Created
July 19, 2011 17:00
-
-
Save sidharthkuruvila/1093078 to your computer and use it in GitHub Desktop.
Scala Traversable for jena's TurtleParser
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 com.hp.hpl.jena.{ n3, graph } | |
import n3.turtle.TurtleEventHandler | |
import n3.turtle.parser.TurtleParser | |
import graph.Triple | |
import java.io.Reader | |
/** | |
* Wrapper to convert a TurtleParser into a Traversable | |
*/ | |
class NTripleTraversable(parser:TurtleParser, inputFileName: String) extends Traversable[Triple] { | |
def this(reader: Reader, inputFileName: String){ | |
this(new BadUrlsTurtleParser(reader), inputFileName) | |
} | |
def foreach[U](f: Triple => U): Unit = { | |
val extractor = new TurtleEventHandler { | |
def triple(line: Int, col: Int, triple: Triple) = f(triple) | |
def prefix(line: Int, col: Int, prefix: String, iri: String) = ni | |
def startFormula(line: Int, col: Int) = ni | |
def endFormula(line: Int, col: Int) = ni | |
private def ni = throw new RuntimeException("Not implemented"); | |
} | |
parser.setEventHandler(extractor) | |
parser.setBaseURI("file:///" + inputFileName) | |
parser.parse() | |
} | |
} | |
/** | |
* A turtle parser that does not throw TurtleParseExceptions when it comes | |
* across malformed urls | |
*/ | |
class BadUrlsTurtleParser(reader: Reader) extends TurtleParser(reader) { | |
override def resolveIRI(iriStr: String, line: Int, column: Int): String = { | |
try { | |
super.resolveIRI(iriStr, line, column) | |
} catch { | |
case ex: com.hp.hpl.jena.n3.turtle.TurtleParseException => { | |
println("bad iri:" + iriStr) | |
iriStr | |
} | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment