Merge branch 'master' of git://factorcode.org/git/factor
Slava Pestov
commit
e32c167b7a
|
|
@ -32,7 +32,7 @@ HELP: month-names
|
|||
{ $warning "Do not use this array for looking up a month name directly. Use month-name instead." } ;
|
||||
|
||||
HELP: month-name
|
||||
{ $values { "n" integer } { "string" string } }
|
||||
{ $values { "obj" { $or integer timestamp } } { "string" string } }
|
||||
{ $description "Looks up the month name and returns it as a string. January has an index of 1 instead of zero." } ;
|
||||
|
||||
HELP: month-abbreviations
|
||||
|
|
@ -46,11 +46,11 @@ HELP: month-abbreviation
|
|||
|
||||
|
||||
HELP: day-names
|
||||
{ $values { "array" array } }
|
||||
{ $values { "value" array } }
|
||||
{ $description "Returns an array with the English names of the days of the week." } ;
|
||||
|
||||
HELP: day-name
|
||||
{ $values { "n" integer } { "string" string } }
|
||||
{ $values { "obj" { $or integer timestamp } } { "string" string } }
|
||||
{ $description "Looks up the day name and returns it as a string." } ;
|
||||
|
||||
HELP: day-abbreviations2
|
||||
|
|
|
|||
|
|
@ -3,13 +3,13 @@
|
|||
USING: accessors assocs byte-arrays calendar classes
|
||||
combinators combinators.short-circuit concurrency.promises
|
||||
continuations destructors ftp io io.backend io.directories
|
||||
io.encodings io.encodings.8-bit io.encodings.binary
|
||||
io.encodings io.encodings.binary
|
||||
tools.files io.encodings.utf8 io.files io.files.info
|
||||
io.pathnames io.launcher.unix.parser io.servers.connection
|
||||
io.sockets io.streams.duplex io.streams.string io.timeouts
|
||||
kernel make math math.bitwise math.parser namespaces sequences
|
||||
splitting threads unicode.case logging calendar.format
|
||||
strings io.files.links io.files.types ;
|
||||
strings io.files.links io.files.types io.encodings.8-bit.latin1 ;
|
||||
IN: ftp.server
|
||||
|
||||
SYMBOL: server
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
USING: http help.markup help.syntax io.pathnames io.streams.string
|
||||
io.encodings.8-bit io.encodings.binary kernel urls
|
||||
io.encodings.binary kernel urls
|
||||
urls.encoding byte-arrays strings assocs sequences destructors
|
||||
http.client.post-data.private ;
|
||||
http.client.post-data.private io.encodings.8-bit.latin1 ;
|
||||
IN: http.client
|
||||
|
||||
HELP: download-failed
|
||||
|
|
|
|||
|
|
@ -5,7 +5,7 @@ sequences strings splitting calendar continuations accessors vectors
|
|||
math.order hashtables byte-arrays destructors
|
||||
io io.sockets io.streams.string io.files io.timeouts
|
||||
io.pathnames io.encodings io.encodings.string io.encodings.ascii
|
||||
io.encodings.utf8 io.encodings.8-bit io.encodings.binary io.crlf
|
||||
io.encodings.utf8 io.encodings.binary io.crlf
|
||||
io.streams.duplex fry ascii urls urls.encoding present locals
|
||||
http http.parsers http.client.post-data ;
|
||||
IN: http.client
|
||||
|
|
|
|||
|
|
@ -2,7 +2,8 @@ USING: http http.server http.client http.client.private tools.test
|
|||
multiline io.streams.string io.encodings.utf8 io.encodings.8-bit
|
||||
io.encodings.binary io.encodings.string io.encodings.ascii kernel
|
||||
arrays splitting sequences assocs io.sockets db db.sqlite
|
||||
continuations urls hashtables accessors namespaces xml.data ;
|
||||
continuations urls hashtables accessors namespaces xml.data
|
||||
io.encodings.8-bit.latin1 ;
|
||||
IN: http.tests
|
||||
|
||||
[ "text/plain" latin1 ] [ "text/plain" parse-content-type ] unit-test
|
||||
|
|
|
|||
|
|
@ -5,9 +5,7 @@ sequences splitting sorting sets strings vectors hashtables
|
|||
quotations arrays byte-arrays math.parser calendar
|
||||
calendar.format present urls fry
|
||||
io io.encodings io.encodings.iana io.encodings.binary
|
||||
io.encodings.8-bit io.crlf ascii
|
||||
http.parsers
|
||||
base64 ;
|
||||
io.crlf ascii io.encodings.8-bit.latin1 http.parsers base64 ;
|
||||
IN: http
|
||||
|
||||
CONSTANT: max-redirects 10
|
||||
|
|
|
|||
|
|
@ -2,9 +2,9 @@
|
|||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: accessors alien.c-types arrays byte-arrays combinators
|
||||
compression.run-length fry grouping images images.loader io
|
||||
io.binary io.encodings.8-bit io.encodings.binary
|
||||
io.binary io.encodings.binary
|
||||
io.encodings.string io.streams.limited kernel math math.bitwise
|
||||
sequences specialized-arrays summary images.bitmap ;
|
||||
io.encodings.8-bit.latin1 sequences specialized-arrays summary images.bitmap ;
|
||||
QUALIFIED-WITH: bitstreams b
|
||||
SPECIALIZED-ARRAY: ushort
|
||||
IN: images.bitmap.loading
|
||||
|
|
|
|||
|
|
@ -5,106 +5,34 @@ strings ;
|
|||
IN: io.encodings.8-bit
|
||||
|
||||
ARTICLE: "io.encodings.8-bit" "Legacy 8-bit encodings"
|
||||
"Many encodings are a simple mapping of bytes onto characters. The " { $vocab-link "io.encodings.8-bit" } " vocabulary implements these generically using existing resource files. These encodings should be used with extreme caution, as fully general Unicode encodings like UTF-8 are nearly always more appropriate. The following 8-bit encodings are already defined:"
|
||||
{ $subsections
|
||||
latin1
|
||||
latin2
|
||||
latin3
|
||||
latin4
|
||||
latin/cyrillic
|
||||
latin/arabic
|
||||
latin/greek
|
||||
latin/hebrew
|
||||
latin5
|
||||
latin6
|
||||
latin/thai
|
||||
latin7
|
||||
latin8
|
||||
latin9
|
||||
latin10
|
||||
koi8-r
|
||||
windows-1252
|
||||
ebcdic
|
||||
mac-roman
|
||||
"Many encodings are a simple mapping of bytes onto characters. The " { $vocab-link "io.encodings.8-bit" } " vocabulary implements these generically using existing resource files. These encodings should be used with extreme caution, as fully general Unicode encodings like UTF-8 are nearly always more appropriate. The following 8-bit encodings are available:"
|
||||
{ $list
|
||||
{ $vocab-link "io.encodings.8-bit.ebcdic" }
|
||||
{ $vocab-link "io.encodings.8-bit.latin1" }
|
||||
{ $vocab-link "io.encodings.8-bit.latin2" }
|
||||
{ $vocab-link "io.encodings.8-bit.latin3" }
|
||||
{ $vocab-link "io.encodings.8-bit.latin4" }
|
||||
{ $vocab-link "io.encodings.8-bit.cyrillic" }
|
||||
{ $vocab-link "io.encodings.8-bit.arabic" }
|
||||
{ $vocab-link "io.encodings.8-bit.greek" }
|
||||
{ $vocab-link "io.encodings.8-bit.hebrew" }
|
||||
{ $vocab-link "io.encodings.8-bit.latin5" }
|
||||
{ $vocab-link "io.encodings.8-bit.latin6" }
|
||||
{ $vocab-link "io.encodings.8-bit.thai" }
|
||||
{ $vocab-link "io.encodings.8-bit.latin7" }
|
||||
{ $vocab-link "io.encodings.8-bit.latin8" }
|
||||
{ $vocab-link "io.encodings.8-bit.latin9" }
|
||||
{ $vocab-link "io.encodings.8-bit.koi8-r" }
|
||||
{ $vocab-link "io.encodings.8-bit.mac-roman" }
|
||||
{ $vocab-link "io.encodings.8-bit.windows-1250" }
|
||||
{ $vocab-link "io.encodings.8-bit.windows-1251" }
|
||||
{ $vocab-link "io.encodings.8-bit.windows-1252" }
|
||||
{ $vocab-link "io.encodings.8-bit.windows-1253" }
|
||||
{ $vocab-link "io.encodings.8-bit.windows-1254" }
|
||||
{ $vocab-link "io.encodings.8-bit.windows-1255" }
|
||||
{ $vocab-link "io.encodings.8-bit.windows-1256" }
|
||||
{ $vocab-link "io.encodings.8-bit.windows-1257" }
|
||||
{ $vocab-link "io.encodings.8-bit.windows-1258" }
|
||||
} ;
|
||||
|
||||
ABOUT: "io.encodings.8-bit"
|
||||
|
||||
HELP: 8-bit
|
||||
{ $class-description "Describes an 8-bit encoding, including its name (a symbol) and a table used for encoding and decoding." } ;
|
||||
|
||||
HELP: latin1
|
||||
{ $description "This is the ISO-8859-1 encoding, also called Latin-1: Western European. It is an 8-bit superset of ASCII which is the default for a mimetype starting with 'text' and provides the characters necessary for most western European languages." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
HELP: latin2
|
||||
{ $description "This is the ISO-8859-2 encoding, also called Latin-2: Eastern European. It is an 8-bit superset of ASCII and provides the characters necessary for most eastern European languages." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
HELP: latin3
|
||||
{ $description "This is the ISO-8859-3 encoding, also called Latin-3: South European. It is an 8-bit superset of ASCII and provides the characters necessary for Turkish, Maltese and Esperanto." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
HELP: latin4
|
||||
{ $description "This is the ISO-8859-4 encoding, also called Latin-4: North European. It is an 8-bit superset of ASCII and provides the characters necessary for Latvian, Lithuanian, Estonian, Greenlandic and Sami." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
HELP: latin/cyrillic
|
||||
{ $description "This is the ISO-8859-5 encoding, also called Latin/Cyrillic. It is an 8-bit superset of ASCII and provides the characters necessary for most languages which use Cyrilic, including Russian, Macedonian, Belarusian, Bulgarian, Serbian, and Ukrainian. KOI8-R is used much more commonly." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
