1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 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 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416
|
/*************************************************************************
*
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
*
* Copyright 2000, 2010 Oracle and/or its affiliates.
*
* OpenOffice.org - a multi-platform office productivity suite
*
* This file is part of OpenOffice.org.
*
* OpenOffice.org is free software: you can redistribute it and/or modify
* it under the terms of the GNU Lesser General Public License version 3
* only, as published by the Free Software Foundation.
*
* OpenOffice.org is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU Lesser General Public License version 3 for more details
* (a copy is included in the LICENSE file that accompanied this code).
*
* You should have received a copy of the GNU Lesser General Public License
* version 3 along with OpenOffice.org. If not, see
* <http://www.openoffice.org/license.html>
* for a copy of the LGPLv3 License.
*
************************************************************************/
package ifc.i18n;
import lib.MultiMethodTest;
import com.sun.star.i18n.KParseTokens;
import com.sun.star.i18n.KParseType;
import com.sun.star.i18n.ParseResult;
import com.sun.star.i18n.XCharacterClassification;
import com.sun.star.lang.Locale;
/**
* Testing <code>com.sun.star.i18n.XCharacterClassification</code>
* interface methods:
* <ul>
* <li><code> toUpper() </code></li>
* <li><code> toLower() </code></li>
* <li><code> toTitle() </code></li>
* <li><code> getType() </code></li>
* <li><code> getCharacterType() </code></li>
* <li><code> getStringType() </code></li>
* <li><code> getCharacterDirection() </code></li>
* <li><code> getScript() </code></li>
* <li><code> parseAnyToken() </code></li>
* <li><code> parsePredefinedToken() </code></li>
* </ul><p>
* Test is <b> NOT </b> multithread compilant. <p>
* @see com.sun.star.i18n.XCharacterClassification
*/
public class _XCharacterClassification extends MultiMethodTest {
public XCharacterClassification oObj = null;
public String[] languages = new String[]{"de","en","es","fr","ja","ko","zh"};
public String[] countries = new String[]{"DE","US","ES","FR","JP","KR","CN"};
public String[] charstyles_java = new String[] {"UNASSIGNED","UPPERCASE_LETTER",
"LOWERCASE_LETTER","TITLECASE_LETTER","MODIFIER_LETTER","OTHER_LETTER",
"NON_SPACING_MARK","ENCLOSING_MARK","COMBINING_SPACING_MARK",
"DECIMAL_DIGIT_NUMBER","LETTER_NUMBER","OTHER_NUMBER","SPACE_SEPARATOR",
"LINE_SEPARATOR","PARAGRAPH_SEPARATOR","CONTROL","FORMAT","none17",
"PRIVATE_USE","none19","DASH_PUNCTUATION","START_PUNCTUATION","END_PUNCTUATION",
"CONNECTOR_PUNCTUATION","OTHER_PUNCTUATION","MATH_SYMBOL","CURRENCY_SYMBOL",
"MODIFIER_SYMBOL","OTHER_SYMBOL"};
public String[] charstyles_office = new String[] {"UNASSIGNED","UPPERCASE_LETTER",
"LOWERCASE_LETTER","TITLECASE_LETTER","MODIFIER_LETTER","OTHER_LETTER",
"NON_SPACING_MARK","ENCLOSING_MARK","COMBINING_SPACING_MARK",
"DECIMAL_DIGIT_NUMBER","LETTER_NUMBER","OTHER_NUMBER","SPACE_SEPARATOR",
"LINE_SEPARATOR","PARAGRAPH_SEPARATOR","CONTROL","FORMAT","PRIVATE_USE",
"OTHER_PUNCTUATION","DASH_PUNCTUATION","START_PUNCTUATION","END_PUNCTUATION",
"CONNECTOR_PUNCTUATION",
"OTHER_PUNCTUATION","MATH_SYMBOL","CURRENCY_SYMBOL","MODIFIER_SYMBOL",
"OTHER_SYMBOL","INITIAL_PUNCTUATION","FINAL_PUNCTUATION","GENERAL_TYPES_COUNT"};
public String[] unicode_script = new String[] {"U_BASIC_LATIN","U_LATIN_1_SUPPLEMENT",
"U_LATIN_EXTENDED_A","U_LATIN_EXTENDED_B","U_IPA_EXTENSIONS","U_SPACING_MODIFIER_LETTERS",
"U_COMBINING_DIACRITICAL_MARKS","U_GREEK","U_CYRILLIC","U_ARMENIAN","U_HEBREW",
"U_ARABIC","U_SYRIAC","U_THAANA","U_DEVANAGARI","U_BENGALI","U_GURMUKHI",
"U_GUJARATI","U_ORIYA","U_TAMIL","U_TELUGU","U_KANNADA","U_MALAYALAM",
"U_SINHALA","U_THAI","U_LAO","U_TIBETAN","U_MYANMAR","U_GEORGIAN",
"U_HANGUL_JAMO","U_ETHIOPIC","U_CHEROKEE","U_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS",
"U_OGHAM","U_RUNIC","U_KHMER","U_MONGOLIAN","U_LATIN_EXTENDED_ADDITIONAL",
"U_GREEK_EXTENDED","U_GENERAL_PUNCTUATION","U_SUPERSCRIPTS_AND_SUBSCRIPTS",
"U_CURRENCY_SYMBOLS","U_COMBINING_MARKS_FOR_SYMBOLS","U_LETTERLIKE_SYMBOLS",
"U_NUMBER_FORMS","U_ARROWS","U_MATHEMATICAL_OPERATORS","U_MISCELLANEOUS_TECHNICAL",
"U_CONTROL_PICTURES","U_OPTICAL_CHARACTER_RECOGNITION","U_ENCLOSED_ALPHANUMERICS",
"U_BOX_DRAWING","U_BLOCK_ELEMENTS","U_GEOMETRIC_SHAPES","U_MISCELLANEOUS_SYMBOLS",
"U_DINGBATS","U_BRAILLE_PATTERNS","U_CJK_RADICALS_SUPPLEMENT","U_KANGXI_RADICALS",
"U_IDEOGRAPHIC_DESCRIPTION_CHARACTERS","U_CJK_SYMBOLS_AND_PUNCTUATION",
"U_HIRAGANA","U_KATAKANA","U_BOPOMOFO","U_HANGUL_COMPATIBILITY_JAMO","U_KANBUN",
"U_BOPOMOFO_EXTENDED","U_ENCLOSED_CJK_LETTERS_AND_MONTHS","U_CJK_COMPATIBILITY",
"U_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A","U_CJK_UNIFIED_IDEOGRAPHS","U_YI_SYLLABLES",
"U_YI_RADICALS","U_HANGUL_SYLLABLES","U_HIGH_SURROGATES","U_HIGH_PRIVATE_USE_SURROGATES",
"U_LOW_SURROGATES","U_PRIVATE_USE_AREA","U_CJK_COMPATIBILITY_IDEOGRAPHS",
"U_ALPHABETIC_PRESENTATION_FORMS","U_ARABIC_PRESENTATION_FORMS_A","U_COMBINING_HALF_MARKS",
"U_CJK_COMPATIBILITY_FORMS","U_SMALL_FORM_VARIANTS","U_ARABIC_PRESENTATION_FORMS_B",
"U_SPECIALS","U_HALFWIDTH_AND_FULLWIDTH_FORMS","U_CHAR_SCRIPT_COUNT","U_NO_SCRIPT"};
/**
* Test calls the method for different locales. Then each result is compared
* with a string, converted to a upper case using
* <code>java.lang.String</code> method <code>toUpperCase()</code>.<p>
* Has <b> OK </b> status if string, returned by the method is equal to
* a string that is returned by String.toUpperCase() for all locales.
