io/utf8 and 16 were moved to core/io/encodings
parent
99ff43b404
commit
8bbc144ce7
|
@ -1 +0,0 @@
|
|||
Daniel Ehrenberg
|
|
@ -1 +0,0 @@
|
|||
UTF16 encoding/decoding
|
|
@ -1,45 +0,0 @@
|
|||
USING: help.markup help.syntax io.encodings strings ;
|
||||
IN: io.utf16
|
||||
|
||||
ARTICLE: "io.utf16" "Working with UTF16-encoded data"
|
||||
"The UTF16 encoding is a variable-width encoding. Unicode code points are encoded as 2 or 4 byte sequences."
|
||||
{ $subsection encode-utf16le }
|
||||
{ $subsection encode-utf16be }
|
||||
{ $subsection decode-utf16le }
|
||||
{ $subsection decode-utf16be }
|
||||
"Support for UTF16 data with a byte order mark:"
|
||||
{ $subsection encode-utf16 }
|
||||
{ $subsection decode-utf16 } ;
|
||||
|
||||
ABOUT: "io.utf16"
|
||||
|
||||
HELP: decode-utf16
|
||||
{ $values { "seq" "a sequence of bytes" } { "str" string } }
|
||||
{ $description "Decodes a sequence of bytes representing a Unicode string in UTF16 format. The bytes must begin with a UTF16 byte order mark, which determines if the input is in little or big endian. To decode data without a byte order mark, use " { $link decode-utf16le } " or " { $link decode-utf16be } "." }
|
||||
{ $errors "Throws a " { $link decode-error } " if the input is malformed." } ;
|
||||
|
||||
HELP: decode-utf16be
|
||||
{ $values { "seq" "a sequence of bytes" } { "str" string } }
|
||||
{ $description "Decodes a sequence of bytes representing a Unicode string in big endian UTF16 format. The bytes must not begin with a UTF16 byte order mark. To decode data with a byte order mark, use " { $link decode-utf16 } "." }
|
||||
{ $errors "Throws a " { $link decode-error } " if the input is malformed." } ;
|
||||
|
||||
HELP: decode-utf16le
|
||||
{ $values { "seq" "a sequence of bytes" } { "str" string } }
|
||||
{ $description "Decodes a sequence of bytes representing a Unicode string in little endian UTF16 format. The bytes must not begin with a UTF16 byte order mark. To decode data with a byte order mark, use " { $link decode-utf16 } "." }
|
||||
{ $errors "Throws a " { $link decode-error } " if the input is malformed." } ;
|
||||
|
||||
{ decode-utf16 decode-utf16le decode-utf16be } related-words
|
||||
|
||||
HELP: encode-utf16be
|
||||
{ $values { "str" string } { "seq" "a sequence of bytes" } }
|
||||
{ $description "Encodes a Unicode string as a sequence of bytes in big endian UTF16 format." } ;
|
||||
|
||||
HELP: encode-utf16le
|
||||
{ $values { "str" string } { "seq" "a sequence of bytes" } }
|
||||
{ $description "Encodes a Unicode string as a sequence of bytes in little endian UTF16 format." } ;
|
||||
|
||||
HELP: encode-utf16
|
||||
{ $values { "str" string } { "seq" "a sequence of bytes" } }
|
||||
{ $description "Encodes a Unicode string as a sequence of bytes in UTF16 format with a byte order mark." } ;
|
||||
|
||||
{ encode-utf16 encode-utf16be encode-utf16le } related-words
|
|
@ -1,15 +0,0 @@
|
|||
USING: tools.test io.utf16 arrays unicode.syntax ;
|
||||
|
||||
[ { CHAR: x } ] [ { 0 CHAR: x } decode-utf16be >array ] unit-test
|
||||
[ { HEX: 1D11E } ] [ { HEX: D8 HEX: 34 HEX: DD HEX: 1E } decode-utf16be >array ] unit-test
|
||||
