Skip to content
Navigation Menu
{{ message }}
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathGetUserStatus.java
More file actions
349 lines (310 loc) · 13.8 KB
/
Copy pathGetUserStatus.java
File metadata and controls
349 lines (310 loc) · 13.8 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
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
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
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
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
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
import java.io.BufferedWriter;
import java.io.File;
import java.io.FileOutputStream;
import java.io.FileWriter;
import java.io.IOException;
import java.io.OutputStreamWriter;
import java.text.DateFormat;
import java.text.SimpleDateFormat;
import java.util.ArrayList;
import java.util.Date;
import java.util.List;
import java.util.Map;
import java.util.Properties;
import java.util.TimeZone;
import com.google.gson.Gson;
import edu.stanford.nlp.dcoref.CorefChain;
import edu.stanford.nlp.dcoref.CorefCoreAnnotations.CorefChainAnnotation;
import edu.stanford.nlp.ling.CoreLabel;
import edu.stanford.nlp.ling.CoreAnnotations.NamedEntityTagAnnotation;
import edu.stanford.nlp.ling.CoreAnnotations.PartOfSpeechAnnotation;
import edu.stanford.nlp.ling.CoreAnnotations.SentencesAnnotation;
import edu.stanford.nlp.ling.CoreAnnotations.TextAnnotation;
import edu.stanford.nlp.ling.CoreAnnotations.TokensAnnotation;
import edu.stanford.nlp.pipeline.*;
import edu.stanford.nlp.pipeline.Annotation;
import edu.stanford.nlp.pipeline.StanfordCoreNLP;
import edu.stanford.nlp.semgraph.SemanticGraph;
import edu.stanford.nlp.semgraph.SemanticGraphCoreAnnotations.CollapsedCCProcessedDependenciesAnnotation;
import edu.stanford.nlp.trees.Tree;
import edu.stanford.nlp.trees.TreeCoreAnnotations.TreeAnnotation;
import edu.stanford.nlp.util.CoreMap;
import twitter4j.HashtagEntity;
import twitter4j.Paging;
import twitter4j.Query;
import twitter4j.QueryResult;
import twitter4j.ResponseList;
import twitter4j.Status;
import twitter4j.TweetEntity;
import twitter4j.Twitter;
import twitter4j.TwitterException;
import twitter4j.TwitterFactory;
import twitter4j.URLEntity;
import twitter4j.auth.AccessToken;
public class GetUserStatus {
public static void main(String[] args) {
Query englishQuery = new Query("Paris Attack");
englishQuery.setLang("en");
Query germanQuery= new Query("Paris Angriff");
germanQuery.setLang("de");
Query russianQuery= new Query("Париж Атака");
russianQuery.setLang("ru");
Query arabicQuery= new Query("باريس هجوم");
arabicQuery.setLang("ar");
Query frenchQuery= new Query("Paris Attaque");
frenchQuery.setLang("fr");
List<Query> queryList=new ArrayList<Query>();
//queryList.add(englishQuery);
//queryList.add(russianQuery);
//queryList.add(germanQuery);
queryList.add(arabicQuery);
//queryList.add(frenchQuery);
Twitter twitter= new TwitterFactory().getInstance();
twitter.setOAuthConsumer("2auhiiDGj3V8j0U7gotdjzM75","olL59ab0bGcekV8FeahdHI0308CXkVfRNThcpKeeSdsKWnm3X9");
twitter.setOAuthAccessToken(new AccessToken("3523962137-u1cV7n6QmM0VXw16J6rHF2AgPt6y2Y7L6jtpUah","xfQqireAobRH7fL11Mf9WpgZDSZVtscDc9ZX9Zy0iCqWb"));
try{
QueryResult result;
int count=0;
for(Query query : queryList){
count++;
query.setCount(100);
result=twitter.search(query);
//result=twitter.search(englishQuery);
//System.out.println("Twitter Counts for lang " + count + " : " + result.getCount());
//------------
/*int numberOfTweets = 2000;
long lastID = Long.MAX_VALUE;
ArrayList<Status> tweets = new ArrayList<Status>();
while (tweets.size () < numberOfTweets)
{
if (numberOfTweets - tweets.size() > 100)
query.setCount(100);
else
query.setCount(numberOfTweets - tweets.size());
//QueryResult result = twitter.search(query);
tweets.addAll(result.getTweets());
System.out.println("Gathered " + tweets.size() + " tweets"+"\n");
for (Status t: tweets)
if(t.getId() < lastID)
lastID = t.getId();;
query.setMaxId(lastID-1);
}*/
//------------
//List<Status> statusList = result.getTweets(); //Keval
ArrayList<Status> tweets = new ArrayList<Status>();
tweets.addAll(result.getTweets());
List<UserEntity> userEntitiesList= new ArrayList<UserEntity>();
for (Status tweet : tweets) {
UserEntity userEntity=new UserEntity();
