Hello
I am writing a xml grammar with xtext. Therefore i am using an external lexer.
My problem appears when starting content assist while inside a RULE_STRING inside a tag. Example:
<sometag someattr="somestring"> </sometag>
pressing ctrl + space inside >"somestring"< will cause a endless loop.
I tryed to investigate why this is happening.
Because i am not allowing rule_pcdata inside tags with my tagMode variable.
this is the function of the lexer.
public final void mRULE_PCDATA() throws RecognitionException {
try {
int _type = RULE_PCDATA;
int _channel = DEFAULT_TOKEN_CHANNEL;
// ../com.groupion.ixml.sdk.xtext/src/com/groupion/ixml/sdk/xtext/lexer/XMLLexer.g:39:13: ({...}? => (~ ( ( '<' | '%' ) ) )+ )
// ../com.groupion.ixml.sdk.xtext/src/com/groupion/ixml/sdk/xtext/lexer/XMLLexer.g:39:15: {...}? => (~ ( ( '<' | '%' ) ) )+
{
if ( !(( !tagMode )) ) {
throw new FailedPredicateException(input, "RULE_PCDATA", " !tagMode ");
}
// ../com.groupion.ixml.sdk.xtext/src/com/groupion/ixml/sdk/xtext/lexer/XMLLexer.g:39:31: (~ ( ( '<' | '%' ) ) )+
int cnt2=0;
loop2:
do {
int alt2=2;
int LA2_0 = input.LA(1);
if ( ((LA2_0>='\u0000' && LA2_0<='$')||(LA2_0>='&' && LA2_0<=';')||(LA2_0>='=' && LA2_0<='\uFFFF')) ) {
alt2=1;
}
switch (alt2) {
case 1 :
// ../com.groupion.ixml.sdk.xtext/src/com/groupion/ixml/sdk/xtext/lexer/XMLLexer.g:39:31: ~ ( ( '<' | '%' ) )
{
if ( (input.LA(1)>='\u0000' && input.LA(1)<='$')||(input.LA(1)>='&' && input.LA(1)<=';')||(input.LA(1)>='=' && input.LA(1)<='\uFFFF') ) {
input.consume();
}
else {
MismatchedSetException mse = new MismatchedSetException(null,input);
recover(mse);
throw mse;}
}
break;
default :
if ( cnt2 >= 1 ) break loop2;
EarlyExitException eee =
new EarlyExitException(2, input);
throw eee;
}
cnt2++;
} while (true);
}
state.type = _type;
state.channel = _channel;
}
finally {
}
}
And the endless loop happening because he runs into the
throw new FailedPredicateException(input, "RULE_PCDATA", " !tagMode ");
and that seam to happen because the current sign is not consumed.
for example simply adding "input.comsumed()" before the exception will be thrown causes the endless loop to disapear.
Am i doing something wrong or might this happen cause of the not completly supported extern lexer / xml grammar. And what would be the best workaround for this problem ?
I am not sure why the predicate is failing anyway.
the rule_pcdata "is not allowed" inside tags and should not be called?
The parsing/lexing without content assist and in all other cases works great!
I added my xtext file and the external lexer.
Thanks for any suggestions.
lexer grammar XMLLexer;
@header {
package com.groupion.ixml.sdk.xtext.lexer;
// Hack: Use our own Lexer superclass by means of import.
// Currently there is no other way to specify the superclass for the lexer.
import org.eclipse.xtext.parser.antlr.Lexer;
}
@members {
boolean tagMode = true;
}
KEYWORD_9 : '<?xml version="1.0" encoding="UTF-8"?>';
KEYWORD_8 : { tagMode }?=> 'DOCTYPE ixml SYSTEM';
KEYWORD_7 : { tagMode }?=> 'ixml';
KEYWORD_4 : { tagMode }?=> '/>' { tagMode = false; } ;
KEYWORD_5 : '<!' { tagMode = true; } ;
KEYWORD_6 : '</' { tagMode = true; } ;
KEYWORD_1 : '<' { tagMode = true; } ;
KEYWORD_2 : { tagMode }?=> '=';
KEYWORD_3 : { tagMode }?=> '>' { tagMode = false; } ;
RULE_TAG_NAME : { tagMode }?=> RULE_ID ':' RULE_ID?;
RULE_PCDATA : { !tagMode }?=> ~(('<'|'%'))+;
RULE_ML_COMMENT : '<!--' ( options {greedy=false;} : . )* '-->';
RULE_IXML_VAR : '%' (RULE_IXML_IDENT ('[' (RULE_IXML_VAR|RULE_IXML_IDENT)? ']'|'.' RULE_IXML_IDENT)*)? '%'?;
fragment RULE_IXML_IDENT : ('a'..'z'|'A'..'Z'|'_'|'0'..'9')+;
RULE_CDATA : '<![CDATA[' ( options {greedy=false;} : . )*']]';
//define rules from org.eclipse.xtext.common.Terminals
RULE_ID : { tagMode }?=> '^'? ('a'..'z'|'A'..'Z'|'_') ('a'..'z'|'A'..'Z'|'_'|'0'..'9')*;
RULE_INT : { tagMode }?=> ('0'..'9')+;
RULE_STRING : { tagMode }?=> ('"' ('\\' ('b'|'t'|'n'|'f'|'r'|'u'|'"'|'\''|'\\')|~(('\\'|'"')))* '"'|'\'' ('\\' ('b'|'t'|'n'|'f'|'r'|'u'|'"'|'\''|'\\')|~(('\\'|'\'')))* '\'');
RULE_SL_COMMENT : '//' ~(('\n'|'\r'))* ('\r'? '\n')?;
RULE_WS : { tagMode }?=> (' '|'\t'|'\r'|'\n')+;
RULE_ANY_OTHER : { tagMode }?=> .;
grammar com.groupion.ixml.sdk.xtext.IXML with org.eclipse.xtext.common.Terminals
generate iXML "my url"
IXML:
'<?xml version="1.0" encoding="UTF-8"?>'
'<!''DOCTYPE ixml SYSTEM' dtdUrl = STRING '>'
// Dirty fix: Allow pcdata to allow whitespaces here
PCDATA
rootTag = RootTag
;
RootTag: {rootContent}
'<' 'ixml' '>'
(content += TagContent)*
'</' 'ixml' '>'
;
Tag:
StdTag | EmptyTag
;
StdTag:
startTag = StartTag
(content += TagContent)*
endTag = EndTag
;
StartTag:
'<' name = TagName WS? attributes += Attribute* '>'
;
EndTag:
'</' name = TagName '>'
;
EmptyTag:
'<' name = TagName WS? attributes += Attribute* '/>'
;
TagContent:
Tag | {pcdata} PCDATA | {ixml_var} IXML_VAR | {cdata} CDATA
;
Attribute:
name = ID '=' (value = STRING) WS?
;
TagName:
ID | TAG_NAME
;
terminal TAG_NAME:
ID':'ID?
;
terminal PCDATA:
!('<'|'%')+
;
/*
* change default comment to html comments
*/
terminal ML_COMMENT :
'<!--' -> '-->'
;
terminal fragment IXML_IDENT :
('a'..'z'|'A'..'Z'|'_'|'0'..'9')+
;
terminal IXML_VAR :
'%'(IXML_IDENT( '[' (IXML_VAR | IXML_IDENT)? ']' | '.'IXML_IDENT )*)?'%'?
;
terminal CDATA:
'<![CDATA[' -> ']]'
;
] 
Search
Help
Register
Login
Home