[ { UNICHAR: replacement-character } ] [ { BIN: 11011111 CHAR: q } decode-utf16be >array ] unit-test
|
||||
[ { UNICHAR: replacement-character } ] [ { BIN: 11011011 CHAR: x BIN: 11011011 CHAR: x } decode-utf16be >array ] unit-test
|
||||
|
||||
[ B{ 0 120 216 52 221 30 } ] [ { CHAR: x HEX: 1d11e } encode-utf16be ] unit-test
|
||||
|
||||
[ { CHAR: x } ] [ { CHAR: x 0 } decode-utf16le >array ] unit-test
|
||||
[ { 119070 } ] [ { HEX: 34 HEX: D8 HEX: 1E HEX: DD } decode-utf16le >array ] unit-test
|
||||
[ { UNICHAR: replacement-character } ] [ { 0 BIN: 11011111 } decode-utf16le >array ] unit-test
|
||||
[ { UNICHAR: replacement-character } ] [ { 0 BIN: 11011011 0 0 } decode-utf16le >array ] unit-test
|
||||
|
||||
[ B{ 120 0 52 216 30 221 } ] [ { CHAR: x HEX: 1d11e } encode-utf16le ] unit-test
|
|
@ -1,116 +0,0 @@
|
|||
! Copyright (C) 2006, 2007 Daniel Ehrenberg.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: math kernel sequences sbufs vectors namespaces io.binary
|
||||
io.encodings combinators splitting ;
|
||||
IN: io.utf16
|
||||
|
||||
SYMBOL: double
|
||||
SYMBOL: quad1
|
||||
SYMBOL: quad2
|
||||
SYMBOL: quad3
|
||||
SYMBOL: ignore
|
||||
|
||||
: do-ignore ( -- ch state ) 0 ignore ;
|
||||
|
||||
: append-nums ( byte ch -- ch )
|
||||
8 shift bitor ;
|
||||
|
||||
: end-multibyte ( buf byte ch -- buf ch state )
|
||||
append-nums decoded ;
|
||||
|
||||
: begin-utf16be ( buf byte -- buf ch state )
|
||||
dup -3 shift BIN: 11011 number= [
|
||||
dup BIN: 00000100 bitand zero?
|
||||
[ BIN: 11 bitand quad1 ]
|
||||
[ drop do-ignore ] if
|
||||
] [ double ] if ;
|
||||
|
||||
: handle-quad2be ( byte ch -- ch state )
|
||||
swap dup -2 shift BIN: 110111 number= [
|
||||
>r 2 shift r> BIN: 11 bitand bitor quad3
|
||||
] [ 2drop do-ignore ] if ;
|
||||
|
||||
: (decode-utf16be) ( buf byte ch state -- buf ch state )
|
||||
{
|
||||
{ begin [ drop begin-utf16be ] }
|
||||
{ double [ end-multibyte ] }
|
||||
{ quad1 [ append-nums quad2 ] }
|
||||
{ quad2 [ handle-quad2be ] }
|
||||
{ quad3 [ append-nums HEX: 10000 + decoded ] }
|
||||
{ ignore [ 2drop push-replacement ] }
|
||||
} case ;
|
||||
|
||||
: decode-utf16be ( seq -- str )
|
||||
[ -rot (decode-utf16be) ] decode ;
|
||||
|
||||
: handle-double ( buf byte ch -- buf ch state )
|
||||
swap dup -3 shift BIN: 11011 = [
|
||||
dup BIN: 100 bitand 0 number=
|
||||
[ BIN: 11 bitand 8 shift bitor quad2 ]
|
||||
[ 2drop push-replacement ] if
|
||||
] [ end-multibyte ] if ;
|
||||
|
||||
: handle-quad3le ( buf byte ch -- buf ch state )
|
||||
swap dup -2 shift BIN: 110111 = [
|
||||
BIN: 11 bitand append-nums HEX: 10000 + decoded
|
||||
] [ 2drop push-replacement ] if ;
|
||||
|
||||
: (decode-utf16le) ( buf byte ch state -- buf ch state )
|
||||
{
|
||||
{ begin [ drop double ] }
|
||||
{ double [ handle-double ] }
|
||||
{ quad1 [ append-nums quad2 ] }
|
||||
{ quad2 [ 10 shift bitor quad3 ] }
|
||||
{ quad3 [ handle-quad3le ] }
|
||||
} case ;
|
||||
|
||||
: decode-utf16le ( seq -- str )
|
||||
[ -rot (decode-utf16le) ] decode ;
|
||||
|
||||
: encode-first
|
||||
-10 shift
|
||||
dup -8 shift BIN: 11011000 bitor
|
||||
swap HEX: FF bitand ;
|
||||
|
||||
: encode-second
|
||||
BIN: 1111111111 bitand
|
||||
