diff --git a/core/bootstrap/image/image.factor b/core/bootstrap/image/image.factor
index 52a2496755..6aa4b9212d 100755
--- a/core/bootstrap/image/image.factor
+++ b/core/bootstrap/image/image.factor
@@ -348,8 +348,10 @@ M: curry '
: emit-global ( -- )
[
{
- dictionary source-files
- typemap builtins class<map class-map update-map
+ dictionary source-files builtins
+ update-map class<-cache class-not-cache
+ classes-intersect-cache class-and-cache
+ class-or-cache
} [ dup get swap bootstrap-word set ] each
] H{ } make-assoc
bootstrap-global set
diff --git a/core/bootstrap/primitives.factor b/core/bootstrap/primitives.factor
index 825ee05584..0f38839c87 100755
--- a/core/bootstrap/primitives.factor
+++ b/core/bootstrap/primitives.factor
@@ -31,6 +31,10 @@ crossref off
H{ } clone dictionary set
H{ } clone changed-words set
H{ } clone root-cache set
+H{ } clone source-files set
+H{ } clone update-map set
+num-types get f <array> builtins set
+init-caches
! Vocabulary for slot accessors
"accessors" create-vocab drop
@@ -93,11 +97,6 @@ call
"vectors.private"
} [ create-vocab drop ] each
-H{ } clone source-files set
-H{ } clone update-map set
-H{ } clone class<map set
-H{ } clone class-map set
-
! Builtin classes
: builtin-predicate-quot ( class -- quot )
[
@@ -130,9 +129,6 @@ H{ } clone class-map set
dup define-builtin-predicate
r> define-builtin-slots ;
-H{ } clone typemap set
-num-types get f <array> builtins set
-
! Forward definitions
"object" "kernel" create t "class" set-word-prop
"object" "kernel" create union-class "metaclass" set-word-prop
diff --git a/core/classes/algebra/algebra-docs.factor b/core/classes/algebra/algebra-docs.factor
new file mode 100755
index 0000000000..c21098916d
--- /dev/null
+++ b/core/classes/algebra/algebra-docs.factor
@@ -0,0 +1,55 @@
+USING: help.markup help.syntax kernel classes ;
+IN: classes.algebra
+
+ARTICLE: "class-operations" "Class operations"
+"Set-theoretic operations on classes:"
+{ $subsection class< }
+{ $subsection class-and }
+{ $subsection class-or }
+{ $subsection classes-intersect? }
+"Topological sort:"
+{ $subsection sort-classes }
+{ $subsection min-class }
+"Low-level implementation detail:"
+{ $subsection class-types }
+{ $subsection flatten-class }
+{ $subsection flatten-builtin-class }
+{ $subsection class-types }
+{ $subsection class-tags } ;
+
+HELP: flatten-builtin-class
+{ $values { "class" class } { "assoc" "an assoc whose keys are classes" } }
+{ $description "Outputs a set of tuple classes whose union is the smallest cover of " { $snippet "class" } " intersected with " { $link tuple } "." } ;
+
+HELP: flatten-class
+{ $values { "class" class } { "assoc" "an assoc whose keys are classes" } }
+{ $description "Outputs a set of builtin and tuple classes whose union is the smallest cover of " { $snippet "class" } "." } ;
+
+HELP: class-types
+{ $values { "class" class } { "seq" "an increasing sequence of integers" } }
+{ $description "Outputs a sequence of builtin type numbers whose instances can possibly be instances of the given class." } ;
+
+HELP: class<
+{ $values { "class1" "a class" } { "class2" "a class" } { "?" "a boolean" } }
+{ $description "Tests if all instances of " { $snippet "class1" } " are also instances of " { $snippet "class2" } "." }
+{ $notes "Classes are partially ordered. This means that if " { $snippet "class1 <= class2" } " and " { $snippet "class2 <= class1" } ", then " { $snippet "class1 = class2" } ". Also, if " { $snippet "class1 <= class2" } " and " { $snippet "class2 <= class3" } ", then " { $snippet "class1 <= class3" } "." } ;
+
+HELP: sort-classes
+{ $values { "seq" "a sequence of class" } { "newseq" "a new seqence of classes" } }
+{ $description "Outputs a topological sort of a sequence of classes. Larger classes come before their subclasses." } ;
+
+HELP: class-or
+{ $values { "class1" class } { "class2" class } { "class" class } }
+{ $description "Outputs the smallest anonymous class containing both " { $snippet "class1" } " and " { $snippet "class2" } "." } ;
+
+HELP: class-and
+{ $values { "class1" class } { "class2" class } { "class" class } }
+{ $description "Outputs the largest anonymous class contained in both " { $snippet "class1" } " and " { $snippet "class2" } "." } ;
+
+HELP: classes-intersect?
+{ $values { "class1" class } { "class2" class } { "?" "a boolean" } }
+{ $description "Tests if two classes have a non-empty intersection. If the intersection is empty, no object can be an instance of both classes at once." } ;
+
+HELP: min-class
+{ $values { "class" class } { "seq" "a sequence of class words" } { "class/f" "a class word or " { $link f } } }
+{ $description "If all classes in " { $snippet "seq" } " that intersect " { $snippet "class" } " are subtypes of " { $snippet "class" } ", outputs the last such element of " { $snippet "seq" } ". If any conditions fail to hold, outputs " { $link f } "." } ;
diff --git a/core/classes/algebra/algebra-tests.factor b/core/classes/algebra/algebra-tests.factor
new file mode 100755
index 0000000000..24a18559fe
--- /dev/null
+++ b/core/classes/algebra/algebra-tests.factor
@@ -0,0 +1,201 @@
+IN: classes.algebra.tests
+USING: alien arrays definitions generic assocs hashtables io
+kernel math namespaces parser prettyprint sequences strings
+tools.test vectors words quotations classes classes.algebra
+classes.private classes.union classes.mixin classes.predicate
+vectors definitions source-files compiler.units growable
+random inference effects ;
+
+: class= [ class< ] 2keep swap class< and ;
+
+: class-and* >r class-and r> class= ;
+
+: class-or* >r class-or r> class= ;
+
+[ t ] [ object object object class-and* ] unit-test
+[ t ] [ fixnum object fixnum class-and* ] unit-test
+[ t ] [ object fixnum fixnum class-and* ] unit-test
+[ t ] [ fixnum fixnum fixnum class-and* ] unit-test
+[ t ] [ fixnum integer fixnum class-and* ] unit-test
+[ t ] [ integer fixnum fixnum class-and* ] unit-test
+
+[ t ] [ vector fixnum null class-and* ] unit-test
+[ t ] [ number object number class-and* ] unit-test
+[ t ] [ object number number class-and* ] unit-test
+[ t ] [ slice reversed null class-and* ] unit-test
+[ t ] [ general-t \ f null class-and* ] unit-test
+[ t ] [ general-t \ f object class-or* ] unit-test
+
+TUPLE: first-one ;
+TUPLE: second-one ;
+UNION: both first-one union-class ;
+
+[ t ] [ both tuple classes-intersect? ] unit-test
+[ t ] [ vector virtual-sequence null class-and* ] unit-test
+[ f ] [ vector virtual-sequence classes-intersect? ] unit-test
+
+[ t ] [ number vector class-or sequence classes-intersect? ] unit-test
+
+[ f ] [ number vector class-and sequence classes-intersect? ] unit-test
+
+[ t ] [ \ fixnum \ integer class< ] unit-test
+[ t ] [ \ fixnum \ fixnum class< ] unit-test
+[ f ] [ \ integer \ fixnum class< ] unit-test
+[ t ] [ \ integer \ object class< ] unit-test
+[ f ] [ \ integer \ null class< ] unit-test
+[ t ] [ \ null \ object class< ] unit-test
+
+[ t ] [ \ generic \ word class< ] unit-test
+[ f ] [ \ word \ generic class< ] unit-test
+
+[ f ] [ \ reversed \ slice class< ] unit-test
+[ f ] [ \ slice \ reversed class< ] unit-test
+
+PREDICATE: word no-docs "documentation" word-prop not ;
+
+UNION: no-docs-union no-docs integer ;
+
+[ t ] [ no-docs no-docs-union class< ] unit-test
+[ f ] [ no-docs-union no-docs class< ] unit-test
+
+TUPLE: a ;
+TUPLE: b ;
+UNION: c a b ;
+
+[ t ] [ \ c \ tuple class< ] unit-test
+[ f ] [ \ tuple \ c class< ] unit-test
+
+[ t ] [ \ tuple-class \ class class< ] unit-test
+[ f ] [ \ class \ tuple-class class< ] unit-test
+
+TUPLE: delegate-clone ;
+
+[ t ] [ \ null \ delegate-clone class< ] unit-test
+[ f ] [ \ object \ delegate-clone class< ] unit-test
+[ f ] [ \ object \ delegate-clone class< ] unit-test
+[ t ] [ \ delegate-clone \ tuple class< ] unit-test
+[ f ] [ \ tuple \ delegate-clone class< ] unit-test
+
+TUPLE: a1 ;
+TUPLE: b1 ;
+TUPLE: c1 ;
+
+UNION: x1 a1 b1 ;
+UNION: y1 a1 c1 ;
+UNION: z1 b1 c1 ;
+
+[ f ] [ z1 x1 y1 class-and class< ] unit-test
+
+[ t ] [ x1 y1 class-and a1 class< ] unit-test
+
+[ f ] [ y1 z1 class-and x1 classes-intersect? ] unit-test
+
+[ f ] [ b1 c1 class-or a1 b1 class-or a1 c1 class-and class-and class< ] unit-test
+
+[ t ] [ a1 b1 class-or a1 c1 class-or class-and a1 class< ] unit-test
+
+[ f ] [ a1 c1 class-or b1 c1 class-or class-and a1 b1 class-or classes-intersect? ] unit-test
+
+[ f ] [ growable hi-tag classes-intersect? ] unit-test
+
+[ t ] [
+ growable tuple sequence class-and class<
+] unit-test
+
+[ t ] [
+ growable assoc class-and tuple class<
+] unit-test
+
+[ t ] [ object \ f \ f class-not class-or class< ] unit-test
+
+[ t ] [ fixnum class-not integer class-and bignum class= ] unit-test
+
+[ f ] [ integer integer class-not classes-intersect? ] unit-test
+
+[ t ] [ array number class-not class< ] unit-test
+
+[ f ] [ bignum number class-not class< ] unit-test
+
+[ vector ] [ vector class-not class-not ] unit-test
+
+[ t ] [ fixnum fixnum bignum class-or class< ] unit-test
+
+[ f ] [ fixnum class-not integer class-and array class< ] unit-test
+
+[ f ] [ fixnum class-not integer class< ] unit-test
+
+[ f ] [ number class-not array class< ] unit-test
+
+[ f ] [ fixnum class-not array class< ] unit-test
+
+[ t ] [ number class-not integer class-not class< ] unit-test
+
+[ t ] [ vector array class-not class-and vector class= ] unit-test
+
+[ f ] [ fixnum class-not number class-and array classes-intersect? ] unit-test
+
+[ f ] [ fixnum class-not integer class< ] unit-test
+
+[ t ] [ null class-not object class= ] unit-test
+
+[ t ] [ object class-not null class= ] unit-test
+
+[ f ] [ object class-not object class= ] unit-test
+
+[ f ] [ null class-not null class= ] unit-test
+
+! Test for hangs?
+: random-class classes random ;
+
+: random-op
+ {
+ class-and
+ class-or
+ class-not
+ } random ;
+
+10 [
+ [ ] [
+ 20 [ drop random-op ] map >quotation
+ [ infer effect-in [ random-class ] times ] keep
+ call
+ drop
+ ] unit-test
+] times
+
+: random-boolean
+ { t f } random ;
+
+: boolean>class
+ object null ? ;
+
+: random-boolean-op
+ {
+ and
+ or
+ not
+ xor
+ } random ;
+
+: class-xor [ class-or ] 2keep class-and class-not class-and ;
+
+: boolean-op>class-op
+ {
+ { and class-and }
+ { or class-or }
+ { not class-not }
+ { xor class-xor }
+ } at ;
+
+20 [
+ [ t ] [
+ 20 [ drop random-boolean-op ] [ ] map-as dup .
+ [ infer effect-in [ drop random-boolean ] map dup . ] keep
+
+ [ >r [ ] each r> call ] 2keep
+
+ >r [ boolean>class ] each r> [ boolean-op>class-op ] map call object class=
+
+ =
+ ] unit-test
+] times
diff --git a/core/classes/algebra/algebra.factor b/core/classes/algebra/algebra.factor
new file mode 100755
index 0000000000..e2206213a6
--- /dev/null
+++ b/core/classes/algebra/algebra.factor
@@ -0,0 +1,233 @@
+! Copyright (C) 2004, 2008 Slava Pestov.
+! See http://factorcode.org/license.txt for BSD license.
+USING: kernel classes combinators accessors sequences arrays
+vectors assocs namespaces words sorting layouts math hashtables
+;
+IN: classes.algebra
+
+: 2cache ( key1 key2 assoc quot -- value )
+ >r >r 2array r> [ first2 ] r> compose cache ; inline
+
+DEFER: (class<)
+
+: class< ( first second -- ? )
+ class<-cache get [ (class<) ] 2cache ;
+
+DEFER: (class-not)
+
+: class-not ( class -- complement )
+ class-not-cache get [ (class-not) ] cache ;
+
+DEFER: (classes-intersect?) ( first second -- ? )
+
+: classes-intersect? ( first second -- ? )
+ classes-intersect-cache get [ (classes-intersect?) ] 2cache ;
+
+DEFER: (class-and)
+
+: class-and ( first second -- class )
+ class-and-cache get [ (class-and) ] 2cache ;
+
+DEFER: (class-or)
+
+: class-or ( first second -- class )
+ class-or-cache get [ (class-or) ] 2cache ;
+
+TUPLE: anonymous-union members ;
+
+C: <anonymous-union> anonymous-union
+
+TUPLE: anonymous-intersection members ;
+
+C: <anonymous-intersection> anonymous-intersection
+
+TUPLE: anonymous-complement class ;
+
+C: <anonymous-complement> anonymous-complement
+
+: superclass< ( first second -- ? )
+ >r superclass r> class< ;
+
+: left-union-class< ( first second -- ? )
+ >r members r> [ class< ] curry all? ;
+
+: right-union-class< ( first second -- ? )
+ members [ class< ] with contains? ;
+
+: left-anonymous-union< ( first second -- ? )
+ >r members>> r> [ class< ] curry all? ;
+
+: right-anonymous-union< ( first second -- ? )
+ members>> [ class< ] with contains? ;
+
+: left-anonymous-intersection< ( first second -- ? )
+ >r members>> r> [ class< ] curry contains? ;
+
+: right-anonymous-intersection< ( first second -- ? )
+ members>> [ class< ] with all? ;
+
+: anonymous-complement< ( first second -- ? )
+ [ class>> ] 2apply swap class< ;
+
+: (class<) ( first second -- -1/0/1 )
+ {
+ { [ 2dup eq? ] [ 2drop t ] }
+ { [ dup object eq? ] [ 2drop t ] }
+ { [ over null eq? ] [ 2drop t ] }
+ { [ 2dup [ anonymous-complement? ] both? ] [ anonymous-complement< ] }
+ { [ over anonymous-union? ] [ left-anonymous-union< ] }
+ { [ over anonymous-intersection? ] [ left-anonymous-intersection< ] }
+ { [ over anonymous-complement? ] [ 2drop f ] }
+ { [ over members ] [ left-union-class< ] }
+ { [ dup anonymous-union? ] [ right-anonymous-union< ] }
+ { [ dup anonymous-intersection? ] [ right-anonymous-intersection< ] }
+ { [ dup anonymous-complement? ] [ class>> classes-intersect? not ] }
+ { [ dup members ] [ right-union-class< ] }
+ { [ over superclass ] [ superclass< ] }
+ { [ t ] [ 2drop f ] }
+ } cond ;
+
+: anonymous-union-intersect? ( first second -- ? )
+ members>> [ classes-intersect? ] with contains? ;
+
+: anonymous-intersection-intersect? ( first second -- ? )
+ members>> [ classes-intersect? ] with all? ;
+
+: anonymous-complement-intersect? ( first second -- ? )
+ class>> class< not ;
+
+: union-class-intersect? ( first second -- ? )
+ members [ classes-intersect? ] with contains? ;
+
+: tuple-class-intersect? ( first second -- ? )
+ {
+ { [ over tuple eq? ] [ 2drop t ] }
+ { [ over builtin-class? ] [ 2drop f ] }
+ { [ over tuple-class? ] [ [ class< ] 2keep swap class< or ] }
+ { [ t ] [ swap classes-intersect? ] }
+ } cond ;
+
+: builtin-class-intersect? ( first second -- ? )
+ {
+ { [ 2dup eq? ] [ 2drop t ] }
+ { [ over builtin-class? ] [ 2drop f ] }
+ { [ t ] [ swap classes-intersect? ] }
+ } cond ;
+
+: (classes-intersect?) ( first second -- ? )
+ {
+ { [ dup anonymous-union? ] [ anonymous-union-intersect? ] }
+ { [ dup anonymous-intersection? ] [ anonymous-intersection-intersect? ] }
+ { [ dup anonymous-complement? ] [ anonymous-complement-intersect? ] }
+ { [ dup tuple-class? ] [ tuple-class-intersect? ] }
+ { [ dup builtin-class? ] [ builtin-class-intersect? ] }
+ { [ dup superclass ] [ superclass classes-intersect? ] }
+ { [ dup members ] [ union-class-intersect? ] }
+ } cond ;
+
+: left-union-and ( first second -- class )
+ >r members r> [ class-and ] curry map <anonymous-union> ;
+
+: right-union-and ( first second -- class )
+ members [ class-and ] with map <anonymous-union> ;
+
+: left-anonymous-union-and ( first second -- class )
+ >r members>> r> [ class-and ] curry map <anonymous-union> ;
+
+: right-anonymous-union-and ( first second -- class )
+ members>> [ class-and ] with map <anonymous-union> ;
+
+: left-anonymous-intersection-and ( first second -- class )
+ >r members>> r> add <anonymous-intersection> ;
+
+: right-anonymous-intersection-and ( first second -- class )
+ members>> swap add <anonymous-intersection> ;
+
+: (class-and) ( first second -- class )
+ {
+ { [ 2dup class< ] [ drop ] }
+ { [ 2dup swap class< ] [ nip ] }
+ { [ 2dup classes-intersect? not ] [ 2drop null ] }
+ { [ dup members ] [ right-union-and ] }
+ { [ dup anonymous-union? ] [ right-anonymous-union-and ] }
+ { [ dup anonymous-intersection? ] [ right-anonymous-intersection-and ] }
+ { [ over members ] [ left-union-and ] }
+ { [ over anonymous-union? ] [ left-anonymous-union-and ] }
+ { [ over anonymous-intersection? ] [ left-anonymous-intersection-and ] }
+ { [ t ] [ 2array <anonymous-intersection> ] }
+ } cond ;
+
+: left-anonymous-union-or ( first second -- class )
+ >r members>> r> add <anonymous-union> ;
+
+: right-anonymous-union-or ( first second -- class )
+ members>> swap add <anonymous-union> ;
+
+: (class-or) ( first second -- class )
+ {
+ { [ 2dup class< ] [ nip ] }
+ { [ 2dup swap class< ] [ drop ] }
+ { [ dup anonymous-union? ] [ right-anonymous-union-or ] }
+ { [ over anonymous-union? ] [ left-anonymous-union-or ] }
+ { [ t ] [ 2array <anonymous-union> ] }
+ } cond ;
+
+: (class-not) ( class -- complement )
+ {
+ { [ dup anonymous-complement? ] [ class>> ] }
+ { [ dup object eq? ] [ drop null ] }
+ { [ dup null eq? ] [ drop object ] }
+ { [ t ] [ <anonymous-complement> ] }
+ } cond ;
+
+: largest-class ( seq -- n elt )
+ dup [
+ [ 2dup class< >r swap class< not r> and ]
+ with subset empty?
+ ] curry find [ "Topological sort failed" throw ] unless* ;
+
+: sort-classes ( seq -- newseq )
+ >vector
+ [ dup empty? not ]
+ [ dup largest-class >r over delete-nth r> ]
+ [ ] unfold nip ;
+
+: min-class ( class seq -- class/f )
+ [ dupd classes-intersect? ] subset dup empty? [
+ 2drop f
+ ] [
+ tuck [ class< ] with all? [ peek ] [ drop f ] if
+ ] if ;
+
+: (flatten-class) ( class -- )
+ {
+ { [ dup tuple-class? ] [ dup set ] }
+ { [ dup builtin-class? ] [ dup set ] }
+ { [ dup members ] [ members [ (flatten-class) ] each ] }
+ { [ dup superclass ] [ superclass (flatten-class) ] }
+ { [ t ] [ drop ] }
+ } cond ;
+
+: flatten-class ( class -- assoc )
+ [ (flatten-class) ] H{ } make-assoc ;
+
+: class-hashes ( class -- seq )
+ flatten-class keys [
+ dup builtin-class?
+ [ "type" word-prop ] [ hashcode ] if
+ ] map ;
+
+: flatten-builtin-class ( class -- assoc )
+ flatten-class [
+ dup tuple class< [ 2drop tuple tuple ] when
+ ] assoc-map ;
+
+: class-types ( class -- seq )
+ flatten-builtin-class keys
+ [ "type" word-prop ] map natural-sort ;
+
+: class-tags ( class -- tag/f )
+ class-types [
+ dup num-tags get >=
+ [ drop object tag-number ] when
+ ] map prune ;
diff --git a/core/classes/classes-docs.factor b/core/classes/classes-docs.factor
index 1e71173153..9573de8949 100755
--- a/core/classes/classes-docs.factor
+++ b/core/classes/classes-docs.factor
@@ -12,21 +12,6 @@ $nl
{ $subsection builtin-class? }
"See " { $link "type-index" } " for a list of built-in classes." ;
-ARTICLE: "class-operations" "Class operations"
-"Set-theoretic operations on classes:"
-{ $subsection class< }
-{ $subsection class-and }
-{ $subsection class-or }
-{ $subsection classes-intersect? }
-"Topological sort:"
-{ $subsection sort-classes }
-{ $subsection min-class }
-"Low-level implementation detail:"
-{ $subsection types }
-{ $subsection flatten-class }
-{ $subsection flatten-builtin-class }
-{ $subsection flatten-union-class } ;
-
ARTICLE: "class-predicates" "Class predicate words"
"With a handful of exceptions, each class has a membership predicate word, named " { $snippet { $emphasis "class" } "?" } " . A quotation calling this predicate is stored in the " { $snippet "\"predicate\"" } " word property."
$nl
@@ -93,15 +78,9 @@ HELP: tuple-class
{ $class-description "The class of tuple class words." }
{ $examples { $example "USING: classes prettyprint ;" "TUPLE: name title first last ;" "name tuple-class? ." "t" } } ;
-HELP: typemap
-{ $var-description "Hashtable mapping unions to class words, used to implement " { $link class-and } " and " { $link class-or } "." } ;
-
HELP: builtins
{ $var-description "Vector mapping type numbers to builtin class words." } ;
-HELP: class<map
-{ $var-description "Hashtable mapping each class to a set of classes which are contained in that class under the " { $link (class<) } " relation. The " { $link class< } " word uses this hashtable to avoid frequent expensive calls to " { $link (class<) } "." } ;
-
HELP: update-map
{ $var-description "Hashtable mapping each class to a set of classes defined in terms of this class. The " { $link define-class } " word uses this information to update generic words when classes are redefined." } ;
@@ -121,70 +100,13 @@ $low-level-note ;
HELP: superclass
{ $values { "class" class } { "super" class } }
-{ $description "Outputs the superclass of a class. All instances of this class are also instances of the superclass." }
-{ $notes "If " { $link class< } " yields that one class is a subtype of another, it does not imply that a superclass relation is involved. The superclass relation is a technical implementation detail of predicate and tuple classes." } ;
+{ $description "Outputs the superclass of a class. All instances of this class are also instances of the superclass." } ;
HELP: members
{ $values { "class" class } { "seq" "a sequence of union members, or " { $link f } } }
{ $description "If " { $snippet "class" } " is a union class, outputs a sequence of its member classes, otherwise outputs " { $link f } "." } ;
-HELP: flatten-union-class
-{ $values { "class" class } { "assoc" "an assoc whose keys are classes" } }
-{ $description "Outputs the set of classes whose union is equal to " { $snippet "class" } ". Unions are expanded recursively so the output assoc does not contain any union classes. However, it may contain predicate classes whose superclasses are unions." } ;
-
-HELP: flatten-builtin-class
-{ $values { "class" class } { "assoc" "an assoc whose keys are classes" } }
-{ $description "Outputs a set of tuple classes whose union is the smallest cover of " { $snippet "class" } " intersected with " { $link tuple } "." } ;
-
-HELP: flatten-class
-{ $values { "class" class } { "assoc" "an assoc whose keys are classes" } }
-{ $description "Outputs a set of builtin and tuple classes whose union is the smallest cover of " { $snippet "class" } "." } ;
-
-HELP: types
-{ $values { "class" class } { "seq" "an increasing sequence of integers" } }
-{ $description "Outputs a sequence of builtin type numbers whose instances can possibly be instances of the given class." } ;
-
-HELP: class-empty?
-{ $values { "class" "a class" } { "?" "a boolean" } }
-{ $description "Tests if a class is a union class with no members." }
-{ $examples { $example "USING: classes kernel prettyprint ;" "null class-empty? ." "t" } } ;
-
-HELP: (class<)
-{ $values { "class1" "a class" } { "class2" "a class" } { "?" "a boolean" } }
-{ $description "Performs the calculation for " { $link class< } ". There is never any reason to call this word from user code since " { $link class< } " outputs identical values and caches results for better performance." } ;
-
-HELP: class<
-{ $values { "class1" "a class" } { "class2" "a class" } { "?" "a boolean" } }
-{ $description "Tests if all instances of " { $snippet "class1" } " are also instances of " { $snippet "class2" } "." }
-{ $notes "Classes are partially ordered. This means that if " { $snippet "class1 <= class2" } " and " { $snippet "class2 <= class1" } ", then " { $snippet "class1 = class2" } ". Also, if " { $snippet "class1 <= class2" } " and " { $snippet "class2 <= class3" } ", then " { $snippet "class1 <= class3" } "." } ;
-
-HELP: sort-classes
-{ $values { "seq" "a sequence of class" } { "newseq" "a new seqence of classes" } }
-{ $description "Outputs a topological sort of a sequence of classes. Larger classes come before their subclasses." } ;
-
-HELP: lookup-union
-{ $values { "classes" "a hashtable mapping class words to themselves" } { "class" class } }
-{ $description "Given a set of classes represented as a hashtable with equal keys and values, looks up a previously-defined union class having those members. If no union is defined, outputs " { $link object } "." } ;
-
-{ class-and class-or lookup-union } related-words
-
-HELP: class-or
-{ $values { "class1" class } { "class2" class } { "class" class } }
-{ $description "Outputs the smallest known class containing both " { $snippet "class1" } " and " { $snippet "class2" } "." } ;
-
-HELP: class-and
-{ $values { "class1" class } { "class2" class } { "class" class } }
-{ $description "Outputs the largest known class contained in both " { $snippet "class1" } " and " { $snippet "class2" } ". If the intersection is non-empty but no union class with those exact members is defined, outputs " { $link object } ". If the intersection is empty, outputs " { $link null } "." } ;
-
-HELP: classes-intersect?
-{ $values { "class1" class } { "class2" class } { "?" "a boolean" } }
-{ $description "Tests if two classes have a non-empty intersection. If the intersection is empty, no object can be an instance of both classes at once." } ;
-
-HELP: min-class
-{ $values { "class" class } { "seq" "a sequence of class words" } { "class/f" "a class word or " { $link f } } }
-{ $description "If all classes in " { $snippet "seq" } " that intersect " { $snippet "class" } " are subtypes of " { $snippet "class" } ", outputs the last such element of " { $snippet "seq" } ". If any conditions fail to hold, outputs " { $link f } "." } ;
-
HELP: define-class
{ $values { "word" word } { "members" "a sequence of class words" } { "superclass" class } { "metaclass" class } }
-{ $description "Sets a property indicating this word is a class word, thus making it an instance of " { $link class } ", and registers it with " { $link typemap } " and " { $link class<map } "." }
+{ $description "Sets a property indicating this word is a class word, thus making it an instance of " { $link class } ", and registers it with " { $link update-map } "." }
$low-level-note ;
diff --git a/core/classes/classes-tests.factor b/core/classes/classes-tests.factor
index 3322c3b043..8f43aa3336 100755
--- a/core/classes/classes-tests.factor
+++ b/core/classes/classes-tests.factor
@@ -2,64 +2,10 @@ USING: alien arrays definitions generic assocs hashtables io
kernel math namespaces parser prettyprint sequences strings
tools.test vectors words quotations classes
classes.private classes.union classes.mixin classes.predicate
-vectors definitions source-files compiler.units ;
+classes.algebra vectors definitions source-files
+compiler.units ;
IN: classes.tests
-H{ } "s" set
-
-[ ] [ 1 2 "s" get push-at ] unit-test
-[ 1 ] [ 2 "s" get at first ] unit-test
-[ ] [ 1 2 "s" get pop-at ] unit-test
-[ t ] [ 2 "s" get at empty? ] unit-test
-
-[ object ] [ object object class-and ] unit-test
-[ fixnum ] [ fixnum object class-and ] unit-test
-[ fixnum ] [ object fixnum class-and ] unit-test
-[ fixnum ] [ fixnum fixnum class-and ] unit-test
-[ fixnum ] [ fixnum integer class-and ] unit-test
-[ fixnum ] [ integer fixnum class-and ] unit-test
-[ null ] [ vector fixnum class-and ] unit-test
-[ number ] [ number object class-and ] unit-test
-[ number ] [ object number class-and ] unit-test
-[ null ] [ slice reversed class-and ] unit-test
-[ null ] [ general-t \ f class-and ] unit-test
-[ object ] [ general-t \ f class-or ] unit-test
-
-TUPLE: first-one ;
-TUPLE: second-one ;
-UNION: both first-one union-class ;
-
-[ t ] [ both tuple classes-intersect? ] unit-test
-[ null ] [ vector virtual-sequence class-and ] unit-test
-[ f ] [ vector virtual-sequence classes-intersect? ] unit-test
-
-[ t ] [ \ fixnum \ integer class< ] unit-test
-[ t ] [ \ fixnum \ fixnum class< ] unit-test
-[ f ] [ \ integer \ fixnum class< ] unit-test
-[ t ] [ \ integer \ object class< ] unit-test
-[ f ] [ \ integer \ null class< ] unit-test
-[ t ] [ \ null \ object class< ] unit-test
-
-[ t ] [ \ generic \ word class< ] unit-test
-[ f ] [ \ word \ generic class< ] unit-test
-
-[ f ] [ \ reversed \ slice class< ] unit-test
-[ f ] [ \ slice \ reversed class< ] unit-test
-
-PREDICATE: word no-docs "documentation" word-prop not ;
-
-UNION: no-docs-union no-docs integer ;
-
-[ t ] [ no-docs no-docs-union class< ] unit-test
-[ f ] [ no-docs-union no-docs class< ] unit-test
-
-TUPLE: a ;
-TUPLE: b ;
-UNION: c a b ;
-
-[ t ] [ \ c \ tuple class< ] unit-test
-[ f ] [ \ tuple \ c class< ] unit-test
-
! DEFER: bah
! FORGET: bah
UNION: bah fixnum alien ;
@@ -76,16 +22,12 @@ M: union-1 generic-update-test drop "union-1" ;
[ t ] [ union-1 number class< ] unit-test
[ "union-1" ] [ 1.0 generic-update-test ] unit-test
-[ union-1 ] [ fixnum float class-or ] unit-test
-
"IN: classes.tests USE: math USE: arrays UNION: union-1 rational array ;" eval
[ t ] [ bignum union-1 class< ] unit-test
[ f ] [ union-1 number class< ] unit-test
[ "union-1" ] [ { 1.0 } generic-update-test ] unit-test
-[ object ] [ fixnum float class-or ] unit-test
-
"IN: classes.tests USE: math PREDICATE: integer union-1 even? ;" eval
[ f ] [ union-1 union-class? ] unit-test
@@ -118,6 +60,9 @@ M: assoc-mixin collection-size assoc-size ;
[ 2 ] [ H{ { 1 2 } { 2 3 } } collection-size ] unit-test
! Test mixing in of new classes after the fact
+DEFER: mx1
+FORGET: mx1
+
MIXIN: mx1
INSTANCE: integer mx1
@@ -131,12 +76,8 @@ INSTANCE: integer mx1
[ t ] [ array mx1 class< ] unit-test
[ f ] [ mx1 number class< ] unit-test
-[ mx1 ] [ array integer class-or ] unit-test
-
[ \ mx1 forget ] with-compilation-unit
-[ f ] [ array integer class-or mx1 = ] unit-test
-
! Empty unions were causing problems
GENERIC: empty-union-test
@@ -155,28 +96,12 @@ UNION: redefine-bug-2 redefine-bug-1 quotation ;
[ t ] [ fixnum redefine-bug-2 class< ] unit-test
[ t ] [ quotation redefine-bug-2 class< ] unit-test
-[ redefine-bug-2 ] [ fixnum quotation class-or ] unit-test
[ ] [ "IN: classes.tests USE: math UNION: redefine-bug-1 bignum ;" eval ] unit-test
[ t ] [ bignum redefine-bug-1 class< ] unit-test
[ f ] [ fixnum redefine-bug-2 class< ] unit-test
[ t ] [ bignum redefine-bug-2 class< ] unit-test
-[ f ] [ fixnum quotation class-or redefine-bug-2 eq? ] unit-test
-[ redefine-bug-2 ] [ bignum quotation class-or ] unit-test
-
-! Another issue similar to the above
-UNION: forget-class-bug-1 integer ;
-UNION: forget-class-bug-2 forget-class-bug-1 dll ;
-
-[
- \ forget-class-bug-1 forget
- \ forget-class-bug-2 forget
-] with-compilation-unit
-
-[ f ] [ forget-class-bug-1 typemap get values [ memq? ] with contains? ] unit-test
-
-[ f ] [ forget-class-bug-2 typemap get values [ memq? ] with contains? ] unit-test
USE: io.streams.string
diff --git a/core/classes/classes.factor b/core/classes/classes.factor
index e47dbd20e5..e5039d8050 100755
--- a/core/classes/classes.factor
+++ b/core/classes/classes.factor
@@ -1,15 +1,32 @@
! Copyright (C) 2004, 2008 Slava Pestov.
! See http://factorcode.org/license.txt for BSD license.
+USING: arrays definitions assocs kernel kernel.private
+slots.private namespaces sequences strings words vectors math
+quotations combinators sorting effects graphs vocabs ;
IN: classes
-USING: arrays definitions assocs kernel
-kernel.private slots.private namespaces sequences strings words
-vectors math quotations combinators sorting effects graphs ;
+
+SYMBOL: class<-cache
+SYMBOL: class-not-cache
+SYMBOL: classes-intersect-cache
+SYMBOL: class-and-cache
+SYMBOL: class-or-cache
+
+: init-caches ( -- )
+ H{ } clone class<-cache set
+ H{ } clone class-not-cache set
+ H{ } clone classes-intersect-cache set
+ H{ } clone class-and-cache set
+ H{ } clone class-or-cache set ;
+
+: reset-caches ( -- )
+ class<-cache get clear-assoc
+ class-not-cache get clear-assoc
+ classes-intersect-cache get clear-assoc
+ class-and-cache get clear-assoc
+ class-or-cache get clear-assoc ;
PREDICATE: word class ( obj -- ? ) "class" word-prop ;
-SYMBOL: typemap
-SYMBOL: class-map
-SYMBOL: class<map
SYMBOL: update-map
SYMBOL: builtins
@@ -19,7 +36,7 @@ PREDICATE: class builtin-class
PREDICATE: class tuple-class
"metaclass" word-prop tuple-class eq? ;
-: classes ( -- seq ) class<map get keys ;
+: classes ( -- seq ) all-words [ class? ] subset ;
: type>class ( n -- class ) builtins get-global nth ;
@@ -37,146 +54,12 @@ PREDICATE: word predicate "predicating" word-prop >boolean ;
r> predicate-effect define-declared ;
: superclass ( class -- super )
- "superclass" word-prop ;
+ #! Output f for non-classes to work with algebra code
+ dup class? [ "superclass" word-prop ] [ drop f ] if ;
-: members ( class -- seq ) "members" word-prop ;
-
-: class-empty? ( class -- ? ) members dup [ empty? ] when ;
-
-: (flatten-union-class) ( class -- )
- dup members [
- [ (flatten-union-class) ] each
- ] [
- dup set
- ] ?if ;
-
-: flatten-union-class ( class -- assoc )
- [ (flatten-union-class) ] H{ } make-assoc ;
-
-: (flatten-class) ( class -- )
- {
- { [ dup tuple-class? ] [ dup set ] }
- { [ dup builtin-class? ] [ dup set ] }
- { [ dup members ] [ members [ (flatten-class) ] each ] }
- { [ dup superclass ] [ superclass (flatten-class) ] }
- { [ t ] [ drop ] }
- } cond ;
-
-: flatten-class ( class -- assoc )
- [ (flatten-class) ] H{ } make-assoc ;
-
-: class-hashes ( class -- seq )
- flatten-class keys [
- dup builtin-class?
- [ "type" word-prop ] [ hashcode ] if
- ] map ;
-
-: (flatten-builtin-class) ( class -- )
- {
- { [ dup members ] [ members [ (flatten-builtin-class) ] each ] }
- { [ dup superclass ] [ superclass (flatten-builtin-class) ] }
- { [ t ] [ dup set ] }
- } cond ;
-
-: flatten-builtin-class ( class -- assoc )
- [ (flatten-builtin-class) ] H{ } make-assoc ;
-
-: types ( class -- seq )
- flatten-builtin-class keys
- [ "type" word-prop ] map natural-sort ;
-
-: class< ( class1 class2 -- ? ) swap class<map get at key? ;
-
-<PRIVATE
-
-DEFER: (class<)
-
-: superclass< ( cls1 cls2 -- ? )
- >r superclass r> 2dup and [ (class<) ] [ 2drop f ] if ;
-
-: union-class< ( cls1 cls2 -- ? )
- [ flatten-union-class ] 2apply keys
- [ nip [ (class<) ] with contains? ] curry assoc-all? ;
-
-: (class<) ( class1 class2 -- ? )
- {
- { [ 2dup eq? ] [ 2drop t ] }
- { [ over class-empty? ] [ 2drop t ] }
- { [ 2dup superclass< ] [ 2drop t ] }
- { [ 2dup [ members not ] both? ] [ 2drop f ] }
- { [ t ] [ union-class< ] }
- } cond ;
-
-: lookup-union ( classes -- class )
- typemap get at dup empty? [ drop object ] [ first ] if ;
-
-: lookup-tuple-union ( classes -- class )
- class-map get at dup empty? [ drop object ] [ first ] if ;
-
-! : (class-or) ( class class -- class )
-! [ flatten-builtin-class ] 2apply union lookup-union ;
-!
-! : (class-and) ( class class -- class )
-! [ flatten-builtin-class ] 2apply intersect lookup-union ;
-
-: class-or-fixup ( set set -- set )
- union
- tuple over key?
- [ [ drop tuple-class? not ] assoc-subset ] when ;
-
-: (class-or) ( class class -- class )
- [ flatten-class ] 2apply class-or-fixup lookup-tuple-union ;
-
-: (class-and) ( class class -- class )
- 2dup [ tuple swap class< ] either? [
- [ flatten-builtin-class ] 2apply
- intersect lookup-union
- ] [
- [ flatten-class ] 2apply
- intersect lookup-tuple-union
- ] if ;
-
-: tuple-class-and ( class1 class2 -- class )
- dupd eq? [ drop null ] unless ;
-
-: largest-class ( seq -- n elt )
- dup [
- [ 2dup class< >r swap class< not r> and ]
- with subset empty?
- ] curry find [ "Topological sort failed" throw ] unless* ;
-
-PRIVATE>
-
-: sort-classes ( seq -- newseq )
- >vector
- [ dup empty? not ]
- [ dup largest-class >r over delete-nth r> ]
- [ ] unfold nip ;
-
-: class-or ( class1 class2 -- class )
- {
- { [ 2dup class< ] [ nip ] }
- { [ 2dup swap class< ] [ drop ] }
- { [ t ] [ (class-or) ] }
- } cond ;
-
-: class-and ( class1 class2 -- class )
- {
- { [ 2dup class< ] [ drop ] }
- { [ 2dup swap class< ] [ nip ] }
- { [ 2dup [ tuple-class? ] both? ] [ tuple-class-and ] }
- { [ t ] [ (class-and) ] }
- } cond ;
-
-: classes-intersect? ( class1 class2 -- ? )
- class-and class-empty? not ;
-
-: min-class ( class seq -- class/f )
- [ dupd classes-intersect? ] subset dup empty? [
- 2drop f
- ] [
- tuck [ class< ] with all? [ peek ] [ drop f ] if
- ] if ;
+: members ( class -- seq )
+ #! Output f for non-classes to work with algebra code
+ dup class? [ "members" word-prop ] [ drop f ] if ;
GENERIC: reset-class ( class -- )
@@ -184,36 +67,9 @@ M: word reset-class drop ;
<PRIVATE
-! class<map
-: bigger-classes ( class -- seq )
- classes [ (class<) ] with subset ;
-
-: bigger-classes+ ( class -- )
- [ bigger-classes [ dup ] H{ } map>assoc ] keep
- class<map get set-at ;
-
-: bigger-classes- ( class -- )
- class<map get delete-at ;
-
-: smaller-classes ( class -- seq )
- classes swap [ (class<) ] curry subset ;
-
-: smaller-classes+ ( class -- )
- dup smaller-classes class<map get add-vertex ;
-
-: smaller-classes- ( class -- )
- dup smaller-classes class<map get remove-vertex ;
-
-: class<map+ ( class -- )
- H{ } clone over class<map get set-at
- dup smaller-classes+ bigger-classes+ ;
-
-: class<map- ( class -- )
- dup smaller-classes- bigger-classes- ;
-
! update-map
: class-uses ( class -- seq )
- [ dup members % superclass [ , ] when* ] { } make ;
+ dup members swap superclass [ add ] when* ;
: class-usages ( class -- assoc )
[ update-map get at ] closure ;
@@ -224,47 +80,6 @@ M: word reset-class drop ;
: update-map- ( class -- )
dup class-uses update-map get remove-vertex ;
-! typemap
-: push-at ( value key assoc -- )
- 2dup at* [
- 2nip push
- ] [
- drop >r >r 1vector r> r> set-at
- ] if ;
-
-: typemap+ ( class -- )
- dup flatten-builtin-class typemap get push-at ;
-
-: pop-at ( value key assoc -- )
- at* [ delete ] [ 2drop ] if ;
-
-: typemap- ( class -- )
- dup flatten-builtin-class typemap get pop-at ;
-
-! class-map
-: class-map+ ( class -- )
- dup flatten-class class-map get push-at ;
-
-: class-map- ( class -- )
- dup flatten-class class-map get pop-at ;
-
-! Class definition
-: cache-class ( class -- )
- dup typemap+ dup class-map+ dup class<map+ update-map+ ;
-
-: cache-classes ( assoc -- )
- [ drop cache-class ] assoc-each ;
-
-GENERIC: uncache-class ( class -- )
-
-M: class uncache-class
- dup update-map- dup class<map- dup class-map- typemap- ;
-
-M: word uncache-class drop ;
-
-: uncache-classes ( assoc -- )
- [ drop uncache-class ] assoc-each ;
-
PRIVATE>
: define-class-props ( members superclass metaclass -- assoc )
@@ -293,14 +108,12 @@ GENERIC: update-methods ( assoc -- )
: define-class ( word members superclass metaclass -- )
#! If it was already a class, update methods after.
+ reset-caches
define-class-props
- over class? >r
- over class-usages [
- uncache-classes
- dupd (define-class)
- ] keep cache-classes r>
- [ class-usages dup update-predicates update-methods ]
- [ drop ] if ;
+ over update-map-
+ dupd (define-class)
+ dup update-map+
+ class-usages dup update-predicates update-methods ;
GENERIC: class ( object -- class ) inline
diff --git a/core/generator/registers/registers.factor b/core/generator/registers/registers.factor
index 307e3a99f1..e03923e860 100755
--- a/core/generator/registers/registers.factor
+++ b/core/generator/registers/registers.factor
@@ -1,9 +1,9 @@
! Copyright (C) 2006, 2007 Slava Pestov.
! See http://factorcode.org/license.txt for BSD license.
-USING: arrays assocs classes classes.private combinators
-cpu.architecture generator.fixup hashtables kernel layouts math
-namespaces quotations sequences system vectors words effects
-alien byte-arrays bit-arrays float-arrays ;
+USING: arrays assocs classes classes.private classes.algebra
+combinators cpu.architecture generator.fixup hashtables kernel
+layouts math namespaces quotations sequences system vectors
+words effects alien byte-arrays bit-arrays float-arrays ;
IN: generator.registers
SYMBOL: +input+
@@ -581,13 +581,14 @@ M: loc lazy-store
2drop t
] if ;
+: class-tags ( class -- tag/f )
+ class-types [
+ dup num-tags get >=
+ [ drop object tag-number ] when
+ ] map prune ;
+
: class-tag ( class -- tag/f )
- dup hi-tag class< [
- drop object tag-number
- ] [
- flatten-builtin-class keys
- dup length 1 = [ first tag-number ] [ drop f ] if
- ] if ;
+ class-tags dup length 1 = [ first ] [ drop f ] if ;
: class-matches? ( actual expected -- ? )
{
diff --git a/core/generic/generic-docs.factor b/core/generic/generic-docs.factor
index b59c92c798..56de801e7a 100755
--- a/core/generic/generic-docs.factor
+++ b/core/generic/generic-docs.factor
@@ -1,6 +1,6 @@
-USING: help.markup help.syntax words classes definitions kernel
-alien sequences math quotations generic.standard generic.math
-combinators ;
+USING: help.markup help.syntax words classes classes.algebra
+definitions kernel alien sequences math quotations
+generic.standard generic.math combinators ;
IN: generic
ARTICLE: "method-order" "Method precedence"
diff --git a/core/generic/generic-tests.factor b/core/generic/generic-tests.factor
index 785600cfb0..853a03d184 100755
--- a/core/generic/generic-tests.factor
+++ b/core/generic/generic-tests.factor
@@ -1,8 +1,8 @@
USING: alien arrays definitions generic generic.standard
generic.math assocs hashtables io kernel math namespaces parser
prettyprint sequences strings tools.test vectors words
-quotations classes continuations layouts classes.union sorting
-compiler.units ;
+quotations classes classes.algebra continuations layouts
+classes.union sorting compiler.units ;
IN: generic.tests
GENERIC: foobar ( x -- y )
diff --git a/core/generic/generic.factor b/core/generic/generic.factor
index 8fe5e4921a..36ca0358b7 100755
--- a/core/generic/generic.factor
+++ b/core/generic/generic.factor
@@ -2,7 +2,7 @@
! See http://factorcode.org/license.txt for BSD license.
USING: words kernel sequences namespaces assocs hashtables
definitions kernel.private classes classes.private
-quotations arrays vocabs effects ;
+classes.algebra quotations arrays vocabs effects ;
IN: generic
! Method combination protocol
@@ -138,7 +138,7 @@ M: method-body forget*
M: class forget* ( class -- )
dup forget-methods
- dup uncache-class
+ dup update-map-
forget-word ;
M: assoc update-methods ( assoc -- )
diff --git a/core/generic/math/math.factor b/core/generic/math/math.factor
index 46f57a1629..93c89af25c 100755
--- a/core/generic/math/math.factor
+++ b/core/generic/math/math.factor
@@ -1,8 +1,8 @@
-! Copyright (C) 2005, 2007 Slava Pestov.
+! Copyright (C) 2005, 2008 Slava Pestov.
! See http://factorcode.org/license.txt for BSD license.
USING: arrays generic hashtables kernel kernel.private
math namespaces sequences words quotations layouts combinators
-sequences.private classes definitions ;
+sequences.private classes classes.algebra definitions ;
IN: generic.math
PREDICATE: class math-class ( object -- ? )
@@ -16,8 +16,8 @@ PREDICATE: class math-class ( object -- ? )
: math-precedence ( class -- n )
{
- { [ dup class-empty? ] [ drop { -1 -1 } ] }
- { [ dup math-class? ] [ types last/first ] }
+ { [ dup null class< ] [ drop { -1 -1 } ] }
+ { [ dup math-class? ] [ class-types last/first ] }
{ [ t ] [ drop { 100 100 } ] }
} cond ;
diff --git a/core/generic/standard/standard.factor b/core/generic/standard/standard.factor
index 37f72e7d95..4105a05cb1 100755
--- a/core/generic/standard/standard.factor
+++ b/core/generic/standard/standard.factor
@@ -3,7 +3,7 @@
USING: arrays assocs kernel kernel.private slots.private math
namespaces sequences vectors words quotations definitions
hashtables layouts combinators sequences.private generic
-classes classes.private ;
+classes classes.algebra classes.private ;
IN: generic.standard
TUPLE: standard-combination # ;
diff --git a/core/inference/class/class.factor b/core/inference/class/class.factor
index 690571de98..7764fd4fd1 100755
--- a/core/inference/class/class.factor
+++ b/core/inference/class/class.factor
@@ -2,8 +2,8 @@
! See http://factorcode.org/license.txt for BSD license.
USING: arrays generic assocs hashtables inference kernel
math namespaces sequences words parser math.intervals
-effects classes inference.dataflow inference.backend
-combinators ;
+effects classes classes.algebra inference.dataflow
+inference.backend combinators ;
IN: inference.class
! Class inference
@@ -88,8 +88,11 @@ M: interval-constraint apply-constraint
swap interval-constraint-value intersect-value-interval ;
: set-class-interval ( class value -- )
- >r "interval" word-prop dup
- [ r> set-value-interval* ] [ r> 2drop ] if ;
+ over class? [
+ over "interval" word-prop [
+ >r "interval" word-prop r> set-value-interval*
+ ] [ 2drop ] if
+ ] [ 2drop ] if ;
: value-class* ( value -- class )
value-classes get at object or ;
diff --git a/core/io/encodings/encodings-docs.factor b/core/io/encodings/encodings-docs.factor
index fd5ddaa82d..d5bdf24dc0 100644
--- a/core/io/encodings/encodings-docs.factor
+++ b/core/io/encodings/encodings-docs.factor
@@ -37,10 +37,11 @@ HELP: <encoder-duplex>
ARTICLE: "encodings-descriptors" "Encoding descriptors"
"An encoding descriptor is something which can be used for input or output streams to encode or decode files. It must conform to the " { $link "encodings-protocol" } ". Encodings which you can use are defined in the following vocabularies:"
-$nl { $vocab-link "io.encodings.utf8" }
-$nl { $vocab-link "io.encodings.ascii" }
-$nl { $vocab-link "io.encodings.binary" }
-$nl { $vocab-link "io.encodings.utf16" } ;
+{ $vocab-subsection "io.encodings.utf8" }
+{ $vocab-subsection "io.encodings.ascii" }
+{ $vocab-subsection "io.encodings.8-bit" }
+{ $vocab-subsection "io.encodings.binary" }
+{ $vocab-subsection "io.encodings.utf16" } ;
ARTICLE: "encodings-protocol" "Encoding protocol"
"An encoding descriptor must implement the following methods. The methods are implemented on tuple classes by instantiating the class and calling the method again."
diff --git a/core/io/io-tests.factor b/core/io/io-tests.factor
index 8a9089a564..91e51f25b0 100755
--- a/core/io/io-tests.factor
+++ b/core/io/io-tests.factor
@@ -1,5 +1,5 @@
USING: arrays io io.files kernel math parser strings system
-tools.test words namespaces io.encodings.latin1
+tools.test words namespaces io.encodings.8-bit
io.encodings.binary ;
IN: io.tests
@@ -9,7 +9,7 @@ IN: io.tests
] unit-test
: <resource-reader> ( resource -- stream )
- resource-path latin1 <file-reader> ;
+ resource-path iso-8859-1 <file-reader> ;
[
"This is a line.\rThis is another line.\r"
diff --git a/core/optimizer/control/control.factor b/core/optimizer/control/control.factor
index b04d4677ce..c108e3b1a7 100755
--- a/core/optimizer/control/control.factor
+++ b/core/optimizer/control/control.factor
@@ -3,8 +3,8 @@
USING: arrays generic assocs inference inference.class
inference.dataflow inference.backend inference.state io kernel
math namespaces sequences vectors words quotations hashtables
-combinators classes generic.math continuations optimizer.def-use
-optimizer.backend generic.standard ;
+combinators classes classes.algebra generic.math continuations
+optimizer.def-use optimizer.backend generic.standard ;
IN: optimizer.control
! ! ! Rudimentary CFA
diff --git a/core/optimizer/inlining/inlining.factor b/core/optimizer/inlining/inlining.factor
index 04d7ab4ee5..1f3df92421 100755
--- a/core/optimizer/inlining/inlining.factor
+++ b/core/optimizer/inlining/inlining.factor
@@ -3,10 +3,10 @@
USING: arrays generic assocs inference inference.class
inference.dataflow inference.backend inference.state io kernel
math namespaces sequences vectors words quotations hashtables
-combinators classes generic.math continuations optimizer.def-use
-optimizer.backend generic.standard optimizer.specializers
-optimizer.def-use optimizer.pattern-match generic.standard
-optimizer.control kernel.private ;
+combinators classes classes.algebra generic.math continuations
+optimizer.def-use optimizer.backend generic.standard
+optimizer.specializers optimizer.def-use optimizer.pattern-match
+generic.standard optimizer.control kernel.private ;
IN: optimizer.inlining
: remember-inlining ( node history -- )
@@ -175,7 +175,7 @@ DEFER: (flat-length)
: optimistic-inline? ( #call -- ? )
dup node-param "specializer" word-prop dup [
>r node-input-classes r> specialized-length tail*
- [ types length 1 = ] all?
+ [ class-types length 1 = ] all?
] [
2drop f
] if ;
diff --git a/core/optimizer/known-words/known-words.factor b/core/optimizer/known-words/known-words.factor
index 18c98c5115..0a3442566c 100755
--- a/core/optimizer/known-words/known-words.factor
+++ b/core/optimizer/known-words/known-words.factor
@@ -7,8 +7,9 @@ sequences words parser vectors strings sbufs io namespaces
assocs quotations sequences.private io.binary io.crc32
io.streams.string layouts splitting math.intervals
math.floats.private tuples tuples.private classes
-optimizer.def-use optimizer.backend optimizer.pattern-match
-optimizer.inlining float-arrays sequences.private combinators ;
+classes.algebra optimizer.def-use optimizer.backend
+optimizer.pattern-match optimizer.inlining float-arrays
+sequences.private combinators ;
! the output of <tuple> and <tuple-boa> has the class which is
! its second-to-last input
@@ -89,10 +90,10 @@ optimizer.inlining float-arrays sequences.private combinators ;
! type applied to an object of a known type can be folded
: known-type? ( node -- ? )
- node-class-first types length 1 number= ;
+ node-class-first class-types length 1 number= ;
: fold-known-type ( node -- node )
- dup node-class-first types inline-literals ;
+ dup node-class-first class-types inline-literals ;
\ type [
{ [ dup known-type? ] [ fold-known-type ] }
diff --git a/core/optimizer/math/math.factor b/core/optimizer/math/math.factor
index 7afc177d10..349cf88f17 100755
--- a/core/optimizer/math/math.factor
+++ b/core/optimizer/math/math.factor
@@ -5,9 +5,10 @@ USING: alien alien.accessors arrays generic hashtables kernel
assocs math math.private kernel.private sequences words parser
inference.class inference.dataflow vectors strings sbufs io
namespaces assocs quotations math.intervals sequences.private
-combinators splitting layouts math.parser classes generic.math
-optimizer.pattern-match optimizer.backend optimizer.def-use
-optimizer.inlining generic.standard system ;
+combinators splitting layouts math.parser classes
+classes.algebra generic.math optimizer.pattern-match
+optimizer.backend optimizer.def-use optimizer.inlining
+generic.standard system ;
{ + bignum+ float+ fixnum+fast } {
{ { number 0 } [ drop ] }
diff --git a/core/optimizer/optimizer-tests.factor b/core/optimizer/optimizer-tests.factor
index 3abccecc7f..89cea45aee 100755
--- a/core/optimizer/optimizer-tests.factor
+++ b/core/optimizer/optimizer-tests.factor
@@ -1,8 +1,9 @@
USING: arrays compiler.units generic hashtables inference kernel
kernel.private math optimizer prettyprint sequences sbufs
strings tools.test vectors words sequences.private quotations
-optimizer.backend classes inference.dataflow tuples.private
-continuations growable optimizer.inlining namespaces hints ;
+optimizer.backend classes classes.algebra inference.dataflow
+tuples.private continuations growable optimizer.inlining
+namespaces hints ;
IN: optimizer.tests
[ H{ { 1 5 } { 3 4 } { 2 5 } } ] [
diff --git a/core/optimizer/pattern-match/pattern-match.factor b/core/optimizer/pattern-match/pattern-match.factor
old mode 100644
new mode 100755
index ed78330492..0e7e801938
--- a/core/optimizer/pattern-match/pattern-match.factor
+++ b/core/optimizer/pattern-match/pattern-match.factor
@@ -2,7 +2,7 @@
! See http://factorcode.org/license.txt for BSD license.
