steve
/
factor
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

refactor state parser some more, add a word to parse escaped strings

db4
Doug Coleman 2009-04-01 14:36:08 -05:00
parent d52535b63a
commit 1e4eebda3a
2 changed files with 34 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
extra/html/parser/state/state-tests.factor
View File

@ -52,3 +52,17 @@ IN: html.parser.state.tests
[ "cd" ] [ "cd" ]
[ "abcd" <state-parser> [ "ab" take-sequence drop ] [ "cd" take-sequence ] bi ] unit-test [ "abcd" <state-parser> [ "ab" take-sequence drop ] [ "cd" take-sequence ] bi ] unit-test
[ f ]
[
"\"abc\" asdf" <state-parser>
[ CHAR: \ CHAR: " take-quoted-string drop ] [ "asdf" take-sequence ] bi
] unit-test
[ "asdf" ]
[
"\"abc\" asdf" <state-parser>
[ CHAR: \ CHAR: " take-quoted-string drop ]
[ skip-whitespace "asdf" take-sequence ] bi
] unit-test

29
extra/html/parser/state/state.factor
View File

@ -1,7 +1,7 @@
! Copyright (C) 2005, 2009 Daniel Ehrenberg ! Copyright (C) 2005, 2009 Daniel Ehrenberg
! See http://factorcode.org/license.txt for BSD license. ! See http://factorcode.org/license.txt for BSD license.
USING: namespaces math kernel sequences accessors fry circular USING: namespaces math kernel sequences accessors fry circular
unicode.case unicode.categories locals ; unicode.case unicode.categories locals combinators.short-circuit ;
IN: html.parser.state IN: html.parser.state
@ -12,21 +12,22 @@ TUPLE: state-parser sequence n ;
swap >>sequence swap >>sequence
0 >>n ; 0 >>n ;
: state-parser-nth ( n state-parser -- char/f ) : offset ( state-parser offset -- char/f )
sequence>> ?nth ; inline swap
[ n>> + ] [ sequence>> ?nth ] bi ; inline
: current ( state-parser -- char/f ) : current ( state-parser -- char/f ) 0 offset ; inline
[ n>> ] keep state-parser-nth ; inline
: previous ( state-parser -- char/f ) : previous ( state-parser -- char/f ) -1 offset ; inline
[ n>> 1 - ] keep state-parser-nth ; inline
: peek-next ( state-parser -- char/f ) : peek-next ( state-parser -- char/f ) 1 offset ; inline
[ n>> 1 + ] keep state-parser-nth ; inline
: advance ( state-parser -- state-parser ) : advance ( state-parser -- state-parser )
[ 1 + ] change-n ; inline [ 1 + ] change-n ; inline
: advance* ( state-parser -- )
advance drop ; inline
: get+increment ( state-parser -- char/f ) : get+increment ( state-parser -- char/f )
[ current ] [ advance drop ] bi ; inline [ current ] [ advance drop ] bi ; inline
@ -80,3 +81,13 @@ TUPLE: state-parser sequence n ;
: state-parse ( sequence quot -- ) : state-parse ( sequence quot -- )
[ <state-parser> ] dip call ; inline [ <state-parser> ] dip call ; inline
:: take-quoted-string ( state-parser escape-char quote-char -- string )
state-parser advance
[
{
[ { [ previous quote-char = ] [ current quote-char = ] } 1&& ]
[ current quote-char = not ]
} 1||
] take-while
state-parser advance* ;