1 /************************************************************** 2 * 3 * Licensed to the Apache Software Foundation (ASF) under one 4 * or more contributor license agreements. See the NOTICE file 5 * distributed with this work for additional information 6 * regarding copyright ownership. The ASF licenses this file 7 * to you under the Apache License, Version 2.0 (the 8 * "License"); you may not use this file except in compliance 9 * with the License. You may obtain a copy of the License at 10 * 11 * http://www.apache.org/licenses/LICENSE-2.0 12 * 13 * Unless required by applicable law or agreed to in writing, 14 * software distributed under the License is distributed on an 15 * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY 16 * KIND, either express or implied. See the License for the 17 * specific language governing permissions and limitations 18 * under the License. 19 * 20 *************************************************************/ 21 22 23 24 package api.i18n; 25 26 import com.sun.star.i18n.KParseTokens; 27 import com.sun.star.i18n.KParseType; 28 import com.sun.star.i18n.ParseResult; 29 import com.sun.star.i18n.XCharacterClassification; 30 import com.sun.star.lang.Locale; 31 import com.sun.star.uno.UnoRuntime; 32 import com.sun.star.uno.XComponentContext; 33 import org.junit.After; 34 import org.junit.AfterClass; 35 import org.junit.Before; 36 import org.junit.BeforeClass; 37 import org.junit.Assert; 38 import org.junit.Test; 39 import org.openoffice.test.uno.UnoApp; 40 41 /** 42 * Testing <code>com.sun.star.i18n.XCharacterClassification</code> 43 * interface methods: 44 * <ul> 45 * <li><code> toUpper() </code></li> 46 * <li><code> toLower() </code></li> 47 * <li><code> toTitle() </code></li> 48 * <li><code> getType() </code></li> 49 * <li><code> getCharacterType() </code></li> 50 * <li><code> getStringType() </code></li> 51 * <li><code> getCharacterDirection() </code></li> 52 * <li><code> getScript() </code></li> 53 * <li><code> parseAnyToken() </code></li> 54 * <li><code> parsePredefinedToken() </code></li> 55 * </ul><p> 56 * Test is <b> NOT </b> multithread compliant. <p> 57 * @see com.sun.star.i18n.XCharacterClassification 58 */ 59 public class XCharacterClassificationTest { 60 private static final UnoApp app = new UnoApp(); 61 62 private XComponentContext xContext = null; 63 public XCharacterClassification oObj = null; 64 public String[] languages = new String[]{"de","en","es","fr","ja","ko","zh"}; 65 public String[] countries = new String[]{"DE","US","ES","FR","JP","KR","CN"}; 66 67 public String[] charstyles_java = new String[] {"UNASSIGNED","UPPERCASE_LETTER", 68 "LOWERCASE_LETTER","TITLECASE_LETTER","MODIFIER_LETTER","OTHER_LETTER", 69 "NON_SPACING_MARK","ENCLOSING_MARK","COMBINING_SPACING_MARK", 70 "DECIMAL_DIGIT_NUMBER","LETTER_NUMBER","OTHER_NUMBER","SPACE_SEPARATOR", 71 "LINE_SEPARATOR","PARAGRAPH_SEPARATOR","CONTROL","FORMAT","none17", 72 "PRIVATE_USE","none19","DASH_PUNCTUATION","START_PUNCTUATION","END_PUNCTUATION", 73 "CONNECTOR_PUNCTUATION","OTHER_PUNCTUATION","MATH_SYMBOL","CURRENCY_SYMBOL", 74 "MODIFIER_SYMBOL","OTHER_SYMBOL"}; 75 76 public String[] charstyles_office = new String[] {"UNASSIGNED","UPPERCASE_LETTER", 77 "LOWERCASE_LETTER","TITLECASE_LETTER","MODIFIER_LETTER","OTHER_LETTER", 78 "NON_SPACING_MARK","ENCLOSING_MARK","COMBINING_SPACING_MARK", 79 "DECIMAL_DIGIT_NUMBER","LETTER_NUMBER","OTHER_NUMBER","SPACE_SEPARATOR", 80 "LINE_SEPARATOR","PARAGRAPH_SEPARATOR","CONTROL","FORMAT","PRIVATE_USE", 81 "OTHER_PUNCTUATION","DASH_PUNCTUATION","START_PUNCTUATION","END_PUNCTUATION", 82 "CONNECTOR_PUNCTUATION", 83 "OTHER_PUNCTUATION","MATH_SYMBOL","CURRENCY_SYMBOL","MODIFIER_SYMBOL", 84 "OTHER_SYMBOL","INITIAL_PUNCTUATION","FINAL_PUNCTUATION","GENERAL_TYPES_COUNT"}; 85 86 public String[] unicode_script = new String[] {"U_BASIC_LATIN","U_LATIN_1_SUPPLEMENT", 87 "U_LATIN_EXTENDED_A","U_LATIN_EXTENDED_B","U_IPA_EXTENSIONS","U_SPACING_MODIFIER_LETTERS", 88 "U_COMBINING_DIACRITICAL_MARKS","U_GREEK","U_CYRILLIC","U_ARMENIAN","U_HEBREW", 89 "U_ARABIC","U_SYRIAC","U_THAANA","U_DEVANAGARI","U_BENGALI","U_GURMUKHI", 90 "U_GUJARATI","U_ORIYA","U_TAMIL","U_TELUGU","U_KANNADA","U_MALAYALAM", 91 "U_SINHALA","U_THAI","U_LAO","U_TIBETAN","U_MYANMAR","U_GEORGIAN", 92 "U_HANGUL_JAMO","U_ETHIOPIC","U_CHEROKEE","U_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS", 93 "U_OGHAM","U_RUNIC","U_KHMER","U_MONGOLIAN","U_LATIN_EXTENDED_ADDITIONAL", 94 "U_GREEK_EXTENDED","U_GENERAL_PUNCTUATION","U_SUPERSCRIPTS_AND_SUBSCRIPTS", 95 "U_CURRENCY_SYMBOLS","U_COMBINING_MARKS_FOR_SYMBOLS","U_LETTERLIKE_SYMBOLS", 96 "U_NUMBER_FORMS","U_ARROWS","U_MATHEMATICAL_OPERATORS","U_MISCELLANEOUS_TECHNICAL", 97 "U_CONTROL_PICTURES","U_OPTICAL_CHARACTER_RECOGNITION","U_ENCLOSED_ALPHANUMERICS", 98 "U_BOX_DRAWING","U_BLOCK_ELEMENTS","U_GEOMETRIC_SHAPES","U_MISCELLANEOUS_SYMBOLS", 99 "U_DINGBATS","U_BRAILLE_PATTERNS","U_CJK_RADICALS_SUPPLEMENT","U_KANGXI_RADICALS", 100 "U_IDEOGRAPHIC_DESCRIPTION_CHARACTERS","U_CJK_SYMBOLS_AND_PUNCTUATION", 101 "U_HIRAGANA","U_KATAKANA","U_BOPOMOFO","U_HANGUL_COMPATIBILITY_JAMO","U_KANBUN", 102 "U_BOPOMOFO_EXTENDED","U_ENCLOSED_CJK_LETTERS_AND_MONTHS","U_CJK_COMPATIBILITY", 103 "U_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A","U_CJK_UNIFIED_IDEOGRAPHS","U_YI_SYLLABLES", 104 "U_YI_RADICALS","U_HANGUL_SYLLABLES","U_HIGH_SURROGATES","U_HIGH_PRIVATE_USE_SURROGATES", 105 "U_LOW_SURROGATES","U_PRIVATE_USE_AREA","U_CJK_COMPATIBILITY_IDEOGRAPHS", 106 "U_ALPHABETIC_PRESENTATION_FORMS","U_ARABIC_PRESENTATION_FORMS_A","U_COMBINING_HALF_MARKS", 107 "U_CJK_COMPATIBILITY_FORMS","U_SMALL_FORM_VARIANTS","U_ARABIC_PRESENTATION_FORMS_B", 108 "U_SPECIALS","U_HALFWIDTH_AND_FULLWIDTH_FORMS","U_CHAR_SCRIPT_COUNT","U_NO_SCRIPT"}; 109 110 // setup and close connections 111 @BeforeClass 112 public static void setUpConnection() throws Exception 113 { 114 app.start(); 115 } 116 117 @AfterClass 118 public static void tearDownConnection() throws InterruptedException, com.sun.star.uno.Exception 119 { 120 app.close(); 121 } 122 123 @Before 124 public void before() throws Exception { 125 xContext = app.getComponentContext(); 126 oObj = UnoRuntime.queryInterface( 127 XCharacterClassification.class, 128 xContext.getServiceManager().createInstanceWithContext("com.sun.star.i18n.CharacterClassification", xContext) 129 ); 130 } 131 132 /** 133 * Test calls the method for different locales. Then each result is compared 134 * with a string, converted to a upper case using 135 * <code>java.lang.String</code> method <code>toUpperCase()</code>.<p> 136 * Has <b> OK </b> status if string, returned by the method is equal to 137 * a string that is returned by String.toUpperCase() for all locales. 138 */ 139 @Test 140 public void _toUpper() { 141 boolean res = true; 142 char[] characters = new char[]{586,65,97,498,721,4588,772,8413,3404}; 143 String toCheck = new String(characters); 144 String get = ""; 145 String exp = ""; 146 147 for (int i=0;i<7;i++) { 148 get = oObj.toUpper(toCheck, 0, toCheck.length(), getLocale(i)); 149 exp = toCheck.toUpperCase( 150 new java.util.Locale(languages[i], countries[i])); 151 res &= get.equals(exp); 152 if (!res) { 153 System.out.println("FAILED for: language=" + languages[i] + 154 " ; country=" + countries[i]); 155 System.out.println("Expected: " + exp); 156 System.out.println("Gained : " + get); 157 } 158 } 159 Assert.assertTrue("toUpper()", res); 160 } 161 162 /** 163 * Test calls the method for different locales. Then each result is compared 164 * with a string, converted to a lower case using 165 * <code>java.lang.String</code> method <code>toLowerCase()</code>.<p> 166 * Has <b> OK </b> status if string, returned by the method is equal to 167 * a string that is returned by String.toLowerCase() for all locales. 168 */ 169 @Test 170 public void _toLower() { 171 boolean res = true; 172 char[] characters = new char[]{586,65,97,498,721,4588,772,8413,3404}; 173 String toCheck = new String(characters); 174 String get = ""; 175 String exp = ""; 176 177 for (int i=0;i<7;i++) { 178 get = oObj.toLower(toCheck,0,toCheck.length(),getLocale(i)); 179 exp = toCheck.toLowerCase( 180 new java.util.Locale(languages[i],countries[i])); 181 res &= get.equals(exp); 182 if (!res) { 183 System.out.println("FAILED for: language=" + languages[i] 184 + " ; country=" + countries[i]); 185 System.out.println("Expected: " + exp); 186 System.out.println("Gained : " + get); 187 } 188 } 189 Assert.assertTrue("toLower()", res); 190 } 191 192 /** 193 * Test calls the method for different locales. Then each result is compared 194 * with a string, converted to a title case using 195 * <code>java.lang.Character</code> method <code>toTitleCase()</code>.<p> 196 * Has <b> OK </b> status if string, returned by the method is equal to 197 * a string that was converted using Character.toTitleCase() for all locales. 198 */ 199 @Test 200 public void _toTitle() { 201 boolean res = true; 202 String toCheck = new String(new char[]{8112}); 203 String get = ""; 204 String exp = ""; 205 206 for (int i=0;i<7;i++) { 207 get = oObj.toTitle(toCheck, 0, 1, getLocale(i)); 208 exp = new String( 209 new char[]{Character.toTitleCase(toCheck.toCharArray()[0])}); 210 res &= get.equals(exp); 211 if (!res) { 212 System.out.println("FAILED for: language=" + languages[i] 213 + " ; country=" + countries[i]); 214 System.out.println("Expected: " + exp); 215 System.out.println("Gained : " + get); 216 } 217 } 218 Assert.assertTrue("toTitle()", res); 219 } 220 221 /** 222 * At first we define <code>int[]</code> and <code>char[]</code> arrays of 223 * unicode symbol numbers, arranged as sequences, where symbols are sorted 224 * by type, so the character of <code>i<sup><small>th</small></sup></code> 225 * type is located on <code>i<sup><small>th</small></sup></code> position.<p> 226 * Has <b> OK </b> status if for all 30 types the method returns value, that 227 * is equal to an element number.<p> 228 * @see com.sun.star.i18n.CharType 229 */ 230 @Test 231 public void _getType() { 232 boolean res = true; 233 // If or when this list gets out of date again, 234 // find new characters of the required type with: 235 // for (int i = 30; i <= 0xffff; i++) { 236 // String s = new String("" + (char)i); 237 // int type = oObj.getType(s, 0); 238 // System.out.println("character " + i + " has type " + charstyles_office[type]); 239 // } 240 char[] characters = new char[]{888,65,97,498,721,4588,772,8413,3404, 241 48,8544,179,32,8232,8233,144,8204,57344,56320,45,40,41,95,3852,247, 242 3647,901,3896,171,187}; 243 String toCheck = new String(characters); 244 245 for (int i=0;i<characters.length;i++) { 246 int get = oObj.getType(toCheck, i); 247 res &= (charstyles_office[get] == charstyles_office[i]); 248 if (!res) { 249 System.out.println("Code: " + Integer.toHexString((int)characters[i])); 250 System.out.println("Gained: " + charstyles_office[get]); 251 System.out.println("Expected: " + charstyles_office[i]); 252 } 253 } 254 Assert.assertTrue("getType()", res); 255 } 256 257 /** 258 * After defining string to be checked and array of expected types, test 259 * calls the method for each character of a string and for all locales.<p> 260 * Has <b> OK </b> status if the method returns type, expected for a given 261 * character and locale. 