IN: optimizer.pattern-match
USING: kernel sequences inference namespaces generic
-combinators classes inference.dataflow ;
+combinators classes classes.algebra inference.dataflow ;
! Funny pattern matching
SYMBOL: @
diff --git a/core/tuples/tuples-tests.factor b/core/tuples/tuples-tests.factor
index b5076ea22b..fec3bdbc6f 100755
--- a/core/tuples/tuples-tests.factor
+++ b/core/tuples/tuples-tests.factor
@@ -5,9 +5,6 @@ generic.standard effects tuples tuples.private arrays vectors
strings compiler.units ;
IN: tuples.tests
-[ t ] [ \ tuple-class \ class class< ] unit-test
-[ f ] [ \ class \ tuple-class class< ] unit-test
-
TUPLE: rect x y w h ;
: <rect> rect construct-boa ;
@@ -90,12 +87,6 @@ TUPLE: delegate-clone ;
[ T{ delegate-clone T{ empty f } } ]
[ T{ delegate-clone T{ empty f } } clone ] unit-test
-[ t ] [ \ null \ delegate-clone class< ] unit-test
-[ f ] [ \ object \ delegate-clone class< ] unit-test
-[ f ] [ \ object \ delegate-clone class< ] unit-test
-[ t ] [ \ delegate-clone \ tuple class< ] unit-test
-[ f ] [ \ tuple \ delegate-clone class< ] unit-test
-
! Compiler regression
[ t length ] [ no-method-object t eq? ] must-fail-with
@@ -121,7 +112,7 @@ TUPLE: yo-momma ;
[
[ t ] [ \ yo-momma class? ] unit-test
[ ] [ \ yo-momma forget ] unit-test
- [ f ] [ \ yo-momma typemap get values memq? ] unit-test
+ [ f ] [ \ yo-momma update-map get values memq? ] unit-test
[ f ] [ \ yo-momma crossref get at ] unit-test
] with-compilation-unit
diff --git a/extra/benchmark/reverse-complement/reverse-complement.factor b/extra/benchmark/reverse-complement/reverse-complement.factor
index 9c782e65e6..d83b720187 100755
--- a/extra/benchmark/reverse-complement/reverse-complement.factor
+++ b/extra/benchmark/reverse-complement/reverse-complement.factor
@@ -1,6 +1,6 @@
USING: io io.files io.streams.duplex kernel sequences
sequences.private strings vectors words memoize splitting
-hints unicode.case continuations io.encodings.latin1 ;
+hints unicode.case continuations io.encodings.ascii ;
IN: benchmark.reverse-complement
MEMO: trans-map ( -- str )
@@ -32,8 +32,8 @@ HINTS: do-line vector string ;
readln [ do-line (reverse-complement) ] [ show-seq ] if* ;
: reverse-complement ( infile outfile -- )
- latin1 <file-writer> [
- swap latin1 <file-reader> [
+ ascii <file-writer> [
+ swap ascii <file-reader> [
swap <duplex-stream> [
500000 <vector> (reverse-complement)
] with-stream
diff --git a/extra/combinators/lib/lib-tests.factor b/extra/combinators/lib/lib-tests.factor
index 0a08948346..ed481f72e6 100755
--- a/extra/combinators/lib/lib-tests.factor
+++ b/extra/combinators/lib/lib-tests.factor
@@ -46,3 +46,8 @@ IN: combinators.lib.tests
[ dup array? ] [ dup vector? ] [ dup float? ]
} || nip
] unit-test
+
+
+{ 1 1 } [
+ [ even? ] [ drop 1 ] [ drop 2 ] ifte
+] must-infer-as
diff --git a/extra/http/client/client.factor b/extra/http/client/client.factor
index fc85cce3ad..233b61ea74 100755
--- a/extra/http/client/client.factor
+++ b/extra/http/client/client.factor
@@ -3,7 +3,7 @@
USING: assocs http kernel math math.parser namespaces sequences
io io.sockets io.streams.string io.files io.timeouts strings
splitting calendar continuations accessors vectors
-io.encodings.latin1 io.encodings.binary fry ;
+io.encodings.8-bit io.encodings.binary fry ;
IN: http.client
DEFER: http-request
@@ -52,7 +52,7 @@ PRIVATE>
: http-request ( request -- response stream )
dup request [
- dup request-addr latin1 <client>
+ dup request-addr iso-8859-1 <client>
1 minutes over set-timeout
[
write-request flush
@@ -82,7 +82,7 @@ PRIVATE>
: download-to ( url file -- )
#! Downloads the contents of a URL to a file.
swap http-get-stream swap check-response
- [ swap latin1 <file-writer> stream-copy ] with-disposal ;
+ [ swap iso-8859-1 <file-writer> stream-copy ] with-disposal ;
: download ( url -- )
dup download-name download-to ;
diff --git a/extra/http/server/server.factor b/extra/http/server/server.factor
index 6b3ae52730..3df21adf26 100755
--- a/extra/http/server/server.factor
+++ b/extra/http/server/server.factor
@@ -4,7 +4,7 @@ USING: assocs kernel namespaces io io.timeouts strings splitting
threads http sequences prettyprint io.server logging calendar
html.elements accessors math.parser combinators.lib
tools.vocabs debugger html continuations random combinators
-destructors io.encodings.latin1 fry combinators.cleave ;
+destructors io.encodings.8-bit fry combinators.cleave ;
IN: http.server
GENERIC: call-responder ( path responder -- response )
@@ -217,7 +217,7 @@ SYMBOL: exit-continuation
: httpd ( port -- )
internet-server "http.server"
- latin1 [ handle-client ] with-server ;
+ iso-8859-1 [ handle-client ] with-server ;
: httpd-main ( -- ) 8888 httpd ;
diff --git a/extra/io/encodings/8-bit/8-bit-tests.factor b/extra/io/encodings/8-bit/8-bit-tests.factor
new file mode 100644
index 0000000000..5dbe28cb14
--- /dev/null
+++ b/extra/io/encodings/8-bit/8-bit-tests.factor
@@ -0,0 +1,10 @@
+USING: io.encodings.string io.encodings.8-bit tools.test strings arrays ;
+IN: io.encodings.8-bit.tests
+
+[ B{ CHAR: f CHAR: o CHAR: o } ] [ "foo" iso-8859-1 encode ] unit-test
+[ { 256 } >string iso-8859-1 encode ] must-fail
+[ B{ 255 } ] [ { 255 } iso-8859-1 encode ] unit-test
+
+[ "bar" ] [ "bar" iso-8859-1 decode ] unit-test
+[ { CHAR: b 233 CHAR: r } ] [ { CHAR: b 233 CHAR: r } iso-8859-1 decode >array ] unit-test
+[ { HEX: fffd HEX: 20AC } ] [ { HEX: 81 HEX: 80 } windows-1252 decode >array ] unit-test
diff --git a/extra/io/encodings/8-bit/8-bit.factor b/extra/io/encodings/8-bit/8-bit.factor
new file mode 100644
index 0000000000..2cc6b2e57c
--- /dev/null
+++ b/extra/io/encodings/8-bit/8-bit.factor
@@ -0,0 +1,93 @@
+! Copyright (C) 2008 Daniel Ehrenberg
+! See http://factorcode.org/license.txt for BSD license.
+USING: math.parser arrays io.encodings sequences kernel
+assocs hashtables io.encodings.ascii combinators.cleave
+generic parser tuples words io io.files splitting namespaces
+classes quotations math compiler.units ;
+IN: io.encodings.8-bit
+
+<PRIVATE
+
+: mappings {
+ { "iso-8859-1" "8859-1" }
+ { "iso-8859-2" "8859-2" }
+ { "iso-8859-3" "8859-3" }
+ { "iso-8859-4" "8859-4" }
+ { "iso-8859-5" "8859-5" }
+ { "iso-8859-6" "8859-6" }
+ { "iso-8859-7" "8859-7" }
+ { "iso-8859-8" "8859-8" }
+ { "iso-8859-9" "8859-9" }
+ { "iso-8859-10" "8859-10" }
+ { "iso-8859-11" "8859-11" }
+ { "iso-8859-13" "8859-13" }
+ { "iso-8859-14" "8859-14" }
+ { "iso-8859-15" "8859-15" }
+ { "iso-8859-16" "8859-16" }
+ { "koi8-r" "KOI8-R" }
+ { "windows-1252" "CP1252" }
+ { "ebcdic" "CP037" }
+ { "mac-roman" "ROMAN" }
+} ;
+
+: full-path ( file-name -- path )
+ "extra/io/encodings/8-bit/" ".TXT"
+ swapd 3append resource-path ;
+
+: tail-if ( seq n -- newseq )
+ 2dup swap length <= [ tail ] [ drop ] if ;
+
+: process-contents ( lines -- assoc )
+ [ "#" split first ] map
+ [ empty? not ] subset
+ [ "\t " split 2 head [ 2 tail-if hex> ] map ] map ;
+
+: byte>ch ( assoc -- array )
+ 256 replacement-char <array>
+ [ [ swapd set-nth ] curry assoc-each ] keep ;
+
+: ch>byte ( assoc -- newassoc )
+ [ swap ] assoc-map >hashtable ;
+
+: parse-file ( file-name -- byte>ch ch>byte )
+ full-path ascii file-lines process-contents
+ [ byte>ch ] [ ch>byte ] bi ;
+
+: empty-tuple-class ( string -- class )
+ in get create
+ dup { f } "slots" set-word-prop
+ dup predicate-word drop
+ dup { } define-tuple-class ;
+
+: data-quot ( class word data -- quot )
+ >r [ word-name ] 2apply "/" swap 3append
+ "/data" append in get create dup 1quotation swap r>
+ 1quotation define ;
+
+: method-with-data ( class data word quot -- )
+ >r swap >r 2dup r> data-quot r>
+ compose >r create-method r> define ;
+
+: encode-8-bit ( char stream encoding assoc -- )
+ nip swapd at* [ encode-error ] unless swap stream-write1 ;
+
+: define-encode-char ( class assoc -- )
+ \ encode-char [ encode-8-bit ] method-with-data ;
+
+: decode-8-bit ( stream encoding array -- char/f )
+ nip swap stream-read1
+ [ swap nth [ replacement-char ] unless* ]
+ [ drop f ] if* ;
+
+: define-decode-char ( class array -- )
+ \ decode-char [ decode-8-bit ] method-with-data ;
+
+: 8-bit-methods ( class byte>ch ch>byte -- )
+ >r over r> define-encode-char define-decode-char ;
+
+: define-8-bit-encoding ( tuple-name file-name -- )
+ >r empty-tuple-class r> parse-file 8-bit-methods ;
+
+PRIVATE>
+
+[ mappings [ define-8-bit-encoding ] assoc-each ] with-compilation-unit
diff --git a/extra/io/encodings/8-bit/8859-1.TXT b/extra/io/encodings/8-bit/8859-1.TXT
new file mode 100644
index 0000000000..473ecabc17
--- /dev/null
+++ b/extra/io/encodings/8-bit/8859-1.TXT
@@ -0,0 +1,303 @@
+#
+# Name: ISO/IEC 8859-1:1998 to Unicode
+# Unicode version: 3.0
+# Table version: 1.0
+# Table format: Format A
+# Date: 1999 July 27
+# Authors: Ken Whistler <kenw@sybase.com>
+#
+# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved.
+#
+# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
+# No claims are made as to fitness for any particular purpose. No
+# warranties of any kind are expressed or implied. The recipient
+# agrees to determine applicability of information provided. If this
+# file has been provided on optical media by Unicode, Inc., the sole
+# remedy for any claim will be exchange of defective media within 90
+# days of receipt.
+#
+# Unicode, Inc. hereby grants the right to freely use the information
+# supplied in this file in the creation of products supporting the
+# Unicode Standard, and to make copies of this file in any form for
+# internal or external distribution as long as this notice remains
+# attached.
+#
+# General notes:
+#
+# This table contains the data the Unicode Consortium has on how
+# ISO/IEC 8859-1:1998 characters map into Unicode.
+#
+# Format: Three tab-separated columns
+# Column #1 is the ISO/IEC 8859-1 code (in hex as 0xXX)
+# Column #2 is the Unicode (in hex as 0xXXXX)
+# Column #3 the Unicode name (follows a comment sign, '#')
+#
+# The entries are in ISO/IEC 8859-1 order.
+#
+# Version history
+# 1.0 version updates 0.1 version by adding mappings for all
+# control characters.
+#
+# Updated versions of this file may be found in:
+# <ftp://ftp.unicode.org/Public/MAPPINGS/>
+#
+# Any comments or problems, contact <errata@unicode.org>
+# Please note that <errata@unicode.org> is an archival address;
+# notices will be checked, but do not expect an immediate response.
+#
+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 0x0080 # <control>
+0x81 0x0081 # <control>
+0x82 0x0082 # <control>
+0x83 0x0083 # <control>
+0x84 0x0084 # <control>
+0x85 0x0085 # <control>
+0x86 0x0086 # <control>
+0x87 0x0087 # <control>
+0x88 0x0088 # <control>
+0x89 0x0089 # <control>
+0x8A 0x008A # <control>
+0x8B 0x008B # <control>
+0x8C 0x008C # <control>
+0x8D 0x008D # <control>
+0x8E 0x008E # <control>
+0x8F 0x008F # <control>
+0x90 0x0090 # <control>
+0x91 0x0091 # <control>
+0x92 0x0092 # <control>
+0x93 0x0093 # <control>
+0x94 0x0094 # <control>
+0x95 0x0095 # <control>
+0x96 0x0096 # <control>
+0x97 0x0097 # <control>
+0x98 0x0098 # <control>
+0x99 0x0099 # <control>
+0x9A 0x009A # <control>
+0x9B 0x009B # <control>
+0x9C 0x009C # <control>
+0x9D 0x009D # <control>
+0x9E 0x009E # <control>
+0x9F 0x009F # <control>
+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 0x00D0 # LATIN CAPITAL LETTER ETH (Icelandic)
+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 0x00DD # LATIN CAPITAL LETTER Y WITH ACUTE
+0xDE 0x00DE # LATIN CAPITAL LETTER THORN (Icelandic)
+0xDF 0x00DF # LATIN SMALL LETTER SHARP S (German)
+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 0x00F0 # LATIN SMALL LETTER ETH (Icelandic)
+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 0x00FD # LATIN SMALL LETTER Y WITH ACUTE
+0xFE 0x00FE # LATIN SMALL LETTER THORN (Icelandic)
+0xFF 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS
diff --git a/extra/io/encodings/8-bit/8859-10.TXT b/extra/io/encodings/8-bit/8859-10.TXT
new file mode 100644
index 0000000000..374a42b1a5
--- /dev/null
+++ b/extra/io/encodings/8-bit/8859-10.TXT
@@ -0,0 +1,303 @@
+#
+# Name: ISO/IEC 8859-10:1998 to Unicode
+# Unicode version: 3.0
+# Table version: 1.1
+# Table format: Format A
+# Date: 1999 October 11
+# Authors: Ken Whistler <kenw@sybase.com>
+#
+# Copyright (c) 1999 Unicode, Inc. All Rights reserved.
+#
+# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
+# No claims are made as to fitness for any particular purpose. No
+# warranties of any kind are expressed or implied. The recipient
+# agrees to determine applicability of information provided. If this
+# file has been provided on optical media by Unicode, Inc., the sole
+# remedy for any claim will be exchange of defective media within 90
+# days of receipt.
+#
+# Unicode, Inc. hereby grants the right to freely use the information
+# supplied in this file in the creation of products supporting the
+# Unicode Standard, and to make copies of this file in any form for
+# internal or external distribution as long as this notice remains
+# attached.
+#
+# General notes:
+#
+# This table contains the data the Unicode Consortium has on how
+# ISO/IEC 8859-10:1998 characters map into Unicode.
+#
+# Format: Three tab-separated columns
+# Column #1 is the ISO/IEC 8859-10 code (in hex as 0xXX)
+# Column #2 is the Unicode (in hex as 0xXXXX)
+# Column #3 the Unicode name (follows a comment sign, '#')
+#
+# The entries are in ISO/IEC 8859-10 order.
+#
+# Version history
+# 1.0 version new.
+# 1.1 corrected mistake in mapping of 0xA4
+#
+# Updated versions of this file may be found in:
+# <ftp://ftp.unicode.org/Public/MAPPINGS/>
+#
+# Any comments or problems, contact <errata@unicode.org>
+# Please note that <errata@unicode.org> is an archival address;
+# notices will be checked, but do not expect an immediate response.
+#
+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 0x0080 # <control>
+0x81 0x0081 # <control>
+0x82 0x0082 # <control>
+0x83 0x0083 # <control>
+0x84 0x0084 # <control>
+0x85 0x0085 # <control>
+0x86 0x0086 # <control>
+0x87 0x0087 # <control>
+0x88 0x0088 # <control>
+0x89 0x0089 # <control>
+0x8A 0x008A # <control>
+0x8B 0x008B # <control>
+0x8C 0x008C # <control>
+0x8D 0x008D # <control>
+0x8E 0x008E # <control>
+0x8F 0x008F # <control>
+0x90 0x0090 # <control>
+0x91 0x0091 # <control>
+0x92 0x0092 # <control>
+0x93 0x0093 # <control>
+0x94 0x0094 # <control>
+0x95 0x0095 # <control>
+0x96 0x0096 # <control>
+0x97 0x0097 # <control>
+0x98 0x0098 # <control>
+0x99 0x0099 # <control>
+0x9A 0x009A # <control>
+0x9B 0x009B # <control>
+0x9C 0x009C # <control>
+0x9D 0x009D # <control>
+0x9E 0x009E # <control>
+0x9F 0x009F # <control>
+0xA0 0x00A0 # NO-BREAK SPACE
+0xA1 0x0104 # LATIN CAPITAL LETTER A WITH OGONEK
+0xA2 0x0112 # LATIN CAPITAL LETTER E WITH MACRON
+0xA3 0x0122 # LATIN CAPITAL LETTER G WITH CEDILLA
+0xA4 0x012A # LATIN CAPITAL LETTER I WITH MACRON
+0xA5 0x0128 # LATIN CAPITAL LETTER I WITH TILDE
+0xA6 0x0136 # LATIN CAPITAL LETTER K WITH CEDILLA
+0xA7 0x00A7 # SECTION SIGN
+0xA8 0x013B # LATIN CAPITAL LETTER L WITH CEDILLA
+0xA9 0x0110 # LATIN CAPITAL LETTER D WITH STROKE
+0xAA 0x0160 # LATIN CAPITAL LETTER S WITH CARON
+0xAB 0x0166 # LATIN CAPITAL LETTER T WITH STROKE
+0xAC 0x017D # LATIN CAPITAL LETTER Z WITH CARON
+0xAD 0x00AD # SOFT HYPHEN
+0xAE 0x016A # LATIN CAPITAL LETTER U WITH MACRON
+0xAF 0x014A # LATIN CAPITAL LETTER ENG
+0xB0 0x00B0 # DEGREE SIGN
+0xB1 0x0105 # LATIN SMALL LETTER A WITH OGONEK
+0xB2 0x0113 # LATIN SMALL LETTER E WITH MACRON
+0xB3 0x0123 # LATIN SMALL LETTER G WITH CEDILLA
+0xB4 0x012B # LATIN SMALL LETTER I WITH MACRON
+0xB5 0x0129 # LATIN SMALL LETTER I WITH TILDE
+0xB6 0x0137 # LATIN SMALL LETTER K WITH CEDILLA
+0xB7 0x00B7 # MIDDLE DOT
+0xB8 0x013C # LATIN SMALL LETTER L WITH CEDILLA
+0xB9 0x0111 # LATIN SMALL LETTER D WITH STROKE
+0xBA 0x0161 # LATIN SMALL LETTER S WITH CARON
+0xBB 0x0167 # LATIN SMALL LETTER T WITH STROKE
+0xBC 0x017E # LATIN SMALL LETTER Z WITH CARON
+0xBD 0x2015 # HORIZONTAL BAR
+0xBE 0x016B # LATIN SMALL LETTER U WITH MACRON
+0xBF 0x014B # LATIN SMALL LETTER ENG
+0xC0 0x0100 # LATIN CAPITAL LETTER A WITH MACRON
+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 0x012E # LATIN CAPITAL LETTER I WITH OGONEK
+0xC8 0x010C # LATIN CAPITAL LETTER C WITH CARON
+0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
+0xCA 0x0118 # LATIN CAPITAL LETTER E WITH OGONEK
+0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS
+0xCC 0x0116 # LATIN CAPITAL LETTER E WITH DOT ABOVE
+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 0x00D0 # LATIN CAPITAL LETTER ETH (Icelandic)
+0xD1 0x0145 # LATIN CAPITAL LETTER N WITH CEDILLA
+0xD2 0x014C # LATIN CAPITAL LETTER O WITH MACRON
+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 0x0168 # LATIN CAPITAL LETTER U WITH TILDE
+0xD8 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE
+0xD9 0x0172 # LATIN CAPITAL LETTER U WITH OGONEK
+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 0x00DD # LATIN CAPITAL LETTER Y WITH ACUTE
+0xDE 0x00DE # LATIN CAPITAL LETTER THORN (Icelandic)
+0xDF 0x00DF # LATIN SMALL LETTER SHARP S (German)
+0xE0 0x0101 # LATIN SMALL LETTER A WITH MACRON
+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 0x012F # LATIN SMALL LETTER I WITH OGONEK
+0xE8 0x010D # LATIN SMALL LETTER C WITH CARON
+0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
+0xEA 0x0119 # LATIN SMALL LETTER E WITH OGONEK
+0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS
+0xEC 0x0117 # LATIN SMALL LETTER E WITH DOT ABOVE
+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 0x00F0 # LATIN SMALL LETTER ETH (Icelandic)
+0xF1 0x0146 # LATIN SMALL LETTER N WITH CEDILLA
+0xF2 0x014D # LATIN SMALL LETTER O WITH MACRON
+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 0x0169 # LATIN SMALL LETTER U WITH TILDE
+0xF8 0x00F8 # LATIN SMALL LETTER O WITH STROKE
+0xF9 0x0173 # LATIN SMALL LETTER U WITH OGONEK
+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 0x00FD # LATIN SMALL LETTER Y WITH ACUTE
+0xFE 0x00FE # LATIN SMALL LETTER THORN (Icelandic)
+0xFF 0x0138 # LATIN SMALL LETTER KRA
diff --git a/extra/io/encodings/8-bit/8859-11.TXT b/extra/io/encodings/8-bit/8859-11.TXT
new file mode 100644
index 0000000000..192bd9d7cf
--- /dev/null
+++ b/extra/io/encodings/8-bit/8859-11.TXT
@@ -0,0 +1,297 @@
+#
+# Name: ISO/IEC 8859-11:2001 to Unicode
+# Unicode version: 3.2
+# Table version: 1.0
+# Table format: Format A
+# Date: 2002 October 7
+# Authors: Ken Whistler <kenw@sybase.com>
+#
+# Copyright (c) 2002 Unicode, Inc. All Rights reserved.
+#
+# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
+# No claims are made as to fitness for any particular purpose. No
+# warranties of any kind are expressed or implied. The recipient
+# agrees to determine applicability of information provided. If this
+# file has been provided on optical media by Unicode, Inc., the sole
+# remedy for any claim will be exchange of defective media within 90
+# days of receipt.
+#
+# Unicode, Inc. hereby grants the right to freely use the information
+# supplied in this file in the creation of products supporting the
+# Unicode Standard, and to make copies of this file in any form for
+# internal or external distribution as long as this notice remains
+# attached.
+#
+# General notes:
+#
+# This table contains the data the Unicode Consortium has on how
+# ISO/IEC 8859-11:2001 characters map into Unicode.
+#
+# ISO/IEC 8859-11:2001 is equivalent to TIS 620-2533 (1990) with
+# the addition of 0xA0 NO-BREAK SPACE.
+#
+# Format: Three tab-separated columns
+# Column #1 is the ISO/IEC 8859-11 code (in hex as 0xXX)
+# Column #2 is the Unicode (in hex as 0xXXXX)
+# Column #3 the Unicode name (follows a comment sign, '#')
+#
+# The entries are in ISO/IEC 8859-11 order.