*/
public void _toUpper() {
boolean res = true;
char[] characters = new char[]{586,65,97,498,721,4588,772,8413,3404};
String toCheck = new String(characters);
String get = "";
String exp = "";
for (int i=0;i<7;i++) {
get = oObj.toUpper(toCheck, 0, toCheck.length(), getLocale(i));
exp = toCheck.toUpperCase(
new java.util.Locale(languages[i], countries[i]));
res &= get.equals(exp);
if (!res) {
log.println("FAILED for: language=" + languages[i] +
" ; country=" + countries[i]);
log.println("Expected: " + exp);
log.println("Gained : " + get);
}
}
tRes.tested("toUpper()", res);
}
/**
* Test calls the method for different locales. Then each result is compared
* with a string, converted to a lower case using
* <code>java.lang.String</code> method <code>toLowerCase()</code>.<p>
* Has <b> OK </b> status if string, returned by the method is equal to
* a string that is returned by String.toLowerCase() for all locales.
*/
public void _toLower() {
boolean res = true;
char[] characters = new char[]{586,65,97,498,721,4588,772,8413,3404};
String toCheck = new String(characters);
String get = "";
String exp = "";
for (int i=0;i<7;i++) {
get = oObj.toLower(toCheck,0,toCheck.length(),getLocale(i));
exp = toCheck.toLowerCase(
new java.util.Locale(languages[i],countries[i]));
res &= get.equals(exp);
if (!res) {
log.println("FAILED for: language=" + languages[i]
+ " ; country=" + countries[i]);
log.println("Expected: " + exp);
log.println("Gained : " + get);
}
}
tRes.tested("toLower()", res);
}
/**
* Test calls the method for different locales. Then each result is compared
* with a string, converted to a title case using
* <code>java.lang.Character</code> method <code>toTitleCase()</code>.<p>
* Has <b> OK </b> status if string, returned by the method is equal to
* a string that was converted using Character.toTitleCase() for all locales.
*/
public void _toTitle() {
boolean res = true;
String toCheck = new String(new char[]{8112});
String get = "";
String exp = "";
for (int i=0;i<7;i++) {
get = oObj.toTitle(toCheck, 0, 1, getLocale(i));
exp = new String(
new char[]{Character.toTitleCase(toCheck.toCharArray()[0])});
res &= get.equals(exp);
if (!res) {
log.println("FAILED for: language=" + languages[i]
+ " ; country=" + countries[i]);
log.println("Expected: " + exp);
log.println("Gained : " + get);
}
}
tRes.tested("toTitle()", res);
}
/**
* At first we define <code>int[]</code> and <code>char[]</code> arrays of
* unicode symbol numbers, arranged as sequences, where symbols are sorted
* by type, so the character of <code>i<sup><small>th</small></sup></code>
* type is located on <code>i<sup><small>th</small></sup></code> position.<p>
* Has <b> OK </b> status if for all 30 types the method returns value, that
* is equal to an element number.<p>
* @see com.sun.star.i18n.CharType
*/
public void _getType() {
boolean res = true;
char[] characters = new char[]{586,65,97,498,721,4588,772,8413,3404,
48,8544,179,32,8232,8233,144,8204,57344,56320,173,40,41,95,3852,247,
3647,901,3896,171,187};
int[] charsInt = new int[]{586,65,97,498,721,4588,772,8413,3404,48,
8544,179,32,8232,8233,144,8204,57344,56320,173,40,41,95,3852,247,
3647,901,3896,171,187};
String toCheck = new String(characters);
for (int i=0;i<characters.length;i++) {
int get = oObj.getType(toCheck, i);
res &= (charstyles_office[get] == charstyles_office[i]);
if (!res) {
log.println("Code :" + Integer.toHexString(charsInt[i]));
log.println("Gained: " + charstyles_office[get]);
log.println("Expected : " + charstyles_office[i]);
}
}
tRes.tested("getType()", res);
}
/**
* After defining string to be checked and array of expected types, test
* calls the method for each character of a string and for all locales.<p>
* Has <b> OK </b> status if the method returns type, expected for a given
* character and locale.