262 */ 263 @Test 264 public void _getCharacterType() { 265 boolean res = true; 266 // If or when this list gets out of date again, 267 // find new characters of the required type with: 268 //for (int i = 32; i <= 0xffff; i++) { 269 // int charType = oObj.getCharacterType("" + (char)i, 0, getLocale(1)); 270 // if (charType == 32) { 271 // System.out.println("character " + i + " has type 32"); 272 // } 273 //} 274 String toCheck = "Ab0*"; 275 int[] expected = new int[]{226,228,97,32}; 276 277 for (int i=0;i<toCheck.length();i++) { 278 for (int j=1;j<7;j++) { 279 int get = oObj.getCharacterType(toCheck, i, getLocale(j)); 280 res &= (get == expected[i]); 281 if (!res) { 282 System.out.println("FAILED for: language=" + languages[j] + 283 " ; country=" + countries[j]); 284 System.out.println("Symbol: " + toCheck.toCharArray()[i]); 285 System.out.println("Gained: " + get); 286 System.out.println("Expected: " + expected[i]); 287 } 288 } 289 } 290 Assert.assertTrue("getCharacterType()", res); 291 } 292 293 /** 294 * After defining array of strings to be checked and array of expected types, 295 * test calls the method for each string of an array and for all locales.<p> 296 * Has <b> OK </b> status if the method returns type, expected for a given 297 * string and locale. 298 */ 299 @Test 300 public void _getStringType() { 301 boolean res = true; 302 String[] toCheck = new String[]{"01234","AAAAA","bbbbb","AA()bb"}; 303 int[] exp = new int[]{97,226,228,230}; 304 305 for (int j=0;j<toCheck.length;j++) { 306 for (int i=0;i<7;i++) { 307 int get = oObj.getStringType(toCheck[j], 0, 308 toCheck[j].length(), getLocale(i)); 309 res &= (get == exp[j]); 310 if (!res) { 311 System.out.println("FAILED for: language=" + languages[i] + 312 " ; country=" + countries[i]); 313 System.out.println("Expected: " + exp[j]); 314 System.out.println("Gained : " + get); 315 } 316 } 317 } 318 Assert.assertTrue("getStringType()", res); 319 } 320 321 /** 322 * After string to be checked is initialized (all symbols are sorted 323 * by direction, so the character of <code>i<sup><small>th</small></sup></code> 324 * direction is located on <code>i<sup><small>th</small></sup></code> 325 * position), test calls the method for every character of that string. <p> 326 * Has <b> OK </b> status if the method returns direction, that's equal to 327 * a symbol position in the string. 328 */ 329 @Test 330 public void _getCharacterDirection() { 331 boolean res = true; 332 String toCheck = new String(new char[]{65,1470,48,43,35,1632,44,10, 333 9,12,33,8234,8237,1563,8235,8238,8236,768,1}); 334 for (short i=0;i<19;i++) { 335 short get = oObj.getCharacterDirection(toCheck, i); 336 res &= (get == i); 337 if (!res) { 338 System.out.println("Code :" + toCheck.toCharArray()[i]); 339 System.out.println("Gained: " + get); 340 System.out.println("Expected: " + i); 341 } 342 } 343 Assert.assertTrue("getCharacterDirection()", res); 344 } 345 346 /** 347 * At first we define <code>int[]</code> and <code>char[]</code> arrays of 348 * unicode symbol numbers, arranged as sequences, where symbols are sorted 349 * by type, so the character of <code>i<sup><small>th</small></sup></code> 350 * type is located on <code>i<sup><small>th</small></sup></code> position.<p> 351 * Has <b> OK </b> status if for each character method returns value, that 352 * is equal to a number where element is located in array. Also method has 353 * <b> OK </b> status for symbol with code 55296, because it doesn't work 354 * since it hasn't the right neighborhood.