diff --git a/basis/syndication/syndication-tests.factor b/basis/syndication/syndication-tests.factor
index 1ddcbf8090..4fbfee03d9 100644
--- a/basis/syndication/syndication-tests.factor
+++ b/basis/syndication/syndication-tests.factor
@@ -1,5 +1,5 @@
USING: syndication io kernel io.files tools.test io.encodings.utf8
-calendar urls ;
+calendar urls xml.writer ;
IN: syndication.tests
\ download-feed must-infer
@@ -43,3 +43,4 @@ IN: syndication.tests
}
}
} ] [ "resource:basis/syndication/test/atom.xml" load-news-file ] unit-test
+[ ] [ "resource:basis/syndication/test/atom.xml" load-news-file xml>string drop ] unit-test
diff --git a/basis/syndication/syndication.factor b/basis/syndication/syndication.factor
index 9d0419a818..fadb4f4fb3 100644
--- a/basis/syndication/syndication.factor
+++ b/basis/syndication/syndication.factor
@@ -1,10 +1,10 @@
! Copyright (C) 2006 Chris Double, Daniel Ehrenberg.
! Portions copyright (C) 2008 Slava Pestov.
! See http://factorcode.org/license.txt for BSD license.
-USING: xml.utilities kernel assocs xml.generator math.order
+USING: xml.utilities kernel assocs math.order
strings sequences xml.data xml.writer
io.streams.string combinators xml xml.entities.html io.files io
- http.client namespaces make xml.generator hashtables
+ http.client namespaces make xml.interpolate hashtables
calendar.format accessors continuations urls present ;
IN: syndication
@@ -114,26 +114,31 @@ TUPLE: entry title url description date ;
http-get nip string>feed ;
! Atom generation
-: simple-tag, ( content name -- )
- [ , ] tag, ;
-: simple-tag*, ( content name attrs -- )
- [ , ] tag*, ;
-
-: entry, ( entry -- )
- "entry" [
- {
- [ title>> "title" { { "type" "html" } } simple-tag*, ]
- [ url>> present "href" associate "link" swap contained*, ]
- [ date>> timestamp>rfc3339 "published" simple-tag, ]
- [ description>> [ "content" { { "type" "html" } } simple-tag*, ] when* ]
- } cleave
- ] tag, ;
+: entry>xml ( entry -- xml )
+ {
+ [ title>> ]
+ [ url>> present ]
+ [ date>> timestamp>rfc3339 ]
+ [ description>> ]
+ } cleave
+ [XML
+
+ <->
+ />
+ <->
+ <->
+
+ XML] ;
: feed>xml ( feed -- xml )
- "feed" { { "xmlns" "http://www.w3.org/2005/Atom" } } [
- [ title>> "title" simple-tag, ]
- [ url>> present "href" associate "link" swap contained*, ]
- [ entries>> [ entry, ] each ]
- tri
- ] make-xml* ;
+ [ title>> ]
+ [ url>> present ]
+ [ entries>> [ entry>xml ] map ] tri
+
+ <->
+ />
+ <->
+
+ XML> ;
diff --git a/basis/xml/autoencoding/autoencoding.factor b/basis/xml/autoencoding/autoencoding.factor
index 5d7e460862..5dc32958d4 100644
--- a/basis/xml/autoencoding/autoencoding.factor
+++ b/basis/xml/autoencoding/autoencoding.factor
@@ -10,8 +10,8 @@ IN: xml.autoencoding
: start-utf16le ( -- tag )
utf16le decode-input-if
- CHAR: ? expect
- 0 expect check instruct ;
+ "?\0" expect
+ check instruct ;
: 10xxxxxx? ( ch -- ? )
-6 shift 3 bitand 2 = ;
@@ -36,10 +36,10 @@ IN: xml.autoencoding
: skip-utf8-bom ( -- tag )
"\u0000bb\u0000bf" expect utf8 decode-input
- CHAR: < expect check make-tag ;
+ "<" expect check make-tag ;
: decode-expecting ( encoding string -- tag )
- [ decode-input-if next ] [ expect-string ] bi* check make-tag ;
+ [ decode-input-if next ] [ expect ] bi* check make-tag ;
: start-utf16be ( -- tag )
utf16be "<" decode-expecting ;
diff --git a/basis/xml/data/data-docs.factor b/basis/xml/data/data-docs.factor
index c5f4f6d670..9a8c535f91 100644
--- a/basis/xml/data/data-docs.factor
+++ b/basis/xml/data/data-docs.factor
@@ -150,3 +150,52 @@ HELP: assure-name
HELP:
{ $values { "string" string } { "name" name } }
{ $description "Converts a string into an XML name with an empty prefix and URL." } ;
+
+HELP: element-decl
+{ $class-description "Describes the class of element declarations, like ." } ;
+
+HELP:
+{ $values { "name" name } { "content-spec" string } { "element-decl" entity-decl } }
+{ $description "Creates an element declaration object, of the class " { $link element-decl } } ;
+
+HELP: attlist-decl
+{ $class-description "Describes the class of element declarations, like ." } ;
+
+HELP:
+{ $values { "name" name } { "att-defs" string } { "attlist-decl" attlist-decl } }
+{ $description "Creates an element declaration object, of the class " { $link attlist-decl } } ;
+
+HELP: entity-decl
+{ $class-description "Describes the class of element declarations, like ." } ;
+
+HELP:
+{ $values { "name" name } { "def" string } { "pe?" "t or f" } { "entity-decl" entity-decl } }
+{ $description "Creates an entity declaration object, of the class " { $link entity-decl } ". The pe? slot should be t if the object is a DTD-internal entity, like and f if the object is like , that is, it can be used outside of the DTD." } ;
+
+HELP: system-id
+{ $class-description "Describes the class of system identifiers within an XML DTD directive, such as " } ;
+
+HELP:
+{ $values { "system-literal" string } { "system-id" system-id } }
+{ $description "Constructs a " { $link system-id } " tuple." } ;
+
+HELP: public-id
+{ $class-description "Describes the class of public identifiers within an XML DTD directive, such as " } ;
+
+HELP:
+{ $values { "pubid-literal" string } { "system-literal" string } { "public-id" public-id } }
+{ $description "Constructs a " { $link system-id } " tuple." } ;
+
+HELP: notation-decl
+{ $class-description "Describes the class of element declarations, like ." } ;
+
+HELP:
+{ $values { "name" string } { "id" id } { "notation-decl" notation-decl } }
+{ $description "Creates an notation declaration object, of the class " { $link notation-decl } "." } ;
+
+HELP: doctype-decl
+{ $class-description "Describes the class of doctype declarations." } ;
+
+HELP:
+{ $values { "name" name } { "external-id" id } { "internal-subset" sequence } { "doctype-decl" doctype-decl } }
+{ $description "Creates a new doctype declaration object, of the class " { $link doctype-decl } ". Only one of external-id or internal-subset will be non-null." } ;
diff --git a/basis/xml/data/data.factor b/basis/xml/data/data.factor
index 9d84791c1f..b014a96180 100644
--- a/basis/xml/data/data.factor
+++ b/basis/xml/data/data.factor
@@ -5,6 +5,9 @@ delegate.protocols delegate vectors accessors multiline
macros words quotations combinators slots fry strings ;
IN: xml.data
+TUPLE: interpolated var ;
+C: interpolated
+
UNION: nullable-string string POSTPONE: f ;
TUPLE: name
@@ -85,11 +88,13 @@ C: comment
TUPLE: directive ;
TUPLE: element-decl < directive
- { name string } { content-spec string } ;
+ { name string }
+ { content-spec string } ;
C: element-decl
TUPLE: attlist-decl < directive
- { name string } { att-defs string } ;
+ { name string }
+ { att-defs string } ;
C: attlist-decl
UNION: boolean t POSTPONE: f ;
@@ -108,13 +113,23 @@ C: public-id
UNION: id system-id public-id POSTPONE: f ;
+TUPLE: dtd
+ { directives sequence }
+ { entities assoc }
+ { parameter-entities assoc } ;
+C: dtd
+
+UNION: dtd/f dtd POSTPONE: f ;
+
TUPLE: doctype-decl < directive
{ name string }
{ external-id id }
- { internal-subset sequence } ;
+ { internal-subset dtd/f } ;
C: doctype-decl
-TUPLE: notation-decl < directive name id ;
+TUPLE: notation-decl < directive
+ { name string }
+ { id string } ;
C: notation-decl
TUPLE: instruction { text string } ;
diff --git a/basis/xml/dtd/dtd.factor b/basis/xml/dtd/dtd.factor
index a668717626..50de78ec11 100644
--- a/basis/xml/dtd/dtd.factor
+++ b/basis/xml/dtd/dtd.factor
@@ -2,12 +2,9 @@
! See http://factorcode.org/license.txt for BSD license.
