1.1 --- /dev/null Thu Jan 01 00:00:00 1970 +0000
1.2 +++ b/intl/lwbrk/tests/TestLineBreak.cpp Wed Dec 31 06:09:35 2014 +0100
1.3 @@ -0,0 +1,494 @@
1.4 +/* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
1.5 +/* This Source Code Form is subject to the terms of the Mozilla Public
1.6 + * License, v. 2.0. If a copy of the MPL was not distributed with this
1.7 + * file, You can obtain one at http://mozilla.org/MPL/2.0/. */
1.8 +#include <stdio.h>
1.9 +#include "nsXPCOM.h"
1.10 +#include "nsIComponentManager.h"
1.11 +#include "nsISupports.h"
1.12 +#include "nsServiceManagerUtils.h"
1.13 +#include "nsILineBreaker.h"
1.14 +#include "nsIWordBreaker.h"
1.15 +#include "nsLWBrkCIID.h"
1.16 +#include "nsStringAPI.h"
1.17 +#include "nsEmbedString.h"
1.18 +#include "TestHarness.h"
1.19 +
1.20 +#define WORK_AROUND_SERVICE_MANAGER_ASSERT
1.21 +
1.22 +NS_DEFINE_CID(kLBrkCID, NS_LBRK_CID);
1.23 +NS_DEFINE_CID(kWBrkCID, NS_WBRK_CID);
1.24 +
1.25 +
1.26 +static char teng1[] =
1.27 +// 1 2 3 4 5 6 7
1.28 +//01234567890123456789012345678901234567890123456789012345678901234567890123456789
1.29 + "This is a test to test(reasonable) line break. This 0.01123 = 45 x 48.";
1.30 +
1.31 +static uint32_t exp1[] = {
1.32 + 4,7,9,14,17,34,39,40,41,42,49,54,62,64,67,69,73
1.33 +};
1.34 +
1.35 +static uint32_t wexp1[] = {
1.36 +
1.37 + 4,5,7,8,9,10,14,15,17,18,22,23,33,34,35,39,43,48,49,50,54,55,56,57,62,63,
1.38 + 64,65,67,68,69,70,72
1.39 +};
1.40 +// 1 2 3 4 5 6 7
1.41 +//01234567890123456789012345678901234567890123456789012345678901234567890123456789
1.42 +static char teng2[] =
1.43 + "()((reasonab(l)e) line break. .01123=45x48.";
1.44 +
1.45 +static uint32_t lexp2[] = {
1.46 + 17,22,23,30,44
1.47 +};
1.48 +static uint32_t wexp2[] = {
1.49 + 4,12,13,14,15,16,17,18,22,24,29,30,31,32,37,38,43
1.50 +};
1.51 +
1.52 +// 1 2 3 4 5 6 7
1.53 +//01234567890123456789012345678901234567890123456789012345678901234567890123456789
1.54 +static char teng3[] =
1.55 + "It's a test to test(ronae ) line break....";
1.56 +static uint32_t exp3[] = {
1.57 + 4,6,11,14,25,27,32,42
1.58 +};
1.59 +static uint32_t wexp3[] = {
1.60 + 2,3,4,5,6,7,11,12,14,15,19,20,25,26,27,28,32,33,38
1.61 +};
1.62 +
1.63 +static char ruler1[] =
1.64 +" 1 2 3 4 5 6 7 ";
1.65 +static char ruler2[] =
1.66 +"0123456789012345678901234567890123456789012345678901234567890123456789012";
1.67 +
1.68 +
1.69 +bool TestASCIILB(nsILineBreaker *lb,
1.70 + const char* in, const uint32_t len,
1.71 + const uint32_t* out, uint32_t outlen)
1.72 +{
1.73 + NS_ConvertASCIItoUTF16 eng1(in);
1.74 + uint32_t i,j;
1.75 + uint32_t res[256];
1.76 + bool ok = true;
1.77 + int32_t curr;
1.78 + for(i = 0, curr = 0; (curr != NS_LINEBREAKER_NEED_MORE_TEXT) &&
1.79 + (i < 256); i++)
1.80 + {
1.81 + curr = lb->Next(eng1.get(), eng1.Length(), curr);
1.82 + res [i] = curr != NS_LINEBREAKER_NEED_MORE_TEXT ? curr : eng1.Length();
1.83 +
1.84 + }
1.85 + if (i != outlen)
1.86 + {
1.87 + ok = false;
