qadevOOo/tests/java/ifc/i18n/_XCharacterClassification.java

   1 /*************************************************************************
   2  *
   3  * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
   4  *
   5  * Copyright 2008 by Sun Microsystems, Inc.
   6  *
   7  * OpenOffice.org - a multi-platform office productivity suite
   8  *
   9  * $RCSfile: _XCharacterClassification.java,v $
  10  * $Revision: 1.5 $
  11  *
  12  * This file is part of OpenOffice.org.
  13  *
  14  * OpenOffice.org is free software: you can redistribute it and/or modify
  15  * it under the terms of the GNU Lesser General Public License version 3
  16  * only, as published by the Free Software Foundation.
  17  *
  18  * OpenOffice.org is distributed in the hope that it will be useful,
  19  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  20  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  21  * GNU Lesser General Public License version 3 for more details
  22  * (a copy is included in the LICENSE file that accompanied this code).
  23  *
  24  * You should have received a copy of the GNU Lesser General Public License
  25  * version 3 along with OpenOffice.org.  If not, see
  26  * <http://www.openoffice.org/license.html>
  27  * for a copy of the LGPLv3 License.
  28  *
  29  ************************************************************************/
  30
  31 package ifc.i18n;
  32
  33 import lib.MultiMethodTest;
  34
  35 import com.sun.star.i18n.KParseTokens;
  36 import com.sun.star.i18n.KParseType;
  37 import com.sun.star.i18n.ParseResult;
  38 import com.sun.star.i18n.XCharacterClassification;
  39 import com.sun.star.lang.Locale;
  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 compilant. <p>
  57  * @see com.sun.star.i18n.XCharacterClassification
  58  */
  59 public class _XCharacterClassification extends MultiMethodTest {
  60     public XCharacterClassification oObj = null;
  61     public String[] languages = new String[]{"de","en","es","fr","ja","ko","zh"};
  62     public String[] countries = new String[]{"DE","US","ES","FR","JP","KR","CN"};
  63
  64     public String[] charstyles_java = new String[] {"UNASSIGNED","UPPERCASE_LETTER",
  65         "LOWERCASE_LETTER","TITLECASE_LETTER","MODIFIER_LETTER","OTHER_LETTER",
  66         "NON_SPACING_MARK","ENCLOSING_MARK","COMBINING_SPACING_MARK",
  67         "DECIMAL_DIGIT_NUMBER","LETTER_NUMBER","OTHER_NUMBER","SPACE_SEPARATOR",
  68         "LINE_SEPARATOR","PARAGRAPH_SEPARATOR","CONTROL","FORMAT","none17",
  69         "PRIVATE_USE","none19","DASH_PUNCTUATION","START_PUNCTUATION","END_PUNCTUATION",
  70         "CONNECTOR_PUNCTUATION","OTHER_PUNCTUATION","MATH_SYMBOL","CURRENCY_SYMBOL",
  71         "MODIFIER_SYMBOL","OTHER_SYMBOL"};
  72
  73     public String[] charstyles_office = new String[] {"UNASSIGNED","UPPERCASE_LETTER",
  74         "LOWERCASE_LETTER","TITLECASE_LETTER","MODIFIER_LETTER","OTHER_LETTER",
  75         "NON_SPACING_MARK","ENCLOSING_MARK","COMBINING_SPACING_MARK",
  76         "DECIMAL_DIGIT_NUMBER","LETTER_NUMBER","OTHER_NUMBER","SPACE_SEPARATOR",
  77         "LINE_SEPARATOR","PARAGRAPH_SEPARATOR","CONTROL","FORMAT","PRIVATE_USE",
  78         "OTHER_PUNCTUATION","DASH_PUNCTUATION","START_PUNCTUATION","END_PUNCTUATION",
  79         "CONNECTOR_PUNCTUATION",
  80         "OTHER_PUNCTUATION","MATH_SYMBOL","CURRENCY_SYMBOL","MODIFIER_SYMBOL",
  81         "OTHER_SYMBOL","INITIAL_PUNCTUATION","FINAL_PUNCTUATION","GENERAL_TYPES_COUNT"};
  82
  83     public String[] unicode_script = new String[] {"U_BASIC_LATIN","U_LATIN_1_SUPPLEMENT",
  84         "U_LATIN_EXTENDED_A","U_LATIN_EXTENDED_B","U_IPA_EXTENSIONS","U_SPACING_MODIFIER_LETTERS",