<p> 355 * @see "http://ppewww.ph.gla.ac.uk/~flavell/unicode/unidata.html" 356 */ 357 @Test 358 public void _getScript() { 359 boolean res = true; 360 char[] characters = new char[]{65,128,256,384,592,750,773,924,1030,1331,1448, 361 1569,1792,1936,2313,2465,2570,2707,2822,2972,3079,3240,3337,3464,3590, 362 3745,3906,4097,4274,4357,4621,5040,5200,5776,5806,6030,6155,7683,7943, 363 8202,8319,8352,8413,8452,8545,8616,8715,8965,9217,9281,9336,9474,9608,9719, 364 9734,9999,10247,11911,12034,12274,12294,12358,12456,12552,12605,12688,12727, 365 12806,13065,13312,19968,40964,42152,44032,55296,56192,56320,57344,63744, 366 64257,64370,65056,65073,65131,65146,65532,65288}; 367 String toCheck = new String(characters); 368 369 for (int i=0;i<characters.length;i++) { 370 int get = oObj.getScript(toCheck, i); 371 //The HIGH_SURROGATE 55296 doesn't work since it hasn't the right 372 //neighborhood. Neither does 56192 - it combines with 55296 into another code point. 373 if (toCheck.charAt(i) != 55296 && toCheck.charAt(i) != 56192) { 374 res &= (get == i); 375 } 376 if (!res) { 377 System.out.println("-- " + toCheck.substring(i, i + 1).hashCode()); 378 System.out.println("Code: " + Integer.toHexString((int)characters[i])); 379 System.out.println("Gained: " + get + " (" + (0 <= get && get < unicode_script.length ? unicode_script[get] : "out of range") + ")"); 380 System.out.println("Expected: " + unicode_script[i]); 381 } 382 } 383 Assert.assertTrue("getScript()", res); 384 } 385 386 /** 387 * After defining a string to be parsed and parse conditions (flags), test 388 * calls the method for different locales three times with different parameters, 389 * checking result after every call. <p> 390 * Has <b> OK </b> status if the method returns right results all three 391 * times. 392 */ 393 @Test 394 public void _parseAnyToken() { 395 int nStartFlags = KParseTokens.ANY_ALPHA | KParseTokens.ASC_UNDERSCORE; 396 int nContFlags = KParseTokens.ANY_ALNUM | KParseTokens.ASC_UNDERSCORE 397 | KParseTokens.ASC_DOT; 398 String toCheck = " 18 i18n ^"; 399 ParseResult pRes = null; 400 boolean res = true; 401 402 for (int i=0;i<7;i++) { 403 pRes = oObj.parseAnyToken(toCheck, 1, getLocale(i), 404 nStartFlags, "", nContFlags, ""); 405 res = ( (pRes.CharLen==2) 406 && (pRes.TokenType==32) 407 && (pRes.Value==18.0) ); 408 pRes = oObj.parseAnyToken(toCheck, 4, getLocale(i), 409 nStartFlags, "", nContFlags, ""); 410 res &= ( (pRes.CharLen==4) 411 && (pRes.TokenType==4) 412 && (pRes.Value==0.0) ); 413 pRes = oObj.parseAnyToken(toCheck, 9, getLocale(i), 414 nStartFlags, "", nContFlags, ""); 415 res &= ( (pRes.CharLen==1) 416 && (pRes.TokenType==1) 417 && (pRes.Value==0.0) ); 418 } 419 Assert.assertTrue("parseAnyToken()", res); 420 } 421 422 /** 423 * After defining a string to be parsed and parse conditions (flags), test 424 * calls the method for different locales two times with different parameters, 425 * checking result after every call. <p> 426 * Has <b> OK </b> status if the method returns right results. 427 */ 428 @Test 429 public void _parsePredefinedToken() { 430 int nStartFlags = KParseTokens.ANY_ALPHA | KParseTokens.ASC_UNDERSCORE; 431 int nContFlags = nStartFlags; 432 String toCheck = " 18 int"; 433 ParseResult pRes = null; 434 boolean res = true; 435 436 for (int i=0;i<7;i++) { 437 pRes = oObj.parsePredefinedToken(KParseType.IDENTNAME, toCheck, 438 1, getLocale(i), nStartFlags, "", nContFlags, ""); 439 res = (pRes.CharLen==0); 440 pRes = oObj.parsePredefinedToken(KParseType.IDENTNAME, toCheck, 441 4, getLocale(i), nStartFlags, "", nContFlags, ""); 442 res &= ( (pRes.CharLen==3) 443 && (pRes.TokenType==4) 444 && (pRes.Value==0.0) ); 445 } 446 Assert.assertTrue("parsePredefinedToken()", res); 447 } 448 449 450 /** 451 * Method returns locale for a given language and country. 452 * @param k index of needed locale. 453 */ 454 private Locale getLocale(int k) { 455 return new Locale(languages[k],countries[k],""); 456 } 457 458 459 } // end XCharacterClassification 460