webtranslateit-hpricot 0.9.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +15 -0
- data/CHANGELOG +122 -0
- data/COPYING +18 -0
- data/README.md +295 -0
- data/Rakefile +237 -0
- data/ext/fast_xs/FastXsService.java +1123 -0
- data/ext/fast_xs/extconf.rb +4 -0
- data/ext/fast_xs/fast_xs.c +210 -0
- data/ext/hpricot_scan/HpricotCss.java +850 -0
- data/ext/hpricot_scan/HpricotScanService.java +2085 -0
- data/ext/hpricot_scan/MANIFEST +0 -0
- data/ext/hpricot_scan/extconf.rb +9 -0
- data/ext/hpricot_scan/hpricot_common.rl +76 -0
- data/ext/hpricot_scan/hpricot_css.c +3511 -0
- data/ext/hpricot_scan/hpricot_css.java.rl +155 -0
- data/ext/hpricot_scan/hpricot_css.rl +120 -0
- data/ext/hpricot_scan/hpricot_scan.c +6848 -0
- data/ext/hpricot_scan/hpricot_scan.h +79 -0
- data/ext/hpricot_scan/hpricot_scan.java.rl +1173 -0
- data/ext/hpricot_scan/hpricot_scan.rl +911 -0
- data/extras/hpricot.png +0 -0
- data/hpricot.gemspec +18 -0
- data/lib/hpricot/blankslate.rb +63 -0
- data/lib/hpricot/builder.rb +217 -0
- data/lib/hpricot/elements.rb +514 -0
- data/lib/hpricot/htmlinfo.rb +691 -0
- data/lib/hpricot/inspect.rb +103 -0
- data/lib/hpricot/modules.rb +40 -0
- data/lib/hpricot/parse.rb +38 -0
- data/lib/hpricot/tag.rb +219 -0
- data/lib/hpricot/tags.rb +164 -0
- data/lib/hpricot/traverse.rb +839 -0
- data/lib/hpricot/xchar.rb +95 -0
- data/lib/hpricot.rb +26 -0
- data/setup.rb +1585 -0
- data/test/files/basic.xhtml +17 -0
- data/test/files/boingboing.html +2266 -0
- data/test/files/cy0.html +3653 -0
- data/test/files/immob.html +400 -0
- data/test/files/pace_application.html +1320 -0
- data/test/files/tenderlove.html +16 -0
- data/test/files/uswebgen.html +220 -0
- data/test/files/utf8.html +1054 -0
- data/test/files/week9.html +1723 -0
- data/test/files/why.xml +19 -0
- data/test/load_files.rb +7 -0
- data/test/nokogiri-bench.rb +64 -0
- data/test/test_alter.rb +96 -0
- data/test/test_builder.rb +37 -0
- data/test/test_parser.rb +496 -0
- data/test/test_paths.rb +25 -0
- data/test/test_preserved.rb +88 -0
- data/test/test_xml.rb +28 -0
- metadata +106 -0
File without changes
|
@@ -0,0 +1,76 @@
|
|
1
|
+
%%{
|
2
|
+
|
3
|
+
machine hpricot_common;
|
4
|
+
|
5
|
+
#
|
6
|
+
# HTML tokens
|
7
|
+
# (a blatant rip from HTree)
|
8
|
+
#
|
9
|
+
newline = '\n' @{curline += 1;} ;
|
10
|
+
NameChar = [\-A-Za-z0-9._:?] ;
|
11
|
+
Name = [A-Za-z_:] NameChar* ;
|
12
|
+
StartComment = "<!--" ;
|
13
|
+
EndComment = "-->" ;
|
14
|
+
StartCdata = "<![CDATA[" ;
|
15
|
+
EndCdata = "]]>" ;
|
16
|
+
|
17
|
+
NameCap = Name >_tag %tag;
|
18
|
+
NameAttr = NameChar+ >_akey %akey ;
|
19
|
+
Q1Char = [^'] ;
|
20
|
+
Q1Attr = Q1Char* >_aval %aval ;
|
21
|
+
Q2Char = [^"] ;
|
22
|
+
Q2Attr = Q2Char* >_aval %aval ;
