8/11/2019 Opennlp-servlet

1/3

9/3/2014 Opennlp-servlet

https://gist.github.com/spatzle/1104702 1/3

Opennlp-servlet

spatzle/ OpennlpServlet.javaCreated on Jul 25, 2011

1

2

3

4

5

6

7

8

9

10

11

12

13

14

1516

17

18

19

20

21

22

23

24

25

26

27

28

29

30

31

32

3334

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

6869

70

71

72

73

74

packagecom.example.opennlp;

importjava.io.*;

importjava.util.ArrayList;

importjava.util.Arrays;

importjava.util.Map;

importjava.util.TreeSet;

importjavax.servlet.*;

importjavax.servlet.http.*;

importcom.google.gson.Gson;

importopennlp.tools.dictionary.Dictionary;

importopennlp.tools.namefind.DictionaryNameFinder;importopennlp.tools.namefind.NameFinderME;

importopennlp.tools.namefind.TokenNameFinder;

importopennlp.tools.namefind.TokenNameFinderModel;

importopennlp.tools.util.Span;

importopennlp.tools.util.StringList;

importopennlp.tools.tokenize.TokenizerModel;

importopennlp.tools.tokenize.TokenizerME;

/**

* This is a servlet interface to the Opennlp maxent classifier.

*

* @author Joyce Chan 2011

**/

publicclassOpennlpServletextendsHttpServlet {

privateTokenNameFinder f_nameFinder; privateTokenNameFinder r_nameFinder;

privateTokenizerME tokenizer ;

privateTokenizerME tokenizer_internal_use ;

privateTreeSetstopwords =newTreeSet();

privatefinalString ENGLISH_STOP_WORDS[]={

"a","an","and","are","as","at","be","but","by",

"for","if","in","into","is","it",

"no","not","of","on","or","such",

"that","the","their","then","there","these",

"they","this","to","was","will","with"

};

privateDictionary r_dictionary;

privatestaticfinallongserialVersionUID =1L;

privateTokenizerME getTokenizer(String tokenizer_title)throwsServletException{

String title;

String location;

TokenizerME tokenizer =null;

// get default classifier

title =getServletConfig().getInitParameter(tokenizer_title);

if(title ==null||title.trim().equals(""))thrownewServletException("Default Tokenize

location =getServletConfig().getInitParameter(title);

if(location ==null||location.trim().equals(""))thrownewServletException("Tokenizer

InputStream stream =getServletConfig().getServletContext().getResourceAsStream(location);

if(stream ==null)thrownewServletException("File not found. Filename = "+location);

try{

tokenizer =newTokenizerME(newTokenizerModel(newBufferedInputStream(stream)));

}catch(IOException e){

try{

stream =newFileInputStream(location);

}catch(IOException e2){

thrownewServletException("IO problem reading tokenizer A. "+location); }

thrownewServletException("IO problem reading tokenizer B.");

}

finally{

if(stream !=null){

try{stream.close();}catch(IOException e){}

OpennlpServlet.java

https://gist.github.com/https://gist.github.com/spatzlehttps://gist.github.com/https://gist.github.com/spatzle/1104702https://gist.github.com/spatzlehttps://gist.github.com/

8/11/2019 Opennlp-servlet

2/3

9/3/2014 Opennlp-servlet

https://gist.github.com/spatzle/1104702 2/3

75

76

77

78

79

80

81

82

83

84

85

86

8788

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

122123

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

157158

159

160

161

162

163

}

}returntokenizer;

}//end getTokenModel

// for ner

privateTokenNameFinder getNameFinder(String classifier_title)throwsServletException{

String title;

String location;

TokenNameFinder nmFinder =null;

// get default classifier

title =getServletConfig().getInitParameter(classifier_title);

if(title ==null||title.trim().equals(""))thrownewServletException("Default classifi

location =getServletConfig().getInitParameter(title); if(location ==null||location.trim().equals(""))thrownewServletException("Classifier

InputStream filestream =getServletConfig().getServletContext().getResourceAsStream(locati

if(filestream ==null)thrownewServletException("File not found. Filename = "+location);

try{

nmFinder =newNameFinderME(newTokenNameFinderModel(newBufferedInputStream(filestream))

}catch(IOException e){

thrownewServletException("IO problem reading classifier.");

}finally{

if(filestream !=null){

try{filestream.close();}catch(IOException e){}

}

}returnnmFinder;

}//end getTokenNameFinder

privateDictionaryNameFinder getDictionaryNameFinder(String filetitle)throwsServletException{

r_dictionary =newDictionary();

String title;

String location;

title =getServletConfig().getInitParameter(filetitle);

if(title ==null||title.trim().equals(""))thrownewServletException("Default classifi

location =getServletConfig().getInitParameter(title);

if(location ==null||location.trim().equals(""))thrownewServletException("Classifier

InputStream filestream = getServletConfig().getServletContext().getResourceAsStream(locat

if(filestream ==null)thrownewServletException("File not found. Filename = "+location);

try{

BufferedReader br =newBufferedReader(newInputStreamReader(newDataInputStream(f

String strLine;

while((strLine =br.readLine())!=null){

//change to lower case, remove commas, tokenize, remove stop words

String s[]=removeStopWordsFromSentence(tokenizer.tokenize(strLine.toLowe

putInDict(r_dictionary,s);

for(inti =0;i

8/11/2019 Opennlp-servlet

3/3

9/3/2014 Opennlp-servlet

https://gist.github.com/spatzle/1104702 3/3

164

165

166

167

168

169

170

171

172

173

174

175

176177

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

211212

213

214

215

216

217

218

219

220

221

222

223

224

225

226

227

228

229

230

String sentence =request.getParameter("sentence");

String tokens[]=removeStopWordsFromSentence(tokenizer.tokenize(sentence.toLowerC

Span spannames[]=null;

if(reqMap.containsKey("dict")&&request.getParameter("dict").equals("on")){

spannames =r_nameFinder.find(tokens);

}else{

spannames =f_nameFinder.find(tokens);

}

names =Span.spansToStrings(spannames,tokens);

if(reqMap.containsKey("wt")&&request.getParameter("wt").equals("json")){

printAsJson(response,pw,names);

}elseprintAsHtml(response,pw,names);

}

}//end doPost

// private methods

privatevoidaddToStopWords(){

for(inti=0;i