1.88 + printf("WARNING!!! return size wrong, expect %d but got %d \n",
1.89 + outlen, i);
1.90 + }
1.91 + printf("string = \n%s\n", in);
1.92 + printf("%s\n", ruler1);
1.93 + printf("%s\n", ruler2);
1.94 + printf("Expect = \n");
1.95 + for(j=0;j<outlen;j++)
1.96 + {
1.97 + printf("%d,", out[j]);
1.98 + }
1.99 + printf("\nResult = \n");
1.100 + for(j=0;j<i;j++)
1.101 + {
1.102 + printf("%d,", res[j]);
1.103 + }
1.104 + printf("\n");
1.105 + for(j=0;j<i;j++)
1.106 + {
1.107 + if(j < outlen)
1.108 + {
1.109 + if (res[j] != out[j])
1.110 + {
1.111 + ok = false;
1.112 + printf("[%d] expect %d but got %d\n", j, out[j], res[j]);
1.113 + }
1.114 + } else {
1.115 + ok = false;
1.116 + printf("[%d] additional %d\n", j, res[j]);
1.117 + }
1.118 + }
1.119 + return ok;
1.120 +}
1.121 +
1.122 +bool TestASCIIWB(nsIWordBreaker *lb,
1.123 + const char* in, const uint32_t len,
1.124 + const uint32_t* out, uint32_t outlen)
1.125 +{
1.126 + NS_ConvertASCIItoUTF16 eng1(in);
1.127 +
1.128 + uint32_t i,j;
1.129 + uint32_t res[256];
1.130 + bool ok = true;
1.131 + int32_t curr = 0;
1.132 +
1.133 + for(i = 0, curr = lb->NextWord(eng1.get(), eng1.Length(), curr);
1.134 + (curr != NS_WORDBREAKER_NEED_MORE_TEXT) && (i < 256);
1.135 + curr = lb->NextWord(eng1.get(), eng1.Length(), curr), i++)
1.136 + {
1.137 + res [i] = curr != NS_WORDBREAKER_NEED_MORE_TEXT ? curr : eng1.Length();
1.138 + }
1.139 + if (i != outlen)
1.140 + {
1.141 + ok = false;
1.142 + printf("WARNING!!! return size wrong, expect %d but got %d\n",
1.143 + outlen, i);
1.144 + }
1.145 + printf("string = \n%s\n", in);
1.146 + printf("%s\n", ruler1);
1.147 + printf("%s\n", ruler2);
1.148 + printf("Expect = \n");
1.149 + for(j=0;j<outlen;j++)
1.150 + {
1.151 + printf("%d,", out[j]);
1.152 + }
1.153 + printf("\nResult = \n");
1.154 + for(j=0;j<i;j++)
1.155 + {
1.156 + printf("%d,", res[j]);
1.157 + }
1.158 + printf("\n");
1.159 + for(j=0;j<i;j++)
1.160 + {
1.161 + if(j < outlen)
1.162 + {
1.163 + if (res[j] != out[j])
1.164 + {
1.165 + ok = false;
1.166 + printf("[%d] expect %d but got %d\n", j, out[j], res[j]);
1.167 + }
1.168 + } else {
1.169 + ok = false;
1.170 + printf("[%d] additional %d\n", j, res[j]);
1.171 + }
1.172 + }
1.173 + return ok;
1.174 +}
1.175 +
1.176 +
1.177 +bool TestLineBreaker()
1.178 +{
1.179 + printf("===========================\n");
1.180 + printf("Finish nsILineBreaker Test \n");
1.181 + printf("===========================\n");
1.182 + nsILineBreaker *t = nullptr;
1.183 + nsresult res;
1.184 + bool ok = true;
1.185 + res = CallGetService(kLBrkCID, &t);
1.186 +
1.187 + printf("Test 1 - GetService():\n");
1.188 + if (NS_FAILED(res) || !t) {
1.189 + printf("\t1st GetService failed\n");
1.190 + ok = false;
1.191 + }
1.192 +
1.193 + NS_IF_RELEASE(t);
1.194 +
1.195 + res = CallGetService(kLBrkCID, &t);
1.196 +
1.197 + if (NS_FAILED(res) || !t) {
1.198 + printf("\t2nd GetService failed\n");
1.199 + ok = false;
1.200 + } else {
1.201 + printf("Test 4 - {First,Next}ForwardBreak():\n");
1.202 + if( TestASCIILB(t, teng1, sizeof(teng1)/sizeof(char),
1.203 + exp1, sizeof(exp1)/sizeof(uint32_t)) )
1.204 + {
1.205 + printf("Test 4 Passed\n\n");
1.206 + } else {
1.207 + ok = false;
1.208 + printf("Test 4 Failed\n\n");
1.209 + }
1.210 +
1.211 + printf("Test 5 - {First,Next}ForwardBreak():\n");
1.212 + if(TestASCIILB(t, teng2, sizeof(teng2)/sizeof(char),
1.213 + lexp2, sizeof(lexp2)/sizeof(uint32_t)) )
1.214 + {
1.215 + printf("Test 5 Passed\n\n");
1.216 + } else {
1.217 + ok = false;
1.218 + printf("Test 5 Failed\n\n");
1.219 + }
1.220 +
1.221 + printf("Test 6 - {First,Next}ForwardBreak():\n");
1.222 + if(TestASCIILB(t, teng3, sizeof(teng3)/sizeof(char),
1.223 + exp3, sizeof(exp3)/sizeof(uint32_t)) )
1.224 + {
1.225 + printf("Test 6 Passed\n\n");
1.226 + } else {
1.227 + ok = false;
1.228 + printf("Test 6 Failed\n\n");
1.229 + }
1.230 +
1.231 +
1.232 + NS_RELEASE(t);
1.233 +
1.234 + }
1.235 +
1.236 + printf("===========================\n");
1.237 + printf("Finish nsILineBreaker Test \n");
1.238 + printf("===========================\n");
1.239 +
1.240 + return ok;
1.241 +}
1.242 +
1.243 +bool TestWordBreaker()
1.244 +{
1.245 + printf("===========================\n");
1.246 + printf("Finish nsIWordBreaker Test \n");
1.247 + printf("===========================\n");
1.248 + nsIWordBreaker *t = nullptr;
1.249 + nsresult res;
1.250 + bool ok = true;
1.251 + res = CallGetService(kWBrkCID, &t);
1.252 +
1.253 + printf("Test 1 - GetService():\n");
1.254 + if (NS_FAILED(res) || !t) {
1.255 + printf("\t1st GetService failed\n");
1.256 + ok = false;
1.257 + } else {
1.258 + NS_RELEASE(t);
1.259 + }
1.260 +
1.261 + res = CallGetService(kWBrkCID, &t);
1.262 +
1.263 + if (NS_FAILED(res) || !t) {
1.264 + printf("\t2nd GetService failed\n");
1.265 + ok = false;
1.266 + } else {
1.267 +
1.268 + printf("Test 4 - {First,Next}ForwardBreak():\n");
1.269 + if( TestASCIIWB(t, teng1, sizeof(teng1)/sizeof(char),
1.270 + wexp1, sizeof(wexp1)/sizeof(uint32_t)) )
1.271 + {
1.272 + printf("Test 4 Passed\n\n");
1.273 + } else {
1.274 + ok = false;
1.275 + printf("Test 4 Failed\n\n");
1.276 + }
1.277 +
1.278 + printf("Test 5 - {First,Next}ForwardBreak():\n");
1.279 + if(TestASCIIWB(t, teng2, sizeof(teng2)/sizeof(char),
1.280 + wexp2, sizeof(wexp2)/sizeof(uint32_t)) )
1.281 + {
1.282 + printf("Test 5 Passed\n\n");
1.283 + } else {
1.284 + ok = false;
1.285 + printf("Test 5 Failed\n\n");
1.286 + }
1.287 +
1.288 + printf("Test 6 - {First,Next}ForwardBreak():\n");
1.289 + if(TestASCIIWB(t, teng3, sizeof(teng3)/sizeof(char),
1.290 + wexp3, sizeof(wexp3)/sizeof(uint32_t)) )
1.291 + {
1.292 + printf("Test 6 Passed\n\n");
1.293 + } else {
1.294 + ok = false;
1.295 + printf("Test 6 Failed\n\n");
1.296 + }
1.297 +
1.298 +
1.299 + NS_RELEASE(t);
1.300 + }
1.301 +
1.302 + printf("===========================\n");
1.303 + printf("Finish nsIWordBreaker Test \n");
1.304 + printf("===========================\n");