*/
public void _getCharacterType() {
boolean res = true;
String toCheck = "Ab0)";
int[] expected = new int[]{226,228,97,32};
for (int i=0;i<toCheck.length();i++) {
for (int j=1;j<7;j++) {
int get = oObj.getCharacterType(toCheck, i, getLocale(j));
res &= (get == expected[i]);
if (!res) {
log.println("FAILED for: language=" + languages[j] +
" ; country=" + countries[j]);
log.println("Sysmbol :" + toCheck.toCharArray()[i]);
log.println("Gained: " + get);
log.println("Expected : " + expected[i]);
}
}
}
tRes.tested("getCharacterType()", res);
}
/**
* After defining array of strings to be checked and array of expected types,
* test calls the method for each string of an array and for all locales.<p>
* Has <b> OK </b> status if the method returns type, expected for a given
* string and locale.
*/
public void _getStringType() {
boolean res = true;
String[] toCheck = new String[]{"01234","AAAAA","bbbbb","AA()bb"};
int[] exp = new int[]{97,226,228,230};
for (int j=0;j<toCheck.length;j++) {
for (int i=0;i<7;i++) {
int get = oObj.getStringType(toCheck[j], 0,
toCheck[j].length(), getLocale(i));
res &= (get == exp[j]);
if (!res) {
log.println("FAILED for: language=" + languages[i] +
" ; country=" + countries[i]);
log.println("Expected: " + exp[j]);
log.println("Gained : " + get);
}
}
}
tRes.tested("getStringType()", res);
}
/**
* After string to be checked is initialized (all symbols are sorted
* by direction, so the character of <code>i<sup><small>th</small></sup></code>
* direction is located on <code>i<sup><small>th</small></sup></code>
* position), test calls the method for every character of that string. <p>
* Has <b> OK </b> status if the method returns direction, that's equal to
* a symbol position in the string.
*/
public void _getCharacterDirection() {
boolean res = true;
String toCheck = new String(new char[]{65,1470,48,47,35,1632,44,10,
9,12,33,8234,8237,1563,8235,8238,8236,768,1});
for (short i=0;i<19;i++) {
short get = oObj.getCharacterDirection(toCheck, i);
res &= (get == i);
if (!res) {
log.println("Code :" + toCheck.toCharArray()[i]);
log.println("Gained: " + get);
log.println("Expected: " + i);
}
}
tRes.tested("getCharacterDirection()", res);
}
/**
* At first we define <code>int[]</code> and <code>char[]</code> arrays of
* unicode symbol numbers, arranged as sequences, where symbols are sorted
* by type, so the character of <code>i<sup><small>th</small></sup></code>
* type is located on <code>i<sup><small>th</small></sup></code> position.<p>
* Has <b> OK </b> status if for each character method returns value, that
* is equal to a number where element is located in array. Also method has
* <b> OK </b> status for symbol with code 55296, because it doesn't work
* since it hasn't the right neighborhood.<p>
* @see http://ppewww.ph.gla.ac.uk/~flavell/unicode/unidata.html
*/
public void _getScript() {
boolean res = true;
char[] characters = new char[]{65,128,256,384,592,750,773,924,1030,1331,1448,
1569,1792,1936,2313,2465,2570,2707,2822,2972,3079,3240,3337,3464,3590,
3745,3906,4097,4274,4357,4621,5040,5200,5776,5806,6030,6155,7683,7943,
8202,8319,8352,8413,8452,8545,8616,8715,8965,9217,9281,9336,9474,9608,9719,
9734,9999,10247,11911,12034,12274,12294,12358,12456,12552,12605,12688,12727,
12806,13065,13312,19968,40964,42152,44032,55296,56192,56320,57344,63744,