+#
+# Version history:
+# 2002 October 7 Created
+#
+# Updated versions of this file may be found in:
+# <ftp://ftp.unicode.org/Public/MAPPINGS/>
+#
+# For any comments or problems, please use the Unicode
+# web contact form at:
+# http://www.unicode.org/unicode/reporting.html
+#
+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 0x0080 # <control>
+0x81 0x0081 # <control>
+0x82 0x0082 # <control>
+0x83 0x0083 # <control>
+0x84 0x0084 # <control>
+0x85 0x0085 # <control>
+0x86 0x0086 # <control>
+0x87 0x0087 # <control>
+0x88 0x0088 # <control>
+0x89 0x0089 # <control>
+0x8A 0x008A # <control>
+0x8B 0x008B # <control>
+0x8C 0x008C # <control>
+0x8D 0x008D # <control>
+0x8E 0x008E # <control>
+0x8F 0x008F # <control>
+0x90 0x0090 # <control>
+0x91 0x0091 # <control>
+0x92 0x0092 # <control>
+0x93 0x0093 # <control>
+0x94 0x0094 # <control>
+0x95 0x0095 # <control>
+0x96 0x0096 # <control>
+0x97 0x0097 # <control>
+0x98 0x0098 # <control>
+0x99 0x0099 # <control>
+0x9A 0x009A # <control>
+0x9B 0x009B # <control>
+0x9C 0x009C # <control>
+0x9D 0x009D # <control>
+0x9E 0x009E # <control>
+0x9F 0x009F # <control>
+0xA0 0x00A0 # NO-BREAK SPACE
+0xA1 0x0E01 # THAI CHARACTER KO KAI
+0xA2 0x0E02 # THAI CHARACTER KHO KHAI
+0xA3 0x0E03 # THAI CHARACTER KHO KHUAT
+0xA4 0x0E04 # THAI CHARACTER KHO KHWAI
+0xA5 0x0E05 # THAI CHARACTER KHO KHON
+0xA6 0x0E06 # THAI CHARACTER KHO RAKHANG
+0xA7 0x0E07 # THAI CHARACTER NGO NGU
+0xA8 0x0E08 # THAI CHARACTER CHO CHAN
+0xA9 0x0E09 # THAI CHARACTER CHO CHING
+0xAA 0x0E0A # THAI CHARACTER CHO CHANG
+0xAB 0x0E0B # THAI CHARACTER SO SO
+0xAC 0x0E0C # THAI CHARACTER CHO CHOE
+0xAD 0x0E0D # THAI CHARACTER YO YING
+0xAE 0x0E0E # THAI CHARACTER DO CHADA
+0xAF 0x0E0F # THAI CHARACTER TO PATAK
+0xB0 0x0E10 # THAI CHARACTER THO THAN
+0xB1 0x0E11 # THAI CHARACTER THO NANGMONTHO
+0xB2 0x0E12 # THAI CHARACTER THO PHUTHAO
+0xB3 0x0E13 # THAI CHARACTER NO NEN
+0xB4 0x0E14 # THAI CHARACTER DO DEK
+0xB5 0x0E15 # THAI CHARACTER TO TAO
+0xB6 0x0E16 # THAI CHARACTER THO THUNG
+0xB7 0x0E17 # THAI CHARACTER THO THAHAN
+0xB8 0x0E18 # THAI CHARACTER THO THONG
+0xB9 0x0E19 # THAI CHARACTER NO NU
+0xBA 0x0E1A # THAI CHARACTER BO BAIMAI
+0xBB 0x0E1B # THAI CHARACTER PO PLA
+0xBC 0x0E1C # THAI CHARACTER PHO PHUNG
+0xBD 0x0E1D # THAI CHARACTER FO FA
+0xBE 0x0E1E # THAI CHARACTER PHO PHAN
+0xBF 0x0E1F # THAI CHARACTER FO FAN
+0xC0 0x0E20 # THAI CHARACTER PHO SAMPHAO
+0xC1 0x0E21 # THAI CHARACTER MO MA
+0xC2 0x0E22 # THAI CHARACTER YO YAK
+0xC3 0x0E23 # THAI CHARACTER RO RUA
+0xC4 0x0E24 # THAI CHARACTER RU
+0xC5 0x0E25 # THAI CHARACTER LO LING
+0xC6 0x0E26 # THAI CHARACTER LU
+0xC7 0x0E27 # THAI CHARACTER WO WAEN
+0xC8 0x0E28 # THAI CHARACTER SO SALA
+0xC9 0x0E29 # THAI CHARACTER SO RUSI
+0xCA 0x0E2A # THAI CHARACTER SO SUA
+0xCB 0x0E2B # THAI CHARACTER HO HIP
+0xCC 0x0E2C # THAI CHARACTER LO CHULA
+0xCD 0x0E2D # THAI CHARACTER O ANG
+0xCE 0x0E2E # THAI CHARACTER HO NOKHUK
+0xCF 0x0E2F # THAI CHARACTER PAIYANNOI
+0xD0 0x0E30 # THAI CHARACTER SARA A
+0xD1 0x0E31 # THAI CHARACTER MAI HAN-AKAT
+0xD2 0x0E32 # THAI CHARACTER SARA AA
+0xD3 0x0E33 # THAI CHARACTER SARA AM
+0xD4 0x0E34 # THAI CHARACTER SARA I
+0xD5 0x0E35 # THAI CHARACTER SARA II
+0xD6 0x0E36 # THAI CHARACTER SARA UE
+0xD7 0x0E37 # THAI CHARACTER SARA UEE
+0xD8 0x0E38 # THAI CHARACTER SARA U
+0xD9 0x0E39 # THAI CHARACTER SARA UU
+0xDA 0x0E3A # THAI CHARACTER PHINTHU
+0xDF 0x0E3F # THAI CURRENCY SYMBOL BAHT
+0xE0 0x0E40 # THAI CHARACTER SARA E
+0xE1 0x0E41 # THAI CHARACTER SARA AE
+0xE2 0x0E42 # THAI CHARACTER SARA O
+0xE3 0x0E43 # THAI CHARACTER SARA AI MAIMUAN
+0xE4 0x0E44 # THAI CHARACTER SARA AI MAIMALAI
+0xE5 0x0E45 # THAI CHARACTER LAKKHANGYAO
+0xE6 0x0E46 # THAI CHARACTER MAIYAMOK
+0xE7 0x0E47 # THAI CHARACTER MAITAIKHU
+0xE8 0x0E48 # THAI CHARACTER MAI EK
+0xE9 0x0E49 # THAI CHARACTER MAI THO
+0xEA 0x0E4A # THAI CHARACTER MAI TRI
+0xEB 0x0E4B # THAI CHARACTER MAI CHATTAWA
+0xEC 0x0E4C # THAI CHARACTER THANTHAKHAT
+0xED 0x0E4D # THAI CHARACTER NIKHAHIT
+0xEE 0x0E4E # THAI CHARACTER YAMAKKAN
+0xEF 0x0E4F # THAI CHARACTER FONGMAN
+0xF0 0x0E50 # THAI DIGIT ZERO
+0xF1 0x0E51 # THAI DIGIT ONE
+0xF2 0x0E52 # THAI DIGIT TWO
+0xF3 0x0E53 # THAI DIGIT THREE
+0xF4 0x0E54 # THAI DIGIT FOUR
+0xF5 0x0E55 # THAI DIGIT FIVE
+0xF6 0x0E56 # THAI DIGIT SIX
+0xF7 0x0E57 # THAI DIGIT SEVEN
+0xF8 0x0E58 # THAI DIGIT EIGHT
+0xF9 0x0E59 # THAI DIGIT NINE
+0xFA 0x0E5A # THAI CHARACTER ANGKHANKHU
+0xFB 0x0E5B # THAI CHARACTER KHOMUT
diff --git a/extra/io/encodings/8-bit/8859-13.TXT b/extra/io/encodings/8-bit/8859-13.TXT
new file mode 100644
index 0000000000..cd11b53fd7
--- /dev/null
+++ b/extra/io/encodings/8-bit/8859-13.TXT
@@ -0,0 +1,299 @@
+#
+# Name: ISO/IEC 8859-13:1998 to Unicode
+# Unicode version: 3.0
+# Table version: 1.0
+# Table format: Format A
+# Date: 1999 July 27
+# Authors: Ken Whistler <kenw@sybase.com>
+#
+# Copyright (c) 1998 - 1999 Unicode, Inc. All Rights reserved.
+#
+# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
+# No claims are made as to fitness for any particular purpose. No
+# warranties of any kind are expressed or implied. The recipient
+# agrees to determine applicability of information provided. If this
+# file has been provided on optical media by Unicode, Inc., the sole
+# remedy for any claim will be exchange of defective media within 90
+# days of receipt.
+#
+# Unicode, Inc. hereby grants the right to freely use the information
+# supplied in this file in the creation of products supporting the
+# Unicode Standard, and to make copies of this file in any form for
+# internal or external distribution as long as this notice remains
+# attached.
+#
+# General notes:
+#
+# This table contains the data the Unicode Consortium has on how
+# ISO/IEC 8859-13:1998 characters map into Unicode.
+#
+# Format: Three tab-separated columns
+# Column #1 is the ISO/IEC 8859-13 code (in hex as 0xXX)
+# Column #2 is the Unicode (in hex as 0xXXXX)
+# Column #3 the Unicode name (follows a comment sign, '#')
+#
+# The entries are in ISO/IEC 8859-13 order.
+#
+# Updated versions of this file may be found in:
+# <ftp://ftp.unicode.org/Public/MAPPINGS/>
+#
+# Any comments or problems, contact <errata@unicode.org>
+# Please note that <errata@unicode.org> is an archival address;
+# notices will be checked, but do not expect an immediate response.
+#
+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 0x0080 # <control>
+0x81 0x0081 # <control>
+0x82 0x0082 # <control>
+0x83 0x0083 # <control>
+0x84 0x0084 # <control>
+0x85 0x0085 # <control>
+0x86 0x0086 # <control>
+0x87 0x0087 # <control>
+0x88 0x0088 # <control>
+0x89 0x0089 # <control>
+0x8A 0x008A # <control>
+0x8B 0x008B # <control>
+0x8C 0x008C # <control>
+0x8D 0x008D # <control>
+0x8E 0x008E # <control>
+0x8F 0x008F # <control>
+0x90 0x0090 # <control>
+0x91 0x0091 # <control>
+0x92 0x0092 # <control>
+0x93 0x0093 # <control>
+0x94 0x0094 # <control>
+0x95 0x0095 # <control>
+0x96 0x0096 # <control>
+0x97 0x0097 # <control>
+0x98 0x0098 # <control>
+0x99 0x0099 # <control>
+0x9A 0x009A # <control>
+0x9B 0x009B # <control>
+0x9C 0x009C # <control>
+0x9D 0x009D # <control>
+0x9E 0x009E # <control>
+0x9F 0x009F # <control>
+0xA0 0x00A0 # NO-BREAK SPACE
+0xA1 0x201D # RIGHT DOUBLE QUOTATION MARK
+0xA2 0x00A2 # CENT SIGN
+0xA3 0x00A3 # POUND SIGN
+0xA4 0x00A4 # CURRENCY SIGN
+0xA5 0x201E # DOUBLE LOW-9 QUOTATION MARK
+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 0x201C # LEFT DOUBLE QUOTATION MARK
+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 (German)
+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 0x2019 # RIGHT SINGLE QUOTATION MARK
diff --git a/extra/io/encodings/8-bit/8859-14.TXT b/extra/io/encodings/8-bit/8859-14.TXT
new file mode 100644
index 0000000000..73e98555ea
--- /dev/null
+++ b/extra/io/encodings/8-bit/8859-14.TXT
@@ -0,0 +1,301 @@
+#
+# Name: ISO/IEC 8859-14:1998 to Unicode
+# Unicode version: 3.0
+# Table version: 1.0
+# Table format: Format A
+# Date: 1999 July 27
+# Authors: Markus Kuhn <http://www.cl.cam.ac.uk/~mgk25/>
+# Ken Whistler <kenw@sybase.com>
+#
+# Copyright (c) 1998 - 1999 Unicode, Inc. All Rights reserved.
+#
+# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
+# No claims are made as to fitness for any particular purpose. No
+# warranties of any kind are expressed or implied. The recipient
+# agrees to determine applicability of information provided. If this
+# file has been provided on optical media by Unicode, Inc., the sole
+# remedy for any claim will be exchange of defective media within 90
+# days of receipt.
+#
+# Unicode, Inc. hereby grants the right to freely use the information
+# supplied in this file in the creation of products supporting the
+# Unicode Standard, and to make copies of this file in any form for
+# internal or external distribution as long as this notice remains
+# attached.
+#
+# General notes:
+#
+# This table contains the data the Unicode Consortium has on how
+# ISO/IEC 8859-14:1998 characters map into Unicode.
+#
+# Format: Three tab-separated columns
+# Column #1 is the ISO/IEC 8859-14 code (in hex as 0xXX)
+# Column #2 is the Unicode (in hex as 0xXXXX)
+# Column #3 the Unicode name (follows a comment sign, '#')
+#
+# The entries are in ISO/IEC 8859-14 order.
+#
+# Updated versions of this file may be found in:
+# <ftp://ftp.unicode.org/Public/MAPPINGS/>
+#
+# Any comments or problems, contact <errata@unicode.org>
+# Please note that <errata@unicode.org> is an archival address;
+# notices will be checked, but do not expect an immediate response.
+#
+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 0x0080 # <control>
+0x81 0x0081 # <control>
+0x82 0x0082 # <control>
+0x83 0x0083 # <control>
+0x84 0x0084 # <control>
+0x85 0x0085 # <control>
+0x86 0x0086 # <control>
+0x87 0x0087 # <control>
+0x88 0x0088 # <control>
+0x89 0x0089 # <control>
+0x8A 0x008A # <control>
+0x8B 0x008B # <control>
+0x8C 0x008C # <control>
+0x8D 0x008D # <control>
+0x8E 0x008E # <control>
+0x8F 0x008F # <control>
+0x90 0x0090 # <control>
+0x91 0x0091 # <control>
+0x92 0x0092 # <control>
+0x93 0x0093 # <control>
+0x94 0x0094 # <control>
+0x95 0x0095 # <control>
+0x96 0x0096 # <control>
+0x97 0x0097 # <control>
+0x98 0x0098 # <control>
+0x99 0x0099 # <control>
+0x9A 0x009A # <control>
+0x9B 0x009B # <control>
+0x9C 0x009C # <control>
+0x9D 0x009D # <control>
+0x9E 0x009E # <control>
+0x9F 0x009F # <control>
+0xA0 0x00A0 # NO-BREAK SPACE
+0xA1 0x1E02 # LATIN CAPITAL LETTER B WITH DOT ABOVE
+0xA2 0x1E03 # LATIN SMALL LETTER B WITH DOT ABOVE
+0xA3 0x00A3 # POUND SIGN
+0xA4 0x010A # LATIN CAPITAL LETTER C WITH DOT ABOVE
+0xA5 0x010B # LATIN SMALL LETTER C WITH DOT ABOVE
+0xA6 0x1E0A # LATIN CAPITAL LETTER D WITH DOT ABOVE
+0xA7 0x00A7 # SECTION SIGN
+0xA8 0x1E80 # LATIN CAPITAL LETTER W WITH GRAVE
+0xA9 0x00A9 # COPYRIGHT SIGN
+0xAA 0x1E82 # LATIN CAPITAL LETTER W WITH ACUTE
+0xAB 0x1E0B # LATIN SMALL LETTER D WITH DOT ABOVE
+0xAC 0x1EF2 # LATIN CAPITAL LETTER Y WITH GRAVE
+0xAD 0x00AD # SOFT HYPHEN
+0xAE 0x00AE # REGISTERED SIGN
+0xAF 0x0178 # LATIN CAPITAL LETTER Y WITH DIAERESIS
+0xB0 0x1E1E # LATIN CAPITAL LETTER F WITH DOT ABOVE
+0xB1 0x1E1F # LATIN SMALL LETTER F WITH DOT ABOVE
+0xB2 0x0120 # LATIN CAPITAL LETTER G WITH DOT ABOVE
+0xB3 0x0121 # LATIN SMALL LETTER G WITH DOT ABOVE
+0xB4 0x1E40 # LATIN CAPITAL LETTER M WITH DOT ABOVE
+0xB5 0x1E41 # LATIN SMALL LETTER M WITH DOT ABOVE
+0xB6 0x00B6 # PILCROW SIGN
+0xB7 0x1E56 # LATIN CAPITAL LETTER P WITH DOT ABOVE
+0xB8 0x1E81 # LATIN SMALL LETTER W WITH GRAVE
+0xB9 0x1E57 # LATIN SMALL LETTER P WITH DOT ABOVE
+0xBA 0x1E83 # LATIN SMALL LETTER W WITH ACUTE
+0xBB 0x1E60 # LATIN CAPITAL LETTER S WITH DOT ABOVE
+0xBC 0x1EF3 # LATIN SMALL LETTER Y WITH GRAVE
+0xBD 0x1E84 # LATIN CAPITAL LETTER W WITH DIAERESIS
+0xBE 0x1E85 # LATIN SMALL LETTER W WITH DIAERESIS
+0xBF 0x1E61 # LATIN SMALL LETTER S WITH DOT ABOVE
+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 0x0174 # LATIN CAPITAL LETTER W WITH CIRCUMFLEX
+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 0x1E6A # LATIN CAPITAL LETTER T WITH DOT ABOVE
+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 0x00DD # LATIN CAPITAL LETTER Y WITH ACUTE
+0xDE 0x0176 # LATIN CAPITAL LETTER Y WITH CIRCUMFLEX
+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 0x0175 # LATIN SMALL LETTER W WITH CIRCUMFLEX
+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 0x1E6B # LATIN SMALL LETTER T WITH DOT ABOVE
+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 0x00FD # LATIN SMALL LETTER Y WITH ACUTE
+0xFE 0x0177 # LATIN SMALL LETTER Y WITH CIRCUMFLEX
+0xFF 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS
+
diff --git a/extra/io/encodings/8-bit/8859-15.TXT b/extra/io/encodings/8-bit/8859-15.TXT
new file mode 100644
index 0000000000..ab2f32fcea
--- /dev/null
+++ b/extra/io/encodings/8-bit/8859-15.TXT
@@ -0,0 +1,303 @@
+#
+# Name: ISO/IEC 8859-15:1999 to Unicode
+# Unicode version: 3.0
+# Table version: 1.0
+# Table format: Format A
+# Date: 1999 July 27
+# Authors: Markus Kuhn <http://www.cl.cam.ac.uk/~mgk25/>
+# Ken Whistler <kenw@sybase.com>
+#
+# Copyright (c) 1998 - 1999 Unicode, Inc. All Rights reserved.
+#
+# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
+# No claims are made as to fitness for any particular purpose. No
+# warranties of any kind are expressed or implied. The recipient
+# agrees to determine applicability of information provided. If this
+# file has been provided on optical media by Unicode, Inc., the sole
+# remedy for any claim will be exchange of defective media within 90
+# days of receipt.
+#
+# Unicode, Inc. hereby grants the right to freely use the information
+# supplied in this file in the creation of products supporting the
+# Unicode Standard, and to make copies of this file in any form for
+# internal or external distribution as long as this notice remains
+# attached.
+#
+# General notes:
+#
+# This table contains the data the Unicode Consortium has on how
+# ISO/IEC 8859-15:1999 characters map into Unicode.
+#
+# Format: Three tab-separated columns
+# Column #1 is the ISO/IEC 8859-15 code (in hex as 0xXX)
+# Column #2 is the Unicode (in hex as 0xXXXX)
+# Column #3 the Unicode name (follows a comment sign, '#')
+#
+# The entries are in ISO/IEC 8859-15 order.
+#
+# Version history
+#
+# Updated versions of this file may be found in:
+# <ftp://ftp.unicode.org/Public/MAPPINGS/>
+#
+# Any comments or problems, contact <errata@unicode.org>
+# Please note that <errata@unicode.org> is an archival address;
+# notices will be checked, but do not expect an immediate response.
+#
+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 0x0080 # <control>
+0x81 0x0081 # <control>
+0x82 0x0082 # <control>
+0x83 0x0083 # <control>
+0x84 0x0084 # <control>
+0x85 0x0085 # <control>
+0x86 0x0086 # <control>
+0x87 0x0087 # <control>
+0x88 0x0088 # <control>
+0x89 0x0089 # <control>
+0x8A 0x008A # <control>
+0x8B 0x008B # <control>
+0x8C 0x008C # <control>
+0x8D 0x008D # <control>
+0x8E 0x008E # <control>
+0x8F 0x008F # <control>
+0x90 0x0090 # <control>
+0x91 0x0091 # <control>
+0x92 0x0092 # <control>
+0x93 0x0093 # <control>
+0x94 0x0094 # <control>
+0x95 0x0095 # <control>
+0x96 0x0096 # <control>
+0x97 0x0097 # <control>
+0x98 0x0098 # <control>
+0x99 0x0099 # <control>
+0x9A 0x009A # <control>
+0x9B 0x009B # <control>
+0x9C 0x009C # <control>
+0x9D 0x009D # <control>
+0x9E 0x009E # <control>
+0x9F 0x009F # <control>
+0xA0 0x00A0 # NO-BREAK SPACE
+0xA1 0x00A1 # INVERTED EXCLAMATION MARK
+0xA2 0x00A2 # CENT SIGN
+0xA3 0x00A3 # POUND SIGN
+0xA4 0x20AC # EURO SIGN
+0xA5 0x00A5 # YEN SIGN
+0xA6 0x0160 # LATIN CAPITAL LETTER S WITH CARON
+0xA7 0x00A7 # SECTION SIGN
+0xA8 0x0161 # LATIN SMALL LETTER S WITH CARON
+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 0x017D # LATIN CAPITAL LETTER Z WITH CARON
+0xB5 0x00B5 # MICRO SIGN
+0xB6 0x00B6 # PILCROW SIGN
+0xB7 0x00B7 # MIDDLE DOT
+0xB8 0x017E # LATIN SMALL LETTER Z WITH CARON
+0xB9 0x00B9 # SUPERSCRIPT ONE
+0xBA 0x00BA # MASCULINE ORDINAL INDICATOR
+0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xBC 0x0152 # LATIN CAPITAL LIGATURE OE
+0xBD 0x0153 # LATIN SMALL LIGATURE OE
+0xBE 0x0178 # LATIN CAPITAL LETTER Y WITH DIAERESIS
+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 0x00D0 # LATIN CAPITAL LETTER ETH
+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 0x00DD # LATIN CAPITAL LETTER Y WITH ACUTE
+0xDE 0x00DE # LATIN CAPITAL LETTER THORN
+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 0x00F0 # LATIN SMALL LETTER ETH
+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 0x00FD # LATIN SMALL LETTER Y WITH ACUTE
+0xFE 0x00FE # LATIN SMALL LETTER THORN
+0xFF 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS
+
diff --git a/extra/io/encodings/8-bit/8859-16.TXT b/extra/io/encodings/8-bit/8859-16.TXT
new file mode 100644
index 0000000000..c0dcf0dac6
--- /dev/null
+++ b/extra/io/encodings/8-bit/8859-16.TXT
@@ -0,0 +1,299 @@
+#
+# Name: ISO/IEC 8859-16:2001 to Unicode
+# Unicode version: 3.0
+# Table version: 1.0
+# Table format: Format A
+# Date: 2001 July 26
+# Authors: Markus Kuhn <http://www.cl.cam.ac.uk/~mgk25/>
+#
+# Copyright (c) 1999-2001 Unicode, Inc. All Rights reserved.
+#
+# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
+# No claims are made as to fitness for any particular purpose. No
+# warranties of any kind are expressed or implied. The recipient
+# agrees to determine applicability of information provided. If this
+# file has been provided on optical media by Unicode, Inc., the sole
+# remedy for any claim will be exchange of defective media within 90
+# days of receipt.
+#
+# Unicode, Inc. hereby grants the right to freely use the information
+# supplied in this file in the creation of products supporting the
+# Unicode Standard, and to make copies of this file in any form for
+# internal or external distribution as long as this notice remains
+# attached.
+#
+# General notes:
+#
+# This table contains the data the Unicode Consortium has on how
+# ISO/IEC 8859-16:2001 characters map into Unicode.
+#
+# Format: Three tab-separated columns
+# Column #1 is the ISO/IEC 8859-16 code (in hex as 0xXX)
+# Column #2 is the Unicode (in hex as 0xXXXX)
+# Column #3 the Unicode name (follows a comment sign, '#')
+#
+# The entries are in ISO/IEC 8859-16 order.
+#
+# Updated versions of this file may be found in:
+# <ftp://ftp.unicode.org/Public/MAPPINGS/>
+#
+# Any comments or problems, contact <errata@unicode.org>
+# Please note that <errata@unicode.org> is an archival address;
+# notices will be checked, but do not expect an immediate response.
+#
+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 0x0080 # <control>
+0x81 0x0081 # <control>
+0x82 0x0082 # <control>
+0x83 0x0083 # <control>
+0x84 0x0084 # <control>
+0x85 0x0085 # <control>
+0x86 0x0086 # <control>
+0x87 0x0087 # <control>
+0x88 0x0088 # <control>
+0x89 0x0089 # <control>
+0x8A 0x008A # <control>
+0x8B 0x008B # <control>
+0x8C 0x008C # <control>
+0x8D 0x008D # <control>
+0x8E 0x008E # <control>
+0x8F 0x008F # <control>
+0x90 0x0090 # <control>
+0x91 0x0091 # <control>
+0x92 0x0092 # <control>
+0x93 0x0093 # <control>
+0x94 0x0094 # <control>
+0x95 0x0095 # <control>
+0x96 0x0096 # <control>
+0x97 0x0097 # <control>
+0x98 0x0098 # <control>
+0x99 0x0099 # <control>
+0x9A 0x009A # <control>
+0x9B 0x009B # <control>
+0x9C 0x009C # <control>
+0x9D 0x009D # <control>
+0x9E 0x009E # <control>
+0x9F 0x009F # <control>
+0xA0 0x00A0 # NO-BREAK SPACE
+0xA1 0x0104 # LATIN CAPITAL LETTER A WITH OGONEK
+0xA2 0x0105 # LATIN SMALL LETTER A WITH OGONEK
+0xA3 0x0141 # LATIN CAPITAL LETTER L WITH STROKE
+0xA4 0x20AC # EURO SIGN
+0xA5 0x201E # DOUBLE LOW-9 QUOTATION MARK
+0xA6 0x0160 # LATIN CAPITAL LETTER S WITH CARON
+0xA7 0x00A7 # SECTION SIGN
+0xA8 0x0161 # LATIN SMALL LETTER S WITH CARON
+0xA9 0x00A9 # COPYRIGHT SIGN
+0xAA 0x0218 # LATIN CAPITAL LETTER S WITH COMMA BELOW
+0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xAC 0x0179 # LATIN CAPITAL LETTER Z WITH ACUTE
+0xAD 0x00AD # SOFT HYPHEN
+0xAE 0x017A # LATIN SMALL LETTER Z WITH ACUTE
+0xAF 0x017B # LATIN CAPITAL LETTER Z WITH DOT ABOVE
+0xB0 0x00B0 # DEGREE SIGN
+0xB1 0x00B1 # PLUS-MINUS SIGN
+0xB2 0x010C # LATIN CAPITAL LETTER C WITH CARON
+0xB3 0x0142 # LATIN SMALL LETTER L WITH STROKE
+0xB4 0x017D # LATIN CAPITAL LETTER Z WITH CARON
+0xB5 0x201D # RIGHT DOUBLE QUOTATION MARK
+0xB6 0x00B6 # PILCROW SIGN
+0xB7 0x00B7 # MIDDLE DOT
+0xB8 0x017E # LATIN SMALL LETTER Z WITH CARON
+0xB9 0x010D # LATIN SMALL LETTER C WITH CARON
+0xBA 0x0219 # LATIN SMALL LETTER S WITH COMMA BELOW
+0xBB 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xBC 0x0152 # LATIN CAPITAL LIGATURE OE
+0xBD 0x0153 # LATIN SMALL LIGATURE OE
+0xBE 0x0178 # LATIN CAPITAL LETTER Y WITH DIAERESIS
+0xBF 0x017C # LATIN SMALL LETTER Z WITH DOT ABOVE
+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 0x0106 # LATIN CAPITAL LETTER C WITH ACUTE
+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 0x0110 # LATIN CAPITAL LETTER D WITH STROKE
+0xD1 0x0143 # LATIN CAPITAL LETTER N WITH ACUTE
+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 0x0150 # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
+0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
+0xD7 0x015A # LATIN CAPITAL LETTER S WITH ACUTE
+0xD8 0x0170 # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
+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 0x0118 # LATIN CAPITAL LETTER E WITH OGONEK
+0xDE 0x021A # LATIN CAPITAL LETTER T WITH COMMA BELOW
+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 0x0107 # LATIN SMALL LETTER C WITH ACUTE
+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 0x0111 # LATIN SMALL LETTER D WITH STROKE
+0xF1 0x0144 # LATIN SMALL LETTER N WITH ACUTE
+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 0x0151 # LATIN SMALL LETTER O WITH DOUBLE ACUTE
+0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
+0xF7 0x015B # LATIN SMALL LETTER S WITH ACUTE
+0xF8 0x0171 # LATIN SMALL LETTER U WITH DOUBLE ACUTE
+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 0x0119 # LATIN SMALL LETTER E WITH OGONEK
+0xFE 0x021B # LATIN SMALL LETTER T WITH COMMA BELOW
+0xFF 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS
diff --git a/extra/io/encodings/8-bit/8859-2.TXT b/extra/io/encodings/8-bit/8859-2.TXT
new file mode 100644
index 0000000000..e45df25eb8
--- /dev/null
+++ b/extra/io/encodings/8-bit/8859-2.TXT
@@ -0,0 +1,303 @@
+#
+# Name: ISO 8859-2:1999 to Unicode
+# Unicode version: 3.0
+# Table version: 1.0
+# Table format: Format A
+# Date: 1999 July 27
+# Authors: Ken Whistler <kenw@sybase.com>
+#
+# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved.
+#
+# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
+# No claims are made as to fitness for any particular purpose. No
+# warranties of any kind are expressed or implied. The recipient
+# agrees to determine applicability of information provided. If this
+# file has been provided on optical media by Unicode, Inc., the sole
+# remedy for any claim will be exchange of defective media within 90
+# days of receipt.
+#
+# Unicode, Inc. hereby grants the right to freely use the information
+# supplied in this file in the creation of products supporting the
+# Unicode Standard, and to make copies of this file in any form for
+# internal or external distribution as long as this notice remains
+# attached.
+#
+# General notes:
+#
+# This table contains the data the Unicode Consortium has on how
+# ISO/IEC 8859-2:1999 characters map into Unicode.
+#
+# Format: Three tab-separated columns
+# Column #1 is the ISO/IEC 8859-2 code (in hex as 0xXX)
+# Column #2 is the Unicode (in hex as 0xXXXX)
+# Column #3 the Unicode name (follows a comment sign, '#')
+#
+# The entries are in ISO/IEC 8859-2 order.
+#
+# Version history
+# 1.0 version updates 0.1 version by adding mappings for all
+# control characters.
+#
+# Updated versions of this file may be found in:
+# <ftp://ftp.unicode.org/Public/MAPPINGS/>
+#
+# Any comments or problems, contact <errata@unicode.org>
+# Please note that <errata@unicode.org> is an archival address;
+# notices will be checked, but do not expect an immediate response.
