http://git-wip-us.apache.org/repos/asf/jena/blob/49c4cffe/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/AbstractLineBasedNodeTupleReader.java ---------------------------------------------------------------------- diff --git a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/AbstractLineBasedNodeTupleReader.java b/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/AbstractLineBasedNodeTupleReader.java deleted file mode 100644 index 6c1abe9..0000000 --- a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/AbstractLineBasedNodeTupleReader.java +++ /dev/null @@ -1,265 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one - * or more contributor license agreements. See the NOTICE file - * distributed with this work for additional information - * regarding copyright ownership. The ASF licenses this file - * to you under the Apache License, Version 2.0 (the - * "License"); you may not use this file except in compliance - * with the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.jena.hadoop.rdf.io.input.readers; - -import java.io.IOException; -import java.util.Iterator; -import org.apache.hadoop.conf.Configuration; -import org.apache.hadoop.fs.FSDataInputStream; -import org.apache.hadoop.fs.FileSystem; -import org.apache.hadoop.fs.Path; -import org.apache.hadoop.io.LongWritable; -import org.apache.hadoop.io.Text; -import org.apache.hadoop.io.compress.CompressionCodec; -import org.apache.hadoop.io.compress.CompressionCodecFactory; -import org.apache.hadoop.mapreduce.InputSplit; -import org.apache.hadoop.mapreduce.RecordReader; -import org.apache.hadoop.mapreduce.TaskAttemptContext; -import org.apache.hadoop.mapreduce.lib.input.FileSplit; -import org.apache.hadoop.util.LineReader; -import org.apache.jena.hadoop.rdf.io.HadoopIOConstants; -import org.apache.jena.hadoop.rdf.io.RdfIOConstants; -import org.apache.jena.hadoop.rdf.io.input.util.RdfIOUtils; -import org.apache.jena.hadoop.rdf.types.AbstractNodeTupleWritable; -import org.apache.jena.riot.system.ParserProfile; -import org.slf4j.Logger; -import org.slf4j.LoggerFactory; - -/** - * An abstract implementation of a record reader that reads records from line - * based tuple formats. This only supports reading from file splits currently. - * <p> - * The keys produced are the position of the line in the file and the values - * will be node tuples - * </p> - * - * - * - * @param <TValue> - * @param <T> - * Writable tuple type - */ -public abstract class AbstractLineBasedNodeTupleReader<TValue, T extends AbstractNodeTupleWritable<TValue>> extends RecordReader<LongWritable, T> { - - private static final Logger LOG = LoggerFactory.getLogger(AbstractLineBasedNodeTupleReader.class); - private CompressionCodecFactory compressionCodecs = null; - private long start, pos, end, estLength; - private int maxLineLength; - private LineReader in; - private LongWritable key = null; - private Text value = null; - private T tuple = null; - private ParserProfile profile = null; - private boolean ignoreBadTuples = true; - - @Override - public final void initialize(InputSplit genericSplit, TaskAttemptContext context) throws IOException, InterruptedException { - LOG.debug("initialize({}, {})", genericSplit, context); - - // Assuming file split - if (!(genericSplit instanceof FileSplit)) - throw new IOException("This record reader only supports FileSplit inputs"); - FileSplit split = (FileSplit) genericSplit; - - // Configuration - profile = RdfIOUtils.createParserProfile(context, split.getPath()); - Configuration config = context.getConfiguration(); - this.ignoreBadTuples = config.getBoolean(RdfIOConstants.INPUT_IGNORE_BAD_TUPLES, true); - if (this.ignoreBadTuples) - LOG.warn( - "Configured to ignore bad tuples, parsing errors will be logged and the bad line skipped but no errors will be thrownConsider setting {} to false to disable this behaviour", - RdfIOConstants.INPUT_IGNORE_BAD_TUPLES); - - // Figure out what portion of the file to read - this.maxLineLength = config.getInt(HadoopIOConstants.MAX_LINE_LENGTH, Integer.MAX_VALUE); - start = split.getStart(); - end = start + split.getLength(); - final Path file = split.getPath(); - long totalLength = file.getFileSystem(context.getConfiguration()).getFileStatus(file).getLen(); - compressionCodecs = new CompressionCodecFactory(config); - final CompressionCodec codec = compressionCodecs.getCodec(file); - - LOG.info(String.format("Got split with start %d and length %d for file with total length of %d", new Object[] { start, split.getLength(), totalLength })); - - // Open the file and seek to the start of the split - FileSystem fs = file.getFileSystem(config); - FSDataInputStream fileIn = fs.open(file); - boolean skipFirstLine = false; - if (codec != null) { - // Compressed input - // For compressed input NLineInputFormat will have failed to find - // any line breaks and will give us a split from 0 -> (length - 1) - // Add 1 and verify we got complete split - if (totalLength > split.getLength() + 1) - throw new IOException("This record reader can only be used with compressed input where the split covers the whole file"); - in = new LineReader(codec.createInputStream(fileIn), config); - estLength = end; - end = Long.MAX_VALUE; - } else { - // Uncompressed input - if (start != 0) { - skipFirstLine = true; - --start; - fileIn.seek(start); - } - in = new LineReader(fileIn, config); - } - // Skip first line and re-establish "start". - // This is to do with how line reader reads lines and how - // NLineInputFormat will provide the split information to use - if (skipFirstLine) { - start += in.readLine(new Text(), 0, (int) Math.min((long) Integer.MAX_VALUE, end - start)); - } - this.pos = start; - } - - /** - * Gets an iterator over the data on the current line - * - * @param line - * Line - * @param profile - * Parser profile - * @return Iterator - */ - protected abstract Iterator<TValue> getIterator(String line, ParserProfile profile); - - /** - * Creates an instance of a writable tuple from the given tuple value - * - * @param tuple - * Tuple value - * @return Writable tuple - */ - protected abstract T createInstance(TValue tuple); - - @Override - public final boolean nextKeyValue() throws IOException, InterruptedException { - // Reuse key for efficiency - if (key == null) { - key = new LongWritable(); - } - - // Reset value which we use for reading lines - if (value == null) { - value = new Text(); - } - tuple = null; - - // Try to read the next valid line - int newSize = 0; - while (pos < end) { - // Read next line - newSize = in.readLine(value, maxLineLength, Math.max((int) Math.min(Integer.MAX_VALUE, end - pos), maxLineLength)); - - // Once we get an empty line we've reached the end of our input - if (newSize == 0) { - break; - } - - // Update position, remember that where inputs are compressed we may - // be at a larger position then we expected because the length of - // the split is likely less than the length of the data once - // decompressed - key.set(pos); - pos += newSize; - if (pos > estLength) - estLength = pos + 1; - - // Skip lines that exceed the line length limit that has been set - if (newSize >= maxLineLength) { - LOG.warn("Skipped oversized line of size {} at position {}", newSize, (pos - newSize)); - continue; - } - - // Attempt to read the tuple from current line - try { - Iterator<TValue> iter = this.getIterator(value.toString(), profile); - if (iter.hasNext()) { - tuple = this.createInstance(iter.next()); - - // If we reach here we've found a valid tuple so we can - // break out of the loop - break; - } else { - // Empty line/Comment line - LOG.debug("Valid line with no triple at position {}", (pos - newSize)); - continue; - } - } catch (Throwable e) { - // Failed to read the tuple on this line - LOG.error("Bad tuple at position " + (pos - newSize), e); - if (this.ignoreBadTuples) - continue; - throw new IOException(String.format("Bad tuple at position %d", (pos - newSize)), e); - } - } - boolean result = this.tuple != null; - - // End of input - if (newSize == 0) { - key = null; - value = null; - tuple = null; - result = false; - estLength = pos; - } - LOG.debug("nextKeyValue() --> {}", result); - return result; - } - - @Override - public LongWritable getCurrentKey() throws IOException, InterruptedException { - LOG.debug("getCurrentKey() --> {}", key); - return key; - } - - @Override - public T getCurrentValue() throws IOException, InterruptedException { - LOG.debug("getCurrentValue() --> {}", tuple); - return tuple; - } - - @Override - public float getProgress() throws IOException, InterruptedException { - float progress = 0.0f; - if (start != end) { - if (end == Long.MAX_VALUE) { - if (estLength == 0) - return 1.0f; - // Use estimated length - progress = Math.min(1.0f, (pos - start) / (float) (estLength - start)); - } else { - // Use actual length - progress = Math.min(1.0f, (pos - start) / (float) (end - start)); - } - } - LOG.debug("getProgress() --> {}", progress); - return progress; - } - - @Override - public void close() throws IOException { - LOG.debug("close()"); - if (in != null) { - in.close(); - } - } - -} \ No newline at end of file
