! Copyright (C) 2008 Doug Coleman.
! See http://factorcode.org/license.txt for BSD license.
-USING: accessors arrays hashtables html.parser.state
-html.parser.utils kernel make namespaces sequences
-unicode.case unicode.categories combinators.short-circuit
-quoting ;
+USING: accessors combinators.short-circuit html.parser.utils
+kernel make math namespaces quoting sequences sequences.parser
+unicode ;
IN: html.parser
-
TUPLE: tag name attributes text closing? ;
SINGLETON: text
SINGLETON: dtd
SINGLETON: comment
+
+<PRIVATE
+
SYMBOL: tagstack
: push-tag ( tag -- )
: closing-tag? ( string -- ? )
[ f ]
- [ [ first ] [ peek ] bi [ CHAR: / = ] bi@ or ] if-empty ;
+ [ { [ first CHAR: / = ] [ last CHAR: / = ] } 1|| ] if-empty ;
: <tag> ( name attributes closing? -- tag )
tag new
: make-tag ( string attribs -- tag )
[ [ closing-tag? ] keep "/" trim1 ] dip rot <tag> ;
-: new-tag ( string type -- tag )
+: new-tag ( text name -- tag )
tag new
swap >>name
swap >>text ; inline
-: make-text-tag ( string -- tag ) text new-tag ; inline
+: (read-quote) ( sequence-parser ch -- string )
+ '[ [ current _ = ] take-until ] [ advance drop ] bi ;
-: make-comment-tag ( string -- tag ) comment new-tag ; inline
+: read-single-quote ( sequence-parser -- string )
+ CHAR: ' (read-quote) ;
-: make-dtd-tag ( string -- tag ) dtd new-tag ; inline
+: read-double-quote ( sequence-parser -- string )
+ CHAR: \" (read-quote) ;
-: read-single-quote ( state-parser -- string )
- [ [ CHAR: ' = ] take-until ] [ next drop ] bi ;
-
-: read-double-quote ( state-parser -- string )
- [ [ CHAR: " = ] take-until ] [ next drop ] bi ;
-
-: read-quote ( state-parser -- string )
+: read-quote ( sequence-parser -- string )
dup get+increment CHAR: ' =
[ read-single-quote ] [ read-double-quote ] if ;
-: read-key ( state-parser -- string )
- skip-whitespace
- [ { [ CHAR: = = ] [ blank? ] } 1|| ] take-until ;
-
-: read-= ( state-parser -- )
+: read-key ( sequence-parser -- string )
skip-whitespace
- [ [ CHAR: = = ] take-until drop ] [ next drop ] bi ;
+ [ current { [ CHAR: = = ] [ blank? ] } 1|| ] take-until ;
-: read-token ( state-parser -- string )
- [ blank? ] take-until ;
+: read-token ( sequence-parser -- string )
+ [ current blank? ] take-until ;
-: read-value ( state-parser -- string )
+: read-value ( sequence-parser -- string )
skip-whitespace
- dup get-char quote? [ read-quote ] [ read-token ] if
+ dup current quote? [ read-quote ] [ read-token ] if
[ blank? ] trim ;
-: read-comment ( state-parser -- )
- "-->" take-until-sequence make-comment-tag push-tag ;
+: read-comment ( sequence-parser -- )
+ [ "-->" take-until-sequence comment new-tag push-tag ]
+ [ '[ _ advance drop ] 3 swap times ] bi ;
-: read-dtd ( state-parser -- )
- ">" take-until-sequence make-dtd-tag push-tag ;
+: read-dtd ( sequence-parser -- )
+ [ ">" take-until-sequence dtd new-tag push-tag ]
+ [ advance drop ] bi ;
-: read-bang ( state-parser -- )
- next dup { [ get-char CHAR: - = ] [ get-next CHAR: - = ] } 1&& [
- next next
- read-comment
- ] [
- read-dtd
- ] if ;
+: read-bang ( sequence-parser -- )
+ advance dup { [ current CHAR: - = ] [ peek-next CHAR: - = ] } 1&&
+ [ advance advance read-comment ] [ read-dtd ] if ;
-: read-tag ( state-parser -- string )
- [ [ "><" member? ] take-until ]
- [ dup get-char CHAR: < = [ next ] unless drop ] bi ;
+: read-tag ( sequence-parser -- string )
+ [
+ [ current "><" member? ] take-until
+ [ CHAR: / = ] trim-tail
+ ] [ dup current CHAR: < = [ advance ] unless drop ] bi ;
+
+: read-until-< ( sequence-parser -- string )
+ [ current CHAR: < = ] take-until ;
-: read-until-< ( state-parser -- string )
- [ CHAR: < = ] take-until ;
+: parse-text ( sequence-parser -- )
+ read-until-< [ text new-tag push-tag ] unless-empty ;
-: parse-text ( state-parser -- )
- read-until-< [ make-text-tag push-tag ] unless-empty ;
+: parse-key/value ( sequence-parser -- key value )
+ [ read-key >lower ]
+ [ skip-whitespace "=" take-sequence ]
+ [ swap [ read-value ] [ drop dup ] if ] tri ;
-: (parse-attributes) ( state-parser -- )
+: (parse-attributes) ( sequence-parser -- )
skip-whitespace
- dup state-parse-end? [
+ dup sequence-parse-end? [
drop
] [
- [
- [ read-key >lower ] [ read-= ] [ read-value ] tri
- 2array ,
- ] keep (parse-attributes)
+ [ parse-key/value swap ,, ] [ (parse-attributes) ] bi
] if ;
-: parse-attributes ( state-parser -- hashtable )
- [ (parse-attributes) ] { } make >hashtable ;
+: parse-attributes ( sequence-parser -- hashtable )
+ [ (parse-attributes) ] H{ } make ;
: (parse-tag) ( string -- string' hashtable )
[
[ read-token >lower ] [ parse-attributes ] bi
- ] state-parse ;
+ ] parse-sequence ;
-: read-< ( state-parser -- string/f )
- next dup get-char [
+: read-< ( sequence-parser -- string/f )
+ advance dup current [
CHAR: ! = [ read-bang f ] [ read-tag ] if
] [
drop f
] if* ;
-: parse-tag ( state-parser -- )
+: parse-tag ( sequence-parser -- )
read-< [ (parse-tag) make-tag push-tag ] unless-empty ;
-: (parse-html) ( state-parser -- )
- dup get-next [
+: (parse-html) ( sequence-parser -- )
+ dup peek-next [
[ parse-text ] [ parse-tag ] [ (parse-html) ] tri
] [ drop ] if ;
: tag-parse ( quot -- vector )
- V{ } clone tagstack [ state-parse ] with-variable ; inline
+ V{ } clone tagstack [ parse-sequence ] with-variable ; inline
+
+PRIVATE>
: parse-html ( string -- vector )
[ (parse-html) tagstack get ] tag-parse ;