~slub.team/goobi-indexserver/3.x

BaseTokenStreamTestCase.assertAnalyzesTo(a, "Վիքիպեդիայի 13 միլիոն հոդվածները (4,600` հայերեն վիքիպեդիայում) գրվել են կամավորների կողմից ու համարյա բոլոր հոդվածները կարող է խմբագրել ցանկաց մարդ ով կարող է բացել Վիքիպեդիայի կայքը։",

new String[] { "Վիքիպեդիայի", "13", "միլիոն", "հոդվածները", "4,600", "հայերեն", "վիքիպեդիայում", "գրվել", "են", "կամավորների", "կողմից",

"ու", "համարյա", "բոլոր", "հոդվածները", "կարող", "է", "խմբագրել", "ցանկաց", "մարդ", "ով", "կարող", "է", "բացել", "Վիքիպեդիայի", "կայքը" } );

}

public void testAmharic() throws Exception {

BaseTokenStreamTestCase.assertAnalyzesTo(a, "ዊኪፔድያ የባለ ብዙ ቋንቋ የተሟላ ትክክለኛና ነጻ መዝገበ ዕውቀት (ኢንሳይክሎፒዲያ) ነው። ማንኛውም",

new String[] { "ዊኪፔድያ", "የባለ", "ብዙ", "ቋንቋ", "የተሟላ", "ትክክለኛና", "ነጻ", "መዝገበ", "ዕውቀት", "ኢንሳይክሎፒዲያ", "ነው", "ማንኛውም" } );

}

public void testArabic() throws Exception {

BaseTokenStreamTestCase.assertAnalyzesTo(a, "الفيلم الوثائقي الأول عن ويكيبيديا يسمى \"الحقيقة بالأرقام: قصة ويكيبيديا\" (بالإنجليزية: Truth in Numbers: The Wikipedia Story)، سيتم إطلاقه في 2008.",

new String[] { "الفيلم", "الوثائقي", "الأول", "عن", "ويكيبيديا", "يسمى", "الحقيقة", "بالأرقام", "قصة", "ويكيبيديا",

"بالإنجليزية", "Truth", "in", "Numbers", "The", "Wikipedia", "Story", "سيتم", "إطلاقه", "في", "2008" } );

}

public void testAramaic() throws Exception {

BaseTokenStreamTestCase.assertAnalyzesTo(a, "ܘܝܩܝܦܕܝܐ (ܐܢܓܠܝܐ: Wikipedia) ܗܘ ܐܝܢܣܩܠܘܦܕܝܐ ܚܐܪܬܐ ܕܐܢܛܪܢܛ ܒܠܫܢ̈ܐ ܣܓܝܐ̈ܐ܂ ܫܡܗ ܐܬܐ ܡܢ ܡ̈ܠܬܐ ܕ\"ܘܝܩܝ\" ܘ\"ܐܝܢܣܩܠܘܦܕܝܐ\"܀",

new String[] { "ܘܝܩܝܦܕܝܐ", "ܐܢܓܠܝܐ", "Wikipedia", "ܗܘ", "ܐܝܢܣܩܠܘܦܕܝܐ", "ܚܐܪܬܐ", "ܕܐܢܛܪܢܛ", "ܒܠܫܢ̈ܐ", "ܣܓܝܐ̈ܐ", "ܫܡܗ",

"ܐܬܐ", "ܡܢ", "ܡ̈ܠܬܐ", "ܕ", "ܘܝܩܝ", "ܘ", "ܐܝܢܣܩܠܘܦܕܝܐ"});

}

public void testBengali() throws Exception {

BaseTokenStreamTestCase.assertAnalyzesTo(a, "এই বিশ্বকোষ পরিচালনা করে উইকিমিডিয়া ফাউন্ডেশন (একটি অলাভজনক সংস্থা)। উইকিপিডিয়ার শুরু ১৫ জানুয়ারি, ২০০১ সালে। এখন পর্যন্ত ২০০টিরও বেশী ভাষায় উইকিপিডিয়া রয়েছে।",

new String[] { "এই", "বিশ্বকোষ", "পরিচালনা", "করে", "উইকিমিডিয়া", "ফাউন্ডেশন", "একটি", "অলাভজনক", "সংস্থা", "উইকিপিডিয়ার",

"শুরু", "১৫", "জানুয়ারি", "২০০১", "সালে", "এখন", "পর্যন্ত", "২০০টিরও", "বেশী", "ভাষায়", "উইকিপিডিয়া", "রয়েছে" });

}

public void testFarsi() throws Exception {

BaseTokenStreamTestCase.assertAnalyzesTo(a, "ویکی پدیای انگلیسی در تاریخ ۲۵ دی ۱۳۷۹ به صورت مکملی برای دانشنامهٔ تخصصی نوپدیا نوشته شد.",

new String[] { "ویکی", "پدیای", "انگلیسی", "در", "تاریخ", "۲۵", "دی", "۱۳۷۹", "به", "صورت", "مکملی",

"برای", "دانشنامهٔ", "تخصصی", "نوپدیا", "نوشته", "شد" });

