Search in sources :

Example 1 with ParseOutputFormat

use of org.apache.nutch.parse.ParseOutputFormat in project nutch by apache.

the class FetcherOutputFormat method getRecordWriter.

@Override
public RecordWriter<Text, NutchWritable> getRecordWriter(TaskAttemptContext context) throws IOException {
    Configuration conf = context.getConfiguration();
    String name = getUniqueFile(context, "part", "");
    Path dir = FileOutputFormat.getOutputPath(context);
    FileSystem fs = dir.getFileSystem(context.getConfiguration());
    Path out = FileOutputFormat.getOutputPath(context);
    final Path fetch = new Path(new Path(out, CrawlDatum.FETCH_DIR_NAME), name);
    final Path content = new Path(new Path(out, Content.DIR_NAME), name);
    final CompressionType compType = SequenceFileOutputFormat.getOutputCompressionType(context);
    Option fKeyClassOpt = MapFile.Writer.keyClass(Text.class);
    org.apache.hadoop.io.SequenceFile.Writer.Option fValClassOpt = SequenceFile.Writer.valueClass(CrawlDatum.class);
    org.apache.hadoop.io.SequenceFile.Writer.Option fProgressOpt = SequenceFile.Writer.progressable((Progressable) context);
    org.apache.hadoop.io.SequenceFile.Writer.Option fCompOpt = SequenceFile.Writer.compression(compType);
    final MapFile.Writer fetchOut = new MapFile.Writer(conf, fetch, fKeyClassOpt, fValClassOpt, fCompOpt, fProgressOpt);
    return new RecordWriter<Text, NutchWritable>() {

        private MapFile.Writer contentOut;

        private RecordWriter<Text, Parse> parseOut;

        {
            if (Fetcher.isStoringContent(conf)) {
                Option cKeyClassOpt = MapFile.Writer.keyClass(Text.class);
                org.apache.hadoop.io.SequenceFile.Writer.Option cValClassOpt = SequenceFile.Writer.valueClass(Content.class);
                org.apache.hadoop.io.SequenceFile.Writer.Option cProgressOpt = SequenceFile.Writer.progressable((Progressable) context);
                org.apache.hadoop.io.SequenceFile.Writer.Option cCompOpt = SequenceFile.Writer.compression(compType);
                contentOut = new MapFile.Writer(conf, content, cKeyClassOpt, cValClassOpt, cCompOpt, cProgressOpt);
            }
            if (Fetcher.isParsing(conf)) {
                parseOut = new ParseOutputFormat().getRecordWriter(context);
            }
        }

        public void write(Text key, NutchWritable value) throws IOException, InterruptedException {
            Writable w = value.get();
            if (w instanceof CrawlDatum)
                fetchOut.append(key, w);
            else if (w instanceof Content && contentOut != null)
                contentOut.append(key, w);
            else if (w instanceof Parse && parseOut != null)
                parseOut.write(key, (Parse) w);
        }

        public void close(TaskAttemptContext context) throws IOException, InterruptedException {
            fetchOut.close();
            if (contentOut != null) {
                contentOut.close();
            }
            if (parseOut != null) {
                parseOut.close(context);
            }
        }
    };
}
Also used : Path(org.apache.hadoop.fs.Path) Configuration(org.apache.hadoop.conf.Configuration) Parse(org.apache.nutch.parse.Parse) MapFile(org.apache.hadoop.io.MapFile) NutchWritable(org.apache.nutch.crawl.NutchWritable) Writable(org.apache.hadoop.io.Writable) NutchWritable(org.apache.nutch.crawl.NutchWritable) CrawlDatum(org.apache.nutch.crawl.CrawlDatum) Text(org.apache.hadoop.io.Text) TaskAttemptContext(org.apache.hadoop.mapreduce.TaskAttemptContext) RecordWriter(org.apache.hadoop.mapreduce.RecordWriter) Content(org.apache.nutch.protocol.Content) FileSystem(org.apache.hadoop.fs.FileSystem) ParseOutputFormat(org.apache.nutch.parse.ParseOutputFormat) Option(org.apache.hadoop.io.MapFile.Writer.Option) CompressionType(org.apache.hadoop.io.SequenceFile.CompressionType) RecordWriter(org.apache.hadoop.mapreduce.RecordWriter)

Aggregations

Configuration (org.apache.hadoop.conf.Configuration)1 FileSystem (org.apache.hadoop.fs.FileSystem)1 Path (org.apache.hadoop.fs.Path)1 MapFile (org.apache.hadoop.io.MapFile)1 Option (org.apache.hadoop.io.MapFile.Writer.Option)1 CompressionType (org.apache.hadoop.io.SequenceFile.CompressionType)1 Text (org.apache.hadoop.io.Text)1 Writable (org.apache.hadoop.io.Writable)1 RecordWriter (org.apache.hadoop.mapreduce.RecordWriter)1 TaskAttemptContext (org.apache.hadoop.mapreduce.TaskAttemptContext)1 CrawlDatum (org.apache.nutch.crawl.CrawlDatum)1 NutchWritable (org.apache.nutch.crawl.NutchWritable)1 Parse (org.apache.nutch.parse.Parse)1 ParseOutputFormat (org.apache.nutch.parse.ParseOutputFormat)1 Content (org.apache.nutch.protocol.Content)1