USING: xml.tokenize xml.data xml.state kernel sequences ascii
fry xml.errors combinators hashtables namespaces xml.entities
-strings ;
+strings xml.name ;
IN: xml.dtd
-: take-word ( -- string )
- [ get-char blank? ] take-until ;
-
: take-decl-contents ( -- first second )
pass-blank take-word pass-blank ">" take-string ;
@@ -20,36 +17,15 @@ IN: xml.dtd
: take-notation-decl ( -- notation-decl )
take-decl-contents ;
-: take-until-one-of ( seps -- str sep )
- '[ get-char _ member? ] take-until get-char ;
-
-: take-system-id ( -- system-id )
- parse-quote close ;
-
-: take-public-id ( -- public-id )
- parse-quote parse-quote close ;
-
UNION: dtd-acceptable
directive comment instruction ;
-: (take-external-id) ( token -- external-id )
- pass-blank {
- { "SYSTEM" [ take-system-id ] }
- { "PUBLIC" [ take-public-id ] }
- [ bad-external-id ]
- } case ;
-
-: take-external-id ( -- external-id )
- take-word (take-external-id) ;
-
-: only-blanks ( str -- )
- [ blank? ] all? [ bad-decl ] unless ;
: take-entity-def ( var -- entity-name entity-def )
[
take-word pass-blank get-char {
{ CHAR: ' [ parse-quote ] }
{ CHAR: " [ parse-quote ] }
- [ drop take-external-id ]
+ [ drop take-external-id close ]
} case
] dip '[ swap _ [ ?set-at ] change ] 2keep ;
diff --git a/basis/xml/elements/elements.factor b/basis/xml/elements/elements.factor
index 947c11e2a8..b2280bacb4 100644
--- a/basis/xml/elements/elements.factor
+++ b/basis/xml/elements/elements.factor
@@ -3,12 +3,26 @@
USING: kernel namespaces xml.tokenize xml.state xml.name
xml.data accessors arrays make xml.char-classes fry assocs sequences
math xml.errors sets combinators io.encodings io.encodings.iana
-unicode.case xml.dtd strings ;
+unicode.case xml.dtd strings xml.entities ;
IN: xml.elements
+: take-interpolated ( quot -- interpolated )
+ interpolating? get [
+ drop get-char CHAR: > =
+ [ next f ] [
+ pass-blank " \t\r\n-" take-to
+ pass-blank "->" expect
+ ] if
+ ] [ call ] if ; inline
+
+: interpolate-quote ( -- interpolated )
+ [ quoteless-attr ] take-interpolated ;
+
: parse-attr ( -- )
- parse-name pass-blank CHAR: = expect pass-blank
- t parse-quote* 2array , ;
+ parse-name pass-blank "=" expect pass-blank
+ get-char CHAR: < =
+ [ "<-" expect interpolate-quote ]
+ [ t parse-quote* ] if 2array , ;
: start-tag ( -- name ? )
#! Outputs the name and whether this is a closing tag
@@ -31,14 +45,14 @@ IN: xml.elements
: end-tag ( name attrs-alist -- tag )
tag-ns pass-blank get-char CHAR: / =
- [ pop-ns next CHAR: > expect ]
+ [ pop-ns next ">" expect ]
[ depth inc close ] if ;
: take-comment ( -- comment )
- "--" expect-string
+ "--" expect
"--" take-string
- CHAR: > expect ;
+ ">" expect ;
: assure-no-extra ( seq -- )
[ first ] map {
@@ -80,7 +94,7 @@ SYMBOL: string-input?
string-input? get [ drop ] [ decode-input ] if ;
: parse-prolog ( -- prolog )
- pass-blank middle-tag "?>" expect-string
+ pass-blank middle-tag "?>" expect
dup assure-no-extra prolog-attrs
dup encoding>> dup "UTF-16" =
[ drop ] [ name>encoding [ decode-input-if ] when* ] if
@@ -96,45 +110,45 @@ SYMBOL: string-input?
: take-cdata ( -- string )
depth get zero? [ bad-cdata ] when
- "[CDATA[" expect-string "]]>" take-string ;
+ "[CDATA[" expect "]]>" take-string ;
DEFER: make-tag ! Is this unavoidable?
: expand-pe ( -- ) ; ! Make this run the contents of the pe within a DOCTYPE
-: (take-internal-subset) ( -- )
+: dtd-loop ( -- )
pass-blank get-char {
{ CHAR: ] [ next ] }
{ CHAR: % [ expand-pe ] }
{ CHAR: < [
next make-tag dup dtd-acceptable?
- [ bad-doctype ] unless , (take-internal-subset)
+ [ bad-doctype ] unless , dtd-loop
] }
+ { f [ ] }
[ 1string bad-doctype ]
} case ;
-: take-internal-subset ( -- seq )
+: take-internal-subset ( -- dtd )
[
- H{ } pe-table set
+ H{ } clone pe-table set
t in-dtd? set
- (take-internal-subset)
- ] { } make ;
+ dtd-loop
+ pe-table get
+ ] { } make swap extra-entities get swap ;
-: nontrivial-doctype ( -- external-id internal-subset )
- pass-blank get-char CHAR: [ = [
- next take-internal-subset f swap close
- ] [
- " >" take-until-one-of {
- { CHAR: \s [ (take-external-id) ] }
- { CHAR: > [ only-blanks f ] }
- } case f
- ] if ;
+: take-optional-id ( -- id/f )
+ get-char "SP" member?
+ [ take-external-id ] [ f ] if ;
+
+: take-internal ( -- dtd/f )
+ get-char CHAR: [ =
+ [ next take-internal-subset ] [ f ] if ;
: take-doctype-decl ( -- doctype-decl )
- pass-blank " >" take-until-one-of {
- { CHAR: \s [ nontrivial-doctype ] }
- { CHAR: > [ f f ] }
- } case ;
+ pass-blank take-name
+ pass-blank take-optional-id
+ pass-blank take-internal
+ close ;
: take-directive ( -- doctype )
take-name dup "DOCTYPE" =
@@ -151,12 +165,18 @@ DEFER: make-tag ! Is this unavoidable?
[ drop take-directive ]
} case ;
+: normal-tag ( -- tag )
+ start-tag
+ [ dup add-ns pop-ns depth dec close ]
+ [ middle-tag end-tag ] if ;
+
+: interpolate-tag ( -- interpolated )
+ [ "-" bad-name ] take-interpolated ;
+
: make-tag ( -- tag )
{
{ [ get-char dup CHAR: ! = ] [ drop next direct ] }
- { [ CHAR: ? = ] [ next instruct ] }
- [
- start-tag [ dup add-ns pop-ns depth dec close ]
- [ middle-tag end-tag ] if
- ]
+ { [ dup CHAR: ? = ] [ drop next instruct ] }
+ { [ dup CHAR: - = ] [ drop next interpolate-tag ] }
+ [ drop normal-tag ]
} cond ;
diff --git a/basis/xml/entities/entities.factor b/basis/xml/entities/entities.factor
index a3812c7723..a730474f20 100644
--- a/basis/xml/entities/entities.factor
+++ b/basis/xml/entities/entities.factor
@@ -1,7 +1,7 @@
! Copyright (C) 2005, 2006 Daniel Ehrenberg
! See http://factorcode.org/license.txt for BSD license.
USING: namespaces make kernel assocs sequences fry values
-io.files io.encodings.binary ;
+io.files io.encodings.binary xml.state ;
IN: xml.entities
: entities-out
@@ -37,7 +37,5 @@ IN: xml.entities
{ "quot" CHAR: " }
} ;
-SYMBOL: extra-entities
-
: with-entities ( entities quot -- )
[ swap extra-entities set call ] with-scope ; inline
diff --git a/basis/xml/entities/html/html.factor b/basis/xml/entities/html/html.factor
index 826dccf79d..f1e52319f1 100644
--- a/basis/xml/entities/html/html.factor
+++ b/basis/xml/entities/html/html.factor
@@ -1,13 +1,13 @@
! Copyright (C) 2009 Daniel Ehrenberg.
! See http://factorcode.org/license.txt for BSD license.
USING: assocs io.encodings.binary io.files kernel namespaces sequences
-values xml xml.entities ;
+values xml xml.entities accessors xml.state ;
IN: xml.entities.html
VALUE: html-entities
: read-entities-file ( file -- table )
- file>dtd nip ;
+ file>dtd entities>> ;
: get-html ( -- table )
{ "lat1" "special" "symbol" } [
diff --git a/basis/xml/generator/authors.txt b/basis/xml/generator/authors.txt
deleted file mode 100755
index f990dd0ed2..0000000000
--- a/basis/xml/generator/authors.txt
+++ /dev/null
@@ -1 +0,0 @@
-Daniel Ehrenberg
diff --git a/basis/xml/generator/generator-tests.factor b/basis/xml/generator/generator-tests.factor
deleted file mode 100644
index 17f7cab509..0000000000
--- a/basis/xml/generator/generator-tests.factor
+++ /dev/null
@@ -1,3 +0,0 @@
-USING: tools.test io.streams.string xml.generator xml.writer accessors ;
-[ "" ]
-[ "html" [ "body" [ "a" { { "href" "blah" } } contained*, ] tag, ] make-xml [ body>> write-xml-chunk ] with-string-writer ] unit-test
diff --git a/basis/xml/generator/generator.factor b/basis/xml/generator/generator.factor
deleted file mode 100644
index ac7b14b89e..0000000000
--- a/basis/xml/generator/generator.factor
+++ /dev/null
@@ -1,25 +0,0 @@
-! Copyright (C) 2006, 2007 Daniel Ehrenberg
-! See http://factorcode.org/license.txt for BSD license.
