1 ! Copyright (C) 2007, 2009 Slava Pestov.
2 ! See http://factorcode.org/license.txt for BSD license.
3 USING: accessors arrays assocs combinators kernel lexer make
4 namespaces parser sequences splitting xml.data xml.syntax
5 xml.syntax.private xml.traversal xml.traversal.private
6 xmode.rules xmode.tokens xmode.utilities ;
7 IN: xmode.loader.syntax
9 ! Rule tag parsing utilities
10 : (parse-rule-tag) ( rule-set tag specs class -- )
11 new swap init-from-tag swap add-rule ; inline
14 scan-token scan-word scan-word [
15 [ parse-definition call( -- ) ] { } make
16 swap [ (parse-rule-tag) ] 2curry
17 ] dip swap define-tag ;
20 : string>boolean ( string -- ? ) "TRUE" = ;
22 : string>match-type ( string -- obj )
29 : string>rule-set-name ( string -- name ) "MAIN" or ;
31 : cdata>string ( tag -- string )
32 children>> [ dup cdata? [ text>> ] when ] map (children>string) ;
35 : parse-prop-tag ( tag -- key value )
36 [ "NAME" attr ] [ "VALUE" attr ] bi ;
38 : parse-props-tag ( tag -- assoc )
39 children-tags [ parse-prop-tag ] H{ } map>assoc ;
41 : position-attrs ( tag -- at-line-start? at-whitespace-end? at-word-start? )
43 { "AT_LINE_START" "AT_WHITESPACE_END" "AT_WORD_START" }
44 [ attr string>boolean ] with map first3 ;
46 : parse-literal-matcher ( tag -- matcher )
48 rule-set get ignore-case?>> <string-matcher>
49 swap position-attrs <matcher> ;
51 : parse-regexp-matcher ( tag -- matcher )
53 rule-set get ignore-case?>> <?insensitive-regexp>
54 swap position-attrs <matcher> ;
56 : shared-tag-attrs ( -- )
57 { "TYPE" string>token body-token<< } , ; inline
59 : parse-delegate ( string -- pair )
60 "::" split1 [ rule-set get swap ] unless* 2array ;
62 : delegate-attr ( -- )
63 { "DELEGATE" f delegate<< } , ;
65 ! XXX: check HASH_CHAR for full prefix, not just first character
67 : char<< ( value object -- )
68 [ ?first ] dip chars<< ;
71 { "HASH_CHAR" f char<< } ,
72 { "HASH_CHARS" f chars<< } , ;
74 : match-type-attr ( -- )
75 { "MATCH_TYPE" string>match-type match-token<< } , ;
77 : string>escape ( str -- escape/f )
78 [ f ] [ <escape-rule> ] if-empty ;
81 { "NO_LINE_BREAK" string>boolean no-line-break?<< } ,
82 { "NO_WORD_BREAK" string>boolean no-word-break?<< } ,
83 { "ESCAPE" string>escape escape-rule<< } , ;
85 : literal-start ( -- )
86 [ parse-literal-matcher >>start drop ] , ;
89 [ parse-regexp-matcher >>start drop ] , ;
92 [ parse-literal-matcher >>end drop ] , ;
94 TAGS: parse-begin/end-tag ( rule tag -- )
96 TAG: BEGIN parse-begin/end-tag
97 parse-literal-matcher >>start drop ;
99 TAG: END parse-begin/end-tag
100 parse-literal-matcher >>end drop ;
102 : parse-begin/end-tags ( -- )
103 [ children-tags [ parse-begin/end-tag ] with each ] , ;
105 TAGS: parse-regexp-begin/end-tag ( rule tag -- )
107 TAG: BEGIN parse-regexp-begin/end-tag
108 parse-regexp-matcher >>start drop ;
110 ! XXX: END AT_WHITESPACE_END="TRUE"?
112 TAG: END parse-regexp-begin/end-tag
113 dup "REGEXP" attr string>boolean
114 [ parse-regexp-matcher ] [ parse-literal-matcher ] if >>end drop ;
116 : parse-regexp-begin/end-tags ( -- )
117 [ children-tags [ parse-regexp-begin/end-tag ] with each ] , ;
119 : init-span-tag ( -- ) [ drop init-span ] , ;
121 : init-eol-span-tag ( -- ) [ drop init-eol-span ] , ;
123 : parse-keyword-tag ( tag keyword-map -- )
124 [ dup main>> string>token swap cdata>string ] dip set-at ;