HELP: latin/arabic
|
||||
{ $description "This is the ISO-8859-6 encoding, also called Latin/Arabic. It is an 8-bit superset of ASCII and provides the characters necessary for Arabic, though not other languages which use Arabic script." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
HELP: latin/greek
|
||||
{ $description "This is the ISO-8859-7 encoding, also called Latin/Greek. It is an 8-bit superset of ASCII and provides the characters necessary for Greek written in modern monotonic orthography, or ancient Greek without accent marks." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
HELP: latin/hebrew
|
||||
{ $description "This is the ISO-8859-8 encoding, also called Latin/Hebrew. It is an 8-bit superset of ASCII and provides the characters necessary for modern Hebrew without explicit vowels. Generally, this is interpreted in logical order, making it ISO-8859-8-I, technically." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
HELP: latin5
|
||||
{ $description "This is the ISO-8859-9 encoding, also called Latin-5: Turkish. It is an 8-bit superset of ASCII and provides the characters necessary for Turkish, similar to Latin-1 but replacing the spots used for Icelandic with characters used in Turkish." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
HELP: latin6
|
||||
{ $description "This is the ISO-8859-10 encoding, also called Latin-6: Nordic. It is an 8-bit superset of ASCII containing the same characters as Latin-4, but rearranged to be of better use to nordic languages." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
HELP: latin/thai
|
||||
{ $description "This is the ISO-8859-11 encoding, also called Latin/Thai. It is an 8-bit superset of ASCII containing the characters necessary to represent Thai. It is basically identical to TIS-620." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
HELP: latin7
|
||||
{ $description "This is the ISO-8859-13 encoding, also called Latin-7: Baltic Rim. It is an 8-bit superset of ASCII containing all characters necesary to represent Baltic Rim languages, as previous character sets were incomplete." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
HELP: latin8
|
||||
{ $description "This is the ISO-8859-14 encoding, also called Latin-8: Celtic. It is an 8-bit superset of ASCII designed for Celtic languages like Gaelic and Breton." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
HELP: latin9
|
||||
{ $description "This is the ISO-8859-15 encoding, also called Latin-9 and unoffically as Latin-0. It is an 8-bit superset of ASCII designed as a modification of Latin-1, removing little-used characters in favor of the Euro symbol and other characters." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
HELP: latin10
|
||||
{ $description "This is the ISO-8859-16 encoding, also called Latin-10: South-Eastern European. It is an 8-bit superset of ASCII." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
HELP: windows-1252
|
||||
{ $description "Windows 1252 is an 8-bit superset of ASCII which is closely related to Latin-1. Control characters in the 0x80 to 0x9F range are replaced with printable characters such as the Euro symbol." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
HELP: ebcdic
|
||||
{ $description "EBCDIC is an 8-bit legacy encoding designed for IBM mainframes like System/360 in the 1960s. It has since fallen into disuse. It contains large unallocated regions, and the version included here (code page 37) contains auxiliary characters in this region for English- and Portugese-speaking countries." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
HELP: mac-roman
|
||||
{ $description "Mac Roman is an 8-bit superset of ASCII which was the standard encoding on Mac OS prior to version 10. It is incompatible with Latin-1 in all but a few places and ASCII, and it is suitable for encoding many Western European languages." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
HELP: koi8-r
|
||||
{ $description "KOI8-R is an 8-bit superset of ASCII which encodes the Cyrillic alphabet, as used in Russian and Bulgarian. Characters are in such an order that, if the eight bit is stripped, text is still interpretable as ASCII. Block-building characters also exist." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
|
|
|||
|
|
@ -1,5 +1,6 @@
|
|||
USING: io.encodings.string io.encodings.8-bit
|
||||
io.encodings.8-bit.private tools.test strings arrays ;
|
||||
io.encodings.8-bit.private tools.test strings arrays
|
||||
io.encodings.8-bit.latin1 io.encodings.8-bit.windows-1252 ;
|
||||
IN: io.encodings.8-bit.tests
|
||||
|
||||
[ B{ CHAR: f CHAR: o CHAR: o } ] [ "foo" latin1 encode ] unit-test
|
||||
|
|
|
|||
|
|
@ -1,42 +1,19 @@
|
|||
! Copyright (C) 2008 Daniel Ehrenberg
|
||||
! Copyright (C) 2008 Daniel Ehrenberg, Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: math.parser arrays io.encodings sequences kernel assocs
|
||||
hashtables io.encodings.ascii generic parser classes.tuple words
|
||||
words.symbol io io.files splitting namespaces math
|
||||
compiler.units accessors classes.singleton classes.mixin
|
||||
io.encodings.iana fry simple-flat-file ;
|
||||
io.encodings.iana fry simple-flat-file lexer ;
|
||||
IN: io.encodings.8-bit
|
||||
|
||||
<PRIVATE
|
||||
|
||||
CONSTANT: mappings {
|
||||
! encoding-name iana-name file-name
|
||||
{ "latin1" "ISO_8859-1:1987" "8859-1" }
|
||||
{ "latin2" "ISO_8859-2:1987" "8859-2" }
|
||||
{ "latin3" "ISO_8859-3:1988" "8859-3" }
|
||||
{ "latin4" "ISO_8859-4:1988" "8859-4" }
|
||||
{ "latin/cyrillic" "ISO_8859-5:1988" "8859-5" }
|
||||
{ "latin/arabic" "ISO_8859-6:1987" "8859-6" }
|
||||
{ "latin/greek" "ISO_8859-7:1987" "8859-7" }
|
||||
{ "latin/hebrew" "ISO_8859-8:1988" "8859-8" }
|
||||
{ "latin5" "ISO_8859-9:1989" "8859-9" }
|
||||
{ "latin6" "ISO-8859-10" "8859-10" }
|
||||
{ "latin/thai" "TIS-620" "8859-11" }
|
||||
{ "latin7" "ISO-8859-13" "8859-13" }
|
||||
{ "latin8" "ISO-8859-14" "8859-14" }
|
||||
{ "latin9" "ISO-8859-15" "8859-15" }
|
||||
{ "latin10" "ISO-8859-16" "8859-16" }
|
||||
{ "koi8-r" "KOI8-R" "KOI8-R" }
|
||||
{ "windows-1250" "windows-1250" "CP1250" }
|
||||
{ "windows-1252" "windows-1252" "CP1252" }
|
||||
{ "ebcdic" "IBM037" "CP037" }
|
||||
{ "mac-roman" "macintosh" "ROMAN" }
|
||||
}
|
||||
|
||||
: encoding-file ( file-name -- stream )
|
||||
"vocab:io/encodings/8-bit/" ".TXT" surround ;
|
||||
|
||||
SYMBOL: 8-bit-encodings
|
||||
8-bit-encodings [ H{ } clone ] initialize
|
||||
|
||||
TUPLE: 8-bit biassoc ;
|
||||
|
||||
|
|
@ -62,20 +39,17 @@ M: 8-bit-encoding <decoder>
|
|||
8-bit-encodings get-global at <decoder> ;
|
||||
|
||||
: create-encoding ( name -- word )
|
||||
"io.encodings.8-bit" create
|
||||
create-in
|
||||
[ define-singleton-class ]
|
||||
[ 8-bit-encoding add-mixin-instance ]
|
||||
[ ] tri ;
|
||||
|
||||
: load-encoding ( name iana-name file-name -- )
|
||||
[ create-encoding dup ]
|
||||
[ register-encoding ]
|
||||
[ encoding-file flat-file>biassoc 8-bit boa ] tri*
|
||||
swap 8-bit-encodings get-global set-at ;
|
||||
|
||||
PRIVATE>
|
||||
|
||||
[
|
||||
mappings [
|
||||
first3
|
||||
[ create-encoding ]
|
||||
[ dupd register-encoding ]
|
||||
[ encoding-file flat-file>biassoc 8-bit boa ]
|
||||
tri*
|
||||
] H{ } map>assoc
|
||||
8-bit-encodings set-global
|
||||
] with-compilation-unit
|
||||
SYNTAX: 8-BIT: scan scan scan load-encoding ;
|
||||
|
|
|
|||
|
|
@ -0,0 +1,274 @@
|
|||
#
|
||||
# Name: cp1251 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 cp1251 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 cp1251 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 0x0402 #CYRILLIC CAPITAL LETTER DJE
|
||||
0x81 0x0403 #CYRILLIC CAPITAL LETTER GJE
|
||||
0x82 0x201A #SINGLE LOW-9 QUOTATION MARK
|
||||
0x83 0x0453 #CYRILLIC SMALL LETTER GJE
|
||||
0x84 0x201E #DOUBLE LOW-9 QUOTATION MARK
|
||||
0x85 0x2026 #HORIZONTAL ELLIPSIS
|
||||
0x86 0x2020 #DAGGER
|
||||
0x87 0x2021 #DOUBLE DAGGER
|
||||
0x88 0x20AC #EURO SIGN
|
||||
0x89 0x2030 #PER MILLE SIGN
|
||||
0x8A 0x0409 #CYRILLIC CAPITAL LETTER LJE
|
||||
0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK
|
||||
0x8C 0x040A #CYRILLIC CAPITAL LETTER NJE
|
||||
0x8D 0x040C #CYRILLIC CAPITAL LETTER KJE
|
||||
0x8E 0x040B #CYRILLIC CAPITAL LETTER TSHE
|
||||
0x8F 0x040F #CYRILLIC CAPITAL LETTER DZHE
|
||||
0x90 0x0452 #CYRILLIC SMALL LETTER DJE
|
||||
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 0x0459 #CYRILLIC SMALL LETTER LJE
|
||||
0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
|
||||
0x9C 0x045A #CYRILLIC SMALL LETTER NJE
|
||||
0x9D 0x045C #CYRILLIC SMALL LETTER KJE
|
||||
0x9E 0x045B #CYRILLIC SMALL LETTER TSHE
|
||||
0x9F 0x045F #CYRILLIC SMALL LETTER DZHE
|
||||
0xA0 0x00A0 #NO-BREAK SPACE
|
||||
0xA1 0x040E #CYRILLIC CAPITAL LETTER SHORT U
