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

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