1 ! Copyright (C) 2008, 2009 Slava Pestov, Doug Coleman.
2 ! See http://factorcode.org/license.txt for BSD license.
3 USING: accessors assocs combinators kernel kernel.private lexer
4 math math.parser namespaces sbufs sequences splitting strings ;
7 ERROR: bad-escape char ;
9 : escape ( escape -- ch )
24 } ?at [ bad-escape ] unless ;
26 SYMBOL: name>char-hook
29 [ "Unicode support not available" throw ]
32 : hex-escape ( str -- ch str' )
33 2 cut-slice [ hex> ] dip ;
35 : unicode-escape ( str -- ch str' )
37 CHAR: } over index cut-slice [
41 >string name>char-hook get call( name -- char )
45 6 cut-slice [ hex> ] dip
48 : next-escape ( str -- ch str' )
50 { CHAR: u [ unicode-escape ] }
51 { CHAR: x [ hex-escape ] }
52 { CHAR: \n [ f swap ] }
58 : (unescape-string) ( accum str i/f -- accum )
59 { sbuf object object } declare
61 cut-slice [ append! ] dip
62 rest-slice next-escape [ [ suffix! ] when* ] dip
63 CHAR: \\ over index (unescape-string)
70 : unescape-string ( str -- str' )
72 [ [ length <sbuf> ] keep ] dip (unescape-string)
77 : lexer-subseq ( i lexer -- before )
78 { fixnum lexer } declare
79 [ [ column>> ] [ line-text>> ] bi swapd subseq ]
82 : rest-of-line ( lexer -- seq )
84 [ line-text>> ] [ column>> ] bi tail-slice ;
86 : current-char ( lexer -- ch/f )
88 [ column>> ] [ line-text>> ] bi ?nth ;
90 : advance-char ( lexer -- )
92 [ 1 + ] change-column drop ;
94 : next-char ( lexer -- ch/f )
96 dup still-parsing-line? [
97 [ current-char ] [ advance-char ] bi
102 : next-line% ( accum lexer -- )
103 { sbuf lexer } declare
104 [ rest-of-line swap push-all ] [ next-line ] bi ;
106 : find-next-token ( lexer -- i elt )
108 [ column>> ] [ line-text>> ] bi
109 [ "\"\\" member-eq? ] find-from ;
111 : check-space ( lexer -- )
112 dup current-char forbid-tab {
113 { CHAR: \s [ advance-char ] }
115 [ "[space]" swap 1string "'" 1surround unexpected ]
118 DEFER: (parse-string)
120 : parse-found-token ( accum lexer i elt -- )
121 { sbuf lexer fixnum fixnum } declare
122 [ over lexer-subseq pick push-all ] dip
124 dup dup [ next-char ] bi@
125 [ [ pick push ] bi@ ]
126 [ drop 2dup next-line% ] if*
128 ] [ dup advance-char check-space drop ] if ;
130 : (parse-string) ( accum lexer -- )
131 { sbuf lexer } declare
133 dup find-next-token [
141 "'\"'" "[eof]" unexpected
146 : parse-string ( -- str )
148 lexer get (parse-string)
149 ] keep unescape-string ;