1 ! Copyright (C) 2008, 2010 Slava Pestov, Joe Groff.
2 ! See http://factorcode.org/license.txt for BSD license.
3 USING: kernel sequences accessors namespaces math words strings
4 io vectors arrays math.parser combinators continuations
8 TUPLE: lexer text line line-text line-length column parsing-words ;
10 TUPLE: lexer-parsing-word word line line-text column ;
12 : next-line ( lexer -- )
13 dup [ line>> ] [ text>> ] bi ?nth
14 [ >>line-text ] [ length >>line-length ] bi
19 : push-parsing-word ( word -- )
20 lexer-parsing-word new
24 [ line-text>> >>line-text ]
25 [ column>> >>column ] tri
26 ] [ parsing-words>> push ] bi ;
28 : pop-parsing-word ( -- )
29 lexer get parsing-words>> pop* ;
31 : new-lexer ( text class -- lexer )
35 V{ } clone >>parsing-words
36 dup next-line ; inline
38 : <lexer> ( text -- lexer )
41 ERROR: unexpected want got ;
43 : forbid-tab ( c -- c )
44 [ CHAR: \t eq? [ "[space]" "[tab]" unexpected ] when ] keep ; inline
46 : skip ( i seq ? -- n )
48 [ [ swap forbid-tab CHAR: \s eq? xor ] curry find-from drop ] dip or ;
50 : change-lexer-column ( lexer quot -- )
51 [ [ column>> ] [ line-text>> ] bi ] prepose keep
54 GENERIC: skip-blank ( lexer -- )
56 M: lexer skip-blank ( lexer -- )
57 [ t skip ] change-lexer-column ;
59 GENERIC: skip-word ( lexer -- )
63 : quote? ( column text -- ? )
64 nth CHAR: " eq? ; inline
66 : shebang? ( column text -- ? )
67 swap zero? [ "#!" head? ] [ drop f ] if ; inline
71 M: lexer skip-word ( lexer -- )
74 { [ 2dup quote? ] [ drop 1 + ] }
75 { [ 2dup shebang? ] [ drop 2 + ] }
78 ] change-lexer-column ;
80 : still-parsing? ( lexer -- ? )
81 [ line>> ] [ text>> length ] bi <= ;
83 : still-parsing-line? ( lexer -- ? )
84 [ column>> ] [ line-length>> ] bi < ;
86 : (parse-token) ( lexer -- str )
94 : parse-token ( lexer -- str/f )
97 dup still-parsing-line?
98 [ (parse-token) ] [ dup next-line parse-token ] if
101 : (scan-token) ( -- str/f ) lexer get parse-token ;
103 PREDICATE: unexpected-eof < unexpected got>> not ;
105 : unexpected-eof ( word -- * ) f unexpected ;
107 : scan-token ( -- str ) (scan-token) [ "token" unexpected-eof ] unless* ;
109 : expect ( token -- )
110 scan-token 2dup = [ 2drop ] [ unexpected ] if ;
112 : each-token ( ... end quot: ( ... token -- ... ) -- ... )
113 [ scan-token ] 2dip 2over =
114 [ 3drop ] [ [ nip call ] [ each-token ] 2bi ] if ; inline recursive
116 : map-tokens ( ... end quot: ( ... token -- ... elt ) -- ... seq )
117 collector [ each-token ] dip { } like ; inline
119 : parse-tokens ( end -- seq )
122 TUPLE: lexer-error line column line-text parsing-words error ;
124 M: lexer-error error-file error>> error-file ;
126 M: lexer-error error-line [ error>> error-line ] [ line>> ] bi or ;
128 : <lexer-error> ( msg -- error )
132 [ column>> >>column ] bi
134 [ line-text>> >>line-text ]
135 [ parsing-words>> clone >>parsing-words ] bi
139 : simple-lexer-dump ( error -- )
140 [ line>> number>string ": " append ]
141 [ line-text>> dup string? [ drop "" ] unless ]
142 [ column>> 0 or ] tri
143 pick length + CHAR: \s <string>
144 [ write ] [ print ] [ write "^" print ] tri* ;
146 : (parsing-word-lexer-dump) ( error parsing-word -- )
149 over line>> number>string length
152 ] [ line-text>> dup string? [ drop "" ] unless print ] bi
155 : parsing-word-lexer-dump ( error parsing-word -- )
156 2dup [ line>> ] same?
157 [ drop simple-lexer-dump ]
158 [ (parsing-word-lexer-dump) ] if ;
160 : lexer-dump ( error -- )
162 [ simple-lexer-dump ]
163 [ last parsing-word-lexer-dump ] if-empty ;
165 : with-lexer ( lexer quot -- newquot )
166 [ lexer set ] dip [ <lexer-error> rethrow ] recover ; inline