/** Create a tokenizer for a line * @param line * Content * @return Tokenizer */ protected Tokenizer getTokenizer(String line) { return TokenizerFactory.makeTokenizerString(line); }
protected Tokenizer makeTokenizer(InputStream in) { Tokenizer tokenizer = TokenizerFactory.makeTokenizerUTF8(in) ; return tokenizer ; }
/** Create a parser for N-Triples * @deprecated use an RDFDataMgr operation with argument Lang.NTRIPLES */ @Deprecated public static LangNTriples createParserNTriples(InputStream input, StreamRDF dest) { Tokenizer tokenizer = TokenizerFactory.makeTokenizerASCII(input) ; return createParserNTriples(tokenizer, dest) ; }
static protected Tokenizer tokenizer(CharSpace charSpace, String string) { byte b[] = StrUtils.asUTF8bytes(string); ByteArrayInputStream in = new ByteArrayInputStream(b); Tokenizer tokenizer = charSpace == CharSpace.ASCII ? TokenizerFactory.makeTokenizerASCII(in) : TokenizerFactory.makeTokenizerUTF8(in); return tokenizer; }
/** Create a parser */ public static LangRIOT createParser(Reader input, Lang lang, String baseIRI, StreamRDF dest) { if ( lang == RDFXML ) { if ( baseIRI != null ) baseIRI = IRIResolver.resolveString(baseIRI) ; return LangRDFXML.create(input, baseIRI, baseIRI, ErrorHandlerFactory.getDefaultErrorHandler(), dest) ; } Tokenizer tokenizer = ( lang == RDFJSON ) ? new TokenizerJSON(PeekReader.make(input)) : TokenizerFactory.makeTokenizer(input) ; return createParser(tokenizer, lang, baseIRI, dest) ; }
/** Reader input */ public static LangRIOT createParser(Reader input, Lang lang, StreamRDF dest, ParserProfile profile) { if ( RDFLanguages.sameLang(RDFJSON, lang) ) { Tokenizer tokenizer = new TokenizerJSON(PeekReader.make(input)); return createParserRdfJson(tokenizer, dest, profile); } @SuppressWarnings("deprecation") Tokenizer tokenizer = TokenizerFactory.makeTokenizer(input); if ( RDFLanguages.sameLang(TURTLE, lang) || RDFLanguages.sameLang(N3, lang) ) return createParserTurtle(tokenizer, dest, profile); if ( RDFLanguages.sameLang(NTRIPLES, lang) ) return createParserNTriples(tokenizer, dest, profile); if ( RDFLanguages.sameLang(NQUADS, lang) ) return createParserNQuads(tokenizer, dest, profile); if ( RDFLanguages.sameLang(TRIG, lang) ) return createParserTriG(tokenizer, dest, profile); return null; }
/** Create a tokenizer for a line * @param line * Content * @return Tokenizer */ protected Tokenizer getTokenizer(String line) { return TokenizerFactory.makeTokenizerString(line); }
protected Tokenizer makeTokenizer(InputStream in) { Tokenizer tokenizer = TokenizerFactory.makeTokenizerUTF8(in) ; return tokenizer ; }
public static Tokenizer makeTokenizerASCII(String string) { byte b[] = StrUtils.asUTF8bytes(string) ; ByteArrayInputStream in = new ByteArrayInputStream(b) ; return makeTokenizerASCII(in) ; }
/** * Parse a string into a stream of Quads. * @param line the line of text * @return the Quad */ public static Stream<Quad> parseQuad(final String line) { final List<Token> tokens = new ArrayList<>(); makeTokenizerString(line).forEachRemaining(tokens::add); final List<Node> nodes = tokens.stream().filter(Token::isNode).map(Token::asNode).filter(Objects::nonNull) .collect(toList()); if (nodes.size() == 3) { return of(rdf.asQuad(create(defaultGraphIRI, nodes.get(0), nodes.get(1), nodes.get(2)))); } else if (nodes.size() == 4) { return of(rdf.asQuad(create(nodes.get(3), nodes.get(0), nodes.get(1), nodes.get(2)))); } else { LOGGER.warn("Skipping invalid data value: {}", line); return empty(); } }
public BindingInputStream(InputStream in) { this(TokenizerFactory.makeTokenizerUTF8(in)) ; }
/** Create a parser for NQuads * @deprecated use an RDFDataMgr operation with argument Lang.NQUADS) */ @Deprecated public static LangNQuads createParserNQuads(InputStream input, StreamRDF dest) { Tokenizer tokenizer = TokenizerFactory.makeTokenizerASCII(input) ; return createParserNQuads(tokenizer, dest) ; }
/** Parse a string to get one Node (the first token in the string) */ public static Node parse(String string) { Tokenizer tokenizer = TokenizerFactory.makeTokenizerString(string); if ( ! tokenizer.hasNext() ) return null; Token t = tokenizer.next(); Node n = profile.create(null, t); if ( tokenizer.hasNext() ) Log.warn(RiotLib.class, "String has more than one token in it: "+string); return n; }
protected Tokenizer makeTokenizer(InputStream in) { Tokenizer tokenizer = TokenizerFactory.makeTokenizerUTF8(in) ; return tokenizer ; }
/** Create a parser for N-Triples, with default behaviour */ public static LangNTriples createParserNTriples(InputStream input, StreamRDF dest) { Tokenizer tokenizer = TokenizerFactory.makeTokenizerASCII(input) ; return createParserNTriples(tokenizer, dest) ; }
/** Parse a string to get one Node (the first token in the string) */ public static Node parse(String string) { Tokenizer tokenizer = TokenizerFactory.makeTokenizerString(string) ; if ( ! tokenizer.hasNext() ) return null ; Token t = tokenizer.next(); Node n = profile.create(null, t) ; if ( tokenizer.hasNext() ) Log.warn(RiotLib.class, "String has more than one token in it: "+string) ; return n ; }
public BindingInputStream(InputStream in) { this(TokenizerFactory.makeTokenizerUTF8(in)) ; }
public static Tokenizer makeTokenizerASCII(String string) { byte b[] = StrUtils.asUTF8bytes(string) ; ByteArrayInputStream in = new ByteArrayInputStream(b) ; return makeTokenizerASCII(in) ; }
/** * Convert a "modified" header field into an Instant * @param line the line * @return the instant */ private static Instant modifiedToInstant(final String line) { final Tokenizer tokenizer = makeTokenizerString(line); try { tokenizer.next(); // H tokenizer.next(); // modified if (tokenizer.hasNext()) { final Node n = tokenizer.next().asNode(); if (nonNull(n) && n.isLiteral()) { return parse(n.getLiteralLexicalForm()); } } } finally { tokenizer.close(); } return null; }
/** Create an iterator for parsing N-Quads. */ public static Iterator<Quad> createIteratorNQuads(InputStream input, StreamRDF dest, ParserProfile profile) { // LangNQuads supports iterator use. Tokenizer tokenizer = TokenizerFactory.makeTokenizerUTF8(input); return createParserNQuads(tokenizer, null, profile); } }