|
||||
0xA2 0x045E #CYRILLIC SMALL LETTER SHORT U
|
||||
0xA3 0x0408 #CYRILLIC CAPITAL LETTER JE
|
||||
0xA4 0x00A4 #CURRENCY SIGN
|
||||
0xA5 0x0490 #CYRILLIC CAPITAL LETTER GHE WITH UPTURN
|
||||
0xA6 0x00A6 #BROKEN BAR
|
||||
0xA7 0x00A7 #SECTION SIGN
|
||||
0xA8 0x0401 #CYRILLIC CAPITAL LETTER IO
|
||||
0xA9 0x00A9 #COPYRIGHT SIGN
|
||||
0xAA 0x0404 #CYRILLIC CAPITAL LETTER UKRAINIAN IE
|
||||
0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xAC 0x00AC #NOT SIGN
|
||||
0xAD 0x00AD #SOFT HYPHEN
|
||||
0xAE 0x00AE #REGISTERED SIGN
|
||||
0xAF 0x0407 #CYRILLIC CAPITAL LETTER YI
|
||||
0xB0 0x00B0 #DEGREE SIGN
|
||||
0xB1 0x00B1 #PLUS-MINUS SIGN
|
||||
0xB2 0x0406 #CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
|
||||
0xB3 0x0456 #CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
|
||||
0xB4 0x0491 #CYRILLIC SMALL LETTER GHE WITH UPTURN
|
||||
0xB5 0x00B5 #MICRO SIGN
|
||||
0xB6 0x00B6 #PILCROW SIGN
|
||||
0xB7 0x00B7 #MIDDLE DOT
|
||||
0xB8 0x0451 #CYRILLIC SMALL LETTER IO
|
||||
0xB9 0x2116 #NUMERO SIGN
|
||||
0xBA 0x0454 #CYRILLIC SMALL LETTER UKRAINIAN IE
|
||||
0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xBC 0x0458 #CYRILLIC SMALL LETTER JE
|
||||
0xBD 0x0405 #CYRILLIC CAPITAL LETTER DZE
|
||||
0xBE 0x0455 #CYRILLIC SMALL LETTER DZE
|
||||
0xBF 0x0457 #CYRILLIC SMALL LETTER YI
|
||||
0xC0 0x0410 #CYRILLIC CAPITAL LETTER A
|
||||
0xC1 0x0411 #CYRILLIC CAPITAL LETTER BE
|
||||
0xC2 0x0412 #CYRILLIC CAPITAL LETTER VE
|
||||
0xC3 0x0413 #CYRILLIC CAPITAL LETTER GHE
|
||||
0xC4 0x0414 #CYRILLIC CAPITAL LETTER DE
|
||||
0xC5 0x0415 #CYRILLIC CAPITAL LETTER IE
|
||||
0xC6 0x0416 #CYRILLIC CAPITAL LETTER ZHE
|
||||
0xC7 0x0417 #CYRILLIC CAPITAL LETTER ZE
|
||||
0xC8 0x0418 #CYRILLIC CAPITAL LETTER I
|
||||
0xC9 0x0419 #CYRILLIC CAPITAL LETTER SHORT I
|
||||
0xCA 0x041A #CYRILLIC CAPITAL LETTER KA
|
||||
0xCB 0x041B #CYRILLIC CAPITAL LETTER EL
|
||||
0xCC 0x041C #CYRILLIC CAPITAL LETTER EM
|
||||
0xCD 0x041D #CYRILLIC CAPITAL LETTER EN
|
||||
0xCE 0x041E #CYRILLIC CAPITAL LETTER O
|
||||
0xCF 0x041F #CYRILLIC CAPITAL LETTER PE
|
||||
0xD0 0x0420 #CYRILLIC CAPITAL LETTER ER
|
||||
0xD1 0x0421 #CYRILLIC CAPITAL LETTER ES
|
||||
0xD2 0x0422 #CYRILLIC CAPITAL LETTER TE
|
||||
0xD3 0x0423 #CYRILLIC CAPITAL LETTER U
|
||||
0xD4 0x0424 #CYRILLIC CAPITAL LETTER EF
|
||||
0xD5 0x0425 #CYRILLIC CAPITAL LETTER HA
|
||||
0xD6 0x0426 #CYRILLIC CAPITAL LETTER TSE
|
||||
0xD7 0x0427 #CYRILLIC CAPITAL LETTER CHE
|
||||
0xD8 0x0428 #CYRILLIC CAPITAL LETTER SHA
|
||||
0xD9 0x0429 #CYRILLIC CAPITAL LETTER SHCHA
|
||||
0xDA 0x042A #CYRILLIC CAPITAL LETTER HARD SIGN
|
||||
0xDB 0x042B #CYRILLIC CAPITAL LETTER YERU
|
||||
0xDC 0x042C #CYRILLIC CAPITAL LETTER SOFT SIGN
|
||||
0xDD 0x042D #CYRILLIC CAPITAL LETTER E
|
||||
0xDE 0x042E #CYRILLIC CAPITAL LETTER YU
|
||||
0xDF 0x042F #CYRILLIC CAPITAL LETTER YA
|
||||
0xE0 0x0430 #CYRILLIC SMALL LETTER A
|
||||
0xE1 0x0431 #CYRILLIC SMALL LETTER BE
|
||||
0xE2 0x0432 #CYRILLIC SMALL LETTER VE
|
||||
0xE3 0x0433 #CYRILLIC SMALL LETTER GHE
|
||||
0xE4 0x0434 #CYRILLIC SMALL LETTER DE
|
||||
0xE5 0x0435 #CYRILLIC SMALL LETTER IE
|
||||
0xE6 0x0436 #CYRILLIC SMALL LETTER ZHE
|
||||
0xE7 0x0437 #CYRILLIC SMALL LETTER ZE
|
||||
0xE8 0x0438 #CYRILLIC SMALL LETTER I
|
||||
0xE9 0x0439 #CYRILLIC SMALL LETTER SHORT I
|
||||
0xEA 0x043A #CYRILLIC SMALL LETTER KA
|
||||
0xEB 0x043B #CYRILLIC SMALL LETTER EL
|
||||
0xEC 0x043C #CYRILLIC SMALL LETTER EM
|
||||
0xED 0x043D #CYRILLIC SMALL LETTER EN
|
||||
0xEE 0x043E #CYRILLIC SMALL LETTER O
|
||||
0xEF 0x043F #CYRILLIC SMALL LETTER PE
|
||||
0xF0 0x0440 #CYRILLIC SMALL LETTER ER
|
||||
0xF1 0x0441 #CYRILLIC SMALL LETTER ES
|
||||
0xF2 0x0442 #CYRILLIC SMALL LETTER TE
|
||||
0xF3 0x0443 #CYRILLIC SMALL LETTER U
|
||||
0xF4 0x0444 #CYRILLIC SMALL LETTER EF
|
||||
0xF5 0x0445 #CYRILLIC SMALL LETTER HA
|
||||
0xF6 0x0446 #CYRILLIC SMALL LETTER TSE
|
||||
0xF7 0x0447 #CYRILLIC SMALL LETTER CHE
|
||||
0xF8 0x0448 #CYRILLIC SMALL LETTER SHA
|
||||
0xF9 0x0449 #CYRILLIC SMALL LETTER SHCHA
|
||||
0xFA 0x044A #CYRILLIC SMALL LETTER HARD SIGN
|
||||
0xFB 0x044B #CYRILLIC SMALL LETTER YERU
|
||||
0xFC 0x044C #CYRILLIC SMALL LETTER SOFT SIGN
|
||||
0xFD 0x044D #CYRILLIC SMALL LETTER E
|
||||
0xFE 0x044E #CYRILLIC SMALL LETTER YU
|
||||
0xFF 0x044F #CYRILLIC SMALL LETTER YA
|
||||
|
|
@ -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
|
||||
|
|
@ -0,0 +1,274 @@
|
|||
#
|
||||
# Name: cp1254 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 cp1254 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 cp1254 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 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT
|
||||
0x89 0x2030 #PER MILLE SIGN
|
||||
0x8A 0x0160 #LATIN CAPITAL LETTER S WITH CARON
|
||||
0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK
|
||||
0x8C 0x0152 #LATIN CAPITAL LIGATURE OE
|
||||
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 0x02DC #SMALL TILDE
|
||||
0x99 0x2122 #TRADE MARK SIGN
|
||||
0x9A 0x0161 #LATIN SMALL LETTER S WITH CARON
|
||||
0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
|
||||
0x9C 0x0153 #LATIN SMALL LIGATURE OE
|
||||
0x9D #UNDEFINED
|
||||
0x9E #UNDEFINED
|
||||
0x9F 0x0178 #LATIN CAPITAL LETTER Y WITH DIAERESIS
|
||||
0xA0 0x00A0 #NO-BREAK SPACE
|
||||
0xA1 0x00A1 #INVERTED EXCLAMATION MARK
|
||||
0xA2 0x00A2 #CENT SIGN
|
||||
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 0x00AA #FEMININE ORDINAL INDICATOR
|
||||
0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xAC 0x00AC #NOT SIGN
|
||||
0xAD 0x00AD #SOFT HYPHEN
|
||||
0xAE 0x00AE #REGISTERED SIGN
|
||||
0xAF 0x00AF #MACRON
|
||||
0xB0 0x00B0 #DEGREE SIGN
|
||||
0xB1 0x00B1 #PLUS-MINUS SIGN
|
||||
0xB2 0x00B2 #SUPERSCRIPT TWO
|
||||
0xB3 0x00B3 #SUPERSCRIPT THREE
|
||||
0xB4 0x00B4 #ACUTE ACCENT
|
||||
0xB5 0x00B5 #MICRO SIGN
|
||||
0xB6 0x00B6 #PILCROW SIGN
|
||||
0xB7 0x00B7 #MIDDLE DOT
|
||||
0xB8 0x00B8 #CEDILLA
|
||||
0xB9 0x00B9 #SUPERSCRIPT ONE
|
||||
0xBA 0x00BA #MASCULINE ORDINAL INDICATOR
|
||||
0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xBC 0x00BC #VULGAR FRACTION ONE QUARTER
|
||||
0xBD 0x00BD #VULGAR FRACTION ONE HALF
|
||||
0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS
|
||||
0xBF 0x00BF #INVERTED QUESTION MARK
|
||||
0xC0 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE
|
||||
0xC1 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0xC2 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0xC3 0x00C3 #LATIN CAPITAL LETTER A WITH TILDE
|
||||
0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0xC5 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0xC6 0x00C6 #LATIN CAPITAL LETTER AE
|
||||
0xC7 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0xC8 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE
|
||||
0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0xCA 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
0xCB 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
0xCC 0x00CC #LATIN CAPITAL LETTER I WITH GRAVE
|
||||
0xCD 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0xCE 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
0xCF 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
0xD0 0x011E #LATIN CAPITAL LETTER G WITH BREVE
|
||||
0xD1 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE
|
||||
0xD2 0x00D2 #LATIN CAPITAL LETTER O WITH GRAVE
|
||||
0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0xD4 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0xD5 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE
|
||||
0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0xD7 0x00D7 #MULTIPLICATION SIGN
|
||||
0xD8 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE
|
||||
0xD9 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE
|
||||
0xDA 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0xDB 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0xDD 0x0130 #LATIN CAPITAL LETTER I WITH DOT ABOVE
|
||||
0xDE 0x015E #LATIN CAPITAL LETTER S WITH CEDILLA
|
||||
0xDF 0x00DF #LATIN SMALL LETTER SHARP S
|
||||
0xE0 0x00E0 #LATIN SMALL LETTER A WITH GRAVE
|
||||
0xE1 0x00E1 #LATIN SMALL LETTER A WITH ACUTE
|
||||
0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0xE3 0x00E3 #LATIN SMALL LETTER A WITH TILDE
|
||||
0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0xE5 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0xE6 0x00E6 #LATIN SMALL LETTER AE
|
||||
0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA
|
||||
0xE8 0x00E8 #LATIN SMALL LETTER E WITH GRAVE
|
||||
0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE
|
||||
0xEA 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0xEC 0x00EC #LATIN SMALL LETTER I WITH GRAVE
|
||||
0xED 0x00ED #LATIN SMALL LETTER I WITH ACUTE
|
||||
0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0xEF 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS
|
||||
0xF0 0x011F #LATIN SMALL LETTER G WITH BREVE
|
||||
0xF1 0x00F1 #LATIN SMALL LETTER N WITH TILDE
|
||||
0xF2 0x00F2 #LATIN SMALL LETTER O WITH GRAVE
|
||||
0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE
|
||||
0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0xF5 0x00F5 #LATIN SMALL LETTER O WITH TILDE
|
||||
0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0xF7 0x00F7 #DIVISION SIGN
|
||||
0xF8 0x00F8 #LATIN SMALL LETTER O WITH STROKE
|
||||
0xF9 0x00F9 #LATIN SMALL LETTER U WITH GRAVE
|
||||
0xFA 0x00FA #LATIN SMALL LETTER U WITH ACUTE
|
||||
0xFB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0xFD 0x0131 #LATIN SMALL LETTER DOTLESS I
|
||||
0xFE 0x015F #LATIN SMALL LETTER S WITH CEDILLA
|
||||
0xFF 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
|
|
@ -0,0 +1,274 @@
|
|||
#
|
||||
# Name: cp1255 to Unicode table
|
||||
# Unicode version: 2.0
|
||||
# Table version: 2.01
|
||||
# Table format: Format A
|
||||
# Date: 1/7/2000
|
||||
#
|
||||
# Contact: Shawn.Steele@microsoft.com
|
||||
#
|
||||
# General notes: none
|
||||
#
|
||||
# Format: Three tab-separated columns
|
||||
# Column #1 is the cp1255 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 cp1255 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 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT
|
||||
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 0x02DC #SMALL TILDE
|
||||
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 0x00A1 #INVERTED EXCLAMATION MARK
|
||||
0xA2 0x00A2 #CENT SIGN
|
||||
0xA3 0x00A3 #POUND SIGN
|
||||
0xA4 0x20AA #NEW SHEQEL SIGN
|
||||
0xA5 0x00A5 #YEN SIGN
|
||||
0xA6 0x00A6 #BROKEN BAR
|
||||
0xA7 0x00A7 #SECTION SIGN
|
||||
0xA8 0x00A8 #DIAERESIS
|
||||
0xA9 0x00A9 #COPYRIGHT SIGN
|
||||
0xAA 0x00D7 #MULTIPLICATION SIGN
|
||||
0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xAC 0x00AC #NOT SIGN
|
||||
0xAD 0x00AD #SOFT HYPHEN
|
||||
0xAE 0x00AE #REGISTERED SIGN
|
||||
0xAF 0x00AF #MACRON
|
||||
0xB0 0x00B0 #DEGREE SIGN
|
||||
0xB1 0x00B1 #PLUS-MINUS SIGN
|
||||
0xB2 0x00B2 #SUPERSCRIPT TWO
|
||||
0xB3 0x00B3 #SUPERSCRIPT THREE
|
||||
0xB4 0x00B4 #ACUTE ACCENT
|
||||
0xB5 0x00B5 #MICRO SIGN
|
||||
0xB6 0x00B6 #PILCROW SIGN
|
||||
0xB7 0x00B7 #MIDDLE DOT
|
||||
0xB8 0x00B8 #CEDILLA
|
||||
0xB9 0x00B9 #SUPERSCRIPT ONE
|
||||
0xBA 0x00F7 #DIVISION SIGN
|
||||
0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xBC 0x00BC #VULGAR FRACTION ONE QUARTER
|
||||
0xBD 0x00BD #VULGAR FRACTION ONE HALF
|
||||
0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS
|
||||
0xBF 0x00BF #INVERTED QUESTION MARK
|
||||
0xC0 0x05B0 #HEBREW POINT SHEVA
|
||||
0xC1 0x05B1 #HEBREW POINT HATAF SEGOL
|
||||
0xC2 0x05B2 #HEBREW POINT HATAF PATAH
|
||||
0xC3 0x05B3 #HEBREW POINT HATAF QAMATS
|
||||
0xC4 0x05B4 #HEBREW POINT HIRIQ
|
||||
0xC5 0x05B5 #HEBREW POINT TSERE
|
||||
0xC6 0x05B6 #HEBREW POINT SEGOL
|
||||
0xC7 0x05B7 #HEBREW POINT PATAH
|
||||
0xC8 0x05B8 #HEBREW POINT QAMATS
|
||||
0xC9 0x05B9 #HEBREW POINT HOLAM
|
||||
0xCA #UNDEFINED
|
||||
0xCB 0x05BB #HEBREW POINT QUBUTS
|
||||
0xCC 0x05BC #HEBREW POINT DAGESH OR MAPIQ
|
||||
0xCD 0x05BD #HEBREW POINT METEG
|
||||
0xCE 0x05BE #HEBREW PUNCTUATION MAQAF
|
||||
0xCF 0x05BF #HEBREW POINT RAFE
|
||||
0xD0 0x05C0 #HEBREW PUNCTUATION PASEQ
|
||||
0xD1 0x05C1 #HEBREW POINT SHIN DOT
|
||||
0xD2 0x05C2 #HEBREW POINT SIN DOT
|
||||
0xD3 0x05C3 #HEBREW PUNCTUATION SOF PASUQ
|
||||
0xD4 0x05F0 #HEBREW LIGATURE YIDDISH DOUBLE VAV
|
||||
0xD5 0x05F1 #HEBREW LIGATURE YIDDISH VAV YOD
|
||||
0xD6 0x05F2 #HEBREW LIGATURE YIDDISH DOUBLE YOD
|
||||
0xD7 0x05F3 #HEBREW PUNCTUATION GERESH
|
||||
0xD8 0x05F4 #HEBREW PUNCTUATION GERSHAYIM
|
||||
0xD9 #UNDEFINED
|
||||
0xDA #UNDEFINED
|
||||
0xDB #UNDEFINED
|
||||
0xDC #UNDEFINED
|
||||
0xDD #UNDEFINED
|
||||
0xDE #UNDEFINED
|
||||
0xDF #UNDEFINED
|
||||
0xE0 0x05D0 #HEBREW LETTER ALEF
|
||||
0xE1 0x05D1 #HEBREW LETTER BET
|
||||
0xE2 0x05D2 #HEBREW LETTER GIMEL
|
||||
0xE3 0x05D3 #HEBREW LETTER DALET
|
||||
0xE4 0x05D4 #HEBREW LETTER HE
|
||||
0xE5 0x05D5 #HEBREW LETTER VAV
|
||||
0xE6 0x05D6 #HEBREW LETTER ZAYIN
|
||||
0xE7 0x05D7 #HEBREW LETTER HET
|
||||
0xE8 0x05D8 #HEBREW LETTER TET
|
||||
0xE9 0x05D9 #HEBREW LETTER YOD
|
||||
0xEA 0x05DA #HEBREW LETTER FINAL KAF
|
||||
0xEB 0x05DB #HEBREW LETTER KAF
|
||||
0xEC 0x05DC #HEBREW LETTER LAMED
|
||||
0xED 0x05DD #HEBREW LETTER FINAL MEM
|
||||
0xEE 0x05DE #HEBREW LETTER MEM
|
||||
0xEF 0x05DF #HEBREW LETTER FINAL NUN
|
||||
0xF0 0x05E0 #HEBREW LETTER NUN
|
||||
0xF1 0x05E1 #HEBREW LETTER SAMEKH
|
||||
0xF2 0x05E2 #HEBREW LETTER AYIN
|
||||
0xF3 0x05E3 #HEBREW LETTER FINAL PE
|
||||
0xF4 0x05E4 #HEBREW LETTER PE
|
||||
0xF5 0x05E5 #HEBREW LETTER FINAL TSADI
|
||||
0xF6 0x05E6 #HEBREW LETTER TSADI
|
||||
0xF7 0x05E7 #HEBREW LETTER QOF
|
||||
0xF8 0x05E8 #HEBREW LETTER RESH
|
||||
0xF9 0x05E9 #HEBREW LETTER SHIN
|
||||
0xFA 0x05EA #HEBREW LETTER TAV
|
||||
0xFB #UNDEFINED
|
||||
0xFC #UNDEFINED
|
||||
0xFD 0x200E #LEFT-TO-RIGHT MARK
|
||||
0xFE 0x200F #RIGHT-TO-LEFT MARK
|
||||
0xFF #UNDEFINED
|
||||
|
|
@ -0,0 +1,274 @@
|
|||
#
|
||||
# Name: cp1256 to Unicode table
|
||||
# Unicode version: 2.1
|
||||
# Table version: 2.01
|
||||
# Table format: Format A
|
||||
# Date: 01/5/99
|
||||
#
|
||||
# Contact: Shawn.Steele@microsoft.com
|
||||
#
|
||||
# General notes: none
|
||||
#
|
||||
# Format: Three tab-separated columns
|
||||
# Column #1 is the cp1256 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 cp1256 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 0x067E #ARABIC LETTER PEH
|
||||
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 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT
|
||||
0x89 0x2030 #PER MILLE SIGN
|
||||
0x8A 0x0679 #ARABIC LETTER TTEH
|
||||
0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK
|
||||
0x8C 0x0152 #LATIN CAPITAL LIGATURE OE
|
||||
0x8D 0x0686 #ARABIC LETTER TCHEH
|
||||
0x8E 0x0698 #ARABIC LETTER JEH
|
||||
0x8F 0x0688 #ARABIC LETTER DDAL
|
||||
0x90 0x06AF #ARABIC LETTER GAF
|
||||
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 0x06A9 #ARABIC LETTER KEHEH
|
||||
0x99 0x2122 #TRADE MARK SIGN
|
||||
0x9A 0x0691 #ARABIC LETTER RREH
|
||||
0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
|
||||
0x9C 0x0153 #LATIN SMALL LIGATURE OE
|
||||
0x9D 0x200C #ZERO WIDTH NON-JOINER
|
||||
0x9E 0x200D #ZERO WIDTH JOINER
|
||||
0x9F 0x06BA #ARABIC LETTER NOON GHUNNA
|
||||
0xA0 0x00A0 #NO-BREAK SPACE
|
||||
0xA1 0x060C #ARABIC COMMA
|
||||
0xA2 0x00A2 #CENT SIGN
|
||||
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 0x06BE #ARABIC LETTER HEH DOACHASHMEE
|
||||
0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xAC 0x00AC #NOT SIGN
|
||||
0xAD 0x00AD #SOFT HYPHEN
|
||||
0xAE 0x00AE #REGISTERED SIGN
|
||||
0xAF 0x00AF #MACRON
|
||||
0xB0 0x00B0 #DEGREE SIGN
|
||||
0xB1 0x00B1 #PLUS-MINUS SIGN
|
||||
0xB2 0x00B2 #SUPERSCRIPT TWO
|
||||
0xB3 0x00B3 #SUPERSCRIPT THREE
|
||||
0xB4 0x00B4 #ACUTE ACCENT
|
||||
0xB5 0x00B5 #MICRO SIGN
|
||||
0xB6 0x00B6 #PILCROW SIGN
|
||||
0xB7 0x00B7 #MIDDLE DOT
|
||||
0xB8 0x00B8 #CEDILLA
|
||||
0xB9 0x00B9 #SUPERSCRIPT ONE
|
||||
0xBA 0x061B #ARABIC SEMICOLON
|
||||
0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xBC 0x00BC #VULGAR FRACTION ONE QUARTER
|
||||
0xBD 0x00BD #VULGAR FRACTION ONE HALF
|
||||
0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS
|
||||
0xBF 0x061F #ARABIC QUESTION MARK
|
||||
0xC0 0x06C1 #ARABIC LETTER HEH GOAL
|
||||
0xC1 0x0621 #ARABIC LETTER HAMZA
|
||||
0xC2 0x0622 #ARABIC LETTER ALEF WITH MADDA ABOVE
|
||||
0xC3 0x0623 #ARABIC LETTER ALEF WITH HAMZA ABOVE
|
||||
0xC4 0x0624 #ARABIC LETTER WAW WITH HAMZA ABOVE
|
||||
0xC5 0x0625 #ARABIC LETTER ALEF WITH HAMZA BELOW
|
||||
0xC6 0x0626 #ARABIC LETTER YEH WITH HAMZA ABOVE
|
||||
0xC7 0x0627 #ARABIC LETTER ALEF
|
||||
0xC8 0x0628 #ARABIC LETTER BEH
|
||||
0xC9 0x0629 #ARABIC LETTER TEH MARBUTA
|
||||
0xCA 0x062A #ARABIC LETTER TEH
|
||||
0xCB 0x062B #ARABIC LETTER THEH
|
||||
0xCC 0x062C #ARABIC LETTER JEEM
|
||||
0xCD 0x062D #ARABIC LETTER HAH
|
||||
0xCE 0x062E #ARABIC LETTER KHAH
|
||||
0xCF 0x062F #ARABIC LETTER DAL
|
||||
0xD0 0x0630 #ARABIC LETTER THAL
|
||||
0xD1 0x0631 #ARABIC LETTER REH
|
||||
0xD2 0x0632 #ARABIC LETTER ZAIN
|
||||
0xD3 0x0633 #ARABIC LETTER SEEN
|
||||
0xD4 0x0634 #ARABIC LETTER SHEEN
|
||||
0xD5 0x0635 #ARABIC LETTER SAD
|
||||
0xD6 0x0636 #ARABIC LETTER DAD
|
||||
0xD7 0x00D7 #MULTIPLICATION SIGN
|
||||
0xD8 0x0637 #ARABIC LETTER TAH
|
||||
0xD9 0x0638 #ARABIC LETTER ZAH
|
||||
0xDA 0x0639 #ARABIC LETTER AIN
|
||||
0xDB 0x063A #ARABIC LETTER GHAIN
|
||||
0xDC 0x0640 #ARABIC TATWEEL
|
||||
0xDD 0x0641 #ARABIC LETTER FEH
|
||||
0xDE 0x0642 #ARABIC LETTER QAF
|
||||
0xDF 0x0643 #ARABIC LETTER KAF
|
||||
0xE0 0x00E0 #LATIN SMALL LETTER A WITH GRAVE
|
||||
0xE1 0x0644 #ARABIC LETTER LAM
|
||||
0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0xE3 0x0645 #ARABIC LETTER MEEM
|
||||
0xE4 0x0646 #ARABIC LETTER NOON
|
||||
0xE5 0x0647 #ARABIC LETTER HEH
|
||||
0xE6 0x0648 #ARABIC LETTER WAW
|
||||
0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA
|
||||
0xE8 0x00E8 #LATIN SMALL LETTER E WITH GRAVE
|
||||
0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE
|
||||
0xEA 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0xEC 0x0649 #ARABIC LETTER ALEF MAKSURA
|
||||
0xED 0x064A #ARABIC LETTER YEH
|
||||
0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0xEF 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS
|
||||
0xF0 0x064B #ARABIC FATHATAN
|
||||
0xF1 0x064C #ARABIC DAMMATAN
|
||||
0xF2 0x064D #ARABIC KASRATAN
|
||||
0xF3 0x064E #ARABIC FATHA
|
||||
0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0xF5 0x064F #ARABIC DAMMA
|
||||
0xF6 0x0650 #ARABIC KASRA
|
||||
0xF7 0x00F7 #DIVISION SIGN
|
||||
0xF8 0x0651 #ARABIC SHADDA
|
||||
0xF9 0x00F9 #LATIN SMALL LETTER U WITH GRAVE
|
||||
0xFA 0x0652 #ARABIC SUKUN
|
||||
0xFB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0xFD 0x200E #LEFT-TO-RIGHT MARK
|
||||
0xFE 0x200F #RIGHT-TO-LEFT MARK
|
||||
0xFF 0x06D2 #ARABIC LETTER YEH BARREE
|
||||
|
|
@ -0,0 +1,274 @@
|
|||
#
|
||||
# Name: cp1257 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 cp1257 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 cp1257 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 #UNDEFINED
|
||||
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 0x00A8 #DIAERESIS
|
||||
0x8E 0x02C7 #CARON
|
||||
0x8F 0x00B8 #CEDILLA
|
||||
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 0x00AF #MACRON
|
||||
0x9E 0x02DB #OGONEK
|
||||
0x9F #UNDEFINED
|
||||
0xA0 0x00A0 #NO-BREAK SPACE
|
||||
0xA1 #UNDEFINED
|
||||
0xA2 0x00A2 #CENT SIGN
|
||||
0xA3 0x00A3 #POUND SIGN
|
||||
0xA4 0x00A4 #CURRENCY SIGN
|
||||
0xA5 #UNDEFINED
|
||||
0xA6 0x00A6 #BROKEN BAR
|
||||
0xA7 0x00A7 #SECTION SIGN
|
||||
0xA8 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE
|
||||
0xA9 0x00A9 #COPYRIGHT SIGN
|
||||
0xAA 0x0156 #LATIN CAPITAL LETTER R WITH CEDILLA
|
||||
0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xAC 0x00AC #NOT SIGN
|
||||
0xAD 0x00AD #SOFT HYPHEN
|
||||
0xAE 0x00AE #REGISTERED SIGN
|
||||
0xAF 0x00C6 #LATIN CAPITAL LETTER AE
|
||||
0xB0 0x00B0 #DEGREE SIGN
|
||||
0xB1 0x00B1 #PLUS-MINUS SIGN
|
||||
0xB2 0x00B2 #SUPERSCRIPT TWO
|
||||
0xB3 0x00B3 #SUPERSCRIPT THREE
|
||||
0xB4 0x00B4 #ACUTE ACCENT
|
||||
0xB5 0x00B5 #MICRO SIGN
|
||||
0xB6 0x00B6 #PILCROW SIGN
|
||||
0xB7 0x00B7 #MIDDLE DOT
|
||||
0xB8 0x00F8 #LATIN SMALL LETTER O WITH STROKE
|
||||
0xB9 0x00B9 #SUPERSCRIPT ONE
|
||||
0xBA 0x0157 #LATIN SMALL LETTER R WITH CEDILLA
|
||||
0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xBC 0x00BC #VULGAR FRACTION ONE QUARTER
|
||||
0xBD 0x00BD #VULGAR FRACTION ONE HALF
|
||||
0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS
|
||||
0xBF 0x00E6 #LATIN SMALL LETTER AE
|
||||
0xC0 0x0104 #LATIN CAPITAL LETTER A WITH OGONEK
|
||||
0xC1 0x012E #LATIN CAPITAL LETTER I WITH OGONEK
|
||||
0xC2 0x0100 #LATIN CAPITAL LETTER A WITH MACRON
|
||||
0xC3 0x0106 #LATIN CAPITAL LETTER C WITH ACUTE
|
||||
0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0xC5 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0xC6 0x0118 #LATIN CAPITAL LETTER E WITH OGONEK
|
||||
0xC7 0x0112 #LATIN CAPITAL LETTER E WITH MACRON
|
||||
0xC8 0x010C #LATIN CAPITAL LETTER C WITH CARON
|
||||
0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0xCA 0x0179 #LATIN CAPITAL LETTER Z WITH ACUTE
|
||||
0xCB 0x0116 #LATIN CAPITAL LETTER E WITH DOT ABOVE
|
||||
0xCC 0x0122 #LATIN CAPITAL LETTER G WITH CEDILLA
|
||||
0xCD 0x0136 #LATIN CAPITAL LETTER K WITH CEDILLA
|
||||
0xCE 0x012A #LATIN CAPITAL LETTER I WITH MACRON
|
||||
0xCF 0x013B #LATIN CAPITAL LETTER L WITH CEDILLA
|
||||
0xD0 0x0160 #LATIN CAPITAL LETTER S WITH CARON
|
||||
0xD1 0x0143 #LATIN CAPITAL LETTER N WITH ACUTE
|
||||
0xD2 0x0145 #LATIN CAPITAL LETTER N WITH CEDILLA
|
||||
0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0xD4 0x014C #LATIN CAPITAL LETTER O WITH MACRON
|
||||
0xD5 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE
|
||||
0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0xD7 0x00D7 #MULTIPLICATION SIGN
|
||||
0xD8 0x0172 #LATIN CAPITAL LETTER U WITH OGONEK
|
||||
0xD9 0x0141 #LATIN CAPITAL LETTER L WITH STROKE
|
||||
0xDA 0x015A #LATIN CAPITAL LETTER S WITH ACUTE
|
||||
0xDB 0x016A #LATIN CAPITAL LETTER U WITH MACRON
|
||||
0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0xDD 0x017B #LATIN CAPITAL LETTER Z WITH DOT ABOVE
|
||||
0xDE 0x017D #LATIN CAPITAL LETTER Z WITH CARON
|
||||
0xDF 0x00DF #LATIN SMALL LETTER SHARP S
|
||||
0xE0 0x0105 #LATIN SMALL LETTER A WITH OGONEK
|
||||
0xE1 0x012F #LATIN SMALL LETTER I WITH OGONEK
|
||||
0xE2 0x0101 #LATIN SMALL LETTER A WITH MACRON
|
||||
0xE3 0x0107 #LATIN SMALL LETTER C WITH ACUTE
|
||||
0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0xE5 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0xE6 0x0119 #LATIN SMALL LETTER E WITH OGONEK
|
||||
0xE7 0x0113 #LATIN SMALL LETTER E WITH MACRON
|
||||
0xE8 0x010D #LATIN SMALL LETTER C WITH CARON
|
||||
0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE
|
||||
0xEA 0x017A #LATIN SMALL LETTER Z WITH ACUTE
|
||||
0xEB 0x0117 #LATIN SMALL LETTER E WITH DOT ABOVE
|
||||
0xEC 0x0123 #LATIN SMALL LETTER G WITH CEDILLA
|
||||
0xED 0x0137 #LATIN SMALL LETTER K WITH CEDILLA
|
||||
0xEE 0x012B #LATIN SMALL LETTER I WITH MACRON
|
||||
0xEF 0x013C #LATIN SMALL LETTER L WITH CEDILLA
|
||||
0xF0 0x0161 #LATIN SMALL LETTER S WITH CARON
|
||||
0xF1 0x0144 #LATIN SMALL LETTER N WITH ACUTE
|
||||
0xF2 0x0146 #LATIN SMALL LETTER N WITH CEDILLA
|
||||
0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE
|
||||
0xF4 0x014D #LATIN SMALL LETTER O WITH MACRON
|
||||
0xF5 0x00F5 #LATIN SMALL LETTER O WITH TILDE
|
||||
0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0xF7 0x00F7 #DIVISION SIGN
|
||||
0xF8 0x0173 #LATIN SMALL LETTER U WITH OGONEK
|
||||
0xF9 0x0142 #LATIN SMALL LETTER L WITH STROKE
|
||||
0xFA 0x015B #LATIN SMALL LETTER S WITH ACUTE
|
||||
0xFB 0x016B #LATIN SMALL LETTER U WITH MACRON
|
||||
0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0xFD 0x017C #LATIN SMALL LETTER Z WITH DOT ABOVE
|
||||
0xFE 0x017E #LATIN SMALL LETTER Z WITH CARON
|
||||
0xFF 0x02D9 #DOT ABOVE
|
||||
|
|
@ -0,0 +1,274 @@
|
|||
#
|
||||
# Name: cp1258 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 cp1258 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 cp1258 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 0x02C6 #MODIFIER LETTER CIRCUMFLEX ACCENT
|
||||
0x89 0x2030 #PER MILLE SIGN
|
||||
0x8A #UNDEFINED
|
||||
0x8B 0x2039 #SINGLE LEFT-POINTING ANGLE QUOTATION MARK
|
||||
0x8C 0x0152 #LATIN CAPITAL LIGATURE OE
|
||||
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 0x02DC #SMALL TILDE
|
||||
0x99 0x2122 #TRADE MARK SIGN
|
||||
0x9A #UNDEFINED
|
||||
0x9B 0x203A #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
|
||||
0x9C 0x0153 #LATIN SMALL LIGATURE OE
|
||||
0x9D #UNDEFINED
|
||||
0x9E #UNDEFINED
|
||||
0x9F 0x0178 #LATIN CAPITAL LETTER Y WITH DIAERESIS
|
||||
0xA0 0x00A0 #NO-BREAK SPACE
|
||||
0xA1 0x00A1 #INVERTED EXCLAMATION MARK
|
||||
0xA2 0x00A2 #CENT SIGN
|
||||
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 0x00AA #FEMININE ORDINAL INDICATOR
|
||||
0xAB 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xAC 0x00AC #NOT SIGN
|
||||
0xAD 0x00AD #SOFT HYPHEN
|
||||
0xAE 0x00AE #REGISTERED SIGN
|
||||
0xAF 0x00AF #MACRON
|
||||
0xB0 0x00B0 #DEGREE SIGN
|
||||
0xB1 0x00B1 #PLUS-MINUS SIGN
|
||||
0xB2 0x00B2 #SUPERSCRIPT TWO
|
||||
0xB3 0x00B3 #SUPERSCRIPT THREE
|
||||
0xB4 0x00B4 #ACUTE ACCENT
|
||||
0xB5 0x00B5 #MICRO SIGN
|
||||
0xB6 0x00B6 #PILCROW SIGN
|
||||
0xB7 0x00B7 #MIDDLE DOT
|
||||
0xB8 0x00B8 #CEDILLA
|
||||
0xB9 0x00B9 #SUPERSCRIPT ONE
|
||||
0xBA 0x00BA #MASCULINE ORDINAL INDICATOR
|
||||
0xBB 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0xBC 0x00BC #VULGAR FRACTION ONE QUARTER
|
||||
0xBD 0x00BD #VULGAR FRACTION ONE HALF
|
||||
0xBE 0x00BE #VULGAR FRACTION THREE QUARTERS
|
||||
0xBF 0x00BF #INVERTED QUESTION MARK
|
||||
0xC0 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE
|
||||
0xC1 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0xC2 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0xC3 0x0102 #LATIN CAPITAL LETTER A WITH BREVE
|
||||
0xC4 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0xC5 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0xC6 0x00C6 #LATIN CAPITAL LETTER AE
|
||||
0xC7 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0xC8 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE
|
||||
0xC9 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0xCA 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