64257,64370,65056,65073,65131,65146,65532,65288};
int[] charsInt = new int[]{65,128,256,384,592,750,773,924,1030,1331,1448,
1569,1792,1936,2313,2465,2570,2707,2822,2972,3079,3240,3337,3464,3590,
3745,3906,4097,4274,4357,4621,5040,5200,5776,5806,6030,6155,7683,7943,
8202,8319,8352,8413,8452,8545,8616,8715,8965,9217,9281,9336,9474,9608,9719,
9734,9999,10247,11911,12034,12274,12294,12358,12456,12552,12605,12688,12727,
12806,13065,13312,19968,40964,42152,44032,55296,56192,56320,57344,63744,
64257,64370,65056,65073,65131,65146,65532,65288};
String toCheck = new String(characters);
for (int i=0;i<characters.length;i++) {
int get = oObj.getScript(toCheck, i);
res &= (get == i);
//The HIGH_SURROGATE 55296 doesn't work since it hasn't the right
//neighborhood
if (toCheck.substring(i, i + 1).hashCode() == 55296) res = true;
if (!res) {
log.println("-- " + toCheck.substring(i, i + 1).hashCode());
log.println("Code: " + Integer.toHexString(charsInt[i]));
log.println("Gained: " + unicode_script[get]);
log.println("Expected: " + unicode_script[i]);
}
}
tRes.tested("getScript()", res);
}
/**
* After defining a string to be parsed and parse conditions (flags), test
* calls the method for different locales three times with different parameters,
* checking result after every call. <p>
* Has <b> OK </b> status if the method returns right results all three
* times.
*/
public void _parseAnyToken() {
int nStartFlags = KParseTokens.ANY_ALPHA | KParseTokens.ASC_UNDERSCORE;
int nContFlags = KParseTokens.ANY_ALNUM | KParseTokens.ASC_UNDERSCORE
| KParseTokens.ASC_DOT;
String toCheck = " 18 i18n ^";
ParseResult pRes = null;
boolean res = true;
for (int i=0;i<7;i++) {
pRes = oObj.parseAnyToken(toCheck, 1, getLocale(i),
nStartFlags, "", nContFlags, "");
res = ( (pRes.CharLen==2)
&& (pRes.TokenType==32)
&& (pRes.Value==18.0) );
pRes = oObj.parseAnyToken(toCheck, 4, getLocale(i),
nStartFlags, "", nContFlags, "");
res &= ( (pRes.CharLen==4)
&& (pRes.TokenType==4)
&& (pRes.Value==0.0) );
pRes = oObj.parseAnyToken(toCheck, 9, getLocale(i),
nStartFlags, "", nContFlags, "");
res &= ( (pRes.CharLen==1)
&& (pRes.TokenType==1)
&& (pRes.Value==0.0) );
}
tRes.tested("parseAnyToken()", res);
}
/**
* After defining a string to be parsed and parse conditions (flags), test
* calls the method for different locales two times with different parameters,
* checking result after every call. <p>
* Has <b> OK </b> status if the method returns right results.
*/
public void _parsePredefinedToken() {
int nStartFlags = KParseTokens.ANY_ALPHA | KParseTokens.ASC_UNDERSCORE;
int nContFlags = nStartFlags;
String toCheck = " 18 int";
ParseResult pRes = null;
boolean res = true;
for (int i=0;i<7;i++) {
pRes = oObj.parsePredefinedToken(KParseType.IDENTNAME, toCheck,
1, getLocale(i), nStartFlags, "", nContFlags, "");
res = (pRes.CharLen==0);
pRes = oObj.parsePredefinedToken(KParseType.IDENTNAME, toCheck,
4, getLocale(i), nStartFlags, "", nContFlags, "");
res &= ( (pRes.CharLen==3)
&& (pRes.TokenType==4)
&& (pRes.Value==0.0) );
}
tRes.tested("parsePredefinedToken()", res);
}
/**
* Method returns locale for a given language and country.
* @param localeIndex index of needed locale.
*/
private Locale getLocale(int k) {
return new Locale(languages[k],countries[k],"");
}
} // end XCharacterClassification
|