http://git-wip-us.apache.org/repos/asf/jena/blob/49c4cffe/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/AbstractLineBasedQuadReader.java ---------------------------------------------------------------------- diff --git a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/AbstractLineBasedQuadReader.java b/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/AbstractLineBasedQuadReader.java deleted file mode 100644 index ac93865..0000000 --- a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/AbstractLineBasedQuadReader.java +++ /dev/null @@ -1,50 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one - * or more contributor license agreements. See the NOTICE file - * distributed with this work for additional information - * regarding copyright ownership. The ASF licenses this file - * to you under the Apache License, Version 2.0 (the - * "License"); you may not use this file except in compliance - * with the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.jena.hadoop.rdf.io.input.readers; - -import java.util.Iterator; - -import org.apache.jena.hadoop.rdf.types.QuadWritable; -import org.apache.jena.riot.system.ParserProfile; -import org.apache.jena.riot.tokens.Tokenizer; -import com.hp.hpl.jena.sparql.core.Quad; - -/** - * An abstract reader for line based quad formats - * - * - * - */ -public abstract class AbstractLineBasedQuadReader extends AbstractLineBasedNodeTupleReader<Quad, QuadWritable> { - - @Override - protected Iterator<Quad> getIterator(String line, ParserProfile profile) { - Tokenizer tokenizer = getTokenizer(line); - return getQuadsIterator(tokenizer, profile); - } - - @Override - protected QuadWritable createInstance(Quad q) { - return new QuadWritable(q); - } - - protected abstract Tokenizer getTokenizer(String line); - - protected abstract Iterator<Quad> getQuadsIterator(Tokenizer tokenizer, ParserProfile profile); -} http://git-wip-us.apache.org/repos/asf/jena/blob/49c4cffe/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/AbstractLineBasedTripleReader.java ---------------------------------------------------------------------- diff --git a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/AbstractLineBasedTripleReader.java b/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/AbstractLineBasedTripleReader.java deleted file mode 100644 index a0232f5..0000000 --- a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/AbstractLineBasedTripleReader.java +++ /dev/null @@ -1,51 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one - * or more contributor license agreements. See the NOTICE file - * distributed with this work for additional information - * regarding copyright ownership. The ASF licenses this file - * to you under the Apache License, Version 2.0 (the - * "License"); you may not use this file except in compliance - * with the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.jena.hadoop.rdf.io.input.readers; - -import java.util.Iterator; - -import org.apache.jena.hadoop.rdf.types.TripleWritable; -import org.apache.jena.riot.system.ParserProfile; -import org.apache.jena.riot.tokens.Tokenizer; -import com.hp.hpl.jena.graph.Triple; - -/** - * An abstract record reader for line based triple formats - * - * - * - */ -public abstract class AbstractLineBasedTripleReader extends AbstractLineBasedNodeTupleReader<Triple, TripleWritable> { - - @Override - protected Iterator<Triple> getIterator(String line, ParserProfile profile) { - Tokenizer tokenizer = getTokenizer(line); - return getTriplesIterator(tokenizer, profile); - } - - @Override - protected TripleWritable createInstance(Triple t) { - return new TripleWritable(t); - } - - protected abstract Tokenizer getTokenizer(String line); - - protected abstract Iterator<Triple> getTriplesIterator(Tokenizer tokenizer, ParserProfile profile); - -} http://git-wip-us.apache.org/repos/asf/jena/blob/49c4cffe/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/AbstractRdfReader.java ---------------------------------------------------------------------- diff --git a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/AbstractRdfReader.java b/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/AbstractRdfReader.java deleted file mode 100644 index d0ffed8..0000000 --- a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/AbstractRdfReader.java +++ /dev/null @@ -1,108 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one - * or more contributor license agreements. See the NOTICE file - * distributed with this work for additional information - * regarding copyright ownership. The ASF licenses this file - * to you under the Apache License, Version 2.0 (the - * "License"); you may not use this file except in compliance - * with the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.jena.hadoop.rdf.io.input.readers; - -import java.io.IOException; - -import org.apache.hadoop.fs.Path; -import org.apache.hadoop.io.LongWritable; -import org.apache.hadoop.mapreduce.InputSplit; -import org.apache.hadoop.mapreduce.RecordReader; -import org.apache.hadoop.mapreduce.TaskAttemptContext; -import org.apache.hadoop.mapreduce.lib.input.FileSplit; -import org.apache.jena.hadoop.rdf.types.AbstractNodeTupleWritable; -import org.apache.jena.riot.Lang; -import org.apache.jena.riot.RDFLanguages; -import org.slf4j.Logger; -import org.slf4j.LoggerFactory; - -/** - * An abstract record reader for arbitrary RDF which provides support for - * selecting the actual record reader to use based on detecting the RDF language - * from the file name - * - * @param <TValue> - * Tuple type - * @param <T> - * Writable tuple type - */ -public abstract class AbstractRdfReader<TValue, T extends AbstractNodeTupleWritable<TValue>> extends - RecordReader<LongWritable, T> { - private static final Logger LOG = LoggerFactory.getLogger(AbstractRdfReader.class); - - private RecordReader<LongWritable, T> reader; - - @Override - public void initialize(InputSplit genericSplit, TaskAttemptContext context) throws IOException, - InterruptedException { - LOG.debug("initialize({}, {})", genericSplit, context); - - // Assuming file split - if (!(genericSplit instanceof FileSplit)) - throw new IOException("This record reader only supports FileSplit inputs"); - - // Find RDF language - FileSplit split = (FileSplit) genericSplit; - Path path = split.getPath(); - Lang lang = RDFLanguages.filenameToLang(path.getName()); - if (lang == null) - throw new IOException("There is no registered RDF language for the input file " + path.toString()); - - // Select the record reader and initialize - this.reader = this.selectRecordReader(lang); - this.reader.initialize(split, context); - } - - /** - * Selects the appropriate record reader to use for the given RDF language - * - * @param lang - * RDF language - * @return Record reader - * @throws IOException - * Should be thrown if no record reader can be selected - */ - protected abstract RecordReader<LongWritable, T> selectRecordReader(Lang lang) throws IOException; - - @Override - public final boolean nextKeyValue() throws IOException, InterruptedException { - return this.reader.nextKeyValue(); - } - - @Override - public final LongWritable getCurrentKey() throws IOException, InterruptedException { - return this.reader.getCurrentKey(); - } - - @Override - public final T getCurrentValue() throws IOException, InterruptedException { - return this.reader.getCurrentValue(); - } - - @Override - public final float getProgress() throws