dup -8 shift BIN: 11011100 bitor
|
||||
swap BIN: 11111111 bitand ;
|
||||
|
||||
: char>utf16be ( char -- )
|
||||
dup HEX: FFFF > [
|
||||
HEX: 10000 -
|
||||
dup encode-first swap , ,
|
||||
encode-second swap , ,
|
||||
] [ h>b/b , , ] if ;
|
||||
|
||||
: encode-utf16be ( str -- seq )
|
||||
[ [ char>utf16be ] each ] B{ } make ;
|
||||
|
||||
: char>utf16le ( char -- )
|
||||
dup HEX: FFFF > [
|
||||
HEX: 10000 -
|
||||
dup encode-first , ,
|
||||
encode-second , ,
|
||||
] [ h>b/b swap , , ] if ;
|
||||
|
||||
: encode-utf16le ( str -- seq )
|
||||
[ [ char>utf16le ] each ] B{ } make ;
|
||||
|
||||
: bom-le B{ HEX: ff HEX: fe } ; inline
|
||||
|
||||
: bom-be B{ HEX: fe HEX: ff } ; inline
|
||||
|
||||
: encode-utf16 ( str -- seq )
|
||||
encode-utf16le bom-le swap append ;
|
||||
|
||||
: utf16le? ( seq1 -- seq2 ? ) bom-le ?head ;
|
||||
|
||||
: utf16be? ( seq1 -- seq2 ? ) bom-be ?head ;
|
||||
|
||||
: decode-utf16 ( seq -- str )
|
||||
{
|
||||
{ [ utf16le? ] [ decode-utf16le ] }
|
||||
{ [ utf16be? ] [ decode-utf16be ] }
|
||||
{ [ t ] [ decode-error ] }
|
||||
} cond ;
|
|
@ -1 +0,0 @@
|
|||
Daniel Ehrenberg
|
|
@ -1 +0,0 @@
|
|||
UTF8 encoding/decoding
|
|
@ -1,18 +0,0 @@
|
|||
USING: help.markup help.syntax io.encodings strings ;
|
||||
IN: io.utf8
|
||||
|
||||
ARTICLE: "io.utf8" "Working with UTF8-encoded data"
|
||||
"The UTF8 encoding is a variable-width encoding. 7-bit ASCII characters are encoded as single bytes, and other Unicode code points are encoded as 2 to 4 byte sequences."
|
||||
{ $subsection encode-utf8 }
|
||||
{ $subsection decode-utf8 } ;
|
||||
|
||||
ABOUT: "io.utf8"
|
||||
|
||||
HELP: decode-utf8
|
||||
{ $values { "seq" "a sequence of bytes" } { "str" string } }
|
||||
{ $description "Decodes a sequence of bytes representing a Unicode string in UTF8 format." }
|
||||
{ $errors "Throws a " { $link decode-error } " if the input is malformed." } ;
|
||||
|
||||
HELP: encode-utf8
|
||||
{ $values { "str" string } { "seq" "a sequence of bytes" } }
|
||||
{ $description "Encodes a Unicode string as a sequence of bytes in UTF8 format." } ;
|
|
@ -1,16 +0,0 @@
|
|||
USING: io.utf8 tools.test strings arrays unicode.syntax ;
|
||||
|
||||
[ { UNICHAR: replacement-character } ] [ { BIN: 11110101 BIN: 10111111 BIN: 10000000 BIN: 11111111 } decode-utf8 >array ] unit-test
|
||||
|
||||
[ { BIN: 101111111000000111111 } ] [ { BIN: 11110101 BIN: 10111111 BIN: 10000000 BIN: 10111111 } decode-utf8 >array ] unit-test
|
||||
|
||||
[ "x" ] [ "x" decode-utf8 >string ] unit-test
|
||||
|
||||
[ { BIN: 11111000000 } ] [ { BIN: 11011111 BIN: 10000000 } decode-utf8 >array ] unit-test
|
||||
|
||||
[ { UNICHAR: replacement-character } ] [ { BIN: 10000000 } decode-utf8 >array ] unit-test
|
||||
|
||||
[ { BIN: 1111000000111111 } ] [ { BIN: 11101111 BIN: 10000000 BIN: 10111111 } decode-utf8 >array ] unit-test
|
||||
|
||||
[ B{ BIN: 11110101 BIN: 10111111 BIN: 10000000 BIN: 10111111 BIN: 11101111 BIN: 10000000 BIN: 10111111 BIN: 11011111 BIN: 10000000 CHAR: x } ]
|
||||
[ { BIN: 101111111000000111111 BIN: 1111000000111111 BIN: 11111000000 CHAR: x } encode-utf8 ] unit-test
|
|
@ -1,72 +0,0 @@
|
|||
! Copyright (C) 2006, 2007 Daniel Ehrenberg.