}

public void testGreek() throws Exception {

BaseTokenStreamTestCase.assertAnalyzesTo(a, "Γράφεται σε συνεργασία από εθελοντές με το λογισμικό wiki, κάτι που σημαίνει ότι άρθρα μπορεί να προστεθούν ή να αλλάξουν από τον καθένα.",

new String[] { "Γράφεται", "σε", "συνεργασία", "από", "εθελοντές", "με", "το", "λογισμικό", "wiki", "κάτι", "που",

"σημαίνει", "ότι", "άρθρα", "μπορεί", "να", "προστεθούν", "ή", "να", "αλλάξουν", "από", "τον", "καθένα" });

}

public void testThai() throws Exception {

BaseTokenStreamTestCase.assertAnalyzesTo(a, "การที่ได้ต้องแสดงว่างานดี. แล้วเธอจะไปไหน? ๑๒๓๔",

new String[] { "การที่ได้ต้องแสดงว่างานดี", "แล้วเธอจะไปไหน", "๑๒๓๔" });

}

public void testLao() throws Exception {

BaseTokenStreamTestCase.assertAnalyzesTo(a, "ສາທາລະນະລັດ ປະຊາທິປະໄຕ ປະຊາຊົນລາວ",

100

new String[] { "ສາທາລະນະລັດ", "ປະຊາທິປະໄຕ", "ປະຊາຊົນລາວ" });

101

}

102

103

public void testTibetan() throws Exception {

104

BaseTokenStreamTestCase.assertAnalyzesTo(a, "སྣོན་མཛོད་དང་ལས་འདིས་བོད་ཡིག་མི་ཉམས་གོང་འཕེལ་དུ་གཏོང་བར་ཧ་ཅང་དགེ་མཚན་མཆིས་སོ། །",

105

new String[] { "སྣོན", "མཛོད", "དང", "ལས", "འདིས", "བོད", "ཡིག",

106

"མི", "ཉམས", "གོང", "འཕེལ", "དུ", "གཏོང", "བར",

107

"ཧ", "ཅང", "དགེ", "མཚན", "མཆིས", "སོ" });

108

}

109

110

111

* For chinese, tokenize as char (these can later form bigrams or whatever)

112

113

public void testChinese() throws Exception {

114

BaseTokenStreamTestCase.assertAnalyzesTo(a, "我是中国人。１２３４Ｔｅｓｔｓ ",

115

new String[] { "我", "是", "中", "国", "人", "１２３４", "Ｔｅｓｔｓ"});

116

}

117

118

public void testEmpty() throws Exception {

119

BaseTokenStreamTestCase.assertAnalyzesTo(a, "", new String[] {});

120

BaseTokenStreamTestCase.assertAnalyzesTo(a, ".", new String[] {});

121

BaseTokenStreamTestCase.assertAnalyzesTo(a, " ", new String[] {});

122

}

123

124

/* test various jira issues this analyzer is related to */

125

126

public void testLUCENE1545() throws Exception {

127

128

* Standard analyzer does not correctly tokenize combining character U+0364 COMBINING LATIN SMALL LETTRE E.

129

* The word "moͤchte" is incorrectly tokenized into "mo" "chte", the combining character is lost.

130

* Expected result is only on token "moͤchte".

131

132

BaseTokenStreamTestCase.assertAnalyzesTo(a, "moͤchte", new String[] { "moͤchte" });

133

}

134

135

/* Tests from StandardAnalyzer, just to show behavior is similar */

136

public void testAlphanumericSA() throws Exception {

137

// alphanumeric tokens

138

BaseTokenStreamTestCase.assertAnalyzesTo(a, "B2B", new String[]{"B2B"});

139

BaseTokenStreamTestCase.assertAnalyzesTo(a, "2B", new String[]{"2B"});

140

}

141

142

public void testDelimitersSA() throws Exception {

143

// other delimiters: "-", "/", ","

144

BaseTokenStreamTestCase.assertAnalyzesTo(a, "some-dashed-phrase", new String[]{"some", "dashed", "phrase"});

145

BaseTokenStreamTestCase.assertAnalyzesTo(a, "dogs,chase,cats", new String[]{"dogs", "chase", "cats"});

146

BaseTokenStreamTestCase.assertAnalyzesTo(a, "ac/dc", new String[]{"ac", "dc"});

147

}

148

149

public void testApostrophesSA() throws Exception {

150

// internal apostrophes: O'Reilly, you're, O'Reilly's

151

BaseTokenStreamTestCase.assertAnalyzesTo(a, "O'Reilly", new String[]{"O'Reilly"});

152

BaseTokenStreamTestCase.assertAnalyzesTo(a, "you're", new String[]{"you're"});

153

BaseTokenStreamTestCase.assertAnalyzesTo(a, "she's", new String[]{"she's"});

154

BaseTokenStreamTestCase.assertAnalyzesTo(a, "Jim's", new String[]{"Jim's"});

155

BaseTokenStreamTestCase.assertAnalyzesTo(a, "don't", new String[]{"don't"});

156

BaseTokenStreamTestCase.assertAnalyzesTo(a, "O'Reilly's", new String[]{"O'Reilly's"});

157

}

158

159

public void testNumericSA() throws Exception {

160

// floating point, serial, model numbers, ip addresses, etc.