0xCB 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
0xCC 0x0300 #COMBINING GRAVE ACCENT
|
||||
0xCD 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0xCE 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
0xCF 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
0xD0 0x0110 #LATIN CAPITAL LETTER D WITH STROKE
|
||||
0xD1 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE
|
||||
0xD2 0x0309 #COMBINING HOOK ABOVE
|
||||
0xD3 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0xD4 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0xD5 0x01A0 #LATIN CAPITAL LETTER O WITH HORN
|
||||
0xD6 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0xD7 0x00D7 #MULTIPLICATION SIGN
|
||||
0xD8 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE
|
||||
0xD9 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE
|
||||
0xDA 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0xDB 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
0xDC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0xDD 0x01AF #LATIN CAPITAL LETTER U WITH HORN
|
||||
0xDE 0x0303 #COMBINING TILDE
|
||||
0xDF 0x00DF #LATIN SMALL LETTER SHARP S
|
||||
0xE0 0x00E0 #LATIN SMALL LETTER A WITH GRAVE
|
||||
0xE1 0x00E1 #LATIN SMALL LETTER A WITH ACUTE
|
||||
0xE2 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0xE3 0x0103 #LATIN SMALL LETTER A WITH BREVE
|
||||
0xE4 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0xE5 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0xE6 0x00E6 #LATIN SMALL LETTER AE
|
||||
0xE7 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA
|
||||
0xE8 0x00E8 #LATIN SMALL LETTER E WITH GRAVE
|
||||
0xE9 0x00E9 #LATIN SMALL LETTER E WITH ACUTE
|
||||
0xEA 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0xEB 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0xEC 0x0301 #COMBINING ACUTE ACCENT
|
||||
0xED 0x00ED #LATIN SMALL LETTER I WITH ACUTE
|
||||
0xEE 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0xEF 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS
|
||||
0xF0 0x0111 #LATIN SMALL LETTER D WITH STROKE
|
||||
0xF1 0x00F1 #LATIN SMALL LETTER N WITH TILDE
|
||||
0xF2 0x0323 #COMBINING DOT BELOW
|
||||
0xF3 0x00F3 #LATIN SMALL LETTER O WITH ACUTE
|
||||
0xF4 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0xF5 0x01A1 #LATIN SMALL LETTER O WITH HORN
|
||||
0xF6 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0xF7 0x00F7 #DIVISION SIGN
|
||||
0xF8 0x00F8 #LATIN SMALL LETTER O WITH STROKE
|
||||
0xF9 0x00F9 #LATIN SMALL LETTER U WITH GRAVE
|
||||
0xFA 0x00FA #LATIN SMALL LETTER U WITH ACUTE
|
||||
0xFB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0xFC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0xFD 0x01B0 #LATIN SMALL LETTER U WITH HORN
|
||||
0xFE 0x20AB #DONG SIGN
|
||||
0xFF 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: help.markup help.syntax ;
|
||||
IN: io.encodings.8-bit.arabic
|
||||
|
||||
HELP: latin/arabic
|
||||
{ $var-description "This is the ISO-8859-6 encoding, also called Latin/Arabic. It is an 8-bit superset of ASCII and provides the characters necessary for Arabic, though not other languages which use Arabic script." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
ARTICLE: "io.encodings.8-bit.arabic" "Arabic encoding"
|
||||
"The " { $vocab-link "io.encodings.8-bit.arabic" } " vocabulary provides the " { $link latin/arabic } " encoding." ;
|
||||
|
||||
ABOUT: "io.encodings.8-bit.arabic"
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: io.encodings.8-bit ;
|
||||
IN: io.encodings.8-bit.arabic
|
||||
|
||||
8-BIT: latin/arabic ISO_8859-6:1987 8859-6
|
||||
|
|
@ -0,0 +1 @@
|
|||
Doug Coleman
|
||||
|
|
@ -0,0 +1 @@
|
|||
Doug Coleman
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: help.markup help.syntax ;
|
||||
IN: io.encodings.8-bit.cyrillic
|
||||
|
||||
HELP: latin/cyrillic
|
||||
{ $var-description "This is the ISO-8859-5 encoding, also called Latin/Cyrillic. It is an 8-bit superset of ASCII and provides the characters necessary for most languages which use Cyrilic, including Russian, Macedonian, Belarusian, Bulgarian, Serbian, and Ukrainian. KOI8-R is used much more commonly." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
ARTICLE: "io.encodings.8-bit.cyrillic" "Cyrillic encoding"
|
||||
"The " { $vocab-link "io.encodings.8-bit.cyrillic" } " vocabulary provides the " { $link latin/cyrillic } " encoding." ;
|
||||
|
||||
ABOUT: "io.encodings.8-bit.cyrillic"
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: io.encodings.8-bit ;
|
||||
IN: io.encodings.8-bit.cyrillic
|
||||
|
||||
8-BIT: latin/cyrillic ISO_8859-5:1988 8859-5
|
||||
|
|
@ -0,0 +1 @@
|
|||
Doug Coleman
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: help.markup help.syntax ;
|
||||
IN: io.encodings.8-bit.ebcdic
|
||||
|
||||
HELP: ebcdic
|
||||
{ $var-description "EBCDIC is an 8-bit legacy encoding designed for IBM mainframes like System/360 in the 1960s. It has since fallen into disuse. It contains large unallocated regions, and the version included here (code page 37) contains auxiliary characters in this region for English- and Portugese-speaking countries." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
ARTICLE: "io.encodings.8-bit.ebcdic" "EBCDIC encoding"
|
||||
"The " { $vocab-link "io.encodings.8-bit.ebcdic" } " vocabulary provides the " { $link ebcdic } " encoding." ;
|
||||
|
||||
ABOUT: "io.encodings.8-bit.ebcdic"
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: io.encodings.8-bit ;
|
||||
IN: io.encodings.8-bit.ebcdic
|
||||
|
||||
8-BIT: ebcdic IBM037 CP037
|
||||
|
|
@ -0,0 +1 @@
|
|||
Doug Coleman
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: help.markup help.syntax ;
|
||||
IN: io.encodings.8-bit.greek
|
||||
|
||||
HELP: latin/greek
|
||||
{ $description "This is the ISO-8859-7 encoding, also called Latin/Greek. It is an 8-bit superset of ASCII and provides the characters necessary for Greek written in modern monotonic orthography, or ancient Greek without accent marks." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
ARTICLE: "io.encodings.8-bit.greek" "Greek encoding"
|
||||
"The " { $vocab-link "io.encodings.8-bit.greek" } " vocabulary provides the " { $link latin/greek } " encoding." ;
|
||||
|
||||
ABOUT: "io.encodings.8-bit.greek"
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: io.encodings.8-bit ;
|
||||
IN: io.encodings.8-bit.greek
|
||||
|
||||
8-BIT: latin/greek ISO_8859-7:1987 8859-7
|
||||
|
|
@ -0,0 +1 @@
|
|||
Doug Coleman
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: help.markup help.syntax ;
|
||||
IN: io.encodings.8-bit.hebrew
|
||||
|
||||
HELP: latin/hebrew
|
||||
{ $var-description "This is the ISO-8859-8 encoding, also called Latin/Hebrew. It is an 8-bit superset of ASCII and provides the characters necessary for modern Hebrew without explicit vowels. Generally, this is interpreted in logical order, making it ISO-8859-8-I, technically." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
ARTICLE: "io.encodings.8-bit.hebrew" "Hebrew encoding"
|
||||
"The " { $vocab-link "io.encodings.8-bit.hebrew" } " vocabulary provides the " { $link latin/hebrew } " encoding." ;
|
||||
|
||||
ABOUT: "io.encodings.8-bit.hebrew"
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: io.encodings.8-bit ;
|
||||
IN: io.encodings.8-bit.hebrew
|
||||
|
||||
8-BIT: latin/hebrew ISO_8859-8:1988 8859-8
|
||||
|
|
@ -0,0 +1 @@
|
|||
Doug Coleman
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: help.markup help.syntax ;
|
||||
IN: io.encodings.8-bit.koi8-r
|
||||
|
||||
HELP: koi8-r
|
||||
{ $var-description "KOI8-R is an 8-bit superset of ASCII which encodes the Cyrillic alphabet, as used in Russian and Bulgarian. Characters are in such an order that, if the eight bit is stripped, text is still interpretable as ASCII. Block-building characters also exist." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
ARTICLE: "io.encodings.8-bit.koi8-r" "KOI8-R encoding"
|
||||
"The " { $vocab-link "io.encodings.8-bit.koi8-r" } " vocabulary provides the " { $link koi8-r } " encoding." ;
|
||||
|
||||
ABOUT: "io.encodings.8-bit.koi8-r"
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: io.encodings.8-bit ;
|
||||
IN: io.encodings.8-bit.koi8-r
|
||||
|
||||
8-BIT: koi8-r KOI8-R KOI8-R
|
||||
|
|
@ -0,0 +1 @@
|
|||
Doug Coleman
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: help.markup help.syntax ;
|
||||
IN: io.encodings.8-bit.latin1
|
||||
|
||||
HELP: latin1
|
||||
{ $var-description "This is the ISO-8859-1 encoding, also called Latin-1: Western European. It is an 8-bit superset of ASCII which is the default for a mimetype starting with 'text' and provides the characters necessary for most western European languages." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
ARTICLE: "io.encodings.8-bit.latin1" "Latin1 encoding"
|
||||
