Package com.digitalpebble.behemoth

Examples of com.digitalpebble.behemoth.BehemothDocument

70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
    public void map(LongWritable key, WritableWarcRecord record,
            OutputCollector<Text, BehemothDocument> output, Reporter reporter)
            throws IOException {

        BehemothDocument behemothDocument = new BehemothDocument();

        if (record.getRecord().getHeaderRecordType().equals("response") == false)
            return;

        byte[] binarycontent = record.getRecord().getContent();

        String uri = record.getRecord()
                .getHeaderMetadataItem("WARC-Target-URI");
        // application/http;msgtype=response
        // but always null?
        // String WARCContentType =
        // record.getRecord().getHeaderMetadataItem("Content-Type");

        HttpResponse response;
        try {
            response = new HttpResponse(binarycontent);
        } catch (ProtocolException e) {
            return;
        }

        behemothDocument.setUrl(uri);
        newKey.set(uri);

        String contentType = response.getHeader(HttpHeaders.CONTENT_TYPE);
        behemothDocument.setContentType(contentType);
        behemothDocument.setContent(response.getContent());

        output.collect(newKey, behemothDocument);
    }
View Full Code Here
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
    public void map(Text key, Content content,
            OutputCollector<Text, BehemothDocument> output, Reporter reporter)
            throws IOException {

        BehemothDocument behemothDocument = new BehemothDocument();

        int status = Integer.parseInt(content.getMetadata().get(
                Nutch.FETCH_STATUS_KEY));
        if (status != CrawlDatum.STATUS_FETCH_SUCCESS) {
            // content not fetched successfully, skip document
            LOG.debug("Skipping " + key
                    + " as content is not fetched successfully");
            return;
        }

        // TODO store the fetch metadata in the Behemoth document
        // store the binary content and mimetype in the Behemoth document

        String contentType = content.getContentType();
        byte[] binarycontent = content.getContent();
        behemothDocument.setUrl(key.toString());
        behemothDocument.setContent(binarycontent);
        behemothDocument.setContentType(contentType);
        output.collect(key, behemothDocument);
    }
View Full Code Here
131
132
133
134
135
136
137
138
139
140
141
        Reader[] cacheReaders = SequenceFileOutputFormat.getReaders(getConf(),
                input);
        for (Reader current : cacheReaders) {
            // read the key + values in that file
            Text key = new Text();
            BehemothDocument inputDoc = new BehemothDocument();
            BufferedWriter writer = null;
            gate.Document gatedocument = null;
            while (current.next(key, inputDoc)) {
                count[0]++;
                // generate a GATE document then save it to XML
View Full Code Here
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
        Reader[] cacheReaders = SequenceFileOutputFormat.getReaders(getConf(),
                input);
        for (Reader current : cacheReaders) {
            // read the key + values in that file
            Text key = new Text();
            BehemothDocument inputDoc = new BehemothDocument();
            while (current.next(key, inputDoc)) {
                count[0]++;
                // filter the doc?
                if (!docFilter.keep(inputDoc))
                    continue;
                if (dumpBinary && inputDoc.getContent() == null)
                    continue;
                else if (!dumpBinary && inputDoc.getText() == null)
                    continue;

                String fileName = Integer.toString(count[0]);
                String urldoc = inputDoc.getUrl();
                if (mode.equals(FileNamingMode.URL) && urldoc != null
                        && urldoc.length() > 0) {
                    fileName = URLEncoder.encode(urldoc, "UTF-8");
                } else if (mode.equals(FileNamingMode.UUID) && urldoc != null
                        && urldoc.length() > 0) {
                    fileName = UUID.nameUUIDFromBytes(urldoc.getBytes())
                            .toString();
                } else {
                    fileName = String.format("%09d", count[0]);
                }

                if (!dumpBinary)
                    fileName += ".txt";

                byte[] contentBytes;
                if (dumpBinary)
                    contentBytes = inputDoc.getContent();
                else
                    contentBytes = inputDoc.getText().getBytes("UTF-8");
                // out.write(contentBytes, 0, contentBytes.length);
                addToArchive(fileName, contentBytes, dir);

                // add the mapping URL->filename in the index -> archive num
                index.writeBytes(urldoc + "\t" + fileName + "\t"
View Full Code Here
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
    public long generate(boolean recurse) throws IOException {
        long result = 0;
        // read from input path
        // create new Content object and add it to the SequenceFile
        Text key = new Text();
        BehemothDocument value = new BehemothDocument();
        SequenceFile.Writer writer = null;
        try {
            Configuration conf = getConf();
            FileSystem fs = output.getFileSystem(conf);
            writer = SequenceFile.createWriter(fs, conf, output,
                    key.getClass(), value.getClass());
            PerformanceFileFilter pff = new PerformanceFileFilter(writer, key,
                    value, conf, reporter);
            // iterate on the files in the source dir
            result = processFiles(conf, input, recurse, pff);
View Full Code Here
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
            if (!path.getName().startsWith("part-")
                    && !path.getName().equals(inputPath.getName()))
                continue;
            SequenceFile.Reader reader = new SequenceFile.Reader(fs, path, conf);
            Text key = new Text();
            BehemothDocument value = new BehemothDocument();
            while (reader.next(key, value)) {
                // skip this document?
                if (doFilter && filters.keep(value) == false)
                    continue;

                System.out.println(value.toString(showBinaryContent,
                        showAnnotations, showText, showMD));
            }
            reader.close();
        }
View Full Code Here
133
134
135
136
137
138
139
140
141
142
143
        Reader[] cacheReaders = SequenceFileOutputFormat.getReaders(getConf(),
                input);
        for (Reader current : cacheReaders) {
            // read the key + values in that file
            Text key = new Text();
            BehemothDocument inputDoc = new BehemothDocument();
            BufferedWriter writer = null;
            gate.Document gatedocument = null;
            while (current.next(key, inputDoc)) {
                count[0]++;
                // generate a GATE document then save it to XML
View Full Code Here
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
        Reader[] cacheReaders = SequenceFileOutputFormat.getReaders(getConf(),
                input);
        for (Reader current : cacheReaders) {
            // read the key + values in that file
            Text key = new Text();
            BehemothDocument inputDoc = new BehemothDocument();
            while (current.next(key, inputDoc)) {
                count[0]++;
                // filter the doc?
                if (!docFilter.keep(inputDoc))
                    continue;
                if (dumpBinary && inputDoc.getContent() == null)
                    continue;
                else if (!dumpBinary && inputDoc.getText() == null)
                    continue;

                String fileName = Integer.toString(count[0]);
                String urldoc = inputDoc.getUrl();
                if (mode.equals(FileNamingMode.URL) && urldoc != null
                        && urldoc.length() > 0) {
                    fileName = URLEncoder.encode(urldoc, "UTF-8");
                } else if (mode.equals(FileNamingMode.UUID) && urldoc != null
                        && urldoc.length() > 0) {
                    fileName = UUID.nameUUIDFromBytes(urldoc.getBytes())
                            .toString();
                } else {
                    fileName = String.format("%09d", count[0]);
                }

                if (!dumpBinary)
                    fileName += ".txt";

                byte[] contentBytes;
                if (dumpBinary)
                    contentBytes = inputDoc.getContent();
                else
                    contentBytes = inputDoc.getText().getBytes("UTF-8");
                // out.write(contentBytes, 0, contentBytes.length);
                addToArchive(fileName, contentBytes, dir);

                // add the mapping URL->filename in the index -> archive num
                index.writeBytes(urldoc + "\t" + fileName + "\t"
View Full Code Here
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
            if (!path.getName().startsWith("part-")
                    && !path.getName().equals(inputPath.getName()))
                continue;
            SequenceFile.Reader reader = new SequenceFile.Reader(fs, path, conf);
            Text key = new Text();
            BehemothDocument value = new BehemothDocument();
            while (reader.next(key, value)) {
                // skip this document?
                if (doFilter && filters.keep(value) == false)
                    continue;

                System.out.println(value.toString(showBinaryContent,
                        showAnnotations, showText, showMD));
            }
            reader.close();
        }
View Full Code Here
15
16
17
18
19
20
21
22
23
24
25
26
27
28
public class SequenceFileConverterMapper extends
        Mapper<Writable, Writable, Text, BehemothDocument> {
    @Override
    protected void map(Writable key, Writable value, Context context)
            throws IOException, InterruptedException {
        BehemothDocument doc = new BehemothDocument();
        doc.setUrl(key.toString());
        // TODO: Is this the right way to do this? We need the bytes.
        DataOutputBuffer out = new DataOutputBuffer();
        value.write(out);
        doc.setContent(out.getData());
        // doc.setContent(value.toString().getBytes(Charset.forName("UTF-8")));
        context.write(new Text(key.toString()), doc);
    }
View Full Code Here
TOP

Related Classes of com.digitalpebble.behemoth.BehemothDocument

  • com.digitalpebble.behemoth.gate.GATECorpusGenerator
  • com.digitalpebble.behemoth.gate.GATEProcessorTest
  • com.digitalpebble.behemoth.io.nutch.NutchSegmentConverterJob
  • com.digitalpebble.behemoth.io.sequencefile.SequenceFileConverterMapper
  • com.digitalpebble.behemoth.io.warc.WARCConverterJob
  • com.digitalpebble.behemoth.languageidentification.LanguageIDProcessorTest
  • com.digitalpebble.behemoth.tika.TikaProcessorTest
  • com.digitalpebble.behemoth.uima.UIMAProcessorTest
  • com.digitalpebble.behemoth.util.ContentExtractor
  • com.digitalpebble.behemoth.util.CorpusGenerator
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.