Bonjour,
je vous souhaite à toutes et à tous une bonne année 2014, avec un peu de retard.
Je viens vous voir aujourd'hui car j'ai fais un script, qui prend en entrée un dossier (qui comprend deux autres dossiers, et chacun de ces deux dossiers comprend des fichiers .txt). Le but étant de lire les fichiers txt, comparer tous les mots de tout les fichiers, et supprimer les mots non fréquents.
Sauf, qu'à ma surprise, il me dit qu'il n'y pas de dossier, alors qu'il y est. Je ne comprend pas :s
Voici le script entier.
Voilà ce que ça me renvoi :
Code : Sélectionner tout - Visualiser dans une fenêtre à part
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 import java.io.File; import java.io.PrintWriter; import java.util.ArrayList; import java.util.HashMap; import java.util.Scanner; import java.util.StringTokenizer; public class suppMotsNonFrequents { //--------------------------------------------------------------------------------------------------------------- //NECESSARY OBJECTS protected ArrayList<String> corpusClasses = new ArrayList<String>(); protected ArrayList<ArrayList<String>> corpusDocuments = new ArrayList<ArrayList<String>>(); protected ArrayList<ArrayList<ArrayList<String>>> corpus = new ArrayList<ArrayList<ArrayList<String>>>(); protected HashMap<String,Integer> tableWordsIndex = new HashMap<String,Integer>(); protected HashMap<Integer,String> tableIndexWords = new HashMap<Integer,String>(); //--------------------------------------------------------------------------------------------------------------- //CONSTRUCTOR public suppMotsNonFrequents(){ super();} //--------------------------------------------------------------------------------------------------------------- //CORPUS INITIALIZER public void initializer(String corpusLocation) throws Exception { File corpusFilePath = new File(corpusLocation); //root directory File[] corpusFiles = null; File[] documentsFromClass = null; File documentLocationFile = null; ArrayList<String> document = new ArrayList<String>(); ArrayList<String> tempdocument = new ArrayList<String>(); ArrayList<ArrayList<String>> documents = new ArrayList<ArrayList<String>>(); //CHECKING IF IT EXISTS A FOLDER AND CHEACKING IF CLASS INSIDE if(corpusFilePath.exists() && corpusFilePath.isDirectory() && (corpusFilePath.listFiles().length > 0) ) { //GETTING CLASS LIST corpusFiles = corpusFilePath.listFiles(); //LOOP FOR EACH CLASS for(int i =0; i < corpusFiles.length; i++) { //SETTING UP ALL CLASS NAME this.corpusClasses.add(corpusFiles[i].getName()); //GETTING DOCUMENTS LIST FILE FROM CLASSE documentsFromClass = corpusFiles[i].listFiles(); //LOOP FOR EACH DOCUMENT for(int j =0; j < documentsFromClass.length; j++) { //GETTING DOCUMENTS LOCATION FILE NAME documentLocationFile = new File(documentsFromClass[j].getPath()); //GETTING EACH DOCUMENTS NAME tempdocument.add(documentLocationFile.getName()); //PROCESSING DOCUMENT this.processingDocument(documentLocationFile.getPath(),document); //CREATING DOCUMENTS LIST FOR EACH CLASS documents.add(document); //RESTARTING LISTS FOR NEXT LOOP document = new ArrayList<String>(); } //SETTING UP CORPUS DOCUMENTS NAME this.corpusDocuments.add(tempdocument); //SETTING UP THE CORPUS corpus.add(documents); //RESTARTING LISTS FOR NEXT LOOP documents = new ArrayList<ArrayList<String>>(); } } else { System.out.println("File doesn't exists.."); } } //--------------------------------------------------------------------------------------------------------------- //DOCUMENT READER METHOD public void processingDocument(String documentPath,ArrayList<String> document) throws Exception { Scanner documentReader = new Scanner(new File(documentPath)); ArrayList<String> lineWords = new ArrayList<String>(); String documentLine = new String(); //CREATING DOCUMENT while (documentReader.hasNext()) { documentLine = documentReader.next(); if(documentLine != null) { //GETTING LIST WORDS PAR LINE lineWords = processingLine(documentLine); for(int i =0; i < lineWords.size(); i++) { //CREATING DOCUMENT document.add(lineWords.get(i)); } } } //CLOSING BUFFED-READER documentReader.close(); } //--------------------------------------------------------------------------------------------------------------- //LINE READER METHOD public ArrayList<String> processingLine(String documentLine) { StringTokenizer tokens = new StringTokenizer(documentLine); ArrayList<String> words = new ArrayList<String>(); String word = new String(); while (tokens.hasMoreTokens()) { //SETTING ALL CHARACTERS ON LOWERCASE word = tokens.nextToken().toLowerCase(); words.add(word); } return words; } //--------------------------------------------------------------------------------------------------------------- //GETTING HOW MANY TIMES THE WORD IS USED ON THE CORPUS public int getFrequencyOfWordInCorpus(String word) { int frequencyOnCorpus = 0; for(int i =0; i< this.corpus.size();i++) { for(int j=0; j< this.corpus.get(i).size();j++) { for(int k = 0; k < corpus.get(i).get(j).size();k++) { if(word.equals(corpus.get(i).get(j).get(k).toString())) { frequencyOnCorpus ++; } } } } return frequencyOnCorpus; } //--------------------------------------------------------------------------------------------------------------- //NEW CORPUS CREATION METHOD public void createNewCorpus(String fileNamePath) throws Exception { if(corpus.size() > 0) { //CREATING FILE File file = null; PrintWriter writer = null; //GENERATING ELEMENTS for(int i =0; i< this.corpus.size();i++) { //FOLDER CLASS CREATION file = new File(fileNamePath+"/"+this.corpusClasses.get(i).toString()); if(file.mkdir()) { for(int j= 0; j< this.corpus.get(i).size();j++) { //DOCUMENT CREATION File file1 = new File(file.getPath()+"/"+this.corpusDocuments.get(i).get(j).toString()); file1.createNewFile(); //RESTARTING OBJECTS writer = new PrintWriter(file1.getPath()); String stringLine = new String(); for(int k = 0; k < this.corpus.get(i).get(j).size();k++) { //FREQUENCY PRESICION if(this.getFrequencyOfWordInCorpus(this.corpus.get(i).get(j).get(k).toString()) >= 10) { //TO CONCAT WORDS OF DOCUMENT stringLine += this.corpus.get(i).get(j).get(k).toString()+" "; } } //WRITING ON FILE writer.println(stringLine.substring(0, (stringLine.length()-1))); //CLOSING FILE writer.close(); } } } System.out.println("New corpus created successfully..."); } else {System.out.println("The corpus is not started...");} } //--------------------------------------------------------------------------------------------------------------- //MAIN FUCTION public static void main(String[] args) throws Exception { //CLASS INSTANCE suppMotsNonFrequents eraser = new suppMotsNonFrequents(); //NEEDED PATHS String corpusPath = "/Corpus"; String outputLocationPath = "/corpusNew"; //STARTING CORPUS eraser.initializer(corpusPath); //CERATING NEW CORPUS ORDER System.out.println(">>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>"); eraser.createNewCorpus(outputLocationPath); System.out.println(">>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>"); } //--------------------------------------------------------------------------------------------------------------- }
Pour info je suis sur eclipse (Mac Os X)File doesn't exists..
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
The corpus is not started...
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
En vous remerciant.
Partager