"The " { $vocab-link "io.encodings.8-bit.latin1" } " vocabulary provides the " { $link latin1 } " encoding." ;
|
||||
|
||||
ABOUT: "io.encodings.8-bit.latin1"
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: io.encodings.8-bit ;
|
||||
IN: io.encodings.8-bit.latin1
|
||||
|
||||
8-BIT: latin1 ISO_8859-1:1987 8859-1
|
||||
|
|
@ -0,0 +1 @@
|
|||
Doug Coleman
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: help.markup help.syntax ;
|
||||
IN: io.encodings.8-bit.latin10
|
||||
|
||||
HELP: latin10
|
||||
{ $var-description "This is the ISO-8859-16 encoding, also called Latin-10: South-Eastern European. It is an 8-bit superset of ASCII." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
ARTICLE: "io.encodings.8-bit.latin10" "Latin10 encoding"
|
||||
"The " { $vocab-link "io.encodings.8-bit.latin10" } " vocabulary provides the " { $link latin10 } " encoding." ;
|
||||
|
||||
ABOUT: "io.encodings.8-bit.latin10"
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: io.encodings.8-bit ;
|
||||
IN: io.encodings.8-bit.latin10
|
||||
|
||||
8-BIT: latin10 ISO-8859-16 8859-16
|
||||
|
|
@ -0,0 +1 @@
|
|||
Doug Coleman
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: help.markup help.syntax ;
|
||||
IN: io.encodings.8-bit.latin2
|
||||
|
||||
HELP: latin2
|
||||
{ $var-description "This is the ISO-8859-2 encoding, also called Latin-2: Eastern European. It is an 8-bit superset of ASCII and provides the characters necessary for most eastern European languages." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
ARTICLE: "io.encodings.8-bit.latin2" "Latin2 encoding"
|
||||
"The " { $vocab-link "io.encodings.8-bit.latin2" } " vocabulary provides the " { $link latin2 } " encoding." ;
|
||||
|
||||
ABOUT: "io.encodings.8-bit.latin2"
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: io.encodings.8-bit ;
|
||||
IN: io.encodings.8-bit.latin2
|
||||
|
||||
8-BIT: latin2 ISO_8859-2:1987 8859-2
|
||||
|
|
@ -0,0 +1 @@
|
|||
Doug Coleman
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: help.markup help.syntax ;
|
||||
IN: io.encodings.8-bit.latin3
|
||||
|
||||
HELP: latin3
|
||||
{ $var-description "This is the ISO-8859-3 encoding, also called Latin-3: South European. It is an 8-bit superset of ASCII and provides the characters necessary for Turkish, Maltese and Esperanto." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
ARTICLE: "io.encodings.8-bit.latin3" "Latin3 encoding"
|
||||
"The " { $vocab-link "io.encodings.8-bit.latin3" } " vocabulary provides the " { $link latin3 } " encoding." ;
|
||||
|
||||
ABOUT: "io.encodings.8-bit.latin3"
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: io.encodings.8-bit ;
|
||||
IN: io.encodings.8-bit.latin3
|
||||
|
||||
8-BIT: latin3 ISO_8859-3:1988 8859-3
|
||||
|
|
@ -0,0 +1 @@
|
|||
Doug Coleman
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: help.markup help.syntax ;
|
||||
IN: io.encodings.8-bit.latin4
|
||||
|
||||
HELP: latin4
|
||||
{ $description "This is the ISO-8859-4 encoding, also called Latin-4: North European. It is an 8-bit superset of ASCII and provides the characters necessary for Latvian, Lithuanian, Estonian, Greenlandic and Sami." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
ARTICLE: "io.encodings.8-bit.latin4" "Latin4 encoding"
|
||||
"The " { $vocab-link "io.encodings.8-bit.latin4" } " vocabulary provides the " { $link latin4 } " encoding." ;
|
||||
|
||||
ABOUT: "io.encodings.8-bit.latin4"
|
||||
|
|
@ -0,0 +1,7 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: io.encodings.8-bit ;
|
||||
IN: io.encodings.8-bit.latin4
|
||||
|
||||
8-BIT: latin4 ISO_8859-4:1988 8859-4
|
||||
|
||||
|
|
@ -0,0 +1 @@
|
|||
Doug Coleman
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: help.markup help.syntax ;
|
||||
IN: io.encodings.8-bit.latin5
|
||||
|
||||
HELP: latin5
|
||||
{ $var-description "This is the ISO-8859-9 encoding, also called Latin-5: Turkish. It is an 8-bit superset of ASCII and provides the characters necessary for Turkish, similar to Latin-1 but replacing the spots used for Icelandic with characters used in Turkish." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
ARTICLE: "io.encodings.8-bit.latin5" "Latin5 encoding"
|
||||
"The " { $vocab-link "io.encodings.8-bit.latin5" } " vocabulary provides the " { $link latin5 } " encoding." ;
|
||||
|
||||
ABOUT: "io.encodings.8-bit.latin5"
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: io.encodings.8-bit ;
|
||||
IN: io.encodings.8-bit.latin5
|
||||
|
||||
8-BIT: latin5 ISO_8859-9:1989 8859-9
|
||||
|
|
@ -0,0 +1 @@
|
|||
Doug Coleman
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: help.markup help.syntax ;
|
||||
IN: io.encodings.8-bit.latin6
|
||||
|
||||
HELP: latin6
|
||||
{ $var-description "This is the ISO-8859-10 encoding, also called Latin-6: Nordic. It is an 8-bit superset of ASCII containing the same characters as Latin-4, but rearranged to be of better use to nordic languages." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
ARTICLE: "io.encodings.8-bit.latin6" "Latin6 encoding"
|
||||
"The " { $vocab-link "io.encodings.8-bit.latin6" } " vocabulary provides the " { $link latin6 } " encoding." ;
|
||||
|
||||
ABOUT: "io.encodings.8-bit.latin6"
|
||||
|
|
@ -0,0 +1,7 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: io.encodings.8-bit ;
|
||||
IN: io.encodings.8-bit.latin6
|
||||
|
||||
8-BIT: latin6 ISO-8859-10 8859-10
|
||||
|
||||
|
|
@ -0,0 +1 @@
|
|||
Doug Coleman
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: help.markup help.syntax ;
|
||||
IN: io.encodings.8-bit.latin7
|
||||
|
||||
HELP: latin7
|
||||
{ $var-description "This is the ISO-8859-13 encoding, also called Latin-7: Baltic Rim. It is an 8-bit superset of ASCII containing all characters necessary to represent Baltic Rim languages, as previous character sets were incomplete." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
ARTICLE: "io.encodings.8-bit.latin7" "Latin7 encoding"
|
||||
"The " { $vocab-link "io.encodings.8-bit.latin7" } " vocabulary provides the " { $link latin7 } " encoding." ;
|
||||
|
||||
ABOUT: "io.encodings.8-bit.latin7"
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: io.encodings.8-bit ;
|
||||
IN: io.encodings.8-bit.latin7
|
||||
|
||||
8-BIT: latin7 ISO-8859-13 8859-13
|
||||
|
|
@ -0,0 +1 @@
|
|||
Doug Coleman
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: help.markup help.syntax ;
|
||||
IN: io.encodings.8-bit.latin8
|
||||
|
||||
HELP: latin8
|
||||
{ $var-description "This is the ISO-8859-14 encoding, also called Latin-8: Celtic. It is an 8-bit superset of ASCII designed for Celtic languages like Gaelic and Breton." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
ARTICLE: "io.encodings.8-bit.latin8" "Latin8 encoding"
|
||||
"The " { $vocab-link "io.encodings.8-bit.latin8" } " vocabulary provides the " { $link latin8 } " encoding." ;
|
||||
|
||||
ABOUT: "io.encodings.8-bit.latin8"
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: io.encodings.8-bit ;
|
||||
IN: io.encodings.8-bit.latin8
|
||||
|
||||
8-BIT: latin8 ISO-8859-14 8859-14
|
||||
|
|
@ -0,0 +1 @@
|
|||
Doug Coleman
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: help.markup help.syntax ;
|
||||
IN: io.encodings.8-bit.latin9
|
||||
|
||||
HELP: latin9
|
||||
{ $var-description "This is the ISO-8859-15 encoding, also called Latin-9 and unoffically as Latin-0. It is an 8-bit superset of ASCII designed as a modification of Latin-1, removing little-used characters in favor of the Euro symbol and other characters." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
ARTICLE: "io.encodings.8-bit.latin9" "Latin9 encoding"
|
||||
"The " { $vocab-link "io.encodings.8-bit.latin9" } " vocabulary provides the " { $link latin9 } " encoding." ;
|
||||
|
||||
ABOUT: "io.encodings.8-bit.latin9"
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: io.encodings.8-bit ;
|
||||
IN: io.encodings.8-bit.latin9
|
||||
|
||||
8-BIT: latin9 ISO-8859-15 8859-15
|
||||
|
|
@ -0,0 +1 @@
|
|||
Doug Coleman
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: help.markup help.syntax ;
|
||||
IN: io.encodings.8-bit.mac-roman
|
||||
|
||||
HELP: mac-roman
|
||||
{ $var-description "Mac Roman is an 8-bit superset of ASCII which was the standard encoding on Mac OS prior to version 10. It is incompatible with Latin-1 in all but a few places and ASCII, and it is suitable for encoding many Western European languages." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
ARTICLE: "io.encodings.8-bit.mac-roman" "Mac Roman encoding"
|
||||
"The " { $vocab-link "io.encodings.8-bit.mac-roman" } " vocabulary provides the " { $link mac-roman } " encoding." ;
|
||||
|
||||
ABOUT: "io.encodings.8-bit.mac-roman"
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: io.encodings.8-bit ;
|
||||
IN: io.encodings.8-bit.mac-roman
|
||||
|
||||