  85         "U_COMBINING_DIACRITICAL_MARKS","U_GREEK","U_CYRILLIC","U_ARMENIAN","U_HEBREW",
  86         "U_ARABIC","U_SYRIAC","U_THAANA","U_DEVANAGARI","U_BENGALI","U_GURMUKHI",
  87         "U_GUJARATI","U_ORIYA","U_TAMIL","U_TELUGU","U_KANNADA","U_MALAYALAM",
  88         "U_SINHALA","U_THAI","U_LAO","U_TIBETAN","U_MYANMAR","U_GEORGIAN",
  89         "U_HANGUL_JAMO","U_ETHIOPIC","U_CHEROKEE","U_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS",
  90         "U_OGHAM","U_RUNIC","U_KHMER","U_MONGOLIAN","U_LATIN_EXTENDED_ADDITIONAL",
  91         "U_GREEK_EXTENDED","U_GENERAL_PUNCTUATION","U_SUPERSCRIPTS_AND_SUBSCRIPTS",
  92         "U_CURRENCY_SYMBOLS","U_COMBINING_MARKS_FOR_SYMBOLS","U_LETTERLIKE_SYMBOLS",
  93         "U_NUMBER_FORMS","U_ARROWS","U_MATHEMATICAL_OPERATORS","U_MISCELLANEOUS_TECHNICAL",
  94         "U_CONTROL_PICTURES","U_OPTICAL_CHARACTER_RECOGNITION","U_ENCLOSED_ALPHANUMERICS",
  95         "U_BOX_DRAWING","U_BLOCK_ELEMENTS","U_GEOMETRIC_SHAPES","U_MISCELLANEOUS_SYMBOLS",
  96         "U_DINGBATS","U_BRAILLE_PATTERNS","U_CJK_RADICALS_SUPPLEMENT","U_KANGXI_RADICALS",
  97         "U_IDEOGRAPHIC_DESCRIPTION_CHARACTERS","U_CJK_SYMBOLS_AND_PUNCTUATION",
  98         "U_HIRAGANA","U_KATAKANA","U_BOPOMOFO","U_HANGUL_COMPATIBILITY_JAMO","U_KANBUN",
  99         "U_BOPOMOFO_EXTENDED","U_ENCLOSED_CJK_LETTERS_AND_MONTHS","U_CJK_COMPATIBILITY",
 100         "U_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A","U_CJK_UNIFIED_IDEOGRAPHS","U_YI_SYLLABLES",
 101         "U_YI_RADICALS","U_HANGUL_SYLLABLES","U_HIGH_SURROGATES","U_HIGH_PRIVATE_USE_SURROGATES",
 102         "U_LOW_SURROGATES","U_PRIVATE_USE_AREA","U_CJK_COMPATIBILITY_IDEOGRAPHS",
 103         "U_ALPHABETIC_PRESENTATION_FORMS","U_ARABIC_PRESENTATION_FORMS_A","U_COMBINING_HALF_MARKS",
 104         "U_CJK_COMPATIBILITY_FORMS","U_SMALL_FORM_VARIANTS","U_ARABIC_PRESENTATION_FORMS_B",
 105         "U_SPECIALS","U_HALFWIDTH_AND_FULLWIDTH_FORMS","U_CHAR_SCRIPT_COUNT","U_NO_SCRIPT"};
 106
 107     /**
 108     * Test calls the method for different locales. Then each result is compared
 109     * with a string, converted to a upper case using
 110     * <code>java.lang.String</code> method <code>toUpperCase()</code>.<p>
 111     * Has <b> OK </b> status if string, returned by the method is equal to
 112     * a string that is returned by String.toUpperCase() for all locales.
 113     */
 114     public void _toUpper() {
 115         boolean res = true;
 116         char[] characters = new char[]{586,65,97,498,721,4588,772,8413,3404};
 117         String toCheck = new String(characters);
 118         String get = "";
 119         String exp = "";
 120
 121         for (int i=0;i<7;i++) {
 122             get = oObj.toUpper(toCheck, 0, toCheck.length(), getLocale(i));
 123             exp = toCheck.toUpperCase(
 124                 new java.util.Locale(languages[i], countries[i]));
 125             res &= get.equals(exp);
 126             if (!res) {
 127                 log.println("FAILED for: language=" + languages[i] +
 128                     " ; country=" + countries[i]);
 129                 log.println("Expected: " + exp);
 130                 log.println("Gained : " + get);
 131             }
 132         }
 133         tRes.tested("toUpper()", res);
 134     }
 135
 136     /**
 137     * Test calls the method for different locales. Then each result is compared
 138     * with a string, converted to a lower case using
 139     * <code>java.lang.String</code> method <code>toLowerCase()</code>.<p>
 140     * Has <b> OK </b> status if string, returned by the method is equal to
 141     * a string that is returned by String.toLowerCase() for all locales.
 142     */
 143     public void _toLower() {
 144         boolean res = true;
 145         char[] characters = new char[]{586,65,97,498,721,4588,772,8413,3404};
 146         String toCheck = new String(characters);
 147         String get = "";
 148         String exp = "";
 149
 150         for (int i=0;i<7;i++) {
 151             get = oObj.toLower(toCheck,0,toCheck.length(),getLocale(i));
 152             exp = toCheck.toLowerCase(
 153                 new java.util.Locale(languages[i],countries[i]));
 154             res &= get.equals(exp);
 155             if (!res) {
 156                 log.println("FAILED for: language=" + languages[i]
 157                     + " ; country=" + countries[i]);
 158                 log.println("Expected: " + exp);
 159                 log.println("Gained : " + get);
 160             }
 161         }
 162         tRes.tested("toLower()", res);
 163     }
 164
 165     /**
 166     * Test calls the method for different locales. Then each result is compared
 167     * with a string, converted to a title case using
 168     * <code>java.lang.Character</code> method <code>toTitleCase()</code>.<p>
 169     * Has <b> OK </b> status if string, returned by the method is equal to
 170     * a string that was converted using Character.toTitleCase() for all locales.
 171     */
 172     public void _toTitle() {
 173         boolean res = true;
 174         String toCheck = new String(new char[]{8112});
 175         String get = "";
 176         String exp = "";
 177
 178         for (int i=0;i<7;i++) {
 179             get = oObj.toTitle(toCheck, 0, 1, getLocale(i));
 180             exp = new String(
 181                 new char[]{Character.toTitleCase(toCheck.toCharArray()[0])});
 182             res &= get.equals(exp);
 183             if (!res) {
 184                 log.println("FAILED for: language=" + languages[i]
 185                     + " ; country=" + countries[i]);
 186                 log.println("Expected: " + exp);
 187                 log.println("Gained : " + get);
 188             }
 189         }
 190         tRes.tested("toTitle()", res);
 191     }
 192
 193     /**
 194     * At first we define <code>int[]</code> and <code>char[]</code> arrays of
 195     * unicode symbol numbers, arranged as sequences, where symbols are sorted
 196     * by type, so the character of <code>i<sup><small>th</small></sup></code>
 197     * type is located on <code>i<sup><small>th</small></sup></code> position.<p>
 198     * Has <b> OK </b> status if for all 30 types the method returns value, that
 199     * is equal to an element number.<p>
 200     * @see com.sun.star.i18n.CharType
 201     */
 202     public void _getType() {
 203         boolean res = true;
 204         char[] characters = new char[]{586,65,97,498,721,4588,772,8413,3404,
 205             48,8544,179,32,8232,8233,144,8204,57344,56320,173,40,41,95,3852,247,
 206             3647,901,3896,171,187};
 207         int[] charsInt = new int[]{586,65,97,498,721,4588,772,8413,3404,48,
 208             8544,179,32,8232,8233,144,8204,57344,56320,173,40,41,95,3852,247,
 209             3647,901,3896,171,187};
 210         String toCheck = new String(characters);
 211
 212         for (int i=0;i<characters.length;i++) {
 213             int get = oObj.getType(toCheck, i);
 214             res &= (charstyles_office[get] == charstyles_office[i]);
 215             if (!res) {
 216                 log.println("Code :" + Integer.toHexString(charsInt[i]));
 217                 log.println("Gained: " + charstyles_office[get]);
 218                 log.println("Expected : " + charstyles_office[i]);
 219             }
 220         }
 221         tRes.tested("getType()", res);
 222     }
 223
 224     /**
 225     * After defining string to be checked and array of expected types, test
 226     * calls the method for each character of a string and for all locales.<p>
 227     * Has <b> OK </b> status if the method returns type, expected for a given
 228     * character and locale.
 229     */
 230     public void _getCharacterType() {
 231         boolean res = true;
 232         String toCheck = "Ab0)";
 233         int[] expected = new int[]{226,228,97,32};
 234
 235         for (int i=0;i<toCheck.length();i++) {
 236             for (int j=1;j<7;j++) {
 237                 int get = oObj.getCharacterType(toCheck, i, getLocale(j));
 238                 res &= (get == expected[i]);
 239                 if (!res) {
 240                     log.println("FAILED for: language=" + languages[j] +
 241                         " ; country=" + countries[j]);
 242                     log.println("Sysmbol :" + toCheck.toCharArray()[i]);
 243                     log.println("Gained: " + get);
 244                     log.println("Expected : " + expected[i]);
 245                 }
 246             }
 247         }
 248         tRes.tested("getCharacterType()", res);
 249     }
 250
 251     /**
 252     * After defining array of strings to be checked and array of expected types,
 253     * test calls the method for each string of an array and for all locales.<p>
 254     * Has <b> OK </b> status if the method returns type, expected for a given
 255     * string and locale.
 256     */
 257     public void _getStringType() {
 258         boolean res = true;
 259         String[] toCheck = new String[]{"01234","AAAAA","bbbbb","AA()bb"};
 260         int[] exp = new int[]{97,226,228,230};
 261
 262         for (int j=0;j<toCheck.length;j++) {
 263             for (int i=0;i<7;i++) {
 264                 int get = oObj.getStringType(toCheck[j], 0,
 265                     toCheck[j].length(), getLocale(i));
 266                 res &= (get == exp[j]);
 267                 if (!res) {
 268                     log.println("FAILED for: language=" + languages[i] +
 269                         " ; country=" + countries[i]);
 270                     log.println("Expected: " + exp[j]);
 271                     log.println("Gained : " + get);
 272                 }
 273             }
 274         }
 275         tRes.tested("getStringType()", res);
 276     }
 277
 278     /**
 279     * After string to be checked is initialized (all symbols are sorted
 280     * by direction, so the character of <code>i<sup><small>th</small></sup></code>
 281     * direction is located on <code>i<sup><small>th</small></sup></code>
 282     * position), test calls the method for every character of that string. <p>
 283     * Has <b> OK </b> status if the method returns direction, that's equal to
 284     * a symbol position in the string.
 285     */
 286     public void _getCharacterDirection() {
 287         boolean res = true;
 288         String toCheck = new String(new char[]{65,1470,48,47,35,1632,44,10,
 289                                 9,12,33,8234,8237,1563,8235,8238,8236,768,1});
 290         for (short i=0;i<19;i++) {
 291             short get = oObj.getCharacterDirection(toCheck, i);
 292             res &= (get == i);
 293             if (!res) {
 294                 log.println("Code :" + toCheck.toCharArray()[i]);
 295                 log.println("Gained: " + get);
 296                 log.println("Expected: " + i);
 297             }
 298         }
 299         tRes.tested("getCharacterDirection()", res);
 300     }
 301
 302     /**
 303     * At first we define <code>int[]</code> and <code>char[]</code> arrays of
 304     * unicode symbol numbers, arranged as sequences, where symbols are sorted
 305     * by type, so the character of <code>i<sup><small>th</small></sup></code>
 306     * type is located on <code>i<sup><small>th</small></sup></code> position.<p>
 307     * Has <b> OK </b> status if for each character method returns value, that
 308     * is equal to a number where element is located in array. Also method has
 309     * <b> OK </b> status for symbol with code 55296, because it doesn't work
 310     * since it hasn't the right neighborhood.<p>
 311     * @see http://ppewww.ph.gla.ac.uk/~flavell/unicode/unidata.html
 312     */
 313     public void _getScript() {
 314         boolean res = true;
 315         char[] characters = new char[]{65,128,256,384,592,750,773,924,1030,1331,1448,
 316             1569,1792,1936,2313,2465,2570,2707,2822,2972,3079,3240,3337,3464,3590,
 317             3745,3906,4097,4274,4357,4621,5040,5200,5776,5806,6030,6155,7683,7943,
 318             8202,8319,8352,8413,8452,8545,8616,8715,8965,9217,9281,9336,9474,9608,9719,
 319             9734,9999,10247,11911,12034,12274,12294,12358,12456,12552,12605,12688,12727,
 320             12806,13065,13312,19968,40964,42152,44032,55296,56192,56320,57344,63744,