-USING: namespaces make kernel xml.data xml.utilities assocs
-sequences ;
-IN: xml.generator
-
-: comment, ( string -- ) , ;
-: instruction, ( string -- ) , ;
-: nl, ( -- ) "\n" , ;
-
-: (tag,) ( name attrs quot -- tag )
- -rot [ V{ } make ] 2dip rot ; inline
-: tag*, ( name attrs quot -- )
- (tag,) , ; inline
-
-: contained*, ( name attrs -- )
- f , ;
-
-: tag, ( name quot -- ) f swap tag*, ; inline
-: contained, ( name -- ) f contained*, ; inline
-
-: make-xml* ( name attrs quot -- xml )
- (tag,) build-xml ; inline
-: make-xml ( name quot -- xml )
- f swap make-xml* ; inline
diff --git a/basis/xml/interpolate/interpolate-tests.factor b/basis/xml/interpolate/interpolate-tests.factor
index 0adcb51123..48f76b8746 100644
--- a/basis/xml/interpolate/interpolate-tests.factor
+++ b/basis/xml/interpolate/interpolate-tests.factor
@@ -1,4 +1,46 @@
! Copyright (C) 2009 Daniel Ehrenberg.
! See http://factorcode.org/license.txt for BSD license.
-USING: tools.test xml.interpolate ;
+USING: tools.test xml.interpolate multiline kernel assocs
+sequences accessors xml.writer xml.interpolate.private
+locals splitting ;
IN: xml.interpolate.tests
+
+[ "a" "c" { "a" "c" f } ] [
+ "<-a->/><->"
+ interpolated-doc
+ [ second var>> ]
+ [ fourth "val" swap at var>> ]
+ [ extract-variables ] tri
+] unit-test
+
+[ {"
+
+ one
+
+ y
+
+"} ] [
+ [let* | a [ "one" ] c [ "two" ] x [ "y" ]
+ d [ [XML <-x-> XML] ] |
+ <-a-> /> <-d->
+ XML> pprint-xml>string
+ ]
+] unit-test
+
+[ {"
+
+ -
+ one
+
+ -
+ two
+
+ -
+ three
+
+"} ] [
+ "one two three" " " split
+ [ [XML - <->
XML] ] map
+ <-> XML> pprint-xml>string
+] unit-test
diff --git a/basis/xml/interpolate/interpolate.factor b/basis/xml/interpolate/interpolate.factor
index 262d0e1adc..7b041ec53d 100644
--- a/basis/xml/interpolate/interpolate.factor
+++ b/basis/xml/interpolate/interpolate.factor
@@ -1,4 +1,95 @@
! Copyright (C) 2009 Daniel Ehrenberg.
! See http://factorcode.org/license.txt for BSD license.