IOException, InterruptedException { - return this.reader.getProgress(); - } - - @Override - public final void close() throws IOException { - this.reader.close(); - } - -} http://git-wip-us.apache.org/repos/asf/jena/blob/49c4cffe/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/AbstractWholeFileNodeTupleReader.java ---------------------------------------------------------------------- diff --git a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/AbstractWholeFileNodeTupleReader.java b/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/AbstractWholeFileNodeTupleReader.java deleted file mode 100644 index c2da3f7..0000000 --- a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/AbstractWholeFileNodeTupleReader.java +++ /dev/null @@ -1,328 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one - * or more contributor license agreements. See the NOTICE file - * distributed with this work for additional information - * regarding copyright ownership. The ASF licenses this file - * to you under the Apache License, Version 2.0 (the - * "License"); you may not use this file except in compliance - * with the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.jena.hadoop.rdf.io.input.readers; - -import java.io.IOException; -import java.io.InputStream; - -import org.apache.hadoop.conf.Configuration; -import org.apache.hadoop.fs.FSDataInputStream; -import org.apache.hadoop.fs.FileSystem; -import org.apache.hadoop.fs.Path; -import org.apache.hadoop.io.LongWritable; -import org.apache.hadoop.io.compress.CompressionCodec; -import org.apache.hadoop.io.compress.CompressionCodecFactory; -import org.apache.hadoop.mapreduce.InputSplit; -import org.apache.hadoop.mapreduce.RecordReader; -import org.apache.hadoop.mapreduce.TaskAttemptContext; -import org.apache.hadoop.mapreduce.lib.input.FileSplit; -import org.apache.jena.hadoop.rdf.io.RdfIOConstants; -import org.apache.jena.hadoop.rdf.io.input.util.RdfIOUtils; -import org.apache.jena.hadoop.rdf.io.input.util.TrackableInputStream; -import org.apache.jena.hadoop.rdf.io.input.util.TrackedInputStream; -import org.apache.jena.hadoop.rdf.io.input.util.TrackedPipedRDFStream; -import org.apache.jena.hadoop.rdf.types.AbstractNodeTupleWritable; -import org.apache.jena.riot.Lang; -import org.apache.jena.riot.RDFDataMgr; -import org.apache.jena.riot.ReaderRIOT; -import org.apache.jena.riot.lang.PipedRDFIterator; -import org.apache.jena.riot.lang.PipedRDFStream; -import org.apache.jena.riot.system.ParserProfile; -import org.slf4j.Logger; -import org.slf4j.LoggerFactory; - -/** - * An abstract implementation for a record reader that reads records from whole - * files i.e. the whole file must be kept together to allow tuples to be - * successfully read. This only supports reading from file splits currently. - * <p> - * The keys produced are the approximate position in the file at which a tuple - * was found and the values will be node tuples. Positions are approximate - * because they are recorded after the point at which the most recent tuple was - * parsed from the input thus they reflect the approximate position in the - * stream immediately after which the triple was found. - * </p> - * <p> - * You should also be aware that with whole file formats syntax compressions in - * the format may mean that there are multiple triples produced with the same - * position and thus key. - * </p> - * - * - * - * @param <TValue> - * Value type - * @param <T> - * Tuple type - */ -public abstract class AbstractWholeFileNodeTupleReader<TValue, T extends AbstractNodeTupleWritable<TValue>> extends RecordReader<LongWritable, T> { - - private static final Logger LOG = LoggerFactory.getLogger(AbstractLineBasedNodeTupleReader.class); - private CompressionCodec compressionCodecs; - private TrackedInputStream input; - private LongWritable key; - private long length; - private T tuple; - private TrackedPipedRDFStream<TValue> stream; - private PipedRDFIterator<TValue> iter; - private Thread parserThread; - private boolean finished = false; - private boolean ignoreBadTuples = true; - private boolean parserFinished = false; - private Throwable parserError = null; - - @Override - public void initialize(InputSplit genericSplit, TaskAttemptContext context) throws IOException, InterruptedException { - LOG.debug("initialize({}, {})", genericSplit, context); - - // Assuming file split - if (!(genericSplit instanceof FileSplit)) - throw new IOException("This record reader only supports FileSplit inputs"); - FileSplit split = (FileSplit) genericSplit; - - // Configuration - Configuration config = context.getConfiguration(); - this.ignoreBadTuples = config.getBoolean(RdfIOConstants.INPUT_IGNORE_BAD_TUPLES, true); - if (this.ignoreBadTuples) - LOG.warn( - "Configured to ignore bad tuples, parsing errors will be logged and further parsing aborted but no user visible errors will be thrown. Consider setting {} to false to disable this behaviour", - RdfIOConstants.INPUT_IGNORE_BAD_TUPLES); - - // Figure out what portion of the file to read - if (split.getStart() > 0) - throw new IOException("This record reader requires a file split which covers the entire file"); - final Path file = split.getPath(); - long totalLength = file.getFileSystem(context.getConfiguration()).getFileStatus(file).getLen(); - CompressionCodecFactory factory = new CompressionCodecFactory(config); - this.compressionCodecs = factory.getCodec(file); - - LOG.info(String.format("Got split with start %d and length %d for file with total length of %d", new Object[] { split.getStart(), split.getLength(), - totalLength })); - - if (totalLength > split.getLength()) - throw new IOException("This record reader requires a file split which covers the entire file"); - - // Open the file and prepare the input stream - FileSystem fs = file.getFileSystem(config); - FSDataInputStream fileIn = fs.open(file); - this.length = split.getLength(); - if (this.compressionCodecs != null) { - // Compressed input - input = new TrackedInputStream(this.compressionCodecs.createInputStream(fileIn)); - } else { - // Uncompressed input - input = new TrackedInputStream(fileIn); - } - - // Set up background thread for parser - iter = this.getPipedIterator(); - this.stream = this.getPipedStream(iter, this.input); - ParserProfile profile = RdfIOUtils.createParserProfile(context, file); - Runnable parserRunnable = this.createRunnable(this, this.input, stream, this.getRdfLanguage(), profile); - this.parserThread = new Thread(parserRunnable); - this.parserThread.setDaemon(true); - this.parserThread.start(); - } - - /** - * Gets the RDF iterator to use - * - * @return Iterator - */ - protected abstract PipedRDFIterator<TValue> getPipedIterator(); - - /** - * Gets the RDF stream to parse to - * - * @param iterator - * Iterator - * @return RDF stream - */ - protected abstract TrackedPipedRDFStream<TValue> getPipedStream(PipedRDFIterator<TValue> iterator, TrackableInputStream input); - - /** - * Gets the RDF language to use for parsing - * - * @return - */ - protected abstract Lang getRdfLanguage(); - - /** - * Creates the runnable upon which the parsing will run - * - * @param input - * Input - * @param stream - * Stream - * @param lang - * Language to use for parsing - * @return Parser runnable - */ - private Runnable createRunnable(@SuppressWarnings("rawtypes") final AbstractWholeFileNodeTupleReader reader, final InputStream input, - final PipedRDFStream<TValue> stream, final Lang lang, final ParserProfile profile) { - return new Runnable() { - @Override - public void run() { - try { - ReaderRIOT riotReader = RDFDataMgr.createReader(lang); - riotReader.setParserProfile(profile); - riotReader.read(input, null, lang.getContentType(), stream, null); - reader.setParserFinished(null); - } catch (Throwable e) { - reader.setParserFinished(e); - } - } - }; - } - - /** - * Sets the parser thread finished state - * - * @param e - * Error (if any) - */ - private void setParserFinished(Throwable e) { - synchronized (this.parserThread) { - this.parserError = e; - this.parserFinished = true; - } - } - - /** - * Waits for the parser thread to have reported as finished - * - * @throws InterruptedException - */ - private void waitForParserFinished() throws InterruptedException { - do { - synchronized (this.parserThread) { - if (this.parserFinished) - return; - } - Thread.sleep(50); - } while (true); - } - - /** - * Creates an instance of a writable tuple from the given tuple value - * - * @param tuple - * Tuple value - * @return Writable tuple - */ - protected abstract T createInstance(TValue tuple); - - @Override - public boolean nextKeyValue() throws IOException, InterruptedException { - // Reuse key for efficiency - if (key == null) { - key = new LongWritable(); - } - - if (this.finished) - return false; - - try { - if (this.iter.hasNext()) { - Long l = this.stream.getPosition(); - if (l != null) { - this.key.set(l); - // For compressed input the actual length from which we - // calculate progress is likely less than the actual - // uncompressed length so we may need to increment the - // length as we go along - // We always add 1 more than the current length because we - // don't want to report 100% progress until we really have - // finished - if (this.compressionCodecs != null && l > this.length) - this.length = l + 1; - } - this.tuple = this.createInstance(this.iter.next()); - return true; - } else { - // Need to ensure that the parser thread has finished in order - // to determine whether we finished without error - this.waitForParserFinished(); - if (this.parserError != null) { - LOG.error("Error parsing whole file, aborting further parsing", this.parserError); - if (!this.ignoreBadTuples) - throw new IOException("Error parsing whole file at position " + this.input.getBytesRead() + ", aborting further parsing", - this.parserError); - - } - - this.key = null; - this.tuple = null; - this.finished = true; - // This is necessary so that when compressed input is used we - // report 100% progress once we've reached the genuine end of - // the stream - if (this.compressionCodecs != null) - this.length--; - return false; - } - } catch (Throwable e) { - // Failed to read the tuple on this line - LOG.error("Error parsing whole file, aborting further parsing", e); - if (!this.ignoreBadTuples) { - this.iter.close(); - throw new IOException("Error parsing whole file at position " + this.input.getBytesRead() + ", aborting further parsing", e); - } - this.key = null; - this.tuple = null; - this.finished = true; - return false; - } - } - - @Override - public LongWritable getCurrentKey() throws IOException, InterruptedException { - return this.key; - } - - @Override - public T getCurrentValue() throws IOException, InterruptedException { - return this.tuple; - } - - @Override - public float getProgress() throws IOException, InterruptedException { - float progress = 0.0f; - if (this.key == null) { - // We've either not started or we've finished - progress = (this.finished ? 1.0f : 0.0f); - } else if (this.key.get() == Long.MIN_VALUE) { - // We don't have a position so we've either in-progress or finished - progress = (this.finished ? 1.0f : 0.5f); - } else { - // We're some way through the file - progress = this.key.get() / (float) this.length; - } - LOG.debug("getProgress() --> {}", progress); - return progress; - } - - @Override - public void close() throws IOException { - this.iter.close(); - this.input.close(); - this.finished = true; - } - -} http://git-wip-us.apache.org/repos/asf/jena/blob/49c4cffe/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/AbstractWholeFileQuadReader.java ---------------------------------------------------------------------- diff --git a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/AbstractWholeFileQuadReader.java b/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/AbstractWholeFileQuadReader.java deleted file mode 100644 index e525bea..0000000 --- a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/AbstractWholeFileQuadReader.java +++ /dev/null @@ -1,51 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one - * or more contributor license agreements. See the NOTICE file - * distributed with this work for additional information - * regarding copyright ownership. The ASF licenses this file - * to you under the Apache License, Version 2.0 (the - * "License"); you may not use this file except in compliance - * with the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.jena.hadoop.rdf.io.input.readers; - -import org.apache.jena.hadoop.rdf.io.input.util.TrackableInputStream; -import org.apache.jena.hadoop.rdf.io.input.util.TrackedPipedQuadsStream; -import org.apache.jena.hadoop.rdf.io.input.util.TrackedPipedRDFStream; -import org.apache.jena.hadoop.rdf.types.QuadWritable; -import org.apache.jena.riot.lang.PipedRDFIterator; - -import com.hp.hpl.jena.sparql.core.Quad; - -/** - * An abstract record reader for whole file triple formats - * - * - * - */ -public abstract class AbstractWholeFileQuadReader extends AbstractWholeFileNodeTupleReader<Quad, QuadWritable> { - - @Override - protected PipedRDFIterator<Quad> getPipedIterator() { - return new PipedRDFIterator<Quad>(); - } - - @Override - protected TrackedPipedRDFStream<Quad> getPipedStream(PipedRDFIterator<Quad> iterator, TrackableInputStream input) { - return new TrackedPipedQuadsStream(iterator, input); - } - - @Override - protected QuadWritable createInstance(Quad tuple) { - return new QuadWritable(tuple); - } -} http://git-wip-us.apache.org/repos/asf/jena/blob/49c4cffe/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/AbstractWholeFileTripleReader.java ---------------------------------------------------------------------- diff --git a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/AbstractWholeFileTripleReader.java b/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/AbstractWholeFileTripleReader.java deleted file mode 100644 index 8710b99..0000000 --- a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/AbstractWholeFileTripleReader.java +++ /dev/null @@ -1,51 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one - * or more contributor license agreements. See the NOTICE file - * distributed with this work for additional information - * regarding copyright ownership. The ASF licenses this file - * to you under the Apache License, Version 2.0 (the - * "License"); you may not use this file except in compliance - * with the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.jena.hadoop.rdf.io.input.readers; - -import org.apache.jena.hadoop.rdf.io.input.util.TrackableInputStream; -import org.apache.jena.hadoop.rdf.io.input.util.TrackedPipedRDFStream; -import org.apache.jena.hadoop.rdf.io.input.util.TrackedPipedTriplesStream; -import org.apache.jena.hadoop.rdf.types.TripleWritable; -import org.apache.jena.riot.lang.PipedRDFIterator; - -import com.hp.hpl.jena.graph.Triple; - -/** - * An abstract record reader for whole file triple formats - * - * - * - */ -public abstract class AbstractWholeFileTripleReader extends AbstractWholeFileNodeTupleReader<Triple, TripleWritable> { - - @Override - protected PipedRDFIterator<Triple> getPipedIterator() { - return new PipedRDFIterator<Triple>(); - } - - @Override - protected TrackedPipedRDFStream<Triple> getPipedStream(PipedRDFIterator<Triple> iterator, TrackableInputStream input) { - return new TrackedPipedTriplesStream(iterator, input); - } - - @Override - protected TripleWritable createInstance(Triple tuple) { - return new TripleWritable(tuple); - } -} http://git-wip-us.apache.org/repos/asf/jena/blob/49c4cffe/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/QuadsReader.java ---------------------------------------------------------------------- diff --git a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/QuadsReader.java b/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/QuadsReader.java deleted file mode 100644 index 26b0a8b..0000000 --- a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/QuadsReader.java +++ /dev/null @@ -1,49 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one - * or more contributor license agreements. See the NOTICE file - * distributed with this work for additional information - * regarding copyright ownership. The ASF licenses this file - * to you under the Apache License, Version 2.0 (the - * "License"); you may not use this file except in compliance - * with the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.jena.hadoop.rdf.io.input.readers; - -import java.io.IOException; - -import org.apache.hadoop.io.LongWritable; -import org.apache.hadoop.mapreduce.RecordReader; -import org.apache.jena.hadoop.rdf.io.registry.HadoopRdfIORegistry; -import org.apache.jena.hadoop.rdf.types.QuadWritable; -import org.apache.jena.riot.Lang; -import org.apache.jena.riot.RDFLanguages; - -import com.hp.hpl.jena.sparql.core.Quad; - -/** - * A record reader that reads triples from any RDF quads format - */ -public class QuadsReader extends AbstractRdfReader<Quad, QuadWritable> { - - @Override - protected RecordReader<LongWritable, QuadWritable> selectRecordReader(Lang lang) throws IOException { - if (!RDFLanguages.isQuads(lang)) - throw new IOException( - lang.getLabel() - + " is not a RDF quads format, perhaps you wanted TriplesInputFormat or TriplesOrQuadsInputFormat instead?"); - - // This will throw an appropriate error if the language does not support - // triples - return HadoopRdfIORegistry.createQuadReader(lang); - } - -} http://git-wip-us.apache.org/repos/asf/jena/blob/49c4cffe/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/TriplesOrQuadsReader.java ---------------------------------------------------------------------- diff --git a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/TriplesOrQuadsReader.java b/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/TriplesOrQuadsReader.java deleted file mode 100644 index b071f67..0000000 --- a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/TriplesOrQuadsReader.java +++ /dev/null @@ -1,72 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one - * or more contributor license agreements. See the NOTICE file - * distributed with this work for additional information - * regarding copyright ownership. The ASF licenses this file - * to you under the Apache License, Version 2.0 (the - * "License"); you may not use this file except in compliance - * with the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.jena.hadoop.rdf.io.input.readers; - -import java.io.IOException; - -import org.apache.hadoop.io.LongWritable; -import org.apache.hadoop.mapreduce.RecordReader; -import org.apache.jena.hadoop.rdf.io.registry.HadoopRdfIORegistry; -import org.apache.jena.hadoop.rdf.types.QuadWritable; -import org.apache.jena.riot.Lang; -import org.apache.jena.riot.RDFLanguages; - -import com.hp.hpl.jena.graph.Node; -import com.hp.hpl.jena.sparql.core.Quad; - -/** - * A record reader that reads RDF from any triples/quads format. Triples are - * converted into quads in the default graph. This behaviour can be changed by - * deriving from this class and overriding the {@link #getGraphNode()} method - * - * - * - */ -@SuppressWarnings("javadoc") -public class TriplesOrQuadsReader extends AbstractRdfReader<Quad, QuadWritable> { - - @Override - protected RecordReader<LongWritable, QuadWritable> selectRecordReader(Lang lang) throws IOException { - if (!RDFLanguages.isQuads(lang) && !RDFLanguages.isTriples(lang)) - throw new IOException(lang.getLabel() + " is not a RDF triples/quads format"); - - if (HadoopRdfIORegistry.hasQuadReader(lang)) { - // Supports quads directly - return HadoopRdfIORegistry.createQuadReader(lang); - } else { - // Try to create a triples reader and wrap upwards into quads - // This will throw an error if a triple reader is not available - return new TriplesToQuadsReader(HadoopRdfIORegistry.createTripleReader(lang)); - } - } - - /** - * Gets the graph node which represents the graph into which triples will be - * indicated to belong to when they are converting into quads. - * <p> - * Defaults to {@link Quad#defaultGraphNodeGenerated} which represents the - * default graph - * </p> - * - * @return Graph node - */ - protected Node getGraphNode() { - return Quad.defaultGraphNodeGenerated; - } -} http://git-wip-us.apache.org/repos/asf/jena/blob/49c4cffe/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/TriplesReader.java ---------------------------------------------------------------------- diff --git a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/TriplesReader.java b/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/TriplesReader.java deleted file mode 100644 index 96c4a65..0000000 --- a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/TriplesReader.java +++ /dev/null @@ -1,49 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one - * or more contributor license agreements. See the NOTICE file - * distributed with this work for additional information - * regarding copyright ownership. The ASF licenses this file - * to you under the Apache License, Version 2.0 (the - * "License"); you may not use this file except in compliance - * with the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.jena.hadoop.rdf.io.input.readers; - -import java.io.IOException; - -import org.apache.hadoop.io.LongWritable; -import org.apache.hadoop.mapreduce.RecordReader; -import org.apache.jena.hadoop.rdf.io.registry.HadoopRdfIORegistry; -import org.apache.jena.hadoop.rdf.types.TripleWritable; -import org.apache.jena.riot.Lang; -import org.apache.jena.riot.RDFLanguages; - -import com.hp.hpl.jena.graph.Triple; - -/** - * A record reader that reads triples from any RDF triples format - */ -public class TriplesReader extends AbstractRdfReader<Triple, TripleWritable> { - - @Override - protected RecordReader<LongWritable, TripleWritable> selectRecordReader(Lang lang) throws IOException { - if (!RDFLanguages.isTriples(lang)) - throw new IOException( - lang.getLabel() - + " is not a RDF triples format, perhaps you wanted QuadsInputFormat or TriplesOrQuadsInputFormat instead?"); - - // This will throw an appropriate error if the language does not support - // triples - return HadoopRdfIORegistry.createTripleReader(lang); - } - -} http://git-wip-us.apache.org/repos/asf/jena/blob/49c4cffe/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/TriplesToQuadsReader.java ---------------------------------------------------------------------- diff --git a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/TriplesToQuadsReader.java b/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/TriplesToQuadsReader.java deleted file mode 100644 index a388f0e..0000000 --- a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/TriplesToQuadsReader.java +++ /dev/null @@ -1,102 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one - * or more contributor license agreements. See the NOTICE file - * distributed with this work for additional information - * regarding copyright ownership. The ASF licenses this file - * to you under the Apache License, Version 2.0 (the - * "License"); you may not use this file except in compliance - * with the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.jena.hadoop.rdf.io.input.readers; - -import java.io.IOException; - -import org.apache.hadoop.io.LongWritable; -import org.apache.hadoop.mapreduce.InputSplit; -import org.apache.hadoop.mapreduce.RecordReader; -import org.apache.hadoop.mapreduce.TaskAttemptContext; -import org.apache.jena.hadoop.rdf.types.QuadWritable; -import org.apache.jena.hadoop.rdf.types.TripleWritable; - -import com.hp.hpl.jena.graph.Node; -import com.hp.hpl.jena.sparql.core.Quad; - -/** - * A record reader that converts triples into quads by wrapping a - * {@code RecordReader<LongWritable, TripleWritable>} implementation - * - * - * - */ -public class TriplesToQuadsReader extends RecordReader<LongWritable, QuadWritable> { - - private final RecordReader<LongWritable, TripleWritable> reader; - private Node graph; - - /** - * Creates a new reader - * - * @param reader - * Triple reader - */ - public TriplesToQuadsReader(RecordReader<LongWritable, TripleWritable> reader) { - this(reader, Quad.defaultGraphNodeGenerated); - } - - /** - * Creates a new reader - * - * @param reader - * Triple reader - * @param graphNode - * Graph node - */ - public TriplesToQuadsReader(RecordReader<LongWritable, TripleWritable> reader, Node graphNode) { - if (reader == null) - throw new NullPointerException("reader cannot be null"); - if (graphNode == null) - throw new NullPointerException("Graph node cannot be null"); - this.reader = reader; - this.graph = graphNode; - } - - @Override - public void initialize(InputSplit split, TaskAttemptContext context) throws IOException, InterruptedException { - this.reader.initialize(split, context); - } - - @Override - public final boolean nextKeyValue() throws IOException, InterruptedException { - return this.reader.nextKeyValue(); - } - - @Override - public final LongWritable getCurrentKey() throws IOException, InterruptedException { - return this.reader.getCurrentKey(); - } - - @Override - public final QuadWritable getCurrentValue() throws IOException, InterruptedException { - TripleWritable t = this.reader.getCurrentValue(); - return new QuadWritable(new Quad(this.graph, t.get())); - } - - @Override - public final float getProgress() throws IOException, InterruptedException { - return this.reader.getProgress(); - } - - @Override - public final void close() throws IOException { - this.reader.close(); - } -} http://git-wip-us.apache.org/repos/asf/jena/blob/49c4cffe/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/jsonld/JsonLDQuadReader.java ---------------------------------------------------------------------- diff --git a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/jsonld/JsonLDQuadReader.java b/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/jsonld/JsonLDQuadReader.java deleted file mode 100644 index 1b3f467..0000000 --- a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/jsonld/JsonLDQuadReader.java +++ /dev/null @@ -1,32 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one - * or more contributor license agreements. See the NOTICE file - * distributed with this work for additional information - * regarding copyright ownership. The ASF licenses this file - * to you under the Apache License, Version 2.0 (the - * "License"); you may not use this file except in compliance - * with the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.jena.hadoop.rdf.io.input.readers.jsonld; - -import org.apache.jena.hadoop.rdf.io.input.readers.AbstractWholeFileQuadReader; -import org.apache.jena.riot.Lang; -import org.apache.jena.riot.RDFLanguages; - -public class JsonLDQuadReader extends AbstractWholeFileQuadReader { - - @Override - protected Lang getRdfLanguage() { - return RDFLanguages.JSONLD; - } - -} http://git-wip-us.apache.org/repos/asf/jena/blob/49c4cffe/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/jsonld/JsonLDTripleReader.java ---------------------------------------------------------------------- diff --git a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/jsonld/JsonLDTripleReader.java b/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/jsonld/JsonLDTripleReader.java deleted file mode 100644 index 7cdea9e..0000000 --- a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/jsonld/JsonLDTripleReader.java +++ /dev/null @@ -1,30 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one - * or more contributor license agreements. See the NOTICE file - * distributed with this work for additional information - * regarding copyright ownership. The ASF licenses this file - * to you under the Apache License, Version 2.0 (the - * "License"); you may not use this file except in compliance - * with the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.jena.hadoop.rdf.io.input.readers.jsonld; - -import org.apache.jena.hadoop.rdf.io.input.readers.AbstractWholeFileTripleReader; -import org.apache.jena.riot.Lang; -import org.apache.jena.riot.RDFLanguages; - -public class JsonLDTripleReader extends AbstractWholeFileTripleReader { - @Override - protected Lang getRdfLanguage() { - return RDFLanguages.JSONLD; - } -} http://git-wip-us.apache.org/repos/asf/jena/blob/49c4cffe/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/nquads/BlockedNQuadsReader.java ---------------------------------------------------------------------- diff --git a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/nquads/BlockedNQuadsReader.java b/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/nquads/BlockedNQuadsReader.java deleted file mode 100644 index cef8ef1..0000000 --- a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/nquads/BlockedNQuadsReader.java +++ /dev/null @@ -1,45 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one - * or more contributor license agreements. See the NOTICE file - * distributed with this work for additional information - * regarding copyright ownership. The ASF licenses this file - * to you under the Apache License, Version 2.0 (the - * "License"); you may not use this file except in compliance - * with the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.jena.hadoop.rdf.io.input.readers.nquads; - -import org.apache.jena.hadoop.rdf.io.input.readers.AbstractBlockBasedQuadReader; -import org.apache.jena.riot.Lang; - -/** - * A record record for NQuads - * <p> - * This is a hybrid of the {@link NQuadsReader} and the - * {@link WholeFileNQuadsReader} in that it does not process individual lines - * rather it processes the inputs in blocks of lines parsing the whole block - * rather than individual lines. This provides a compromise between the higher - * parser setup of creating more parsers and the benefit of being able to split - * input files over multiple mappers. - * </p> - * - * - * - */ -public class BlockedNQuadsReader extends AbstractBlockBasedQuadReader { - - @Override - protected Lang getRdfLanguage() { - return Lang.NQUADS; - } - -} http://git-wip-us.apache.org/repos/asf/jena/blob/49c4cffe/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/nquads/NQuadsReader.java ---------------------------------------------------------------------- diff --git a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/nquads/NQuadsReader.java b/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/nquads/NQuadsReader.java deleted file mode 100644 index e00e318..0000000 --- a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/nquads/NQuadsReader.java +++ /dev/null @@ -1,49 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one - * or more contributor license agreements. See the NOTICE file - * distributed with this work for additional information - * regarding copyright ownership. The ASF licenses this file - * to you under the Apache License, Version 2.0 (the - * "License"); you may not use this file except in compliance - * with the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.jena.hadoop.rdf.io.input.readers.nquads; - -import java.util.Iterator; - -import org.apache.jena.hadoop.rdf.io.input.readers.AbstractLineBasedQuadReader; -import org.apache.jena.riot.lang.LangNQuads; -import org.apache.jena.riot.system.ParserProfile; -import org.apache.jena.riot.tokens.Tokenizer; -import org.apache.jena.riot.tokens.TokenizerFactory; - -import com.hp.hpl.jena.sparql.core.Quad; - -/** - * A record reader for NQuads - * - * - * - */ -public class NQuadsReader extends AbstractLineBasedQuadReader { - - @Override - protected Tokenizer getTokenizer(String line) { - return TokenizerFactory.makeTokenizerString(line); - } - - @Override - protected Iterator<Quad> getQuadsIterator(Tokenizer tokenizer, ParserProfile profile) { - return new LangNQuads(tokenizer, profile, null); - } - -} http://git-wip-us.apache.org/repos/asf/jena/blob/49c4cffe/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/nquads/WholeFileNQuadsReader.java ---------------------------------------------------------------------- diff --git a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/nquads/WholeFileNQuadsReader.java b/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/nquads/WholeFileNQuadsReader.java deleted file mode 100644 index 96e6f80..0000000 --- a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/nquads/WholeFileNQuadsReader.java +++ /dev/null @@ -1,42 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one - * or more contributor license agreements. See the NOTICE file - * distributed with this work for additional information - * regarding copyright ownership. The ASF licenses this file - * to you under the Apache License, Version 2.0 (the - * "License"); you may not use this file except in compliance - * with the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.jena.hadoop.rdf.io.input.readers.nquads; - -import org.apache.jena.hadoop.rdf.io.input.readers.AbstractWholeFileQuadReader; -import org.apache.jena.riot.Lang; - -/** - * A record record for NQuads - * <p> - * Unlike the {@link NQuadsReader} this processes files as a whole rather than - * individual lines. This has the advantage of less parser setup overhead but - * the disadvantage that the input cannot be split between multiple mappers. - * </p> - * - * - * - */ -public class WholeFileNQuadsReader extends AbstractWholeFileQuadReader { - - @Override - protected Lang getRdfLanguage() { - return Lang.NQUADS; - } - -} http://git-wip-us.apache.org/repos/asf/jena/blob/49c4cffe/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/ntriples/BlockedNTriplesReader.java ---------------------------------------------------------------------- diff --git a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/ntriples/BlockedNTriplesReader.java b/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/ntriples/BlockedNTriplesReader.java deleted file mode 100644 index 7268d5a..0000000 --- a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/ntriples/BlockedNTriplesReader.java +++ /dev/null @@ -1,45 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one - * or more contributor license agreements. See the NOTICE file - * distributed with this work for additional information - * regarding copyright ownership. The ASF licenses this file - * to you under the Apache License, Version 2.0 (the - * "License"); you may not use this file except in compliance - * with the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.jena.hadoop.rdf.io.input.readers.ntriples; - -import org.apache.jena.hadoop.rdf.io.input.readers.AbstractBlockBasedTripleReader; -import org.apache.jena.riot.Lang; - -/** - * A record record for NTriples - * <p> - * This is a hybrid of the {@link NTriplesReader} and the - * {@link WholeFileNTriplesReader} in that it does not process individual lines - * rather it processes the inputs in blocks of lines parsing the whole block - * rather than individual lines. This provides a compromise between the higher - * parser setup of creating more parsers and the benefit of being able to split - * input files over multiple mappers. - * </p> - * - * - * - */ -public class BlockedNTriplesReader extends AbstractBlockBasedTripleReader { - - @Override - protected Lang getRdfLanguage() { - return Lang.NTRIPLES; - } - -} http://git-wip-us.apache.org/repos/asf/jena/blob/49c4cffe/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/ntriples/NTriplesReader.java ---------------------------------------------------------------------- diff --git a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/ntriples/NTriplesReader.java b/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/ntriples/NTriplesReader.java deleted file mode 100644 index bfc8503..0000000 --- a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/ntriples/NTriplesReader.java +++ /dev/null @@ -1,48 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one - * or more contributor license agreements. See the NOTICE file - * distributed with this work for additional information - * regarding copyright ownership. The ASF licenses this file - * to you under the Apache License, Version 2.0 (the - * "License"); you may not use this file except in compliance - * with the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.jena.hadoop.rdf.io.input.readers.ntriples; - -import java.util.Iterator; - -import org.apache.jena.hadoop.rdf.io.input.readers.AbstractLineBasedTripleReader; -import org.apache.jena.riot.lang.LangNTriples; -import org.apache.jena.riot.system.ParserProfile; -import org.apache.jena.riot.tokens.Tokenizer; -import org.apache.jena.riot.tokens.TokenizerFactory; - -import com.hp.hpl.jena.graph.Triple; - -/** - * A record reader for NTriples - * - * - * - */ -public class NTriplesReader extends AbstractLineBasedTripleReader { - - @Override - protected Iterator<Triple> getTriplesIterator(Tokenizer tokenizer, ParserProfile profile) { - return new LangNTriples(tokenizer, profile, null); - } - - @Override - protected Tokenizer getTokenizer(String line) { - return TokenizerFactory.makeTokenizerString(line); - } -} http://git-wip-us.apache.org/repos/asf/jena/blob/49c4cffe/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/ntriples/WholeFileNTriplesReader.java ---------------------------------------------------------------------- diff --git a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/ntriples/WholeFileNTriplesReader.java b/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/ntriples/WholeFileNTriplesReader.java deleted file mode 100644 index c200d93..0000000 --- a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/ntriples/WholeFileNTriplesReader.java +++ /dev/null @@ -1,42 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one - * or more contributor license agreements. See the NOTICE file - * distributed with this work for additional information - * regarding copyright ownership. The ASF licenses this file - * to you under the Apache License, Version 2.0 (the - * "License"); you may not use this file except in compliance - * with the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.jena.hadoop.rdf.io.input.readers.ntriples; - -import org.apache.jena.hadoop.rdf.io.input.readers.AbstractWholeFileTripleReader; -import org.apache.jena.riot.Lang; - -/** - * A record record for NTriples - * <p> - * Unlike the {@link NTriplesReader} this processes files as a whole rather than - * individual lines. This has the advantage of less parser setup overhead but - * the disadvantage that the input cannot be split between multiple mappers. - * </p> - * - * - * - */ -public class WholeFileNTriplesReader extends AbstractWholeFileTripleReader { - - @Override - protected Lang getRdfLanguage() { - return Lang.NTRIPLES; - } - -} http://git-wip-us.apache.org/repos/asf/jena/blob/49c4cffe/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/rdfjson/RdfJsonReader.java ---------------------------------------------------------------------- diff --git a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/rdfjson/RdfJsonReader.java b/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/rdfjson/RdfJsonReader.java deleted file mode 100644 index 009024b..0000000 --- a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/rdfjson/RdfJsonReader.java +++ /dev/null @@ -1,37 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one - * or more contributor license agreements. See the NOTICE file - * distributed with this work for additional information - * regarding copyright ownership. The ASF licenses this file - * to you under the Apache License, Version 2.0 (the - * "License"); you may not use this file except in compliance - * with the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.jena.hadoop.rdf.io.input.readers.rdfjson; - -import org.apache.jena.hadoop.rdf.io.input.readers.AbstractWholeFileTripleReader; -import org.apache.jena.riot.Lang; - -/** - * A record reader for RDF/JSON files - * - * - * - */ -public class RdfJsonReader extends AbstractWholeFileTripleReader { - - @Override - protected Lang getRdfLanguage() { - return Lang.RDFJSON; - } - -} http://git-wip-us.apache.org/repos/asf/jena/blob/49c4cffe/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/rdfxml/RdfXmlReader.java ---------------------------------------------------------------------- diff --git a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/rdfxml/RdfXmlReader.java b/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/rdfxml/RdfXmlReader.java deleted file mode 100644 index 9c374c6..0000000 --- a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/rdfxml/RdfXmlReader.java +++ /dev/null @@ -1,37 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one - * or more contributor license agreements. See the NOTICE file - * distributed with this work for additional information - * regarding copyright ownership. The ASF licenses this file - * to you under the Apache License, Version 2.0 (the - * "License"); you may not use this file except in compliance - * with the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.jena.hadoop.rdf.io.input.readers.rdfxml; - -import org.apache.jena.hadoop.rdf.io.input.readers.AbstractWholeFileTripleReader; -import org.apache.jena.riot.Lang; - -/** - * A record reader for RDF/XML files - * - * - * - */ -public class RdfXmlReader extends AbstractWholeFileTripleReader { - - @Override - protected Lang getRdfLanguage() { - return Lang.RDFXML; - } - -} http://git-wip-us.apache.org/repos/asf/jena/blob/49c4cffe/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/thrift/ThriftQuadReader.java ---------------------------------------------------------------------- diff --git a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/thrift/ThriftQuadReader.java b/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/thrift/ThriftQuadReader.java deleted file mode 100644 index 084b1ec..0000000 --- a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/thrift/ThriftQuadReader.java +++ /dev/null @@ -1,32 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one - * or more contributor license agreements. See the NOTICE file - * distributed with this work for additional information - * regarding copyright ownership. The ASF licenses this file - * to you under the Apache License, Version 2.0 (the - * "License"); you may not use this file except in compliance - * with the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.jena.hadoop.rdf.io.input.readers.thrift; - -import org.apache.jena.hadoop.rdf.io.input.readers.AbstractWholeFileQuadReader; -import org.apache.jena.riot.Lang; -import org.apache.jena.riot.RDFLanguages; - -public class ThriftQuadReader extends AbstractWholeFileQuadReader { - - @Override - protected Lang getRdfLanguage() { - return RDFLanguages.THRIFT; - } - -} http://git-wip-us.apache.org/repos/asf/jena/blob/49c4cffe/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/thrift/ThriftTripleReader.java ---------------------------------------------------------------------- diff --git a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/thrift/ThriftTripleReader.java b/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/thrift/ThriftTripleReader.java deleted file mode 100644 index 713bfa7..0000000 --- a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/thrift/ThriftTripleReader.java +++ /dev/null @@ -1,30 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one - * or more contributor license agreements. See the NOTICE file - * distributed with this work for additional information - * regarding copyright ownership. The ASF licenses this file - * to you under the Apache License, Version 2.0 (the - * "License"); you may not use this file except in compliance - * with the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.jena.hadoop.rdf.io.input.readers.thrift; - -import org.apache.jena.hadoop.rdf.io.input.readers.AbstractWholeFileTripleReader; -import org.apache.jena.riot.Lang; -import org.apache.jena.riot.RDFLanguages; - -public class ThriftTripleReader extends AbstractWholeFileTripleReader { - @Override - protected Lang getRdfLanguage() { - return RDFLanguages.THRIFT; - } -} http://git-wip-us.apache.org/repos/asf/jena/blob/49c4cffe/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/trig/TriGReader.java ---------------------------------------------------------------------- diff --git a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/trig/TriGReader.java b/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/trig/TriGReader.java deleted file mode 100644 index b1b0c3c..0000000 --- a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/trig/TriGReader.java +++ /dev/null @@ -1,37 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one - * or more contributor license agreements. See the NOTICE file - * distributed with this work for additional information - * regarding copyright ownership. The ASF licenses this file - * to you under the Apache License, Version 2.0 (the - * "License"); you may not use this file except in compliance - * with the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.jena.hadoop.rdf.io.input.readers.trig; - -import org.apache.jena.hadoop.rdf.io.input.readers.AbstractWholeFileQuadReader; -import org.apache.jena.riot.Lang; - -/** - * A record reader for TriG files - * - * - * - */ -public class TriGReader extends AbstractWholeFileQuadReader { - - @Override - protected Lang getRdfLanguage() { - return Lang.TRIG; - } - -} http://git-wip-us.apache.org/repos/asf/jena/blob/49c4cffe/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/trix/TriXReader.java ---------------------------------------------------------------------- diff --git a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/trix/TriXReader.java b/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/trix/TriXReader.java deleted file mode 100644 index 6873c64..0000000 --- a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/trix/TriXReader.java +++ /dev/null @@ -1,37 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one - * or more contributor license agreements. See the NOTICE file - * distributed with this work for additional information - * regarding copyright ownership. The ASF licenses this file - * to you under the Apache License, Version 2.0 (the - * "License"); you may not use this file except in compliance - * with the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.jena.hadoop.rdf.io.input.readers.trix; - -import org.apache.jena.hadoop.rdf.io.input.readers.AbstractWholeFileQuadReader; -import org.apache.jena.riot.Lang; - -/** - * A record reader for TriX files - * - * - * - */ -public class TriXReader extends AbstractWholeFileQuadReader { - - @Override - protected Lang getRdfLanguage() { - return Lang.TRIX; - } - -} http://git-wip-us.apache.org/repos/asf/jena/blob/49c4cffe/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/turtle/TurtleReader.java ---------------------------------------------------------------------- diff --git a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/turtle/TurtleReader.java b/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/turtle/TurtleReader.java deleted file mode 100644 index b3fb377..0000000 --- a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/readers/turtle/TurtleReader.java +++ /dev/null @@ -1,37 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one - * or more contributor license agreements. See the NOTICE file - * distributed with this work for additional information - * regarding copyright ownership. The ASF licenses this file - * to you under the Apache License, Version 2.0 (the - * "License"); you may not use this file except in compliance - * with the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.jena.hadoop.rdf.io.input.readers.turtle; - -import org.apache.jena.hadoop.rdf.io.input.readers.AbstractWholeFileTripleReader; -import org.apache.jena.riot.Lang; - -/** - * A record reader for Turtle files - * - * - * - */ -public class TurtleReader extends AbstractWholeFileTripleReader { - - @Override - protected Lang getRdfLanguage() { - return Lang.TURTLE; - } - -} http://git-wip-us.apache.org/repos/asf/jena/blob/49c4cffe/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/thrift/ThriftQuadInputFormat.java ---------------------------------------------------------------------- diff --git a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/thrift/ThriftQuadInputFormat.java b/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/thrift/ThriftQuadInputFormat.java deleted file mode 100644 index f75542a..0000000 --- a/jena-hadoop-rdf/jena-elephas-io/src/main/java/org/apache/jena/hadoop/rdf/io/input/thrift/ThriftQuadInputFormat.java +++ /dev/null @@ -1,39 +0,0 @@ -/* - * Licensed to the Apache Software Foundation (ASF) under one - * or more contributor license agreements. See the NOTICE file - * distributed with this work for additional information - * regarding copyright ownership. The ASF licenses this file - * to you under the Apache License, Version 2.0 (the - * "License"); you may not use this file except in compliance - * with the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -package org.apache.jena.hadoop.rdf.io.input.thrift; - -import java.io.IOException; - -import org.apache.hadoop.io.LongWritable; -import org.apache.hadoop.mapreduce.InputSplit; -import org.apache.hadoop.mapreduce.RecordReader; -import org.apache.hadoop.mapreduce.TaskAttemptContext; -import org.apache.jena.hadoop.rdf.io.input.AbstractWholeFileInputFormat; -import org.apache.jena.hadoop.rdf.io.input.readers.thrift.ThriftQuadReader; -import org.apache.jena.hadoop.rdf.types.QuadWritable; - -public class ThriftQuadInputFormat extends AbstractWholeFileInputFormat<LongWritable, QuadWritable> { - - @Override - public RecordReader<LongWritable, QuadWritable> createRecordReader(InputSplit split, TaskAttemptContext context) - throws IOException, InterruptedException { - return new ThriftQuadReader(); - } - -}
