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
|
/* TweetTracker. Copyright (c) Arizona Board of Regents on behalf of Arizona State University
* @author shamanth
*/
package Chapter5.trends;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.text.ParseException;
import java.text.SimpleDateFormat;
import java.util.ArrayList;
import java.util.Collections;
import java.util.Date;
import java.util.HashMap;
import java.util.Set;
import java.util.logging.Level;
import java.util.logging.Logger;
import org.json.JSONArray;
import org.json.JSONException;
import org.json.JSONObject;
public class TrendComparisonExample
{
static final String DEF_INFILENAME = "ows.json";
static final SimpleDateFormat SDM = new SimpleDateFormat("dd MMM yyyy HH:mm");
public JSONArray GenerateDataTrend(String inFilename, ArrayList<String> keywords)
{
BufferedReader br = null;
JSONArray result = new JSONArray();
HashMap<String,HashMap<String,Integer>> datecount = new HashMap<String,HashMap<String,Integer>>();
try{
br= new BufferedReader(new InputStreamReader(new FileInputStream(inFilename),"UTF-8"));
String temp = "";
while((temp = br.readLine())!=null)
{
try {
JSONObject jobj = new JSONObject(temp);
String text = jobj.getString("text").toLowerCase();
long timestamp = jobj.getLong("timestamp");
Date d = new Date(timestamp);
String strdate = SDM.format(d);
for(String word:keywords)
{
if(text.contains(word))
{
HashMap<String,Integer> wordcount = new HashMap<String,Integer>();
if(datecount.containsKey(strdate))
{
wordcount = datecount.get(strdate);
}
if(wordcount.containsKey(word))
{
wordcount.put(word, wordcount.get(word)+1);
}
else
{
wordcount.put(word, 1);
}
//update the wordcount for the specific date
datecount.put(strdate, wordcount);
}
}
} catch (JSONException ex) {
Logger.getLogger(TrendComparisonExample.class.getName()).log(Level.SEVERE, null, ex);
}
}
//sort the dates
ArrayList<TCDateInfo> dinfos = new ArrayList<TCDateInfo>();
Set<String> keys = datecount.keySet();
for(String key:keys)
{
TCDateInfo dinfo = new TCDateInfo();
try {
dinfo.d = SDM.parse(key);
} catch (ParseException ex) {
ex.printStackTrace();
continue;
}
dinfo.wordcount = datecount.get(key);
dinfos.add(dinfo);
}
Collections.sort(dinfos);
//prepare the output
for(TCDateInfo date:dinfos)
{
JSONObject item = new JSONObject();
String strdate = SDM.format(date.d);
try{
item.put("date",strdate);
HashMap<String,Integer> wordcount = date.wordcount;
for(String word:keywords)
{
if(wordcount.containsKey(word))
{
item.put(word, wordcount.get(word));
}
else
{
item.put(word, 0);
}
}
result.put(item);
}catch(JSONException ex)
{
ex.printStackTrace();
}
}
}catch(IOException ex)
{
ex.printStackTrace();
}finally{
try {
br.close();
} catch (IOException ex) {
Logger.getLogger(TrendComparisonExample.class.getName()).log(Level.SEVERE, null, ex);
}
}
return result;
}
public static void main(String[] args)
{
TrendComparisonExample tce = new TrendComparisonExample();
ArrayList<String> words = new ArrayList<String>();
String infilename = DEF_INFILENAME;
if(args!=null)
{
if(args.length>=1&&!args[0].isEmpty())
{
File fl = new File(args[0]);
if(fl.exists())
{
infilename = args[0];
}
}
for(int i=1;i<args.length;i++)
{
if(args[i]!=null&&!args[i].isEmpty())
{
words.add(args[i]);
}
}
}
if(words.isEmpty())
{
words.add("#nypd");
words.add("#ows");
}
System.out.println(tce.GenerateDataTrend(infilename,words));
}
}
|