-USING: ;
+USING: xml xml.state kernel sequences fry assocs xml.data
+accessors strings make multiline parser namespaces macros
+sequences.deep generalizations locals words combinators
+math ;
IN: xml.interpolate
+
+xml-chunk ] with-variable ;
+
+: interpolated-doc ( string -- xml )
+ t interpolating? [ string>xml ] with-variable ;
+
+DEFER: interpolate-sequence
+
+: interpolate-attrs ( table attrs -- attrs )
+ swap '[ dup interpolated? [ var>> _ at ] when ] assoc-map ;
+
+: interpolate-tag ( table tag -- tag )
+ [ nip name>> ]
+ [ attrs>> interpolate-attrs ]
+ [ children>> [ interpolate-sequence ] [ drop f ] if* ] 2tri
+ ;
+
+GENERIC: push-item ( item -- )
+M: string push-item , ;
+M: object push-item , ;
+M: sequence push-item % ;
+
+GENERIC: interpolate-item ( table item -- )
+M: object interpolate-item nip , ;
+M: tag interpolate-item interpolate-tag , ;
+M: interpolated interpolate-item
+ var>> swap at push-item ;
+
+: interpolate-sequence ( table seq -- seq )
+ [ [ interpolate-item ] with each ] { } make ;
+
+: interpolate-xml-doc ( table xml -- xml )
+ (clone) [ interpolate-tag ] change-body ;
+
+GENERIC# (each-interpolated) 1 ( item quot -- ) inline
+M: interpolated (each-interpolated) call ;
+M: tag (each-interpolated)
+ swap attrs>> values
+ [ interpolated? ] filter
+ swap each ;
+M: object (each-interpolated) 2drop ;
+
+: each-interpolated ( xml quot -- )
+ '[ _ (each-interpolated) ] deep-each ; inline
+
+:: number<-> ( doc -- doc )
+ 0 :> n! doc [
+ dup var>> [ n >>var n 1+ n! ] unless drop
+ ] each-interpolated doc ;
+
+MACRO: interpolate-xml ( string -- doc )
+ interpolated-doc number<-> '[ _ interpolate-xml-doc ] ;
+
+MACRO: interpolate-chunk ( string -- chunk )
+ interpolated-chunk number<-> '[ _ interpolate-sequence ] ;
+
+: >search-hash ( seq -- hash )
+ [ dup search ] H{ } map>assoc ;
+
+: extract-variables ( xml -- seq )
+ [ [ var>> , ] each-interpolated ] { } make ;
+
+: collect ( accum seq -- accum )
+ {
+ { [ dup [ ] all? ] [ >search-hash parsed ] } ! locals
+ { [ dup [ not ] all? ] [ ! fry
+ length parsed \ narray parsed \ parsed
+ ] }
+ [ drop "XML interpolation contains both fry and locals" throw ] ! mixed
+ } cond ;
+
+: parse-def ( accum delimiter word -- accum )
+ [
+ parse-multiline-string
+ [ interpolated-chunk extract-variables collect ] keep
+ parsed
+ ] dip parsed ;
+
+PRIVATE>
+
+: " \ interpolate-xml parse-def ; parsing
+
+: [XML
+ "XML]" \ interpolate-chunk parse-def ; parsing
diff --git a/basis/xml/name/name.factor b/basis/xml/name/name.factor
index 32053b1eb4..83132d4d29 100644
--- a/basis/xml/name/name.factor
+++ b/basis/xml/name/name.factor
@@ -2,7 +2,7 @@
! See http://factorcode.org/license.txt for BSD license.
USING: kernel namespaces accessors xml.tokenize xml.data assocs
xml.errors xml.char-classes combinators.short-circuit splitting
-fry xml.state sequences ;
+fry xml.state sequences combinators ascii ;
IN: xml.name
! XML namespace processing: ns = namespace
@@ -74,3 +74,21 @@ SYMBOL: ns-stack
: parse-name-starting ( string -- name )
take-name append interpret-name ;
+: take-system-id ( -- system-id )
+ parse-quote ;
+
+: take-public-id ( -- public-id )
+ parse-quote parse-quote ;
+
+: (take-external-id) ( token -- external-id )
+ pass-blank {
+ { "SYSTEM" [ take-system-id ] }
+ { "PUBLIC" [ take-public-id ] }
+ [ bad-external-id ]
+ } case ;
+
+: take-word ( -- string )
+ [ get-char blank? ] take-until ;
+
+: take-external-id ( -- external-id )
+ take-word (take-external-id) ;
diff --git a/basis/xml/state/state.factor b/basis/xml/state/state.factor
index b00d723a1a..059d8267a0 100644
--- a/basis/xml/state/state.factor
+++ b/basis/xml/state/state.factor
@@ -23,3 +23,11 @@ SYMBOL: xml-stack
SYMBOL: prolog-data
SYMBOL: depth
+
+SYMBOL: interpolating?
+
+SYMBOL: in-dtd?
