Add more codepage data; support disjoint mappings

Add additional codepage data from the Unicode Consortium.
Additionally, add support for generating codepage files for the case
where the filesystem codepage and the display codepage do not match.
The standard Makefile doesn't actually do that, however.

1 files changed, 274 insertions, 0 deletions

diff --git a/codepage/cp1253.txt b/codepage/cp1253.txt
new file mode 100644
index 00000000..20a55b04
--- /dev/null
+++ b/codepage/cp1253.txt
@@ -0,0 +1,274 @@
+#
+#    Name:     cp1253 to Unicode table
+#    Unicode version: 2.0
+#    Table version: 2.01
+#    Table format:  Format A
+#    Date:          04/15/98
+#
+#    Contact:       Shawn.Steele@microsoft.com
+#
+#    General notes: none
+#
+#    Format: Three tab-separated columns
+#        Column #1 is the cp1253 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 cp1253 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	0x20AC	#EURO SIGN
+0x81	      	#UNDEFINED
+0x82	0x201A	#SINGLE LOW-9 QUOTATION MARK
+0x83	0x0192	#LATIN SMALL LETTER F WITH HOOK
+0x84	0x201E	#DOUBLE LOW-9 QUOTATION MARK
+0x85	0x2026	#HORIZONTAL ELLIPSIS
+0x86	0x2020	#DAGGER
+0x87	0x2021	#DOUBLE DAGGER
+0x88	      	#UNDEFINED
+0x89	0x2030	#PER MILLE SIGN
+0x8A	      	#UNDEFINED
+0x8B	0x2039	#SINGLE LEFT-POINTING ANGLE QUOTATION MARK
+0x8C	      	#UNDEFINED
+0x8D	      	#UNDEFINED
+0x8E	      	#UNDEFINED
+0x8F	      	#UNDEFINED
+0x90	      	#UNDEFINED
+0x91	0x2018	#LEFT SINGLE QUOTATION MARK
+0x92	0x2019	#RIGHT SINGLE QUOTATION MARK
+0x93	0x201C	#LEFT DOUBLE QUOTATION MARK
+0x94	0x201D	#RIGHT DOUBLE QUOTATION MARK
+0x95	0x2022	#BULLET
+0x96	0x2013	#EN DASH
+0x97	0x2014	#EM DASH
+0x98	      	#UNDEFINED
+0x99	0x2122	#TRADE MARK SIGN
+0x9A	      	#UNDEFINED
+0x9B	0x203A	#SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
+0x9C	      	#UNDEFINED
+0x9D	      	#UNDEFINED
+0x9E	      	#UNDEFINED
+0x9F	      	#UNDEFINED
+0xA0	0x00A0	#NO-BREAK SPACE
+0xA1	0x0385	#GREEK DIALYTIKA TONOS
+0xA2	0x0386	#GREEK CAPITAL LETTER ALPHA WITH TONOS
+0xA3	0x00A3	#POUND SIGN
+0xA4	0x00A4	#CURRENCY SIGN
+0xA5	0x00A5	#YEN SIGN
+0xA6	0x00A6	#BROKEN BAR
+0xA7	0x00A7	#SECTION SIGN
+0xA8	0x00A8	#DIAERESIS
+0xA9	0x00A9	#COPYRIGHT SIGN
+0xAA	      	#UNDEFINED
+0xAB	0x00AB	#LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xAC	0x00AC	#NOT SIGN
+0xAD	0x00AD	#SOFT HYPHEN
+0xAE	0x00AE	#REGISTERED SIGN
+0xAF	0x2015	#HORIZONTAL BAR
+0xB0	0x00B0	#DEGREE SIGN
+0xB1	0x00B1	#PLUS-MINUS SIGN
+0xB2	0x00B2	#SUPERSCRIPT TWO
+0xB3	0x00B3	#SUPERSCRIPT THREE
+0xB4	0x0384	#GREEK TONOS
+0xB5	0x00B5	#MICRO SIGN
+0xB6	0x00B6	#PILCROW SIGN
+0xB7	0x00B7	#MIDDLE DOT
+0xB8	0x0388	#GREEK CAPITAL LETTER EPSILON WITH TONOS
+0xB9	0x0389	#GREEK CAPITAL LETTER ETA WITH TONOS
+0xBA	0x038A	#GREEK CAPITAL LETTER IOTA WITH TONOS
+0xBB	0x00BB	#RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xBC	0x038C	#GREEK CAPITAL LETTER OMICRON WITH TONOS