+#
+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 0x0080 # <control>
+0x81 0x0081 # <control>
+0x82 0x0082 # <control>
+0x83 0x0083 # <control>
+0x84 0x0084 # <control>
+0x85 0x0085 # <control>
+0x86 0x0086 # <control>
+0x87 0x0087 # <control>
+0x88 0x0088 # <control>
+0x89 0x0089 # <control>
+0x8A 0x008A # <control>
+0x8B 0x008B # <control>
+0x8C 0x008C # <control>
+0x8D 0x008D # <control>
+0x8E 0x008E # <control>
+0x8F 0x008F # <control>
+0x90 0x0090 # <control>
+0x91 0x0091 # <control>
+0x92 0x0092 # <control>
+0x93 0x0093 # <control>
+0x94 0x0094 # <control>
+0x95 0x0095 # <control>
+0x96 0x0096 # <control>
+0x97 0x0097 # <control>
+0x98 0x0098 # <control>
+0x99 0x0099 # <control>
+0x9A 0x009A # <control>
+0x9B 0x009B # <control>
+0x9C 0x009C # <control>
+0x9D 0x009D # <control>
+0x9E 0x009E # <control>
+0x9F 0x009F # <control>
+0xA0 0x00A0 # NO-BREAK SPACE
+0xA1 0x0104 # LATIN CAPITAL LETTER A WITH OGONEK
+0xA2 0x02D8 # BREVE
+0xA3 0x0141 # LATIN CAPITAL LETTER L WITH STROKE
+0xA4 0x00A4 # CURRENCY SIGN
+0xA5 0x013D # LATIN CAPITAL LETTER L WITH CARON
+0xA6 0x015A # LATIN CAPITAL LETTER S WITH ACUTE
+0xA7 0x00A7 # SECTION SIGN
+0xA8 0x00A8 # DIAERESIS
+0xA9 0x0160 # LATIN CAPITAL LETTER S WITH CARON
+0xAA 0x015E # LATIN CAPITAL LETTER S WITH CEDILLA
+0xAB 0x0164 # LATIN CAPITAL LETTER T WITH CARON
+0xAC 0x0179 # LATIN CAPITAL LETTER Z WITH ACUTE
+0xAD 0x00AD # SOFT HYPHEN
+0xAE 0x017D # LATIN CAPITAL LETTER Z WITH CARON
+0xAF 0x017B # LATIN CAPITAL LETTER Z WITH DOT ABOVE
+0xB0 0x00B0 # DEGREE SIGN
+0xB1 0x0105 # LATIN SMALL LETTER A WITH OGONEK
+0xB2 0x02DB # OGONEK
+0xB3 0x0142 # LATIN SMALL LETTER L WITH STROKE
+0xB4 0x00B4 # ACUTE ACCENT
+0xB5 0x013E # LATIN SMALL LETTER L WITH CARON
+0xB6 0x015B # LATIN SMALL LETTER S WITH ACUTE
+0xB7 0x02C7 # CARON
+0xB8 0x00B8 # CEDILLA
+0xB9 0x0161 # LATIN SMALL LETTER S WITH CARON
+0xBA 0x015F # LATIN SMALL LETTER S WITH CEDILLA
+0xBB 0x0165 # LATIN SMALL LETTER T WITH CARON
+0xBC 0x017A # LATIN SMALL LETTER Z WITH ACUTE
+0xBD 0x02DD # DOUBLE ACUTE ACCENT
+0xBE 0x017E # LATIN SMALL LETTER Z WITH CARON
+0xBF 0x017C # LATIN SMALL LETTER Z WITH DOT ABOVE
+0xC0 0x0154 # LATIN CAPITAL LETTER R WITH ACUTE
+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 0x0139 # LATIN CAPITAL LETTER L WITH ACUTE
+0xC6 0x0106 # LATIN CAPITAL LETTER C WITH ACUTE
+0xC7 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA
+0xC8 0x010C # LATIN CAPITAL LETTER C WITH CARON
+0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
+0xCA 0x0118 # LATIN CAPITAL LETTER E WITH OGONEK
+0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS
+0xCC 0x011A # LATIN CAPITAL LETTER E WITH CARON
+0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE
+0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+0xCF 0x010E # LATIN CAPITAL LETTER D WITH CARON
+0xD0 0x0110 # LATIN CAPITAL LETTER D WITH STROKE
+0xD1 0x0143 # LATIN CAPITAL LETTER N WITH ACUTE
+0xD2 0x0147 # LATIN CAPITAL LETTER N WITH CARON
+0xD3 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE
+0xD4 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+0xD5 0x0150 # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
+0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
+0xD7 0x00D7 # MULTIPLICATION SIGN
+0xD8 0x0158 # LATIN CAPITAL LETTER R WITH CARON
+0xD9 0x016E # LATIN CAPITAL LETTER U WITH RING ABOVE
+0xDA 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE
+0xDB 0x0170 # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
+0xDC 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS
+0xDD 0x00DD # LATIN CAPITAL LETTER Y WITH ACUTE
+0xDE 0x0162 # LATIN CAPITAL LETTER T WITH CEDILLA
+0xDF 0x00DF # LATIN SMALL LETTER SHARP S
+0xE0 0x0155 # LATIN SMALL LETTER R WITH ACUTE
+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 0x013A # LATIN SMALL LETTER L WITH ACUTE
+0xE6 0x0107 # LATIN SMALL LETTER C WITH ACUTE
+0xE7 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA
+0xE8 0x010D # LATIN SMALL LETTER C WITH CARON
+0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
+0xEA 0x0119 # LATIN SMALL LETTER E WITH OGONEK
+0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS
+0xEC 0x011B # LATIN SMALL LETTER E WITH CARON
+0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE
+0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX
+0xEF 0x010F # LATIN SMALL LETTER D WITH CARON
+0xF0 0x0111 # LATIN SMALL LETTER D WITH STROKE
+0xF1 0x0144 # LATIN SMALL LETTER N WITH ACUTE
+0xF2 0x0148 # LATIN SMALL LETTER N WITH CARON
+0xF3 0x00F3 # LATIN SMALL LETTER O WITH ACUTE
+0xF4 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX
+0xF5 0x0151 # LATIN SMALL LETTER O WITH DOUBLE ACUTE
+0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
+0xF7 0x00F7 # DIVISION SIGN
+0xF8 0x0159 # LATIN SMALL LETTER R WITH CARON
+0xF9 0x016F # LATIN SMALL LETTER U WITH RING ABOVE
+0xFA 0x00FA # LATIN SMALL LETTER U WITH ACUTE
+0xFB 0x0171 # LATIN SMALL LETTER U WITH DOUBLE ACUTE
+0xFC 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS
+0xFD 0x00FD # LATIN SMALL LETTER Y WITH ACUTE
+0xFE 0x0163 # LATIN SMALL LETTER T WITH CEDILLA
+0xFF 0x02D9 # DOT ABOVE
diff --git a/extra/io/encodings/8-bit/8859-3.TXT b/extra/io/encodings/8-bit/8859-3.TXT
new file mode 100644
index 0000000000..9b6ac69dd8
--- /dev/null
+++ b/extra/io/encodings/8-bit/8859-3.TXT
@@ -0,0 +1,296 @@
+#
+# Name: ISO/IEC 8859-3:1999 to Unicode
+# Unicode version: 3.0
+# Table version: 1.0
+# Table format: Format A
+# Date: 1999 July 27
+# Authors: Ken Whistler <kenw@sybase.com>
+#
+# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved.
+#
+# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
+# No claims are made as to fitness for any particular purpose. No
+# warranties of any kind are expressed or implied. The recipient
+# agrees to determine applicability of information provided. If this
+# file has been provided on optical media by Unicode, Inc., the sole
+# remedy for any claim will be exchange of defective media within 90
+# days of receipt.
+#
+# Unicode, Inc. hereby grants the right to freely use the information
+# supplied in this file in the creation of products supporting the
+# Unicode Standard, and to make copies of this file in any form for
+# internal or external distribution as long as this notice remains
+# attached.
+#
+# General notes:
+#
+# This table contains the data the Unicode Consortium has on how
+# ISO/IEC 8859-3:1999 characters map into Unicode.
+#
+# Format: Three tab-separated columns
+# Column #1 is the ISO/IEC 8859-3 code (in hex as 0xXX)
+# Column #2 is the Unicode (in hex as 0xXXXX)
+# Column #3 the Unicode name (follows a comment sign, '#')
+#
+# The entries are in ISO/IEC 8859-3 order.
+#
+# Version history
+# 1.0 version updates 0.1 version by adding mappings for all
+# control characters.
+#
+# Updated versions of this file may be found in:
+# <ftp://ftp.unicode.org/Public/MAPPINGS/>
+#
+# Any comments or problems, contact <errata@unicode.org>
+# Please note that <errata@unicode.org> is an archival address;
+# notices will be checked, but do not expect an immediate response.
+#
+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 0x0080 # <control>
+0x81 0x0081 # <control>
+0x82 0x0082 # <control>
+0x83 0x0083 # <control>
+0x84 0x0084 # <control>
+0x85 0x0085 # <control>
+0x86 0x0086 # <control>
+0x87 0x0087 # <control>
+0x88 0x0088 # <control>
+0x89 0x0089 # <control>
+0x8A 0x008A # <control>
+0x8B 0x008B # <control>
+0x8C 0x008C # <control>
+0x8D 0x008D # <control>
+0x8E 0x008E # <control>
+0x8F 0x008F # <control>
+0x90 0x0090 # <control>
+0x91 0x0091 # <control>
+0x92 0x0092 # <control>
+0x93 0x0093 # <control>
+0x94 0x0094 # <control>
+0x95 0x0095 # <control>
+0x96 0x0096 # <control>
+0x97 0x0097 # <control>
+0x98 0x0098 # <control>
+0x99 0x0099 # <control>
+0x9A 0x009A # <control>
+0x9B 0x009B # <control>
+0x9C 0x009C # <control>
+0x9D 0x009D # <control>
+0x9E 0x009E # <control>
+0x9F 0x009F # <control>
+0xA0 0x00A0 # NO-BREAK SPACE
+0xA1 0x0126 # LATIN CAPITAL LETTER H WITH STROKE
+0xA2 0x02D8 # BREVE
+0xA3 0x00A3 # POUND SIGN
+0xA4 0x00A4 # CURRENCY SIGN
+0xA6 0x0124 # LATIN CAPITAL LETTER H WITH CIRCUMFLEX
+0xA7 0x00A7 # SECTION SIGN
+0xA8 0x00A8 # DIAERESIS
+0xA9 0x0130 # LATIN CAPITAL LETTER I WITH DOT ABOVE
+0xAA 0x015E # LATIN CAPITAL LETTER S WITH CEDILLA
+0xAB 0x011E # LATIN CAPITAL LETTER G WITH BREVE
+0xAC 0x0134 # LATIN CAPITAL LETTER J WITH CIRCUMFLEX
+0xAD 0x00AD # SOFT HYPHEN
+0xAF 0x017B # LATIN CAPITAL LETTER Z WITH DOT ABOVE
+0xB0 0x00B0 # DEGREE SIGN
+0xB1 0x0127 # LATIN SMALL LETTER H WITH STROKE
+0xB2 0x00B2 # SUPERSCRIPT TWO
+0xB3 0x00B3 # SUPERSCRIPT THREE
+0xB4 0x00B4 # ACUTE ACCENT
+0xB5 0x00B5 # MICRO SIGN
+0xB6 0x0125 # LATIN SMALL LETTER H WITH CIRCUMFLEX
+0xB7 0x00B7 # MIDDLE DOT
+0xB8 0x00B8 # CEDILLA
+0xB9 0x0131 # LATIN SMALL LETTER DOTLESS I
+0xBA 0x015F # LATIN SMALL LETTER S WITH CEDILLA
+0xBB 0x011F # LATIN SMALL LETTER G WITH BREVE
+0xBC 0x0135 # LATIN SMALL LETTER J WITH CIRCUMFLEX
+0xBD 0x00BD # VULGAR FRACTION ONE HALF
+0xBF 0x017C # LATIN SMALL LETTER Z WITH DOT ABOVE
+0xC0 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE
+0xC1 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE
+0xC2 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+0xC4 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS
+0xC5 0x010A # LATIN CAPITAL LETTER C WITH DOT ABOVE
+0xC6 0x0108 # LATIN CAPITAL LETTER C WITH CIRCUMFLEX
+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
+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 0x0120 # LATIN CAPITAL LETTER G WITH DOT ABOVE
+0xD6 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
+0xD7 0x00D7 # MULTIPLICATION SIGN
+0xD8 0x011C # LATIN CAPITAL LETTER G WITH CIRCUMFLEX
+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 0x016C # LATIN CAPITAL LETTER U WITH BREVE
+0xDE 0x015C # LATIN CAPITAL LETTER S WITH CIRCUMFLEX
+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
+0xE4 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS
+0xE5 0x010B # LATIN SMALL LETTER C WITH DOT ABOVE
+0xE6 0x0109 # LATIN SMALL LETTER C WITH CIRCUMFLEX
+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
+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 0x0121 # LATIN SMALL LETTER G WITH DOT ABOVE
+0xF6 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
+0xF7 0x00F7 # DIVISION SIGN
+0xF8 0x011D # LATIN SMALL LETTER G WITH CIRCUMFLEX
+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 0x016D # LATIN SMALL LETTER U WITH BREVE
+0xFE 0x015D # LATIN SMALL LETTER S WITH CIRCUMFLEX
+0xFF 0x02D9 # DOT ABOVE
diff --git a/extra/io/encodings/8-bit/8859-4.TXT b/extra/io/encodings/8-bit/8859-4.TXT
new file mode 100644
index 0000000000..662e698ab2
--- /dev/null
+++ b/extra/io/encodings/8-bit/8859-4.TXT
@@ -0,0 +1,303 @@
+#
+# Name: ISO/IEC 8859-4:1998 to Unicode
+# Unicode version: 3.0
+# Table version: 1.0
+# Table format: Format A
+# Date: 1999 July 27
+# Authors: Ken Whistler <kenw@sybase.com>
+#
+# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved.
+#
+# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
+# No claims are made as to fitness for any particular purpose. No
+# warranties of any kind are expressed or implied. The recipient
+# agrees to determine applicability of information provided. If this
+# file has been provided on optical media by Unicode, Inc., the sole
+# remedy for any claim will be exchange of defective media within 90
+# days of receipt.
+#
+# Unicode, Inc. hereby grants the right to freely use the information
+# supplied in this file in the creation of products supporting the
+# Unicode Standard, and to make copies of this file in any form for
+# internal or external distribution as long as this notice remains
+# attached.
+#
+# General notes:
+#
+# This table contains the data the Unicode Consortium has on how
+# ISO/IEC 8859-4:1998 characters map into Unicode.
+#
+# Format: Three tab-separated columns
+# Column #1 is the ISO/IEC 8859-4 code (in hex as 0xXX)
+# Column #2 is the Unicode (in hex as 0xXXXX)
+# Column #3 the Unicode name (follows a comment sign, '#')
+#
+# The entries are in ISO/IEC 8859-4 order.
+#
+# Version history
+# 1.0 version updates 0.1 version by adding mappings for all
+# control characters.
+#
+# Updated versions of this file may be found in:
+# <ftp://ftp.unicode.org/Public/MAPPINGS/>
+#
+# Any comments or problems, contact <errata@unicode.org>
+# Please note that <errata@unicode.org> is an archival address;
+# notices will be checked, but do not expect an immediate response.
+#
+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 0x0080 # <control>
+0x81 0x0081 # <control>
+0x82 0x0082 # <control>
+0x83 0x0083 # <control>
+0x84 0x0084 # <control>
+0x85 0x0085 # <control>
+0x86 0x0086 # <control>
+0x87 0x0087 # <control>
+0x88 0x0088 # <control>
+0x89 0x0089 # <control>
+0x8A 0x008A # <control>
+0x8B 0x008B # <control>
+0x8C 0x008C # <control>
+0x8D 0x008D # <control>
+0x8E 0x008E # <control>
+0x8F 0x008F # <control>
+0x90 0x0090 # <control>
+0x91 0x0091 # <control>
+0x92 0x0092 # <control>
+0x93 0x0093 # <control>
+0x94 0x0094 # <control>
+0x95 0x0095 # <control>
+0x96 0x0096 # <control>
+0x97 0x0097 # <control>
+0x98 0x0098 # <control>
+0x99 0x0099 # <control>
+0x9A 0x009A # <control>
+0x9B 0x009B # <control>
+0x9C 0x009C # <control>
+0x9D 0x009D # <control>
+0x9E 0x009E # <control>
+0x9F 0x009F # <control>
+0xA0 0x00A0 # NO-BREAK SPACE
+0xA1 0x0104 # LATIN CAPITAL LETTER A WITH OGONEK
+0xA2 0x0138 # LATIN SMALL LETTER KRA
+0xA3 0x0156 # LATIN CAPITAL LETTER R WITH CEDILLA
+0xA4 0x00A4 # CURRENCY SIGN
+0xA5 0x0128 # LATIN CAPITAL LETTER I WITH TILDE
+0xA6 0x013B # LATIN CAPITAL LETTER L WITH CEDILLA
+0xA7 0x00A7 # SECTION SIGN
+0xA8 0x00A8 # DIAERESIS
+0xA9 0x0160 # LATIN CAPITAL LETTER S WITH CARON
+0xAA 0x0112 # LATIN CAPITAL LETTER E WITH MACRON
+0xAB 0x0122 # LATIN CAPITAL LETTER G WITH CEDILLA
+0xAC 0x0166 # LATIN CAPITAL LETTER T WITH STROKE
+0xAD 0x00AD # SOFT HYPHEN
+0xAE 0x017D # LATIN CAPITAL LETTER Z WITH CARON
+0xAF 0x00AF # MACRON
+0xB0 0x00B0 # DEGREE SIGN
+0xB1 0x0105 # LATIN SMALL LETTER A WITH OGONEK
+0xB2 0x02DB # OGONEK
+0xB3 0x0157 # LATIN SMALL LETTER R WITH CEDILLA
+0xB4 0x00B4 # ACUTE ACCENT
+0xB5 0x0129 # LATIN SMALL LETTER I WITH TILDE
+0xB6 0x013C # LATIN SMALL LETTER L WITH CEDILLA
+0xB7 0x02C7 # CARON
+0xB8 0x00B8 # CEDILLA
+0xB9 0x0161 # LATIN SMALL LETTER S WITH CARON
+0xBA 0x0113 # LATIN SMALL LETTER E WITH MACRON
+0xBB 0x0123 # LATIN SMALL LETTER G WITH CEDILLA
+0xBC 0x0167 # LATIN SMALL LETTER T WITH STROKE
+0xBD 0x014A # LATIN CAPITAL LETTER ENG
+0xBE 0x017E # LATIN SMALL LETTER Z WITH CARON
+0xBF 0x014B # LATIN SMALL LETTER ENG
+0xC0 0x0100 # LATIN CAPITAL LETTER A WITH MACRON
+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 0x012E # LATIN CAPITAL LETTER I WITH OGONEK
+0xC8 0x010C # LATIN CAPITAL LETTER C WITH CARON
+0xC9 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
+0xCA 0x0118 # LATIN CAPITAL LETTER E WITH OGONEK
+0xCB 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS
+0xCC 0x0116 # LATIN CAPITAL LETTER E WITH DOT ABOVE
+0xCD 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE
+0xCE 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+0xCF 0x012A # LATIN CAPITAL LETTER I WITH MACRON
+0xD0 0x0110 # LATIN CAPITAL LETTER D WITH STROKE
+0xD1 0x0145 # LATIN CAPITAL LETTER N WITH CEDILLA
+0xD2 0x014C # LATIN CAPITAL LETTER O WITH MACRON
+0xD3 0x0136 # LATIN CAPITAL LETTER K WITH CEDILLA
+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 0x0172 # LATIN CAPITAL LETTER U WITH OGONEK
+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 0x0168 # LATIN CAPITAL LETTER U WITH TILDE
+0xDE 0x016A # LATIN CAPITAL LETTER U WITH MACRON
+0xDF 0x00DF # LATIN SMALL LETTER SHARP S
+0xE0 0x0101 # LATIN SMALL LETTER A WITH MACRON
+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 0x012F # LATIN SMALL LETTER I WITH OGONEK
+0xE8 0x010D # LATIN SMALL LETTER C WITH CARON
+0xE9 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
+0xEA 0x0119 # LATIN SMALL LETTER E WITH OGONEK
+0xEB 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS
+0xEC 0x0117 # LATIN SMALL LETTER E WITH DOT ABOVE
+0xED 0x00ED # LATIN SMALL LETTER I WITH ACUTE
+0xEE 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX
+0xEF 0x012B # LATIN SMALL LETTER I WITH MACRON
+0xF0 0x0111 # LATIN SMALL LETTER D WITH STROKE
+0xF1 0x0146 # LATIN SMALL LETTER N WITH CEDILLA
+0xF2 0x014D # LATIN SMALL LETTER O WITH MACRON
+0xF3 0x0137 # LATIN SMALL LETTER K WITH CEDILLA
+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 0x0173 # LATIN SMALL LETTER U WITH OGONEK
+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 0x0169 # LATIN SMALL LETTER U WITH TILDE
+0xFE 0x016B # LATIN SMALL LETTER U WITH MACRON
+0xFF 0x02D9 # DOT ABOVE
diff --git a/extra/io/encodings/8-bit/8859-5.TXT b/extra/io/encodings/8-bit/8859-5.TXT
new file mode 100644
index 0000000000..a7ed1ce2ab
--- /dev/null
+++ b/extra/io/encodings/8-bit/8859-5.TXT
@@ -0,0 +1,303 @@
+#
+# Name: ISO 8859-5:1999 to Unicode
+# Unicode version: 3.0
+# Table version: 1.0
+# Table format: Format A
+# Date: 1999 July 27
+# Authors: Ken Whistler <kenw@sybase.com>
+#
+# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved.
+#
+# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
+# No claims are made as to fitness for any particular purpose. No
+# warranties of any kind are expressed or implied. The recipient
+# agrees to determine applicability of information provided. If this
+# file has been provided on optical media by Unicode, Inc., the sole
+# remedy for any claim will be exchange of defective media within 90
+# days of receipt.
+#
+# Unicode, Inc. hereby grants the right to freely use the information
+# supplied in this file in the creation of products supporting the
+# Unicode Standard, and to make copies of this file in any form for
+# internal or external distribution as long as this notice remains
+# attached.
+#
+# General notes:
+#
+# This table contains the data the Unicode Consortium has on how
+# ISO/IEC 8859-5:1999 characters map into Unicode.
+#
+# Format: Three tab-separated columns
+# Column #1 is the ISO/IEC 8859-5 code (in hex as 0xXX)
+# Column #2 is the Unicode (in hex as 0xXXXX)
+# Column #3 the Unicode name (follows a comment sign, '#')
+#
+# The entries are in ISO/IEC 8859-5 order.
+#
+# Version history
+# 1.0 version updates 0.1 version by adding mappings for all
+# control characters.
+#
+# Updated versions of this file may be found in:
+# <ftp://ftp.unicode.org/Public/MAPPINGS/>
+#
+# Any comments or problems, contact <errata@unicode.org>
+# Please note that <errata@unicode.org> is an archival address;
+# notices will be checked, but do not expect an immediate response.
+#
+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 0x0080 # <control>
+0x81 0x0081 # <control>
+0x82 0x0082 # <control>
+0x83 0x0083 # <control>
+0x84 0x0084 # <control>
+0x85 0x0085 # <control>
+0x86 0x0086 # <control>
+0x87 0x0087 # <control>
+0x88 0x0088 # <control>
+0x89 0x0089 # <control>
+0x8A 0x008A # <control>
+0x8B 0x008B # <control>
+0x8C 0x008C # <control>
+0x8D 0x008D # <control>
+0x8E 0x008E # <control>
+0x8F 0x008F # <control>
+0x90 0x0090 # <control>
+0x91 0x0091 # <control>
+0x92 0x0092 # <control>
+0x93 0x0093 # <control>
+0x94 0x0094 # <control>
+0x95 0x0095 # <control>
+0x96 0x0096 # <control>
+0x97 0x0097 # <control>
+0x98 0x0098 # <control>
+0x99 0x0099 # <control>
+0x9A 0x009A # <control>
+0x9B 0x009B # <control>
+0x9C 0x009C # <control>
+0x9D 0x009D # <control>
+0x9E 0x009E # <control>
+0x9F 0x009F # <control>
+0xA0 0x00A0 # NO-BREAK SPACE
+0xA1 0x0401 # CYRILLIC CAPITAL LETTER IO
+0xA2 0x0402 # CYRILLIC CAPITAL LETTER DJE
+0xA3 0x0403 # CYRILLIC CAPITAL LETTER GJE
+0xA4 0x0404 # CYRILLIC CAPITAL LETTER UKRAINIAN IE
+0xA5 0x0405 # CYRILLIC CAPITAL LETTER DZE
+0xA6 0x0406 # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
+0xA7 0x0407 # CYRILLIC CAPITAL LETTER YI
+0xA8 0x0408 # CYRILLIC CAPITAL LETTER JE
+0xA9 0x0409 # CYRILLIC CAPITAL LETTER LJE
+0xAA 0x040A # CYRILLIC CAPITAL LETTER NJE
+0xAB 0x040B # CYRILLIC CAPITAL LETTER TSHE
+0xAC 0x040C # CYRILLIC CAPITAL LETTER KJE
+0xAD 0x00AD # SOFT HYPHEN
+0xAE 0x040E # CYRILLIC CAPITAL LETTER SHORT U
+0xAF 0x040F # CYRILLIC CAPITAL LETTER DZHE
+0xB0 0x0410 # CYRILLIC CAPITAL LETTER A
+0xB1 0x0411 # CYRILLIC CAPITAL LETTER BE
+0xB2 0x0412 # CYRILLIC CAPITAL LETTER VE
+0xB3 0x0413 # CYRILLIC CAPITAL LETTER GHE
+0xB4 0x0414 # CYRILLIC CAPITAL LETTER DE
+0xB5 0x0415 # CYRILLIC CAPITAL LETTER IE
+0xB6 0x0416 # CYRILLIC CAPITAL LETTER ZHE
+0xB7 0x0417 # CYRILLIC CAPITAL LETTER ZE
+0xB8 0x0418 # CYRILLIC CAPITAL LETTER I
+0xB9 0x0419 # CYRILLIC CAPITAL LETTER SHORT I
+0xBA 0x041A # CYRILLIC CAPITAL LETTER KA
+0xBB 0x041B # CYRILLIC CAPITAL LETTER EL
+0xBC 0x041C # CYRILLIC CAPITAL LETTER EM
+0xBD 0x041D # CYRILLIC CAPITAL LETTER EN
+0xBE 0x041E # CYRILLIC CAPITAL LETTER O
+0xBF 0x041F # CYRILLIC CAPITAL LETTER PE
+0xC0 0x0420 # CYRILLIC CAPITAL LETTER ER
+0xC1 0x0421 # CYRILLIC CAPITAL LETTER ES
+0xC2 0x0422 # CYRILLIC CAPITAL LETTER TE
+0xC3 0x0423 # CYRILLIC CAPITAL LETTER U
+0xC4 0x0424 # CYRILLIC CAPITAL LETTER EF
+0xC5 0x0425 # CYRILLIC CAPITAL LETTER HA
+0xC6 0x0426 # CYRILLIC CAPITAL LETTER TSE
+0xC7 0x0427 # CYRILLIC CAPITAL LETTER CHE
+0xC8 0x0428 # CYRILLIC CAPITAL LETTER SHA
+0xC9 0x0429 # CYRILLIC CAPITAL LETTER SHCHA
+0xCA 0x042A # CYRILLIC CAPITAL LETTER HARD SIGN
+0xCB 0x042B # CYRILLIC CAPITAL LETTER YERU
+0xCC 0x042C # CYRILLIC CAPITAL LETTER SOFT SIGN
+0xCD 0x042D # CYRILLIC CAPITAL LETTER E
+0xCE 0x042E # CYRILLIC CAPITAL LETTER YU
+0xCF 0x042F # CYRILLIC CAPITAL LETTER YA
+0xD0 0x0430 # CYRILLIC SMALL LETTER A
+0xD1 0x0431 # CYRILLIC SMALL LETTER BE
+0xD2 0x0432 # CYRILLIC SMALL LETTER VE
+0xD3 0x0433 # CYRILLIC SMALL LETTER GHE
+0xD4 0x0434 # CYRILLIC SMALL LETTER DE
+0xD5 0x0435 # CYRILLIC SMALL LETTER IE
+0xD6 0x0436 # CYRILLIC SMALL LETTER ZHE
+0xD7 0x0437 # CYRILLIC SMALL LETTER ZE
+0xD8 0x0438 # CYRILLIC SMALL LETTER I
+0xD9 0x0439 # CYRILLIC SMALL LETTER SHORT I
+0xDA 0x043A # CYRILLIC SMALL LETTER KA
+0xDB 0x043B # CYRILLIC SMALL LETTER EL
+0xDC 0x043C # CYRILLIC SMALL LETTER EM
+0xDD 0x043D # CYRILLIC SMALL LETTER EN
+0xDE 0x043E # CYRILLIC SMALL LETTER O
+0xDF 0x043F # CYRILLIC SMALL LETTER PE
+0xE0 0x0440 # CYRILLIC SMALL LETTER ER
+0xE1 0x0441 # CYRILLIC SMALL LETTER ES
+0xE2 0x0442 # CYRILLIC SMALL LETTER TE
+0xE3 0x0443 # CYRILLIC SMALL LETTER U
+0xE4 0x0444 # CYRILLIC SMALL LETTER EF
+0xE5 0x0445 # CYRILLIC SMALL LETTER HA
+0xE6 0x0446 # CYRILLIC SMALL LETTER TSE
+0xE7 0x0447 # CYRILLIC SMALL LETTER CHE
+0xE8 0x0448 # CYRILLIC SMALL LETTER SHA
+0xE9 0x0449 # CYRILLIC SMALL LETTER SHCHA
+0xEA 0x044A # CYRILLIC SMALL LETTER HARD SIGN
+0xEB 0x044B # CYRILLIC SMALL LETTER YERU
+0xEC 0x044C # CYRILLIC SMALL LETTER SOFT SIGN
+0xED 0x044D # CYRILLIC SMALL LETTER E
+0xEE 0x044E # CYRILLIC SMALL LETTER YU
+0xEF 0x044F # CYRILLIC SMALL LETTER YA
+0xF0 0x2116 # NUMERO SIGN
+0xF1 0x0451 # CYRILLIC SMALL LETTER IO
+0xF2 0x0452 # CYRILLIC SMALL LETTER DJE
+0xF3 0x0453 # CYRILLIC SMALL LETTER GJE
+0xF4 0x0454 # CYRILLIC SMALL LETTER UKRAINIAN IE
+0xF5 0x0455 # CYRILLIC SMALL LETTER DZE
+0xF6 0x0456 # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
+0xF7 0x0457 # CYRILLIC SMALL LETTER YI
+0xF8 0x0458 # CYRILLIC SMALL LETTER JE
+0xF9 0x0459 # CYRILLIC SMALL LETTER LJE
+0xFA 0x045A # CYRILLIC SMALL LETTER NJE
+0xFB 0x045B # CYRILLIC SMALL LETTER TSHE
+0xFC 0x045C # CYRILLIC SMALL LETTER KJE
+0xFD 0x00A7 # SECTION SIGN
+0xFE 0x045E # CYRILLIC SMALL LETTER SHORT U
+0xFF 0x045F # CYRILLIC SMALL LETTER DZHE
diff --git a/extra/io/encodings/8-bit/8859-6.TXT b/extra/io/encodings/8-bit/8859-6.TXT
new file mode 100644
index 0000000000..69ac7f5894
--- /dev/null
+++ b/extra/io/encodings/8-bit/8859-6.TXT
@@ -0,0 +1,260 @@
+#
+# Name: ISO 8859-6:1999 to Unicode
+# Unicode version: 3.0
+# Table version: 1.0
+# Table format: Format A
+# Date: 1999 July 27
+# Authors: Ken Whistler <kenw@sybase.com>
+#
+# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved.