 321             64257,64370,65056,65073,65131,65146,65532,65288};
 322         int[] charsInt = new int[]{65,128,256,384,592,750,773,924,1030,1331,1448,
 323             1569,1792,1936,2313,2465,2570,2707,2822,2972,3079,3240,3337,3464,3590,
 324             3745,3906,4097,4274,4357,4621,5040,5200,5776,5806,6030,6155,7683,7943,
 325             8202,8319,8352,8413,8452,8545,8616,8715,8965,9217,9281,9336,9474,9608,9719,
 326             9734,9999,10247,11911,12034,12274,12294,12358,12456,12552,12605,12688,12727,
 327             12806,13065,13312,19968,40964,42152,44032,55296,56192,56320,57344,63744,
 328             64257,64370,65056,65073,65131,65146,65532,65288};
 329         String toCheck = new String(characters);
 330
 331         for (int i=0;i<characters.length;i++) {
 332             int get = oObj.getScript(toCheck, i);
 333             res &= (get == i);
 334             //The HIGH_SURROGATE 55296 doesn't work since it hasn't the right
 335             //neighborhood
 336             if (toCheck.substring(i, i + 1).hashCode() == 55296) res = true;
 337             if (!res) {
 338                 log.println("-- " + toCheck.substring(i, i + 1).hashCode());
 339                 log.println("Code: " + Integer.toHexString(charsInt[i]));
 340                 log.println("Gained: " + unicode_script[get]);
 341                 log.println("Expected: " + unicode_script[i]);
 342             }
 343         }
 344         tRes.tested("getScript()", res);
 345     }
 346
 347     /**
 348     * After defining a string to be parsed and parse conditions (flags), test
 349     * calls the method for different locales three times with different parameters,
 350     * checking result after every call.  <p>
 351     * Has <b> OK </b> status if the method returns right results all three
 352     * times.
 353     */
 354     public void _parseAnyToken() {
 355         int nStartFlags = KParseTokens.ANY_ALPHA | KParseTokens.ASC_UNDERSCORE;
 356         int nContFlags = KParseTokens.ANY_ALNUM | KParseTokens.ASC_UNDERSCORE
 357                         | KParseTokens.ASC_DOT;
 358         String toCheck = " 18 i18n ^";
 359         ParseResult pRes = null;
 360         boolean res = true;
 361
 362         for (int i=0;i<7;i++) {
 363             pRes = oObj.parseAnyToken(toCheck, 1, getLocale(i),
 364                 nStartFlags, "", nContFlags, "");
 365             res = ( (pRes.CharLen==2)
 366                  && (pRes.TokenType==32)
 367                  && (pRes.Value==18.0) );
 368             pRes = oObj.parseAnyToken(toCheck, 4, getLocale(i),
 369                 nStartFlags, "", nContFlags, "");
 370             res &= ( (pRes.CharLen==4)
 371                   && (pRes.TokenType==4)
 372                   && (pRes.Value==0.0) );
 373             pRes = oObj.parseAnyToken(toCheck, 9, getLocale(i),
 374                 nStartFlags, "", nContFlags, "");
 375             res &= ( (pRes.CharLen==1)
 376                   && (pRes.TokenType==1)
 377                   && (pRes.Value==0.0) );
 378         }
 379         tRes.tested("parseAnyToken()", res);
 380     }
 381
 382     /**
 383     * After defining a string to be parsed and parse conditions (flags), test
 384     * calls the method for different locales two times with different parameters,
 385     * checking result after every call. <p>
 386     * Has <b> OK </b> status if the method returns right results.
 387     */
 388     public void _parsePredefinedToken() {
 389         int nStartFlags = KParseTokens.ANY_ALPHA | KParseTokens.ASC_UNDERSCORE;
 390         int nContFlags = nStartFlags;
 391         String toCheck = " 18 int";
 392         ParseResult pRes = null;
 393         boolean res = true;
 394
 395         for (int i=0;i<7;i++) {
 396             pRes = oObj.parsePredefinedToken(KParseType.IDENTNAME, toCheck,
 397                 1, getLocale(i), nStartFlags, "", nContFlags, "");
 398             res = (pRes.CharLen==0);
 399             pRes = oObj.parsePredefinedToken(KParseType.IDENTNAME, toCheck,
 400                 4, getLocale(i), nStartFlags, "", nContFlags, "");
 401             res &= ( (pRes.CharLen==3)
 402                   && (pRes.TokenType==4)
 403                   && (pRes.Value==0.0) );
 404         }
 405         tRes.tested("parsePredefinedToken()", res);
 406     }
 407
 408
 409     /**
 410     * Method returns locale for a given language and country.
 411     * @param localeIndex index of needed locale.
 412     */
 413     private Locale getLocale(int k) {
 414         return new Locale(languages[k],countries[k],"");
 415     }
 416
 417
 418 } // end XCharacterClassification
 419