+
+SYMBOL: pe-table
+
+SYMBOL: extra-entities
diff --git a/basis/xml/tests/state-parser-tests.factor b/basis/xml/tests/state-parser-tests.factor
index 31d4a03c7b..24c3bc4b69 100644
--- a/basis/xml/tests/state-parser-tests.factor
+++ b/basis/xml/tests/state-parser-tests.factor
@@ -7,6 +7,9 @@ IN: xml.test.state
: take-rest ( -- string )
[ f ] take-until ;
+: take-char ( char -- string )
+ 1string take-to ;
+
[ "hello" ] [ "hello" [ take-rest ] string-parse ] unit-test
[ 2 4 ] [ "12\n123" [ take-rest drop get-line get-column ] string-parse ] unit-test
[ "hi" " how are you?" ] [ "hi how are you?" [ [ get-char blank? ] take-until take-rest ] string-parse ] unit-test
diff --git a/basis/xml/tests/test.factor b/basis/xml/tests/test.factor
index 794796339e..488bd911bd 100644
--- a/basis/xml/tests/test.factor
+++ b/basis/xml/tests/test.factor
@@ -49,10 +49,10 @@ SYMBOL: xml-file
[ "foo" ] [ "" string>xml children>string ] unit-test
[ "" string>xml ] must-fail
[ ] [ "" string>xml drop ] unit-test
-[ T{ element-decl f "br" "EMPTY" } ] [ "" string>dtd drop second ] unit-test
-[ T{ element-decl f "p" "(#PCDATA|emph)*" } ] [ "" string>dtd drop second ] unit-test
-[ T{ element-decl f "%name.para;" "%content.para;" } ] [ "" string>dtd drop second ] unit-test
-[ T{ element-decl f "container" "ANY" } ] [ "" string>dtd drop second ] unit-test
+[ T{ element-decl f "br" "EMPTY" } ] [ "" string>dtd directives>> first ] unit-test
+[ T{ element-decl f "p" "(#PCDATA|emph)*" } ] [ "" string>dtd directives>> first ] unit-test
+[ T{ element-decl f "%name.para;" "%content.para;" } ] [ "" string>dtd directives>> first ] unit-test
+[ T{ element-decl f "container" "ANY" } ] [ "" string>dtd directives>> first ] unit-test
[ T{ doctype-decl f "foo" } ] [ "" string>xml-chunk first ] unit-test
[ T{ doctype-decl f "foo" } ] [ "" string>xml-chunk first ] unit-test
[ T{ doctype-decl f "foo" T{ system-id f "blah.dtd" } } ] [ "" string>xml-chunk first ] unit-test
diff --git a/basis/xml/tests/xmode-dtd.factor b/basis/xml/tests/xmode-dtd.factor
index 85e3516444..4408655d9c 100644
--- a/basis/xml/tests/xmode-dtd.factor
+++ b/basis/xml/tests/xmode-dtd.factor
@@ -1,8 +1,8 @@
! Copyright (C) 2008 Slava Pestov.
! See http://factorcode.org/license.txt for BSD license.
-USING: xml io.encodings.utf8 io.files kernel tools.test ;
+USING: xml xml.data kernel tools.test ;
IN: xml.tests
-[ ] [
- "resource:basis/xmode/xmode.dtd" file>dtd 2drop
+[ t ] [
+ "resource:basis/xmode/xmode.dtd" file>dtd dtd?
] unit-test
diff --git a/basis/xml/tokenize/tokenize.factor b/basis/xml/tokenize/tokenize.factor
index 943f4e7a15..b629d46455 100644
--- a/basis/xml/tokenize/tokenize.factor
+++ b/basis/xml/tokenize/tokenize.factor
@@ -58,8 +58,8 @@ IN: xml.tokenize
'[ @ [ t ] [ get-char _ push f ] if ] skip-until
] keep >string ; inline
-: take-char ( ch -- string )
- [ dup get-char = ] take-until nip ;
+: take-to ( seq -- string )
+ '[ get-char _ member? ] take-until ;
: pass-blank ( -- )
#! Advance code past any whitespace, including newlines
@@ -75,33 +75,29 @@ IN: xml.tokenize
dup length rot length 1- - head
get-char [ missing-close ] unless next ;
-: expect ( ch -- )
- get-char 2dup = [ 2drop ] [
- [ 1string ] bi@ expected
- ] if next ;
-
-: expect-string ( string -- )
+: expect ( string -- )
dup [ get-char next ] replicate 2dup =
[ 2drop ] [ expected ] if ;
+! Suddenly XML-specific
+
: parse-named-entity ( string -- )
dup entities at [ , ] [
dup extra-entities get at
[ % ] [ no-entity ] ?if
] ?if ;
+: take-; ( -- string )
+ next ";" take-to next ;
+
: parse-entity ( -- )
- next CHAR: ; take-char next
- "#" ?head [
+ take-; "#" ?head [
"x" ?head 16 10 ? base> ,
] [ parse-named-entity ] if ;
-SYMBOL: pe-table
-SYMBOL: in-dtd?