+0xBD	0x00BD	#VULGAR FRACTION ONE HALF
+0xBE	0x038E	#GREEK CAPITAL LETTER UPSILON WITH TONOS
+0xBF	0x038F	#GREEK CAPITAL LETTER OMEGA WITH TONOS
+0xC0	0x0390	#GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
+0xC1	0x0391	#GREEK CAPITAL LETTER ALPHA
+0xC2	0x0392	#GREEK CAPITAL LETTER BETA
+0xC3	0x0393	#GREEK CAPITAL LETTER GAMMA
+0xC4	0x0394	#GREEK CAPITAL LETTER DELTA
+0xC5	0x0395	#GREEK CAPITAL LETTER EPSILON
+0xC6	0x0396	#GREEK CAPITAL LETTER ZETA
+0xC7	0x0397	#GREEK CAPITAL LETTER ETA
+0xC8	0x0398	#GREEK CAPITAL LETTER THETA
+0xC9	0x0399	#GREEK CAPITAL LETTER IOTA
+0xCA	0x039A	#GREEK CAPITAL LETTER KAPPA
+0xCB	0x039B	#GREEK CAPITAL LETTER LAMDA
+0xCC	0x039C	#GREEK CAPITAL LETTER MU
+0xCD	0x039D	#GREEK CAPITAL LETTER NU
+0xCE	0x039E	#GREEK CAPITAL LETTER XI
+0xCF	0x039F	#GREEK CAPITAL LETTER OMICRON
+0xD0	0x03A0	#GREEK CAPITAL LETTER PI
+0xD1	0x03A1	#GREEK CAPITAL LETTER RHO
+0xD2	      	#UNDEFINED
+0xD3	0x03A3	#GREEK CAPITAL LETTER SIGMA
+0xD4	0x03A4	#GREEK CAPITAL LETTER TAU
+0xD5	0x03A5	#GREEK CAPITAL LETTER UPSILON
+0xD6	0x03A6	#GREEK CAPITAL LETTER PHI
+0xD7	0x03A7	#GREEK CAPITAL LETTER CHI
+0xD8	0x03A8	#GREEK CAPITAL LETTER PSI
+0xD9	0x03A9	#GREEK CAPITAL LETTER OMEGA
+0xDA	0x03AA	#GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
+0xDB	0x03AB	#GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
+0xDC	0x03AC	#GREEK SMALL LETTER ALPHA WITH TONOS
+0xDD	0x03AD	#GREEK SMALL LETTER EPSILON WITH TONOS
+0xDE	0x03AE	#GREEK SMALL LETTER ETA WITH TONOS
+0xDF	0x03AF	#GREEK SMALL LETTER IOTA WITH TONOS
+0xE0	0x03B0	#GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
+0xE1	0x03B1	#GREEK SMALL LETTER ALPHA
+0xE2	0x03B2	#GREEK SMALL LETTER BETA
+0xE3	0x03B3	#GREEK SMALL LETTER GAMMA
+0xE4	0x03B4	#GREEK SMALL LETTER DELTA
+0xE5	0x03B5	#GREEK SMALL LETTER EPSILON
+0xE6	0x03B6	#GREEK SMALL LETTER ZETA
+0xE7	0x03B7	#GREEK SMALL LETTER ETA
+0xE8	0x03B8	#GREEK SMALL LETTER THETA
+0xE9	0x03B9	#GREEK SMALL LETTER IOTA
+0xEA	0x03BA	#GREEK SMALL LETTER KAPPA
+0xEB	0x03BB	#GREEK SMALL LETTER LAMDA
+0xEC	0x03BC	#GREEK SMALL LETTER MU
+0xED	0x03BD	#GREEK SMALL LETTER NU
+0xEE	0x03BE	#GREEK SMALL LETTER XI
+0xEF	0x03BF	#GREEK SMALL LETTER OMICRON
+0xF0	0x03C0	#GREEK SMALL LETTER PI
+0xF1	0x03C1	#GREEK SMALL LETTER RHO
+0xF2	0x03C2	#GREEK SMALL LETTER FINAL SIGMA
+0xF3	0x03C3	#GREEK SMALL LETTER SIGMA
+0xF4	0x03C4	#GREEK SMALL LETTER TAU
+0xF5	0x03C5	#GREEK SMALL LETTER UPSILON
+0xF6	0x03C6	#GREEK SMALL LETTER PHI
+0xF7	0x03C7	#GREEK SMALL LETTER CHI
+0xF8	0x03C8	#GREEK SMALL LETTER PSI
+0xF9	0x03C9	#GREEK SMALL LETTER OMEGA
+0xFA	0x03CA	#GREEK SMALL LETTER IOTA WITH DIALYTIKA
+0xFB	0x03CB	#GREEK SMALL LETTER UPSILON WITH DIALYTIKA
+0xFC	0x03CC	#GREEK SMALL LETTER OMICRON WITH TONOS
+0xFD	0x03CD	#GREEK SMALL LETTER UPSILON WITH TONOS
+0xFE	0x03CE	#GREEK SMALL LETTER OMEGA WITH TONOS
+0xFF	      	#UNDEFINED