd5 0x2552 #BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE +0xd6 0x2553 #BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE +0xd7 0x256b #BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE +0xd8 0x256a #BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE +0xd9 0x2518 #BOX DRAWINGS LIGHT UP AND LEFT +0xda 0x250c #BOX DRAWINGS LIGHT DOWN AND RIGHT +0xdb 0x2588 #FULL BLOCK +0xdc 0x2584 #LOWER HALF BLOCK +0xdd 0x258c #LEFT HALF BLOCK +0xde 0x2590 #RIGHT HALF BLOCK +0xdf 0x2580 #UPPER HALF BLOCK +0xe0 0x03b1 #GREEK SMALL LETTER ALPHA +0xe1 0x00df #LATIN SMALL LETTER SHARP S +0xe2 0x0393 #GREEK CAPITAL LETTER GAMMA +0xe3 0x03c0 #GREEK SMALL LETTER PI +0xe4 0x03a3 #GREEK CAPITAL LETTER SIGMA +0xe5 0x03c3 #GREEK SMALL LETTER SIGMA +0xe6 0x00b5 #MICRO SIGN +0xe7 0x03c4 #GREEK SMALL LETTER TAU +0xe8 0x03a6 #GREEK CAPITAL LETTER PHI +0xe9 0x0398 #GREEK CAPITAL LETTER THETA +0xea 0x03a9 #GREEK CAPITAL LETTER OMEGA +0xeb 0x03b4 #GREEK SMALL LETTER DELTA +0xec 0x221e #INFINITY +0xed 0x03c6 #GREEK SMALL LETTER PHI +0xee 0x03b5 #GREEK SMALL LETTER EPSILON +0xef 0x2229 #INTERSECTION +0xf0 0x2261 #IDENTICAL TO +0xf1 0x00b1 #PLUS-MINUS SIGN +0xf2 0x2265 #GREATER-THAN OR EQUAL TO +0xf3 0x2264 #LESS-THAN OR EQUAL TO +0xf4 0x2320 #TOP HALF INTEGRAL +0xf5 0x2321 #BOTTOM HALF INTEGRAL +0xf6 0x00f7 #DIVISION SIGN +0xf7 0x2248 #ALMOST EQUAL TO +0xf8 0x00b0 #DEGREE SIGN +0xf9 0x2219 #BULLET OPERATOR +0xfa 0x00b7 #MIDDLE DOT +0xfb 0x221a #SQUARE ROOT +0xfc 0x207f #SUPERSCRIPT LATIN SMALL LETTER N +0xfd 0x00b2 #SUPERSCRIPT TWO +0xfe 0x25a0 #BLACK SQUARE +0xff 0x00a0 #NO-BREAK SPACE + diff --git a/codepage/cptable.pl b/codepage/cptable.pl new file mode 100755 index 0000000..c183d08 --- /dev/null +++ b/codepage/cptable.pl @@ -0,0 +1,58 @@ +#!/usr/bin/perl +# +# Produce a codepage matching table. For each 8-bit character, list +# a primary and an alternate match (the latter used for case-insensitive +# matching.) +# +# Usage: +# cptable.pl UnicodeData cpXXX.txt cpXXX.bin +# + +($ucd, $cpin, $cpout) = @ARGV; + +%altcase = (); + +open(UCD, '<', $ucd) or die; +while (defined($line = )) { + chomp $line; + @f = split(/;/, $line); + if ($f[12] ne '') { + $altcase{hex $f[0]} = hex $f[12]; # Upper case equivalent + } elsif ($f[13] ne '') { + $altcase{hex $f[0]} = hex $f[13]; # Lower case equivalent + } elsif ($f[14] ne '') { + $altcase{hex $f[0]} = hex $f[14]; # Title case, would be unusual + } else { + $altcase{hex $f[0]} = hex $f[0]; + } +} +close(UCD); + +@xtab = (undef) x 256; + +open(CPIN, '<', $cpin) or die; +while (defined($line = )) { + $line =~ s/\s*(\#.*|)$//; + @f = split(/\s+/, $line); + next if (scalar @f != 2); + next if (hex $f[0] > 255); + $xtab[hex $f[0]] = hex $f[1]; +} +close(CPIN); + +open(CPOUT, '>', $cpout) or die; +for ($i = 0; $i < 256; $i++) { + if (!defined($xtab[$i])) { + $p0 = $p1 = 0xffff; + } else { + $p0 = $xtab[$i]; + $p1 = defined($altcase{$p0}) ? $altcase{$p0} : $p0; + } + # Only the BMP is supported... + $p0 = 0xffff if ($p0 > 0xffff); + $p1 = 0xffff if ($p1 > 0xffff); + print CPOUT pack("vv", $p0, $p1); +} +close (CPOUT); + + diff --git a/codepage/gensubset.pl b/codepage/gensubset.pl new file mode 100755 index 0000000..5fde460 --- /dev/null +++ b/codepage/gensubset.pl @@ -0,0 +1,38 @@ +#!/usr/bin/perl +# +# Generate a subset of the UnicodeData.txt file, available from +# ftp://ftp.unicode.org/Public/UNIDATA/UnicodeData.txt +# +# Usage: +# gensubset.pl [subset files] < UnicodeData.txt > MiniUCD.txt +# + +%need_these = (); + +foreach $file (@ARGV) { + open(F, '<', $file) or die; + while (defined($line = )) { + $line =~ s/\s*(\#.*|)$//; # Remove comments and final blanks + @f = split(/\s+/, $line); + next if (scalar @f != 2); + $need_these{hex $f[1]}++; + } + close(F); +} + +while (defined($line = )) { + ($v, $l) = split(/;/, $line, 2); + if ($v =~ /^([0-9a-f]+)\-([0-9a-f]+)$/i) { + $r1 = hex $1; + $r2 = hex $2; + } elsif ($v =~ /^([0-9a-f]+)$/i) { + $r1 = $r2 = hex $1; + } else { + next; + } + for ($r = $r1; $r <= $r2; $r++) { + printf "%04X;%s", $r, $l if ($need_these{$r}); + } +} + + -- 2.7.4