161

BaseTokenStreamTestCase.assertAnalyzesTo(a, "21.35", new String[]{"21.35"});

162

BaseTokenStreamTestCase.assertAnalyzesTo(a, "R2D2 C3PO", new String[]{"R2D2", "C3PO"});

163

BaseTokenStreamTestCase.assertAnalyzesTo(a, "216.239.63.104", new String[]{"216.239.63.104"});

164

BaseTokenStreamTestCase.assertAnalyzesTo(a, "216.239.63.104", new String[]{"216.239.63.104"});

165

}

166

167

public void testTextWithNumbersSA() throws Exception {

168

// numbers

169

BaseTokenStreamTestCase.assertAnalyzesTo(a, "David has 5000 bones", new String[]{"David", "has", "5000", "bones"});

170

}

171

172

public void testVariousTextSA() throws Exception {

173

// various

174

BaseTokenStreamTestCase.assertAnalyzesTo(a, "C embedded developers wanted", new String[]{"C", "embedded", "developers", "wanted"});

175

BaseTokenStreamTestCase.assertAnalyzesTo(a, "foo bar FOO BAR", new String[]{"foo", "bar", "FOO", "BAR"});

176

BaseTokenStreamTestCase.assertAnalyzesTo(a, "foo bar . FOO <> BAR", new String[]{"foo", "bar", "FOO", "BAR"});

177

BaseTokenStreamTestCase.assertAnalyzesTo(a, "\"QUOTED\" word", new String[]{"QUOTED", "word"});

178

}

179

180

public void testKoreanSA() throws Exception {

181

// Korean words

182

BaseTokenStreamTestCase.assertAnalyzesTo(a, "안녕하세요 한글입니다", new String[]{"안녕하세요", "한글입니다"});

183

}

184

185

public void testOffsets() throws Exception {

186

BaseTokenStreamTestCase.assertAnalyzesTo(a, "David has 5000 bones",

187

new String[] {"David", "has", "5000", "bones"},

188

new int[] {0, 6, 10, 15},

189

new int[] {5, 9, 14, 20});

190

}

191

192

public void testTypes() throws Exception {

193

BaseTokenStreamTestCase.assertAnalyzesTo(a, "David has 5000 bones",

194

new String[] {"David", "has", "5000", "bones"},

195

new String[] { "<ALPHANUM>", "<ALPHANUM>", "<NUM>", "<ALPHANUM>" });

196

}

197

198

public void testUnicodeWordBreaks() throws Exception {

199

WordBreakTestUnicode_6_0_0 wordBreakTest = new WordBreakTestUnicode_6_0_0();

200

wordBreakTest.test(a);

201

}

202

203

public void testSupplementary() throws Exception {

204

BaseTokenStreamTestCase.assertAnalyzesTo(a, "𩬅艱鍟䇹愯瀛",

205

new String[] {"𩬅", "艱", "鍟", "䇹", "愯", "瀛"},

206

new String[] { "<IDEOGRAPHIC>", "<IDEOGRAPHIC>", "<IDEOGRAPHIC>", "<IDEOGRAPHIC>", "<IDEOGRAPHIC>", "<IDEOGRAPHIC>" });

207

}

208

209

public void testKorean() throws Exception {

210

BaseTokenStreamTestCase.assertAnalyzesTo(a, "훈민정음",

211

new String[] { "훈민정음" },

212

new String[] { "<HANGUL>" });

213

}

214

215

public void testJapanese() throws Exception {

216

BaseTokenStreamTestCase.assertAnalyzesTo(a, "仮名遣いカタカナ",

217

new String[] { "仮", "名", "遣", "い", "カタカナ" },

218

new String[] { "<IDEOGRAPHIC>", "<IDEOGRAPHIC>", "<IDEOGRAPHIC>", "<HIRAGANA>", "<KATAKANA>" });

219

}

220

221

public void testCombiningMarks() throws Exception {

222

checkOneTerm(a, "ざ", "ざ"); // hiragana

223

checkOneTerm(a, "ザ", "ザ"); // katakana

224

checkOneTerm(a, "壹゙", "壹゙"); // ideographic

225

checkOneTerm(a, "아゙", "아゙"); // hangul

226

}

227

228

/** @deprecated remove this and sophisticated backwards layer in 5.0 */

229

@Deprecated

230

public void testCombiningMarksBackwards() throws Exception {

231

Analyzer a = new StandardAnalyzer(Version.LUCENE_33);

232

checkOneTerm(a, "ざ", "さ"); // hiragana Bug

233

checkOneTerm(a, "ザ", "ザ"); // katakana Works

234

checkOneTerm(a, "壹゙", "壹"); // ideographic Bug

235

checkOneTerm(a, "아゙", "아゙"); // hangul Works

236

}

237

238

/** blast some random strings through the analyzer */

239

public void testRandomStrings() throws Exception {

240

checkRandomData(random, new StandardAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);

241

}

242

}

Older »