//userEntity.setText_en(tweet.getText());
//userEntity.setText_ru(tweet.getText());
//userEntity.setText_de(tweet.getText());
userEntity.setText_ar(tweet.getText());
//userEntity.setText_fr(tweet.getText());
/*if(count==1){
userEntity.setText_en(tweet.getText());
}
else if(count==2){
userEntity.setText_ru(tweet.getText());
}
else if(count==3){
userEntity.setText_de(tweet.getText());
}
else if(count==4){
userEntity.setText_ar(tweet.getText());
}
else if(count==5){
userEntity.setText_fr(tweet.getText());
}*/
userEntity.setCreated_at(GetUserStatus.tweeterToSolrDateConverter(tweet.getCreatedAt()));
userEntity.setTweetSource(tweet.getSource());
userEntity.setUserId(tweet.getUser().getId());
userEntity.setLang(tweet.getLang());
userEntity.setUserLocation(tweet.getUser().getLocation());
userEntity.setUserName(tweet.getUser().getName());
userEntity.setUserScreenName(tweet.getUser().getScreenName());
userEntity.setUserTimeZone(tweet.getUser().getTimeZone());
userEntity.setMentionedURLInTweet(tweet.getUser().getURLEntity().getURL());
userEntity.setUserDescription(tweet.getUser().getDescription());
//userEntity.setTweet_urls(tweet.getUser().getURLEntity().getExpandedURL());
List<String> urlEntitiesList= new ArrayList<String>();
for(URLEntity urlEntity : tweet.getURLEntities()){
urlEntitiesList.add(urlEntity.getExpandedURL());
}
userEntity.setTweet_urls(urlEntitiesList);
List<String> hashtagsText = new ArrayList<String>();
for(HashtagEntity hashtagEntity : tweet.getHashtagEntities()){
hashtagsText.add(hashtagEntity.getText());
}
//System.out.println(hashtagsText);
userEntity.setTweet_hashtags(hashtagsText);
userEntitiesList.add(GetUserStatus.stanfordTagger(userEntity));
}
Gson gson= new Gson();
String userEntityJSON = gson.toJson(userEntitiesList);
//System.out.println("UserEntity : "+ userEntityJSON);
new File("Json_Files_New").mkdir();
//String fileName = "Json_Files/Arabic.json";
FileOutputStream fileOutStream = null;
OutputStreamWriter outStreamWriter = null;
BufferedWriter bufferedWriter = null;
try {
fileOutStream = new FileOutputStream("Json_Files_New/Arabic_ParisAttack_1.json");
outStreamWriter = new OutputStreamWriter(fileOutStream, "UTF-8");
bufferedWriter = new BufferedWriter(outStreamWriter);
bufferedWriter.write(userEntityJSON);
bufferedWriter.flush();
System.out.println("Successfully Done");
/*if(count==1){
fileOutStream = new FileOutputStream("Json_Files/English.json");
outStreamWriter = new OutputStreamWriter(fileOutStream, "UTF-8");
bufferedWriter = new BufferedWriter(outStreamWriter);
bufferedWriter.write(userEntityJSON);
bufferedWriter.flush();
System.out.println("Successfully entered English data");
/*
FileWriter fileWriter=new FileWriter("JsonFiles/English.json", true);
fileWriter.write(userEntityJSON);
fileWriter.close();
System.out.println("Successfully entered English data");
}
else if (count==2) {
fileOutStream = new FileOutputStream("Json_Files/Russian.json");
outStreamWriter = new OutputStreamWriter(fileOutStream, "UTF-8");
bufferedWriter = new BufferedWriter(outStreamWriter);
bufferedWriter.write(userEntityJSON);
bufferedWriter.flush();
/*FileWriter fileWriter=new FileWriter("JsonFiles/Russian.json", true);
fileWriter.write(userEntityJSON);
fileWriter.close();
//System.out.println("UserEntity : "+ userEntityJSON);
System.out.println("successfully entered Russian data");
}
else if (count==3){
fileOutStream = new FileOutputStream("Json_Files/German.json");
outStreamWriter = new OutputStreamWriter(fileOutStream, "UTF-8");
bufferedWriter = new BufferedWriter(outStreamWriter);
bufferedWriter.write(userEntityJSON);
bufferedWriter.flush();
/*
FileWriter fileWriter=new FileWriter("JsonFiles/German.json", true);
fileWriter.write(userEntityJSON);
fileWriter.close();
System.out.println("successfully entered German data");
}
else if (count==4){
fileOutStream = new FileOutputStream("Json_Files/Arabic.json");
outStreamWriter = new OutputStreamWriter(fileOutStream, "UTF-8");
bufferedWriter = new BufferedWriter(outStreamWriter);
bufferedWriter.write(userEntityJSON);
bufferedWriter.flush();
/*
FileWriter fileWriter=new FileWriter("JsonFiles/Arabic.json", true);
fileWriter.write(userEntityJSON);
fileWriter.close();
System.out.println("successfully entered Arabic data");
}