8-BIT: mac-roman macintosh ROMAN
|
||||
|
|
@ -0,0 +1 @@
|
|||
Doug Coleman
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: help.markup help.syntax ;
|
||||
IN: io.encodings.8-bit.thai
|
||||
|
||||
HELP: latin/thai
|
||||
{ $var-description "This is the ISO-8859-11 encoding, also called Latin/Thai. It is an 8-bit superset of ASCII containing the characters necessary to represent Thai. It is basically identical to TIS-620." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
ARTICLE: "io.encodings.8-bit.thai" "Thai encoding"
|
||||
"The " { $vocab-link "io.encodings.8-bit.thai" } " vocabulary provides the " { $link latin/thai } " encoding." ;
|
||||
|
||||
ABOUT: "io.encodings.8-bit.thai"
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: io.encodings.8-bit ;
|
||||
IN: io.encodings.8-bit.thai
|
||||
|
||||
8-BIT: latin/thai TIS-620 8859-11
|
||||
|
|
@ -0,0 +1 @@
|
|||
Doug Coleman
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: io.encodings.8-bit ;
|
||||
IN: io.encodings.8-bit.windows-1250
|
||||
|
||||
8-BIT: windows-1250 windows-1250 CP1250
|
||||
|
|
@ -0,0 +1 @@
|
|||
Doug Coleman
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: io.encodings.8-bit ;
|
||||
IN: io.encodings.8-bit.windows-1251
|
||||
|
||||
8-BIT: windows-1251 windows-1251 CP1251
|
||||
|
|
@ -0,0 +1 @@
|
|||
Doug Coleman
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: help.markup help.syntax ;
|
||||
IN: io.encodings.8-bit.windows-1252
|
||||
|
||||
HELP: windows-1252
|
||||
{ $var-description "Windows 1252 is an 8-bit superset of ASCII which is closely related to Latin-1. Control characters in the 0x80 to 0x9F range are replaced with printable characters such as the Euro symbol." }
|
||||
{ $see-also "encodings-introduction" } ;
|
||||
|
||||
ARTICLE: "io.encodings.8-bit.windows-1252" "Windows 1252 encoding"
|
||||
"The " { $vocab-link "io.encodings.8-bit.windows-1252" } " vocabulary provides the " { $link windows-1252 } " encoding." ;
|
||||
|
||||
ABOUT: "io.encodings.8-bit.windows-1252"
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: io.encodings.8-bit ;
|
||||
IN: io.encodings.8-bit.windows-1252
|
||||
|
||||
8-BIT: windows-1252 windows-1252 CP1252
|
||||
|
|
@ -0,0 +1 @@
|
|||
Doug Coleman
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: io.encodings.8-bit ;
|
||||
IN: io.encodings.8-bit.windows-1253
|
||||
|
||||
8-BIT: windows-1253 windows-1253 CP1253
|
||||
|
|
@ -0,0 +1 @@
|
|||
Doug Coleman
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: io.encodings.8-bit ;
|
||||
IN: io.encodings.8-bit.windows-1254
|
||||
|
||||
8-BIT: windows-1254 windows-1254 CP1254
|
||||
|
|
@ -0,0 +1 @@
|
|||
Doug Coleman
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: io.encodings.8-bit ;
|
||||
IN: io.encodings.8-bit.windows-1255
|
||||
|
||||
8-BIT: windows-1255 windows-1255 CP1255
|
||||
|
|
@ -0,0 +1 @@
|
|||
Doug Coleman
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: io.encodings.8-bit ;
|
||||
IN: io.encodings.8-bit.windows-1256
|
||||
|
||||
8-BIT: windows-1256 windows-1256 CP1256
|
||||
|
|
@ -0,0 +1 @@
|
|||
Doug Coleman
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: io.encodings.8-bit ;
|
||||
IN: io.encodings.8-bit.windows-1257
|
||||
|
||||
8-BIT: windows-1257 windows-1257 CP1257
|
||||
|
|
@ -0,0 +1 @@
|
|||
Doug Coleman
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
! Copyright (C) 2009 Doug Coleman.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: io.encodings.8-bit ;
|
||||
IN: io.encodings.8-bit.windows-1258
|
||||
|
||||
8-BIT: windows-1258 windows-1258 CP1258
|
||||
|
|
@ -57,4 +57,4 @@ e>n-table [ initial-e>n ] initialize
|
|||
ascii "ANSI_X3.4-1968" register-encoding
|
||||
utf16be "UTF-16BE" register-encoding
|
||||
utf16le "UTF-16LE" register-encoding
|
||||
utf16 "UTF-16" register-encoding
|
||||
utf16 "UTF-16" register-encoding
|
||||
|
|
|
|||
|
|
@ -5,7 +5,7 @@ math.order combinators init alien alien.c-types alien.data
|
|||
alien.strings libc continuations destructors summary splitting
|
||||
assocs random math.parser locals unicode.case openssl
|
||||
openssl.libcrypto openssl.libssl io.backend io.ports io.pathnames
|
||||
io.encodings.8-bit io.timeouts io.sockets.secure ;
|
||||
io.encodings.8-bit.latin1 io.timeouts io.sockets.secure ;
|
||||
IN: io.sockets.secure.openssl
|
||||
|
||||
GENERIC: ssl-method ( symbol -- method )
|
||||
|
|
|
|||
|
|
@ -1,8 +1,9 @@
|
|||
USING: accessors continuations destructors io io.encodings
|
||||
io.encodings.8-bit io.encodings.ascii io.encodings.binary
|
||||
io.encodings.ascii io.encodings.binary
|
||||
io.encodings.string io.encodings.utf8 io.files io.pipes
|
||||
io.streams.byte-array io.streams.limited io.streams.string
|
||||
kernel namespaces strings tools.test system ;
|
||||
kernel namespaces strings tools.test system
|
||||
io.encodings.8-bit.latin1 ;
|
||||
IN: io.streams.limited.tests
|
||||
|
||||
[ ] [
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
! Copyright (C) 2009 Daniel Ehrenberg
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: tools.test quoted-printable io.encodings.string
|
||||
sequences io.encodings.8-bit splitting kernel ;
|
||||
sequences splitting kernel io.encodings.8-bit.latin2 ;
|
||||
IN: quoted-printable.tests
|
||||
|
||||
[ """José was the
|
||||
|
|
|
|||
|
|
@ -1,5 +1,5 @@
|
|||
USING: io.encodings.string kernel io.encodings.8-bit.latin7 ;
|
||||
IN: tools.deploy.test.4
|
||||
USING: io.encodings.8-bit io.encodings.string kernel ;
|
||||
|
||||
: deploy-test-4 ( -- )
|
||||
"xyzthg" \ latin7 encode drop ;
|
||||
|
|
|
|||
|
|
@ -60,7 +60,7 @@ IN: tools.profiler.tests
|
|||
|
||||
[ [ gensym execute ] profile ] [ T{ undefined } = ] must-fail-with
|
||||
|
||||
: crash-bug-1 ( -- x ) "hi" "bye" <word> ;
|
||||
: crash-bug-1 ( -- x ) "hi" <uninterned-word> ;
|
||||
: crash-bug-2 ( -- ) 100000 [ crash-bug-1 drop ] times ;
|
||||
|
||||
[ ] [ [ crash-bug-2 ] profile ] unit-test
|
||||
|
|
|
|||
|
|
@ -1,5 +1,4 @@
|
|||
USING: xml xml.data xml.traversal tools.test accessors kernel
|
||||
io.encodings.8-bit ;
|
||||
USING: xml xml.data xml.traversal tools.test accessors kernel ;
|
||||
|
||||
[ "\u000131" ] [ "vocab:xml/tests/latin5.xml" file>xml children>string ] unit-test
|
||||
[ "\u0000e9" ] [ "vocab:xml/tests/latin1.xml" file>xml children>string ] unit-test
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
USING: alien.strings alien.c-types alien.data tools.test kernel libc
|
||||
io.encodings.8-bit io.encodings.utf8 io.encodings.utf16
|
||||
io.encodings.utf16n io.encodings.ascii alien io.encodings.string ;
|
||||
USING: alien.strings alien.c-types alien.data tools.test
|
||||
kernel libc io.encodings.utf8 io.encodings.utf16 io.encodings.utf16n
|
||||
io.encodings.ascii alien io.encodings.string io.encodings.8-bit.latin1 ;
|
||||
IN: alien.strings.tests
|
||||
|
||||
[ "\u0000ff" ]
|
||||
|
|
|
|||
|
|
@ -39,6 +39,9 @@ INTERSECTION: generic-class generic class ;
|
|||
|
||||
UNION: union-with-one-member a ;
|
||||
|
||||
MIXIN: mixin-with-one-member
|
||||
INSTANCE: union-with-one-member mixin-with-one-member
|
||||
|
||||
! class<=
|
||||
[ t ] [ \ fixnum \ integer class<= ] unit-test
|
||||
[ t ] [ \ fixnum \ fixnum class<= ] unit-test
|
||||
|
|
@ -176,6 +179,22 @@ UNION: union-with-one-member a ;
|
|||
|
||||
[ f ] [ sa sb classes-intersect? ] unit-test
|
||||
|
||||
[ t ] [ a union-with-one-member classes-intersect? ] unit-test
|
||||
[ f ] [ fixnum union-with-one-member classes-intersect? ] unit-test
|
||||
[ t ] [ object union-with-one-member classes-intersect? ] unit-test
|
||||
|
||||
[ t ] [ union-with-one-member a classes-intersect? ] unit-test
|
||||
[ f ] [ union-with-one-member fixnum classes-intersect? ] unit-test
|
||||
[ t ] [ union-with-one-member object classes-intersect? ] unit-test
|
||||
|
||||
[ t ] [ a mixin-with-one-member classes-intersect? ] unit-test
|
||||
[ f ] [ fixnum mixin-with-one-member classes-intersect? ] unit-test
|
||||
[ t ] [ object mixin-with-one-member classes-intersect? ] unit-test
|
||||
|
||||
[ t ] [ mixin-with-one-member a classes-intersect? ] unit-test
|
||||
[ f ] [ mixin-with-one-member fixnum classes-intersect? ] unit-test
|
||||
[ t ] [ mixin-with-one-member object classes-intersect? ] unit-test
|
||||
|
||||
! class=
|
||||
[ t ] [ null class-not object class= ] unit-test
|
||||
|
||||
|
|
|
|||
|
|
@ -36,8 +36,8 @@ GENERIC: (flatten-class) ( class -- )
|
|||
|
||||
: normalize-class ( class -- class' )
|
||||
{
|
||||
{ [ dup members ] [ members <anonymous-union> ] }
|
||||
{ [ dup participants ] [ participants <anonymous-intersection> ] }
|
||||
{ [ dup members ] [ members <anonymous-union> normalize-class ] }
|
||||
{ [ dup participants ] [ participants <anonymous-intersection> normalize-class ] }
|
||||
[ ]
|
||||
} cond ;
|
||||
|
||||
|
|
|
|||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue