Last active
December 17, 2015 01:39
-
-
Save butlermh/5529862 to your computer and use it in GitHub Desktop.
A minimal test case that shows the problem I am encountered parsing quoted strings with regex expressions in Parboiled.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import static org.junit.Assert.*; | |
import static org.parboiled.support.ParseTreeUtils.printNodeTree; | |
import org.junit.Test; | |
import org.parboiled.BaseParser; | |
import org.parboiled.Parboiled; | |
import org.parboiled.Rule; | |
import org.parboiled.annotations.BuildParseTree; | |
import org.parboiled.buffers.IndentDedentInputBuffer; | |
import org.parboiled.errors.ErrorUtils; | |
import org.parboiled.matchers.CharMatcher; | |
import org.parboiled.parserunners.ReportingParseRunner; | |
import org.parboiled.support.ParsingResult; | |
public class MinimalTest { | |
MyDSLParser parser = Parboiled.createParser(MyDSLParser.class); | |
void parse(Rule rule, String input) { | |
ParsingResult<?> result = new ReportingParseRunner(rule) | |
.run(new IndentDedentInputBuffer(input.toCharArray(), 2, ";", | |
true, true)); | |
if (!result.parseErrors.isEmpty()) { | |
System.out.println(ErrorUtils.printParseError(result.parseErrors | |
.get(0))); | |
} else { | |
System.out.println("NodeTree: " + printNodeTree(result) + '\n'); | |
} | |
assertTrue(result.parseErrors.isEmpty()); | |
} | |
// this fails | |
@Test | |
public void testQuotedString() { | |
parse(parser.quotedString(), "\";\""); | |
} | |
} | |
@BuildParseTree | |
class MyDSLParser extends BaseParser<Object> { | |
Rule quotedString() { | |
return Sequence( | |
quote(), | |
stringValue(), | |
quote()); | |
} | |
public Rule stringValue() { | |
return Sequence( | |
ZeroOrMore( | |
FirstOf( | |
semicolon(), | |
escapedQuote(), | |
Sequence(TestNot(quote()), ANY))), | |
push(match())); | |
} | |
public Rule semicolon() { | |
return new CharMatcher(';'); | |
} | |
public Rule escapedQuote() { | |
return Sequence(escape(), quote()); | |
} | |
public Rule quote() { | |
return new CharMatcher('"'); | |
} | |
public Rule escape() { | |
return String("\\"); | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment