Package cc.twittertools.corpus.data

Examples of cc.twittertools.corpus.data.StatusStream

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
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
    }

    File indexLocation = new File(cmdline.getOptionValue(INDEX_OPTION));

    LOG.info("Indexing " + cmdline.getOptionValue(INPUT_OPTION));
    StatusStream stream;

    File file = new File(cmdline.getOptionValue(INPUT_OPTION));
    if (!file.exists()) {
      System.err.println("Error: " + file + " does not exist!");
      System.exit(-1);
    }

    if (file.isDirectory()) {
      stream = new JsonStatusCorpusReader(file);
    } else {
      stream = new JsonStatusBlockReader(file);
    }

    Analyzer analyzer = ANALYZER;
    Similarity similarity = new ConstantNormSimilarity();
    IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_31, analyzer);
    config.setSimilarity(similarity);
    config.setOpenMode(IndexWriterConfig.OpenMode.CREATE); // Overwrite existing.

    IndexWriter writer = new IndexWriter(FSDirectory.open(indexLocation), config);

    int cnt = 0;
    Status status;
    try {
      while ((status = stream.next()) != null) {
        if (status.getText() == null) {
          continue;
        }

        cnt++;
        String createdAt = status.getCreatedAt();
        Document doc = new Document();
        doc.add(new Field(StatusField.ID.name, status.getId() + "",
            Store.YES, Index.NOT_ANALYZED_NO_NORMS));
        doc.add(new Field(StatusField.SCREEN_NAME.name, status.getScreenname(),
            Store.YES, Index.NOT_ANALYZED_NO_NORMS));
        doc.add(new Field(StatusField.CREATED_AT.name, createdAt, Store.YES, Index.NO));
        doc.add(new Field(StatusField.TEXT.name, status.getText(), Store.YES, Index.ANALYZED));

        String[] arr = createdAt.split(" ");
        String createDay = new StringBuffer().append(arr[1]).append("_").append(arr[2]).toString();
        doc.add(new Field(StatusField.DAY.name, createDay, Store.YES, Index.NOT_ANALYZED_NO_NORMS));

        writer.addDocument(doc);
        if (cnt % 10000 == 0) {
          LOG.info(cnt + " statuses indexed");
        }
      }
      LOG.info("Optimizing index...");
      writer.optimize();
      writer.close();
    } finally {
      stream.close();
    }

    LOG.info(String.format("Total of %s statuses indexed", cnt));
  }
View Full Code Here
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
      System.exit(-1);
    }

    PrintStream out = new PrintStream(System.out, true, "UTF-8");

    StatusStream stream;
    // Figure out if we're reading from HTML SequenceFiles or JSON.
    File file = new File(cmdline.getOptionValue(INPUT_OPTION));
    if (!file.exists()) {
      System.err.println("Error: " + file + " does not exist!");
      System.exit(-1);
    }

    if (file.isDirectory()) {
      stream = new JsonStatusCorpusReader(file);
    } else {
      stream = new JsonStatusBlockReader(file);
    }

    int cnt = 0;
    Status status;
    while ((status = stream.next()) != null) {
      if (cmdline.hasOption(DUMP_OPTION)) {
        String text = status.getText();
        if (text != null) {
          text = text.replaceAll("\\s+", " ");
          text = text.replaceAll("\0", "");
        }
        out.println(String.format("%d\t%s\t%s\t%s", status.getId(), status.getScreenname(),
            status.getCreatedAt(), text));
      }
      cnt++;
      if ( cnt % 10000 == 0 && cmdline.hasOption(VERBOSE_OPTION)) {
        LOG.info(cnt + " statuses read");
      }
    }
    stream.close();
    LOG.info(String.format("Total of %s statuses read.", cnt));
  }
View Full Code Here
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
      System.err.println("Error: " + file + " does not exist!");
      System.exit(-1);
    }

    PrintStream out = new PrintStream(System.out, true, "UTF-8");
    StatusStream stream = new JsonStatusCorpusReader(file);
    Status status;
    while ((status = stream.next()) != null) {
      if (tweetids.contains(status.getId())) {
        out.println(status.getJsonObject().toString());
      }
    }
    stream.close();
    out.close();
  }
View Full Code Here
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
    LongOpenHashSet seen = new LongOpenHashSet();
    TreeMap<Long, String> tweets = Maps.newTreeMap();

    PrintStream out = new PrintStream(System.out, true, "UTF-8");
    StatusStream stream = new JsonStatusCorpusReader(file);
    Status status;
    int cnt = 0;
    while ((status = stream.next()) != null) {
      if (!tweetids.contains(status.getId())) {
        LOG.error("tweetid " + status.getId() + " doesn't belong in collection");
        continue;
      }
      if (seen.contains(status.getId())) {
        LOG.error("tweetid " + status.getId() + " already seen!");
        continue;
      }

      tweets.put(status.getId(), status.getJsonObject().toString());
      seen.add(status.getId());
      cnt++;
    }
    LOG.info("total of " + cnt + " tweets in subcollection.");

    for ( Map.Entry<Long, String> entry : tweets.entrySet()){
      out.println(entry.getValue());
    }

    stream.close();
    out.close();
  }
View Full Code Here
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
  }

  public boolean verify() throws IOException {
    LOG.info(String.format("Reading statuses read from %s.", statuses));

    StatusStream stream;
    if (statuses.isDirectory()) {
      throw new RuntimeException(statuses + " cannot be a directory!");
    }
    stream = new JsonStatusBlockReader(statuses);

    Map<Long, String> ids = new HashMap<Long, String>();

    int cnt = 0;
    Status status;
    while ((status = stream.next()) != null) {
      ids.put(status.getId(), status.getJsonString());
      cnt++;
    }
    LOG.info(String.format("Total of %d statuses read.", cnt));
View Full Code Here
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
    if (!file.exists()) {
      System.err.println("Error: " + file + " does not exist!");
      System.exit(-1);
    }

    StatusStream stream = new JsonStatusCorpusReader(file);

    Directory dir = FSDirectory.open(new File(indexPath));
    IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_43, IndexStatuses.ANALYZER);
    config.setOpenMode(OpenMode.CREATE);

    LOG.info("collection: " + collectionPath);
    LOG.info("index: " + indexPath);

    IndexWriter writer = new IndexWriter(dir, config);
    int cnt = 0;
    Status status;
    try {
      while ((status = stream.next()) != null) {
        if (status.getText() == null) {
          continue;
        }

        cnt++;
        Document doc = new Document();
        doc.add(new LongField(StatusField.ID.name, status.getId(), Field.Store.YES));
        doc.add(new LongField(StatusField.EPOCH.name, status.getEpoch(), Field.Store.YES));
        doc.add(new TextField(StatusField.SCREEN_NAME.name, status.getScreenname(), Store.YES));

        doc.add(new Field(StatusField.TEXT.name, status.getText(), textOptions));

        doc.add(new IntField(StatusField.FRIENDS_COUNT.name, status.getFollowersCount(), Store.YES));
        doc.add(new IntField(StatusField.FOLLOWERS_COUNT.name, status.getFriendsCount(), Store.YES));
        doc.add(new IntField(StatusField.STATUSES_COUNT.name, status.getStatusesCount(), Store.YES));

        long inReplyToStatusId = status.getInReplyToStatusId();
        if (inReplyToStatusId > 0) {
          doc.add(new LongField(StatusField.IN_REPLY_TO_STATUS_ID.name, inReplyToStatusId, Field.Store.YES));
          doc.add(new LongField(StatusField.IN_REPLY_TO_USER_ID.name, status.getInReplyToUserId(), Field.Store.YES));
        }
       
        String lang = status.getLang();
        if (!lang.equals("unknown")) {
          doc.add(new TextField(StatusField.LANG.name, status.getLang(), Store.YES));
        }
       
        long retweetStatusId = status.getRetweetedStatusId();
        if (retweetStatusId > 0) {
          doc.add(new LongField(StatusField.RETWEETED_STATUS_ID.name, retweetStatusId, Field.Store.YES));
          doc.add(new LongField(StatusField.RETWEETED_USER_ID.name, status.getRetweetedUserId(), Field.Store.YES));
          doc.add(new IntField(StatusField.RETWEET_COUNT.name, status.getRetweetCount(), Store.YES));
          if ( status.getRetweetCount() < 0 || status.getRetweetedStatusId() < 0) {
            LOG.warn("Error parsing retweet fields of " + status.getId());
          }
        }
       
        writer.addDocument(doc);
        if (cnt % 100000 == 0) {
          LOG.info(cnt + " statuses indexed");
        }
      }

      LOG.info(String.format("Total of %s statuses added", cnt));
     
      if (cmdline.hasOption(OPTIMIZE_OPTION)) {
        LOG.info("Merging segments...");
        writer.forceMerge(1);
        LOG.info("Done!");
      }

      LOG.info("Total elapsed time: " + (System.currentTimeMillis() - startTime) + "ms");
    } catch (Exception e) {
      e.printStackTrace();
    } finally {
      writer.close();
      dir.close();
      stream.close();
    }
  }
View Full Code Here
45
46
47
48
49
50
51
52
53
54
55
56
    if (!file.exists()) {
      System.err.println("Error: " + file + " does not exist!");
      System.exit(-1);
    }

    StatusStream stream = new JsonStatusCorpusReader(file);

    Status status;
    while ((status = stream.next()) != null) {
      System.out.println(status.getId() + "\t" + status.getScreenname());
    }
  }
View Full Code Here
61
62
63
64
65
66
67
68
69
70
71
72
    if (!file.exists()) {
      System.err.println("Error: " + file + " does not exist!");
      System.exit(-1);
    }

    StatusStream stream = new JsonStatusCorpusReader(file);

    Status status;
    while ((status = stream.next()) != null) {
      System.out.println(status.getId() + "\t" + status.getScreenname());
    }
  }
View Full Code Here
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
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
262
263
264
265
    if (!file.exists()) {
      System.err.println("Error: " + file + " does not exist!");
      System.exit(-1);
    }

    StatusStream stream = new JsonStatusCorpusReader(file);

    Directory dir = FSDirectory.open(new File(indexPath));
    IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_43, IndexStatuses.ANALYZER);
    config.setOpenMode(OpenMode.CREATE);

    IndexWriter writer = new IndexWriter(dir, config);
    int cnt = 0;
    Status status;
    try {
      while ((status = stream.next()) != null) {
        if (status.getText() == null) {
          continue;
        }

        // Skip deletes tweetids.
        if (deletes != null && deletes.contains(status.getId())) {
          continue;
        }

        if (status.getId() > maxId) {
          continue;
        }

        cnt++;
        Document doc = new Document();
        doc.add(new LongField(StatusField.ID.name, status.getId(), Field.Store.YES));
        doc.add(new LongField(StatusField.EPOCH.name, status.getEpoch(), Field.Store.YES));
        doc.add(new TextField(StatusField.SCREEN_NAME.name, status.getScreenname(), Store.YES));

        doc.add(new Field(StatusField.TEXT.name, status.getText(), textOptions));

        doc.add(new IntField(StatusField.FRIENDS_COUNT.name, status.getFollowersCount(), Store.YES));
        doc.add(new IntField(StatusField.FOLLOWERS_COUNT.name, status.getFriendsCount(), Store.YES));
        doc.add(new IntField(StatusField.STATUSES_COUNT.name, status.getStatusesCount(), Store.YES));

        long inReplyToStatusId = status.getInReplyToStatusId();
        if (inReplyToStatusId > 0) {
          doc.add(new LongField(StatusField.IN_REPLY_TO_STATUS_ID.name, inReplyToStatusId, Field.Store.YES));
          doc.add(new LongField(StatusField.IN_REPLY_TO_USER_ID.name, status.getInReplyToUserId(), Field.Store.YES));
        }
       
        String lang = status.getLang();
        if (!lang.equals("unknown")) {
          doc.add(new TextField(StatusField.LANG.name, status.getLang(), Store.YES));
        }
       
        long retweetStatusId = status.getRetweetedStatusId();
        if (retweetStatusId > 0) {
          doc.add(new LongField(StatusField.RETWEETED_STATUS_ID.name, retweetStatusId, Field.Store.YES));
          doc.add(new LongField(StatusField.RETWEETED_USER_ID.name, status.getRetweetedUserId(), Field.Store.YES));
          doc.add(new IntField(StatusField.RETWEET_COUNT.name, status.getRetweetCount(), Store.YES));
          if ( status.getRetweetCount() < 0 || status.getRetweetedStatusId() < 0) {
            LOG.warn("Error parsing retweet fields of " + status.getId());
          }
        }
       
        writer.addDocument(doc);
        if (cnt % 100000 == 0) {
          LOG.info(cnt + " statuses indexed");
        }
      }

      LOG.info(String.format("Total of %s statuses added", cnt));
     
      if (cmdline.hasOption(OPTIMIZE_OPTION)) {
        LOG.info("Merging segments...");
        writer.forceMerge(1);
        LOG.info("Done!");
      }

      LOG.info("Total elapsed time: " + (System.currentTimeMillis() - startTime) + "ms");
    } catch (Exception e) {
      e.printStackTrace();
    } finally {
      writer.close();
      dir.close();
      stream.close();
    }
  }
View Full Code Here
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
    String collectionPath = cmdline.getOptionValue(COLLECTION_OPTION);
    String indexPath = cmdline.getOptionValue(INDEX_OPTION);

    long startTime = System.currentTimeMillis();

    StatusStream stream;

    File file = new File(collectionPath);
    if (!file.exists()) {
      System.err.println("Error: " + file + " does not exist!");
      System.exit(-1);
    }

    if (cmdline.hasOption(TSV_OPTION)) {
      stream = new TSVStatusCorpusReader(file);
    } else {
      stream = new JsonStatusCorpusReader(file);
    }

    Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_41);

    Directory dir = FSDirectory.open(new File(indexPath));
    IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_41, analyzer);
    config.setOpenMode(OpenMode.CREATE);

    LOG.info("collection: " + collectionPath);
    LOG.info("index: " + indexPath);

    IndexWriter writer = new IndexWriter(dir, config);
    int cnt = 0;
    Status status;
    try {
      while ((status = stream.next()) != null) {
        if (status.getText() == null) {
          continue;
        }

        cnt++;
        Document doc = new Document();
        doc.add(new LongField(StatusField.ID.name, status.getId(), Field.Store.YES));
        doc.add(new LongField(StatusField.EPOCH.name, status.getEpoch(), Field.Store.YES));
        doc.add(new TextField(StatusField.SCREEN_NAME.name, status.getScreenname(), Store.YES));
        doc.add(new TextField(StatusField.TEXT.name, status.getText(), Store.YES));

        doc.add(new IntField(StatusField.FRIENDS_COUNT.name, status.getFollowersCount(), Store.YES));
        doc.add(new IntField(StatusField.FOLLOWERS_COUNT.name, status.getFriendsCount(), Store.YES));
        doc.add(new IntField(StatusField.STATUSES_COUNT.name, status.getStatusesCount(), Store.YES));

        long inReplyToStatusId = status.getInReplyToStatusId();
        if (inReplyToStatusId > 0) {
          doc.add(new LongField(StatusField.IN_REPLY_TO_STATUS_ID.name, inReplyToStatusId, Field.Store.YES));
          doc.add(new LongField(StatusField.IN_REPLY_TO_USER_ID.name, status.getInReplyToUserId(), Field.Store.YES));
        }
       
        String lang = status.getLang();
        if (!lang.equals("unknown")) {
          doc.add(new TextField(StatusField.LANG.name, status.getLang(), Store.YES));
        }
       
        long retweetStatusId = status.getRetweetedStatusId();
        if (retweetStatusId > 0) {
          doc.add(new LongField(StatusField.RETWEETED_STATUS_ID.name, retweetStatusId, Field.Store.YES));
          doc.add(new LongField(StatusField.RETWEETED_USER_ID.name, status.getRetweetedUserId(), Field.Store.YES));
          doc.add(new IntField(StatusField.RETWEET_COUNT.name, status.getRetweetCount(), Store.YES));
          if ( status.getRetweetCount() < 0 || status.getRetweetedStatusId() < 0) {
            LOG.warn("Error parsing retweet fields of " + status.getId());
          }
        }
       
        writer.addDocument(doc);
        if (cnt % 100000 == 0) {
          LOG.info(cnt + " statuses indexed");
        }
      }

      LOG.info(String.format("Total of %s statuses added", cnt));
      LOG.info("Merging segments...");
      writer.forceMerge(1);
      LOG.info("Done!");
      LOG.info("Total elapsed time: " + (System.currentTimeMillis() - startTime) + "ms");
    } catch (Exception e) {
      e.printStackTrace();
    } finally {
      writer.close();
      dir.close();
      stream.close();
    }
  }
View Full Code Here
TOP

Related Classes of cc.twittertools.corpus.data.StatusStream

  • cc.twittertools.corpus.demo.IndexStatuses
  • cc.twittertools.corpus.demo.ReadStatuses
  • cc.twittertools.download.VerifyJsonStatusBlockCrawl
  • cc.twittertools.index.ExtractTweetidsFromCollection
  • cc.twittertools.index.IndexStatuses
  • cc.twittertools.search.indexing.IndexStatuses
  • cc.twittertools.util.ExtractSubcollection
  • cc.twittertools.util.VerifySubcollection
    • 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.