else if (count==5){
fileOutStream = new FileOutputStream("Json_Files/French.json");
outStreamWriter = new OutputStreamWriter(fileOutStream, "UTF-8");
bufferedWriter = new BufferedWriter(outStreamWriter);
bufferedWriter.write(userEntityJSON);
bufferedWriter.flush();
/*
FileWriter fileWriter=new FileWriter("JsonFiles/French.json", true);
fileWriter.write(userEntityJSON);
fileWriter.close();
System.out.println("successfully entered French data");
}*/
} catch (IOException e) {
// TODO Auto-generated catch block
System.out.println("Error while creating File");
e.printStackTrace();
}
}
System.exit(0);
}catch(TwitterException te) {
te.printStackTrace();
System.out.println("Failed to search tweets: " + te.getMessage());
System.exit(-1);
}
}
public static String tweeterToSolrDateConverter(Date tweeterDate){
DateFormat df = new SimpleDateFormat("YYYY-MM-dd'T'hh:mm:ss'Z'");
df.setTimeZone(TimeZone.getTimeZone("UTC"));
return df.format(tweeterDate);
}
public static UserEntity stanfordTagger(UserEntity userEntity) {
// creates a StanfordCoreNLP object, with POS tagging, lemmatization, NER, parsing, and coreference resolution
Properties props = new Properties();
props.setProperty("annotators", "tokenize, ssplit, pos, lemma, ner, parse, dcoref, regexner");
StanfordCoreNLP pipeline = new StanfordCoreNLP(props);
// read some text in the text variable
/* BufferedReader bufferReader = new BufferedReader(new FileReader(args[0]));
while ((wordString = bufferReader.readLine()) != null) {*/
//String text = userEntity.getText_en();
//String text = userEntity.getText_ru(); // Add your text here!
//String text = userEntity.getText_de();
String text = userEntity.getText_ar();
//String text = userEntity.getText_fr();
// create an empty Annotation just with the given text
Annotation document = new Annotation(text);
// run all Annotators on this text
pipeline.annotate(document);
// these are all the sentences in this document
// a CoreMap is essentially a Map that uses class objects as keys and has values with custom types
List<CoreMap> sentences = document.get(SentencesAnnotation.class);
List<String> organizations=new ArrayList<String>();
List<String> person=new ArrayList<String>();
List<String> location=new ArrayList<String>();
for(CoreMap sentence: sentences) {
// traversing the words in the current sentence
// a CoreLabel is a CoreMap with additional token-specific methods
for (CoreLabel token: sentence.get(TokensAnnotation.class)) {
// this is the text of the token
String word = token.get(TextAnnotation.class);
// this is the POS tag of the token
//String pos = token.get(PartOfSpeechAnnotation.class);
// this is the NER label of the token
String ne = token.get(NamedEntityTagAnnotation.class);
if(ne.equals("ORGANIZATION")){
if(!organizations.contains(word)){
organizations.add(word);
}
}
else if(ne.equals("LOCATION")){
if(!location.contains(word)){
location.add(word);
}
}
else if(ne.equals("PERSON")){
if(!person.contains(word)){
person.add(word);
}
}
// this is the sentiment label of the token
//String sentiment = token.get(SentimentCoreAnnotations.SentimentClass.class);
//this is the relationship label of the token MachineReadingAnnotations
//String relation = token.get(MachineReadingAnnotations.RelationMentionsAnnotation.class).toString();
//System.out.println("word: "+word+", pos: "+pos+", ne: "+ne+", token:"+token.toString());
}
// this is the parse tree of the current sentence
// Tree tree = sentence.get(TreeAnnotation.class);
//System.out.println("tree: "+tree.toString());
// this is the Stanford dependency graph of the current sentence
//SemanticGraph dependencies = sentence.get(CollapsedCCProcessedDependenciesAnnotation.class);
//System.out.println("dependencies: "+dependencies.toString());
}
userEntity.setOrganizationTag(organizations);
userEntity.setLocationTag(location);
userEntity.setPersonTag(person);
// This is the coreference link graph
// Each chain stores a set of mentions that link to each other,
// along with a method for getting the most representative mention
// Both sentence and token offsets start at 1!
// Map<Integer, CorefChain> graph =
document.get(CorefChainAnnotation.class);
System.out.println("userEntity:"+userEntity.toString());
return userEntity;
}
}
You can’t perform that action at this time.