1.305 +
1.306 + return ok;
1.307 +}
1.308 +
1.309 +void SamplePrintWordWithBreak();
1.310 +void SampleFindWordBreakFromPosition(uint32_t fragN, uint32_t offset);
1.311 +// Sample Code
1.312 +
1.313 +// 012345678901234
1.314 +static const char wb0[] = "T";
1.315 +static const char wb1[] = "h";
1.316 +static const char wb2[] = "is is a int";
1.317 +static const char wb3[] = "ernationali";
1.318 +static const char wb4[] = "zation work.";
1.319 +
1.320 +static const char* wb[] = {wb0,wb1,wb2,wb3,wb4};
1.321 +void SampleWordBreakUsage()
1.322 +{
1.323 + SamplePrintWordWithBreak();
1.324 + SampleFindWordBreakFromPosition(0,0); // This
1.325 + SampleFindWordBreakFromPosition(1,0); // This
1.326 + SampleFindWordBreakFromPosition(2,0); // This
1.327 + SampleFindWordBreakFromPosition(2,1); // This
1.328 + SampleFindWordBreakFromPosition(2,9); // [space]
1.329 + SampleFindWordBreakFromPosition(2,10); // internationalization
1.330 + SampleFindWordBreakFromPosition(3,4); // internationalization
1.331 + SampleFindWordBreakFromPosition(3,8); // internationalization
1.332 + SampleFindWordBreakFromPosition(4,6); // [space]
1.333 + SampleFindWordBreakFromPosition(4,7); // work
1.334 +}
1.335 +
1.336 +
1.337 +void SamplePrintWordWithBreak()
1.338 +{
1.339 + uint32_t numOfFragment = sizeof(wb) / sizeof(char*);
1.340 + nsIWordBreaker *wbk = nullptr;
1.341 +
1.342 + CallGetService(kWBrkCID, &wbk);
1.343 +
1.344 + nsAutoString result;
1.345 +
1.346 + for(uint32_t i = 0; i < numOfFragment; i++)
1.347 + {
1.348 + NS_ConvertASCIItoUTF16 fragText(wb[i]);
1.349 +
1.350 + int32_t cur = 0;
1.351 + cur = wbk->NextWord(fragText.get(), fragText.Length(), cur);
1.352 + uint32_t start = 0;
1.353 + for(uint32_t j = 0; cur != NS_WORDBREAKER_NEED_MORE_TEXT ; j++)
1.354 + {
1.355 + result.Append(Substring(fragText, start, cur - start));
1.356 + result.Append('^');
1.357 + start = (cur >= 0 ? cur : cur - start);
1.358 + cur = wbk->NextWord(fragText.get(), fragText.Length(), cur);
1.359 + }
1.360 +
1.361 + result.Append(Substring(fragText, fragText.Length() - start));
1.362 +
1.363 + if( i != (numOfFragment -1 ))
1.364 + {
1.365 + NS_ConvertASCIItoUTF16 nextFragText(wb[i+1]);
1.366 +
1.367 + bool canBreak = true;
1.368 + canBreak = wbk->BreakInBetween( fragText.get(),
1.369 + fragText.Length(),
1.370 + nextFragText.get(),
1.371 + nextFragText.Length());
1.372 + if(canBreak)
1.373 + result.Append('^');
1.374 +
1.375 + fragText.Assign(nextFragText);
1.376 + }
1.377 + }
1.378 + printf("Output From SamplePrintWordWithBreak() \n\n");
1.379 + printf("[%s]\n", NS_ConvertUTF16toUTF8(result).get());
1.380 +
1.381 + NS_IF_RELEASE(wbk);
1.382 +}
1.383 +
1.384 +void SampleFindWordBreakFromPosition(uint32_t fragN, uint32_t offset)
1.385 +{
1.386 + uint32_t numOfFragment = sizeof(wb) / sizeof(char*);
1.387 + nsIWordBreaker *wbk = nullptr;
1.388 +
1.389 + CallGetService(kWBrkCID, &wbk);
1.390 +
1.391 + NS_ConvertASCIItoUTF16 fragText(wb[fragN]);
1.392 +
1.393 + nsWordRange res = wbk->FindWord(fragText.get(), fragText.Length(), offset);
1.394 +
1.395 + bool canBreak;
1.396 + nsAutoString result(Substring(fragText, res.mBegin, res.mEnd-res.mBegin));
1.397 +
1.398 + if((uint32_t)fragText.Length() == res.mEnd) // if we hit the end of the fragment
1.399 + {
1.400 + nsAutoString curFragText = fragText;
1.401 + for(uint32_t p = fragN +1; p < numOfFragment ;p++)
1.402 + {
1.403 + NS_ConvertASCIItoUTF16 nextFragText(wb[p]);
1.404 + canBreak = wbk->BreakInBetween(curFragText.get(),
1.405 + curFragText.Length(),
1.406 + nextFragText.get(),
1.407 + nextFragText.Length());
1.408 + if(canBreak)
1.409 + break;
1.410 +
1.411 + nsWordRange r = wbk->FindWord(nextFragText.get(), nextFragText.Length(),
1.412 + 0);
1.413 +
1.414 + result.Append(Substring(nextFragText, r.mBegin, r.mEnd - r.mBegin));
1.415 +
1.416 + if((uint32_t)nextFragText.Length() != r.mEnd)
1.417 + break;
1.418 +
1.419 + nextFragText.Assign(curFragText);
1.420 + }
1.421 + }
1.422 +
1.423 + if(0 == res.mBegin) // if we hit the beginning of the fragment
1.424 + {
1.425 + nsAutoString curFragText = fragText;
1.426 + for(uint32_t p = fragN ; p > 0 ;p--)
1.427 + {
1.428 + NS_ConvertASCIItoUTF16 prevFragText(wb[p-1]);
1.429 + canBreak = wbk->BreakInBetween(prevFragText.get(),
1.430 + prevFragText.Length(),
1.431 + curFragText.get(),
1.432 + curFragText.Length());
1.433 + if(canBreak)
1.434 + break;
1.435 +
1.436 + nsWordRange r = wbk->FindWord(prevFragText.get(), prevFragText.Length(),
1.437 + prevFragText.Length());
1.438 +
1.439 + result.Insert(Substring(prevFragText, r.mBegin, r.mEnd - r.mBegin), 0);
1.440 +
1.441 + if(0 != r.mBegin)
1.442 + break;
1.443 +
1.444 + prevFragText.Assign(curFragText);
1.445 + }
1.446 + }
1.447 +
1.448 + printf("Output From SamplePrintWordWithBreak() \n\n");
1.449 + printf("[%s]\n", NS_ConvertUTF16toUTF8(result).get());
1.450 +
1.451 + NS_IF_RELEASE(wbk);
1.452 +}
1.453 +
1.454 +// Main
1.455 +
1.456 +int main(int argc, char** argv) {
1.457 +
1.458 + int rv = 0;
1.459 + ScopedXPCOM xpcom("TestLineBreak");
1.460 + if (xpcom.failed())
1.461 + return -1;
1.462 +
1.463 + // --------------------------------------------
1.464 + printf("Test Line Break\n");
1.465 +
1.466 + bool lbok ;
1.467 + bool wbok ;
1.468 + lbok =TestWordBreaker();
1.469 + if(lbok)
1.470 + passed("Line Break Test");
1.471 + else {
1.472 + fail("Line Break Test");
1.473 + rv = -1;
1.474 + }
1.475 +
1.476 + wbok = TestLineBreaker();
1.477 + if(wbok)
1.478 + passed("Word Break Test");
1.479 + else {
1.480 + fail("Word Break Test");
1.481 + rv = -1;
1.482 + }
1.483 +
1.484 + SampleWordBreakUsage();
1.485 +
1.486 +
1.487 + // --------------------------------------------
1.488 + printf("Finish All The Test Cases\n");
1.489 +
1.490 + if(lbok && wbok)
1.491 + passed("Line/Word Break Test");
1.492 + else {
1.493 + fail("Line/Word Break Test");
1.494 + rv = -1;
1.495 + }
1.496 + return rv;
1.497 +}