-
: parse-pe ( -- )
- next CHAR: ; take-char dup next
- pe-table get at [ % ] [ no-entity ] ?if ;
+ take-; dup pe-table get at
+ [ % ] [ no-entity ] ?if ;
:: (parse-char) ( quot: ( ch -- ? ) -- )
get-char :> char
@@ -131,7 +127,7 @@ SYMBOL: in-dtd?
] parse-char ;
: close ( -- )
- pass-blank CHAR: > expect ;
+ pass-blank ">" expect ;
: normalize-quote ( str -- str )
[ dup "\t\r\n" member? [ drop CHAR: \s ] when ] map ;
diff --git a/basis/xml/writer/writer.factor b/basis/xml/writer/writer.factor
index d8283963f1..8cb32af12f 100644
--- a/basis/xml/writer/writer.factor
+++ b/basis/xml/writer/writer.factor
@@ -136,10 +136,10 @@ M: public-id write-xml-chunk
[ pubid-literal>> write "' '" write ]
[ system-literal>> write "'" write ] bi ;
-: write-internal-subset ( seq -- )
+: write-internal-subset ( dtd -- )
[
"[" write indent
- [ ?indent write-xml-chunk ] each
+ directives>> [ ?indent write-xml-chunk ] each
unindent ?indent "]" write
] when* ;
diff --git a/basis/xml/xml.factor b/basis/xml/xml.factor
index 4dd872156e..fdabbdc4df 100644
--- a/basis/xml/xml.factor
+++ b/basis/xml/xml.factor
@@ -164,21 +164,15 @@ TUPLE: pull-xml scope ;
: file>xml ( filename -- xml )
binary read-xml ;
-: (read-dtd) ( -- dtd )
- ! should filter out blanks, throw error on non-dtd stuff
- V{ } clone dup [ push ] curry sax-loop ;
-
-: read-dtd ( stream -- dtd entities )
+: read-dtd ( stream -- dtd )
[
- t in-dtd? set
reset-prolog
H{ } clone extra-entities set
- (read-dtd)
- extra-entities get
+ take-internal-subset
] with-state ;
-: file>dtd ( filename -- dtd entities )
+: file>dtd ( filename -- dtd )
utf8 read-dtd ;
-: string>dtd ( string -- dtd entities )
+: string>dtd ( string -- dtd )
read-dtd ;
diff --git a/unmaintained/xml/syntax/syntax.factor b/unmaintained/xml/syntax/syntax.factor
deleted file mode 100644
index 91b31ec7e6..0000000000
--- a/unmaintained/xml/syntax/syntax.factor
+++ /dev/null
@@ -1,58 +0,0 @@
-! Copyright (C) 2008 Daniel Ehrenberg.
-! See http://factorcode.org/license.txt for BSD license.
-USING: lexer parser splitting kernel quotations namespaces make
-sequences assocs sequences.lib xml.generator xml.utilities
-xml.data ;
-IN: xml.syntax
-
-: parsed-name ( accum -- accum )
- scan ":" split1 [ f ] [ ] if* parsed ;
-
-: run-combinator ( accum quot1 quot2 -- accum )
- >r [ ] like parsed r> [ parsed ] each ;
-
-: parse-tag-contents ( accum contained? -- accum )
- [ \ contained*, parsed ] [
- scan-word \ [ =
- [ POSTPONE: [ \ tag*, parsed ]
- [ "Expected [ missing" throw ] if
- ] if ;
-
-DEFER: >>
-
-: attributes-parsed ( accum quot -- accum )
- [ f parsed ] [
- >r \ >r parsed r> parsed
- [ H{ } make-assoc r> swap ] [ parsed ] each
- ] if-empty ;
-
-: <<
- parsed-name [
- \ >> parse-until >quotation
- attributes-parsed \ contained? get
- ] with-scope parse-tag-contents ; parsing
-
-: ==
- \ call parsed parsed-name \ set parsed ; parsing
-
-: //
- \ contained? on ; parsing
-
-: parse-special ( accum end-token word -- accum )
- >r parse-tokens " " join parsed r> parsed ;
-
-: " \ comment, parse-special ; parsing
-
-: " \ directive, parse-special ; parsing
-
-: " \ instruction, parse-special ; parsing
-
-: >xml-document ( seq -- xml )
- dup first prolog? [ unclip-slice ] [ standard-prolog ] if swap
- [ tag? ] split-around ;
-
-DEFER: XML>
-
-: [ >quotation ] parse-literal
- { } parsed \ make parsed \ >xml-document parsed ; parsing