+#
+# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
+# No claims are made as to fitness for any particular purpose. No
+# warranties of any kind are expressed or implied. The recipient
+# agrees to determine applicability of information provided. If this
+# file has been provided on optical media by Unicode, Inc., the sole
+# remedy for any claim will be exchange of defective media within 90
+# days of receipt.
+#
+# Unicode, Inc. hereby grants the right to freely use the information
+# supplied in this file in the creation of products supporting the
+# Unicode Standard, and to make copies of this file in any form for
+# internal or external distribution as long as this notice remains
+# attached.
+#
+# General notes:
+#
+# This table contains the data the Unicode Consortium has on how
+# ISO/IEC 8859-6:1999 characters map into Unicode.
+#
+# Format: Three tab-separated columns
+# Column #1 is the ISO/IEC 8859-6 code (in hex as 0xXX)
+# Column #2 is the Unicode (in hex as 0xXXXX)
+# Column #3 the Unicode name (follows a comment sign, '#')
+#
+# The entries are in ISO/IEC 8859-6 order.
+#
+# Version history
+# 1.0 version updates 0.1 version by adding mappings for all
+# control characters.
+# 0x30..0x39 remapped to the ASCII digits (U+0030..U+0039) instead
+# of the Arabic digits (U+0660..U+0669).
+#
+# Updated versions of this file may be found in:
+# <ftp://ftp.unicode.org/Public/MAPPINGS/>
+#
+# Any comments or problems, contact <errata@unicode.org>
+# Please note that <errata@unicode.org> is an archival address;
+# notices will be checked, but do not expect an immediate response.
+#
+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 0x0080 # <control>
+0x81 0x0081 # <control>
+0x82 0x0082 # <control>
+0x83 0x0083 # <control>
+0x84 0x0084 # <control>
+0x85 0x0085 # <control>
+0x86 0x0086 # <control>
+0x87 0x0087 # <control>
+0x88 0x0088 # <control>
+0x89 0x0089 # <control>
+0x8A 0x008A # <control>
+0x8B 0x008B # <control>
+0x8C 0x008C # <control>
+0x8D 0x008D # <control>
+0x8E 0x008E # <control>
+0x8F 0x008F # <control>
+0x90 0x0090 # <control>
+0x91 0x0091 # <control>
+0x92 0x0092 # <control>
+0x93 0x0093 # <control>
+0x94 0x0094 # <control>
+0x95 0x0095 # <control>
+0x96 0x0096 # <control>
+0x97 0x0097 # <control>
+0x98 0x0098 # <control>
+0x99 0x0099 # <control>
+0x9A 0x009A # <control>
+0x9B 0x009B # <control>
+0x9C 0x009C # <control>
+0x9D 0x009D # <control>
+0x9E 0x009E # <control>
+0x9F 0x009F # <control>
+0xA0 0x00A0 # NO-BREAK SPACE
+0xA4 0x00A4 # CURRENCY SIGN
+0xAC 0x060C # ARABIC COMMA
+0xAD 0x00AD # SOFT HYPHEN
+0xBB 0x061B # ARABIC SEMICOLON
+0xBF 0x061F # ARABIC QUESTION MARK
+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 0x0637 # ARABIC LETTER TAH
+0xD8 0x0638 # ARABIC LETTER ZAH
+0xD9 0x0639 # ARABIC LETTER AIN
+0xDA 0x063A # ARABIC LETTER GHAIN
+0xE0 0x0640 # ARABIC TATWEEL
+0xE1 0x0641 # ARABIC LETTER FEH
+0xE2 0x0642 # ARABIC LETTER QAF
+0xE3 0x0643 # ARABIC LETTER KAF
+0xE4 0x0644 # ARABIC LETTER LAM
+0xE5 0x0645 # ARABIC LETTER MEEM
+0xE6 0x0646 # ARABIC LETTER NOON
+0xE7 0x0647 # ARABIC LETTER HEH
+0xE8 0x0648 # ARABIC LETTER WAW
+0xE9 0x0649 # ARABIC LETTER ALEF MAKSURA
+0xEA 0x064A # ARABIC LETTER YEH
+0xEB 0x064B # ARABIC FATHATAN
+0xEC 0x064C # ARABIC DAMMATAN
+0xED 0x064D # ARABIC KASRATAN
+0xEE 0x064E # ARABIC FATHA
+0xEF 0x064F # ARABIC DAMMA
+0xF0 0x0650 # ARABIC KASRA
+0xF1 0x0651 # ARABIC SHADDA
+0xF2 0x0652 # ARABIC SUKUN
diff --git a/extra/io/encodings/8-bit/8859-7.TXT b/extra/io/encodings/8-bit/8859-7.TXT
new file mode 100644
index 0000000000..bc46b74719
--- /dev/null
+++ b/extra/io/encodings/8-bit/8859-7.TXT
@@ -0,0 +1,308 @@
+#
+# Name: ISO 8859-7:2003 to Unicode
+# Unicode version: 4.0
+# Table version: 2.0
+# Table format: Format A
+# Date: 2003-Nov-12
+# Authors: Ken Whistler <kenw@sybase.com>
+#
+# Copyright (c) 1991-2003 Unicode, Inc. All Rights reserved.
+#
+# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
+# No claims are made as to fitness for any particular purpose. No
+# warranties of any kind are expressed or implied. The recipient
+# agrees to determine applicability of information provided. If this
+# file has been provided on optical media by Unicode, Inc., the sole
+# remedy for any claim will be exchange of defective media within 90
+# days of receipt.
+#
+# Unicode, Inc. hereby grants the right to freely use the information
+# supplied in this file in the creation of products supporting the
+# Unicode Standard, and to make copies of this file in any form for
+# internal or external distribution as long as this notice remains
+# attached.
+#
+# General notes:
+#
+# This table contains the data the Unicode Consortium has on how
+# ISO 8859-7:2003 characters map into Unicode.
+#
+# ISO 8859-7:1987 is equivalent to ISO-IR-126, ELOT 928,
+# and ECMA 118. ISO 8859-7:2003 adds two currency signs
+# and one other character not in the earlier standard.
+#
+# Format: Three tab-separated columns
+# Column #1 is the ISO 8859-7 code (in hex as 0xXX)
+# Column #2 is the Unicode (in hex as 0xXXXX)
+# Column #3 the Unicode name (follows a comment sign, '#')
+#
+# The entries are in ISO 8859-7 order.
+#
+# Version history
+# 1.0 version updates 0.1 version by adding mappings for all
+# control characters.
+# Remap 0xA1 to U+2018 (instead of 0x02BD) to match text of 8859-7
+# Remap 0xA2 to U+2019 (instead of 0x02BC) to match text of 8859-7
+#
+# 2.0 version updates 1.0 version by adding mappings for the
+# three newly added characters 0xA4, 0xA5, 0xAA.
+#
+# Updated versions of this file may be found in:
+# <http://www.unicode.org/Public/MAPPINGS/>
+#
+# Any comments or problems, contact the Unicode Consortium at:
+# <http://www.unicode.org/reporting.html>
+#
+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 0x0080 # <control>
+0x81 0x0081 # <control>
+0x82 0x0082 # <control>
+0x83 0x0083 # <control>
+0x84 0x0084 # <control>
+0x85 0x0085 # <control>
+0x86 0x0086 # <control>
+0x87 0x0087 # <control>
+0x88 0x0088 # <control>
+0x89 0x0089 # <control>
+0x8A 0x008A # <control>
+0x8B 0x008B # <control>
+0x8C 0x008C # <control>
+0x8D 0x008D # <control>
+0x8E 0x008E # <control>
+0x8F 0x008F # <control>
+0x90 0x0090 # <control>
+0x91 0x0091 # <control>
+0x92 0x0092 # <control>
+0x93 0x0093 # <control>
+0x94 0x0094 # <control>
+0x95 0x0095 # <control>
+0x96 0x0096 # <control>
+0x97 0x0097 # <control>
+0x98 0x0098 # <control>
+0x99 0x0099 # <control>
+0x9A 0x009A # <control>
+0x9B 0x009B # <control>
+0x9C 0x009C # <control>
+0x9D 0x009D # <control>
+0x9E 0x009E # <control>
+0x9F 0x009F # <control>
+0xA0 0x00A0 # NO-BREAK SPACE
+0xA1 0x2018 # LEFT SINGLE QUOTATION MARK
+0xA2 0x2019 # RIGHT SINGLE QUOTATION MARK
+0xA3 0x00A3 # POUND SIGN
+0xA4 0x20AC # EURO SIGN
+0xA5 0x20AF # DRACHMA SIGN
+0xA6 0x00A6 # BROKEN BAR
+0xA7 0x00A7 # SECTION SIGN
+0xA8 0x00A8 # DIAERESIS
+0xA9 0x00A9 # COPYRIGHT SIGN
+0xAA 0x037A # GREEK YPOGEGRAMMENI
+0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xAC 0x00AC # NOT SIGN
+0xAD 0x00AD # SOFT HYPHEN
+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 0x0385 # GREEK DIALYTIKA TONOS
+0xB6 0x0386 # GREEK CAPITAL LETTER ALPHA WITH TONOS
+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
+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
diff --git a/extra/io/encodings/8-bit/8859-8.TXT b/extra/io/encodings/8-bit/8859-8.TXT
new file mode 100644
index 0000000000..bc8da4c7fd
--- /dev/null
+++ b/extra/io/encodings/8-bit/8859-8.TXT
@@ -0,0 +1,270 @@
+#
+# Name: ISO/IEC 8859-8:1999 to Unicode
+# Unicode version: 3.0
+# Table version: 1.1
+# Table format: Format A
+# Date: 2000-Jan-03
+# Authors: Ken Whistler <kenw@sybase.com>
+#
+# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved.
+#
+# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
+# No claims are made as to fitness for any particular purpose. No
+# warranties of any kind are expressed or implied. The recipient
+# agrees to determine applicability of information provided. If this
+# file has been provided on optical media by Unicode, Inc., the sole
+# remedy for any claim will be exchange of defective media within 90
+# days of receipt.
+#
+# Unicode, Inc. hereby grants the right to freely use the information
+# supplied in this file in the creation of products supporting the
+# Unicode Standard, and to make copies of this file in any form for
+# internal or external distribution as long as this notice remains
+# attached.
+#
+# General notes:
+#
+# This table contains the data the Unicode Consortium has on how
+# ISO/IEC 8859-8:1999 characters map into Unicode.
+#
+# Format: Three tab-separated columns
+# Column #1 is the ISO/IEC 8859-8 code (in hex as 0xXX)
+# Column #2 is the Unicode (in hex as 0xXXXX)
+# Column #3 the Unicode name (follows a comment sign, '#')
+#
+# The entries are in ISO/IEC 8859-8 order.
+#
+# Version history
+# 1.0 version updates 0.1 version by adding mappings for all
+# control characters.
+# 1.1 version updates to the published 8859-8:1999, correcting
+# the mapping of 0xAF and adding mappings for LRM and RLM.
+#
+# Updated versions of this file may be found in:
+# <ftp://ftp.unicode.org/Public/MAPPINGS/>
+#
+# Any comments or problems, contact <errata@unicode.org>
+# Please note that <errata@unicode.org> is an archival address;
+# notices will be checked, but do not expect an immediate response.
+#
+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 0x0080 # <control>
+0x81 0x0081 # <control>
+0x82 0x0082 # <control>
+0x83 0x0083 # <control>
+0x84 0x0084 # <control>
+0x85 0x0085 # <control>
+0x86 0x0086 # <control>
+0x87 0x0087 # <control>
+0x88 0x0088 # <control>
+0x89 0x0089 # <control>
+0x8A 0x008A # <control>
+0x8B 0x008B # <control>
+0x8C 0x008C # <control>
+0x8D 0x008D # <control>
+0x8E 0x008E # <control>
+0x8F 0x008F # <control>
+0x90 0x0090 # <control>
+0x91 0x0091 # <control>
+0x92 0x0092 # <control>
+0x93 0x0093 # <control>
+0x94 0x0094 # <control>
+0x95 0x0095 # <control>
+0x96 0x0096 # <control>
+0x97 0x0097 # <control>
+0x98 0x0098 # <control>
+0x99 0x0099 # <control>
+0x9A 0x009A # <control>
+0x9B 0x009B # <control>
+0x9C 0x009C # <control>
+0x9D 0x009D # <control>
+0x9E 0x009E # <control>
+0x9F 0x009F # <control>
+0xA0 0x00A0 # NO-BREAK SPACE
+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 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
+0xDF 0x2017 # DOUBLE LOW LINE
+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
+0xFD 0x200E # LEFT-TO-RIGHT MARK
+0xFE 0x200F # RIGHT-TO-LEFT MARK
+
diff --git a/extra/io/encodings/8-bit/8859-9.TXT b/extra/io/encodings/8-bit/8859-9.TXT
new file mode 100644
index 0000000000..22901f1077
--- /dev/null
+++ b/extra/io/encodings/8-bit/8859-9.TXT
@@ -0,0 +1,307 @@
+#
+# Name: ISO/IEC 8859-9:1999 to Unicode
+# Unicode version: 3.0
+# Table version: 1.0
+# Table format: Format A
+# Date: 1999 July 27
+# Authors: Ken Whistler <kenw@sybase.com>
+#
+# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved.
+#
+# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
+# No claims are made as to fitness for any particular purpose. No
+# warranties of any kind are expressed or implied. The recipient
+# agrees to determine applicability of information provided. If this
+# file has been provided on magnetic media by Unicode, Inc., the sole
+# remedy for any claim will be exchange of defective media within 90
+# days of receipt.
+#
+# Unicode, Inc. hereby grants the right to freely use the information
+# supplied in this file in the creation of products supporting the
+# Unicode Standard, and to make copies of this file in any form for
+# internal or external distribution as long as this notice remains
+# attached.
+#
+# General notes:
+#
+# This table contains the data the Unicode Consortium has on how
+# ISO/IEC 8859-9:1999 characters map into Unicode.
+#
+# Format: Three tab-separated columns
+# Column #1 is the ISO/IEC 8859-9 code (in hex as 0xXX)
+# Column #2 is the Unicode (in hex as 0xXXXX)
+# Column #3 the Unicode name (follows a comment sign, '#')
+#
+# The entries are in ISO/IEC 8859-9 order.
+#
+# ISO/IEC 8859-9 is also equivalent to ISO-IR-148.
+#
+# Version history
+# 1.0 version updates 0.1 version by adding mappings for all
+# control characters.
+#
+# Updated versions of this file may be found in:
+# <ftp://ftp.unicode.org/Public/MAPPINGS/>
+#
+# Any comments or problems, contact <errata@unicode.org>
+# Please note that <errata@unicode.org> is an archival address;
+# notices will be checked, but do not expect an immediate response.
+#
+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 0x0080 # <control>
+0x81 0x0081 # <control>
+0x82 0x0082 # <control>
+0x83 0x0083 # <control>
+0x84 0x0084 # <control>
+0x85 0x0085 # <control>
+0x86 0x0086 # <control>
+0x87 0x0087 # <control>
+0x88 0x0088 # <control>
+0x89 0x0089 # <control>
+0x8A 0x008A # <control>
+0x8B 0x008B # <control>
+0x8C 0x008C # <control>
+0x8D 0x008D # <control>
+0x8E 0x008E # <control>
+0x8F 0x008F # <control>
+0x90 0x0090 # <control>
+0x91 0x0091 # <control>
+0x92 0x0092 # <control>
+0x93 0x0093 # <control>
+0x94 0x0094 # <control>
+0x95 0x0095 # <control>
+0x96 0x0096 # <control>
+0x97 0x0097 # <control>
+0x98 0x0098 # <control>
+0x99 0x0099 # <control>
+0x9A 0x009A # <control>
+0x9B 0x009B # <control>
+0x9C 0x009C # <control>
+0x9D 0x009D # <control>
+0x9E 0x009E # <control>
+0x9F 0x009F # <control>
+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
+
+
diff --git a/extra/io/encodings/8-bit/CP037.TXT b/extra/io/encodings/8-bit/CP037.TXT
new file mode 100644
index 0000000000..43186f7bf9
--- /dev/null
+++ b/extra/io/encodings/8-bit/CP037.TXT
@@ -0,0 +1,273 @@
+#
+# Name: cp037_IBMUSCanada to Unicode table
+# Unicode version: 2.0
+# Table version: 2.00
+# Table format: Format A
+# Date: 04/24/96
+# Contact: Shawn.Steele@microsoft.com
+#
+# General notes: none
+#
+# Format: Three tab-separated columns
+# Column #1 is the cp037_IBMUSCanada 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 cp037_IBMUSCanada order
+#
+0x00 0x0000 #NULL
+0x01 0x0001 #START OF HEADING
+0x02 0x0002 #START OF TEXT
+0x03 0x0003 #END OF TEXT
+0x04 0x009C #CONTROL
+0x05 0x0009 #HORIZONTAL TABULATION
+0x06 0x0086 #CONTROL
+0x07 0x007F #DELETE
+0x08 0x0097 #CONTROL
+0x09 0x008D #CONTROL
+0x0A 0x008E #CONTROL
+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 0x009D #CONTROL
+0x15 0x0085 #CONTROL
+0x16 0x0008 #BACKSPACE
+0x17 0x0087 #CONTROL
+0x18 0x0018 #CANCEL
+0x19 0x0019 #END OF MEDIUM
+0x1A 0x0092 #CONTROL
+0x1B 0x008F #CONTROL
+0x1C 0x001C #FILE SEPARATOR
+0x1D 0x001D #GROUP SEPARATOR
+0x1E 0x001E #RECORD SEPARATOR
+0x1F 0x001F #UNIT SEPARATOR
+0x20 0x0080 #CONTROL
+0x21 0x0081 #CONTROL
+0x22 0x0082 #CONTROL
+0x23 0x0083 #CONTROL
+0x24 0x0084 #CONTROL
+0x25 0x000A #LINE FEED
+0x26 0x0017 #END OF TRANSMISSION BLOCK
+0x27 0x001B #ESCAPE
+0x28 0x0088 #CONTROL
+0x29 0x0089 #CONTROL
+0x2A 0x008A #CONTROL
+0x2B 0x008B #CONTROL
+0x2C 0x008C #CONTROL
+0x2D 0x0005 #ENQUIRY
+0x2E 0x0006 #ACKNOWLEDGE
+0x2F 0x0007 #BELL
+0x30 0x0090 #CONTROL
+0x31 0x0091 #CONTROL
+0x32 0x0016 #SYNCHRONOUS IDLE
+0x33 0x0093 #CONTROL
+0x34 0x0094 #CONTROL
+0x35 0x0095 #CONTROL
+0x36 0x0096 #CONTROL
+0x37 0x0004 #END OF TRANSMISSION
+0x38 0x0098 #CONTROL
+0x39 0x0099 #CONTROL
+0x3A 0x009A #CONTROL
+0x3B 0x009B #CONTROL
+0x3C 0x0014 #DEVICE CONTROL FOUR
+0x3D 0x0015 #NEGATIVE ACKNOWLEDGE
+0x3E 0x009E #CONTROL
+0x3F 0x001A #SUBSTITUTE
+0x40 0x0020 #SPACE
+0x41 0x00A0 #NO-BREAK SPACE
+0x42 0x00E2 #LATIN SMALL LETTER A WITH CIRCUMFLEX
+0x43 0x00E4 #LATIN SMALL LETTER A WITH DIAERESIS
+0x44 0x00E0 #LATIN SMALL LETTER A WITH GRAVE
+0x45 0x00E1 #LATIN SMALL LETTER A WITH ACUTE
+0x46 0x00E3 #LATIN SMALL LETTER A WITH TILDE
+0x47 0x00E5 #LATIN SMALL LETTER A WITH RING ABOVE
+0x48 0x00E7 #LATIN SMALL LETTER C WITH CEDILLA
+0x49 0x00F1 #LATIN SMALL LETTER N WITH TILDE
+0x4A 0x00A2 #CENT SIGN
+0x4B 0x002E #FULL STOP
+0x4C 0x003C #LESS-THAN SIGN
+0x4D 0x0028 #LEFT PARENTHESIS
+0x4E 0x002B #PLUS SIGN
+0x4F 0x007C #VERTICAL LINE
+0x50 0x0026 #AMPERSAND
+0x51 0x00E9 #LATIN SMALL LETTER E WITH ACUTE
+0x52 0x00EA #LATIN SMALL LETTER E WITH CIRCUMFLEX
+0x53 0x00EB #LATIN SMALL LETTER E WITH DIAERESIS
+0x54 0x00E8 #LATIN SMALL LETTER E WITH GRAVE
+0x55 0x00ED #LATIN SMALL LETTER I WITH ACUTE
+0x56 0x00EE #LATIN SMALL LETTER I WITH CIRCUMFLEX
+0x57 0x00EF #LATIN SMALL LETTER I WITH DIAERESIS
+0x58 0x00EC #LATIN SMALL LETTER I WITH GRAVE
+0x59 0x00DF #LATIN SMALL LETTER SHARP S (GERMAN)
+0x5A 0x0021 #EXCLAMATION MARK
+0x5B 0x0024 #DOLLAR SIGN
+0x5C 0x002A #ASTERISK
+0x5D 0x0029 #RIGHT PARENTHESIS
+0x5E 0x003B #SEMICOLON
+0x5F 0x00AC #NOT SIGN
+0x60 0x002D #HYPHEN-MINUS
+0x61 0x002F #SOLIDUS
+0x62 0x00C2 #LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+0x63 0x00C4 #LATIN CAPITAL LETTER A WITH DIAERESIS
+0x64 0x00C0 #LATIN CAPITAL LETTER A WITH GRAVE
+0x65 0x00C1 #LATIN CAPITAL LETTER A WITH ACUTE
+0x66 0x00C3 #LATIN CAPITAL LETTER A WITH TILDE
+0x67 0x00C5 #LATIN CAPITAL LETTER A WITH RING ABOVE
+0x68 0x00C7 #LATIN CAPITAL LETTER C WITH CEDILLA
+0x69 0x00D1 #LATIN CAPITAL LETTER N WITH TILDE
+0x6A 0x00A6 #BROKEN BAR
+0x6B 0x002C #COMMA
+0x6C 0x0025 #PERCENT SIGN
+0x6D 0x005F #LOW LINE
+0x6E 0x003E #GREATER-THAN SIGN
+0x6F 0x003F #QUESTION MARK
+0x70 0x00F8 #LATIN SMALL LETTER O WITH STROKE
+0x71 0x00C9 #LATIN CAPITAL LETTER E WITH ACUTE
+0x72 0x00CA #LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+0x73 0x00CB #LATIN CAPITAL LETTER E WITH DIAERESIS
+0x74 0x00C8 #LATIN CAPITAL LETTER E WITH GRAVE
+0x75 0x00CD #LATIN CAPITAL LETTER I WITH ACUTE
+0x76 0x00CE #LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+0x77 0x00CF #LATIN CAPITAL LETTER I WITH DIAERESIS
+0x78 0x00CC #LATIN CAPITAL LETTER I WITH GRAVE
+0x79 0x0060 #GRAVE ACCENT
+0x7A 0x003A #COLON
+0x7B 0x0023 #NUMBER SIGN
+0x7C 0x0040 #COMMERCIAL AT
+0x7D 0x0027 #APOSTROPHE
+0x7E 0x003D #EQUALS SIGN
+0x7F 0x0022 #QUOTATION MARK
+0x80 0x00D8 #LATIN CAPITAL LETTER O WITH STROKE
+0x81 0x0061 #LATIN SMALL LETTER A
+0x82 0x0062 #LATIN SMALL LETTER B
+0x83 0x0063 #LATIN SMALL LETTER C
+0x84 0x0064 #LATIN SMALL LETTER D
+0x85 0x0065 #LATIN SMALL LETTER E
+0x86 0x0066 #LATIN SMALL LETTER F
+0x87 0x0067 #LATIN SMALL LETTER G
+0x88 0x0068 #LATIN SMALL LETTER H
+0x89 0x0069 #LATIN SMALL LETTER I
+0x8A 0x00AB #LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+0x8B 0x00BB #RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+0x8C 0x00F0 #LATIN SMALL LETTER ETH (ICELANDIC)
+0x8D 0x00FD #LATIN SMALL LETTER Y WITH ACUTE
+0x8E 0x00FE #LATIN SMALL LETTER THORN (ICELANDIC)
+0x8F 0x00B1 #PLUS-MINUS SIGN
+0x90 0x00B0 #DEGREE SIGN
+0x91 0x006A #LATIN SMALL LETTER J
+0x92 0x006B #LATIN SMALL LETTER K
+0x93 0x006C #LATIN SMALL LETTER L
+0x94 0x006D #LATIN SMALL LETTER M
+0x95 0x006E #LATIN SMALL LETTER N
+0x96 0x006F #LATIN SMALL LETTER O
+0x97 0x0070 #LATIN SMALL LETTER P
+0x98 0x0071 #LATIN SMALL LETTER Q
+0x99 0x0072 #LATIN SMALL LETTER R
+0x9A 0x00AA #FEMININE ORDINAL INDICATOR
+0x9B 0x00BA #MASCULINE ORDINAL INDICATOR
+0x9C 0x00E6 #LATIN SMALL LIGATURE AE
+0x9D 0x00B8 #CEDILLA
+0x9E 0x00C6 #LATIN CAPITAL LIGATURE AE
+0x9F 0x00A4 #CURRENCY SIGN
+0xA0 0x00B5 #MICRO SIGN
+0xA1 0x007E #TILDE
+0xA2 0x0073 #LATIN SMALL LETTER S
+0xA3 0x0074 #LATIN SMALL LETTER T
+0xA4 0x0075 #LATIN SMALL LETTER U
+0xA5 0x0076 #LATIN SMALL LETTER V
+0xA6 0x0077 #LATIN SMALL LETTER W
+0xA7 0x0078 #LATIN SMALL LETTER X
+0xA8 0x0079 #LATIN SMALL LETTER Y
+0xA9 0x007A #LATIN SMALL LETTER Z
+0xAA 0x00A1 #INVERTED EXCLAMATION MARK
+0xAB 0x00BF #INVERTED QUESTION MARK
+0xAC 0x00D0 #LATIN CAPITAL LETTER ETH (ICELANDIC)
+0xAD 0x00DD #LATIN CAPITAL LETTER Y WITH ACUTE
+0xAE 0x00DE #LATIN CAPITAL LETTER THORN (ICELANDIC)
+0xAF 0x00AE #REGISTERED SIGN
+0xB0 0x005E #CIRCUMFLEX ACCENT
+0xB1 0x00A3 #POUND SIGN
+0xB2 0x00A5 #YEN SIGN
+0xB3 0x00B7 #MIDDLE DOT
+0xB4 0x00A9 #COPYRIGHT SIGN
+0xB5 0x00A7 #SECTION SIGN
+0xB6 0x00B6 #PILCROW SIGN
+0xB7 0x00BC #VULGAR FRACTION ONE QUARTER
+0xB8 0x00BD #VULGAR FRACTION ONE HALF
+0xB9 0x00BE #VULGAR FRACTION THREE QUARTERS
+0xBA 0x005B #LEFT SQUARE BRACKET
+0xBB 0x005D #RIGHT SQUARE BRACKET
+0xBC 0x00AF #MACRON
+0xBD 0x00A8 #DIAERESIS
+0xBE 0x00B4 #ACUTE ACCENT
+0xBF 0x00D7 #MULTIPLICATION SIGN
+0xC0 0x007B #LEFT CURLY BRACKET
+0xC1 0x0041 #LATIN CAPITAL LETTER A
+0xC2 0x0042 #LATIN CAPITAL LETTER B
+0xC3 0x0043 #LATIN CAPITAL LETTER C
+0xC4 0x0044 #LATIN CAPITAL LETTER D
+0xC5 0x0045 #LATIN CAPITAL LETTER E
+0xC6 0x0046 #LATIN CAPITAL LETTER F
+0xC7 0x0047 #LATIN CAPITAL LETTER G
+0xC8 0x0048 #LATIN CAPITAL LETTER H
+0xC9 0x0049 #LATIN CAPITAL LETTER I
+0xCA 0x00AD #SOFT HYPHEN
+0xCB 0x00F4 #LATIN SMALL LETTER O WITH CIRCUMFLEX
+0xCC 0x00F6 #LATIN SMALL LETTER O WITH DIAERESIS
+0xCD 0x00F2 #LATIN SMALL LETTER O WITH GRAVE
+0xCE 0x00F3 #LATIN SMALL LETTER O WITH ACUTE
+0xCF 0x00F5 #LATIN SMALL LETTER O WITH TILDE
+0xD0 0x007D #RIGHT CURLY BRACKET
+0xD1 0x004A #LATIN CAPITAL LETTER J
+0xD2 0x004B #LATIN CAPITAL LETTER K
+0xD3 0x004C #LATIN CAPITAL LETTER L
+0xD4 0x004D #LATIN CAPITAL LETTER M
+0xD5 0x004E #LATIN CAPITAL LETTER N
+0xD6 0x004F #LATIN CAPITAL LETTER O
+0xD7 0x0050 #LATIN CAPITAL LETTER P
+0xD8 0x0051 #LATIN CAPITAL LETTER Q
+0xD9 0x0052 #LATIN CAPITAL LETTER R
+0xDA 0x00B9 #SUPERSCRIPT ONE
+0xDB 0x00FB #LATIN SMALL LETTER U WITH CIRCUMFLEX
+0xDC 0x00FC #LATIN SMALL LETTER U WITH DIAERESIS
+0xDD 0x00F9 #LATIN SMALL LETTER U WITH GRAVE
+0xDE 0x00FA #LATIN SMALL LETTER U WITH ACUTE
+0xDF 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS
+0xE0 0x005C #REVERSE SOLIDUS
+0xE1 0x00F7 #DIVISION SIGN
+0xE2 0x0053 #LATIN CAPITAL LETTER S
+0xE3 0x0054 #LATIN CAPITAL LETTER T
+0xE4 0x0055 #LATIN CAPITAL LETTER U
+0xE5 0x0056 #LATIN CAPITAL LETTER V
+0xE6 0x0057 #LATIN CAPITAL LETTER W
+0xE7 0x0058 #LATIN CAPITAL LETTER X
+0xE8 0x0059 #LATIN CAPITAL LETTER Y
+0xE9 0x005A #LATIN CAPITAL LETTER Z
+0xEA 0x00B2 #SUPERSCRIPT TWO
+0xEB 0x00D4 #LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+0xEC 0x00D6 #LATIN CAPITAL LETTER O WITH DIAERESIS
+0xED 0x00D2 #LATIN CAPITAL LETTER O WITH GRAVE
+0xEE 0x00D3 #LATIN CAPITAL LETTER O WITH ACUTE
+0xEF 0x00D5 #LATIN CAPITAL LETTER O WITH TILDE
+0xF0 0x0030 #DIGIT ZERO
+0xF1 0x0031 #DIGIT ONE
+0xF2 0x0032 #DIGIT TWO
+0xF3 0x0033 #DIGIT THREE
+0xF4 0x0034 #DIGIT FOUR
+0xF5 0x0035 #DIGIT FIVE
+0xF6 0x0036 #DIGIT SIX
+0xF7 0x0037 #DIGIT SEVEN
+0xF8 0x0038 #DIGIT EIGHT
+0xF9 0x0039 #DIGIT NINE
+0xFA 0x00B3 #SUPERSCRIPT THREE
+0xFB 0x00DB #LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+0xFC 0x00DC #LATIN CAPITAL LETTER U WITH DIAERESIS
+0xFD 0x00D9 #LATIN CAPITAL LETTER U WITH GRAVE
+0xFE 0x00DA #LATIN CAPITAL LETTER U WITH ACUTE
+0xFF 0x009F #CONTROL
diff --git a/extra/io/encodings/8-bit/CP1252.TXT b/extra/io/encodings/8-bit/CP1252.TXT
new file mode 100644
index 0000000000..8ff4b204b7
--- /dev/null
+++ b/extra/io/encodings/8-bit/CP1252.TXT
@@ -0,0 +1,274 @@
+#
+# Name: cp1252 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 cp1252 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 cp1252 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 0x017D #LATIN CAPITAL LETTER Z WITH CARON
+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 0x017E #LATIN SMALL LETTER Z WITH CARON
+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 0x00D0 #LATIN CAPITAL LETTER ETH
+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 0x00DD #LATIN CAPITAL LETTER Y WITH ACUTE
+0xDE 0x00DE #LATIN CAPITAL LETTER THORN
+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 0x00F0 #LATIN SMALL LETTER ETH
+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 0x00FD #LATIN SMALL LETTER Y WITH ACUTE
+0xFE 0x00FE #LATIN SMALL LETTER THORN
+0xFF 0x00FF #LATIN SMALL LETTER Y WITH DIAERESIS
diff --git a/extra/io/encodings/8-bit/KOI8-R.TXT b/extra/io/encodings/8-bit/KOI8-R.TXT
new file mode 100644
index 0000000000..510561005c
--- /dev/null
+++ b/extra/io/encodings/8-bit/KOI8-R.TXT
@@ -0,0 +1,302 @@
+#
+# Name: KOI8-R (RFC1489) to Unicode
+# Unicode version: 3.0
+# Table version: 1.0
+# Table format: Format A
+# Date: 18 August 1999
+# Authors: Helmut Richter <richter@lrz.de>
+#
+# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved.