|
23
|
+
UnqAttr = ( space >_aval | [^ \t\r\n<>"'] >_aval [^ \t\r\n<>]* %aunq ) ;
|
24
|
+
Nmtoken = NameChar+ >_akey %akey ;
|
25
|
+
|
26
|
+
Attr = NameAttr space* "=" space* ('"' Q2Attr '"' | "'" Q1Attr "'" | UnqAttr space+ ) space* ;
|
27
|
+
AttrEnd = ( NameAttr space* "=" space* UnqAttr? | Nmtoken >new_attr %save_attr ) ;
|
28
|
+
AttrSet = ( Attr >new_attr %save_attr | Nmtoken >new_attr space+ %save_attr ) ;
|
29
|
+
StartTag = "<" NameCap space+ AttrSet* (AttrEnd >new_attr %save_attr)? ">" | "<" NameCap ">";
|
30
|
+
EmptyTag = "<" NameCap space+ AttrSet* (AttrEnd >new_attr %save_attr)? "/>" | "<" NameCap "/>" ;
|
31
|
+
|
32
|
+
EndTag = "</" NameCap space* ">" ;
|
33
|
+
XmlVersionNum = [a-zA-Z0-9_.:\-]+ >_aval %xmlver ;
|
34
|
+
XmlVersionInfo = space+ "version" space* "=" space* ("'" XmlVersionNum "'" | '"' XmlVersionNum '"' ) ;
|
35
|
+
XmlEncName = [A-Za-z] >_aval [A-Za-z0-9._\-]* %xmlenc ;
|
36
|
+
XmlEncodingDecl = space+ "encoding" space* "=" space* ("'" XmlEncName "'" | '"' XmlEncName '"' ) ;
|
37
|
+
XmlYesNo = ("yes" | "no") >_aval %xmlsd ;
|
38
|
+
XmlSDDecl = space+ "standalone" space* "=" space* ("'" XmlYesNo "'" | '"' XmlYesNo '"') ;
|
39
|
+
XmlDecl = "<?xml" XmlVersionInfo XmlEncodingDecl? XmlSDDecl? space* "?"? ">" ;
|
40
|
+
|
41
|
+
SystemLiteral = '"' [^"]* >_aval %sysid '"' | "'" [^']* >_aval %sysid "'" ;
|
42
|
+
PubidLiteral = '"' [\t a-zA-Z0-9\-'()+,./:=?;!*\#@$_%]* >_aval %pubid '"' |
|
43
|
+
"'" [\t a-zA-Z0-9\-'()+,./:=?;!*\#@$_%]* >_aval %pubid "'" ;
|
44
|
+
ExternalID = ( "SYSTEM" | "PUBLIC" space+ PubidLiteral ) (space+ SystemLiteral)? ;
|
45
|
+
DocType = "<!DOCTYPE" space+ NameCap (space+ ExternalID)? space* ("[" [^\]]* "]" space*)? ">" ;
|
46
|
+
StartXmlProcIns = "<?" Name >{ TEXT_PASS(); } space+ ;
|
47
|
+
EndXmlProcIns = "?"? ">" ;
|
48
|
+
|
49
|
+
html_comment := |*
|
50
|
+
EndComment @{ EBLK(comment, 3); fgoto main; };
|
51
|
+
any | newline { TEXT_PASS(); };
|
52
|
+
*|;
|
53
|
+
|
54
|
+
html_cdata := |*
|
55
|
+
EndCdata @{ EBLK(cdata, 3); fgoto main; };
|
56
|
+
any | newline { TEXT_PASS(); };
|
57
|
+
*|;
|
58
|
+
|
59
|
+
html_procins := |*
|
60
|
+
EndXmlProcIns @{ EBLK(procins, 2); fgoto main; };
|
61
|
+
any | newline { TEXT_PASS(); };
|
62
|
+
*|;
|
63
|
+
|
64
|
+
main := |*
|
65
|
+
XmlDecl >newEle { ELE(xmldecl); };
|
66
|
+
DocType >newEle { ELE(doctype); };
|
67
|
+
StartXmlProcIns >newEle { fgoto html_procins; };
|
68
|
+
StartTag >newEle { ELE(stag); };
|
69
|
+
EndTag >newEle { ELE(etag); };
|
70
|
+
EmptyTag >newEle { ELE(emptytag); };
|
71
|
+
StartComment >newEle { fgoto html_comment; };
|
72
|
+
StartCdata >newEle { fgoto html_cdata; };
|
73
|
+
any | newline { TEXT_PASS(); };
|
74
|
+
*|;
|
75
|
+
|
76
|
+
}%%;
|