|
||||
! See http://factorcode.org/license.txt for BSD license.
|
||||
USING: math kernel sequences sbufs vectors
|
||||
namespaces io.encodings combinators ;
|
||||
IN: io.utf8
|
||||
|
||||
SYMBOL: double
|
||||
SYMBOL: triple
|
||||
SYMBOL: triple2
|
||||
SYMBOL: quad
|
||||
SYMBOL: quad2
|
||||
SYMBOL: quad3
|
||||
|
||||
: starts-2? ( char -- ? )
|
||||
-6 shift BIN: 10 number= ;
|
||||
|
||||
: append-nums ( buf bottom top state-out -- buf num state )
|
||||
>r over starts-2?
|
||||
[ 6 shift swap BIN: 111111 bitand bitor r> ]
|
||||
[ r> 3drop push-replacement ] if ;
|
||||
|
||||
: begin-utf8 ( buf byte -- buf ch state )
|
||||
{
|
||||
{ [ dup -7 shift zero? ] [ decoded ] }
|
||||
{ [ dup -5 shift BIN: 110 number= ] [ BIN: 11111 bitand double ] }
|
||||
{ [ dup -4 shift BIN: 1110 number= ] [ BIN: 1111 bitand triple ] }
|
||||
{ [ dup -3 shift BIN: 11110 number= ] [ BIN: 111 bitand quad ] }
|
||||
{ [ t ] [ drop push-replacement ] }
|
||||
} cond ;
|
||||
|
||||
: end-multibyte ( buf byte ch -- buf ch state )
|
||||
f append-nums [ decoded ] unless* ;
|
||||
|
||||
: (decode-utf8) ( buf byte ch state -- buf ch state )
|
||||
{
|
||||
{ begin [ drop begin-utf8 ] }
|
||||
{ double [ end-multibyte ] }
|
||||
{ triple [ triple2 append-nums ] }
|
||||
{ triple2 [ end-multibyte ] }
|
||||
{ quad [ quad2 append-nums ] }
|
||||
{ quad2 [ quad3 append-nums ] }
|
||||
{ quad3 [ end-multibyte ] }
|
||||
} case ;
|
||||
|
||||
: decode-utf8 ( seq -- str )
|
||||
[ -rot (decode-utf8) ] decode ;
|
||||
|
||||
: encoded ( char -- )
|
||||
BIN: 111111 bitand BIN: 10000000 bitor , ;
|
||||
|
||||
: char>utf8 ( char -- )
|
||||
{
|
||||
{ [ dup -7 shift zero? ] [ , ] }
|
||||
{ [ dup -11 shift zero? ] [
|
||||
dup -6 shift BIN: 11000000 bitor ,
|
||||
encoded
|
||||
] }
|
||||
{ [ dup -16 shift zero? ] [
|
||||
dup -12 shift BIN: 11100000 bitor ,
|
||||
dup -6 shift encoded
|
||||
encoded
|
||||
] }
|
||||
{ [ t ] [
|
||||
dup -18 shift BIN: 11110000 bitor ,
|
||||
dup -12 shift encoded
|
||||
dup -6 shift encoded
|
||||
encoded
|
||||
] }
|
||||
} cond ;
|
||||
|
||||
: encode-utf8 ( str -- seq )
|
||||
[ [ char>utf8 ] each ] B{ } make ;
|
Loading…
Reference in New Issue