+#
+# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
+# No claims are made as to fitness for any particular purpose. No
+# warranties of any kind are expressed or implied. The recipient
+# agrees to determine applicability of information provided. If this
+# file has been provided on optical media by Unicode, Inc., the sole
+# remedy for any claim will be exchange of defective media within 90
+# days of receipt.
+#
+# Unicode, Inc. hereby grants the right to freely use the information
+# supplied in this file in the creation of products supporting the
+# Unicode Standard, and to make copies of this file in any form for
+# internal or external distribution as long as this notice remains
+# attached.
+#
+# General notes:
+#
+# This table contains the data the Unicode Consortium has on how
+# KOI8-R characters map into Unicode. The underlying document is the
+# mapping described in RFC 1489. No statements are made as to whether
+# this mapping is the same as the mapping defined as "Code Page 878"
+# with some vendors.
+#
+# Format: Three tab-separated columns
+# Column #1 is the KOI8-R code (in hex as 0xXX)
+# Column #2 is the Unicode (in hex as 0xXXXX)
+# Column #3 the Unicode name (follows a comment sign, '#')
+#
+# The entries are in KOI8-R order.
+#
+# Version history
+# 1.0 version: created.
+#
+# Any comments or problems, contact <errata@unicode.org>
+# Please note that <errata@unicode.org> is an archival address;
+# notices will be checked, but do not expect an immediate response.
+#
+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 0x2500 # BOX DRAWINGS LIGHT HORIZONTAL
+0x81 0x2502 # BOX DRAWINGS LIGHT VERTICAL
+0x82 0x250C # BOX DRAWINGS LIGHT DOWN AND RIGHT
+0x83 0x2510 # BOX DRAWINGS LIGHT DOWN AND LEFT
+0x84 0x2514 # BOX DRAWINGS LIGHT UP AND RIGHT
+0x85 0x2518 # BOX DRAWINGS LIGHT UP AND LEFT
+0x86 0x251C # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+0x87 0x2524 # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+0x88 0x252C # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+0x89 0x2534 # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+0x8A 0x253C # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+0x8B 0x2580 # UPPER HALF BLOCK
+0x8C 0x2584 # LOWER HALF BLOCK
+0x8D 0x2588 # FULL BLOCK
+0x8E 0x258C # LEFT HALF BLOCK
+0x8F 0x2590 # RIGHT HALF BLOCK
+0x90 0x2591 # LIGHT SHADE
+0x91 0x2592 # MEDIUM SHADE
+0x92 0x2593 # DARK SHADE
+0x93 0x2320 # TOP HALF INTEGRAL
+0x94 0x25A0 # BLACK SQUARE
+0x95 0x2219 # BULLET OPERATOR
+0x96 0x221A # SQUARE ROOT
+0x97 0x2248 # ALMOST EQUAL TO
+0x98 0x2264 # LESS-THAN OR EQUAL TO
+0x99 0x2265 # GREATER-THAN OR EQUAL TO
+0x9A 0x00A0 # NO-BREAK SPACE
+0x9B 0x2321 # BOTTOM HALF INTEGRAL
+0x9C 0x00B0 # DEGREE SIGN
+0x9D 0x00B2 # SUPERSCRIPT TWO
+0x9E 0x00B7 # MIDDLE DOT
+0x9F 0x00F7 # DIVISION SIGN
+0xA0 0x2550 # BOX DRAWINGS DOUBLE HORIZONTAL
+0xA1 0x2551 # BOX DRAWINGS DOUBLE VERTICAL
+0xA2 0x2552 # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+0xA3 0x0451 # CYRILLIC SMALL LETTER IO
+0xA4 0x2553 # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+0xA5 0x2554 # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+0xA6 0x2555 # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+0xA7 0x2556 # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+0xA8 0x2557 # BOX DRAWINGS DOUBLE DOWN AND LEFT
+0xA9 0x2558 # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+0xAA 0x2559 # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+0xAB 0x255A # BOX DRAWINGS DOUBLE UP AND RIGHT
+0xAC 0x255B # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+0xAD 0x255C # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+0xAE 0x255D # BOX DRAWINGS DOUBLE UP AND LEFT
+0xAF 0x255E # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+0xB0 0x255F # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+0xB1 0x2560 # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+0xB2 0x2561 # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+0xB3 0x0401 # CYRILLIC CAPITAL LETTER IO
+0xB4 0x2562 # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+0xB5 0x2563 # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+0xB6 0x2564 # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+0xB7 0x2565 # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+0xB8 0x2566 # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+0xB9 0x2567 # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+0xBA 0x2568 # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+0xBB 0x2569 # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+0xBC 0x256A # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+0xBD 0x256B # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+0xBE 0x256C # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+0xBF 0x00A9 # COPYRIGHT SIGN
+0xC0 0x044E # CYRILLIC SMALL LETTER YU
+0xC1 0x0430 # CYRILLIC SMALL LETTER A
+0xC2 0x0431 # CYRILLIC SMALL LETTER BE
+0xC3 0x0446 # CYRILLIC SMALL LETTER TSE
+0xC4 0x0434 # CYRILLIC SMALL LETTER DE
+0xC5 0x0435 # CYRILLIC SMALL LETTER IE
+0xC6 0x0444 # CYRILLIC SMALL LETTER EF
+0xC7 0x0433 # CYRILLIC SMALL LETTER GHE
+0xC8 0x0445 # CYRILLIC SMALL LETTER HA
+0xC9 0x0438 # CYRILLIC SMALL LETTER I
+0xCA 0x0439 # CYRILLIC SMALL LETTER SHORT I
+0xCB 0x043A # CYRILLIC SMALL LETTER KA
+0xCC 0x043B # CYRILLIC SMALL LETTER EL
+0xCD 0x043C # CYRILLIC SMALL LETTER EM
+0xCE 0x043D # CYRILLIC SMALL LETTER EN
+0xCF 0x043E # CYRILLIC SMALL LETTER O
+0xD0 0x043F # CYRILLIC SMALL LETTER PE
+0xD1 0x044F # CYRILLIC SMALL LETTER YA
+0xD2 0x0440 # CYRILLIC SMALL LETTER ER
+0xD3 0x0441 # CYRILLIC SMALL LETTER ES
+0xD4 0x0442 # CYRILLIC SMALL LETTER TE
+0xD5 0x0443 # CYRILLIC SMALL LETTER U
+0xD6 0x0436 # CYRILLIC SMALL LETTER ZHE
+0xD7 0x0432 # CYRILLIC SMALL LETTER VE
+0xD8 0x044C # CYRILLIC SMALL LETTER SOFT SIGN
+0xD9 0x044B # CYRILLIC SMALL LETTER YERU
+0xDA 0x0437 # CYRILLIC SMALL LETTER ZE
+0xDB 0x0448 # CYRILLIC SMALL LETTER SHA
+0xDC 0x044D # CYRILLIC SMALL LETTER E
+0xDD 0x0449 # CYRILLIC SMALL LETTER SHCHA
+0xDE 0x0447 # CYRILLIC SMALL LETTER CHE
+0xDF 0x044A # CYRILLIC SMALL LETTER HARD SIGN
+0xE0 0x042E # CYRILLIC CAPITAL LETTER YU
+0xE1 0x0410 # CYRILLIC CAPITAL LETTER A
+0xE2 0x0411 # CYRILLIC CAPITAL LETTER BE
+0xE3 0x0426 # CYRILLIC CAPITAL LETTER TSE
+0xE4 0x0414 # CYRILLIC CAPITAL LETTER DE
+0xE5 0x0415 # CYRILLIC CAPITAL LETTER IE
+0xE6 0x0424 # CYRILLIC CAPITAL LETTER EF
+0xE7 0x0413 # CYRILLIC CAPITAL LETTER GHE
+0xE8 0x0425 # CYRILLIC CAPITAL LETTER HA
+0xE9 0x0418 # CYRILLIC CAPITAL LETTER I
+0xEA 0x0419 # CYRILLIC CAPITAL LETTER SHORT I
+0xEB 0x041A # CYRILLIC CAPITAL LETTER KA
+0xEC 0x041B # CYRILLIC CAPITAL LETTER EL
+0xED 0x041C # CYRILLIC CAPITAL LETTER EM
+0xEE 0x041D # CYRILLIC CAPITAL LETTER EN
+0xEF 0x041E # CYRILLIC CAPITAL LETTER O
+0xF0 0x041F # CYRILLIC CAPITAL LETTER PE
+0xF1 0x042F # CYRILLIC CAPITAL LETTER YA
+0xF2 0x0420 # CYRILLIC CAPITAL LETTER ER
+0xF3 0x0421 # CYRILLIC CAPITAL LETTER ES
+0xF4 0x0422 # CYRILLIC CAPITAL LETTER TE
+0xF5 0x0423 # CYRILLIC CAPITAL LETTER U
+0xF6 0x0416 # CYRILLIC CAPITAL LETTER ZHE
+0xF7 0x0412 # CYRILLIC CAPITAL LETTER VE
+0xF8 0x042C # CYRILLIC CAPITAL LETTER SOFT SIGN
+0xF9 0x042B # CYRILLIC CAPITAL LETTER YERU
+0xFA 0x0417 # CYRILLIC CAPITAL LETTER ZE
+0xFB 0x0428 # CYRILLIC CAPITAL LETTER SHA
+0xFC 0x042D # CYRILLIC CAPITAL LETTER E
+0xFD 0x0429 # CYRILLIC CAPITAL LETTER SHCHA
+0xFE 0x0427 # CYRILLIC CAPITAL LETTER CHE
+0xFF 0x042A # CYRILLIC CAPITAL LETTER HARD SIGN
diff --git a/extra/io/encodings/8-bit/ROMAN.TXT b/extra/io/encodings/8-bit/ROMAN.TXT
new file mode 100644
index 0000000000..5b3b8b4005
--- /dev/null
+++ b/extra/io/encodings/8-bit/ROMAN.TXT
@@ -0,0 +1,370 @@
+#=======================================================================
+# File name: ROMAN.TXT
+#
+# Contents: Map (external version) from Mac OS Roman
+# character set to Unicode 2.1 and later.
+#
+# Copyright: (c) 1994-2002, 2005 by Apple Computer, Inc., all rights
+# reserved.
+#
+# Contact: charsets@apple.com
+#
+# Changes:
+#
+# c02 2005-Apr-05 Update header comments. Matches internal xml
+# <c1.1> and Text Encoding Converter 2.0.
+# b4,c1 2002-Dec-19 Update URLs, notes. Matches internal
+# utom<b5>.
+# b03 1999-Sep-22 Update contact e-mail address. Matches
+# internal utom<b4>, ufrm<b3>, and Text
+# Encoding Converter version 1.5.
+# b02 1998-Aug-18 Encoding changed for Mac OS 8.5; change
+# mapping of 0xDB from CURRENCY SIGN to
+# EURO SIGN. Matches internal utom<b3>,
+# ufrm<b3>.
+# n08 1998-Feb-05 Minor update to header comments
+# n06 1997-Dec-14 Add warning about future changes to 0xDB
+# from CURRENCY SIGN to EURO SIGN. Clarify
+# some header information
+# n04 1997-Dec-01 Update to match internal utom<n3>, ufrm<n22>:
+# Change standard mapping for 0xBD from U+2126
+# to its canonical decomposition, U+03A9.
+# n03 1995-Apr-15 First version (after fixing some typos).
+# Matches internal ufrm<n9>.
+#
+# Standard header:
+# ----------------
+#
+# Apple, the Apple logo, and Macintosh are trademarks of Apple
+# Computer, Inc., registered in the United States and other countries.
+# Unicode is a trademark of Unicode Inc. For the sake of brevity,
+# throughout this document, "Macintosh" can be used to refer to
+# Macintosh computers and "Unicode" can be used to refer to the
+# Unicode standard.
+#
+# Apple Computer, Inc. ("Apple") makes no warranty or representation,
+# either express or implied, with respect to this document and the
+# included data, its quality, accuracy, or fitness for a particular
+# purpose. In no event will Apple be liable for direct, indirect,
+# special, incidental, or consequential damages resulting from any
+# defect or inaccuracy in this document or the included data.
+#
+# These mapping tables and character lists are subject to change.
+# The latest tables should be available from the following:
+#
+# <http://www.unicode.org/Public/MAPPINGS/VENDORS/APPLE/>
+#
+# For general information about Mac OS encodings and these mapping
+# tables, see the file "README.TXT".
+#
+# Format:
+# -------
+#
+# Three tab-separated columns;
+# '#' begins a comment which continues to the end of the line.
+# Column #1 is the Mac OS Roman code (in hex as 0xNN)
+# Column #2 is the corresponding Unicode (in hex as 0xNNNN)
+# Column #3 is a comment containing the Unicode name
+#
+# The entries are in Mac OS Roman code order.
+#
+# One of these mappings requires the use of a corporate character.
+# See the file "CORPCHAR.TXT" and notes below.
+#
+# Control character mappings are not shown in this table, following
+# the conventions of the standard UTC mapping tables. However, the
+# Mac OS Roman character set uses the standard control characters at
+# 0x00-0x1F and 0x7F.
+#
+# Notes on Mac OS Roman:
+# ----------------------
+#
+# This is a legacy Mac OS encoding; in the Mac OS X Carbon and Cocoa
+# environments, it is only supported directly in programming
+# interfaces for QuickDraw Text, the Script Manager, and related
+# Text Utilities. For other purposes it is supported via transcoding
+# to and from Unicode.
+#
+# This character set is used for at least the following Mac OS
+# localizations: U.S., British, Canadian French, French, Swiss
+# French, German, Swiss German, Italian, Swiss Italian, Dutch,
+# Swedish, Norwegian, Danish, Finnish, Spanish, Catalan,
+# Portuguese, Brazilian, and the default International system.
+#
+# Variants of Mac OS Roman are used for Croatian, Icelandic,
+# Turkish, Romanian, and other encodings. Separate mapping tables
+# are available for these encodings.
+#
+# Before Mac OS 8.5, code point 0xDB was CURRENCY SIGN, and was
+# mapped to U+00A4. In Mac OS 8.5 and later versions, code point
+# 0xDB is changed to EURO SIGN and maps to U+20AC; the standard
+# Apple fonts are updated for Mac OS 8.5 to reflect this. There is
+# a "currency sign" variant of the Mac OS Roman encoding that still
+# maps 0xDB to U+00A4; this can be used for older fonts.
+#
+# Before Mac OS 8.5, the ROM bitmap versions of the fonts Chicago,
+# New York, Geneva, and Monaco did not implement the full Mac OS
+# Roman character set; they only supported character codes up to
+# 0xD8. The TrueType versions of these fonts have always implemented
+# the full character set, as with the bitmap and TrueType versions
+# of the other standard Roman fonts.
+#
+# In all Mac OS encodings, fonts such as Chicago which are used
+# as "system" fonts (for menus, dialogs, etc.) have four glyphs
+# at code points 0x11-0x14 for transient use by the Menu Manager.
+# These glyphs are not intended as characters for use in normal
+# text, and the associated code points are not generally
+# interpreted as associated with these glyphs; they are usually
+# interpreted (if at all) as the control codes DC1-DC4.
+#
+# Unicode mapping issues and notes:
+# ---------------------------------
+#
+# The following corporate zone Unicode character is used in this
+# mapping:
+#
+# 0xF8FF Apple logo
+#
+# NOTE: The graphic image associated with the Apple logo character
+# is not authorized for use without permission of Apple, and
+# unauthorized use might constitute trademark infringement.
+#
+# Details of mapping changes in each version:
+# -------------------------------------------
+#
+# Changes from version n08 to version b02:
+#
+# - Encoding changed for Mac OS 8.5; change mapping of 0xDB from
+# CURRENCY SIGN (U+00A4) to EURO SIGN (U+20AC).
+#
+# Changes from version n03 to version n04:
+#
+# - Change mapping of 0xBD from U+2126 to its canonical
+# decomposition, U+03A9.
+#
+##################
+
+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
+#
+0x80 0x00C4 # LATIN CAPITAL LETTER A WITH DIAERESIS
+0x81 0x00C5 # LATIN CAPITAL LETTER A WITH RING ABOVE
+0x82 0x00C7 # LATIN CAPITAL LETTER C WITH CEDILLA
+0x83 0x00C9 # LATIN CAPITAL LETTER E WITH ACUTE
+0x84 0x00D1 # LATIN CAPITAL LETTER N WITH TILDE
+0x85 0x00D6 # LATIN CAPITAL LETTER O WITH DIAERESIS
+0x86 0x00DC # LATIN CAPITAL LETTER U WITH DIAERESIS
+0x87 0x00E1 # LATIN SMALL LETTER A WITH ACUTE
+0x88 0x00E0 # LATIN SMALL LETTER A WITH GRAVE
+0x89 0x00E2 # LATIN SMALL LETTER A WITH CIRCUMFLEX
+0x8A 0x00E4 # LATIN SMALL LETTER A WITH DIAERESIS
+0x8B 0x00E3 # LATIN SMALL LETTER A WITH TILDE
+0x8C 0x00E5 # LATIN SMALL LETTER A WITH RING ABOVE
+0x8D 0x00E7 # LATIN SMALL LETTER C WITH CEDILLA
+0x8E 0x00E9 # LATIN SMALL LETTER E WITH ACUTE
+0x8F 0x00E8 # LATIN SMALL LETTER E WITH GRAVE
+0x90 0x00EA # LATIN SMALL LETTER E WITH CIRCUMFLEX
+0x91 0x00EB # LATIN SMALL LETTER E WITH DIAERESIS
+0x92 0x00ED # LATIN SMALL LETTER I WITH ACUTE
+0x93 0x00EC # LATIN SMALL LETTER I WITH GRAVE
+0x94 0x00EE # LATIN SMALL LETTER I WITH CIRCUMFLEX
+0x95 0x00EF # LATIN SMALL LETTER I WITH DIAERESIS
+0x96 0x00F1 # LATIN SMALL LETTER N WITH TILDE
+0x97 0x00F3 # LATIN SMALL LETTER O WITH ACUTE
+0x98 0x00F2 # LATIN SMALL LETTER O WITH GRAVE
+0x99 0x00F4 # LATIN SMALL LETTER O WITH CIRCUMFLEX
+0x9A 0x00F6 # LATIN SMALL LETTER O WITH DIAERESIS
+0x9B 0x00F5 # LATIN SMALL LETTER O WITH TILDE
+0x9C 0x00FA # LATIN SMALL LETTER U WITH ACUTE
+0x9D 0x00F9 # LATIN SMALL LETTER U WITH GRAVE
+0x9E 0x00FB # LATIN SMALL LETTER U WITH CIRCUMFLEX
+0x9F 0x00FC # LATIN SMALL LETTER U WITH DIAERESIS
+0xA0 0x2020 # DAGGER
+0xA1 0x00B0 # DEGREE SIGN
+0xA2 0x00A2 # CENT SIGN
+0xA3 0x00A3 # POUND SIGN
+0xA4 0x00A7 # SECTION SIGN
+0xA5 0x2022 # BULLET
+0xA6 0x00B6 # PILCROW SIGN
+0xA7 0x00DF # LATIN SMALL LETTER SHARP S
+0xA8 0x00AE # REGISTERED SIGN
+0xA9 0x00A9 # COPYRIGHT SIGN
+0xAA 0x2122 # TRADE MARK SIGN
+0xAB 0x00B4 # ACUTE ACCENT
+0xAC 0x00A8 # DIAERESIS
+0xAD 0x2260 # NOT EQUAL TO
+0xAE 0x00C6 # LATIN CAPITAL LETTER AE
+0xAF 0x00D8 # LATIN CAPITAL LETTER O WITH STROKE
+0xB0 0x221E # INFINITY
+0xB1 0x00B1 # PLUS-MINUS SIGN
+0xB2 0x2264 # LESS-THAN OR EQUAL TO
+0xB3 0x2265 # GREATER-THAN OR EQUAL TO
+0xB4 0x00A5 # YEN SIGN
+0xB5 0x00B5 # MICRO SIGN
+0xB6 0x2202 # PARTIAL DIFFERENTIAL
+0xB7 0x2211 # N-ARY SUMMATION
+0xB8 0x220F # N-ARY PRODUCT
+0xB9 0x03C0 # GREEK SMALL LETTER PI
+0xBA 0x222B # INTEGRAL
+0xBB 0x00AA # FEMININE ORDINAL INDICATOR
+0xBC 0x00BA # MASCULINE ORDINAL INDICATOR
+0xBD 0x03A9 # GREEK CAPITAL LETTER OMEGA
+0xBE 0x00E6 # LATIN SMALL LETTER AE
+0xBF 0x00F8 # LATIN SMALL LETTER O WITH STROKE
+0xC0 0x00BF # INVERTED QUESTION MARK
+0xC1 0x00A1 # INVERTED EXCLAMATION MARK
+0xC2 0x00AC # NOT SIGN
+0xC3 0x221A # SQUARE ROOT
+0xC4 0x0192 # LATIN SMALL LETTER F WITH HOOK
+0xC5 0x2248 # ALMOST EQUAL TO
+0xC6 0x2206 # INCREMENT
+0xC7 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xC8 0x00BB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+0xC9 0x2026 # HORIZONTAL ELLIPSIS
+0xCA 0x00A0 # NO-BREAK SPACE
+0xCB 0x00C0 # LATIN CAPITAL LETTER A WITH GRAVE
+0xCC 0x00C3 # LATIN CAPITAL LETTER A WITH TILDE
+0xCD 0x00D5 # LATIN CAPITAL LETTER O WITH TILDE
+0xCE 0x0152 # LATIN CAPITAL LIGATURE OE
+0xCF 0x0153 # LATIN SMALL LIGATURE OE
+0xD0 0x2013 # EN DASH
+0xD1 0x2014 # EM DASH
+0xD2 0x201C # LEFT DOUBLE QUOTATION MARK
+0xD3 0x201D # RIGHT DOUBLE QUOTATION MARK
+0xD4 0x2018 # LEFT SINGLE QUOTATION MARK
+0xD5 0x2019 # RIGHT SINGLE QUOTATION MARK
+0xD6 0x00F7 # DIVISION SIGN
+0xD7 0x25CA # LOZENGE
+0xD8 0x00FF # LATIN SMALL LETTER Y WITH DIAERESIS
+0xD9 0x0178 # LATIN CAPITAL LETTER Y WITH DIAERESIS
+0xDA 0x2044 # FRACTION SLASH
+0xDB 0x20AC # EURO SIGN
+0xDC 0x2039 # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
+0xDD 0x203A # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
+0xDE 0xFB01 # LATIN SMALL LIGATURE FI
+0xDF 0xFB02 # LATIN SMALL LIGATURE FL
+0xE0 0x2021 # DOUBLE DAGGER
+0xE1 0x00B7 # MIDDLE DOT
+0xE2 0x201A # SINGLE LOW-9 QUOTATION MARK
+0xE3 0x201E # DOUBLE LOW-9 QUOTATION MARK
+0xE4 0x2030 # PER MILLE SIGN
+0xE5 0x00C2 # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+0xE6 0x00CA # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+0xE7 0x00C1 # LATIN CAPITAL LETTER A WITH ACUTE
+0xE8 0x00CB # LATIN CAPITAL LETTER E WITH DIAERESIS
+0xE9 0x00C8 # LATIN CAPITAL LETTER E WITH GRAVE
+0xEA 0x00CD # LATIN CAPITAL LETTER I WITH ACUTE
+0xEB 0x00CE # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+0xEC 0x00CF # LATIN CAPITAL LETTER I WITH DIAERESIS
+0xED 0x00CC # LATIN CAPITAL LETTER I WITH GRAVE
+0xEE 0x00D3 # LATIN CAPITAL LETTER O WITH ACUTE
+0xEF 0x00D4 # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+0xF0 0xF8FF # Apple logo
+0xF1 0x00D2 # LATIN CAPITAL LETTER O WITH GRAVE
+0xF2 0x00DA # LATIN CAPITAL LETTER U WITH ACUTE
+0xF3 0x00DB # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+0xF4 0x00D9 # LATIN CAPITAL LETTER U WITH GRAVE
+0xF5 0x0131 # LATIN SMALL LETTER DOTLESS I
+0xF6 0x02C6 # MODIFIER LETTER CIRCUMFLEX ACCENT
+0xF7 0x02DC # SMALL TILDE
+0xF8 0x00AF # MACRON
+0xF9 0x02D8 # BREVE
+0xFA 0x02D9 # DOT ABOVE
+0xFB 0x02DA # RING ABOVE
+0xFC 0x00B8 # CEDILLA
+0xFD 0x02DD # DOUBLE ACUTE ACCENT
+0xFE 0x02DB # OGONEK
+0xFF 0x02C7 # CARON
diff --git a/extra/io/encodings/latin1/authors.txt b/extra/io/encodings/8-bit/authors.txt
similarity index 100%
rename from extra/io/encodings/latin1/authors.txt
rename to extra/io/encodings/8-bit/authors.txt
diff --git a/extra/io/encodings/8-bit/summary.txt b/extra/io/encodings/8-bit/summary.txt
new file mode 100644
index 0000000000..7fe8064015
--- /dev/null
+++ b/extra/io/encodings/8-bit/summary.txt
@@ -0,0 +1 @@
+Definitions of 8-bit encodings like ISO 8859 and Windows 1252
diff --git a/extra/io/encodings/latin1/tags.txt b/extra/io/encodings/8-bit/tags.txt
similarity index 100%
rename from extra/io/encodings/latin1/tags.txt
rename to extra/io/encodings/8-bit/tags.txt
diff --git a/extra/io/encodings/latin1/latin1-docs.factor b/extra/io/encodings/latin1/latin1-docs.factor
deleted file mode 100644
index 5872b2bcfd..0000000000
--- a/extra/io/encodings/latin1/latin1-docs.factor
+++ /dev/null
@@ -1,5 +0,0 @@
-USING: help.syntax help.markup ;
-IN: io.encodings.latin1
-
-HELP: latin1
-{ $class-description "This class is used for Latin 1 (ISO 8859-1) encoding and decoding" } ;
diff --git a/extra/io/encodings/latin1/latin1-tests.factor b/extra/io/encodings/latin1/latin1-tests.factor
deleted file mode 100644
index a89bfe0e6f..0000000000
--- a/extra/io/encodings/latin1/latin1-tests.factor
+++ /dev/null
@@ -1,9 +0,0 @@
-USING: io.encodings.string io.encodings.latin1 tools.test strings arrays ;
-IN: io.encodings.latin1.tests
-
-[ B{ CHAR: f CHAR: o CHAR: o } ] [ "foo" latin1 encode ] unit-test
-[ { 256 } >string latin1 encode ] must-fail
-[ B{ 255 } ] [ { 255 } latin1 encode ] unit-test
-
-[ "bar" ] [ "bar" latin1 decode ] unit-test
-[ { CHAR: b 233 CHAR: r } ] [ { CHAR: b 233 CHAR: r } latin1 decode >array ] unit-test
diff --git a/extra/io/encodings/latin1/latin1.factor b/extra/io/encodings/latin1/latin1.factor
deleted file mode 100755
index 2b82318885..0000000000
--- a/extra/io/encodings/latin1/latin1.factor
+++ /dev/null
@@ -1,12 +0,0 @@
-! Copyright (C) 2008 Daniel Ehrenberg.
-! See http://factorcode.org/license.txt for BSD license.
-USING: io io.encodings kernel io.encodings.ascii.private ;
-IN: io.encodings.latin1
-
-TUPLE: latin1 ;
-
-M: latin1 encode-char
- 256 encode-if< ;
-
-M: latin1 decode-char
- drop stream-read1 ;
diff --git a/extra/io/encodings/latin1/summary.txt b/extra/io/encodings/latin1/summary.txt
deleted file mode 100644
index d40d628767..0000000000
--- a/extra/io/encodings/latin1/summary.txt
+++ /dev/null
@@ -1 +0,0 @@
-ISO 8859-1 encoding/decoding
diff --git a/extra/io/encodings/strict/authors.txt b/extra/io/encodings/strict/authors.txt
new file mode 100644
index 0000000000..f990dd0ed2
--- /dev/null
+++ b/extra/io/encodings/strict/authors.txt
@@ -0,0 +1 @@
+Daniel Ehrenberg
diff --git a/extra/io/encodings/strict/strict-tests.factor b/extra/io/encodings/strict/strict-tests.factor
new file mode 100644
index 0000000000..aebb58cc30
--- /dev/null
+++ b/extra/io/encodings/strict/strict-tests.factor
@@ -0,0 +1,6 @@
+USING: io.encodings.strict io.encodings.ascii tools.test
+arrays io.encodings.string ;
+IN: io.encodings.strict.test
+
+[ { HEX: fffd } ] [ { 128 } ascii decode >array ] unit-test
+[ { 128 } ascii strict decode ] must-fail
diff --git a/extra/io/encodings/strict/strict.factor b/extra/io/encodings/strict/strict.factor
new file mode 100644
index 0000000000..89c10d89cc
--- /dev/null
+++ b/extra/io/encodings/strict/strict.factor
@@ -0,0 +1,18 @@
+! Copyright (C) 2008 Daniel Ehrenberg
+! See http://factorcode.org/license.txt for BSD license.
+USING: io.encodings kernel accessors inspector ;
+IN: io.encodings.strict
+
+TUPLE: strict code ;
+C: strict strict
+
+TUPLE: decode-error ;
+: decode-error ( -- * ) \ decode-error construct-empty throw ;
+M: decode-error summary
+ drop "Error in decoding input stream" ;
+
+M: strict <decoder>
+ code>> <decoder> [ strict ] change-code ;
+
+M: strict decode-char
+ code>> decode-char dup replacement-char = [ decode-error ] when ;
diff --git a/extra/io/encodings/strict/summary.txt b/extra/io/encodings/strict/summary.txt
new file mode 100644
index 0000000000..9fd0fe3bf1
--- /dev/null
+++ b/extra/io/encodings/strict/summary.txt
@@ -0,0 +1 @@
+Strict wrapper for encodings
diff --git a/extra/io/encodings/strict/tags.txt b/extra/io/encodings/strict/tags.txt
new file mode 100644
index 0000000000..8e27be7d61
--- /dev/null
+++ b/extra/io/encodings/strict/tags.txt
@@ -0,0 +1 @@
+text
diff --git a/extra/io/launcher/launcher-docs.factor b/extra/io/launcher/launcher-docs.factor
index 7fdd22c8a5..0f6ca3a2c9 100755
--- a/extra/io/launcher/launcher-docs.factor
+++ b/extra/io/launcher/launcher-docs.factor
@@ -33,6 +33,17 @@ $nl
{ "a file stream or a socket - the stream is connected to the given Factor stream, which cannot be used again from within Factor and must be closed after the process has been started" }
} ;
+ARTICLE: "io.launcher.priority" "Setting process priority"
+"The priority of the child process can be set by storing one of the below symbols in the " { $snippet "priority" } " slot of a " { $link process } " tuple:"
+{ $list
+ { $link +lowest-priority+ }
+ { $link +low-priority+ }
+ { $link +normal-priority+ }
+ { $link +high-priority+ }
+ { $link +highest-priority+ }
+}
+"The default value is " { $link f } ", which denotes that the child process should inherit the current process priority." ;
+
HELP: +closed+
{ $description "Possible value for the " { $snippet "stdin" } ", " { $snippet "stdout" } ", and " { $snippet "stderr" } " slots of a " { $link process } "." } ;
@@ -216,6 +227,7 @@ ARTICLE: "io.launcher" "Operating system processes"
{ $subsection "io.launcher.detached" }
{ $subsection "io.launcher.environment" }
{ $subsection "io.launcher.redirection" }
+{ $subsection "io.launcher.priority" }
{ $subsection "io.launcher.timeouts" } ;
ABOUT: "io.launcher"
diff --git a/extra/io/launcher/launcher.factor b/extra/io/launcher/launcher.factor
index 9c7d64934e..ac8dc15661 100755
--- a/extra/io/launcher/launcher.factor
+++ b/extra/io/launcher/launcher.factor
@@ -6,7 +6,6 @@ init threads continuations math io.encodings io.streams.duplex
io.nonblocking accessors ;
IN: io.launcher
-
TUPLE: process
command
@@ -19,6 +18,8 @@ stdin
stdout
stderr
+priority
+
timeout
handle status
@@ -32,6 +33,12 @@ SYMBOL: +prepend-environment+
SYMBOL: +replace-environment+
SYMBOL: +append-environment+
+SYMBOL: +lowest-priority+
+SYMBOL: +low-priority+
+SYMBOL: +normal-priority+
+SYMBOL: +high-priority+
+SYMBOL: +highest-priority+
+
: <process> ( -- process )
process construct-empty
H{ } clone >>environment
diff --git a/extra/io/process/process.factor b/extra/io/process/process.factor
deleted file mode 100644
index 8a7c5b1a11..0000000000
--- a/extra/io/process/process.factor
+++ /dev/null
@@ -1,17 +0,0 @@
-USING: io.backend kernel ;
-IN: io.priority
-
-SYMBOL: +lowest-priority+
-SYMBOL: +low-priority+
-SYMBOL: +normal-priority+
-SYMBOL: +high-priority+
-SYMBOL: +highest-priority+
-
-HOOK: current-priority io-backend ( -- symbol )
-HOOK: set-current-priority io-backend ( symbol -- )
-HOOK: priority-values ( -- assoc )
-
-: lookup-priority ( symbol -- n )
- priority-values at ;
-
-HOOK: get-process-list io-backend ( -- assoc )
diff --git a/extra/io/unix/launcher/launcher.factor b/extra/io/unix/launcher/launcher.factor
index a1e42fddf2..e16ecde6fa 100755
--- a/extra/io/unix/launcher/launcher.factor
+++ b/extra/io/unix/launcher/launcher.factor
@@ -4,7 +4,7 @@ USING: io io.backend io.launcher io.nonblocking io.unix.backend
io.unix.files io.nonblocking sequences kernel namespaces math
system alien.c-types debugger continuations arrays assocs
combinators unix.process strings threads unix
-io.unix.launcher.parser io.encodings.latin1 accessors ;
+io.unix.launcher.parser accessors ;
IN: io.unix.launcher
! Search unix first
@@ -16,6 +16,17 @@ USE: unix
: assoc>env ( assoc -- env )
[ "=" swap 3append ] { } assoc>map ;
+: setup-priority ( process -- process )
+ dup priority>> [
+ H{
+ { +lowest-priority+ 20 }
+ { +low-priority+ 10 }
+ { +normal-priority+ 0 }
+ { +high-priority+ -10 }
+ { +highest-priority+ -20 }
+ } at set-priority
+ ] when* ;
+
: redirect-fd ( oldfd fd -- )
2dup = [ 2drop ] [ dupd dup2 io-error close ] if ;
@@ -47,11 +58,15 @@ USE: unix
: setup-redirection ( process -- process )
dup stdin>> ?closed read-flags 0 redirect
dup stdout>> ?closed write-flags 1 redirect
- dup stderr>> dup +stdout+ eq?
- [ drop 1 2 dup2 io-error ] [ ?closed write-flags 2 redirect ] if ;
+ dup stderr>> dup +stdout+ eq? [
+ drop 1 2 dup2 io-error
+ ] [
+ ?closed write-flags 2 redirect
+ ] if ;
: spawn-process ( process -- * )
[
+ setup-priority
setup-redirection
dup pass-environment? [
dup get-environment set-os-envs
diff --git a/extra/io/unix/process/process.factor b/extra/io/unix/process/process.factor
deleted file mode 100644
index 00df6b6f52..0000000000
--- a/extra/io/unix/process/process.factor
+++ /dev/null
@@ -1,19 +0,0 @@
-USING: alien.syntax kernel io.process io.unix.backend
-unix ;
-IN: io.unix.process
-
-M: unix-io current-priority ( -- n )
- clear_err_no
- 0 0 getpriority dup -1 = [ check-errno ] when ;
-
-M: unix-io set-current-priority ( n -- )
- 0 0 rot setpriority io-error ;
-
-M: unix-io priority-values ( -- assoc )
- {
- { +lowest-priority+ 20 }
- { +low-priority+ 10 }
- { +normal-priority+ 0 }
- { +high-priority+ -10 }
- { +highest-priority+ -20 }
- } ;
diff --git a/extra/io/unix/unix.factor b/extra/io/unix/unix.factor
index d1c0db72f4..0a7fc72662 100755
--- a/extra/io/unix/unix.factor
+++ b/extra/io/unix/unix.factor
@@ -1,5 +1,5 @@
USING: io.unix.backend io.unix.files io.unix.sockets io.timeouts
-io.unix.launcher io.unix.mmap io.backend io.unix.process
-combinators namespaces system vocabs.loader sequences ;
+io.unix.launcher io.unix.mmap io.backend combinators namespaces
+system vocabs.loader sequences ;
"io.unix." os append require
diff --git a/extra/io/windows/process/process.factor b/extra/io/windows/process/process.factor
deleted file mode 100644
index f0ca04fd8a..0000000000
--- a/extra/io/windows/process/process.factor
+++ /dev/null
@@ -1,8 +0,0 @@
-USING: kernel ;
-IN: io.windows.process
-
-M: windows-io current-priority ( -- n )
- ;
-
-M: windows-io set-current-priority ( n -- )
- ;
diff --git a/extra/lsys/ui/ui.factor b/extra/lsys/ui/ui.factor
index 45372aec6c..c8d103a084 100644
--- a/extra/lsys/ui/ui.factor
+++ b/extra/lsys/ui/ui.factor
@@ -196,6 +196,8 @@ slate> handler> set-gadget-delegate
handler> "L-system view" open-window
+500 sleep
+
slate> find-gl-context
1 glGenLists >model
diff --git a/extra/peg/ebnf/ebnf-tests.factor b/extra/peg/ebnf/ebnf-tests.factor
index 54639431a4..c9b9f5d977 100644
--- a/extra/peg/ebnf/ebnf-tests.factor
+++ b/extra/peg/ebnf/ebnf-tests.factor
@@ -1,7 +1,7 @@
! Copyright (C) 2007 Chris Double.
! See http://factorcode.org/license.txt for BSD license.
!
-USING: kernel tools.test peg peg.ebnf ;
+USING: kernel tools.test peg peg.ebnf words ;
IN: peg.ebnf.tests
{ T{ ebnf-non-terminal f "abc" } } [
diff --git a/extra/peg/ebnf/ebnf.factor b/extra/peg/ebnf/ebnf.factor
index ab7baa547e..db478e571f 100644
--- a/extra/peg/ebnf/ebnf.factor
+++ b/extra/peg/ebnf/ebnf.factor
@@ -278,7 +278,7 @@ M: ebnf-non-terminal (transform) ( ast -- parser )
: ebnf>quot ( string -- hashtable quot )
'ebnf' parse check-parse-result
- parse-result-ast transform dup main swap at compile ;
+ parse-result-ast transform dup main swap at compile 1quotation ;
: [EBNF "EBNF]" parse-multiline-string ebnf>quot nip parsed ; parsing
diff --git a/extra/peg/parsers/parsers.factor b/extra/peg/parsers/parsers.factor
index 3ccb1e7d10..4bba60bb09 100755
--- a/extra/peg/parsers/parsers.factor
+++ b/extra/peg/parsers/parsers.factor
@@ -16,8 +16,8 @@ TUPLE: just-parser p1 ;
] ;
-M: just-parser compile ( parser -- quot )
- just-parser-p1 compile just-pattern append ;
+M: just-parser (compile) ( parser -- quot )
+ just-parser-p1 compiled-parser just-pattern curry ;
: just ( parser -- parser )
just-parser construct-boa ;
diff --git a/extra/peg/peg.factor b/extra/peg/peg.factor
index b3200ec5eb..1707193e70 100755
--- a/extra/peg/peg.factor
+++ b/extra/peg/peg.factor
@@ -3,24 +3,43 @@
USING: kernel sequences strings namespaces math assocs shuffle
vectors arrays combinators.lib math.parser match
unicode.categories sequences.lib compiler.units parser
- words ;
+ words quotations effects memoize ;
IN: peg
TUPLE: parse-result remaining ast ;
-GENERIC: compile ( parser -- quot )
-
-: parse ( state parser -- result )
- compile call ;
-
SYMBOL: ignore
: <parse-result> ( remaining ast -- parse-result )
parse-result construct-boa ;
+SYMBOL: compiled-parsers
+
+GENERIC: (compile) ( parser -- quot )
+
+: compiled-parser ( parser -- word )
+ #! Look to see if the given parser has been compiled.
+ #! If not, compile it to a temporary word, cache it,
+ #! and return it. Otherwise return the existing one.
+ dup compiled-parsers get at [
+ nip
+ ] [
+ dup (compile) define-temp
+ [ swap compiled-parsers get set-at ] keep
+ ] if* ;
+
+MEMO: compile ( parser -- word )
+ H{ } clone compiled-parsers [
+ [ compiled-parser ] with-compilation-unit
+ ] with-variable ;
+
+: parse ( state parser -- result )
+ compile execute ;
+
<PRIVATE
TUPLE: token-parser symbol ;
+! M: token-parser equal? eq? ;
MATCH-VARS: ?token ;
@@ -33,7 +52,7 @@ MATCH-VARS: ?token ;
] if
] ;
-M: token-parser compile ( parser -- quot )
+M: token-parser (compile) ( parser -- quot )
token-parser-symbol \ ?token token-pattern match-replace ;
TUPLE: satisfy-parser quot ;
@@ -53,7 +72,7 @@ MATCH-VARS: ?quot ;
] if
] ;
-M: satisfy-parser compile ( parser -- quot )
+M: satisfy-parser (compile) ( parser -- quot )
satisfy-parser-quot \ ?quot satisfy-pattern match-replace ;
TUPLE: range-parser min max ;
@@ -74,7 +93,7 @@ MATCH-VARS: ?min ?max ;
] if
] ;
-M: range-parser compile ( parser -- quot )
+M: range-parser (compile) ( parser -- quot )
T{ range-parser _ ?min ?max } range-pattern match-replace ;
TUPLE: seq-parser parsers ;
@@ -82,7 +101,7 @@ TUPLE: seq-parser parsers ;
: seq-pattern ( -- quot )
[
dup [
- dup parse-result-remaining ?quot call [
+ dup parse-result-remaining ?quot [
[ parse-result-remaining swap set-parse-result-remaining ] 2keep
parse-result-ast dup ignore = [
drop
@@ -97,10 +116,10 @@ TUPLE: seq-parser parsers ;
] if
] ;
-M: seq-parser compile ( parser -- quot )
+M: seq-parser (compile) ( parser -- quot )
[
[ V{ } clone <parse-result> ] %
- seq-parser-parsers [ compile \ ?quot seq-pattern match-replace % ] each
+ seq-parser-parsers [ compiled-parser \ ?quot seq-pattern match-replace % ] each
] [ ] make ;
TUPLE: choice-parser parsers ;
@@ -110,14 +129,14 @@ TUPLE: choice-parser parsers ;
dup [
] [
- drop dup ?quot call
+ drop dup ?quot
] if
] ;
-M: choice-parser compile ( parser -- quot )
+M: choice-parser (compile) ( parser -- quot )
[
f ,
- choice-parser-parsers [ compile \ ?quot choice-pattern match-replace % ] each
+ choice-parser-parsers [ compiled-parser \ ?quot choice-pattern match-replace % ] each
\ nip ,
] [ ] make ;
@@ -134,20 +153,20 @@ TUPLE: repeat0-parser p1 ;
: repeat0-pattern ( -- quot )
[
- ?quot swap (repeat0)
+ [ ?quot ] swap (repeat0)
] ;
-M: repeat0-parser compile ( parser -- quot )
+M: repeat0-parser (compile) ( parser -- quot )
[
[ V{ } clone <parse-result> ] %
- repeat0-parser-p1 compile \ ?quot repeat0-pattern match-replace %
+ repeat0-parser-p1 compiled-parser \ ?quot repeat0-pattern match-replace %
] [ ] make ;
TUPLE: repeat1-parser p1 ;
: repeat1-pattern ( -- quot )
[
- ?quot swap (repeat0) [
+ [ ?quot ] swap (repeat0) [
dup parse-result-ast empty? [
drop f
] when
@@ -156,49 +175,49 @@ TUPLE: repeat1-parser p1 ;
] if*
] ;
-M: repeat1-parser compile ( parser -- quot )
+M: repeat1-parser (compile) ( parser -- quot )
[
[ V{ } clone <parse-result> ] %
- repeat1-parser-p1 compile \ ?quot repeat1-pattern match-replace %
+ repeat1-parser-p1 compiled-parser \ ?quot repeat1-pattern match-replace %
] [ ] make ;
TUPLE: optional-parser p1 ;
: optional-pattern ( -- quot )
[
- dup ?quot call swap f <parse-result> or
+ dup ?quot swap f <parse-result> or
] ;
-M: optional-parser compile ( parser -- quot )
- optional-parser-p1 compile \ ?quot optional-pattern match-replace ;
+M: optional-parser (compile) ( parser -- quot )
+ optional-parser-p1 compiled-parser \ ?quot optional-pattern match-replace ;
TUPLE: ensure-parser p1 ;
: ensure-pattern ( -- quot )
[
- dup ?quot call [
+ dup ?quot [
ignore <parse-result>
] [
drop f
] if
] ;
-M: ensure-parser compile ( parser -- quot )
- ensure-parser-p1 compile \ ?quot ensure-pattern match-replace ;
+M: ensure-parser (compile) ( parser -- quot )
+ ensure-parser-p1 compiled-parser \ ?quot ensure-pattern match-replace ;
TUPLE: ensure-not-parser p1 ;
: ensure-not-pattern ( -- quot )
[
- dup ?quot call [
+ dup ?quot [
drop f
] [
ignore <parse-result>
] if
] ;
-M: ensure-not-parser compile ( parser -- quot )
- ensure-not-parser-p1 compile \ ?quot ensure-not-pattern match-replace ;
+M: ensure-not-parser (compile) ( parser -- quot )
+ ensure-not-parser-p1 compiled-parser \ ?quot ensure-not-pattern match-replace ;
TUPLE: action-parser p1 quot ;
@@ -206,14 +225,14 @@ MATCH-VARS: ?action ;
: action-pattern ( -- quot )
[
- ?quot call dup [
+ ?quot dup [
dup parse-result-ast ?action call
swap [ set-parse-result-ast ] keep
] when
] ;
-M: action-parser compile ( parser -- quot )
- { action-parser-p1 action-parser-quot } get-slots [ compile ] dip
+M: action-parser (compile) ( parser -- quot )
+ { action-parser-p1 action-parser-quot } get-slots [ compiled-parser ] dip
2array { ?quot ?action } action-pattern match-replace ;
: left-trim-slice ( string -- string )
@@ -225,17 +244,22 @@ M: action-parser compile ( parser -- quot )
TUPLE: sp-parser p1 ;
-M: sp-parser compile ( parser -- quot )
+M: sp-parser (compile) ( parser -- quot )
[
- \ left-trim-slice , sp-parser-p1 compile %
+ \ left-trim-slice , sp-parser-p1 compiled-parser ,
] [ ] make ;
TUPLE: delay-parser quot ;
-M: delay-parser compile ( parser -- quot )
+M: delay-parser (compile) ( parser -- quot )
+ #! For efficiency we memoize the quotation.
+ #! This way it is run only once and the
+ #! parser constructed once at run time.
[
- delay-parser-quot % \ compile , \ call ,
- ] [ ] make ;
+ delay-parser-quot % \ compile ,
+ ] [ ] make
+ { } { "word" } <effect> memoize-quot
+ [ % \ execute , ] [ ] make ;
PRIVATE>
@@ -308,7 +332,7 @@ PRIVATE>
: PEG:
(:) [
[
- call compile
+ call compile 1quotation
[ dup [ parse-result-ast ] [ "Parse failed" throw ] if ]
append define
] with-compilation-unit
diff --git a/extra/tools/deploy/shaker/shaker.factor b/extra/tools/deploy/shaker/shaker.factor
index 76e4a212b2..f731f5d694 100755
--- a/extra/tools/deploy/shaker/shaker.factor
+++ b/extra/tools/deploy/shaker/shaker.factor
@@ -139,27 +139,29 @@ IN: tools.deploy.shaker
{ } { "cpu" } strip-vocab-globals %
{
- vocabs:dictionary
- lexer-factory
- vocabs:load-vocab-hook
- root-cache
+ classes:class-and-cache
+ classes:class-not-cache
+ classes:class-or-cache
+ classes:class<-cache
+ classes:classes-intersect-cache
+ classes:update-map
+ compiled-crossref
+ compiler.units:recompile-hook
+ definitions:crossref
+ interactive-vocabs
layouts:num-tags
layouts:num-types
layouts:tag-mask
layouts:tag-numbers
layouts:type-numbers
- classes:typemap
- classes:class-map
- vocab-roots
- definitions:crossref
- compiled-crossref
- interactive-vocabs
- word
- compiler.units:recompile-hook
- listener:listener-hook
lexer-factory
- classes:update-map
- classes:class<map
+ lexer-factory
+ listener:listener-hook
+ root-cache
+ vocab-roots
+ vocabs:dictionary
+ vocabs:load-vocab-hook
+ word
} %
] when
diff --git a/extra/unix/process/process.factor b/extra/unix/process/process.factor
index 6fdc8e358b..c9612c4384 100755
--- a/extra/unix/process/process.factor
+++ b/extra/unix/process/process.factor
@@ -33,4 +33,7 @@ IN: unix.process
fork dup io-error dup zero? -roll swap curry if ; inline
: wait-for-pid ( pid -- status )
- 0 <int> [ 0 waitpid drop ] keep *int WEXITSTATUS ;
\ No newline at end of file
+ 0 <int> [ 0 waitpid drop ] keep *int WEXITSTATUS ;
+
+: set-priority ( n -- )
+ 0 0 rot setpriority io-error ;
\ No newline at end of file